{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.6784354447905849, "eval_steps": 500, "global_step": 4410, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00015384023691396485, "grad_norm": 27.228328704833984, "learning_rate": 0.0, "loss": 3.6344, "step": 1 }, { "epoch": 0.0003076804738279297, "grad_norm": 15.770339965820312, "learning_rate": 4.000000000000001e-06, "loss": 3.1337, "step": 2 }, { "epoch": 0.0004615207107418945, "grad_norm": 14.093010902404785, "learning_rate": 8.000000000000001e-06, "loss": 3.0746, "step": 3 }, { "epoch": 0.0006153609476558594, "grad_norm": 13.087334632873535, "learning_rate": 1.2e-05, "loss": 3.0812, "step": 4 }, { "epoch": 0.0007692011845698242, "grad_norm": 11.334531784057617, "learning_rate": 1.6000000000000003e-05, "loss": 3.0017, "step": 5 }, { "epoch": 0.000923041421483789, "grad_norm": 10.079632759094238, "learning_rate": 2e-05, "loss": 2.6219, "step": 6 }, { "epoch": 0.0010768816583977539, "grad_norm": 9.388604164123535, "learning_rate": 1.9996921182266012e-05, "loss": 2.3951, "step": 7 }, { "epoch": 0.0012307218953117188, "grad_norm": 7.191956043243408, "learning_rate": 1.999384236453202e-05, "loss": 2.4252, "step": 8 }, { "epoch": 0.0013845621322256837, "grad_norm": 9.068796157836914, "learning_rate": 1.999076354679803e-05, "loss": 2.3429, "step": 9 }, { "epoch": 0.0015384023691396484, "grad_norm": 6.196566104888916, "learning_rate": 1.998768472906404e-05, "loss": 2.008, "step": 10 }, { "epoch": 0.0016922426060536134, "grad_norm": 6.486144542694092, "learning_rate": 1.998460591133005e-05, "loss": 2.165, "step": 11 }, { "epoch": 0.001846082842967578, "grad_norm": 5.526679992675781, "learning_rate": 1.998152709359606e-05, "loss": 2.3516, "step": 12 }, { "epoch": 0.001999923079881543, "grad_norm": 5.122188091278076, "learning_rate": 1.997844827586207e-05, "loss": 2.0066, "step": 13 }, { "epoch": 0.0021537633167955077, "grad_norm": 5.245275020599365, "learning_rate": 1.997536945812808e-05, "loss": 2.1113, "step": 14 }, { "epoch": 0.002307603553709473, "grad_norm": 10.889349937438965, "learning_rate": 1.997229064039409e-05, "loss": 2.3993, "step": 15 }, { "epoch": 0.0024614437906234376, "grad_norm": 6.539618492126465, "learning_rate": 1.9969211822660098e-05, "loss": 1.9175, "step": 16 }, { "epoch": 0.0026152840275374023, "grad_norm": 5.288671016693115, "learning_rate": 1.996613300492611e-05, "loss": 1.8673, "step": 17 }, { "epoch": 0.0027691242644513675, "grad_norm": 5.818685054779053, "learning_rate": 1.996305418719212e-05, "loss": 1.9924, "step": 18 }, { "epoch": 0.002922964501365332, "grad_norm": 4.989151954650879, "learning_rate": 1.995997536945813e-05, "loss": 1.8293, "step": 19 }, { "epoch": 0.003076804738279297, "grad_norm": 4.915114879608154, "learning_rate": 1.9956896551724137e-05, "loss": 1.9103, "step": 20 }, { "epoch": 0.0032306449751932616, "grad_norm": 5.284971714019775, "learning_rate": 1.9953817733990148e-05, "loss": 1.5668, "step": 21 }, { "epoch": 0.0033844852121072268, "grad_norm": 4.4927239418029785, "learning_rate": 1.995073891625616e-05, "loss": 1.7777, "step": 22 }, { "epoch": 0.0035383254490211915, "grad_norm": 4.086378574371338, "learning_rate": 1.994766009852217e-05, "loss": 1.8921, "step": 23 }, { "epoch": 0.003692165685935156, "grad_norm": 4.801977634429932, "learning_rate": 1.994458128078818e-05, "loss": 1.7384, "step": 24 }, { "epoch": 0.0038460059228491213, "grad_norm": 4.164169788360596, "learning_rate": 1.994150246305419e-05, "loss": 1.9897, "step": 25 }, { "epoch": 0.003999846159763086, "grad_norm": 4.522672176361084, "learning_rate": 1.99384236453202e-05, "loss": 1.9407, "step": 26 }, { "epoch": 0.004153686396677051, "grad_norm": 5.2660932540893555, "learning_rate": 1.9935344827586208e-05, "loss": 1.9323, "step": 27 }, { "epoch": 0.0043075266335910155, "grad_norm": 5.354686737060547, "learning_rate": 1.993226600985222e-05, "loss": 1.7618, "step": 28 }, { "epoch": 0.00446136687050498, "grad_norm": 4.945455551147461, "learning_rate": 1.992918719211823e-05, "loss": 1.7407, "step": 29 }, { "epoch": 0.004615207107418946, "grad_norm": 4.048459529876709, "learning_rate": 1.992610837438424e-05, "loss": 1.9187, "step": 30 }, { "epoch": 0.0047690473443329105, "grad_norm": 4.348483562469482, "learning_rate": 1.9923029556650247e-05, "loss": 1.7839, "step": 31 }, { "epoch": 0.004922887581246875, "grad_norm": 5.392942905426025, "learning_rate": 1.9919950738916258e-05, "loss": 1.843, "step": 32 }, { "epoch": 0.00507672781816084, "grad_norm": 4.759573459625244, "learning_rate": 1.991687192118227e-05, "loss": 1.6085, "step": 33 }, { "epoch": 0.005230568055074805, "grad_norm": 4.122617244720459, "learning_rate": 1.991379310344828e-05, "loss": 1.8646, "step": 34 }, { "epoch": 0.005384408291988769, "grad_norm": 4.32858419418335, "learning_rate": 1.9910714285714287e-05, "loss": 1.8349, "step": 35 }, { "epoch": 0.005538248528902735, "grad_norm": 4.9940505027771, "learning_rate": 1.9907635467980297e-05, "loss": 1.7817, "step": 36 }, { "epoch": 0.0056920887658167, "grad_norm": 4.662458896636963, "learning_rate": 1.9904556650246308e-05, "loss": 1.5019, "step": 37 }, { "epoch": 0.005845929002730664, "grad_norm": 4.286136150360107, "learning_rate": 1.990147783251232e-05, "loss": 1.6976, "step": 38 }, { "epoch": 0.005999769239644629, "grad_norm": 4.3825507164001465, "learning_rate": 1.9898399014778326e-05, "loss": 1.7523, "step": 39 }, { "epoch": 0.006153609476558594, "grad_norm": 4.448425769805908, "learning_rate": 1.9895320197044336e-05, "loss": 1.7987, "step": 40 }, { "epoch": 0.0063074497134725585, "grad_norm": 4.808777809143066, "learning_rate": 1.9892241379310347e-05, "loss": 1.7518, "step": 41 }, { "epoch": 0.006461289950386523, "grad_norm": 4.438681602478027, "learning_rate": 1.9889162561576358e-05, "loss": 1.7229, "step": 42 }, { "epoch": 0.006615130187300489, "grad_norm": 4.486683368682861, "learning_rate": 1.9886083743842365e-05, "loss": 1.8346, "step": 43 }, { "epoch": 0.0067689704242144535, "grad_norm": 4.425765514373779, "learning_rate": 1.9883004926108376e-05, "loss": 1.9053, "step": 44 }, { "epoch": 0.006922810661128418, "grad_norm": 4.397668838500977, "learning_rate": 1.9879926108374386e-05, "loss": 1.9889, "step": 45 }, { "epoch": 0.007076650898042383, "grad_norm": 4.389277458190918, "learning_rate": 1.9876847290640397e-05, "loss": 1.7143, "step": 46 }, { "epoch": 0.007230491134956348, "grad_norm": 4.604084491729736, "learning_rate": 1.9873768472906404e-05, "loss": 1.6365, "step": 47 }, { "epoch": 0.007384331371870312, "grad_norm": 5.26084041595459, "learning_rate": 1.9870689655172415e-05, "loss": 2.073, "step": 48 }, { "epoch": 0.007538171608784278, "grad_norm": 4.048437118530273, "learning_rate": 1.9867610837438426e-05, "loss": 1.7411, "step": 49 }, { "epoch": 0.007692011845698243, "grad_norm": 4.388775825500488, "learning_rate": 1.9864532019704436e-05, "loss": 1.8606, "step": 50 }, { "epoch": 0.007845852082612207, "grad_norm": 5.024675369262695, "learning_rate": 1.9861453201970443e-05, "loss": 1.8139, "step": 51 }, { "epoch": 0.007999692319526172, "grad_norm": 4.119935989379883, "learning_rate": 1.9858374384236454e-05, "loss": 1.7192, "step": 52 }, { "epoch": 0.008153532556440137, "grad_norm": 4.859318256378174, "learning_rate": 1.9855295566502465e-05, "loss": 1.6424, "step": 53 }, { "epoch": 0.008307372793354102, "grad_norm": 4.780176162719727, "learning_rate": 1.9852216748768472e-05, "loss": 1.6564, "step": 54 }, { "epoch": 0.008461213030268066, "grad_norm": 4.386979579925537, "learning_rate": 1.9849137931034483e-05, "loss": 1.7013, "step": 55 }, { "epoch": 0.008615053267182031, "grad_norm": 4.195468425750732, "learning_rate": 1.9846059113300493e-05, "loss": 1.6497, "step": 56 }, { "epoch": 0.008768893504095996, "grad_norm": 4.601858615875244, "learning_rate": 1.9842980295566504e-05, "loss": 1.6528, "step": 57 }, { "epoch": 0.00892273374100996, "grad_norm": 4.456797122955322, "learning_rate": 1.9839901477832515e-05, "loss": 1.6624, "step": 58 }, { "epoch": 0.009076573977923927, "grad_norm": 4.753119468688965, "learning_rate": 1.9836822660098525e-05, "loss": 1.5616, "step": 59 }, { "epoch": 0.009230414214837892, "grad_norm": 4.300702095031738, "learning_rate": 1.9833743842364536e-05, "loss": 1.6934, "step": 60 }, { "epoch": 0.009384254451751856, "grad_norm": 4.593196392059326, "learning_rate": 1.9830665024630543e-05, "loss": 1.9076, "step": 61 }, { "epoch": 0.009538094688665821, "grad_norm": 4.574037551879883, "learning_rate": 1.9827586206896554e-05, "loss": 1.403, "step": 62 }, { "epoch": 0.009691934925579786, "grad_norm": 3.332855224609375, "learning_rate": 1.9824507389162564e-05, "loss": 1.5569, "step": 63 }, { "epoch": 0.00984577516249375, "grad_norm": 3.5556325912475586, "learning_rate": 1.9821428571428575e-05, "loss": 1.5171, "step": 64 }, { "epoch": 0.009999615399407715, "grad_norm": 3.7531235218048096, "learning_rate": 1.9818349753694582e-05, "loss": 1.9245, "step": 65 }, { "epoch": 0.01015345563632168, "grad_norm": 5.39735746383667, "learning_rate": 1.9815270935960593e-05, "loss": 1.6778, "step": 66 }, { "epoch": 0.010307295873235645, "grad_norm": 3.45717191696167, "learning_rate": 1.9812192118226604e-05, "loss": 1.5925, "step": 67 }, { "epoch": 0.01046113611014961, "grad_norm": 4.662351131439209, "learning_rate": 1.9809113300492614e-05, "loss": 1.6686, "step": 68 }, { "epoch": 0.010614976347063574, "grad_norm": 4.754248142242432, "learning_rate": 1.980603448275862e-05, "loss": 1.7816, "step": 69 }, { "epoch": 0.010768816583977539, "grad_norm": 4.356899738311768, "learning_rate": 1.9802955665024632e-05, "loss": 1.514, "step": 70 }, { "epoch": 0.010922656820891503, "grad_norm": 4.409180164337158, "learning_rate": 1.9799876847290643e-05, "loss": 1.6072, "step": 71 }, { "epoch": 0.01107649705780547, "grad_norm": 3.747793674468994, "learning_rate": 1.9796798029556653e-05, "loss": 1.7023, "step": 72 }, { "epoch": 0.011230337294719435, "grad_norm": 4.649120807647705, "learning_rate": 1.979371921182266e-05, "loss": 1.4765, "step": 73 }, { "epoch": 0.0113841775316334, "grad_norm": 4.276346206665039, "learning_rate": 1.979064039408867e-05, "loss": 1.4439, "step": 74 }, { "epoch": 0.011538017768547364, "grad_norm": 5.319912910461426, "learning_rate": 1.9787561576354682e-05, "loss": 1.6105, "step": 75 }, { "epoch": 0.011691858005461329, "grad_norm": 4.890751361846924, "learning_rate": 1.9784482758620693e-05, "loss": 1.7348, "step": 76 }, { "epoch": 0.011845698242375293, "grad_norm": 4.562079429626465, "learning_rate": 1.97814039408867e-05, "loss": 1.3518, "step": 77 }, { "epoch": 0.011999538479289258, "grad_norm": 4.331586837768555, "learning_rate": 1.977832512315271e-05, "loss": 1.7523, "step": 78 }, { "epoch": 0.012153378716203223, "grad_norm": 4.0774993896484375, "learning_rate": 1.977524630541872e-05, "loss": 1.706, "step": 79 }, { "epoch": 0.012307218953117188, "grad_norm": 4.6590471267700195, "learning_rate": 1.9772167487684732e-05, "loss": 1.6183, "step": 80 }, { "epoch": 0.012461059190031152, "grad_norm": 4.8601603507995605, "learning_rate": 1.976908866995074e-05, "loss": 1.7943, "step": 81 }, { "epoch": 0.012614899426945117, "grad_norm": 4.317503452301025, "learning_rate": 1.976600985221675e-05, "loss": 1.5332, "step": 82 }, { "epoch": 0.012768739663859082, "grad_norm": 4.008917808532715, "learning_rate": 1.976293103448276e-05, "loss": 1.7062, "step": 83 }, { "epoch": 0.012922579900773046, "grad_norm": 4.200716972351074, "learning_rate": 1.975985221674877e-05, "loss": 1.7968, "step": 84 }, { "epoch": 0.013076420137687013, "grad_norm": 3.901301622390747, "learning_rate": 1.9756773399014778e-05, "loss": 1.8, "step": 85 }, { "epoch": 0.013230260374600978, "grad_norm": 4.303157806396484, "learning_rate": 1.975369458128079e-05, "loss": 1.5252, "step": 86 }, { "epoch": 0.013384100611514942, "grad_norm": 4.4023895263671875, "learning_rate": 1.97506157635468e-05, "loss": 1.7763, "step": 87 }, { "epoch": 0.013537940848428907, "grad_norm": 3.8324241638183594, "learning_rate": 1.974753694581281e-05, "loss": 1.7443, "step": 88 }, { "epoch": 0.013691781085342872, "grad_norm": 4.815861225128174, "learning_rate": 1.9744458128078817e-05, "loss": 1.491, "step": 89 }, { "epoch": 0.013845621322256836, "grad_norm": 5.011135578155518, "learning_rate": 1.9741379310344828e-05, "loss": 1.5325, "step": 90 }, { "epoch": 0.013999461559170801, "grad_norm": 5.678106307983398, "learning_rate": 1.973830049261084e-05, "loss": 1.5675, "step": 91 }, { "epoch": 0.014153301796084766, "grad_norm": 4.88396692276001, "learning_rate": 1.973522167487685e-05, "loss": 1.6777, "step": 92 }, { "epoch": 0.01430714203299873, "grad_norm": 3.8692288398742676, "learning_rate": 1.973214285714286e-05, "loss": 1.8609, "step": 93 }, { "epoch": 0.014460982269912695, "grad_norm": 3.8001465797424316, "learning_rate": 1.972906403940887e-05, "loss": 1.8956, "step": 94 }, { "epoch": 0.01461482250682666, "grad_norm": 3.650113582611084, "learning_rate": 1.9725985221674878e-05, "loss": 1.6767, "step": 95 }, { "epoch": 0.014768662743740625, "grad_norm": 4.278175354003906, "learning_rate": 1.972290640394089e-05, "loss": 1.6956, "step": 96 }, { "epoch": 0.01492250298065459, "grad_norm": 4.2311272621154785, "learning_rate": 1.97198275862069e-05, "loss": 1.7377, "step": 97 }, { "epoch": 0.015076343217568556, "grad_norm": 4.425539493560791, "learning_rate": 1.971674876847291e-05, "loss": 1.6934, "step": 98 }, { "epoch": 0.01523018345448252, "grad_norm": 4.040899276733398, "learning_rate": 1.9713669950738917e-05, "loss": 1.6987, "step": 99 }, { "epoch": 0.015384023691396485, "grad_norm": 4.320919990539551, "learning_rate": 1.9710591133004928e-05, "loss": 1.4944, "step": 100 }, { "epoch": 0.01553786392831045, "grad_norm": 3.7272744178771973, "learning_rate": 1.970751231527094e-05, "loss": 1.6246, "step": 101 }, { "epoch": 0.015691704165224415, "grad_norm": 4.171842575073242, "learning_rate": 1.970443349753695e-05, "loss": 1.6047, "step": 102 }, { "epoch": 0.015845544402138378, "grad_norm": 3.9457051753997803, "learning_rate": 1.9701354679802956e-05, "loss": 1.7626, "step": 103 }, { "epoch": 0.015999384639052344, "grad_norm": 4.283596515655518, "learning_rate": 1.9698275862068967e-05, "loss": 1.8219, "step": 104 }, { "epoch": 0.01615322487596631, "grad_norm": 5.797484874725342, "learning_rate": 1.9695197044334978e-05, "loss": 1.6667, "step": 105 }, { "epoch": 0.016307065112880274, "grad_norm": 4.083309650421143, "learning_rate": 1.9692118226600988e-05, "loss": 1.6708, "step": 106 }, { "epoch": 0.01646090534979424, "grad_norm": 4.131434440612793, "learning_rate": 1.9689039408866995e-05, "loss": 1.6346, "step": 107 }, { "epoch": 0.016614745586708203, "grad_norm": 4.438586235046387, "learning_rate": 1.9685960591133006e-05, "loss": 1.7426, "step": 108 }, { "epoch": 0.01676858582362217, "grad_norm": 5.242117404937744, "learning_rate": 1.9682881773399017e-05, "loss": 1.5136, "step": 109 }, { "epoch": 0.016922426060536132, "grad_norm": 4.288669586181641, "learning_rate": 1.9679802955665027e-05, "loss": 1.6144, "step": 110 }, { "epoch": 0.0170762662974501, "grad_norm": 5.1755499839782715, "learning_rate": 1.9676724137931035e-05, "loss": 1.7726, "step": 111 }, { "epoch": 0.017230106534364062, "grad_norm": 5.058839797973633, "learning_rate": 1.9673645320197045e-05, "loss": 1.3387, "step": 112 }, { "epoch": 0.01738394677127803, "grad_norm": 3.810755729675293, "learning_rate": 1.9670566502463056e-05, "loss": 1.7223, "step": 113 }, { "epoch": 0.01753778700819199, "grad_norm": 3.214873790740967, "learning_rate": 1.9667487684729067e-05, "loss": 1.4551, "step": 114 }, { "epoch": 0.017691627245105958, "grad_norm": 3.9409077167510986, "learning_rate": 1.9664408866995074e-05, "loss": 1.6482, "step": 115 }, { "epoch": 0.01784546748201992, "grad_norm": 4.296072959899902, "learning_rate": 1.9661330049261085e-05, "loss": 1.4571, "step": 116 }, { "epoch": 0.017999307718933887, "grad_norm": 3.8605239391326904, "learning_rate": 1.9658251231527095e-05, "loss": 1.4188, "step": 117 }, { "epoch": 0.018153147955847854, "grad_norm": 4.760791778564453, "learning_rate": 1.9655172413793106e-05, "loss": 1.7745, "step": 118 }, { "epoch": 0.018306988192761817, "grad_norm": 3.3741776943206787, "learning_rate": 1.9652093596059113e-05, "loss": 1.6515, "step": 119 }, { "epoch": 0.018460828429675783, "grad_norm": 4.367099761962891, "learning_rate": 1.9649014778325124e-05, "loss": 1.7166, "step": 120 }, { "epoch": 0.018614668666589746, "grad_norm": 4.1655659675598145, "learning_rate": 1.9645935960591134e-05, "loss": 1.6352, "step": 121 }, { "epoch": 0.018768508903503713, "grad_norm": 4.029080867767334, "learning_rate": 1.9642857142857145e-05, "loss": 1.7897, "step": 122 }, { "epoch": 0.018922349140417676, "grad_norm": 4.024429798126221, "learning_rate": 1.9639778325123152e-05, "loss": 1.6393, "step": 123 }, { "epoch": 0.019076189377331642, "grad_norm": 4.504501819610596, "learning_rate": 1.9636699507389163e-05, "loss": 1.3215, "step": 124 }, { "epoch": 0.019230029614245605, "grad_norm": 4.682461738586426, "learning_rate": 1.9633620689655174e-05, "loss": 1.7657, "step": 125 }, { "epoch": 0.01938386985115957, "grad_norm": 5.247325420379639, "learning_rate": 1.9630541871921184e-05, "loss": 1.6794, "step": 126 }, { "epoch": 0.019537710088073534, "grad_norm": 4.408361434936523, "learning_rate": 1.9627463054187195e-05, "loss": 1.5027, "step": 127 }, { "epoch": 0.0196915503249875, "grad_norm": 4.612606525421143, "learning_rate": 1.9624384236453205e-05, "loss": 1.6976, "step": 128 }, { "epoch": 0.019845390561901464, "grad_norm": 4.947434902191162, "learning_rate": 1.9621305418719213e-05, "loss": 1.5183, "step": 129 }, { "epoch": 0.01999923079881543, "grad_norm": 4.198423385620117, "learning_rate": 1.9618226600985223e-05, "loss": 1.5844, "step": 130 }, { "epoch": 0.020153071035729397, "grad_norm": 3.920921802520752, "learning_rate": 1.9615147783251234e-05, "loss": 1.4848, "step": 131 }, { "epoch": 0.02030691127264336, "grad_norm": 4.020627498626709, "learning_rate": 1.9612068965517245e-05, "loss": 1.6807, "step": 132 }, { "epoch": 0.020460751509557326, "grad_norm": 3.8125557899475098, "learning_rate": 1.9608990147783252e-05, "loss": 1.6176, "step": 133 }, { "epoch": 0.02061459174647129, "grad_norm": 3.9175567626953125, "learning_rate": 1.9605911330049263e-05, "loss": 1.7007, "step": 134 }, { "epoch": 0.020768431983385256, "grad_norm": 4.118912696838379, "learning_rate": 1.9602832512315273e-05, "loss": 1.5902, "step": 135 }, { "epoch": 0.02092227222029922, "grad_norm": 3.55366849899292, "learning_rate": 1.9599753694581284e-05, "loss": 1.7129, "step": 136 }, { "epoch": 0.021076112457213185, "grad_norm": 4.133559226989746, "learning_rate": 1.959667487684729e-05, "loss": 1.6703, "step": 137 }, { "epoch": 0.021229952694127148, "grad_norm": 4.5519700050354, "learning_rate": 1.9593596059113302e-05, "loss": 1.576, "step": 138 }, { "epoch": 0.021383792931041114, "grad_norm": 3.9101014137268066, "learning_rate": 1.9590517241379312e-05, "loss": 1.5249, "step": 139 }, { "epoch": 0.021537633167955077, "grad_norm": 4.592325687408447, "learning_rate": 1.9587438423645323e-05, "loss": 1.6213, "step": 140 }, { "epoch": 0.021691473404869044, "grad_norm": 5.139246940612793, "learning_rate": 1.958435960591133e-05, "loss": 1.7719, "step": 141 }, { "epoch": 0.021845313641783007, "grad_norm": 5.294092178344727, "learning_rate": 1.958128078817734e-05, "loss": 1.8878, "step": 142 }, { "epoch": 0.021999153878696973, "grad_norm": 4.455688953399658, "learning_rate": 1.957820197044335e-05, "loss": 1.7997, "step": 143 }, { "epoch": 0.02215299411561094, "grad_norm": 4.1391167640686035, "learning_rate": 1.9575123152709362e-05, "loss": 1.6329, "step": 144 }, { "epoch": 0.022306834352524903, "grad_norm": 4.518065929412842, "learning_rate": 1.957204433497537e-05, "loss": 1.8912, "step": 145 }, { "epoch": 0.02246067458943887, "grad_norm": 3.9967377185821533, "learning_rate": 1.956896551724138e-05, "loss": 1.4948, "step": 146 }, { "epoch": 0.022614514826352832, "grad_norm": 3.7498128414154053, "learning_rate": 1.956588669950739e-05, "loss": 1.4707, "step": 147 }, { "epoch": 0.0227683550632668, "grad_norm": 4.673575401306152, "learning_rate": 1.95628078817734e-05, "loss": 1.7419, "step": 148 }, { "epoch": 0.02292219530018076, "grad_norm": 4.127596378326416, "learning_rate": 1.955972906403941e-05, "loss": 1.741, "step": 149 }, { "epoch": 0.023076035537094728, "grad_norm": 4.317342281341553, "learning_rate": 1.955665024630542e-05, "loss": 1.5771, "step": 150 }, { "epoch": 0.02322987577400869, "grad_norm": 4.247869968414307, "learning_rate": 1.955357142857143e-05, "loss": 1.7432, "step": 151 }, { "epoch": 0.023383716010922657, "grad_norm": 3.6222832202911377, "learning_rate": 1.955049261083744e-05, "loss": 1.289, "step": 152 }, { "epoch": 0.02353755624783662, "grad_norm": 4.17736291885376, "learning_rate": 1.9547413793103448e-05, "loss": 1.3079, "step": 153 }, { "epoch": 0.023691396484750587, "grad_norm": 4.036698818206787, "learning_rate": 1.954433497536946e-05, "loss": 1.7277, "step": 154 }, { "epoch": 0.02384523672166455, "grad_norm": 3.4287264347076416, "learning_rate": 1.954125615763547e-05, "loss": 1.6251, "step": 155 }, { "epoch": 0.023999076958578516, "grad_norm": 4.469813346862793, "learning_rate": 1.953817733990148e-05, "loss": 1.5914, "step": 156 }, { "epoch": 0.024152917195492483, "grad_norm": 4.0893473625183105, "learning_rate": 1.9535098522167487e-05, "loss": 1.708, "step": 157 }, { "epoch": 0.024306757432406446, "grad_norm": 4.781553745269775, "learning_rate": 1.9532019704433498e-05, "loss": 1.4083, "step": 158 }, { "epoch": 0.024460597669320412, "grad_norm": 4.408946990966797, "learning_rate": 1.952894088669951e-05, "loss": 1.4955, "step": 159 }, { "epoch": 0.024614437906234375, "grad_norm": 4.717752933502197, "learning_rate": 1.952586206896552e-05, "loss": 1.7368, "step": 160 }, { "epoch": 0.02476827814314834, "grad_norm": 4.014177322387695, "learning_rate": 1.952278325123153e-05, "loss": 1.6961, "step": 161 }, { "epoch": 0.024922118380062305, "grad_norm": 3.9345500469207764, "learning_rate": 1.951970443349754e-05, "loss": 1.5504, "step": 162 }, { "epoch": 0.02507595861697627, "grad_norm": 4.373135089874268, "learning_rate": 1.9516625615763548e-05, "loss": 1.6733, "step": 163 }, { "epoch": 0.025229798853890234, "grad_norm": 3.1571249961853027, "learning_rate": 1.9513546798029558e-05, "loss": 1.9385, "step": 164 }, { "epoch": 0.0253836390908042, "grad_norm": 3.680243492126465, "learning_rate": 1.951046798029557e-05, "loss": 1.506, "step": 165 }, { "epoch": 0.025537479327718163, "grad_norm": 4.374537944793701, "learning_rate": 1.950738916256158e-05, "loss": 1.7332, "step": 166 }, { "epoch": 0.02569131956463213, "grad_norm": 4.00348424911499, "learning_rate": 1.9504310344827587e-05, "loss": 1.5569, "step": 167 }, { "epoch": 0.025845159801546093, "grad_norm": 4.857664108276367, "learning_rate": 1.9501231527093597e-05, "loss": 1.79, "step": 168 }, { "epoch": 0.02599900003846006, "grad_norm": 3.415651559829712, "learning_rate": 1.9498152709359608e-05, "loss": 1.536, "step": 169 }, { "epoch": 0.026152840275374026, "grad_norm": 4.274453639984131, "learning_rate": 1.949507389162562e-05, "loss": 1.5081, "step": 170 }, { "epoch": 0.02630668051228799, "grad_norm": 3.9193856716156006, "learning_rate": 1.9491995073891626e-05, "loss": 1.2442, "step": 171 }, { "epoch": 0.026460520749201955, "grad_norm": 4.409398078918457, "learning_rate": 1.9488916256157637e-05, "loss": 1.5554, "step": 172 }, { "epoch": 0.026614360986115918, "grad_norm": 4.2769293785095215, "learning_rate": 1.9485837438423647e-05, "loss": 1.5992, "step": 173 }, { "epoch": 0.026768201223029885, "grad_norm": 4.372714996337891, "learning_rate": 1.9482758620689658e-05, "loss": 1.9983, "step": 174 }, { "epoch": 0.026922041459943848, "grad_norm": 3.6766815185546875, "learning_rate": 1.9479679802955665e-05, "loss": 1.4723, "step": 175 }, { "epoch": 0.027075881696857814, "grad_norm": 4.291491508483887, "learning_rate": 1.9476600985221676e-05, "loss": 1.4497, "step": 176 }, { "epoch": 0.027229721933771777, "grad_norm": 3.618546962738037, "learning_rate": 1.9473522167487686e-05, "loss": 1.5789, "step": 177 }, { "epoch": 0.027383562170685743, "grad_norm": 3.6395962238311768, "learning_rate": 1.9470443349753697e-05, "loss": 1.6737, "step": 178 }, { "epoch": 0.027537402407599706, "grad_norm": 4.28580904006958, "learning_rate": 1.9467364532019704e-05, "loss": 1.7409, "step": 179 }, { "epoch": 0.027691242644513673, "grad_norm": 4.047371864318848, "learning_rate": 1.9464285714285715e-05, "loss": 1.3828, "step": 180 }, { "epoch": 0.027845082881427636, "grad_norm": 4.161651134490967, "learning_rate": 1.9461206896551726e-05, "loss": 1.5296, "step": 181 }, { "epoch": 0.027998923118341602, "grad_norm": 4.035069465637207, "learning_rate": 1.9458128078817736e-05, "loss": 1.5586, "step": 182 }, { "epoch": 0.02815276335525557, "grad_norm": 4.554925918579102, "learning_rate": 1.9455049261083744e-05, "loss": 1.5688, "step": 183 }, { "epoch": 0.028306603592169532, "grad_norm": 4.3065948486328125, "learning_rate": 1.9451970443349754e-05, "loss": 1.5487, "step": 184 }, { "epoch": 0.028460443829083498, "grad_norm": 4.284791469573975, "learning_rate": 1.9448891625615765e-05, "loss": 1.684, "step": 185 }, { "epoch": 0.02861428406599746, "grad_norm": 3.9373273849487305, "learning_rate": 1.9445812807881775e-05, "loss": 1.7057, "step": 186 }, { "epoch": 0.028768124302911428, "grad_norm": 4.334797382354736, "learning_rate": 1.9442733990147783e-05, "loss": 1.5724, "step": 187 }, { "epoch": 0.02892196453982539, "grad_norm": 4.620547771453857, "learning_rate": 1.9439655172413793e-05, "loss": 1.5432, "step": 188 }, { "epoch": 0.029075804776739357, "grad_norm": 4.359286785125732, "learning_rate": 1.9436576354679804e-05, "loss": 1.629, "step": 189 }, { "epoch": 0.02922964501365332, "grad_norm": 4.285168647766113, "learning_rate": 1.9433497536945815e-05, "loss": 1.6513, "step": 190 }, { "epoch": 0.029383485250567287, "grad_norm": 4.356363296508789, "learning_rate": 1.9430418719211822e-05, "loss": 1.6004, "step": 191 }, { "epoch": 0.02953732548748125, "grad_norm": 4.346536159515381, "learning_rate": 1.9427339901477833e-05, "loss": 1.5713, "step": 192 }, { "epoch": 0.029691165724395216, "grad_norm": 3.5740437507629395, "learning_rate": 1.9424261083743847e-05, "loss": 1.7, "step": 193 }, { "epoch": 0.02984500596130918, "grad_norm": 4.803465366363525, "learning_rate": 1.9421182266009854e-05, "loss": 1.5972, "step": 194 }, { "epoch": 0.029998846198223145, "grad_norm": 3.904435634613037, "learning_rate": 1.9418103448275865e-05, "loss": 1.5587, "step": 195 }, { "epoch": 0.030152686435137112, "grad_norm": 4.201726913452148, "learning_rate": 1.9415024630541875e-05, "loss": 1.6275, "step": 196 }, { "epoch": 0.030306526672051075, "grad_norm": 3.771109104156494, "learning_rate": 1.9411945812807886e-05, "loss": 1.7711, "step": 197 }, { "epoch": 0.03046036690896504, "grad_norm": 4.3905487060546875, "learning_rate": 1.9408866995073893e-05, "loss": 1.8089, "step": 198 }, { "epoch": 0.030614207145879004, "grad_norm": 4.121624946594238, "learning_rate": 1.9405788177339904e-05, "loss": 1.6127, "step": 199 }, { "epoch": 0.03076804738279297, "grad_norm": 4.230374336242676, "learning_rate": 1.9402709359605914e-05, "loss": 1.6605, "step": 200 }, { "epoch": 0.030921887619706934, "grad_norm": 3.9047675132751465, "learning_rate": 1.939963054187192e-05, "loss": 1.6347, "step": 201 }, { "epoch": 0.0310757278566209, "grad_norm": 4.425257205963135, "learning_rate": 1.9396551724137932e-05, "loss": 1.8195, "step": 202 }, { "epoch": 0.031229568093534863, "grad_norm": 4.2252044677734375, "learning_rate": 1.9393472906403943e-05, "loss": 1.4811, "step": 203 }, { "epoch": 0.03138340833044883, "grad_norm": 4.060047149658203, "learning_rate": 1.9390394088669954e-05, "loss": 1.8073, "step": 204 }, { "epoch": 0.03153724856736279, "grad_norm": 4.698678970336914, "learning_rate": 1.938731527093596e-05, "loss": 1.7163, "step": 205 }, { "epoch": 0.031691088804276756, "grad_norm": 4.1575422286987305, "learning_rate": 1.938423645320197e-05, "loss": 1.3557, "step": 206 }, { "epoch": 0.031844929041190725, "grad_norm": 4.128330707550049, "learning_rate": 1.9381157635467982e-05, "loss": 1.6294, "step": 207 }, { "epoch": 0.03199876927810469, "grad_norm": 4.394817352294922, "learning_rate": 1.9378078817733993e-05, "loss": 1.1291, "step": 208 }, { "epoch": 0.03215260951501865, "grad_norm": 4.117674350738525, "learning_rate": 1.9375e-05, "loss": 1.464, "step": 209 }, { "epoch": 0.03230644975193262, "grad_norm": 3.880251169204712, "learning_rate": 1.937192118226601e-05, "loss": 1.6801, "step": 210 }, { "epoch": 0.032460289988846584, "grad_norm": 4.4803595542907715, "learning_rate": 1.936884236453202e-05, "loss": 1.5985, "step": 211 }, { "epoch": 0.03261413022576055, "grad_norm": 4.796767234802246, "learning_rate": 1.9365763546798032e-05, "loss": 1.5631, "step": 212 }, { "epoch": 0.03276797046267451, "grad_norm": 5.247900009155273, "learning_rate": 1.936268472906404e-05, "loss": 1.4018, "step": 213 }, { "epoch": 0.03292181069958848, "grad_norm": 4.314574718475342, "learning_rate": 1.935960591133005e-05, "loss": 1.7931, "step": 214 }, { "epoch": 0.03307565093650244, "grad_norm": 3.843625068664551, "learning_rate": 1.935652709359606e-05, "loss": 1.7047, "step": 215 }, { "epoch": 0.033229491173416406, "grad_norm": 4.5460638999938965, "learning_rate": 1.935344827586207e-05, "loss": 1.5772, "step": 216 }, { "epoch": 0.03338333141033037, "grad_norm": 4.10468864440918, "learning_rate": 1.935036945812808e-05, "loss": 1.5629, "step": 217 }, { "epoch": 0.03353717164724434, "grad_norm": 4.423603534698486, "learning_rate": 1.934729064039409e-05, "loss": 1.7062, "step": 218 }, { "epoch": 0.0336910118841583, "grad_norm": 4.1333231925964355, "learning_rate": 1.93442118226601e-05, "loss": 1.5985, "step": 219 }, { "epoch": 0.033844852121072265, "grad_norm": 4.476043701171875, "learning_rate": 1.934113300492611e-05, "loss": 1.4307, "step": 220 }, { "epoch": 0.03399869235798623, "grad_norm": 4.730133533477783, "learning_rate": 1.9338054187192118e-05, "loss": 1.5748, "step": 221 }, { "epoch": 0.0341525325949002, "grad_norm": 4.064263820648193, "learning_rate": 1.9334975369458128e-05, "loss": 1.613, "step": 222 }, { "epoch": 0.03430637283181416, "grad_norm": 4.016196250915527, "learning_rate": 1.933189655172414e-05, "loss": 1.5027, "step": 223 }, { "epoch": 0.034460213068728124, "grad_norm": 3.9161574840545654, "learning_rate": 1.932881773399015e-05, "loss": 1.8423, "step": 224 }, { "epoch": 0.034614053305642094, "grad_norm": 4.4477739334106445, "learning_rate": 1.9325738916256157e-05, "loss": 1.6665, "step": 225 }, { "epoch": 0.03476789354255606, "grad_norm": 4.502500534057617, "learning_rate": 1.932266009852217e-05, "loss": 1.507, "step": 226 }, { "epoch": 0.03492173377947002, "grad_norm": 3.518771171569824, "learning_rate": 1.931958128078818e-05, "loss": 1.3858, "step": 227 }, { "epoch": 0.03507557401638398, "grad_norm": 4.339448928833008, "learning_rate": 1.931650246305419e-05, "loss": 1.6519, "step": 228 }, { "epoch": 0.03522941425329795, "grad_norm": 3.935678243637085, "learning_rate": 1.93134236453202e-05, "loss": 1.4945, "step": 229 }, { "epoch": 0.035383254490211916, "grad_norm": 3.47182559967041, "learning_rate": 1.931034482758621e-05, "loss": 1.4761, "step": 230 }, { "epoch": 0.03553709472712588, "grad_norm": 4.7916364669799805, "learning_rate": 1.930726600985222e-05, "loss": 1.9077, "step": 231 }, { "epoch": 0.03569093496403984, "grad_norm": 4.722495079040527, "learning_rate": 1.9304187192118228e-05, "loss": 1.6442, "step": 232 }, { "epoch": 0.03584477520095381, "grad_norm": 4.887296676635742, "learning_rate": 1.930110837438424e-05, "loss": 1.7056, "step": 233 }, { "epoch": 0.035998615437867774, "grad_norm": 4.438931465148926, "learning_rate": 1.929802955665025e-05, "loss": 1.6653, "step": 234 }, { "epoch": 0.03615245567478174, "grad_norm": 5.025758743286133, "learning_rate": 1.929495073891626e-05, "loss": 1.6352, "step": 235 }, { "epoch": 0.03630629591169571, "grad_norm": 4.433369159698486, "learning_rate": 1.9291871921182267e-05, "loss": 1.6216, "step": 236 }, { "epoch": 0.03646013614860967, "grad_norm": 3.739698886871338, "learning_rate": 1.9288793103448278e-05, "loss": 1.1118, "step": 237 }, { "epoch": 0.03661397638552363, "grad_norm": 5.019486427307129, "learning_rate": 1.928571428571429e-05, "loss": 1.6015, "step": 238 }, { "epoch": 0.036767816622437596, "grad_norm": 4.746649265289307, "learning_rate": 1.92826354679803e-05, "loss": 1.6311, "step": 239 }, { "epoch": 0.036921656859351566, "grad_norm": 4.729990482330322, "learning_rate": 1.9279556650246306e-05, "loss": 1.5651, "step": 240 }, { "epoch": 0.03707549709626553, "grad_norm": 3.6162843704223633, "learning_rate": 1.9276477832512317e-05, "loss": 1.5593, "step": 241 }, { "epoch": 0.03722933733317949, "grad_norm": 4.206906795501709, "learning_rate": 1.9273399014778328e-05, "loss": 1.4824, "step": 242 }, { "epoch": 0.037383177570093455, "grad_norm": 3.8867921829223633, "learning_rate": 1.9270320197044338e-05, "loss": 1.5417, "step": 243 }, { "epoch": 0.037537017807007425, "grad_norm": 3.7932798862457275, "learning_rate": 1.9267241379310345e-05, "loss": 1.6231, "step": 244 }, { "epoch": 0.03769085804392139, "grad_norm": 4.510362148284912, "learning_rate": 1.9264162561576356e-05, "loss": 1.4557, "step": 245 }, { "epoch": 0.03784469828083535, "grad_norm": 4.405462741851807, "learning_rate": 1.9261083743842367e-05, "loss": 1.6445, "step": 246 }, { "epoch": 0.037998538517749314, "grad_norm": 4.467000484466553, "learning_rate": 1.9258004926108374e-05, "loss": 1.6201, "step": 247 }, { "epoch": 0.038152378754663284, "grad_norm": 3.6909635066986084, "learning_rate": 1.9254926108374385e-05, "loss": 1.3985, "step": 248 }, { "epoch": 0.03830621899157725, "grad_norm": 4.108460903167725, "learning_rate": 1.9251847290640395e-05, "loss": 1.6284, "step": 249 }, { "epoch": 0.03846005922849121, "grad_norm": 3.6774582862854004, "learning_rate": 1.9248768472906406e-05, "loss": 1.5283, "step": 250 }, { "epoch": 0.03861389946540518, "grad_norm": 3.4591641426086426, "learning_rate": 1.9245689655172413e-05, "loss": 1.6445, "step": 251 }, { "epoch": 0.03876773970231914, "grad_norm": 3.422475814819336, "learning_rate": 1.9242610837438424e-05, "loss": 1.5916, "step": 252 }, { "epoch": 0.038921579939233106, "grad_norm": 4.045068264007568, "learning_rate": 1.9239532019704435e-05, "loss": 1.3383, "step": 253 }, { "epoch": 0.03907542017614707, "grad_norm": 3.818187952041626, "learning_rate": 1.9236453201970445e-05, "loss": 1.4244, "step": 254 }, { "epoch": 0.03922926041306104, "grad_norm": 5.259893417358398, "learning_rate": 1.9233374384236452e-05, "loss": 1.4622, "step": 255 }, { "epoch": 0.039383100649975, "grad_norm": 4.811656951904297, "learning_rate": 1.9230295566502463e-05, "loss": 1.6046, "step": 256 }, { "epoch": 0.039536940886888965, "grad_norm": 3.924947738647461, "learning_rate": 1.9227216748768474e-05, "loss": 1.6211, "step": 257 }, { "epoch": 0.03969078112380293, "grad_norm": 4.518905162811279, "learning_rate": 1.9224137931034484e-05, "loss": 1.3765, "step": 258 }, { "epoch": 0.0398446213607169, "grad_norm": 4.017415523529053, "learning_rate": 1.922105911330049e-05, "loss": 1.6013, "step": 259 }, { "epoch": 0.03999846159763086, "grad_norm": 3.9720170497894287, "learning_rate": 1.9217980295566506e-05, "loss": 1.6185, "step": 260 }, { "epoch": 0.040152301834544823, "grad_norm": 3.690607786178589, "learning_rate": 1.9214901477832516e-05, "loss": 1.7599, "step": 261 }, { "epoch": 0.04030614207145879, "grad_norm": 5.24265718460083, "learning_rate": 1.9211822660098524e-05, "loss": 1.8272, "step": 262 }, { "epoch": 0.040459982308372756, "grad_norm": 4.255435466766357, "learning_rate": 1.9208743842364534e-05, "loss": 1.6002, "step": 263 }, { "epoch": 0.04061382254528672, "grad_norm": 3.7923760414123535, "learning_rate": 1.9205665024630545e-05, "loss": 1.5302, "step": 264 }, { "epoch": 0.04076766278220068, "grad_norm": 4.401931285858154, "learning_rate": 1.9202586206896555e-05, "loss": 1.6769, "step": 265 }, { "epoch": 0.04092150301911465, "grad_norm": 3.863168239593506, "learning_rate": 1.9199507389162563e-05, "loss": 1.5211, "step": 266 }, { "epoch": 0.041075343256028615, "grad_norm": 3.62870717048645, "learning_rate": 1.9196428571428573e-05, "loss": 1.6257, "step": 267 }, { "epoch": 0.04122918349294258, "grad_norm": 4.6201395988464355, "learning_rate": 1.9193349753694584e-05, "loss": 1.7548, "step": 268 }, { "epoch": 0.04138302372985654, "grad_norm": 3.468604803085327, "learning_rate": 1.9190270935960595e-05, "loss": 1.4423, "step": 269 }, { "epoch": 0.04153686396677051, "grad_norm": 3.719809055328369, "learning_rate": 1.9187192118226602e-05, "loss": 1.6527, "step": 270 }, { "epoch": 0.041690704203684474, "grad_norm": 3.9627797603607178, "learning_rate": 1.9184113300492613e-05, "loss": 1.4417, "step": 271 }, { "epoch": 0.04184454444059844, "grad_norm": 3.835282564163208, "learning_rate": 1.9181034482758623e-05, "loss": 1.5386, "step": 272 }, { "epoch": 0.0419983846775124, "grad_norm": 4.010097503662109, "learning_rate": 1.9177955665024634e-05, "loss": 1.4913, "step": 273 }, { "epoch": 0.04215222491442637, "grad_norm": 4.048743724822998, "learning_rate": 1.917487684729064e-05, "loss": 1.5227, "step": 274 }, { "epoch": 0.04230606515134033, "grad_norm": 4.155489921569824, "learning_rate": 1.9171798029556652e-05, "loss": 1.5319, "step": 275 }, { "epoch": 0.042459905388254296, "grad_norm": 3.9985568523406982, "learning_rate": 1.9168719211822662e-05, "loss": 1.4607, "step": 276 }, { "epoch": 0.042613745625168266, "grad_norm": 4.368554592132568, "learning_rate": 1.9165640394088673e-05, "loss": 1.8687, "step": 277 }, { "epoch": 0.04276758586208223, "grad_norm": 4.586329936981201, "learning_rate": 1.916256157635468e-05, "loss": 1.6742, "step": 278 }, { "epoch": 0.04292142609899619, "grad_norm": 4.505170822143555, "learning_rate": 1.915948275862069e-05, "loss": 1.6204, "step": 279 }, { "epoch": 0.043075266335910155, "grad_norm": 4.013214588165283, "learning_rate": 1.91564039408867e-05, "loss": 1.61, "step": 280 }, { "epoch": 0.043229106572824125, "grad_norm": 3.951573371887207, "learning_rate": 1.9153325123152712e-05, "loss": 1.6753, "step": 281 }, { "epoch": 0.04338294680973809, "grad_norm": 3.658256769180298, "learning_rate": 1.915024630541872e-05, "loss": 1.515, "step": 282 }, { "epoch": 0.04353678704665205, "grad_norm": 3.9189271926879883, "learning_rate": 1.914716748768473e-05, "loss": 1.4585, "step": 283 }, { "epoch": 0.043690627283566014, "grad_norm": 4.271494388580322, "learning_rate": 1.914408866995074e-05, "loss": 1.4739, "step": 284 }, { "epoch": 0.043844467520479984, "grad_norm": 4.319568157196045, "learning_rate": 1.914100985221675e-05, "loss": 1.6606, "step": 285 }, { "epoch": 0.04399830775739395, "grad_norm": 3.4124879837036133, "learning_rate": 1.913793103448276e-05, "loss": 1.2593, "step": 286 }, { "epoch": 0.04415214799430791, "grad_norm": 4.377912521362305, "learning_rate": 1.913485221674877e-05, "loss": 1.3752, "step": 287 }, { "epoch": 0.04430598823122188, "grad_norm": 4.667548656463623, "learning_rate": 1.913177339901478e-05, "loss": 1.6933, "step": 288 }, { "epoch": 0.04445982846813584, "grad_norm": 3.682115077972412, "learning_rate": 1.9128694581280787e-05, "loss": 1.4434, "step": 289 }, { "epoch": 0.044613668705049805, "grad_norm": 4.0281758308410645, "learning_rate": 1.9125615763546798e-05, "loss": 1.5602, "step": 290 }, { "epoch": 0.04476750894196377, "grad_norm": 4.089077472686768, "learning_rate": 1.912253694581281e-05, "loss": 1.3358, "step": 291 }, { "epoch": 0.04492134917887774, "grad_norm": 4.5025787353515625, "learning_rate": 1.911945812807882e-05, "loss": 1.3624, "step": 292 }, { "epoch": 0.0450751894157917, "grad_norm": 3.7649378776550293, "learning_rate": 1.9116379310344826e-05, "loss": 1.6778, "step": 293 }, { "epoch": 0.045229029652705664, "grad_norm": 4.0751051902771, "learning_rate": 1.911330049261084e-05, "loss": 1.5088, "step": 294 }, { "epoch": 0.04538286988961963, "grad_norm": 4.2477335929870605, "learning_rate": 1.911022167487685e-05, "loss": 1.4771, "step": 295 }, { "epoch": 0.0455367101265336, "grad_norm": 3.7729389667510986, "learning_rate": 1.910714285714286e-05, "loss": 1.3563, "step": 296 }, { "epoch": 0.04569055036344756, "grad_norm": 4.28593111038208, "learning_rate": 1.910406403940887e-05, "loss": 1.3372, "step": 297 }, { "epoch": 0.04584439060036152, "grad_norm": 5.259074687957764, "learning_rate": 1.910098522167488e-05, "loss": 1.6697, "step": 298 }, { "epoch": 0.045998230837275486, "grad_norm": 5.17897891998291, "learning_rate": 1.909790640394089e-05, "loss": 1.6276, "step": 299 }, { "epoch": 0.046152071074189456, "grad_norm": 3.913630723953247, "learning_rate": 1.9094827586206898e-05, "loss": 1.5994, "step": 300 }, { "epoch": 0.04630591131110342, "grad_norm": 4.372139930725098, "learning_rate": 1.9091748768472908e-05, "loss": 1.5336, "step": 301 }, { "epoch": 0.04645975154801738, "grad_norm": 4.513306140899658, "learning_rate": 1.908866995073892e-05, "loss": 1.5577, "step": 302 }, { "epoch": 0.04661359178493135, "grad_norm": 4.379326820373535, "learning_rate": 1.908559113300493e-05, "loss": 1.5839, "step": 303 }, { "epoch": 0.046767432021845315, "grad_norm": 3.6816000938415527, "learning_rate": 1.9082512315270937e-05, "loss": 1.3243, "step": 304 }, { "epoch": 0.04692127225875928, "grad_norm": 3.990715503692627, "learning_rate": 1.9079433497536947e-05, "loss": 1.4547, "step": 305 }, { "epoch": 0.04707511249567324, "grad_norm": 4.385611534118652, "learning_rate": 1.9076354679802958e-05, "loss": 1.6492, "step": 306 }, { "epoch": 0.04722895273258721, "grad_norm": 3.838383197784424, "learning_rate": 1.907327586206897e-05, "loss": 1.5172, "step": 307 }, { "epoch": 0.047382792969501174, "grad_norm": 4.355856895446777, "learning_rate": 1.9070197044334976e-05, "loss": 1.5296, "step": 308 }, { "epoch": 0.04753663320641514, "grad_norm": 5.240326881408691, "learning_rate": 1.9067118226600987e-05, "loss": 1.9338, "step": 309 }, { "epoch": 0.0476904734433291, "grad_norm": 4.503302097320557, "learning_rate": 1.9064039408866997e-05, "loss": 1.3769, "step": 310 }, { "epoch": 0.04784431368024307, "grad_norm": 3.6000518798828125, "learning_rate": 1.9060960591133008e-05, "loss": 1.8014, "step": 311 }, { "epoch": 0.04799815391715703, "grad_norm": 4.237121105194092, "learning_rate": 1.9057881773399015e-05, "loss": 1.3454, "step": 312 }, { "epoch": 0.048151994154070996, "grad_norm": 4.117266654968262, "learning_rate": 1.9054802955665026e-05, "loss": 1.6211, "step": 313 }, { "epoch": 0.048305834390984966, "grad_norm": 4.916101932525635, "learning_rate": 1.9051724137931036e-05, "loss": 1.4009, "step": 314 }, { "epoch": 0.04845967462789893, "grad_norm": 4.63978910446167, "learning_rate": 1.9048645320197047e-05, "loss": 1.6247, "step": 315 }, { "epoch": 0.04861351486481289, "grad_norm": 3.8069281578063965, "learning_rate": 1.9045566502463054e-05, "loss": 1.6996, "step": 316 }, { "epoch": 0.048767355101726854, "grad_norm": 3.561722993850708, "learning_rate": 1.9042487684729065e-05, "loss": 1.5889, "step": 317 }, { "epoch": 0.048921195338640824, "grad_norm": 4.183290481567383, "learning_rate": 1.9039408866995076e-05, "loss": 1.337, "step": 318 }, { "epoch": 0.04907503557555479, "grad_norm": 4.33397102355957, "learning_rate": 1.9036330049261086e-05, "loss": 1.3978, "step": 319 }, { "epoch": 0.04922887581246875, "grad_norm": 3.87420916557312, "learning_rate": 1.9033251231527094e-05, "loss": 1.1766, "step": 320 }, { "epoch": 0.04938271604938271, "grad_norm": 3.896658182144165, "learning_rate": 1.9030172413793104e-05, "loss": 1.7247, "step": 321 }, { "epoch": 0.04953655628629668, "grad_norm": 4.803473472595215, "learning_rate": 1.9027093596059115e-05, "loss": 1.3546, "step": 322 }, { "epoch": 0.049690396523210646, "grad_norm": 4.092232704162598, "learning_rate": 1.9024014778325125e-05, "loss": 1.5148, "step": 323 }, { "epoch": 0.04984423676012461, "grad_norm": 4.236131191253662, "learning_rate": 1.9020935960591133e-05, "loss": 1.6097, "step": 324 }, { "epoch": 0.04999807699703857, "grad_norm": 3.4020094871520996, "learning_rate": 1.9017857142857143e-05, "loss": 1.29, "step": 325 }, { "epoch": 0.05015191723395254, "grad_norm": 3.760632276535034, "learning_rate": 1.9014778325123154e-05, "loss": 1.6269, "step": 326 }, { "epoch": 0.050305757470866505, "grad_norm": 3.8015875816345215, "learning_rate": 1.9011699507389165e-05, "loss": 1.5223, "step": 327 }, { "epoch": 0.05045959770778047, "grad_norm": 5.113397121429443, "learning_rate": 1.9008620689655175e-05, "loss": 1.8169, "step": 328 }, { "epoch": 0.05061343794469444, "grad_norm": 5.057936191558838, "learning_rate": 1.9005541871921186e-05, "loss": 1.6795, "step": 329 }, { "epoch": 0.0507672781816084, "grad_norm": 3.6318209171295166, "learning_rate": 1.9002463054187193e-05, "loss": 1.7287, "step": 330 }, { "epoch": 0.050921118418522364, "grad_norm": 3.7368810176849365, "learning_rate": 1.8999384236453204e-05, "loss": 1.4596, "step": 331 }, { "epoch": 0.05107495865543633, "grad_norm": 4.965750694274902, "learning_rate": 1.8996305418719214e-05, "loss": 1.5627, "step": 332 }, { "epoch": 0.0512287988923503, "grad_norm": 5.112000465393066, "learning_rate": 1.8993226600985225e-05, "loss": 1.4686, "step": 333 }, { "epoch": 0.05138263912926426, "grad_norm": 4.251415729522705, "learning_rate": 1.8990147783251232e-05, "loss": 1.398, "step": 334 }, { "epoch": 0.05153647936617822, "grad_norm": 4.048766613006592, "learning_rate": 1.8987068965517243e-05, "loss": 1.9565, "step": 335 }, { "epoch": 0.051690319603092186, "grad_norm": 4.644125938415527, "learning_rate": 1.8983990147783254e-05, "loss": 1.5028, "step": 336 }, { "epoch": 0.051844159840006156, "grad_norm": 3.8180761337280273, "learning_rate": 1.8980911330049264e-05, "loss": 1.476, "step": 337 }, { "epoch": 0.05199800007692012, "grad_norm": 4.080455303192139, "learning_rate": 1.897783251231527e-05, "loss": 1.7877, "step": 338 }, { "epoch": 0.05215184031383408, "grad_norm": 5.636694431304932, "learning_rate": 1.8974753694581282e-05, "loss": 1.2818, "step": 339 }, { "epoch": 0.05230568055074805, "grad_norm": 3.549755573272705, "learning_rate": 1.8971674876847293e-05, "loss": 1.6118, "step": 340 }, { "epoch": 0.052459520787662015, "grad_norm": 3.761319637298584, "learning_rate": 1.8968596059113304e-05, "loss": 1.418, "step": 341 }, { "epoch": 0.05261336102457598, "grad_norm": 3.5775487422943115, "learning_rate": 1.896551724137931e-05, "loss": 1.4082, "step": 342 }, { "epoch": 0.05276720126148994, "grad_norm": 3.373883008956909, "learning_rate": 1.896243842364532e-05, "loss": 1.409, "step": 343 }, { "epoch": 0.05292104149840391, "grad_norm": 3.6923916339874268, "learning_rate": 1.8959359605911332e-05, "loss": 1.471, "step": 344 }, { "epoch": 0.05307488173531787, "grad_norm": 4.40778112411499, "learning_rate": 1.8956280788177343e-05, "loss": 1.3824, "step": 345 }, { "epoch": 0.053228721972231836, "grad_norm": 4.004933834075928, "learning_rate": 1.895320197044335e-05, "loss": 1.3304, "step": 346 }, { "epoch": 0.0533825622091458, "grad_norm": 4.717761993408203, "learning_rate": 1.895012315270936e-05, "loss": 1.6298, "step": 347 }, { "epoch": 0.05353640244605977, "grad_norm": 3.694333076477051, "learning_rate": 1.894704433497537e-05, "loss": 1.3519, "step": 348 }, { "epoch": 0.05369024268297373, "grad_norm": 4.124557971954346, "learning_rate": 1.8943965517241382e-05, "loss": 1.3542, "step": 349 }, { "epoch": 0.053844082919887695, "grad_norm": 4.8314208984375, "learning_rate": 1.894088669950739e-05, "loss": 1.7106, "step": 350 }, { "epoch": 0.05399792315680166, "grad_norm": 4.562430381774902, "learning_rate": 1.89378078817734e-05, "loss": 1.7443, "step": 351 }, { "epoch": 0.05415176339371563, "grad_norm": 4.363633632659912, "learning_rate": 1.893472906403941e-05, "loss": 1.7166, "step": 352 }, { "epoch": 0.05430560363062959, "grad_norm": 4.42055606842041, "learning_rate": 1.893165024630542e-05, "loss": 1.4273, "step": 353 }, { "epoch": 0.054459443867543554, "grad_norm": 3.871933937072754, "learning_rate": 1.892857142857143e-05, "loss": 1.5526, "step": 354 }, { "epoch": 0.054613284104457524, "grad_norm": 4.304806709289551, "learning_rate": 1.892549261083744e-05, "loss": 1.652, "step": 355 }, { "epoch": 0.05476712434137149, "grad_norm": 5.284874439239502, "learning_rate": 1.892241379310345e-05, "loss": 1.6297, "step": 356 }, { "epoch": 0.05492096457828545, "grad_norm": 3.957707166671753, "learning_rate": 1.891933497536946e-05, "loss": 1.5133, "step": 357 }, { "epoch": 0.05507480481519941, "grad_norm": 3.880399703979492, "learning_rate": 1.8916256157635468e-05, "loss": 1.5378, "step": 358 }, { "epoch": 0.05522864505211338, "grad_norm": 4.176033973693848, "learning_rate": 1.8913177339901478e-05, "loss": 1.4868, "step": 359 }, { "epoch": 0.055382485289027346, "grad_norm": 3.7416510581970215, "learning_rate": 1.891009852216749e-05, "loss": 1.7959, "step": 360 }, { "epoch": 0.05553632552594131, "grad_norm": 3.769122362136841, "learning_rate": 1.89070197044335e-05, "loss": 1.468, "step": 361 }, { "epoch": 0.05569016576285527, "grad_norm": 3.7686378955841064, "learning_rate": 1.890394088669951e-05, "loss": 1.7575, "step": 362 }, { "epoch": 0.05584400599976924, "grad_norm": 4.087277889251709, "learning_rate": 1.890086206896552e-05, "loss": 1.447, "step": 363 }, { "epoch": 0.055997846236683205, "grad_norm": 4.29428768157959, "learning_rate": 1.8897783251231528e-05, "loss": 1.6545, "step": 364 }, { "epoch": 0.05615168647359717, "grad_norm": 3.6573731899261475, "learning_rate": 1.889470443349754e-05, "loss": 1.408, "step": 365 }, { "epoch": 0.05630552671051114, "grad_norm": 3.994508743286133, "learning_rate": 1.889162561576355e-05, "loss": 1.5603, "step": 366 }, { "epoch": 0.0564593669474251, "grad_norm": 3.666337728500366, "learning_rate": 1.888854679802956e-05, "loss": 1.4515, "step": 367 }, { "epoch": 0.056613207184339064, "grad_norm": 3.745919704437256, "learning_rate": 1.8885467980295567e-05, "loss": 1.6675, "step": 368 }, { "epoch": 0.05676704742125303, "grad_norm": 3.8834149837493896, "learning_rate": 1.8882389162561578e-05, "loss": 1.6407, "step": 369 }, { "epoch": 0.056920887658166996, "grad_norm": 3.935720205307007, "learning_rate": 1.887931034482759e-05, "loss": 1.6844, "step": 370 }, { "epoch": 0.05707472789508096, "grad_norm": 3.5764057636260986, "learning_rate": 1.88762315270936e-05, "loss": 1.7388, "step": 371 }, { "epoch": 0.05722856813199492, "grad_norm": 3.585728883743286, "learning_rate": 1.8873152709359606e-05, "loss": 1.4797, "step": 372 }, { "epoch": 0.057382408368908885, "grad_norm": 4.377996921539307, "learning_rate": 1.8870073891625617e-05, "loss": 1.6988, "step": 373 }, { "epoch": 0.057536248605822855, "grad_norm": 3.680140495300293, "learning_rate": 1.8866995073891628e-05, "loss": 1.4347, "step": 374 }, { "epoch": 0.05769008884273682, "grad_norm": 3.4058687686920166, "learning_rate": 1.886391625615764e-05, "loss": 1.6617, "step": 375 }, { "epoch": 0.05784392907965078, "grad_norm": 4.058459281921387, "learning_rate": 1.8860837438423646e-05, "loss": 1.5171, "step": 376 }, { "epoch": 0.057997769316564744, "grad_norm": 4.077273368835449, "learning_rate": 1.8857758620689656e-05, "loss": 1.6158, "step": 377 }, { "epoch": 0.058151609553478714, "grad_norm": 4.136841773986816, "learning_rate": 1.8854679802955667e-05, "loss": 1.5389, "step": 378 }, { "epoch": 0.05830544979039268, "grad_norm": 4.037159442901611, "learning_rate": 1.8851600985221678e-05, "loss": 1.2376, "step": 379 }, { "epoch": 0.05845929002730664, "grad_norm": 3.7544002532958984, "learning_rate": 1.8848522167487685e-05, "loss": 1.6319, "step": 380 }, { "epoch": 0.05861313026422061, "grad_norm": 3.3476240634918213, "learning_rate": 1.8845443349753695e-05, "loss": 1.4155, "step": 381 }, { "epoch": 0.05876697050113457, "grad_norm": 4.198622226715088, "learning_rate": 1.8842364532019706e-05, "loss": 1.478, "step": 382 }, { "epoch": 0.058920810738048536, "grad_norm": 4.402987957000732, "learning_rate": 1.8839285714285717e-05, "loss": 1.3437, "step": 383 }, { "epoch": 0.0590746509749625, "grad_norm": 3.4735682010650635, "learning_rate": 1.8836206896551724e-05, "loss": 1.3556, "step": 384 }, { "epoch": 0.05922849121187647, "grad_norm": 3.8555190563201904, "learning_rate": 1.8833128078817735e-05, "loss": 1.5795, "step": 385 }, { "epoch": 0.05938233144879043, "grad_norm": 4.6788649559021, "learning_rate": 1.8830049261083745e-05, "loss": 1.7124, "step": 386 }, { "epoch": 0.059536171685704395, "grad_norm": 3.6840226650238037, "learning_rate": 1.8826970443349756e-05, "loss": 1.3997, "step": 387 }, { "epoch": 0.05969001192261836, "grad_norm": 3.6833741664886475, "learning_rate": 1.8823891625615763e-05, "loss": 1.5964, "step": 388 }, { "epoch": 0.05984385215953233, "grad_norm": 4.505414009094238, "learning_rate": 1.8820812807881774e-05, "loss": 1.5714, "step": 389 }, { "epoch": 0.05999769239644629, "grad_norm": 4.49121618270874, "learning_rate": 1.8817733990147784e-05, "loss": 1.4275, "step": 390 }, { "epoch": 0.060151532633360254, "grad_norm": 3.5432639122009277, "learning_rate": 1.8814655172413795e-05, "loss": 1.6874, "step": 391 }, { "epoch": 0.060305372870274224, "grad_norm": 3.3381755352020264, "learning_rate": 1.8811576354679802e-05, "loss": 1.5917, "step": 392 }, { "epoch": 0.06045921310718819, "grad_norm": 4.172170162200928, "learning_rate": 1.8808497536945813e-05, "loss": 1.5263, "step": 393 }, { "epoch": 0.06061305334410215, "grad_norm": 3.569709062576294, "learning_rate": 1.8805418719211824e-05, "loss": 1.4538, "step": 394 }, { "epoch": 0.06076689358101611, "grad_norm": 4.052530765533447, "learning_rate": 1.8802339901477834e-05, "loss": 1.5091, "step": 395 }, { "epoch": 0.06092073381793008, "grad_norm": 4.9973673820495605, "learning_rate": 1.8799261083743845e-05, "loss": 1.5477, "step": 396 }, { "epoch": 0.061074574054844046, "grad_norm": 3.9234137535095215, "learning_rate": 1.8796182266009856e-05, "loss": 1.6142, "step": 397 }, { "epoch": 0.06122841429175801, "grad_norm": 4.620669841766357, "learning_rate": 1.8793103448275863e-05, "loss": 1.536, "step": 398 }, { "epoch": 0.06138225452867197, "grad_norm": 3.91044020652771, "learning_rate": 1.8790024630541874e-05, "loss": 1.5167, "step": 399 }, { "epoch": 0.06153609476558594, "grad_norm": 4.061367988586426, "learning_rate": 1.8786945812807884e-05, "loss": 1.5209, "step": 400 }, { "epoch": 0.061689935002499904, "grad_norm": 3.709010362625122, "learning_rate": 1.8783866995073895e-05, "loss": 1.4811, "step": 401 }, { "epoch": 0.06184377523941387, "grad_norm": 4.470370292663574, "learning_rate": 1.8780788177339902e-05, "loss": 1.3858, "step": 402 }, { "epoch": 0.06199761547632783, "grad_norm": 4.416262149810791, "learning_rate": 1.8777709359605913e-05, "loss": 1.6631, "step": 403 }, { "epoch": 0.0621514557132418, "grad_norm": 4.026382923126221, "learning_rate": 1.8774630541871923e-05, "loss": 1.8503, "step": 404 }, { "epoch": 0.06230529595015576, "grad_norm": 4.257750034332275, "learning_rate": 1.8771551724137934e-05, "loss": 1.6479, "step": 405 }, { "epoch": 0.062459136187069726, "grad_norm": 4.481858730316162, "learning_rate": 1.876847290640394e-05, "loss": 1.4336, "step": 406 }, { "epoch": 0.0626129764239837, "grad_norm": 3.9142441749572754, "learning_rate": 1.8765394088669952e-05, "loss": 1.7037, "step": 407 }, { "epoch": 0.06276681666089766, "grad_norm": 3.9232358932495117, "learning_rate": 1.8762315270935963e-05, "loss": 1.8272, "step": 408 }, { "epoch": 0.06292065689781162, "grad_norm": 3.6557867527008057, "learning_rate": 1.8759236453201973e-05, "loss": 1.347, "step": 409 }, { "epoch": 0.06307449713472559, "grad_norm": 4.029257297515869, "learning_rate": 1.875615763546798e-05, "loss": 1.7987, "step": 410 }, { "epoch": 0.06322833737163955, "grad_norm": 4.148924350738525, "learning_rate": 1.875307881773399e-05, "loss": 1.7059, "step": 411 }, { "epoch": 0.06338217760855351, "grad_norm": 3.6873106956481934, "learning_rate": 1.8750000000000002e-05, "loss": 1.4498, "step": 412 }, { "epoch": 0.06353601784546749, "grad_norm": 4.0995612144470215, "learning_rate": 1.8746921182266012e-05, "loss": 1.6455, "step": 413 }, { "epoch": 0.06368985808238145, "grad_norm": 4.452944278717041, "learning_rate": 1.874384236453202e-05, "loss": 1.4478, "step": 414 }, { "epoch": 0.06384369831929541, "grad_norm": 4.568933010101318, "learning_rate": 1.874076354679803e-05, "loss": 1.567, "step": 415 }, { "epoch": 0.06399753855620938, "grad_norm": 3.581433057785034, "learning_rate": 1.873768472906404e-05, "loss": 1.4315, "step": 416 }, { "epoch": 0.06415137879312334, "grad_norm": 3.7856252193450928, "learning_rate": 1.873460591133005e-05, "loss": 1.8834, "step": 417 }, { "epoch": 0.0643052190300373, "grad_norm": 3.3687944412231445, "learning_rate": 1.873152709359606e-05, "loss": 1.4096, "step": 418 }, { "epoch": 0.06445905926695127, "grad_norm": 3.57985520362854, "learning_rate": 1.872844827586207e-05, "loss": 1.3527, "step": 419 }, { "epoch": 0.06461289950386524, "grad_norm": 3.7013726234436035, "learning_rate": 1.872536945812808e-05, "loss": 1.4971, "step": 420 }, { "epoch": 0.0647667397407792, "grad_norm": 4.507592678070068, "learning_rate": 1.872229064039409e-05, "loss": 1.4941, "step": 421 }, { "epoch": 0.06492057997769317, "grad_norm": 3.756960391998291, "learning_rate": 1.8719211822660098e-05, "loss": 1.704, "step": 422 }, { "epoch": 0.06507442021460713, "grad_norm": 3.9086415767669678, "learning_rate": 1.871613300492611e-05, "loss": 1.6391, "step": 423 }, { "epoch": 0.0652282604515211, "grad_norm": 4.382242202758789, "learning_rate": 1.871305418719212e-05, "loss": 1.4342, "step": 424 }, { "epoch": 0.06538210068843506, "grad_norm": 4.234858989715576, "learning_rate": 1.870997536945813e-05, "loss": 1.5888, "step": 425 }, { "epoch": 0.06553594092534902, "grad_norm": 3.8904547691345215, "learning_rate": 1.8706896551724137e-05, "loss": 1.661, "step": 426 }, { "epoch": 0.06568978116226298, "grad_norm": 4.379353046417236, "learning_rate": 1.8703817733990148e-05, "loss": 1.8317, "step": 427 }, { "epoch": 0.06584362139917696, "grad_norm": 4.537791728973389, "learning_rate": 1.870073891625616e-05, "loss": 1.5765, "step": 428 }, { "epoch": 0.06599746163609092, "grad_norm": 4.312771320343018, "learning_rate": 1.869766009852217e-05, "loss": 1.6538, "step": 429 }, { "epoch": 0.06615130187300489, "grad_norm": 4.40094518661499, "learning_rate": 1.869458128078818e-05, "loss": 1.4086, "step": 430 }, { "epoch": 0.06630514210991885, "grad_norm": 4.235193252563477, "learning_rate": 1.869150246305419e-05, "loss": 1.5416, "step": 431 }, { "epoch": 0.06645898234683281, "grad_norm": 4.569365501403809, "learning_rate": 1.86884236453202e-05, "loss": 1.8231, "step": 432 }, { "epoch": 0.06661282258374678, "grad_norm": 4.026181697845459, "learning_rate": 1.868534482758621e-05, "loss": 1.549, "step": 433 }, { "epoch": 0.06676666282066074, "grad_norm": 3.804682493209839, "learning_rate": 1.868226600985222e-05, "loss": 1.5399, "step": 434 }, { "epoch": 0.06692050305757472, "grad_norm": 4.053563117980957, "learning_rate": 1.867918719211823e-05, "loss": 1.1757, "step": 435 }, { "epoch": 0.06707434329448868, "grad_norm": 3.4317290782928467, "learning_rate": 1.867610837438424e-05, "loss": 1.8607, "step": 436 }, { "epoch": 0.06722818353140264, "grad_norm": 3.5456552505493164, "learning_rate": 1.8673029556650248e-05, "loss": 1.5826, "step": 437 }, { "epoch": 0.0673820237683166, "grad_norm": 3.6892943382263184, "learning_rate": 1.8669950738916258e-05, "loss": 1.5194, "step": 438 }, { "epoch": 0.06753586400523057, "grad_norm": 3.839491605758667, "learning_rate": 1.866687192118227e-05, "loss": 1.4445, "step": 439 }, { "epoch": 0.06768970424214453, "grad_norm": 4.359033584594727, "learning_rate": 1.8663793103448276e-05, "loss": 1.5394, "step": 440 }, { "epoch": 0.06784354447905849, "grad_norm": 3.637179374694824, "learning_rate": 1.8660714285714287e-05, "loss": 1.4682, "step": 441 }, { "epoch": 0.06799738471597246, "grad_norm": 4.327478885650635, "learning_rate": 1.8657635467980297e-05, "loss": 1.7219, "step": 442 }, { "epoch": 0.06815122495288643, "grad_norm": 3.4856321811676025, "learning_rate": 1.8654556650246308e-05, "loss": 1.4984, "step": 443 }, { "epoch": 0.0683050651898004, "grad_norm": 3.95900297164917, "learning_rate": 1.8651477832512315e-05, "loss": 1.3877, "step": 444 }, { "epoch": 0.06845890542671436, "grad_norm": 3.925269603729248, "learning_rate": 1.8648399014778326e-05, "loss": 1.7695, "step": 445 }, { "epoch": 0.06861274566362832, "grad_norm": 3.885570526123047, "learning_rate": 1.8645320197044337e-05, "loss": 1.4496, "step": 446 }, { "epoch": 0.06876658590054228, "grad_norm": 4.536112308502197, "learning_rate": 1.8642241379310347e-05, "loss": 1.5128, "step": 447 }, { "epoch": 0.06892042613745625, "grad_norm": 4.987498760223389, "learning_rate": 1.8639162561576354e-05, "loss": 1.4599, "step": 448 }, { "epoch": 0.06907426637437021, "grad_norm": 4.276919364929199, "learning_rate": 1.8636083743842365e-05, "loss": 1.6014, "step": 449 }, { "epoch": 0.06922810661128419, "grad_norm": 3.8465652465820312, "learning_rate": 1.8633004926108376e-05, "loss": 1.7843, "step": 450 }, { "epoch": 0.06938194684819815, "grad_norm": 3.5193631649017334, "learning_rate": 1.8629926108374386e-05, "loss": 1.3468, "step": 451 }, { "epoch": 0.06953578708511211, "grad_norm": 4.1895527839660645, "learning_rate": 1.8626847290640394e-05, "loss": 1.4898, "step": 452 }, { "epoch": 0.06968962732202608, "grad_norm": 3.8893816471099854, "learning_rate": 1.8623768472906404e-05, "loss": 1.3427, "step": 453 }, { "epoch": 0.06984346755894004, "grad_norm": 3.9521751403808594, "learning_rate": 1.8620689655172415e-05, "loss": 1.3767, "step": 454 }, { "epoch": 0.069997307795854, "grad_norm": 4.51972770690918, "learning_rate": 1.8617610837438426e-05, "loss": 1.476, "step": 455 }, { "epoch": 0.07015114803276797, "grad_norm": 3.474942684173584, "learning_rate": 1.8614532019704433e-05, "loss": 1.3196, "step": 456 }, { "epoch": 0.07030498826968193, "grad_norm": 3.1028947830200195, "learning_rate": 1.8611453201970444e-05, "loss": 1.4168, "step": 457 }, { "epoch": 0.0704588285065959, "grad_norm": 3.3937854766845703, "learning_rate": 1.8608374384236454e-05, "loss": 1.6025, "step": 458 }, { "epoch": 0.07061266874350987, "grad_norm": 4.43461275100708, "learning_rate": 1.8605295566502465e-05, "loss": 1.7323, "step": 459 }, { "epoch": 0.07076650898042383, "grad_norm": 3.6207337379455566, "learning_rate": 1.8602216748768472e-05, "loss": 1.1135, "step": 460 }, { "epoch": 0.0709203492173378, "grad_norm": 3.832486629486084, "learning_rate": 1.8599137931034483e-05, "loss": 1.7403, "step": 461 }, { "epoch": 0.07107418945425176, "grad_norm": 3.561846971511841, "learning_rate": 1.8596059113300493e-05, "loss": 1.3177, "step": 462 }, { "epoch": 0.07122802969116572, "grad_norm": 4.648700714111328, "learning_rate": 1.8592980295566504e-05, "loss": 1.5675, "step": 463 }, { "epoch": 0.07138186992807968, "grad_norm": 3.12400221824646, "learning_rate": 1.8589901477832515e-05, "loss": 1.5895, "step": 464 }, { "epoch": 0.07153571016499366, "grad_norm": 4.031516075134277, "learning_rate": 1.8586822660098525e-05, "loss": 1.3117, "step": 465 }, { "epoch": 0.07168955040190762, "grad_norm": 4.2717485427856445, "learning_rate": 1.8583743842364536e-05, "loss": 1.6493, "step": 466 }, { "epoch": 0.07184339063882159, "grad_norm": 4.211914539337158, "learning_rate": 1.8580665024630543e-05, "loss": 1.6635, "step": 467 }, { "epoch": 0.07199723087573555, "grad_norm": 4.723093032836914, "learning_rate": 1.8577586206896554e-05, "loss": 1.3157, "step": 468 }, { "epoch": 0.07215107111264951, "grad_norm": 4.67276668548584, "learning_rate": 1.8574507389162564e-05, "loss": 1.5225, "step": 469 }, { "epoch": 0.07230491134956347, "grad_norm": 4.984416484832764, "learning_rate": 1.8571428571428575e-05, "loss": 1.4456, "step": 470 }, { "epoch": 0.07245875158647744, "grad_norm": 3.4448935985565186, "learning_rate": 1.8568349753694582e-05, "loss": 1.4275, "step": 471 }, { "epoch": 0.07261259182339141, "grad_norm": 3.7218034267425537, "learning_rate": 1.8565270935960593e-05, "loss": 1.4665, "step": 472 }, { "epoch": 0.07276643206030538, "grad_norm": 3.9621286392211914, "learning_rate": 1.8562192118226604e-05, "loss": 1.6227, "step": 473 }, { "epoch": 0.07292027229721934, "grad_norm": 4.022317409515381, "learning_rate": 1.8559113300492614e-05, "loss": 1.6654, "step": 474 }, { "epoch": 0.0730741125341333, "grad_norm": 4.331937313079834, "learning_rate": 1.855603448275862e-05, "loss": 1.7647, "step": 475 }, { "epoch": 0.07322795277104727, "grad_norm": 3.7037270069122314, "learning_rate": 1.8552955665024632e-05, "loss": 1.5641, "step": 476 }, { "epoch": 0.07338179300796123, "grad_norm": 4.3244452476501465, "learning_rate": 1.8549876847290643e-05, "loss": 1.3241, "step": 477 }, { "epoch": 0.07353563324487519, "grad_norm": 3.7647109031677246, "learning_rate": 1.8546798029556654e-05, "loss": 1.5315, "step": 478 }, { "epoch": 0.07368947348178916, "grad_norm": 4.007983207702637, "learning_rate": 1.854371921182266e-05, "loss": 1.1849, "step": 479 }, { "epoch": 0.07384331371870313, "grad_norm": 4.14566707611084, "learning_rate": 1.854064039408867e-05, "loss": 1.6338, "step": 480 }, { "epoch": 0.0739971539556171, "grad_norm": 5.159285545349121, "learning_rate": 1.8537561576354682e-05, "loss": 1.4868, "step": 481 }, { "epoch": 0.07415099419253106, "grad_norm": 3.8821170330047607, "learning_rate": 1.8534482758620693e-05, "loss": 1.4612, "step": 482 }, { "epoch": 0.07430483442944502, "grad_norm": 4.101090431213379, "learning_rate": 1.85314039408867e-05, "loss": 1.6065, "step": 483 }, { "epoch": 0.07445867466635898, "grad_norm": 3.7905161380767822, "learning_rate": 1.852832512315271e-05, "loss": 1.6546, "step": 484 }, { "epoch": 0.07461251490327295, "grad_norm": 4.028254508972168, "learning_rate": 1.852524630541872e-05, "loss": 1.5204, "step": 485 }, { "epoch": 0.07476635514018691, "grad_norm": 3.5728375911712646, "learning_rate": 1.852216748768473e-05, "loss": 1.5172, "step": 486 }, { "epoch": 0.07492019537710089, "grad_norm": 4.131420135498047, "learning_rate": 1.851908866995074e-05, "loss": 1.3946, "step": 487 }, { "epoch": 0.07507403561401485, "grad_norm": 5.084820747375488, "learning_rate": 1.851600985221675e-05, "loss": 1.6008, "step": 488 }, { "epoch": 0.07522787585092881, "grad_norm": 4.371963977813721, "learning_rate": 1.851293103448276e-05, "loss": 1.655, "step": 489 }, { "epoch": 0.07538171608784278, "grad_norm": 4.658143043518066, "learning_rate": 1.8509852216748768e-05, "loss": 1.6966, "step": 490 }, { "epoch": 0.07553555632475674, "grad_norm": 3.156682252883911, "learning_rate": 1.850677339901478e-05, "loss": 1.2678, "step": 491 }, { "epoch": 0.0756893965616707, "grad_norm": 3.4438159465789795, "learning_rate": 1.850369458128079e-05, "loss": 1.3063, "step": 492 }, { "epoch": 0.07584323679858467, "grad_norm": 3.9253177642822266, "learning_rate": 1.85006157635468e-05, "loss": 1.3925, "step": 493 }, { "epoch": 0.07599707703549863, "grad_norm": 3.9431488513946533, "learning_rate": 1.8497536945812807e-05, "loss": 1.6097, "step": 494 }, { "epoch": 0.0761509172724126, "grad_norm": 3.665189743041992, "learning_rate": 1.8494458128078818e-05, "loss": 1.7447, "step": 495 }, { "epoch": 0.07630475750932657, "grad_norm": 3.4875595569610596, "learning_rate": 1.8491379310344828e-05, "loss": 1.5656, "step": 496 }, { "epoch": 0.07645859774624053, "grad_norm": 4.597902297973633, "learning_rate": 1.848830049261084e-05, "loss": 1.332, "step": 497 }, { "epoch": 0.0766124379831545, "grad_norm": 4.29017972946167, "learning_rate": 1.848522167487685e-05, "loss": 1.8033, "step": 498 }, { "epoch": 0.07676627822006846, "grad_norm": 3.4772064685821533, "learning_rate": 1.848214285714286e-05, "loss": 1.6527, "step": 499 }, { "epoch": 0.07692011845698242, "grad_norm": 3.6495518684387207, "learning_rate": 1.847906403940887e-05, "loss": 1.569, "step": 500 }, { "epoch": 0.07707395869389638, "grad_norm": 3.7781736850738525, "learning_rate": 1.8475985221674878e-05, "loss": 1.4927, "step": 501 }, { "epoch": 0.07722779893081036, "grad_norm": 3.8614799976348877, "learning_rate": 1.847290640394089e-05, "loss": 1.5866, "step": 502 }, { "epoch": 0.07738163916772432, "grad_norm": 4.854774475097656, "learning_rate": 1.84698275862069e-05, "loss": 1.3599, "step": 503 }, { "epoch": 0.07753547940463829, "grad_norm": 3.85322642326355, "learning_rate": 1.846674876847291e-05, "loss": 1.4672, "step": 504 }, { "epoch": 0.07768931964155225, "grad_norm": 3.792553424835205, "learning_rate": 1.8463669950738917e-05, "loss": 1.4416, "step": 505 }, { "epoch": 0.07784315987846621, "grad_norm": 3.766540050506592, "learning_rate": 1.8460591133004928e-05, "loss": 1.6882, "step": 506 }, { "epoch": 0.07799700011538017, "grad_norm": 3.8239810466766357, "learning_rate": 1.845751231527094e-05, "loss": 1.6036, "step": 507 }, { "epoch": 0.07815084035229414, "grad_norm": 3.615023374557495, "learning_rate": 1.845443349753695e-05, "loss": 1.5244, "step": 508 }, { "epoch": 0.0783046805892081, "grad_norm": 4.302548885345459, "learning_rate": 1.8451354679802956e-05, "loss": 1.5332, "step": 509 }, { "epoch": 0.07845852082612208, "grad_norm": 3.951646089553833, "learning_rate": 1.8448275862068967e-05, "loss": 1.2321, "step": 510 }, { "epoch": 0.07861236106303604, "grad_norm": 4.175218105316162, "learning_rate": 1.8445197044334978e-05, "loss": 1.4433, "step": 511 }, { "epoch": 0.07876620129995, "grad_norm": 4.084559917449951, "learning_rate": 1.844211822660099e-05, "loss": 1.5958, "step": 512 }, { "epoch": 0.07892004153686397, "grad_norm": 4.585322380065918, "learning_rate": 1.8439039408866996e-05, "loss": 1.551, "step": 513 }, { "epoch": 0.07907388177377793, "grad_norm": 4.340857028961182, "learning_rate": 1.8435960591133006e-05, "loss": 1.6795, "step": 514 }, { "epoch": 0.07922772201069189, "grad_norm": 3.998213291168213, "learning_rate": 1.8432881773399017e-05, "loss": 1.4605, "step": 515 }, { "epoch": 0.07938156224760586, "grad_norm": 4.701998710632324, "learning_rate": 1.8429802955665028e-05, "loss": 1.2896, "step": 516 }, { "epoch": 0.07953540248451983, "grad_norm": 3.818695068359375, "learning_rate": 1.8426724137931035e-05, "loss": 1.6112, "step": 517 }, { "epoch": 0.0796892427214338, "grad_norm": 3.6180856227874756, "learning_rate": 1.8423645320197045e-05, "loss": 1.4404, "step": 518 }, { "epoch": 0.07984308295834776, "grad_norm": 4.014054775238037, "learning_rate": 1.8420566502463056e-05, "loss": 1.433, "step": 519 }, { "epoch": 0.07999692319526172, "grad_norm": 3.6161677837371826, "learning_rate": 1.8417487684729067e-05, "loss": 1.6765, "step": 520 }, { "epoch": 0.08015076343217568, "grad_norm": 3.9025638103485107, "learning_rate": 1.8414408866995074e-05, "loss": 1.4603, "step": 521 }, { "epoch": 0.08030460366908965, "grad_norm": 4.459023475646973, "learning_rate": 1.8411330049261085e-05, "loss": 1.3532, "step": 522 }, { "epoch": 0.08045844390600361, "grad_norm": 4.244007587432861, "learning_rate": 1.8408251231527095e-05, "loss": 1.596, "step": 523 }, { "epoch": 0.08061228414291759, "grad_norm": 3.692716121673584, "learning_rate": 1.8405172413793106e-05, "loss": 1.681, "step": 524 }, { "epoch": 0.08076612437983155, "grad_norm": 3.994295120239258, "learning_rate": 1.8402093596059113e-05, "loss": 1.6406, "step": 525 }, { "epoch": 0.08091996461674551, "grad_norm": 4.235057830810547, "learning_rate": 1.8399014778325124e-05, "loss": 1.6273, "step": 526 }, { "epoch": 0.08107380485365948, "grad_norm": 3.85309100151062, "learning_rate": 1.8395935960591134e-05, "loss": 1.6481, "step": 527 }, { "epoch": 0.08122764509057344, "grad_norm": 3.813279151916504, "learning_rate": 1.8392857142857142e-05, "loss": 1.4383, "step": 528 }, { "epoch": 0.0813814853274874, "grad_norm": 4.100255966186523, "learning_rate": 1.8389778325123152e-05, "loss": 1.5082, "step": 529 }, { "epoch": 0.08153532556440136, "grad_norm": 4.0153350830078125, "learning_rate": 1.8386699507389163e-05, "loss": 1.2057, "step": 530 }, { "epoch": 0.08168916580131533, "grad_norm": 3.772224187850952, "learning_rate": 1.8383620689655174e-05, "loss": 1.5451, "step": 531 }, { "epoch": 0.0818430060382293, "grad_norm": 4.265544891357422, "learning_rate": 1.8380541871921184e-05, "loss": 1.4576, "step": 532 }, { "epoch": 0.08199684627514327, "grad_norm": 4.343531608581543, "learning_rate": 1.8377463054187195e-05, "loss": 1.6285, "step": 533 }, { "epoch": 0.08215068651205723, "grad_norm": 4.309127330780029, "learning_rate": 1.8374384236453206e-05, "loss": 1.4315, "step": 534 }, { "epoch": 0.0823045267489712, "grad_norm": 4.200425148010254, "learning_rate": 1.8371305418719213e-05, "loss": 1.5274, "step": 535 }, { "epoch": 0.08245836698588516, "grad_norm": 4.62114143371582, "learning_rate": 1.8368226600985224e-05, "loss": 1.4776, "step": 536 }, { "epoch": 0.08261220722279912, "grad_norm": 3.631909132003784, "learning_rate": 1.8365147783251234e-05, "loss": 1.4128, "step": 537 }, { "epoch": 0.08276604745971308, "grad_norm": 3.9654574394226074, "learning_rate": 1.8362068965517245e-05, "loss": 1.903, "step": 538 }, { "epoch": 0.08291988769662706, "grad_norm": 4.848973751068115, "learning_rate": 1.8358990147783252e-05, "loss": 1.2159, "step": 539 }, { "epoch": 0.08307372793354102, "grad_norm": 4.3561015129089355, "learning_rate": 1.8355911330049263e-05, "loss": 1.4635, "step": 540 }, { "epoch": 0.08322756817045499, "grad_norm": 3.632338047027588, "learning_rate": 1.8352832512315273e-05, "loss": 1.6328, "step": 541 }, { "epoch": 0.08338140840736895, "grad_norm": 3.3306849002838135, "learning_rate": 1.8349753694581284e-05, "loss": 1.4317, "step": 542 }, { "epoch": 0.08353524864428291, "grad_norm": 4.038285732269287, "learning_rate": 1.834667487684729e-05, "loss": 1.567, "step": 543 }, { "epoch": 0.08368908888119687, "grad_norm": 3.474614143371582, "learning_rate": 1.8343596059113302e-05, "loss": 1.4879, "step": 544 }, { "epoch": 0.08384292911811084, "grad_norm": 4.039064407348633, "learning_rate": 1.8340517241379313e-05, "loss": 1.5787, "step": 545 }, { "epoch": 0.0839967693550248, "grad_norm": 4.368943691253662, "learning_rate": 1.8337438423645323e-05, "loss": 1.4659, "step": 546 }, { "epoch": 0.08415060959193878, "grad_norm": 4.150062084197998, "learning_rate": 1.833435960591133e-05, "loss": 1.5162, "step": 547 }, { "epoch": 0.08430444982885274, "grad_norm": 4.541062831878662, "learning_rate": 1.833128078817734e-05, "loss": 1.6622, "step": 548 }, { "epoch": 0.0844582900657667, "grad_norm": 3.6473052501678467, "learning_rate": 1.8328201970443352e-05, "loss": 1.4576, "step": 549 }, { "epoch": 0.08461213030268067, "grad_norm": 4.237256050109863, "learning_rate": 1.8325123152709362e-05, "loss": 1.7281, "step": 550 }, { "epoch": 0.08476597053959463, "grad_norm": 3.2358641624450684, "learning_rate": 1.832204433497537e-05, "loss": 1.3348, "step": 551 }, { "epoch": 0.08491981077650859, "grad_norm": 3.7876458168029785, "learning_rate": 1.831896551724138e-05, "loss": 1.6042, "step": 552 }, { "epoch": 0.08507365101342255, "grad_norm": 4.505400657653809, "learning_rate": 1.831588669950739e-05, "loss": 1.6037, "step": 553 }, { "epoch": 0.08522749125033653, "grad_norm": 4.112180709838867, "learning_rate": 1.83128078817734e-05, "loss": 1.5886, "step": 554 }, { "epoch": 0.0853813314872505, "grad_norm": 3.326692581176758, "learning_rate": 1.830972906403941e-05, "loss": 1.4056, "step": 555 }, { "epoch": 0.08553517172416446, "grad_norm": 4.762342929840088, "learning_rate": 1.830665024630542e-05, "loss": 1.6628, "step": 556 }, { "epoch": 0.08568901196107842, "grad_norm": 3.987135887145996, "learning_rate": 1.830357142857143e-05, "loss": 1.6612, "step": 557 }, { "epoch": 0.08584285219799238, "grad_norm": 3.768615961074829, "learning_rate": 1.830049261083744e-05, "loss": 1.6648, "step": 558 }, { "epoch": 0.08599669243490635, "grad_norm": 4.081706523895264, "learning_rate": 1.8297413793103448e-05, "loss": 1.6518, "step": 559 }, { "epoch": 0.08615053267182031, "grad_norm": 4.357606410980225, "learning_rate": 1.829433497536946e-05, "loss": 1.683, "step": 560 }, { "epoch": 0.08630437290873427, "grad_norm": 4.174715518951416, "learning_rate": 1.829125615763547e-05, "loss": 1.4303, "step": 561 }, { "epoch": 0.08645821314564825, "grad_norm": 4.226166248321533, "learning_rate": 1.828817733990148e-05, "loss": 1.3969, "step": 562 }, { "epoch": 0.08661205338256221, "grad_norm": 3.8853116035461426, "learning_rate": 1.8285098522167487e-05, "loss": 1.5501, "step": 563 }, { "epoch": 0.08676589361947618, "grad_norm": 4.101150035858154, "learning_rate": 1.8282019704433498e-05, "loss": 1.4864, "step": 564 }, { "epoch": 0.08691973385639014, "grad_norm": 3.6429593563079834, "learning_rate": 1.827894088669951e-05, "loss": 1.5526, "step": 565 }, { "epoch": 0.0870735740933041, "grad_norm": 3.7325403690338135, "learning_rate": 1.827586206896552e-05, "loss": 1.6112, "step": 566 }, { "epoch": 0.08722741433021806, "grad_norm": 3.2195584774017334, "learning_rate": 1.827278325123153e-05, "loss": 1.5922, "step": 567 }, { "epoch": 0.08738125456713203, "grad_norm": 3.1899948120117188, "learning_rate": 1.826970443349754e-05, "loss": 1.5044, "step": 568 }, { "epoch": 0.087535094804046, "grad_norm": 3.803370952606201, "learning_rate": 1.8266625615763548e-05, "loss": 1.5006, "step": 569 }, { "epoch": 0.08768893504095997, "grad_norm": 3.464211940765381, "learning_rate": 1.826354679802956e-05, "loss": 1.5241, "step": 570 }, { "epoch": 0.08784277527787393, "grad_norm": 4.148252010345459, "learning_rate": 1.826046798029557e-05, "loss": 1.6246, "step": 571 }, { "epoch": 0.0879966155147879, "grad_norm": 3.4671688079833984, "learning_rate": 1.825738916256158e-05, "loss": 1.5151, "step": 572 }, { "epoch": 0.08815045575170186, "grad_norm": 3.8084187507629395, "learning_rate": 1.8254310344827587e-05, "loss": 1.437, "step": 573 }, { "epoch": 0.08830429598861582, "grad_norm": 3.750927448272705, "learning_rate": 1.8251231527093598e-05, "loss": 1.4681, "step": 574 }, { "epoch": 0.08845813622552978, "grad_norm": 4.334985733032227, "learning_rate": 1.8248152709359608e-05, "loss": 1.2873, "step": 575 }, { "epoch": 0.08861197646244376, "grad_norm": 4.085562705993652, "learning_rate": 1.824507389162562e-05, "loss": 1.2751, "step": 576 }, { "epoch": 0.08876581669935772, "grad_norm": 3.463196039199829, "learning_rate": 1.8241995073891626e-05, "loss": 1.3313, "step": 577 }, { "epoch": 0.08891965693627168, "grad_norm": 4.156436920166016, "learning_rate": 1.8238916256157637e-05, "loss": 1.4551, "step": 578 }, { "epoch": 0.08907349717318565, "grad_norm": 4.7733154296875, "learning_rate": 1.8235837438423647e-05, "loss": 1.437, "step": 579 }, { "epoch": 0.08922733741009961, "grad_norm": 3.952685832977295, "learning_rate": 1.8232758620689658e-05, "loss": 1.5049, "step": 580 }, { "epoch": 0.08938117764701357, "grad_norm": 3.635544776916504, "learning_rate": 1.8229679802955665e-05, "loss": 1.2637, "step": 581 }, { "epoch": 0.08953501788392754, "grad_norm": 3.7176291942596436, "learning_rate": 1.8226600985221676e-05, "loss": 1.5124, "step": 582 }, { "epoch": 0.0896888581208415, "grad_norm": 4.3880534172058105, "learning_rate": 1.8223522167487687e-05, "loss": 1.6155, "step": 583 }, { "epoch": 0.08984269835775548, "grad_norm": 3.556973695755005, "learning_rate": 1.8220443349753697e-05, "loss": 1.4774, "step": 584 }, { "epoch": 0.08999653859466944, "grad_norm": 3.8446927070617676, "learning_rate": 1.8217364532019704e-05, "loss": 1.5798, "step": 585 }, { "epoch": 0.0901503788315834, "grad_norm": 4.487414360046387, "learning_rate": 1.8214285714285715e-05, "loss": 1.5845, "step": 586 }, { "epoch": 0.09030421906849737, "grad_norm": 4.245489120483398, "learning_rate": 1.8211206896551726e-05, "loss": 1.7388, "step": 587 }, { "epoch": 0.09045805930541133, "grad_norm": 3.5867862701416016, "learning_rate": 1.8208128078817736e-05, "loss": 1.5437, "step": 588 }, { "epoch": 0.09061189954232529, "grad_norm": 3.804252862930298, "learning_rate": 1.8205049261083744e-05, "loss": 1.468, "step": 589 }, { "epoch": 0.09076573977923925, "grad_norm": 4.317119121551514, "learning_rate": 1.8201970443349754e-05, "loss": 1.5353, "step": 590 }, { "epoch": 0.09091958001615323, "grad_norm": 4.333464622497559, "learning_rate": 1.8198891625615765e-05, "loss": 1.6885, "step": 591 }, { "epoch": 0.0910734202530672, "grad_norm": 4.669312000274658, "learning_rate": 1.8195812807881776e-05, "loss": 1.3527, "step": 592 }, { "epoch": 0.09122726048998116, "grad_norm": 4.343209266662598, "learning_rate": 1.8192733990147783e-05, "loss": 1.498, "step": 593 }, { "epoch": 0.09138110072689512, "grad_norm": 3.2082502841949463, "learning_rate": 1.8189655172413793e-05, "loss": 1.4946, "step": 594 }, { "epoch": 0.09153494096380908, "grad_norm": 3.993605375289917, "learning_rate": 1.8186576354679804e-05, "loss": 1.3995, "step": 595 }, { "epoch": 0.09168878120072305, "grad_norm": 3.733123779296875, "learning_rate": 1.8183497536945815e-05, "loss": 1.3795, "step": 596 }, { "epoch": 0.09184262143763701, "grad_norm": 3.867670774459839, "learning_rate": 1.8180418719211822e-05, "loss": 1.4276, "step": 597 }, { "epoch": 0.09199646167455097, "grad_norm": 4.3467793464660645, "learning_rate": 1.8177339901477833e-05, "loss": 1.5731, "step": 598 }, { "epoch": 0.09215030191146495, "grad_norm": 4.1678547859191895, "learning_rate": 1.8174261083743843e-05, "loss": 1.4547, "step": 599 }, { "epoch": 0.09230414214837891, "grad_norm": 4.363110542297363, "learning_rate": 1.8171182266009854e-05, "loss": 1.5212, "step": 600 }, { "epoch": 0.09245798238529288, "grad_norm": 4.603112697601318, "learning_rate": 1.8168103448275865e-05, "loss": 1.2703, "step": 601 }, { "epoch": 0.09261182262220684, "grad_norm": 4.054928779602051, "learning_rate": 1.8165024630541875e-05, "loss": 1.3317, "step": 602 }, { "epoch": 0.0927656628591208, "grad_norm": 4.239939212799072, "learning_rate": 1.8161945812807883e-05, "loss": 1.3412, "step": 603 }, { "epoch": 0.09291950309603476, "grad_norm": 3.8205838203430176, "learning_rate": 1.8158866995073893e-05, "loss": 1.6124, "step": 604 }, { "epoch": 0.09307334333294873, "grad_norm": 3.6218254566192627, "learning_rate": 1.8155788177339904e-05, "loss": 1.5891, "step": 605 }, { "epoch": 0.0932271835698627, "grad_norm": 3.622302770614624, "learning_rate": 1.8152709359605914e-05, "loss": 1.7954, "step": 606 }, { "epoch": 0.09338102380677667, "grad_norm": 4.801969051361084, "learning_rate": 1.8149630541871922e-05, "loss": 1.6857, "step": 607 }, { "epoch": 0.09353486404369063, "grad_norm": 4.242020606994629, "learning_rate": 1.8146551724137932e-05, "loss": 1.3566, "step": 608 }, { "epoch": 0.09368870428060459, "grad_norm": 3.6588668823242188, "learning_rate": 1.8143472906403943e-05, "loss": 1.6655, "step": 609 }, { "epoch": 0.09384254451751856, "grad_norm": 3.4407174587249756, "learning_rate": 1.8140394088669954e-05, "loss": 1.2685, "step": 610 }, { "epoch": 0.09399638475443252, "grad_norm": 3.747307777404785, "learning_rate": 1.813731527093596e-05, "loss": 1.6016, "step": 611 }, { "epoch": 0.09415022499134648, "grad_norm": 3.238820791244507, "learning_rate": 1.813423645320197e-05, "loss": 1.4528, "step": 612 }, { "epoch": 0.09430406522826044, "grad_norm": 4.018573760986328, "learning_rate": 1.8131157635467982e-05, "loss": 1.3135, "step": 613 }, { "epoch": 0.09445790546517442, "grad_norm": 3.5733039379119873, "learning_rate": 1.8128078817733993e-05, "loss": 1.8767, "step": 614 }, { "epoch": 0.09461174570208838, "grad_norm": 4.342269420623779, "learning_rate": 1.8125e-05, "loss": 1.4575, "step": 615 }, { "epoch": 0.09476558593900235, "grad_norm": 3.208928346633911, "learning_rate": 1.812192118226601e-05, "loss": 1.5683, "step": 616 }, { "epoch": 0.09491942617591631, "grad_norm": 4.195964336395264, "learning_rate": 1.811884236453202e-05, "loss": 1.6212, "step": 617 }, { "epoch": 0.09507326641283027, "grad_norm": 3.739165782928467, "learning_rate": 1.8115763546798032e-05, "loss": 1.4557, "step": 618 }, { "epoch": 0.09522710664974424, "grad_norm": 3.108948230743408, "learning_rate": 1.811268472906404e-05, "loss": 1.4143, "step": 619 }, { "epoch": 0.0953809468866582, "grad_norm": 4.157646179199219, "learning_rate": 1.810960591133005e-05, "loss": 1.7216, "step": 620 }, { "epoch": 0.09553478712357218, "grad_norm": 3.826050043106079, "learning_rate": 1.810652709359606e-05, "loss": 1.1897, "step": 621 }, { "epoch": 0.09568862736048614, "grad_norm": 3.7091331481933594, "learning_rate": 1.810344827586207e-05, "loss": 1.5873, "step": 622 }, { "epoch": 0.0958424675974001, "grad_norm": 3.8819079399108887, "learning_rate": 1.810036945812808e-05, "loss": 1.2854, "step": 623 }, { "epoch": 0.09599630783431407, "grad_norm": 4.413211822509766, "learning_rate": 1.809729064039409e-05, "loss": 1.1729, "step": 624 }, { "epoch": 0.09615014807122803, "grad_norm": 3.684490442276001, "learning_rate": 1.80942118226601e-05, "loss": 1.3249, "step": 625 }, { "epoch": 0.09630398830814199, "grad_norm": 4.3151936531066895, "learning_rate": 1.809113300492611e-05, "loss": 1.4392, "step": 626 }, { "epoch": 0.09645782854505595, "grad_norm": 4.262016296386719, "learning_rate": 1.8088054187192118e-05, "loss": 1.4042, "step": 627 }, { "epoch": 0.09661166878196993, "grad_norm": 3.711725950241089, "learning_rate": 1.808497536945813e-05, "loss": 1.4401, "step": 628 }, { "epoch": 0.0967655090188839, "grad_norm": 4.0023651123046875, "learning_rate": 1.808189655172414e-05, "loss": 1.5463, "step": 629 }, { "epoch": 0.09691934925579786, "grad_norm": 4.425678253173828, "learning_rate": 1.807881773399015e-05, "loss": 1.3396, "step": 630 }, { "epoch": 0.09707318949271182, "grad_norm": 3.5439465045928955, "learning_rate": 1.8075738916256157e-05, "loss": 1.7281, "step": 631 }, { "epoch": 0.09722702972962578, "grad_norm": 4.435723781585693, "learning_rate": 1.807266009852217e-05, "loss": 1.4327, "step": 632 }, { "epoch": 0.09738086996653975, "grad_norm": 4.0606465339660645, "learning_rate": 1.8069581280788178e-05, "loss": 1.705, "step": 633 }, { "epoch": 0.09753471020345371, "grad_norm": 4.4206438064575195, "learning_rate": 1.806650246305419e-05, "loss": 1.3571, "step": 634 }, { "epoch": 0.09768855044036767, "grad_norm": 4.030638694763184, "learning_rate": 1.80634236453202e-05, "loss": 1.6904, "step": 635 }, { "epoch": 0.09784239067728165, "grad_norm": 3.747878313064575, "learning_rate": 1.806034482758621e-05, "loss": 1.5331, "step": 636 }, { "epoch": 0.09799623091419561, "grad_norm": 3.272019147872925, "learning_rate": 1.8057266009852217e-05, "loss": 1.3827, "step": 637 }, { "epoch": 0.09815007115110957, "grad_norm": 3.5450096130371094, "learning_rate": 1.8054187192118228e-05, "loss": 1.6931, "step": 638 }, { "epoch": 0.09830391138802354, "grad_norm": 3.412210464477539, "learning_rate": 1.805110837438424e-05, "loss": 1.614, "step": 639 }, { "epoch": 0.0984577516249375, "grad_norm": 4.386414527893066, "learning_rate": 1.804802955665025e-05, "loss": 1.4981, "step": 640 }, { "epoch": 0.09861159186185146, "grad_norm": 4.703189373016357, "learning_rate": 1.8044950738916257e-05, "loss": 1.5412, "step": 641 }, { "epoch": 0.09876543209876543, "grad_norm": 3.8223092555999756, "learning_rate": 1.8041871921182267e-05, "loss": 1.4365, "step": 642 }, { "epoch": 0.0989192723356794, "grad_norm": 3.4148952960968018, "learning_rate": 1.8038793103448278e-05, "loss": 1.4329, "step": 643 }, { "epoch": 0.09907311257259337, "grad_norm": 2.973548412322998, "learning_rate": 1.803571428571429e-05, "loss": 1.3079, "step": 644 }, { "epoch": 0.09922695280950733, "grad_norm": 4.636074542999268, "learning_rate": 1.8032635467980296e-05, "loss": 1.5499, "step": 645 }, { "epoch": 0.09938079304642129, "grad_norm": 3.376358985900879, "learning_rate": 1.8029556650246306e-05, "loss": 1.523, "step": 646 }, { "epoch": 0.09953463328333526, "grad_norm": 3.9303550720214844, "learning_rate": 1.8026477832512317e-05, "loss": 1.5885, "step": 647 }, { "epoch": 0.09968847352024922, "grad_norm": 3.984908103942871, "learning_rate": 1.8023399014778328e-05, "loss": 1.6887, "step": 648 }, { "epoch": 0.09984231375716318, "grad_norm": 3.805101156234741, "learning_rate": 1.8020320197044335e-05, "loss": 1.6359, "step": 649 }, { "epoch": 0.09999615399407714, "grad_norm": 3.75333309173584, "learning_rate": 1.8017241379310346e-05, "loss": 1.6747, "step": 650 }, { "epoch": 0.10014999423099112, "grad_norm": 4.0502448081970215, "learning_rate": 1.8014162561576356e-05, "loss": 1.6084, "step": 651 }, { "epoch": 0.10030383446790508, "grad_norm": 3.8165245056152344, "learning_rate": 1.8011083743842367e-05, "loss": 1.4605, "step": 652 }, { "epoch": 0.10045767470481905, "grad_norm": 3.8906097412109375, "learning_rate": 1.8008004926108374e-05, "loss": 1.524, "step": 653 }, { "epoch": 0.10061151494173301, "grad_norm": 3.900426149368286, "learning_rate": 1.8004926108374385e-05, "loss": 1.5576, "step": 654 }, { "epoch": 0.10076535517864697, "grad_norm": 3.698136568069458, "learning_rate": 1.8001847290640395e-05, "loss": 1.4582, "step": 655 }, { "epoch": 0.10091919541556094, "grad_norm": 3.81986927986145, "learning_rate": 1.7998768472906406e-05, "loss": 1.7482, "step": 656 }, { "epoch": 0.1010730356524749, "grad_norm": 3.780177593231201, "learning_rate": 1.7995689655172413e-05, "loss": 1.4345, "step": 657 }, { "epoch": 0.10122687588938888, "grad_norm": 4.204930305480957, "learning_rate": 1.7992610837438424e-05, "loss": 1.2327, "step": 658 }, { "epoch": 0.10138071612630284, "grad_norm": 4.495303153991699, "learning_rate": 1.7989532019704435e-05, "loss": 1.8026, "step": 659 }, { "epoch": 0.1015345563632168, "grad_norm": 3.7204806804656982, "learning_rate": 1.7986453201970445e-05, "loss": 1.5381, "step": 660 }, { "epoch": 0.10168839660013076, "grad_norm": 4.054187297821045, "learning_rate": 1.7983374384236453e-05, "loss": 1.4699, "step": 661 }, { "epoch": 0.10184223683704473, "grad_norm": 3.7656993865966797, "learning_rate": 1.7980295566502463e-05, "loss": 1.3134, "step": 662 }, { "epoch": 0.10199607707395869, "grad_norm": 4.748908996582031, "learning_rate": 1.7977216748768474e-05, "loss": 1.3955, "step": 663 }, { "epoch": 0.10214991731087265, "grad_norm": 3.5862481594085693, "learning_rate": 1.7974137931034484e-05, "loss": 1.313, "step": 664 }, { "epoch": 0.10230375754778662, "grad_norm": 3.3353700637817383, "learning_rate": 1.7971059113300492e-05, "loss": 1.2493, "step": 665 }, { "epoch": 0.1024575977847006, "grad_norm": 3.6814496517181396, "learning_rate": 1.7967980295566506e-05, "loss": 1.4728, "step": 666 }, { "epoch": 0.10261143802161456, "grad_norm": 4.010184288024902, "learning_rate": 1.7964901477832516e-05, "loss": 1.5457, "step": 667 }, { "epoch": 0.10276527825852852, "grad_norm": 4.257790565490723, "learning_rate": 1.7961822660098524e-05, "loss": 1.3827, "step": 668 }, { "epoch": 0.10291911849544248, "grad_norm": 3.888066053390503, "learning_rate": 1.7958743842364534e-05, "loss": 1.5413, "step": 669 }, { "epoch": 0.10307295873235645, "grad_norm": 3.519183874130249, "learning_rate": 1.7955665024630545e-05, "loss": 1.4575, "step": 670 }, { "epoch": 0.10322679896927041, "grad_norm": 3.0086593627929688, "learning_rate": 1.7952586206896556e-05, "loss": 1.1663, "step": 671 }, { "epoch": 0.10338063920618437, "grad_norm": 4.615567207336426, "learning_rate": 1.7949507389162563e-05, "loss": 1.5659, "step": 672 }, { "epoch": 0.10353447944309835, "grad_norm": 4.6981658935546875, "learning_rate": 1.7946428571428573e-05, "loss": 1.562, "step": 673 }, { "epoch": 0.10368831968001231, "grad_norm": 3.609311580657959, "learning_rate": 1.7943349753694584e-05, "loss": 1.6936, "step": 674 }, { "epoch": 0.10384215991692627, "grad_norm": 3.683351993560791, "learning_rate": 1.7940270935960595e-05, "loss": 1.6866, "step": 675 }, { "epoch": 0.10399600015384024, "grad_norm": 4.026793479919434, "learning_rate": 1.7937192118226602e-05, "loss": 1.5467, "step": 676 }, { "epoch": 0.1041498403907542, "grad_norm": 4.725186824798584, "learning_rate": 1.7934113300492613e-05, "loss": 1.7207, "step": 677 }, { "epoch": 0.10430368062766816, "grad_norm": 3.4378514289855957, "learning_rate": 1.7931034482758623e-05, "loss": 1.5415, "step": 678 }, { "epoch": 0.10445752086458213, "grad_norm": 3.8985788822174072, "learning_rate": 1.792795566502463e-05, "loss": 1.3542, "step": 679 }, { "epoch": 0.1046113611014961, "grad_norm": 3.2677042484283447, "learning_rate": 1.792487684729064e-05, "loss": 1.3648, "step": 680 }, { "epoch": 0.10476520133841007, "grad_norm": 4.360880374908447, "learning_rate": 1.7921798029556652e-05, "loss": 1.2462, "step": 681 }, { "epoch": 0.10491904157532403, "grad_norm": 4.124327182769775, "learning_rate": 1.7918719211822663e-05, "loss": 1.5887, "step": 682 }, { "epoch": 0.10507288181223799, "grad_norm": 4.4300947189331055, "learning_rate": 1.791564039408867e-05, "loss": 1.5984, "step": 683 }, { "epoch": 0.10522672204915196, "grad_norm": 3.8309237957000732, "learning_rate": 1.791256157635468e-05, "loss": 1.4211, "step": 684 }, { "epoch": 0.10538056228606592, "grad_norm": 3.9575023651123047, "learning_rate": 1.790948275862069e-05, "loss": 1.6286, "step": 685 }, { "epoch": 0.10553440252297988, "grad_norm": 3.955641508102417, "learning_rate": 1.7906403940886702e-05, "loss": 1.8192, "step": 686 }, { "epoch": 0.10568824275989384, "grad_norm": 3.408968687057495, "learning_rate": 1.790332512315271e-05, "loss": 1.504, "step": 687 }, { "epoch": 0.10584208299680782, "grad_norm": 3.520569324493408, "learning_rate": 1.790024630541872e-05, "loss": 1.6778, "step": 688 }, { "epoch": 0.10599592323372178, "grad_norm": 3.8056299686431885, "learning_rate": 1.789716748768473e-05, "loss": 1.2028, "step": 689 }, { "epoch": 0.10614976347063575, "grad_norm": 4.83513069152832, "learning_rate": 1.789408866995074e-05, "loss": 1.7497, "step": 690 }, { "epoch": 0.10630360370754971, "grad_norm": 3.2915914058685303, "learning_rate": 1.7891009852216748e-05, "loss": 1.3943, "step": 691 }, { "epoch": 0.10645744394446367, "grad_norm": 4.4447431564331055, "learning_rate": 1.788793103448276e-05, "loss": 1.5351, "step": 692 }, { "epoch": 0.10661128418137764, "grad_norm": 3.23991060256958, "learning_rate": 1.788485221674877e-05, "loss": 1.3565, "step": 693 }, { "epoch": 0.1067651244182916, "grad_norm": 4.509555816650391, "learning_rate": 1.788177339901478e-05, "loss": 1.4744, "step": 694 }, { "epoch": 0.10691896465520558, "grad_norm": 3.879281520843506, "learning_rate": 1.7878694581280787e-05, "loss": 1.6076, "step": 695 }, { "epoch": 0.10707280489211954, "grad_norm": 4.123989105224609, "learning_rate": 1.7875615763546798e-05, "loss": 1.183, "step": 696 }, { "epoch": 0.1072266451290335, "grad_norm": 3.286714792251587, "learning_rate": 1.787253694581281e-05, "loss": 1.213, "step": 697 }, { "epoch": 0.10738048536594746, "grad_norm": 4.429646968841553, "learning_rate": 1.786945812807882e-05, "loss": 1.4088, "step": 698 }, { "epoch": 0.10753432560286143, "grad_norm": 4.006320476531982, "learning_rate": 1.7866379310344827e-05, "loss": 1.7059, "step": 699 }, { "epoch": 0.10768816583977539, "grad_norm": 4.014772415161133, "learning_rate": 1.786330049261084e-05, "loss": 1.4406, "step": 700 }, { "epoch": 0.10784200607668935, "grad_norm": 4.421397686004639, "learning_rate": 1.786022167487685e-05, "loss": 1.382, "step": 701 }, { "epoch": 0.10799584631360332, "grad_norm": 3.8976025581359863, "learning_rate": 1.785714285714286e-05, "loss": 1.5482, "step": 702 }, { "epoch": 0.1081496865505173, "grad_norm": 3.944425106048584, "learning_rate": 1.785406403940887e-05, "loss": 1.6139, "step": 703 }, { "epoch": 0.10830352678743126, "grad_norm": 4.105767250061035, "learning_rate": 1.785098522167488e-05, "loss": 1.351, "step": 704 }, { "epoch": 0.10845736702434522, "grad_norm": 4.143132209777832, "learning_rate": 1.784790640394089e-05, "loss": 1.5485, "step": 705 }, { "epoch": 0.10861120726125918, "grad_norm": 3.90205979347229, "learning_rate": 1.7844827586206898e-05, "loss": 1.5033, "step": 706 }, { "epoch": 0.10876504749817315, "grad_norm": 3.4835164546966553, "learning_rate": 1.784174876847291e-05, "loss": 1.5629, "step": 707 }, { "epoch": 0.10891888773508711, "grad_norm": 3.8839621543884277, "learning_rate": 1.783866995073892e-05, "loss": 1.4407, "step": 708 }, { "epoch": 0.10907272797200107, "grad_norm": 4.178622245788574, "learning_rate": 1.783559113300493e-05, "loss": 1.577, "step": 709 }, { "epoch": 0.10922656820891505, "grad_norm": 3.9331376552581787, "learning_rate": 1.7832512315270937e-05, "loss": 1.1467, "step": 710 }, { "epoch": 0.10938040844582901, "grad_norm": 3.465369701385498, "learning_rate": 1.7829433497536948e-05, "loss": 1.6689, "step": 711 }, { "epoch": 0.10953424868274297, "grad_norm": 4.464198589324951, "learning_rate": 1.7826354679802958e-05, "loss": 1.4435, "step": 712 }, { "epoch": 0.10968808891965694, "grad_norm": 4.16334867477417, "learning_rate": 1.782327586206897e-05, "loss": 1.534, "step": 713 }, { "epoch": 0.1098419291565709, "grad_norm": 3.469987630844116, "learning_rate": 1.7820197044334976e-05, "loss": 1.4331, "step": 714 }, { "epoch": 0.10999576939348486, "grad_norm": 3.4007136821746826, "learning_rate": 1.7817118226600987e-05, "loss": 1.3707, "step": 715 }, { "epoch": 0.11014960963039883, "grad_norm": 3.7211365699768066, "learning_rate": 1.7814039408866997e-05, "loss": 1.2631, "step": 716 }, { "epoch": 0.11030344986731279, "grad_norm": 3.528674602508545, "learning_rate": 1.7810960591133008e-05, "loss": 1.3379, "step": 717 }, { "epoch": 0.11045729010422677, "grad_norm": 4.137120246887207, "learning_rate": 1.7807881773399015e-05, "loss": 1.4253, "step": 718 }, { "epoch": 0.11061113034114073, "grad_norm": 3.7564826011657715, "learning_rate": 1.7804802955665026e-05, "loss": 1.6106, "step": 719 }, { "epoch": 0.11076497057805469, "grad_norm": 3.783517360687256, "learning_rate": 1.7801724137931037e-05, "loss": 1.2805, "step": 720 }, { "epoch": 0.11091881081496865, "grad_norm": 3.5790610313415527, "learning_rate": 1.7798645320197044e-05, "loss": 1.694, "step": 721 }, { "epoch": 0.11107265105188262, "grad_norm": 4.059264183044434, "learning_rate": 1.7795566502463054e-05, "loss": 1.3239, "step": 722 }, { "epoch": 0.11122649128879658, "grad_norm": 3.8528058528900146, "learning_rate": 1.7792487684729065e-05, "loss": 1.3788, "step": 723 }, { "epoch": 0.11138033152571054, "grad_norm": 3.854170322418213, "learning_rate": 1.7789408866995076e-05, "loss": 1.5718, "step": 724 }, { "epoch": 0.11153417176262452, "grad_norm": 4.1276750564575195, "learning_rate": 1.7786330049261083e-05, "loss": 1.7907, "step": 725 }, { "epoch": 0.11168801199953848, "grad_norm": 4.859658718109131, "learning_rate": 1.7783251231527094e-05, "loss": 1.4853, "step": 726 }, { "epoch": 0.11184185223645245, "grad_norm": 3.8474695682525635, "learning_rate": 1.7780172413793104e-05, "loss": 1.4151, "step": 727 }, { "epoch": 0.11199569247336641, "grad_norm": 3.8622324466705322, "learning_rate": 1.7777093596059115e-05, "loss": 1.346, "step": 728 }, { "epoch": 0.11214953271028037, "grad_norm": 3.5349349975585938, "learning_rate": 1.7774014778325122e-05, "loss": 1.3791, "step": 729 }, { "epoch": 0.11230337294719434, "grad_norm": 3.2061684131622314, "learning_rate": 1.7770935960591133e-05, "loss": 1.5262, "step": 730 }, { "epoch": 0.1124572131841083, "grad_norm": 3.5871689319610596, "learning_rate": 1.7767857142857143e-05, "loss": 1.6232, "step": 731 }, { "epoch": 0.11261105342102228, "grad_norm": 3.1389284133911133, "learning_rate": 1.7764778325123154e-05, "loss": 1.4242, "step": 732 }, { "epoch": 0.11276489365793624, "grad_norm": 3.273419141769409, "learning_rate": 1.776169950738916e-05, "loss": 1.5018, "step": 733 }, { "epoch": 0.1129187338948502, "grad_norm": 3.462172508239746, "learning_rate": 1.7758620689655175e-05, "loss": 1.4689, "step": 734 }, { "epoch": 0.11307257413176416, "grad_norm": 3.5557472705841064, "learning_rate": 1.7755541871921186e-05, "loss": 1.4162, "step": 735 }, { "epoch": 0.11322641436867813, "grad_norm": 4.409984111785889, "learning_rate": 1.7752463054187193e-05, "loss": 1.2382, "step": 736 }, { "epoch": 0.11338025460559209, "grad_norm": 4.138044834136963, "learning_rate": 1.7749384236453204e-05, "loss": 1.4814, "step": 737 }, { "epoch": 0.11353409484250605, "grad_norm": 4.244129180908203, "learning_rate": 1.7746305418719215e-05, "loss": 1.5764, "step": 738 }, { "epoch": 0.11368793507942002, "grad_norm": 4.832545280456543, "learning_rate": 1.7743226600985225e-05, "loss": 1.4585, "step": 739 }, { "epoch": 0.11384177531633399, "grad_norm": 3.567150592803955, "learning_rate": 1.7740147783251233e-05, "loss": 1.6701, "step": 740 }, { "epoch": 0.11399561555324796, "grad_norm": 3.9830901622772217, "learning_rate": 1.7737068965517243e-05, "loss": 1.4123, "step": 741 }, { "epoch": 0.11414945579016192, "grad_norm": 3.7608954906463623, "learning_rate": 1.7733990147783254e-05, "loss": 1.5377, "step": 742 }, { "epoch": 0.11430329602707588, "grad_norm": 3.853536605834961, "learning_rate": 1.7730911330049264e-05, "loss": 1.3981, "step": 743 }, { "epoch": 0.11445713626398984, "grad_norm": 3.519902467727661, "learning_rate": 1.7727832512315272e-05, "loss": 1.551, "step": 744 }, { "epoch": 0.11461097650090381, "grad_norm": 3.570486545562744, "learning_rate": 1.7724753694581282e-05, "loss": 1.4422, "step": 745 }, { "epoch": 0.11476481673781777, "grad_norm": 3.80598783493042, "learning_rate": 1.7721674876847293e-05, "loss": 1.4774, "step": 746 }, { "epoch": 0.11491865697473175, "grad_norm": 3.80423903465271, "learning_rate": 1.7718596059113304e-05, "loss": 1.4784, "step": 747 }, { "epoch": 0.11507249721164571, "grad_norm": 4.522387981414795, "learning_rate": 1.771551724137931e-05, "loss": 1.4873, "step": 748 }, { "epoch": 0.11522633744855967, "grad_norm": 4.1318359375, "learning_rate": 1.771243842364532e-05, "loss": 1.6178, "step": 749 }, { "epoch": 0.11538017768547364, "grad_norm": 4.803264141082764, "learning_rate": 1.7709359605911332e-05, "loss": 1.5608, "step": 750 }, { "epoch": 0.1155340179223876, "grad_norm": 3.3900504112243652, "learning_rate": 1.7706280788177343e-05, "loss": 1.5752, "step": 751 }, { "epoch": 0.11568785815930156, "grad_norm": 3.6891446113586426, "learning_rate": 1.770320197044335e-05, "loss": 1.5917, "step": 752 }, { "epoch": 0.11584169839621553, "grad_norm": 3.865277051925659, "learning_rate": 1.770012315270936e-05, "loss": 1.5827, "step": 753 }, { "epoch": 0.11599553863312949, "grad_norm": 4.1312994956970215, "learning_rate": 1.769704433497537e-05, "loss": 1.6312, "step": 754 }, { "epoch": 0.11614937887004347, "grad_norm": 3.644167423248291, "learning_rate": 1.7693965517241382e-05, "loss": 1.3619, "step": 755 }, { "epoch": 0.11630321910695743, "grad_norm": 3.7027411460876465, "learning_rate": 1.769088669950739e-05, "loss": 1.6293, "step": 756 }, { "epoch": 0.11645705934387139, "grad_norm": 3.379812717437744, "learning_rate": 1.76878078817734e-05, "loss": 1.353, "step": 757 }, { "epoch": 0.11661089958078535, "grad_norm": 3.4410440921783447, "learning_rate": 1.768472906403941e-05, "loss": 1.3827, "step": 758 }, { "epoch": 0.11676473981769932, "grad_norm": 4.3588714599609375, "learning_rate": 1.768165024630542e-05, "loss": 1.2618, "step": 759 }, { "epoch": 0.11691858005461328, "grad_norm": 4.403066158294678, "learning_rate": 1.767857142857143e-05, "loss": 1.381, "step": 760 }, { "epoch": 0.11707242029152724, "grad_norm": 3.7166929244995117, "learning_rate": 1.767549261083744e-05, "loss": 1.4082, "step": 761 }, { "epoch": 0.11722626052844122, "grad_norm": 4.017719745635986, "learning_rate": 1.767241379310345e-05, "loss": 1.5729, "step": 762 }, { "epoch": 0.11738010076535518, "grad_norm": 4.022344589233398, "learning_rate": 1.766933497536946e-05, "loss": 1.4774, "step": 763 }, { "epoch": 0.11753394100226915, "grad_norm": 4.230640888214111, "learning_rate": 1.7666256157635468e-05, "loss": 1.543, "step": 764 }, { "epoch": 0.11768778123918311, "grad_norm": 4.385871887207031, "learning_rate": 1.766317733990148e-05, "loss": 1.2407, "step": 765 }, { "epoch": 0.11784162147609707, "grad_norm": 3.4118988513946533, "learning_rate": 1.766009852216749e-05, "loss": 1.2291, "step": 766 }, { "epoch": 0.11799546171301104, "grad_norm": 4.679936408996582, "learning_rate": 1.7657019704433496e-05, "loss": 1.6981, "step": 767 }, { "epoch": 0.118149301949925, "grad_norm": 3.9132325649261475, "learning_rate": 1.765394088669951e-05, "loss": 1.666, "step": 768 }, { "epoch": 0.11830314218683896, "grad_norm": 3.7597007751464844, "learning_rate": 1.765086206896552e-05, "loss": 1.6155, "step": 769 }, { "epoch": 0.11845698242375294, "grad_norm": 3.71954083442688, "learning_rate": 1.7647783251231528e-05, "loss": 1.0565, "step": 770 }, { "epoch": 0.1186108226606669, "grad_norm": 3.8273091316223145, "learning_rate": 1.764470443349754e-05, "loss": 1.6349, "step": 771 }, { "epoch": 0.11876466289758086, "grad_norm": 3.632002592086792, "learning_rate": 1.764162561576355e-05, "loss": 1.545, "step": 772 }, { "epoch": 0.11891850313449483, "grad_norm": 4.241309642791748, "learning_rate": 1.763854679802956e-05, "loss": 1.481, "step": 773 }, { "epoch": 0.11907234337140879, "grad_norm": 3.897573232650757, "learning_rate": 1.7635467980295567e-05, "loss": 1.2703, "step": 774 }, { "epoch": 0.11922618360832275, "grad_norm": 3.805185079574585, "learning_rate": 1.7632389162561578e-05, "loss": 1.7269, "step": 775 }, { "epoch": 0.11938002384523672, "grad_norm": 3.565000534057617, "learning_rate": 1.762931034482759e-05, "loss": 1.2687, "step": 776 }, { "epoch": 0.11953386408215069, "grad_norm": 4.384906768798828, "learning_rate": 1.76262315270936e-05, "loss": 1.2564, "step": 777 }, { "epoch": 0.11968770431906466, "grad_norm": 4.279872417449951, "learning_rate": 1.7623152709359607e-05, "loss": 1.4621, "step": 778 }, { "epoch": 0.11984154455597862, "grad_norm": 3.978550910949707, "learning_rate": 1.7620073891625617e-05, "loss": 1.4223, "step": 779 }, { "epoch": 0.11999538479289258, "grad_norm": 4.011646270751953, "learning_rate": 1.7616995073891628e-05, "loss": 1.4941, "step": 780 }, { "epoch": 0.12014922502980654, "grad_norm": 4.717382907867432, "learning_rate": 1.761391625615764e-05, "loss": 1.5789, "step": 781 }, { "epoch": 0.12030306526672051, "grad_norm": 4.685054779052734, "learning_rate": 1.7610837438423646e-05, "loss": 1.903, "step": 782 }, { "epoch": 0.12045690550363447, "grad_norm": 3.8133797645568848, "learning_rate": 1.7607758620689656e-05, "loss": 1.4235, "step": 783 }, { "epoch": 0.12061074574054845, "grad_norm": 4.286118030548096, "learning_rate": 1.7604679802955667e-05, "loss": 1.5149, "step": 784 }, { "epoch": 0.12076458597746241, "grad_norm": 3.34163236618042, "learning_rate": 1.7601600985221678e-05, "loss": 1.5564, "step": 785 }, { "epoch": 0.12091842621437637, "grad_norm": 3.784450054168701, "learning_rate": 1.7598522167487685e-05, "loss": 1.4313, "step": 786 }, { "epoch": 0.12107226645129034, "grad_norm": 3.6394689083099365, "learning_rate": 1.7595443349753696e-05, "loss": 1.4424, "step": 787 }, { "epoch": 0.1212261066882043, "grad_norm": 4.257595539093018, "learning_rate": 1.7592364532019706e-05, "loss": 1.5473, "step": 788 }, { "epoch": 0.12137994692511826, "grad_norm": 3.8485755920410156, "learning_rate": 1.7589285714285717e-05, "loss": 1.2771, "step": 789 }, { "epoch": 0.12153378716203223, "grad_norm": 3.869032621383667, "learning_rate": 1.7586206896551724e-05, "loss": 1.2571, "step": 790 }, { "epoch": 0.12168762739894619, "grad_norm": 3.7963011264801025, "learning_rate": 1.7583128078817735e-05, "loss": 1.343, "step": 791 }, { "epoch": 0.12184146763586017, "grad_norm": 3.119661808013916, "learning_rate": 1.7580049261083745e-05, "loss": 1.4849, "step": 792 }, { "epoch": 0.12199530787277413, "grad_norm": 4.2311601638793945, "learning_rate": 1.7576970443349756e-05, "loss": 1.5524, "step": 793 }, { "epoch": 0.12214914810968809, "grad_norm": 3.4916839599609375, "learning_rate": 1.7573891625615763e-05, "loss": 1.4633, "step": 794 }, { "epoch": 0.12230298834660205, "grad_norm": 3.884202241897583, "learning_rate": 1.7570812807881774e-05, "loss": 1.5652, "step": 795 }, { "epoch": 0.12245682858351602, "grad_norm": 4.395451068878174, "learning_rate": 1.7567733990147785e-05, "loss": 1.5092, "step": 796 }, { "epoch": 0.12261066882042998, "grad_norm": 4.389745235443115, "learning_rate": 1.7564655172413795e-05, "loss": 1.6778, "step": 797 }, { "epoch": 0.12276450905734394, "grad_norm": 4.262656211853027, "learning_rate": 1.7561576354679803e-05, "loss": 1.5205, "step": 798 }, { "epoch": 0.12291834929425792, "grad_norm": 3.52135968208313, "learning_rate": 1.7558497536945813e-05, "loss": 1.4869, "step": 799 }, { "epoch": 0.12307218953117188, "grad_norm": 3.5920777320861816, "learning_rate": 1.7555418719211824e-05, "loss": 1.3974, "step": 800 }, { "epoch": 0.12322602976808585, "grad_norm": 4.518594741821289, "learning_rate": 1.7552339901477834e-05, "loss": 1.7941, "step": 801 }, { "epoch": 0.12337987000499981, "grad_norm": 3.9781155586242676, "learning_rate": 1.7549261083743845e-05, "loss": 1.5012, "step": 802 }, { "epoch": 0.12353371024191377, "grad_norm": 4.643721103668213, "learning_rate": 1.7546182266009856e-05, "loss": 1.2807, "step": 803 }, { "epoch": 0.12368755047882773, "grad_norm": 3.640810251235962, "learning_rate": 1.7543103448275863e-05, "loss": 1.2823, "step": 804 }, { "epoch": 0.1238413907157417, "grad_norm": 3.7080581188201904, "learning_rate": 1.7540024630541874e-05, "loss": 1.6617, "step": 805 }, { "epoch": 0.12399523095265566, "grad_norm": 4.437281608581543, "learning_rate": 1.7536945812807884e-05, "loss": 1.5387, "step": 806 }, { "epoch": 0.12414907118956964, "grad_norm": 3.6962029933929443, "learning_rate": 1.7533866995073895e-05, "loss": 1.4679, "step": 807 }, { "epoch": 0.1243029114264836, "grad_norm": 3.8691956996917725, "learning_rate": 1.7530788177339902e-05, "loss": 1.482, "step": 808 }, { "epoch": 0.12445675166339756, "grad_norm": 3.9714126586914062, "learning_rate": 1.7527709359605913e-05, "loss": 1.3405, "step": 809 }, { "epoch": 0.12461059190031153, "grad_norm": 3.7547836303710938, "learning_rate": 1.7524630541871923e-05, "loss": 1.3902, "step": 810 }, { "epoch": 0.12476443213722549, "grad_norm": 4.445328712463379, "learning_rate": 1.7521551724137934e-05, "loss": 1.4227, "step": 811 }, { "epoch": 0.12491827237413945, "grad_norm": 3.60370135307312, "learning_rate": 1.751847290640394e-05, "loss": 1.3113, "step": 812 }, { "epoch": 0.12507211261105342, "grad_norm": 3.936115026473999, "learning_rate": 1.7515394088669952e-05, "loss": 1.3918, "step": 813 }, { "epoch": 0.1252259528479674, "grad_norm": 4.328988552093506, "learning_rate": 1.7512315270935963e-05, "loss": 1.5357, "step": 814 }, { "epoch": 0.12537979308488134, "grad_norm": 3.6830005645751953, "learning_rate": 1.7509236453201973e-05, "loss": 1.6369, "step": 815 }, { "epoch": 0.12553363332179532, "grad_norm": 4.5666351318359375, "learning_rate": 1.750615763546798e-05, "loss": 1.7274, "step": 816 }, { "epoch": 0.12568747355870927, "grad_norm": 4.252288341522217, "learning_rate": 1.750307881773399e-05, "loss": 1.4517, "step": 817 }, { "epoch": 0.12584131379562324, "grad_norm": 3.8083088397979736, "learning_rate": 1.7500000000000002e-05, "loss": 1.5213, "step": 818 }, { "epoch": 0.12599515403253722, "grad_norm": 3.6396090984344482, "learning_rate": 1.7496921182266013e-05, "loss": 1.4802, "step": 819 }, { "epoch": 0.12614899426945117, "grad_norm": 4.050459861755371, "learning_rate": 1.749384236453202e-05, "loss": 1.3928, "step": 820 }, { "epoch": 0.12630283450636515, "grad_norm": 3.8880984783172607, "learning_rate": 1.749076354679803e-05, "loss": 1.6832, "step": 821 }, { "epoch": 0.1264566747432791, "grad_norm": 2.9573493003845215, "learning_rate": 1.748768472906404e-05, "loss": 1.2989, "step": 822 }, { "epoch": 0.12661051498019307, "grad_norm": 3.500340223312378, "learning_rate": 1.748460591133005e-05, "loss": 1.2046, "step": 823 }, { "epoch": 0.12676435521710702, "grad_norm": 4.532421588897705, "learning_rate": 1.748152709359606e-05, "loss": 1.494, "step": 824 }, { "epoch": 0.126918195454021, "grad_norm": 4.247411251068115, "learning_rate": 1.747844827586207e-05, "loss": 1.5807, "step": 825 }, { "epoch": 0.12707203569093498, "grad_norm": 3.71700119972229, "learning_rate": 1.747536945812808e-05, "loss": 1.1604, "step": 826 }, { "epoch": 0.12722587592784892, "grad_norm": 3.5440073013305664, "learning_rate": 1.747229064039409e-05, "loss": 1.5523, "step": 827 }, { "epoch": 0.1273797161647629, "grad_norm": 4.208626747131348, "learning_rate": 1.7469211822660098e-05, "loss": 1.1953, "step": 828 }, { "epoch": 0.12753355640167685, "grad_norm": 3.6987521648406982, "learning_rate": 1.746613300492611e-05, "loss": 1.5108, "step": 829 }, { "epoch": 0.12768739663859083, "grad_norm": 4.069637298583984, "learning_rate": 1.746305418719212e-05, "loss": 1.4841, "step": 830 }, { "epoch": 0.12784123687550478, "grad_norm": 3.310743808746338, "learning_rate": 1.745997536945813e-05, "loss": 1.4843, "step": 831 }, { "epoch": 0.12799507711241875, "grad_norm": 4.202353000640869, "learning_rate": 1.7456896551724137e-05, "loss": 1.4272, "step": 832 }, { "epoch": 0.12814891734933273, "grad_norm": 3.782428503036499, "learning_rate": 1.7453817733990148e-05, "loss": 1.3324, "step": 833 }, { "epoch": 0.12830275758624668, "grad_norm": 4.088131427764893, "learning_rate": 1.745073891625616e-05, "loss": 1.1301, "step": 834 }, { "epoch": 0.12845659782316066, "grad_norm": 3.377162456512451, "learning_rate": 1.744766009852217e-05, "loss": 1.2426, "step": 835 }, { "epoch": 0.1286104380600746, "grad_norm": 3.6133952140808105, "learning_rate": 1.744458128078818e-05, "loss": 1.6448, "step": 836 }, { "epoch": 0.12876427829698858, "grad_norm": 3.1978209018707275, "learning_rate": 1.744150246305419e-05, "loss": 1.509, "step": 837 }, { "epoch": 0.12891811853390253, "grad_norm": 4.422596454620361, "learning_rate": 1.7438423645320198e-05, "loss": 1.3287, "step": 838 }, { "epoch": 0.1290719587708165, "grad_norm": 4.135385513305664, "learning_rate": 1.743534482758621e-05, "loss": 1.5509, "step": 839 }, { "epoch": 0.12922579900773049, "grad_norm": 4.193825721740723, "learning_rate": 1.743226600985222e-05, "loss": 1.7578, "step": 840 }, { "epoch": 0.12937963924464443, "grad_norm": 4.05457878112793, "learning_rate": 1.742918719211823e-05, "loss": 1.3937, "step": 841 }, { "epoch": 0.1295334794815584, "grad_norm": 3.511284828186035, "learning_rate": 1.7426108374384237e-05, "loss": 1.6309, "step": 842 }, { "epoch": 0.12968731971847236, "grad_norm": 3.393035411834717, "learning_rate": 1.7423029556650248e-05, "loss": 1.4485, "step": 843 }, { "epoch": 0.12984115995538634, "grad_norm": 4.436893463134766, "learning_rate": 1.7419950738916258e-05, "loss": 1.5436, "step": 844 }, { "epoch": 0.1299950001923003, "grad_norm": 4.020330905914307, "learning_rate": 1.741687192118227e-05, "loss": 1.064, "step": 845 }, { "epoch": 0.13014884042921426, "grad_norm": 3.904075860977173, "learning_rate": 1.7413793103448276e-05, "loss": 1.3789, "step": 846 }, { "epoch": 0.1303026806661282, "grad_norm": 3.805476665496826, "learning_rate": 1.7410714285714287e-05, "loss": 1.4088, "step": 847 }, { "epoch": 0.1304565209030422, "grad_norm": 2.762054681777954, "learning_rate": 1.7407635467980297e-05, "loss": 1.2717, "step": 848 }, { "epoch": 0.13061036113995617, "grad_norm": 4.21365213394165, "learning_rate": 1.7404556650246308e-05, "loss": 1.4109, "step": 849 }, { "epoch": 0.13076420137687012, "grad_norm": 5.194555282592773, "learning_rate": 1.7401477832512315e-05, "loss": 1.7466, "step": 850 }, { "epoch": 0.1309180416137841, "grad_norm": 3.4673566818237305, "learning_rate": 1.7398399014778326e-05, "loss": 1.6535, "step": 851 }, { "epoch": 0.13107188185069804, "grad_norm": 3.839090585708618, "learning_rate": 1.7395320197044337e-05, "loss": 1.4048, "step": 852 }, { "epoch": 0.13122572208761202, "grad_norm": 3.4381823539733887, "learning_rate": 1.7392241379310347e-05, "loss": 1.5239, "step": 853 }, { "epoch": 0.13137956232452597, "grad_norm": 4.279394626617432, "learning_rate": 1.7389162561576355e-05, "loss": 1.3405, "step": 854 }, { "epoch": 0.13153340256143994, "grad_norm": 3.714215040206909, "learning_rate": 1.7386083743842365e-05, "loss": 1.3782, "step": 855 }, { "epoch": 0.13168724279835392, "grad_norm": 3.765925884246826, "learning_rate": 1.7383004926108376e-05, "loss": 1.872, "step": 856 }, { "epoch": 0.13184108303526787, "grad_norm": 3.8320136070251465, "learning_rate": 1.7379926108374387e-05, "loss": 1.5082, "step": 857 }, { "epoch": 0.13199492327218185, "grad_norm": 3.9073641300201416, "learning_rate": 1.7376847290640394e-05, "loss": 1.4916, "step": 858 }, { "epoch": 0.1321487635090958, "grad_norm": 4.634034156799316, "learning_rate": 1.7373768472906404e-05, "loss": 1.9078, "step": 859 }, { "epoch": 0.13230260374600977, "grad_norm": 4.336019992828369, "learning_rate": 1.7370689655172415e-05, "loss": 1.1834, "step": 860 }, { "epoch": 0.13245644398292372, "grad_norm": 4.097862720489502, "learning_rate": 1.7367610837438426e-05, "loss": 1.6976, "step": 861 }, { "epoch": 0.1326102842198377, "grad_norm": 3.758692741394043, "learning_rate": 1.7364532019704433e-05, "loss": 1.1863, "step": 862 }, { "epoch": 0.13276412445675168, "grad_norm": 3.359670400619507, "learning_rate": 1.7361453201970444e-05, "loss": 1.5335, "step": 863 }, { "epoch": 0.13291796469366562, "grad_norm": 4.436004161834717, "learning_rate": 1.7358374384236454e-05, "loss": 1.6517, "step": 864 }, { "epoch": 0.1330718049305796, "grad_norm": 3.29890775680542, "learning_rate": 1.7355295566502465e-05, "loss": 1.3394, "step": 865 }, { "epoch": 0.13322564516749355, "grad_norm": 3.9934818744659424, "learning_rate": 1.7352216748768472e-05, "loss": 1.6666, "step": 866 }, { "epoch": 0.13337948540440753, "grad_norm": 3.957540512084961, "learning_rate": 1.7349137931034483e-05, "loss": 1.4572, "step": 867 }, { "epoch": 0.13353332564132148, "grad_norm": 3.9431896209716797, "learning_rate": 1.7346059113300493e-05, "loss": 1.4543, "step": 868 }, { "epoch": 0.13368716587823545, "grad_norm": 4.6326003074646, "learning_rate": 1.7342980295566504e-05, "loss": 1.5609, "step": 869 }, { "epoch": 0.13384100611514943, "grad_norm": 3.6067097187042236, "learning_rate": 1.7339901477832515e-05, "loss": 1.3231, "step": 870 }, { "epoch": 0.13399484635206338, "grad_norm": 3.328610420227051, "learning_rate": 1.7336822660098525e-05, "loss": 1.381, "step": 871 }, { "epoch": 0.13414868658897736, "grad_norm": 4.430046081542969, "learning_rate": 1.7333743842364533e-05, "loss": 1.6357, "step": 872 }, { "epoch": 0.1343025268258913, "grad_norm": 4.174025535583496, "learning_rate": 1.7330665024630543e-05, "loss": 1.6618, "step": 873 }, { "epoch": 0.13445636706280528, "grad_norm": 3.3086812496185303, "learning_rate": 1.7327586206896554e-05, "loss": 1.6046, "step": 874 }, { "epoch": 0.13461020729971923, "grad_norm": 3.980146884918213, "learning_rate": 1.7324507389162565e-05, "loss": 1.6714, "step": 875 }, { "epoch": 0.1347640475366332, "grad_norm": 3.3819196224212646, "learning_rate": 1.7321428571428572e-05, "loss": 1.5164, "step": 876 }, { "epoch": 0.13491788777354718, "grad_norm": 4.047339916229248, "learning_rate": 1.7318349753694582e-05, "loss": 1.3557, "step": 877 }, { "epoch": 0.13507172801046113, "grad_norm": 4.035795211791992, "learning_rate": 1.7315270935960593e-05, "loss": 1.6492, "step": 878 }, { "epoch": 0.1352255682473751, "grad_norm": 3.6633195877075195, "learning_rate": 1.7312192118226604e-05, "loss": 1.5423, "step": 879 }, { "epoch": 0.13537940848428906, "grad_norm": 3.431617259979248, "learning_rate": 1.730911330049261e-05, "loss": 1.2458, "step": 880 }, { "epoch": 0.13553324872120304, "grad_norm": 3.4326233863830566, "learning_rate": 1.730603448275862e-05, "loss": 1.4121, "step": 881 }, { "epoch": 0.13568708895811699, "grad_norm": 3.7535390853881836, "learning_rate": 1.7302955665024632e-05, "loss": 1.4198, "step": 882 }, { "epoch": 0.13584092919503096, "grad_norm": 3.699575424194336, "learning_rate": 1.7299876847290643e-05, "loss": 1.4777, "step": 883 }, { "epoch": 0.1359947694319449, "grad_norm": 3.1612000465393066, "learning_rate": 1.729679802955665e-05, "loss": 1.377, "step": 884 }, { "epoch": 0.1361486096688589, "grad_norm": 3.7286813259124756, "learning_rate": 1.729371921182266e-05, "loss": 1.4905, "step": 885 }, { "epoch": 0.13630244990577287, "grad_norm": 3.6935625076293945, "learning_rate": 1.729064039408867e-05, "loss": 1.6527, "step": 886 }, { "epoch": 0.13645629014268681, "grad_norm": 4.192127704620361, "learning_rate": 1.7287561576354682e-05, "loss": 1.6971, "step": 887 }, { "epoch": 0.1366101303796008, "grad_norm": 3.789487361907959, "learning_rate": 1.728448275862069e-05, "loss": 1.4916, "step": 888 }, { "epoch": 0.13676397061651474, "grad_norm": 4.2400126457214355, "learning_rate": 1.72814039408867e-05, "loss": 1.3064, "step": 889 }, { "epoch": 0.13691781085342872, "grad_norm": 3.401623487472534, "learning_rate": 1.727832512315271e-05, "loss": 1.338, "step": 890 }, { "epoch": 0.13707165109034267, "grad_norm": 3.6382699012756348, "learning_rate": 1.727524630541872e-05, "loss": 1.4504, "step": 891 }, { "epoch": 0.13722549132725664, "grad_norm": 4.056309223175049, "learning_rate": 1.727216748768473e-05, "loss": 1.5051, "step": 892 }, { "epoch": 0.13737933156417062, "grad_norm": 4.509316444396973, "learning_rate": 1.726908866995074e-05, "loss": 1.7207, "step": 893 }, { "epoch": 0.13753317180108457, "grad_norm": 3.8397819995880127, "learning_rate": 1.726600985221675e-05, "loss": 1.3527, "step": 894 }, { "epoch": 0.13768701203799855, "grad_norm": 4.120513916015625, "learning_rate": 1.726293103448276e-05, "loss": 1.3589, "step": 895 }, { "epoch": 0.1378408522749125, "grad_norm": 3.3005287647247314, "learning_rate": 1.7259852216748768e-05, "loss": 1.51, "step": 896 }, { "epoch": 0.13799469251182647, "grad_norm": 3.5379178524017334, "learning_rate": 1.725677339901478e-05, "loss": 1.5088, "step": 897 }, { "epoch": 0.13814853274874042, "grad_norm": 4.687489986419678, "learning_rate": 1.725369458128079e-05, "loss": 1.4984, "step": 898 }, { "epoch": 0.1383023729856544, "grad_norm": 3.6074626445770264, "learning_rate": 1.72506157635468e-05, "loss": 1.6675, "step": 899 }, { "epoch": 0.13845621322256838, "grad_norm": 3.802720546722412, "learning_rate": 1.7247536945812807e-05, "loss": 1.3173, "step": 900 }, { "epoch": 0.13861005345948232, "grad_norm": 3.923358678817749, "learning_rate": 1.7244458128078818e-05, "loss": 1.6705, "step": 901 }, { "epoch": 0.1387638936963963, "grad_norm": 3.3500499725341797, "learning_rate": 1.7241379310344828e-05, "loss": 1.3848, "step": 902 }, { "epoch": 0.13891773393331025, "grad_norm": 3.5233428478240967, "learning_rate": 1.723830049261084e-05, "loss": 1.6255, "step": 903 }, { "epoch": 0.13907157417022423, "grad_norm": 3.5567266941070557, "learning_rate": 1.723522167487685e-05, "loss": 1.3994, "step": 904 }, { "epoch": 0.13922541440713818, "grad_norm": 3.572519063949585, "learning_rate": 1.723214285714286e-05, "loss": 1.6123, "step": 905 }, { "epoch": 0.13937925464405215, "grad_norm": 3.7124006748199463, "learning_rate": 1.722906403940887e-05, "loss": 1.2669, "step": 906 }, { "epoch": 0.13953309488096613, "grad_norm": 6.934424877166748, "learning_rate": 1.7225985221674878e-05, "loss": 1.5132, "step": 907 }, { "epoch": 0.13968693511788008, "grad_norm": 3.583550453186035, "learning_rate": 1.722290640394089e-05, "loss": 1.3224, "step": 908 }, { "epoch": 0.13984077535479406, "grad_norm": 3.4508564472198486, "learning_rate": 1.72198275862069e-05, "loss": 1.3015, "step": 909 }, { "epoch": 0.139994615591708, "grad_norm": 3.284137487411499, "learning_rate": 1.721674876847291e-05, "loss": 1.323, "step": 910 }, { "epoch": 0.14014845582862198, "grad_norm": 4.503775596618652, "learning_rate": 1.7213669950738917e-05, "loss": 1.608, "step": 911 }, { "epoch": 0.14030229606553593, "grad_norm": 3.8307595252990723, "learning_rate": 1.7210591133004928e-05, "loss": 1.2653, "step": 912 }, { "epoch": 0.1404561363024499, "grad_norm": 3.4663403034210205, "learning_rate": 1.720751231527094e-05, "loss": 1.6095, "step": 913 }, { "epoch": 0.14060997653936386, "grad_norm": 3.6856513023376465, "learning_rate": 1.720443349753695e-05, "loss": 1.401, "step": 914 }, { "epoch": 0.14076381677627783, "grad_norm": 4.119662761688232, "learning_rate": 1.7201354679802957e-05, "loss": 1.6528, "step": 915 }, { "epoch": 0.1409176570131918, "grad_norm": 3.843693494796753, "learning_rate": 1.7198275862068967e-05, "loss": 1.2854, "step": 916 }, { "epoch": 0.14107149725010576, "grad_norm": 4.927124500274658, "learning_rate": 1.7195197044334978e-05, "loss": 1.2755, "step": 917 }, { "epoch": 0.14122533748701974, "grad_norm": 3.6591410636901855, "learning_rate": 1.7192118226600985e-05, "loss": 1.2102, "step": 918 }, { "epoch": 0.14137917772393369, "grad_norm": 4.843090534210205, "learning_rate": 1.7189039408866996e-05, "loss": 1.621, "step": 919 }, { "epoch": 0.14153301796084766, "grad_norm": 4.3849005699157715, "learning_rate": 1.7185960591133006e-05, "loss": 1.6218, "step": 920 }, { "epoch": 0.1416868581977616, "grad_norm": 3.56209397315979, "learning_rate": 1.7182881773399017e-05, "loss": 1.5086, "step": 921 }, { "epoch": 0.1418406984346756, "grad_norm": 3.470125913619995, "learning_rate": 1.7179802955665024e-05, "loss": 1.5121, "step": 922 }, { "epoch": 0.14199453867158957, "grad_norm": 3.6100704669952393, "learning_rate": 1.7176724137931035e-05, "loss": 1.4162, "step": 923 }, { "epoch": 0.14214837890850351, "grad_norm": 3.5654008388519287, "learning_rate": 1.7173645320197046e-05, "loss": 1.4716, "step": 924 }, { "epoch": 0.1423022191454175, "grad_norm": 3.98883318901062, "learning_rate": 1.7170566502463056e-05, "loss": 1.6207, "step": 925 }, { "epoch": 0.14245605938233144, "grad_norm": 3.5120458602905273, "learning_rate": 1.7167487684729063e-05, "loss": 1.4153, "step": 926 }, { "epoch": 0.14260989961924542, "grad_norm": 3.9891602993011475, "learning_rate": 1.7164408866995074e-05, "loss": 1.7164, "step": 927 }, { "epoch": 0.14276373985615937, "grad_norm": 3.807340621948242, "learning_rate": 1.7161330049261085e-05, "loss": 1.2527, "step": 928 }, { "epoch": 0.14291758009307334, "grad_norm": 3.7075138092041016, "learning_rate": 1.7158251231527095e-05, "loss": 1.5058, "step": 929 }, { "epoch": 0.14307142032998732, "grad_norm": 3.7525722980499268, "learning_rate": 1.7155172413793103e-05, "loss": 1.2633, "step": 930 }, { "epoch": 0.14322526056690127, "grad_norm": 4.131142616271973, "learning_rate": 1.7152093596059113e-05, "loss": 1.4422, "step": 931 }, { "epoch": 0.14337910080381525, "grad_norm": 4.591202259063721, "learning_rate": 1.7149014778325124e-05, "loss": 1.1999, "step": 932 }, { "epoch": 0.1435329410407292, "grad_norm": 3.7117626667022705, "learning_rate": 1.7145935960591135e-05, "loss": 1.3253, "step": 933 }, { "epoch": 0.14368678127764317, "grad_norm": 3.2628955841064453, "learning_rate": 1.7142857142857142e-05, "loss": 1.4426, "step": 934 }, { "epoch": 0.14384062151455712, "grad_norm": 3.3784947395324707, "learning_rate": 1.7139778325123152e-05, "loss": 1.4036, "step": 935 }, { "epoch": 0.1439944617514711, "grad_norm": 3.882051706314087, "learning_rate": 1.7136699507389163e-05, "loss": 1.4773, "step": 936 }, { "epoch": 0.14414830198838507, "grad_norm": 3.718755006790161, "learning_rate": 1.7133620689655174e-05, "loss": 1.4769, "step": 937 }, { "epoch": 0.14430214222529902, "grad_norm": 3.9251914024353027, "learning_rate": 1.7130541871921184e-05, "loss": 1.348, "step": 938 }, { "epoch": 0.144455982462213, "grad_norm": 4.248255729675293, "learning_rate": 1.7127463054187195e-05, "loss": 1.7058, "step": 939 }, { "epoch": 0.14460982269912695, "grad_norm": 3.9144487380981445, "learning_rate": 1.7124384236453206e-05, "loss": 1.4125, "step": 940 }, { "epoch": 0.14476366293604093, "grad_norm": 3.646608352661133, "learning_rate": 1.7121305418719213e-05, "loss": 1.5999, "step": 941 }, { "epoch": 0.14491750317295488, "grad_norm": 3.882317066192627, "learning_rate": 1.7118226600985224e-05, "loss": 1.5199, "step": 942 }, { "epoch": 0.14507134340986885, "grad_norm": 4.188870906829834, "learning_rate": 1.7115147783251234e-05, "loss": 1.3403, "step": 943 }, { "epoch": 0.14522518364678283, "grad_norm": 4.300841808319092, "learning_rate": 1.7112068965517245e-05, "loss": 1.4879, "step": 944 }, { "epoch": 0.14537902388369678, "grad_norm": 3.696582317352295, "learning_rate": 1.7108990147783252e-05, "loss": 1.352, "step": 945 }, { "epoch": 0.14553286412061076, "grad_norm": 4.060450553894043, "learning_rate": 1.7105911330049263e-05, "loss": 1.4749, "step": 946 }, { "epoch": 0.1456867043575247, "grad_norm": 4.162936210632324, "learning_rate": 1.7102832512315273e-05, "loss": 1.3692, "step": 947 }, { "epoch": 0.14584054459443868, "grad_norm": 3.1518349647521973, "learning_rate": 1.7099753694581284e-05, "loss": 1.4425, "step": 948 }, { "epoch": 0.14599438483135263, "grad_norm": 3.5312883853912354, "learning_rate": 1.709667487684729e-05, "loss": 1.4863, "step": 949 }, { "epoch": 0.1461482250682666, "grad_norm": 3.8813390731811523, "learning_rate": 1.7093596059113302e-05, "loss": 1.428, "step": 950 }, { "epoch": 0.14630206530518056, "grad_norm": 3.799994468688965, "learning_rate": 1.7090517241379313e-05, "loss": 1.3785, "step": 951 }, { "epoch": 0.14645590554209453, "grad_norm": 3.5148415565490723, "learning_rate": 1.7087438423645323e-05, "loss": 1.2193, "step": 952 }, { "epoch": 0.1466097457790085, "grad_norm": 3.7659695148468018, "learning_rate": 1.708435960591133e-05, "loss": 1.7278, "step": 953 }, { "epoch": 0.14676358601592246, "grad_norm": 3.7503879070281982, "learning_rate": 1.708128078817734e-05, "loss": 1.3913, "step": 954 }, { "epoch": 0.14691742625283644, "grad_norm": 3.848376989364624, "learning_rate": 1.7078201970443352e-05, "loss": 1.3462, "step": 955 }, { "epoch": 0.14707126648975039, "grad_norm": 3.551851987838745, "learning_rate": 1.7075123152709362e-05, "loss": 1.4889, "step": 956 }, { "epoch": 0.14722510672666436, "grad_norm": 3.4269018173217773, "learning_rate": 1.707204433497537e-05, "loss": 1.3451, "step": 957 }, { "epoch": 0.1473789469635783, "grad_norm": 4.683525562286377, "learning_rate": 1.706896551724138e-05, "loss": 1.3321, "step": 958 }, { "epoch": 0.1475327872004923, "grad_norm": 3.7298359870910645, "learning_rate": 1.706588669950739e-05, "loss": 1.5338, "step": 959 }, { "epoch": 0.14768662743740626, "grad_norm": 3.6150784492492676, "learning_rate": 1.7062807881773398e-05, "loss": 1.4807, "step": 960 }, { "epoch": 0.14784046767432021, "grad_norm": 4.492077350616455, "learning_rate": 1.705972906403941e-05, "loss": 1.333, "step": 961 }, { "epoch": 0.1479943079112342, "grad_norm": 4.408016204833984, "learning_rate": 1.705665024630542e-05, "loss": 1.3014, "step": 962 }, { "epoch": 0.14814814814814814, "grad_norm": 4.004219055175781, "learning_rate": 1.705357142857143e-05, "loss": 1.4036, "step": 963 }, { "epoch": 0.14830198838506212, "grad_norm": 3.090730905532837, "learning_rate": 1.7050492610837437e-05, "loss": 1.0686, "step": 964 }, { "epoch": 0.14845582862197607, "grad_norm": 3.6074020862579346, "learning_rate": 1.7047413793103448e-05, "loss": 1.2793, "step": 965 }, { "epoch": 0.14860966885889004, "grad_norm": 3.9478843212127686, "learning_rate": 1.704433497536946e-05, "loss": 1.4373, "step": 966 }, { "epoch": 0.14876350909580402, "grad_norm": 3.1754305362701416, "learning_rate": 1.704125615763547e-05, "loss": 1.6451, "step": 967 }, { "epoch": 0.14891734933271797, "grad_norm": 3.5632224082946777, "learning_rate": 1.7038177339901477e-05, "loss": 1.5075, "step": 968 }, { "epoch": 0.14907118956963195, "grad_norm": 3.769993305206299, "learning_rate": 1.7035098522167487e-05, "loss": 1.7209, "step": 969 }, { "epoch": 0.1492250298065459, "grad_norm": 3.6354241371154785, "learning_rate": 1.7032019704433498e-05, "loss": 1.1761, "step": 970 }, { "epoch": 0.14937887004345987, "grad_norm": 3.9595181941986084, "learning_rate": 1.702894088669951e-05, "loss": 1.5736, "step": 971 }, { "epoch": 0.14953271028037382, "grad_norm": 4.298709392547607, "learning_rate": 1.702586206896552e-05, "loss": 1.3648, "step": 972 }, { "epoch": 0.1496865505172878, "grad_norm": 3.6560206413269043, "learning_rate": 1.702278325123153e-05, "loss": 1.2897, "step": 973 }, { "epoch": 0.14984039075420177, "grad_norm": 3.456251859664917, "learning_rate": 1.701970443349754e-05, "loss": 1.0718, "step": 974 }, { "epoch": 0.14999423099111572, "grad_norm": 3.465113401412964, "learning_rate": 1.7016625615763548e-05, "loss": 1.207, "step": 975 }, { "epoch": 0.1501480712280297, "grad_norm": 3.322127103805542, "learning_rate": 1.701354679802956e-05, "loss": 1.4081, "step": 976 }, { "epoch": 0.15030191146494365, "grad_norm": 3.5565218925476074, "learning_rate": 1.701046798029557e-05, "loss": 1.5877, "step": 977 }, { "epoch": 0.15045575170185763, "grad_norm": 3.5359699726104736, "learning_rate": 1.700738916256158e-05, "loss": 1.3645, "step": 978 }, { "epoch": 0.15060959193877158, "grad_norm": 3.9133925437927246, "learning_rate": 1.7004310344827587e-05, "loss": 1.401, "step": 979 }, { "epoch": 0.15076343217568555, "grad_norm": 3.7533891201019287, "learning_rate": 1.7001231527093598e-05, "loss": 1.4139, "step": 980 }, { "epoch": 0.15091727241259953, "grad_norm": 4.244124889373779, "learning_rate": 1.6998152709359608e-05, "loss": 1.8289, "step": 981 }, { "epoch": 0.15107111264951348, "grad_norm": 3.457691192626953, "learning_rate": 1.699507389162562e-05, "loss": 1.2751, "step": 982 }, { "epoch": 0.15122495288642746, "grad_norm": 4.4449334144592285, "learning_rate": 1.6991995073891626e-05, "loss": 1.1225, "step": 983 }, { "epoch": 0.1513787931233414, "grad_norm": 4.506092071533203, "learning_rate": 1.6988916256157637e-05, "loss": 1.7003, "step": 984 }, { "epoch": 0.15153263336025538, "grad_norm": 3.8230953216552734, "learning_rate": 1.6985837438423647e-05, "loss": 1.4468, "step": 985 }, { "epoch": 0.15168647359716933, "grad_norm": 3.5631349086761475, "learning_rate": 1.6982758620689658e-05, "loss": 1.4801, "step": 986 }, { "epoch": 0.1518403138340833, "grad_norm": 3.8176705837249756, "learning_rate": 1.6979679802955665e-05, "loss": 1.4952, "step": 987 }, { "epoch": 0.15199415407099726, "grad_norm": 3.5821681022644043, "learning_rate": 1.6976600985221676e-05, "loss": 1.2798, "step": 988 }, { "epoch": 0.15214799430791123, "grad_norm": 4.375070095062256, "learning_rate": 1.6973522167487687e-05, "loss": 1.7279, "step": 989 }, { "epoch": 0.1523018345448252, "grad_norm": 3.532012701034546, "learning_rate": 1.6970443349753697e-05, "loss": 1.4432, "step": 990 }, { "epoch": 0.15245567478173916, "grad_norm": 3.848362922668457, "learning_rate": 1.6967364532019705e-05, "loss": 1.4416, "step": 991 }, { "epoch": 0.15260951501865314, "grad_norm": 3.5493407249450684, "learning_rate": 1.6964285714285715e-05, "loss": 1.5169, "step": 992 }, { "epoch": 0.15276335525556708, "grad_norm": 3.7030038833618164, "learning_rate": 1.6961206896551726e-05, "loss": 1.4776, "step": 993 }, { "epoch": 0.15291719549248106, "grad_norm": 4.116561412811279, "learning_rate": 1.6958128078817737e-05, "loss": 1.4362, "step": 994 }, { "epoch": 0.153071035729395, "grad_norm": 3.8364710807800293, "learning_rate": 1.6955049261083744e-05, "loss": 1.6154, "step": 995 }, { "epoch": 0.153224875966309, "grad_norm": 3.709723949432373, "learning_rate": 1.6951970443349754e-05, "loss": 1.6564, "step": 996 }, { "epoch": 0.15337871620322296, "grad_norm": 4.412187576293945, "learning_rate": 1.6948891625615765e-05, "loss": 1.6905, "step": 997 }, { "epoch": 0.1535325564401369, "grad_norm": 3.797536849975586, "learning_rate": 1.6945812807881776e-05, "loss": 1.5172, "step": 998 }, { "epoch": 0.1536863966770509, "grad_norm": 3.7438032627105713, "learning_rate": 1.6942733990147783e-05, "loss": 1.539, "step": 999 }, { "epoch": 0.15384023691396484, "grad_norm": 3.4380106925964355, "learning_rate": 1.6939655172413794e-05, "loss": 1.5942, "step": 1000 }, { "epoch": 0.15399407715087882, "grad_norm": 3.8854494094848633, "learning_rate": 1.6936576354679804e-05, "loss": 1.438, "step": 1001 }, { "epoch": 0.15414791738779277, "grad_norm": 3.113638162612915, "learning_rate": 1.6933497536945815e-05, "loss": 1.4801, "step": 1002 }, { "epoch": 0.15430175762470674, "grad_norm": 4.277237415313721, "learning_rate": 1.6930418719211822e-05, "loss": 1.3541, "step": 1003 }, { "epoch": 0.15445559786162072, "grad_norm": 3.7055022716522217, "learning_rate": 1.6927339901477833e-05, "loss": 1.4568, "step": 1004 }, { "epoch": 0.15460943809853467, "grad_norm": 3.73551082611084, "learning_rate": 1.6924261083743843e-05, "loss": 1.3959, "step": 1005 }, { "epoch": 0.15476327833544865, "grad_norm": 4.706414222717285, "learning_rate": 1.6921182266009854e-05, "loss": 1.6411, "step": 1006 }, { "epoch": 0.1549171185723626, "grad_norm": 3.978839159011841, "learning_rate": 1.6918103448275865e-05, "loss": 1.4471, "step": 1007 }, { "epoch": 0.15507095880927657, "grad_norm": 3.939413070678711, "learning_rate": 1.6915024630541875e-05, "loss": 1.4063, "step": 1008 }, { "epoch": 0.15522479904619052, "grad_norm": 3.4047350883483887, "learning_rate": 1.6911945812807883e-05, "loss": 1.4522, "step": 1009 }, { "epoch": 0.1553786392831045, "grad_norm": 3.397618532180786, "learning_rate": 1.6908866995073893e-05, "loss": 1.15, "step": 1010 }, { "epoch": 0.15553247952001847, "grad_norm": 3.7941501140594482, "learning_rate": 1.6905788177339904e-05, "loss": 1.4896, "step": 1011 }, { "epoch": 0.15568631975693242, "grad_norm": 3.1558797359466553, "learning_rate": 1.6902709359605915e-05, "loss": 1.561, "step": 1012 }, { "epoch": 0.1558401599938464, "grad_norm": 3.719973564147949, "learning_rate": 1.6899630541871922e-05, "loss": 1.1146, "step": 1013 }, { "epoch": 0.15599400023076035, "grad_norm": 3.7061235904693604, "learning_rate": 1.6896551724137932e-05, "loss": 1.2659, "step": 1014 }, { "epoch": 0.15614784046767433, "grad_norm": 3.3530874252319336, "learning_rate": 1.6893472906403943e-05, "loss": 1.3711, "step": 1015 }, { "epoch": 0.15630168070458828, "grad_norm": 4.121303558349609, "learning_rate": 1.6890394088669954e-05, "loss": 1.5776, "step": 1016 }, { "epoch": 0.15645552094150225, "grad_norm": 3.8564326763153076, "learning_rate": 1.688731527093596e-05, "loss": 1.1131, "step": 1017 }, { "epoch": 0.1566093611784162, "grad_norm": 3.8964946269989014, "learning_rate": 1.688423645320197e-05, "loss": 1.7964, "step": 1018 }, { "epoch": 0.15676320141533018, "grad_norm": 3.5591650009155273, "learning_rate": 1.6881157635467982e-05, "loss": 1.1771, "step": 1019 }, { "epoch": 0.15691704165224415, "grad_norm": 3.7073540687561035, "learning_rate": 1.6878078817733993e-05, "loss": 1.3491, "step": 1020 }, { "epoch": 0.1570708818891581, "grad_norm": 3.7119436264038086, "learning_rate": 1.6875e-05, "loss": 1.602, "step": 1021 }, { "epoch": 0.15722472212607208, "grad_norm": 3.584519147872925, "learning_rate": 1.687192118226601e-05, "loss": 1.477, "step": 1022 }, { "epoch": 0.15737856236298603, "grad_norm": 3.485987901687622, "learning_rate": 1.686884236453202e-05, "loss": 1.1748, "step": 1023 }, { "epoch": 0.1575324025999, "grad_norm": 4.0800089836120605, "learning_rate": 1.6865763546798032e-05, "loss": 1.4411, "step": 1024 }, { "epoch": 0.15768624283681396, "grad_norm": 3.375067949295044, "learning_rate": 1.686268472906404e-05, "loss": 1.3683, "step": 1025 }, { "epoch": 0.15784008307372793, "grad_norm": 3.0356228351593018, "learning_rate": 1.685960591133005e-05, "loss": 1.2871, "step": 1026 }, { "epoch": 0.1579939233106419, "grad_norm": 3.139042377471924, "learning_rate": 1.685652709359606e-05, "loss": 1.3752, "step": 1027 }, { "epoch": 0.15814776354755586, "grad_norm": 4.26816987991333, "learning_rate": 1.685344827586207e-05, "loss": 1.4873, "step": 1028 }, { "epoch": 0.15830160378446984, "grad_norm": 3.408867597579956, "learning_rate": 1.685036945812808e-05, "loss": 1.3416, "step": 1029 }, { "epoch": 0.15845544402138378, "grad_norm": 3.0563530921936035, "learning_rate": 1.684729064039409e-05, "loss": 1.3313, "step": 1030 }, { "epoch": 0.15860928425829776, "grad_norm": 3.4409263134002686, "learning_rate": 1.68442118226601e-05, "loss": 1.6516, "step": 1031 }, { "epoch": 0.1587631244952117, "grad_norm": 3.424964427947998, "learning_rate": 1.684113300492611e-05, "loss": 1.6236, "step": 1032 }, { "epoch": 0.1589169647321257, "grad_norm": 4.001779079437256, "learning_rate": 1.6838054187192118e-05, "loss": 1.3559, "step": 1033 }, { "epoch": 0.15907080496903966, "grad_norm": 3.8692221641540527, "learning_rate": 1.683497536945813e-05, "loss": 1.4962, "step": 1034 }, { "epoch": 0.1592246452059536, "grad_norm": 3.756999969482422, "learning_rate": 1.683189655172414e-05, "loss": 1.3689, "step": 1035 }, { "epoch": 0.1593784854428676, "grad_norm": 3.463322877883911, "learning_rate": 1.682881773399015e-05, "loss": 1.1293, "step": 1036 }, { "epoch": 0.15953232567978154, "grad_norm": 3.7598228454589844, "learning_rate": 1.6825738916256157e-05, "loss": 1.4161, "step": 1037 }, { "epoch": 0.15968616591669552, "grad_norm": 4.085216999053955, "learning_rate": 1.682266009852217e-05, "loss": 1.4925, "step": 1038 }, { "epoch": 0.15984000615360947, "grad_norm": 4.12216854095459, "learning_rate": 1.6819581280788178e-05, "loss": 1.3997, "step": 1039 }, { "epoch": 0.15999384639052344, "grad_norm": 3.72601318359375, "learning_rate": 1.681650246305419e-05, "loss": 1.4212, "step": 1040 }, { "epoch": 0.16014768662743742, "grad_norm": 4.053514003753662, "learning_rate": 1.68134236453202e-05, "loss": 1.6095, "step": 1041 }, { "epoch": 0.16030152686435137, "grad_norm": 3.566474199295044, "learning_rate": 1.681034482758621e-05, "loss": 1.6754, "step": 1042 }, { "epoch": 0.16045536710126534, "grad_norm": 3.9589383602142334, "learning_rate": 1.6807266009852217e-05, "loss": 1.4646, "step": 1043 }, { "epoch": 0.1606092073381793, "grad_norm": 3.9784467220306396, "learning_rate": 1.6804187192118228e-05, "loss": 1.2479, "step": 1044 }, { "epoch": 0.16076304757509327, "grad_norm": 4.953857421875, "learning_rate": 1.680110837438424e-05, "loss": 1.2843, "step": 1045 }, { "epoch": 0.16091688781200722, "grad_norm": 2.7377052307128906, "learning_rate": 1.679802955665025e-05, "loss": 1.1322, "step": 1046 }, { "epoch": 0.1610707280489212, "grad_norm": 3.011183977127075, "learning_rate": 1.6794950738916257e-05, "loss": 1.3771, "step": 1047 }, { "epoch": 0.16122456828583517, "grad_norm": 3.559328556060791, "learning_rate": 1.6791871921182267e-05, "loss": 1.5009, "step": 1048 }, { "epoch": 0.16137840852274912, "grad_norm": 3.2515246868133545, "learning_rate": 1.6788793103448278e-05, "loss": 1.5948, "step": 1049 }, { "epoch": 0.1615322487596631, "grad_norm": 4.227931976318359, "learning_rate": 1.678571428571429e-05, "loss": 1.5251, "step": 1050 }, { "epoch": 0.16168608899657705, "grad_norm": 4.2868146896362305, "learning_rate": 1.6782635467980296e-05, "loss": 1.4782, "step": 1051 }, { "epoch": 0.16183992923349103, "grad_norm": 4.245573043823242, "learning_rate": 1.6779556650246307e-05, "loss": 1.799, "step": 1052 }, { "epoch": 0.16199376947040497, "grad_norm": 3.7283148765563965, "learning_rate": 1.6776477832512317e-05, "loss": 1.4705, "step": 1053 }, { "epoch": 0.16214760970731895, "grad_norm": 3.8696436882019043, "learning_rate": 1.6773399014778328e-05, "loss": 1.1043, "step": 1054 }, { "epoch": 0.1623014499442329, "grad_norm": 3.9600205421447754, "learning_rate": 1.6770320197044335e-05, "loss": 1.3608, "step": 1055 }, { "epoch": 0.16245529018114688, "grad_norm": 3.346959114074707, "learning_rate": 1.6767241379310346e-05, "loss": 1.4198, "step": 1056 }, { "epoch": 0.16260913041806085, "grad_norm": 3.1698801517486572, "learning_rate": 1.6764162561576356e-05, "loss": 1.4641, "step": 1057 }, { "epoch": 0.1627629706549748, "grad_norm": 3.953047752380371, "learning_rate": 1.6761083743842367e-05, "loss": 1.4044, "step": 1058 }, { "epoch": 0.16291681089188878, "grad_norm": 3.838930368423462, "learning_rate": 1.6758004926108374e-05, "loss": 1.2844, "step": 1059 }, { "epoch": 0.16307065112880273, "grad_norm": 3.1871612071990967, "learning_rate": 1.6754926108374385e-05, "loss": 1.5744, "step": 1060 }, { "epoch": 0.1632244913657167, "grad_norm": 4.134891986846924, "learning_rate": 1.6751847290640396e-05, "loss": 1.6042, "step": 1061 }, { "epoch": 0.16337833160263066, "grad_norm": 3.605592966079712, "learning_rate": 1.6748768472906406e-05, "loss": 1.3592, "step": 1062 }, { "epoch": 0.16353217183954463, "grad_norm": 3.356247663497925, "learning_rate": 1.6745689655172413e-05, "loss": 1.5595, "step": 1063 }, { "epoch": 0.1636860120764586, "grad_norm": 4.383678436279297, "learning_rate": 1.6742610837438424e-05, "loss": 1.4295, "step": 1064 }, { "epoch": 0.16383985231337256, "grad_norm": 3.8049204349517822, "learning_rate": 1.6739532019704435e-05, "loss": 1.4738, "step": 1065 }, { "epoch": 0.16399369255028654, "grad_norm": 4.372307300567627, "learning_rate": 1.6736453201970445e-05, "loss": 1.3543, "step": 1066 }, { "epoch": 0.16414753278720048, "grad_norm": 4.067920207977295, "learning_rate": 1.6733374384236453e-05, "loss": 1.458, "step": 1067 }, { "epoch": 0.16430137302411446, "grad_norm": 3.301560640335083, "learning_rate": 1.6730295566502463e-05, "loss": 1.3784, "step": 1068 }, { "epoch": 0.1644552132610284, "grad_norm": 3.9903600215911865, "learning_rate": 1.6727216748768474e-05, "loss": 1.7882, "step": 1069 }, { "epoch": 0.1646090534979424, "grad_norm": 3.928886890411377, "learning_rate": 1.6724137931034485e-05, "loss": 1.4064, "step": 1070 }, { "epoch": 0.16476289373485636, "grad_norm": 3.834293842315674, "learning_rate": 1.6721059113300492e-05, "loss": 1.3922, "step": 1071 }, { "epoch": 0.1649167339717703, "grad_norm": 3.586718797683716, "learning_rate": 1.6717980295566506e-05, "loss": 1.3041, "step": 1072 }, { "epoch": 0.1650705742086843, "grad_norm": 4.060189247131348, "learning_rate": 1.6714901477832513e-05, "loss": 1.6636, "step": 1073 }, { "epoch": 0.16522441444559824, "grad_norm": 3.9405393600463867, "learning_rate": 1.6711822660098524e-05, "loss": 1.3598, "step": 1074 }, { "epoch": 0.16537825468251222, "grad_norm": 3.8669769763946533, "learning_rate": 1.6708743842364534e-05, "loss": 1.3273, "step": 1075 }, { "epoch": 0.16553209491942616, "grad_norm": 3.700028657913208, "learning_rate": 1.6705665024630545e-05, "loss": 1.3743, "step": 1076 }, { "epoch": 0.16568593515634014, "grad_norm": 3.0118744373321533, "learning_rate": 1.6702586206896552e-05, "loss": 1.247, "step": 1077 }, { "epoch": 0.16583977539325412, "grad_norm": 3.9007797241210938, "learning_rate": 1.6699507389162563e-05, "loss": 1.4427, "step": 1078 }, { "epoch": 0.16599361563016807, "grad_norm": 4.189929008483887, "learning_rate": 1.6696428571428574e-05, "loss": 1.5029, "step": 1079 }, { "epoch": 0.16614745586708204, "grad_norm": 3.893942356109619, "learning_rate": 1.6693349753694584e-05, "loss": 1.5523, "step": 1080 }, { "epoch": 0.166301296103996, "grad_norm": 4.017568111419678, "learning_rate": 1.669027093596059e-05, "loss": 1.5519, "step": 1081 }, { "epoch": 0.16645513634090997, "grad_norm": 4.0624823570251465, "learning_rate": 1.6687192118226602e-05, "loss": 1.657, "step": 1082 }, { "epoch": 0.16660897657782392, "grad_norm": 4.04845666885376, "learning_rate": 1.6684113300492613e-05, "loss": 1.7221, "step": 1083 }, { "epoch": 0.1667628168147379, "grad_norm": 3.7872679233551025, "learning_rate": 1.6681034482758623e-05, "loss": 1.3256, "step": 1084 }, { "epoch": 0.16691665705165187, "grad_norm": 3.577735424041748, "learning_rate": 1.667795566502463e-05, "loss": 1.4435, "step": 1085 }, { "epoch": 0.16707049728856582, "grad_norm": 4.454763889312744, "learning_rate": 1.667487684729064e-05, "loss": 1.123, "step": 1086 }, { "epoch": 0.1672243375254798, "grad_norm": 3.949857234954834, "learning_rate": 1.6671798029556652e-05, "loss": 1.2953, "step": 1087 }, { "epoch": 0.16737817776239375, "grad_norm": 3.955124616622925, "learning_rate": 1.6668719211822663e-05, "loss": 1.3348, "step": 1088 }, { "epoch": 0.16753201799930773, "grad_norm": 3.776975154876709, "learning_rate": 1.666564039408867e-05, "loss": 1.6871, "step": 1089 }, { "epoch": 0.16768585823622167, "grad_norm": 3.9524052143096924, "learning_rate": 1.666256157635468e-05, "loss": 1.5905, "step": 1090 }, { "epoch": 0.16783969847313565, "grad_norm": 4.012238502502441, "learning_rate": 1.665948275862069e-05, "loss": 1.4361, "step": 1091 }, { "epoch": 0.1679935387100496, "grad_norm": 3.9353363513946533, "learning_rate": 1.6656403940886702e-05, "loss": 1.5191, "step": 1092 }, { "epoch": 0.16814737894696358, "grad_norm": 3.1141316890716553, "learning_rate": 1.665332512315271e-05, "loss": 1.4328, "step": 1093 }, { "epoch": 0.16830121918387755, "grad_norm": 3.9617080688476562, "learning_rate": 1.665024630541872e-05, "loss": 1.5067, "step": 1094 }, { "epoch": 0.1684550594207915, "grad_norm": 3.641610860824585, "learning_rate": 1.664716748768473e-05, "loss": 1.4947, "step": 1095 }, { "epoch": 0.16860889965770548, "grad_norm": 3.4605414867401123, "learning_rate": 1.664408866995074e-05, "loss": 1.4503, "step": 1096 }, { "epoch": 0.16876273989461943, "grad_norm": 3.582505702972412, "learning_rate": 1.6641009852216748e-05, "loss": 1.4236, "step": 1097 }, { "epoch": 0.1689165801315334, "grad_norm": 3.656860589981079, "learning_rate": 1.663793103448276e-05, "loss": 1.2642, "step": 1098 }, { "epoch": 0.16907042036844735, "grad_norm": 3.5979230403900146, "learning_rate": 1.663485221674877e-05, "loss": 1.357, "step": 1099 }, { "epoch": 0.16922426060536133, "grad_norm": 2.9169890880584717, "learning_rate": 1.663177339901478e-05, "loss": 1.4433, "step": 1100 }, { "epoch": 0.1693781008422753, "grad_norm": 3.763446807861328, "learning_rate": 1.6628694581280787e-05, "loss": 1.4711, "step": 1101 }, { "epoch": 0.16953194107918926, "grad_norm": 3.3110289573669434, "learning_rate": 1.6625615763546798e-05, "loss": 1.3765, "step": 1102 }, { "epoch": 0.16968578131610323, "grad_norm": 3.323483467102051, "learning_rate": 1.662253694581281e-05, "loss": 1.4545, "step": 1103 }, { "epoch": 0.16983962155301718, "grad_norm": 4.1291608810424805, "learning_rate": 1.661945812807882e-05, "loss": 1.4014, "step": 1104 }, { "epoch": 0.16999346178993116, "grad_norm": 4.059236526489258, "learning_rate": 1.6616379310344827e-05, "loss": 1.6325, "step": 1105 }, { "epoch": 0.1701473020268451, "grad_norm": 3.0143747329711914, "learning_rate": 1.661330049261084e-05, "loss": 1.3837, "step": 1106 }, { "epoch": 0.1703011422637591, "grad_norm": 3.4566729068756104, "learning_rate": 1.661022167487685e-05, "loss": 1.3205, "step": 1107 }, { "epoch": 0.17045498250067306, "grad_norm": 3.175044298171997, "learning_rate": 1.660714285714286e-05, "loss": 1.4098, "step": 1108 }, { "epoch": 0.170608822737587, "grad_norm": 3.946209669113159, "learning_rate": 1.660406403940887e-05, "loss": 1.3708, "step": 1109 }, { "epoch": 0.170762662974501, "grad_norm": 3.3105063438415527, "learning_rate": 1.660098522167488e-05, "loss": 1.5876, "step": 1110 }, { "epoch": 0.17091650321141494, "grad_norm": 3.8672144412994385, "learning_rate": 1.6597906403940887e-05, "loss": 1.5047, "step": 1111 }, { "epoch": 0.17107034344832892, "grad_norm": 3.8865771293640137, "learning_rate": 1.6594827586206898e-05, "loss": 1.6442, "step": 1112 }, { "epoch": 0.17122418368524286, "grad_norm": 3.266570568084717, "learning_rate": 1.659174876847291e-05, "loss": 1.3958, "step": 1113 }, { "epoch": 0.17137802392215684, "grad_norm": 3.2585346698760986, "learning_rate": 1.658866995073892e-05, "loss": 1.3161, "step": 1114 }, { "epoch": 0.17153186415907082, "grad_norm": 3.5074548721313477, "learning_rate": 1.6585591133004926e-05, "loss": 1.3385, "step": 1115 }, { "epoch": 0.17168570439598477, "grad_norm": 3.4991979598999023, "learning_rate": 1.6582512315270937e-05, "loss": 1.4609, "step": 1116 }, { "epoch": 0.17183954463289874, "grad_norm": 4.258903503417969, "learning_rate": 1.6579433497536948e-05, "loss": 1.5262, "step": 1117 }, { "epoch": 0.1719933848698127, "grad_norm": 3.639997720718384, "learning_rate": 1.6576354679802958e-05, "loss": 1.1925, "step": 1118 }, { "epoch": 0.17214722510672667, "grad_norm": 3.912903308868408, "learning_rate": 1.6573275862068966e-05, "loss": 1.4732, "step": 1119 }, { "epoch": 0.17230106534364062, "grad_norm": 5.028310775756836, "learning_rate": 1.6570197044334976e-05, "loss": 1.6725, "step": 1120 }, { "epoch": 0.1724549055805546, "grad_norm": 3.427211046218872, "learning_rate": 1.6567118226600987e-05, "loss": 1.528, "step": 1121 }, { "epoch": 0.17260874581746855, "grad_norm": 3.9269778728485107, "learning_rate": 1.6564039408866997e-05, "loss": 1.5923, "step": 1122 }, { "epoch": 0.17276258605438252, "grad_norm": 2.863664150238037, "learning_rate": 1.6560960591133005e-05, "loss": 1.5339, "step": 1123 }, { "epoch": 0.1729164262912965, "grad_norm": 4.088393211364746, "learning_rate": 1.6557881773399015e-05, "loss": 1.3766, "step": 1124 }, { "epoch": 0.17307026652821045, "grad_norm": 3.4405062198638916, "learning_rate": 1.6554802955665026e-05, "loss": 1.535, "step": 1125 }, { "epoch": 0.17322410676512442, "grad_norm": 3.426335096359253, "learning_rate": 1.6551724137931037e-05, "loss": 1.3057, "step": 1126 }, { "epoch": 0.17337794700203837, "grad_norm": 3.625657081604004, "learning_rate": 1.6548645320197044e-05, "loss": 1.6527, "step": 1127 }, { "epoch": 0.17353178723895235, "grad_norm": 2.909954786300659, "learning_rate": 1.6545566502463055e-05, "loss": 1.1737, "step": 1128 }, { "epoch": 0.1736856274758663, "grad_norm": 3.404543399810791, "learning_rate": 1.6542487684729065e-05, "loss": 1.3364, "step": 1129 }, { "epoch": 0.17383946771278028, "grad_norm": 3.471806764602661, "learning_rate": 1.6539408866995076e-05, "loss": 1.5686, "step": 1130 }, { "epoch": 0.17399330794969425, "grad_norm": 4.102113246917725, "learning_rate": 1.6536330049261083e-05, "loss": 1.5032, "step": 1131 }, { "epoch": 0.1741471481866082, "grad_norm": 3.7107133865356445, "learning_rate": 1.6533251231527094e-05, "loss": 1.5028, "step": 1132 }, { "epoch": 0.17430098842352218, "grad_norm": 3.588568925857544, "learning_rate": 1.6530172413793104e-05, "loss": 1.2436, "step": 1133 }, { "epoch": 0.17445482866043613, "grad_norm": 4.210711479187012, "learning_rate": 1.6527093596059115e-05, "loss": 1.4795, "step": 1134 }, { "epoch": 0.1746086688973501, "grad_norm": 3.407460927963257, "learning_rate": 1.6524014778325122e-05, "loss": 1.6846, "step": 1135 }, { "epoch": 0.17476250913426405, "grad_norm": 2.8422563076019287, "learning_rate": 1.6520935960591133e-05, "loss": 1.1152, "step": 1136 }, { "epoch": 0.17491634937117803, "grad_norm": 3.8069558143615723, "learning_rate": 1.6517857142857144e-05, "loss": 1.4718, "step": 1137 }, { "epoch": 0.175070189608092, "grad_norm": 3.391810655593872, "learning_rate": 1.6514778325123154e-05, "loss": 1.4166, "step": 1138 }, { "epoch": 0.17522402984500596, "grad_norm": 3.4259583950042725, "learning_rate": 1.651169950738916e-05, "loss": 1.4681, "step": 1139 }, { "epoch": 0.17537787008191993, "grad_norm": 3.847228527069092, "learning_rate": 1.6508620689655176e-05, "loss": 1.4318, "step": 1140 }, { "epoch": 0.17553171031883388, "grad_norm": 3.220391273498535, "learning_rate": 1.6505541871921186e-05, "loss": 1.4628, "step": 1141 }, { "epoch": 0.17568555055574786, "grad_norm": 3.5189433097839355, "learning_rate": 1.6502463054187193e-05, "loss": 1.3465, "step": 1142 }, { "epoch": 0.1758393907926618, "grad_norm": 3.674731731414795, "learning_rate": 1.6499384236453204e-05, "loss": 1.2591, "step": 1143 }, { "epoch": 0.1759932310295758, "grad_norm": 4.3900837898254395, "learning_rate": 1.6496305418719215e-05, "loss": 1.2816, "step": 1144 }, { "epoch": 0.17614707126648976, "grad_norm": 3.4305312633514404, "learning_rate": 1.6493226600985225e-05, "loss": 1.1648, "step": 1145 }, { "epoch": 0.1763009115034037, "grad_norm": 3.855135917663574, "learning_rate": 1.6490147783251233e-05, "loss": 1.5548, "step": 1146 }, { "epoch": 0.1764547517403177, "grad_norm": 4.338353157043457, "learning_rate": 1.6487068965517243e-05, "loss": 1.4075, "step": 1147 }, { "epoch": 0.17660859197723164, "grad_norm": 3.960080862045288, "learning_rate": 1.6483990147783254e-05, "loss": 1.5235, "step": 1148 }, { "epoch": 0.17676243221414562, "grad_norm": 3.5762414932250977, "learning_rate": 1.6480911330049265e-05, "loss": 1.4414, "step": 1149 }, { "epoch": 0.17691627245105956, "grad_norm": 4.416323184967041, "learning_rate": 1.6477832512315272e-05, "loss": 1.4685, "step": 1150 }, { "epoch": 0.17707011268797354, "grad_norm": 4.215223789215088, "learning_rate": 1.6474753694581282e-05, "loss": 1.2048, "step": 1151 }, { "epoch": 0.17722395292488752, "grad_norm": 3.294640302658081, "learning_rate": 1.6471674876847293e-05, "loss": 1.3733, "step": 1152 }, { "epoch": 0.17737779316180147, "grad_norm": 2.9518275260925293, "learning_rate": 1.6468596059113304e-05, "loss": 1.4074, "step": 1153 }, { "epoch": 0.17753163339871544, "grad_norm": 3.440004825592041, "learning_rate": 1.646551724137931e-05, "loss": 1.393, "step": 1154 }, { "epoch": 0.1776854736356294, "grad_norm": 3.4910976886749268, "learning_rate": 1.646243842364532e-05, "loss": 1.4018, "step": 1155 }, { "epoch": 0.17783931387254337, "grad_norm": 3.3454318046569824, "learning_rate": 1.6459359605911332e-05, "loss": 1.5287, "step": 1156 }, { "epoch": 0.17799315410945732, "grad_norm": 4.004363536834717, "learning_rate": 1.645628078817734e-05, "loss": 1.2117, "step": 1157 }, { "epoch": 0.1781469943463713, "grad_norm": 4.098826885223389, "learning_rate": 1.645320197044335e-05, "loss": 1.4591, "step": 1158 }, { "epoch": 0.17830083458328524, "grad_norm": 3.5531089305877686, "learning_rate": 1.645012315270936e-05, "loss": 1.495, "step": 1159 }, { "epoch": 0.17845467482019922, "grad_norm": 3.635902166366577, "learning_rate": 1.644704433497537e-05, "loss": 1.5128, "step": 1160 }, { "epoch": 0.1786085150571132, "grad_norm": 3.6857893466949463, "learning_rate": 1.644396551724138e-05, "loss": 1.2481, "step": 1161 }, { "epoch": 0.17876235529402715, "grad_norm": 3.831865072250366, "learning_rate": 1.644088669950739e-05, "loss": 1.4643, "step": 1162 }, { "epoch": 0.17891619553094112, "grad_norm": 3.5373332500457764, "learning_rate": 1.64378078817734e-05, "loss": 1.3245, "step": 1163 }, { "epoch": 0.17907003576785507, "grad_norm": 3.357659101486206, "learning_rate": 1.643472906403941e-05, "loss": 1.1812, "step": 1164 }, { "epoch": 0.17922387600476905, "grad_norm": 3.594280242919922, "learning_rate": 1.6431650246305418e-05, "loss": 1.5106, "step": 1165 }, { "epoch": 0.179377716241683, "grad_norm": 3.3718039989471436, "learning_rate": 1.642857142857143e-05, "loss": 1.4736, "step": 1166 }, { "epoch": 0.17953155647859698, "grad_norm": 3.947005271911621, "learning_rate": 1.642549261083744e-05, "loss": 1.4853, "step": 1167 }, { "epoch": 0.17968539671551095, "grad_norm": 3.845228910446167, "learning_rate": 1.642241379310345e-05, "loss": 1.2952, "step": 1168 }, { "epoch": 0.1798392369524249, "grad_norm": 3.7643818855285645, "learning_rate": 1.6419334975369457e-05, "loss": 1.5437, "step": 1169 }, { "epoch": 0.17999307718933888, "grad_norm": 4.512478351593018, "learning_rate": 1.6416256157635468e-05, "loss": 1.0696, "step": 1170 }, { "epoch": 0.18014691742625283, "grad_norm": 3.343196392059326, "learning_rate": 1.641317733990148e-05, "loss": 1.3239, "step": 1171 }, { "epoch": 0.1803007576631668, "grad_norm": 3.2533397674560547, "learning_rate": 1.641009852216749e-05, "loss": 1.54, "step": 1172 }, { "epoch": 0.18045459790008075, "grad_norm": 3.1725449562072754, "learning_rate": 1.6407019704433496e-05, "loss": 1.588, "step": 1173 }, { "epoch": 0.18060843813699473, "grad_norm": 3.699810266494751, "learning_rate": 1.640394088669951e-05, "loss": 1.4782, "step": 1174 }, { "epoch": 0.1807622783739087, "grad_norm": 3.576737880706787, "learning_rate": 1.640086206896552e-05, "loss": 1.5278, "step": 1175 }, { "epoch": 0.18091611861082266, "grad_norm": 3.5789291858673096, "learning_rate": 1.6397783251231528e-05, "loss": 1.5747, "step": 1176 }, { "epoch": 0.18106995884773663, "grad_norm": 3.7395098209381104, "learning_rate": 1.639470443349754e-05, "loss": 1.3298, "step": 1177 }, { "epoch": 0.18122379908465058, "grad_norm": 3.808439016342163, "learning_rate": 1.639162561576355e-05, "loss": 1.5525, "step": 1178 }, { "epoch": 0.18137763932156456, "grad_norm": 3.453744649887085, "learning_rate": 1.638854679802956e-05, "loss": 1.4779, "step": 1179 }, { "epoch": 0.1815314795584785, "grad_norm": 3.882368803024292, "learning_rate": 1.6385467980295567e-05, "loss": 1.4932, "step": 1180 }, { "epoch": 0.18168531979539249, "grad_norm": 4.166224002838135, "learning_rate": 1.6382389162561578e-05, "loss": 1.6538, "step": 1181 }, { "epoch": 0.18183916003230646, "grad_norm": 4.16793155670166, "learning_rate": 1.637931034482759e-05, "loss": 1.4102, "step": 1182 }, { "epoch": 0.1819930002692204, "grad_norm": 4.19415283203125, "learning_rate": 1.63762315270936e-05, "loss": 1.2586, "step": 1183 }, { "epoch": 0.1821468405061344, "grad_norm": 4.287524700164795, "learning_rate": 1.6373152709359607e-05, "loss": 1.4855, "step": 1184 }, { "epoch": 0.18230068074304834, "grad_norm": 3.514824151992798, "learning_rate": 1.6370073891625617e-05, "loss": 1.5546, "step": 1185 }, { "epoch": 0.18245452097996231, "grad_norm": 4.004525661468506, "learning_rate": 1.6366995073891628e-05, "loss": 1.4553, "step": 1186 }, { "epoch": 0.18260836121687626, "grad_norm": 3.5744030475616455, "learning_rate": 1.636391625615764e-05, "loss": 1.3398, "step": 1187 }, { "epoch": 0.18276220145379024, "grad_norm": 3.47163724899292, "learning_rate": 1.6360837438423646e-05, "loss": 1.6417, "step": 1188 }, { "epoch": 0.18291604169070422, "grad_norm": 3.4154083728790283, "learning_rate": 1.6357758620689656e-05, "loss": 1.4871, "step": 1189 }, { "epoch": 0.18306988192761817, "grad_norm": 3.604259729385376, "learning_rate": 1.6354679802955667e-05, "loss": 1.4508, "step": 1190 }, { "epoch": 0.18322372216453214, "grad_norm": 4.005915641784668, "learning_rate": 1.6351600985221678e-05, "loss": 1.1718, "step": 1191 }, { "epoch": 0.1833775624014461, "grad_norm": 3.858020305633545, "learning_rate": 1.6348522167487685e-05, "loss": 1.3981, "step": 1192 }, { "epoch": 0.18353140263836007, "grad_norm": 3.9968175888061523, "learning_rate": 1.6345443349753696e-05, "loss": 1.446, "step": 1193 }, { "epoch": 0.18368524287527402, "grad_norm": 3.9230432510375977, "learning_rate": 1.6342364532019706e-05, "loss": 1.6607, "step": 1194 }, { "epoch": 0.183839083112188, "grad_norm": 4.4227728843688965, "learning_rate": 1.6339285714285717e-05, "loss": 1.49, "step": 1195 }, { "epoch": 0.18399292334910194, "grad_norm": 4.371262073516846, "learning_rate": 1.6336206896551724e-05, "loss": 1.4342, "step": 1196 }, { "epoch": 0.18414676358601592, "grad_norm": 4.588959217071533, "learning_rate": 1.6333128078817735e-05, "loss": 1.1346, "step": 1197 }, { "epoch": 0.1843006038229299, "grad_norm": 4.367750644683838, "learning_rate": 1.6330049261083746e-05, "loss": 1.6834, "step": 1198 }, { "epoch": 0.18445444405984385, "grad_norm": 3.51003360748291, "learning_rate": 1.6326970443349753e-05, "loss": 1.5811, "step": 1199 }, { "epoch": 0.18460828429675782, "grad_norm": 3.9103636741638184, "learning_rate": 1.6323891625615763e-05, "loss": 1.3413, "step": 1200 }, { "epoch": 0.18476212453367177, "grad_norm": 3.394361972808838, "learning_rate": 1.6320812807881774e-05, "loss": 1.3173, "step": 1201 }, { "epoch": 0.18491596477058575, "grad_norm": 3.601736307144165, "learning_rate": 1.6317733990147785e-05, "loss": 1.6761, "step": 1202 }, { "epoch": 0.1850698050074997, "grad_norm": 3.593862533569336, "learning_rate": 1.6314655172413792e-05, "loss": 1.2652, "step": 1203 }, { "epoch": 0.18522364524441368, "grad_norm": 4.894131183624268, "learning_rate": 1.6311576354679803e-05, "loss": 1.2165, "step": 1204 }, { "epoch": 0.18537748548132765, "grad_norm": 4.036154270172119, "learning_rate": 1.6308497536945813e-05, "loss": 1.2947, "step": 1205 }, { "epoch": 0.1855313257182416, "grad_norm": 4.112147331237793, "learning_rate": 1.6305418719211824e-05, "loss": 1.2169, "step": 1206 }, { "epoch": 0.18568516595515558, "grad_norm": 3.345982074737549, "learning_rate": 1.630233990147783e-05, "loss": 1.2673, "step": 1207 }, { "epoch": 0.18583900619206953, "grad_norm": 4.127015113830566, "learning_rate": 1.6299261083743845e-05, "loss": 1.4329, "step": 1208 }, { "epoch": 0.1859928464289835, "grad_norm": 3.640613079071045, "learning_rate": 1.6296182266009856e-05, "loss": 1.4421, "step": 1209 }, { "epoch": 0.18614668666589745, "grad_norm": 3.5703675746917725, "learning_rate": 1.6293103448275863e-05, "loss": 1.4014, "step": 1210 }, { "epoch": 0.18630052690281143, "grad_norm": 4.222594261169434, "learning_rate": 1.6290024630541874e-05, "loss": 1.5865, "step": 1211 }, { "epoch": 0.1864543671397254, "grad_norm": 3.2982640266418457, "learning_rate": 1.6286945812807884e-05, "loss": 1.136, "step": 1212 }, { "epoch": 0.18660820737663936, "grad_norm": 3.9698827266693115, "learning_rate": 1.6283866995073895e-05, "loss": 1.4138, "step": 1213 }, { "epoch": 0.18676204761355333, "grad_norm": 3.8470308780670166, "learning_rate": 1.6280788177339902e-05, "loss": 1.3484, "step": 1214 }, { "epoch": 0.18691588785046728, "grad_norm": 4.193209648132324, "learning_rate": 1.6277709359605913e-05, "loss": 1.4724, "step": 1215 }, { "epoch": 0.18706972808738126, "grad_norm": 3.378185987472534, "learning_rate": 1.6274630541871924e-05, "loss": 1.366, "step": 1216 }, { "epoch": 0.1872235683242952, "grad_norm": 3.6878578662872314, "learning_rate": 1.6271551724137934e-05, "loss": 1.1527, "step": 1217 }, { "epoch": 0.18737740856120919, "grad_norm": 3.5435903072357178, "learning_rate": 1.626847290640394e-05, "loss": 1.4173, "step": 1218 }, { "epoch": 0.18753124879812316, "grad_norm": 3.3159148693084717, "learning_rate": 1.6265394088669952e-05, "loss": 1.4156, "step": 1219 }, { "epoch": 0.1876850890350371, "grad_norm": 3.356900691986084, "learning_rate": 1.6262315270935963e-05, "loss": 1.2919, "step": 1220 }, { "epoch": 0.1878389292719511, "grad_norm": 3.5600976943969727, "learning_rate": 1.6259236453201973e-05, "loss": 1.4155, "step": 1221 }, { "epoch": 0.18799276950886504, "grad_norm": 4.166362285614014, "learning_rate": 1.625615763546798e-05, "loss": 1.35, "step": 1222 }, { "epoch": 0.18814660974577901, "grad_norm": 4.157646656036377, "learning_rate": 1.625307881773399e-05, "loss": 1.4569, "step": 1223 }, { "epoch": 0.18830044998269296, "grad_norm": 3.9852142333984375, "learning_rate": 1.6250000000000002e-05, "loss": 1.3688, "step": 1224 }, { "epoch": 0.18845429021960694, "grad_norm": 3.464026927947998, "learning_rate": 1.6246921182266013e-05, "loss": 1.4993, "step": 1225 }, { "epoch": 0.1886081304565209, "grad_norm": 3.800675392150879, "learning_rate": 1.624384236453202e-05, "loss": 1.5149, "step": 1226 }, { "epoch": 0.18876197069343487, "grad_norm": 3.080294132232666, "learning_rate": 1.624076354679803e-05, "loss": 1.0189, "step": 1227 }, { "epoch": 0.18891581093034884, "grad_norm": 3.8506598472595215, "learning_rate": 1.623768472906404e-05, "loss": 1.3531, "step": 1228 }, { "epoch": 0.1890696511672628, "grad_norm": 3.8933730125427246, "learning_rate": 1.6234605911330052e-05, "loss": 1.1346, "step": 1229 }, { "epoch": 0.18922349140417677, "grad_norm": 3.6241495609283447, "learning_rate": 1.623152709359606e-05, "loss": 1.5272, "step": 1230 }, { "epoch": 0.18937733164109072, "grad_norm": 3.2408149242401123, "learning_rate": 1.622844827586207e-05, "loss": 1.48, "step": 1231 }, { "epoch": 0.1895311718780047, "grad_norm": 3.5945935249328613, "learning_rate": 1.622536945812808e-05, "loss": 1.3521, "step": 1232 }, { "epoch": 0.18968501211491864, "grad_norm": 4.285059928894043, "learning_rate": 1.622229064039409e-05, "loss": 1.4997, "step": 1233 }, { "epoch": 0.18983885235183262, "grad_norm": 3.538203477859497, "learning_rate": 1.6219211822660098e-05, "loss": 1.487, "step": 1234 }, { "epoch": 0.1899926925887466, "grad_norm": 3.3582582473754883, "learning_rate": 1.621613300492611e-05, "loss": 1.2725, "step": 1235 }, { "epoch": 0.19014653282566055, "grad_norm": 4.247774600982666, "learning_rate": 1.621305418719212e-05, "loss": 1.4567, "step": 1236 }, { "epoch": 0.19030037306257452, "grad_norm": 3.2379119396209717, "learning_rate": 1.620997536945813e-05, "loss": 1.5176, "step": 1237 }, { "epoch": 0.19045421329948847, "grad_norm": 3.885934829711914, "learning_rate": 1.6206896551724137e-05, "loss": 1.4298, "step": 1238 }, { "epoch": 0.19060805353640245, "grad_norm": 3.7553255558013916, "learning_rate": 1.6203817733990148e-05, "loss": 1.7569, "step": 1239 }, { "epoch": 0.1907618937733164, "grad_norm": 3.571410655975342, "learning_rate": 1.620073891625616e-05, "loss": 1.1971, "step": 1240 }, { "epoch": 0.19091573401023038, "grad_norm": 4.207669734954834, "learning_rate": 1.619766009852217e-05, "loss": 1.1012, "step": 1241 }, { "epoch": 0.19106957424714435, "grad_norm": 4.036749362945557, "learning_rate": 1.619458128078818e-05, "loss": 1.5845, "step": 1242 }, { "epoch": 0.1912234144840583, "grad_norm": 3.9223530292510986, "learning_rate": 1.619150246305419e-05, "loss": 1.4326, "step": 1243 }, { "epoch": 0.19137725472097228, "grad_norm": 3.817096471786499, "learning_rate": 1.6188423645320198e-05, "loss": 1.4773, "step": 1244 }, { "epoch": 0.19153109495788623, "grad_norm": 3.0786538124084473, "learning_rate": 1.618534482758621e-05, "loss": 1.3473, "step": 1245 }, { "epoch": 0.1916849351948002, "grad_norm": 3.5816895961761475, "learning_rate": 1.618226600985222e-05, "loss": 1.4364, "step": 1246 }, { "epoch": 0.19183877543171415, "grad_norm": 3.8814074993133545, "learning_rate": 1.617918719211823e-05, "loss": 1.2245, "step": 1247 }, { "epoch": 0.19199261566862813, "grad_norm": 3.323338747024536, "learning_rate": 1.6176108374384237e-05, "loss": 1.4511, "step": 1248 }, { "epoch": 0.1921464559055421, "grad_norm": 4.726086616516113, "learning_rate": 1.6173029556650248e-05, "loss": 1.3973, "step": 1249 }, { "epoch": 0.19230029614245606, "grad_norm": 3.8804354667663574, "learning_rate": 1.616995073891626e-05, "loss": 1.8604, "step": 1250 }, { "epoch": 0.19245413637937003, "grad_norm": 3.9554784297943115, "learning_rate": 1.616687192118227e-05, "loss": 1.4413, "step": 1251 }, { "epoch": 0.19260797661628398, "grad_norm": 3.653107166290283, "learning_rate": 1.6163793103448276e-05, "loss": 1.5734, "step": 1252 }, { "epoch": 0.19276181685319796, "grad_norm": 3.601043701171875, "learning_rate": 1.6160714285714287e-05, "loss": 1.2789, "step": 1253 }, { "epoch": 0.1929156570901119, "grad_norm": 3.6977829933166504, "learning_rate": 1.6157635467980298e-05, "loss": 1.3524, "step": 1254 }, { "epoch": 0.19306949732702589, "grad_norm": 3.8834681510925293, "learning_rate": 1.6154556650246308e-05, "loss": 1.3499, "step": 1255 }, { "epoch": 0.19322333756393986, "grad_norm": 3.968182325363159, "learning_rate": 1.6151477832512316e-05, "loss": 1.2808, "step": 1256 }, { "epoch": 0.1933771778008538, "grad_norm": 3.3689308166503906, "learning_rate": 1.6148399014778326e-05, "loss": 1.2713, "step": 1257 }, { "epoch": 0.1935310180377678, "grad_norm": 3.8897697925567627, "learning_rate": 1.6145320197044337e-05, "loss": 1.583, "step": 1258 }, { "epoch": 0.19368485827468174, "grad_norm": 3.8058910369873047, "learning_rate": 1.6142241379310347e-05, "loss": 1.5447, "step": 1259 }, { "epoch": 0.19383869851159571, "grad_norm": 3.3721330165863037, "learning_rate": 1.6139162561576355e-05, "loss": 1.5347, "step": 1260 }, { "epoch": 0.19399253874850966, "grad_norm": 3.766221284866333, "learning_rate": 1.6136083743842365e-05, "loss": 1.3535, "step": 1261 }, { "epoch": 0.19414637898542364, "grad_norm": 4.558411121368408, "learning_rate": 1.6133004926108376e-05, "loss": 1.6379, "step": 1262 }, { "epoch": 0.1943002192223376, "grad_norm": 3.580362319946289, "learning_rate": 1.6129926108374387e-05, "loss": 1.5514, "step": 1263 }, { "epoch": 0.19445405945925157, "grad_norm": 3.141549587249756, "learning_rate": 1.6126847290640394e-05, "loss": 1.2575, "step": 1264 }, { "epoch": 0.19460789969616554, "grad_norm": 3.736396312713623, "learning_rate": 1.6123768472906405e-05, "loss": 1.6736, "step": 1265 }, { "epoch": 0.1947617399330795, "grad_norm": 4.00622034072876, "learning_rate": 1.6120689655172415e-05, "loss": 1.3783, "step": 1266 }, { "epoch": 0.19491558016999347, "grad_norm": 3.6404175758361816, "learning_rate": 1.6117610837438426e-05, "loss": 1.3946, "step": 1267 }, { "epoch": 0.19506942040690742, "grad_norm": 4.015316963195801, "learning_rate": 1.6114532019704433e-05, "loss": 1.3659, "step": 1268 }, { "epoch": 0.1952232606438214, "grad_norm": 4.081803321838379, "learning_rate": 1.6111453201970444e-05, "loss": 1.2938, "step": 1269 }, { "epoch": 0.19537710088073534, "grad_norm": 4.026861667633057, "learning_rate": 1.6108374384236454e-05, "loss": 1.3731, "step": 1270 }, { "epoch": 0.19553094111764932, "grad_norm": 4.440724849700928, "learning_rate": 1.6105295566502465e-05, "loss": 1.5655, "step": 1271 }, { "epoch": 0.1956847813545633, "grad_norm": 3.684708595275879, "learning_rate": 1.6102216748768472e-05, "loss": 1.3854, "step": 1272 }, { "epoch": 0.19583862159147725, "grad_norm": 4.4832844734191895, "learning_rate": 1.6099137931034483e-05, "loss": 1.6627, "step": 1273 }, { "epoch": 0.19599246182839122, "grad_norm": 3.8768982887268066, "learning_rate": 1.6096059113300494e-05, "loss": 1.6974, "step": 1274 }, { "epoch": 0.19614630206530517, "grad_norm": 3.3707633018493652, "learning_rate": 1.6092980295566504e-05, "loss": 1.5863, "step": 1275 }, { "epoch": 0.19630014230221915, "grad_norm": 4.199832439422607, "learning_rate": 1.6089901477832515e-05, "loss": 1.1943, "step": 1276 }, { "epoch": 0.1964539825391331, "grad_norm": 4.235736846923828, "learning_rate": 1.6086822660098526e-05, "loss": 1.5871, "step": 1277 }, { "epoch": 0.19660782277604708, "grad_norm": 3.701032876968384, "learning_rate": 1.6083743842364533e-05, "loss": 1.6112, "step": 1278 }, { "epoch": 0.19676166301296105, "grad_norm": 4.2163286209106445, "learning_rate": 1.6080665024630543e-05, "loss": 1.6014, "step": 1279 }, { "epoch": 0.196915503249875, "grad_norm": 3.4419639110565186, "learning_rate": 1.6077586206896554e-05, "loss": 1.491, "step": 1280 }, { "epoch": 0.19706934348678898, "grad_norm": 3.5918028354644775, "learning_rate": 1.6074507389162565e-05, "loss": 1.3913, "step": 1281 }, { "epoch": 0.19722318372370293, "grad_norm": 3.650346279144287, "learning_rate": 1.6071428571428572e-05, "loss": 1.4745, "step": 1282 }, { "epoch": 0.1973770239606169, "grad_norm": 4.191429138183594, "learning_rate": 1.6068349753694583e-05, "loss": 1.2313, "step": 1283 }, { "epoch": 0.19753086419753085, "grad_norm": 3.1915833950042725, "learning_rate": 1.6065270935960593e-05, "loss": 1.6093, "step": 1284 }, { "epoch": 0.19768470443444483, "grad_norm": 3.1069047451019287, "learning_rate": 1.6062192118226604e-05, "loss": 1.2195, "step": 1285 }, { "epoch": 0.1978385446713588, "grad_norm": 4.059824466705322, "learning_rate": 1.605911330049261e-05, "loss": 1.6493, "step": 1286 }, { "epoch": 0.19799238490827276, "grad_norm": 3.6340384483337402, "learning_rate": 1.6056034482758622e-05, "loss": 1.2863, "step": 1287 }, { "epoch": 0.19814622514518673, "grad_norm": 4.083619594573975, "learning_rate": 1.6052955665024632e-05, "loss": 1.4355, "step": 1288 }, { "epoch": 0.19830006538210068, "grad_norm": 3.4604744911193848, "learning_rate": 1.6049876847290643e-05, "loss": 1.3589, "step": 1289 }, { "epoch": 0.19845390561901466, "grad_norm": 3.4574339389801025, "learning_rate": 1.604679802955665e-05, "loss": 1.3444, "step": 1290 }, { "epoch": 0.1986077458559286, "grad_norm": 3.6581006050109863, "learning_rate": 1.604371921182266e-05, "loss": 1.4827, "step": 1291 }, { "epoch": 0.19876158609284258, "grad_norm": 4.136789798736572, "learning_rate": 1.604064039408867e-05, "loss": 1.4627, "step": 1292 }, { "epoch": 0.19891542632975656, "grad_norm": 4.312445163726807, "learning_rate": 1.6037561576354682e-05, "loss": 1.4917, "step": 1293 }, { "epoch": 0.1990692665666705, "grad_norm": 3.707879066467285, "learning_rate": 1.603448275862069e-05, "loss": 1.3747, "step": 1294 }, { "epoch": 0.1992231068035845, "grad_norm": 4.073413848876953, "learning_rate": 1.60314039408867e-05, "loss": 1.7027, "step": 1295 }, { "epoch": 0.19937694704049844, "grad_norm": 3.6213011741638184, "learning_rate": 1.602832512315271e-05, "loss": 1.3958, "step": 1296 }, { "epoch": 0.1995307872774124, "grad_norm": 4.406051158905029, "learning_rate": 1.602524630541872e-05, "loss": 1.4041, "step": 1297 }, { "epoch": 0.19968462751432636, "grad_norm": 3.0079145431518555, "learning_rate": 1.602216748768473e-05, "loss": 1.2469, "step": 1298 }, { "epoch": 0.19983846775124034, "grad_norm": 4.120666027069092, "learning_rate": 1.601908866995074e-05, "loss": 1.5061, "step": 1299 }, { "epoch": 0.1999923079881543, "grad_norm": 3.4665443897247314, "learning_rate": 1.601600985221675e-05, "loss": 1.17, "step": 1300 }, { "epoch": 0.20014614822506827, "grad_norm": 4.192742824554443, "learning_rate": 1.601293103448276e-05, "loss": 1.3358, "step": 1301 }, { "epoch": 0.20029998846198224, "grad_norm": 4.429152488708496, "learning_rate": 1.6009852216748768e-05, "loss": 1.4512, "step": 1302 }, { "epoch": 0.2004538286988962, "grad_norm": 4.289827823638916, "learning_rate": 1.600677339901478e-05, "loss": 1.4663, "step": 1303 }, { "epoch": 0.20060766893581017, "grad_norm": 3.1524465084075928, "learning_rate": 1.600369458128079e-05, "loss": 1.3676, "step": 1304 }, { "epoch": 0.20076150917272412, "grad_norm": 3.636185884475708, "learning_rate": 1.60006157635468e-05, "loss": 1.4273, "step": 1305 }, { "epoch": 0.2009153494096381, "grad_norm": 4.179900169372559, "learning_rate": 1.5997536945812807e-05, "loss": 1.4386, "step": 1306 }, { "epoch": 0.20106918964655204, "grad_norm": 3.7893331050872803, "learning_rate": 1.5994458128078818e-05, "loss": 1.5497, "step": 1307 }, { "epoch": 0.20122302988346602, "grad_norm": 3.5317223072052, "learning_rate": 1.599137931034483e-05, "loss": 1.3329, "step": 1308 }, { "epoch": 0.20137687012038, "grad_norm": 4.0980353355407715, "learning_rate": 1.598830049261084e-05, "loss": 1.4218, "step": 1309 }, { "epoch": 0.20153071035729395, "grad_norm": 3.6966443061828613, "learning_rate": 1.598522167487685e-05, "loss": 1.1845, "step": 1310 }, { "epoch": 0.20168455059420792, "grad_norm": 3.5610172748565674, "learning_rate": 1.598214285714286e-05, "loss": 1.5778, "step": 1311 }, { "epoch": 0.20183839083112187, "grad_norm": 3.9364266395568848, "learning_rate": 1.5979064039408868e-05, "loss": 1.4964, "step": 1312 }, { "epoch": 0.20199223106803585, "grad_norm": 3.703179121017456, "learning_rate": 1.5975985221674878e-05, "loss": 1.2678, "step": 1313 }, { "epoch": 0.2021460713049498, "grad_norm": 4.010179042816162, "learning_rate": 1.597290640394089e-05, "loss": 1.1697, "step": 1314 }, { "epoch": 0.20229991154186377, "grad_norm": 3.3985321521759033, "learning_rate": 1.59698275862069e-05, "loss": 1.0437, "step": 1315 }, { "epoch": 0.20245375177877775, "grad_norm": 3.7428793907165527, "learning_rate": 1.5966748768472907e-05, "loss": 1.4241, "step": 1316 }, { "epoch": 0.2026075920156917, "grad_norm": 3.6895580291748047, "learning_rate": 1.5963669950738917e-05, "loss": 1.4876, "step": 1317 }, { "epoch": 0.20276143225260568, "grad_norm": 3.7481465339660645, "learning_rate": 1.5960591133004928e-05, "loss": 1.4707, "step": 1318 }, { "epoch": 0.20291527248951963, "grad_norm": 5.052331447601318, "learning_rate": 1.595751231527094e-05, "loss": 1.4138, "step": 1319 }, { "epoch": 0.2030691127264336, "grad_norm": 3.8000755310058594, "learning_rate": 1.5954433497536946e-05, "loss": 1.6486, "step": 1320 }, { "epoch": 0.20322295296334755, "grad_norm": 3.6464040279388428, "learning_rate": 1.5951354679802957e-05, "loss": 1.3642, "step": 1321 }, { "epoch": 0.20337679320026153, "grad_norm": 3.7633824348449707, "learning_rate": 1.5948275862068967e-05, "loss": 1.4401, "step": 1322 }, { "epoch": 0.2035306334371755, "grad_norm": 3.4183435440063477, "learning_rate": 1.5945197044334978e-05, "loss": 1.4522, "step": 1323 }, { "epoch": 0.20368447367408946, "grad_norm": 4.248505115509033, "learning_rate": 1.5942118226600985e-05, "loss": 1.28, "step": 1324 }, { "epoch": 0.20383831391100343, "grad_norm": 4.700088977813721, "learning_rate": 1.5939039408866996e-05, "loss": 1.4946, "step": 1325 }, { "epoch": 0.20399215414791738, "grad_norm": 3.841501474380493, "learning_rate": 1.5935960591133006e-05, "loss": 1.4703, "step": 1326 }, { "epoch": 0.20414599438483136, "grad_norm": 3.9810421466827393, "learning_rate": 1.5932881773399017e-05, "loss": 1.6475, "step": 1327 }, { "epoch": 0.2042998346217453, "grad_norm": 3.8439698219299316, "learning_rate": 1.5929802955665024e-05, "loss": 1.3507, "step": 1328 }, { "epoch": 0.20445367485865928, "grad_norm": 4.087709903717041, "learning_rate": 1.5926724137931035e-05, "loss": 0.8978, "step": 1329 }, { "epoch": 0.20460751509557323, "grad_norm": 4.048707485198975, "learning_rate": 1.5923645320197046e-05, "loss": 1.2532, "step": 1330 }, { "epoch": 0.2047613553324872, "grad_norm": 3.40911865234375, "learning_rate": 1.5920566502463056e-05, "loss": 1.5332, "step": 1331 }, { "epoch": 0.2049151955694012, "grad_norm": 4.279049396514893, "learning_rate": 1.5917487684729064e-05, "loss": 1.6438, "step": 1332 }, { "epoch": 0.20506903580631514, "grad_norm": 3.4227750301361084, "learning_rate": 1.5914408866995074e-05, "loss": 1.2395, "step": 1333 }, { "epoch": 0.2052228760432291, "grad_norm": 3.4933555126190186, "learning_rate": 1.5911330049261085e-05, "loss": 1.4495, "step": 1334 }, { "epoch": 0.20537671628014306, "grad_norm": 3.680767774581909, "learning_rate": 1.5908251231527095e-05, "loss": 1.4715, "step": 1335 }, { "epoch": 0.20553055651705704, "grad_norm": 3.557243824005127, "learning_rate": 1.5905172413793103e-05, "loss": 1.4337, "step": 1336 }, { "epoch": 0.205684396753971, "grad_norm": 4.597930908203125, "learning_rate": 1.5902093596059113e-05, "loss": 1.3566, "step": 1337 }, { "epoch": 0.20583823699088497, "grad_norm": 3.73996639251709, "learning_rate": 1.5899014778325124e-05, "loss": 1.3901, "step": 1338 }, { "epoch": 0.20599207722779894, "grad_norm": 3.602614641189575, "learning_rate": 1.5895935960591135e-05, "loss": 1.4329, "step": 1339 }, { "epoch": 0.2061459174647129, "grad_norm": 3.163935422897339, "learning_rate": 1.5892857142857142e-05, "loss": 1.4921, "step": 1340 }, { "epoch": 0.20629975770162687, "grad_norm": 4.034511566162109, "learning_rate": 1.5889778325123153e-05, "loss": 1.5006, "step": 1341 }, { "epoch": 0.20645359793854082, "grad_norm": 4.050163269042969, "learning_rate": 1.5886699507389163e-05, "loss": 1.5591, "step": 1342 }, { "epoch": 0.2066074381754548, "grad_norm": 3.2631001472473145, "learning_rate": 1.5883620689655174e-05, "loss": 1.0731, "step": 1343 }, { "epoch": 0.20676127841236874, "grad_norm": 3.359858274459839, "learning_rate": 1.5880541871921185e-05, "loss": 1.3819, "step": 1344 }, { "epoch": 0.20691511864928272, "grad_norm": 3.610358476638794, "learning_rate": 1.5877463054187195e-05, "loss": 1.4319, "step": 1345 }, { "epoch": 0.2070689588861967, "grad_norm": 3.665485143661499, "learning_rate": 1.5874384236453206e-05, "loss": 1.6228, "step": 1346 }, { "epoch": 0.20722279912311065, "grad_norm": 3.984119176864624, "learning_rate": 1.5871305418719213e-05, "loss": 1.5461, "step": 1347 }, { "epoch": 0.20737663936002462, "grad_norm": 4.298408031463623, "learning_rate": 1.5868226600985224e-05, "loss": 1.2262, "step": 1348 }, { "epoch": 0.20753047959693857, "grad_norm": 4.5708699226379395, "learning_rate": 1.5865147783251234e-05, "loss": 1.3864, "step": 1349 }, { "epoch": 0.20768431983385255, "grad_norm": 4.899787902832031, "learning_rate": 1.586206896551724e-05, "loss": 1.6945, "step": 1350 }, { "epoch": 0.2078381600707665, "grad_norm": 3.3271846771240234, "learning_rate": 1.5858990147783252e-05, "loss": 1.3792, "step": 1351 }, { "epoch": 0.20799200030768047, "grad_norm": 3.678434371948242, "learning_rate": 1.5855911330049263e-05, "loss": 1.0809, "step": 1352 }, { "epoch": 0.20814584054459445, "grad_norm": 4.076742172241211, "learning_rate": 1.5852832512315274e-05, "loss": 1.5104, "step": 1353 }, { "epoch": 0.2082996807815084, "grad_norm": 2.7853477001190186, "learning_rate": 1.584975369458128e-05, "loss": 1.4184, "step": 1354 }, { "epoch": 0.20845352101842238, "grad_norm": 3.6717100143432617, "learning_rate": 1.584667487684729e-05, "loss": 1.5396, "step": 1355 }, { "epoch": 0.20860736125533633, "grad_norm": 3.60562801361084, "learning_rate": 1.5843596059113302e-05, "loss": 1.3899, "step": 1356 }, { "epoch": 0.2087612014922503, "grad_norm": 4.383448600769043, "learning_rate": 1.5840517241379313e-05, "loss": 1.277, "step": 1357 }, { "epoch": 0.20891504172916425, "grad_norm": 4.183526992797852, "learning_rate": 1.583743842364532e-05, "loss": 1.3339, "step": 1358 }, { "epoch": 0.20906888196607823, "grad_norm": 3.727236747741699, "learning_rate": 1.583435960591133e-05, "loss": 1.33, "step": 1359 }, { "epoch": 0.2092227222029922, "grad_norm": 3.2235970497131348, "learning_rate": 1.583128078817734e-05, "loss": 1.5159, "step": 1360 }, { "epoch": 0.20937656243990616, "grad_norm": 3.541266918182373, "learning_rate": 1.5828201970443352e-05, "loss": 1.2453, "step": 1361 }, { "epoch": 0.20953040267682013, "grad_norm": 4.411369800567627, "learning_rate": 1.582512315270936e-05, "loss": 1.6124, "step": 1362 }, { "epoch": 0.20968424291373408, "grad_norm": 3.6448612213134766, "learning_rate": 1.582204433497537e-05, "loss": 1.4328, "step": 1363 }, { "epoch": 0.20983808315064806, "grad_norm": 4.075046539306641, "learning_rate": 1.581896551724138e-05, "loss": 1.5779, "step": 1364 }, { "epoch": 0.209991923387562, "grad_norm": 4.687203884124756, "learning_rate": 1.581588669950739e-05, "loss": 1.5521, "step": 1365 }, { "epoch": 0.21014576362447598, "grad_norm": 3.597548484802246, "learning_rate": 1.58128078817734e-05, "loss": 1.3194, "step": 1366 }, { "epoch": 0.21029960386138993, "grad_norm": 4.4431986808776855, "learning_rate": 1.580972906403941e-05, "loss": 1.1941, "step": 1367 }, { "epoch": 0.2104534440983039, "grad_norm": 4.045696258544922, "learning_rate": 1.580665024630542e-05, "loss": 1.3369, "step": 1368 }, { "epoch": 0.2106072843352179, "grad_norm": 3.1021568775177, "learning_rate": 1.580357142857143e-05, "loss": 1.3085, "step": 1369 }, { "epoch": 0.21076112457213184, "grad_norm": 3.483276844024658, "learning_rate": 1.5800492610837438e-05, "loss": 1.3485, "step": 1370 }, { "epoch": 0.2109149648090458, "grad_norm": 4.18039608001709, "learning_rate": 1.5797413793103448e-05, "loss": 1.5435, "step": 1371 }, { "epoch": 0.21106880504595976, "grad_norm": 4.75321102142334, "learning_rate": 1.579433497536946e-05, "loss": 1.4992, "step": 1372 }, { "epoch": 0.21122264528287374, "grad_norm": 3.6476566791534424, "learning_rate": 1.579125615763547e-05, "loss": 1.4182, "step": 1373 }, { "epoch": 0.2113764855197877, "grad_norm": 3.342714548110962, "learning_rate": 1.5788177339901477e-05, "loss": 1.328, "step": 1374 }, { "epoch": 0.21153032575670166, "grad_norm": 3.1739063262939453, "learning_rate": 1.5785098522167487e-05, "loss": 1.2569, "step": 1375 }, { "epoch": 0.21168416599361564, "grad_norm": 4.150180339813232, "learning_rate": 1.5782019704433498e-05, "loss": 1.3611, "step": 1376 }, { "epoch": 0.2118380062305296, "grad_norm": 3.9422311782836914, "learning_rate": 1.577894088669951e-05, "loss": 1.6653, "step": 1377 }, { "epoch": 0.21199184646744357, "grad_norm": 3.7467103004455566, "learning_rate": 1.577586206896552e-05, "loss": 1.5311, "step": 1378 }, { "epoch": 0.21214568670435752, "grad_norm": 3.1284806728363037, "learning_rate": 1.577278325123153e-05, "loss": 1.4999, "step": 1379 }, { "epoch": 0.2122995269412715, "grad_norm": 3.4988441467285156, "learning_rate": 1.576970443349754e-05, "loss": 1.3292, "step": 1380 }, { "epoch": 0.21245336717818544, "grad_norm": 3.7601711750030518, "learning_rate": 1.5766625615763548e-05, "loss": 1.4875, "step": 1381 }, { "epoch": 0.21260720741509942, "grad_norm": 3.449056625366211, "learning_rate": 1.576354679802956e-05, "loss": 1.2356, "step": 1382 }, { "epoch": 0.2127610476520134, "grad_norm": 3.744074583053589, "learning_rate": 1.576046798029557e-05, "loss": 1.4444, "step": 1383 }, { "epoch": 0.21291488788892735, "grad_norm": 4.099294185638428, "learning_rate": 1.575738916256158e-05, "loss": 1.4803, "step": 1384 }, { "epoch": 0.21306872812584132, "grad_norm": 3.6508796215057373, "learning_rate": 1.5754310344827587e-05, "loss": 1.321, "step": 1385 }, { "epoch": 0.21322256836275527, "grad_norm": 3.5866546630859375, "learning_rate": 1.5751231527093598e-05, "loss": 1.3507, "step": 1386 }, { "epoch": 0.21337640859966925, "grad_norm": 3.340019941329956, "learning_rate": 1.574815270935961e-05, "loss": 1.3647, "step": 1387 }, { "epoch": 0.2135302488365832, "grad_norm": 3.880706787109375, "learning_rate": 1.574507389162562e-05, "loss": 1.3906, "step": 1388 }, { "epoch": 0.21368408907349717, "grad_norm": 3.436885356903076, "learning_rate": 1.5741995073891626e-05, "loss": 1.4108, "step": 1389 }, { "epoch": 0.21383792931041115, "grad_norm": 3.4792208671569824, "learning_rate": 1.5738916256157637e-05, "loss": 1.3497, "step": 1390 }, { "epoch": 0.2139917695473251, "grad_norm": 3.860140800476074, "learning_rate": 1.5735837438423648e-05, "loss": 1.503, "step": 1391 }, { "epoch": 0.21414560978423908, "grad_norm": 3.7042436599731445, "learning_rate": 1.5732758620689655e-05, "loss": 1.4193, "step": 1392 }, { "epoch": 0.21429945002115303, "grad_norm": 4.032693386077881, "learning_rate": 1.5729679802955665e-05, "loss": 1.4309, "step": 1393 }, { "epoch": 0.214453290258067, "grad_norm": 3.1839065551757812, "learning_rate": 1.5726600985221676e-05, "loss": 1.1647, "step": 1394 }, { "epoch": 0.21460713049498095, "grad_norm": 3.4662227630615234, "learning_rate": 1.5723522167487687e-05, "loss": 1.4448, "step": 1395 }, { "epoch": 0.21476097073189493, "grad_norm": 3.9602882862091064, "learning_rate": 1.5720443349753694e-05, "loss": 1.5381, "step": 1396 }, { "epoch": 0.21491481096880888, "grad_norm": 3.764467477798462, "learning_rate": 1.5717364532019705e-05, "loss": 1.6542, "step": 1397 }, { "epoch": 0.21506865120572285, "grad_norm": 3.573115110397339, "learning_rate": 1.5714285714285715e-05, "loss": 1.4251, "step": 1398 }, { "epoch": 0.21522249144263683, "grad_norm": 3.8419480323791504, "learning_rate": 1.5711206896551726e-05, "loss": 1.2998, "step": 1399 }, { "epoch": 0.21537633167955078, "grad_norm": 3.522258996963501, "learning_rate": 1.5708128078817733e-05, "loss": 1.5256, "step": 1400 }, { "epoch": 0.21553017191646476, "grad_norm": 3.2489748001098633, "learning_rate": 1.5705049261083744e-05, "loss": 1.3978, "step": 1401 }, { "epoch": 0.2156840121533787, "grad_norm": 3.531130313873291, "learning_rate": 1.5701970443349755e-05, "loss": 1.4257, "step": 1402 }, { "epoch": 0.21583785239029268, "grad_norm": 5.631087303161621, "learning_rate": 1.5698891625615765e-05, "loss": 1.3618, "step": 1403 }, { "epoch": 0.21599169262720663, "grad_norm": 3.501246929168701, "learning_rate": 1.5695812807881772e-05, "loss": 1.266, "step": 1404 }, { "epoch": 0.2161455328641206, "grad_norm": 3.6910977363586426, "learning_rate": 1.5692733990147783e-05, "loss": 1.3896, "step": 1405 }, { "epoch": 0.2162993731010346, "grad_norm": 3.801971197128296, "learning_rate": 1.5689655172413794e-05, "loss": 1.3557, "step": 1406 }, { "epoch": 0.21645321333794854, "grad_norm": 4.5966997146606445, "learning_rate": 1.5686576354679804e-05, "loss": 1.3965, "step": 1407 }, { "epoch": 0.2166070535748625, "grad_norm": 4.904424667358398, "learning_rate": 1.568349753694581e-05, "loss": 1.5788, "step": 1408 }, { "epoch": 0.21676089381177646, "grad_norm": 3.9525532722473145, "learning_rate": 1.5680418719211822e-05, "loss": 1.3806, "step": 1409 }, { "epoch": 0.21691473404869044, "grad_norm": 4.023223876953125, "learning_rate": 1.5677339901477833e-05, "loss": 1.3502, "step": 1410 }, { "epoch": 0.2170685742856044, "grad_norm": 3.5782034397125244, "learning_rate": 1.5674261083743844e-05, "loss": 1.5414, "step": 1411 }, { "epoch": 0.21722241452251836, "grad_norm": 3.717702627182007, "learning_rate": 1.5671182266009854e-05, "loss": 1.383, "step": 1412 }, { "epoch": 0.21737625475943234, "grad_norm": 3.5691497325897217, "learning_rate": 1.5668103448275865e-05, "loss": 1.3569, "step": 1413 }, { "epoch": 0.2175300949963463, "grad_norm": 3.6481709480285645, "learning_rate": 1.5665024630541875e-05, "loss": 1.4035, "step": 1414 }, { "epoch": 0.21768393523326027, "grad_norm": 3.534494161605835, "learning_rate": 1.5661945812807883e-05, "loss": 1.2694, "step": 1415 }, { "epoch": 0.21783777547017422, "grad_norm": 4.259164333343506, "learning_rate": 1.5658866995073893e-05, "loss": 1.53, "step": 1416 }, { "epoch": 0.2179916157070882, "grad_norm": 3.996373176574707, "learning_rate": 1.5655788177339904e-05, "loss": 1.4332, "step": 1417 }, { "epoch": 0.21814545594400214, "grad_norm": 3.939976453781128, "learning_rate": 1.5652709359605915e-05, "loss": 1.3285, "step": 1418 }, { "epoch": 0.21829929618091612, "grad_norm": 3.635385751724243, "learning_rate": 1.5649630541871922e-05, "loss": 1.2994, "step": 1419 }, { "epoch": 0.2184531364178301, "grad_norm": 4.179490566253662, "learning_rate": 1.5646551724137933e-05, "loss": 1.426, "step": 1420 }, { "epoch": 0.21860697665474405, "grad_norm": 3.687272548675537, "learning_rate": 1.5643472906403943e-05, "loss": 1.5739, "step": 1421 }, { "epoch": 0.21876081689165802, "grad_norm": 4.179978847503662, "learning_rate": 1.5640394088669954e-05, "loss": 1.5562, "step": 1422 }, { "epoch": 0.21891465712857197, "grad_norm": 3.8699142932891846, "learning_rate": 1.563731527093596e-05, "loss": 1.2769, "step": 1423 }, { "epoch": 0.21906849736548595, "grad_norm": 3.460622549057007, "learning_rate": 1.5634236453201972e-05, "loss": 1.3964, "step": 1424 }, { "epoch": 0.2192223376023999, "grad_norm": 3.5749526023864746, "learning_rate": 1.5631157635467982e-05, "loss": 1.3689, "step": 1425 }, { "epoch": 0.21937617783931387, "grad_norm": 3.876032590866089, "learning_rate": 1.5628078817733993e-05, "loss": 1.4668, "step": 1426 }, { "epoch": 0.21953001807622785, "grad_norm": 4.513836860656738, "learning_rate": 1.5625e-05, "loss": 1.2264, "step": 1427 }, { "epoch": 0.2196838583131418, "grad_norm": 3.6870336532592773, "learning_rate": 1.562192118226601e-05, "loss": 1.466, "step": 1428 }, { "epoch": 0.21983769855005578, "grad_norm": 3.8069236278533936, "learning_rate": 1.561884236453202e-05, "loss": 1.5308, "step": 1429 }, { "epoch": 0.21999153878696973, "grad_norm": 4.436100482940674, "learning_rate": 1.5615763546798032e-05, "loss": 1.654, "step": 1430 }, { "epoch": 0.2201453790238837, "grad_norm": 3.2860114574432373, "learning_rate": 1.561268472906404e-05, "loss": 1.3715, "step": 1431 }, { "epoch": 0.22029921926079765, "grad_norm": 3.497689723968506, "learning_rate": 1.560960591133005e-05, "loss": 1.426, "step": 1432 }, { "epoch": 0.22045305949771163, "grad_norm": 3.462191581726074, "learning_rate": 1.560652709359606e-05, "loss": 1.3508, "step": 1433 }, { "epoch": 0.22060689973462558, "grad_norm": 3.18879771232605, "learning_rate": 1.560344827586207e-05, "loss": 1.2664, "step": 1434 }, { "epoch": 0.22076073997153955, "grad_norm": 4.079236030578613, "learning_rate": 1.560036945812808e-05, "loss": 1.2375, "step": 1435 }, { "epoch": 0.22091458020845353, "grad_norm": 3.847795009613037, "learning_rate": 1.559729064039409e-05, "loss": 1.4835, "step": 1436 }, { "epoch": 0.22106842044536748, "grad_norm": 3.3482556343078613, "learning_rate": 1.55942118226601e-05, "loss": 1.2266, "step": 1437 }, { "epoch": 0.22122226068228146, "grad_norm": 4.133804798126221, "learning_rate": 1.5591133004926107e-05, "loss": 1.5624, "step": 1438 }, { "epoch": 0.2213761009191954, "grad_norm": 4.0712809562683105, "learning_rate": 1.5588054187192118e-05, "loss": 1.4171, "step": 1439 }, { "epoch": 0.22152994115610938, "grad_norm": 3.9288668632507324, "learning_rate": 1.558497536945813e-05, "loss": 1.4911, "step": 1440 }, { "epoch": 0.22168378139302333, "grad_norm": 3.5414600372314453, "learning_rate": 1.558189655172414e-05, "loss": 1.3346, "step": 1441 }, { "epoch": 0.2218376216299373, "grad_norm": 3.611719846725464, "learning_rate": 1.5578817733990146e-05, "loss": 1.4396, "step": 1442 }, { "epoch": 0.2219914618668513, "grad_norm": 3.478288412094116, "learning_rate": 1.5575738916256157e-05, "loss": 1.1462, "step": 1443 }, { "epoch": 0.22214530210376524, "grad_norm": 3.6102843284606934, "learning_rate": 1.557266009852217e-05, "loss": 1.4817, "step": 1444 }, { "epoch": 0.2222991423406792, "grad_norm": 3.3080098628997803, "learning_rate": 1.556958128078818e-05, "loss": 1.3708, "step": 1445 }, { "epoch": 0.22245298257759316, "grad_norm": 4.027862548828125, "learning_rate": 1.556650246305419e-05, "loss": 1.2953, "step": 1446 }, { "epoch": 0.22260682281450714, "grad_norm": 3.7208783626556396, "learning_rate": 1.55634236453202e-05, "loss": 1.024, "step": 1447 }, { "epoch": 0.2227606630514211, "grad_norm": 4.273377418518066, "learning_rate": 1.556034482758621e-05, "loss": 1.5894, "step": 1448 }, { "epoch": 0.22291450328833506, "grad_norm": 3.0969626903533936, "learning_rate": 1.5557266009852218e-05, "loss": 1.2846, "step": 1449 }, { "epoch": 0.22306834352524904, "grad_norm": 3.491523027420044, "learning_rate": 1.5554187192118228e-05, "loss": 1.4208, "step": 1450 }, { "epoch": 0.223222183762163, "grad_norm": 3.7506399154663086, "learning_rate": 1.555110837438424e-05, "loss": 1.4051, "step": 1451 }, { "epoch": 0.22337602399907697, "grad_norm": 3.4466712474823, "learning_rate": 1.554802955665025e-05, "loss": 1.3436, "step": 1452 }, { "epoch": 0.22352986423599092, "grad_norm": 4.04315185546875, "learning_rate": 1.5544950738916257e-05, "loss": 1.4711, "step": 1453 }, { "epoch": 0.2236837044729049, "grad_norm": 3.123464584350586, "learning_rate": 1.5541871921182267e-05, "loss": 1.3154, "step": 1454 }, { "epoch": 0.22383754470981884, "grad_norm": 3.684246063232422, "learning_rate": 1.5538793103448278e-05, "loss": 1.7236, "step": 1455 }, { "epoch": 0.22399138494673282, "grad_norm": 4.304720401763916, "learning_rate": 1.553571428571429e-05, "loss": 1.4799, "step": 1456 }, { "epoch": 0.2241452251836468, "grad_norm": 3.8160951137542725, "learning_rate": 1.5532635467980296e-05, "loss": 1.6308, "step": 1457 }, { "epoch": 0.22429906542056074, "grad_norm": 3.9562313556671143, "learning_rate": 1.5529556650246307e-05, "loss": 1.3746, "step": 1458 }, { "epoch": 0.22445290565747472, "grad_norm": 3.0207138061523438, "learning_rate": 1.5526477832512317e-05, "loss": 1.2012, "step": 1459 }, { "epoch": 0.22460674589438867, "grad_norm": 3.8344836235046387, "learning_rate": 1.5523399014778328e-05, "loss": 1.2531, "step": 1460 }, { "epoch": 0.22476058613130265, "grad_norm": 4.207611083984375, "learning_rate": 1.5520320197044335e-05, "loss": 1.6382, "step": 1461 }, { "epoch": 0.2249144263682166, "grad_norm": 5.4312825202941895, "learning_rate": 1.5517241379310346e-05, "loss": 1.5546, "step": 1462 }, { "epoch": 0.22506826660513057, "grad_norm": 3.2647693157196045, "learning_rate": 1.5514162561576356e-05, "loss": 1.3915, "step": 1463 }, { "epoch": 0.22522210684204455, "grad_norm": 4.860627174377441, "learning_rate": 1.5511083743842367e-05, "loss": 1.7374, "step": 1464 }, { "epoch": 0.2253759470789585, "grad_norm": 4.542266368865967, "learning_rate": 1.5508004926108374e-05, "loss": 1.2235, "step": 1465 }, { "epoch": 0.22552978731587248, "grad_norm": 3.8661301136016846, "learning_rate": 1.5504926108374385e-05, "loss": 1.2442, "step": 1466 }, { "epoch": 0.22568362755278643, "grad_norm": 3.39202618598938, "learning_rate": 1.5501847290640396e-05, "loss": 1.5329, "step": 1467 }, { "epoch": 0.2258374677897004, "grad_norm": 3.6514732837677, "learning_rate": 1.5498768472906406e-05, "loss": 1.4786, "step": 1468 }, { "epoch": 0.22599130802661435, "grad_norm": 3.7062745094299316, "learning_rate": 1.5495689655172414e-05, "loss": 1.3146, "step": 1469 }, { "epoch": 0.22614514826352833, "grad_norm": 3.7677690982818604, "learning_rate": 1.5492610837438424e-05, "loss": 1.5053, "step": 1470 }, { "epoch": 0.22629898850044228, "grad_norm": 3.545546054840088, "learning_rate": 1.5489532019704435e-05, "loss": 1.3748, "step": 1471 }, { "epoch": 0.22645282873735625, "grad_norm": 3.606762409210205, "learning_rate": 1.5486453201970445e-05, "loss": 1.3939, "step": 1472 }, { "epoch": 0.22660666897427023, "grad_norm": 3.646765947341919, "learning_rate": 1.5483374384236453e-05, "loss": 1.4401, "step": 1473 }, { "epoch": 0.22676050921118418, "grad_norm": 3.813272714614868, "learning_rate": 1.5480295566502463e-05, "loss": 1.2633, "step": 1474 }, { "epoch": 0.22691434944809816, "grad_norm": 3.85148024559021, "learning_rate": 1.5477216748768474e-05, "loss": 1.2891, "step": 1475 }, { "epoch": 0.2270681896850121, "grad_norm": 3.0102241039276123, "learning_rate": 1.5474137931034485e-05, "loss": 1.0405, "step": 1476 }, { "epoch": 0.22722202992192608, "grad_norm": 3.414259195327759, "learning_rate": 1.5471059113300492e-05, "loss": 1.3606, "step": 1477 }, { "epoch": 0.22737587015884003, "grad_norm": 3.3151347637176514, "learning_rate": 1.5467980295566506e-05, "loss": 1.3781, "step": 1478 }, { "epoch": 0.227529710395754, "grad_norm": 3.172619342803955, "learning_rate": 1.5464901477832513e-05, "loss": 1.44, "step": 1479 }, { "epoch": 0.22768355063266799, "grad_norm": 3.084019422531128, "learning_rate": 1.5461822660098524e-05, "loss": 1.3923, "step": 1480 }, { "epoch": 0.22783739086958193, "grad_norm": 3.7661819458007812, "learning_rate": 1.5458743842364535e-05, "loss": 1.6951, "step": 1481 }, { "epoch": 0.2279912311064959, "grad_norm": 3.4997754096984863, "learning_rate": 1.5455665024630545e-05, "loss": 1.1958, "step": 1482 }, { "epoch": 0.22814507134340986, "grad_norm": 3.699603796005249, "learning_rate": 1.5452586206896552e-05, "loss": 1.503, "step": 1483 }, { "epoch": 0.22829891158032384, "grad_norm": 4.190384387969971, "learning_rate": 1.5449507389162563e-05, "loss": 1.14, "step": 1484 }, { "epoch": 0.2284527518172378, "grad_norm": 4.042606353759766, "learning_rate": 1.5446428571428574e-05, "loss": 1.3381, "step": 1485 }, { "epoch": 0.22860659205415176, "grad_norm": 3.300692081451416, "learning_rate": 1.5443349753694584e-05, "loss": 1.4844, "step": 1486 }, { "epoch": 0.22876043229106574, "grad_norm": 3.309966564178467, "learning_rate": 1.544027093596059e-05, "loss": 1.3583, "step": 1487 }, { "epoch": 0.2289142725279797, "grad_norm": 3.2982161045074463, "learning_rate": 1.5437192118226602e-05, "loss": 0.9596, "step": 1488 }, { "epoch": 0.22906811276489367, "grad_norm": 3.3532874584198, "learning_rate": 1.5434113300492613e-05, "loss": 1.3503, "step": 1489 }, { "epoch": 0.22922195300180762, "grad_norm": 3.4881296157836914, "learning_rate": 1.5431034482758624e-05, "loss": 1.252, "step": 1490 }, { "epoch": 0.2293757932387216, "grad_norm": 3.396252155303955, "learning_rate": 1.542795566502463e-05, "loss": 1.6126, "step": 1491 }, { "epoch": 0.22952963347563554, "grad_norm": 3.2715320587158203, "learning_rate": 1.542487684729064e-05, "loss": 1.5002, "step": 1492 }, { "epoch": 0.22968347371254952, "grad_norm": 4.471312046051025, "learning_rate": 1.5421798029556652e-05, "loss": 1.4847, "step": 1493 }, { "epoch": 0.2298373139494635, "grad_norm": 3.9973294734954834, "learning_rate": 1.5418719211822663e-05, "loss": 1.4498, "step": 1494 }, { "epoch": 0.22999115418637744, "grad_norm": 3.909374475479126, "learning_rate": 1.541564039408867e-05, "loss": 1.2131, "step": 1495 }, { "epoch": 0.23014499442329142, "grad_norm": 4.126767158508301, "learning_rate": 1.541256157635468e-05, "loss": 1.3953, "step": 1496 }, { "epoch": 0.23029883466020537, "grad_norm": 4.545273303985596, "learning_rate": 1.540948275862069e-05, "loss": 1.4231, "step": 1497 }, { "epoch": 0.23045267489711935, "grad_norm": 3.767298936843872, "learning_rate": 1.5406403940886702e-05, "loss": 1.2383, "step": 1498 }, { "epoch": 0.2306065151340333, "grad_norm": 3.5558724403381348, "learning_rate": 1.540332512315271e-05, "loss": 1.46, "step": 1499 }, { "epoch": 0.23076035537094727, "grad_norm": 3.6974425315856934, "learning_rate": 1.540024630541872e-05, "loss": 1.4384, "step": 1500 }, { "epoch": 0.23091419560786122, "grad_norm": 4.161747455596924, "learning_rate": 1.539716748768473e-05, "loss": 1.1888, "step": 1501 }, { "epoch": 0.2310680358447752, "grad_norm": 3.352191925048828, "learning_rate": 1.539408866995074e-05, "loss": 1.4524, "step": 1502 }, { "epoch": 0.23122187608168918, "grad_norm": 3.204127788543701, "learning_rate": 1.539100985221675e-05, "loss": 1.4375, "step": 1503 }, { "epoch": 0.23137571631860313, "grad_norm": 3.0828869342803955, "learning_rate": 1.538793103448276e-05, "loss": 1.3557, "step": 1504 }, { "epoch": 0.2315295565555171, "grad_norm": 3.9791934490203857, "learning_rate": 1.538485221674877e-05, "loss": 1.157, "step": 1505 }, { "epoch": 0.23168339679243105, "grad_norm": 3.166329860687256, "learning_rate": 1.538177339901478e-05, "loss": 1.4042, "step": 1506 }, { "epoch": 0.23183723702934503, "grad_norm": 3.769634962081909, "learning_rate": 1.5378694581280788e-05, "loss": 1.2525, "step": 1507 }, { "epoch": 0.23199107726625898, "grad_norm": 3.8335158824920654, "learning_rate": 1.5375615763546798e-05, "loss": 1.5578, "step": 1508 }, { "epoch": 0.23214491750317295, "grad_norm": 3.372422933578491, "learning_rate": 1.537253694581281e-05, "loss": 1.4368, "step": 1509 }, { "epoch": 0.23229875774008693, "grad_norm": 3.840972900390625, "learning_rate": 1.536945812807882e-05, "loss": 1.4373, "step": 1510 }, { "epoch": 0.23245259797700088, "grad_norm": 3.5974836349487305, "learning_rate": 1.5366379310344827e-05, "loss": 1.3536, "step": 1511 }, { "epoch": 0.23260643821391486, "grad_norm": 3.653265953063965, "learning_rate": 1.536330049261084e-05, "loss": 1.369, "step": 1512 }, { "epoch": 0.2327602784508288, "grad_norm": 4.036389350891113, "learning_rate": 1.5360221674876848e-05, "loss": 1.3045, "step": 1513 }, { "epoch": 0.23291411868774278, "grad_norm": 3.128732204437256, "learning_rate": 1.535714285714286e-05, "loss": 1.4906, "step": 1514 }, { "epoch": 0.23306795892465673, "grad_norm": 3.4743635654449463, "learning_rate": 1.535406403940887e-05, "loss": 1.3182, "step": 1515 }, { "epoch": 0.2332217991615707, "grad_norm": 3.684394598007202, "learning_rate": 1.535098522167488e-05, "loss": 1.1675, "step": 1516 }, { "epoch": 0.23337563939848469, "grad_norm": 3.606600046157837, "learning_rate": 1.5347906403940887e-05, "loss": 1.3751, "step": 1517 }, { "epoch": 0.23352947963539863, "grad_norm": 4.1558685302734375, "learning_rate": 1.5344827586206898e-05, "loss": 1.5586, "step": 1518 }, { "epoch": 0.2336833198723126, "grad_norm": 3.4803054332733154, "learning_rate": 1.534174876847291e-05, "loss": 1.4165, "step": 1519 }, { "epoch": 0.23383716010922656, "grad_norm": 3.2876410484313965, "learning_rate": 1.533866995073892e-05, "loss": 1.562, "step": 1520 }, { "epoch": 0.23399100034614054, "grad_norm": 3.627333879470825, "learning_rate": 1.5335591133004926e-05, "loss": 1.3854, "step": 1521 }, { "epoch": 0.2341448405830545, "grad_norm": 3.7007150650024414, "learning_rate": 1.5332512315270937e-05, "loss": 1.286, "step": 1522 }, { "epoch": 0.23429868081996846, "grad_norm": 4.107419967651367, "learning_rate": 1.5329433497536948e-05, "loss": 1.7175, "step": 1523 }, { "epoch": 0.23445252105688244, "grad_norm": 3.5403854846954346, "learning_rate": 1.532635467980296e-05, "loss": 1.3367, "step": 1524 }, { "epoch": 0.2346063612937964, "grad_norm": 3.881328821182251, "learning_rate": 1.5323275862068966e-05, "loss": 1.6464, "step": 1525 }, { "epoch": 0.23476020153071037, "grad_norm": 4.121071815490723, "learning_rate": 1.5320197044334976e-05, "loss": 1.37, "step": 1526 }, { "epoch": 0.23491404176762432, "grad_norm": 4.1542134284973145, "learning_rate": 1.5317118226600987e-05, "loss": 1.2738, "step": 1527 }, { "epoch": 0.2350678820045383, "grad_norm": 3.67094087600708, "learning_rate": 1.5314039408866998e-05, "loss": 1.4387, "step": 1528 }, { "epoch": 0.23522172224145224, "grad_norm": 4.067325115203857, "learning_rate": 1.5310960591133005e-05, "loss": 1.4269, "step": 1529 }, { "epoch": 0.23537556247836622, "grad_norm": 4.324078559875488, "learning_rate": 1.5307881773399015e-05, "loss": 1.0945, "step": 1530 }, { "epoch": 0.2355294027152802, "grad_norm": 3.4830098152160645, "learning_rate": 1.5304802955665026e-05, "loss": 1.5998, "step": 1531 }, { "epoch": 0.23568324295219414, "grad_norm": 3.6883554458618164, "learning_rate": 1.5301724137931037e-05, "loss": 1.7383, "step": 1532 }, { "epoch": 0.23583708318910812, "grad_norm": 3.6225554943084717, "learning_rate": 1.5298645320197044e-05, "loss": 1.457, "step": 1533 }, { "epoch": 0.23599092342602207, "grad_norm": 3.5454115867614746, "learning_rate": 1.5295566502463055e-05, "loss": 1.3893, "step": 1534 }, { "epoch": 0.23614476366293605, "grad_norm": 3.4374616146087646, "learning_rate": 1.5292487684729065e-05, "loss": 1.3457, "step": 1535 }, { "epoch": 0.23629860389985, "grad_norm": 4.562387943267822, "learning_rate": 1.5289408866995076e-05, "loss": 1.3538, "step": 1536 }, { "epoch": 0.23645244413676397, "grad_norm": 3.7424848079681396, "learning_rate": 1.5286330049261083e-05, "loss": 1.3759, "step": 1537 }, { "epoch": 0.23660628437367792, "grad_norm": 3.5190353393554688, "learning_rate": 1.5283251231527094e-05, "loss": 1.2972, "step": 1538 }, { "epoch": 0.2367601246105919, "grad_norm": 3.7631983757019043, "learning_rate": 1.5280172413793105e-05, "loss": 1.4166, "step": 1539 }, { "epoch": 0.23691396484750588, "grad_norm": 3.3817672729492188, "learning_rate": 1.5277093596059115e-05, "loss": 1.6382, "step": 1540 }, { "epoch": 0.23706780508441982, "grad_norm": 4.155311107635498, "learning_rate": 1.5274014778325122e-05, "loss": 1.272, "step": 1541 }, { "epoch": 0.2372216453213338, "grad_norm": 3.6868224143981934, "learning_rate": 1.5270935960591133e-05, "loss": 1.4807, "step": 1542 }, { "epoch": 0.23737548555824775, "grad_norm": 3.5222887992858887, "learning_rate": 1.5267857142857144e-05, "loss": 1.2517, "step": 1543 }, { "epoch": 0.23752932579516173, "grad_norm": 3.9099342823028564, "learning_rate": 1.5264778325123154e-05, "loss": 1.3135, "step": 1544 }, { "epoch": 0.23768316603207568, "grad_norm": 3.9128761291503906, "learning_rate": 1.526169950738916e-05, "loss": 1.2252, "step": 1545 }, { "epoch": 0.23783700626898965, "grad_norm": 4.718939304351807, "learning_rate": 1.5258620689655174e-05, "loss": 1.5639, "step": 1546 }, { "epoch": 0.23799084650590363, "grad_norm": 3.078111171722412, "learning_rate": 1.5255541871921185e-05, "loss": 1.1406, "step": 1547 }, { "epoch": 0.23814468674281758, "grad_norm": 3.322735548019409, "learning_rate": 1.5252463054187194e-05, "loss": 1.3978, "step": 1548 }, { "epoch": 0.23829852697973156, "grad_norm": 3.1483757495880127, "learning_rate": 1.5249384236453204e-05, "loss": 1.5769, "step": 1549 }, { "epoch": 0.2384523672166455, "grad_norm": 2.77656888961792, "learning_rate": 1.5246305418719213e-05, "loss": 1.1517, "step": 1550 }, { "epoch": 0.23860620745355948, "grad_norm": 3.732771873474121, "learning_rate": 1.5243226600985224e-05, "loss": 1.4723, "step": 1551 }, { "epoch": 0.23876004769047343, "grad_norm": 4.1256103515625, "learning_rate": 1.5240147783251233e-05, "loss": 1.356, "step": 1552 }, { "epoch": 0.2389138879273874, "grad_norm": 3.588512659072876, "learning_rate": 1.5237068965517243e-05, "loss": 1.4064, "step": 1553 }, { "epoch": 0.23906772816430139, "grad_norm": 3.5506272315979004, "learning_rate": 1.5233990147783252e-05, "loss": 1.4553, "step": 1554 }, { "epoch": 0.23922156840121533, "grad_norm": 4.230788230895996, "learning_rate": 1.5230911330049263e-05, "loss": 1.2679, "step": 1555 }, { "epoch": 0.2393754086381293, "grad_norm": 3.8024649620056152, "learning_rate": 1.5227832512315272e-05, "loss": 1.5301, "step": 1556 }, { "epoch": 0.23952924887504326, "grad_norm": 3.769143581390381, "learning_rate": 1.5224753694581283e-05, "loss": 1.353, "step": 1557 }, { "epoch": 0.23968308911195724, "grad_norm": 3.9299917221069336, "learning_rate": 1.5221674876847292e-05, "loss": 1.3742, "step": 1558 }, { "epoch": 0.2398369293488712, "grad_norm": 3.8140904903411865, "learning_rate": 1.5218596059113302e-05, "loss": 1.54, "step": 1559 }, { "epoch": 0.23999076958578516, "grad_norm": 3.5504608154296875, "learning_rate": 1.5215517241379311e-05, "loss": 1.5925, "step": 1560 }, { "epoch": 0.24014460982269914, "grad_norm": 3.549313545227051, "learning_rate": 1.5212438423645322e-05, "loss": 1.3828, "step": 1561 }, { "epoch": 0.2402984500596131, "grad_norm": 3.6726884841918945, "learning_rate": 1.520935960591133e-05, "loss": 1.1819, "step": 1562 }, { "epoch": 0.24045229029652707, "grad_norm": 3.3162894248962402, "learning_rate": 1.5206280788177341e-05, "loss": 1.3337, "step": 1563 }, { "epoch": 0.24060613053344101, "grad_norm": 3.734485626220703, "learning_rate": 1.520320197044335e-05, "loss": 1.6612, "step": 1564 }, { "epoch": 0.240759970770355, "grad_norm": 4.14247989654541, "learning_rate": 1.5200123152709361e-05, "loss": 1.3376, "step": 1565 }, { "epoch": 0.24091381100726894, "grad_norm": 3.787766456604004, "learning_rate": 1.519704433497537e-05, "loss": 1.3589, "step": 1566 }, { "epoch": 0.24106765124418292, "grad_norm": 3.7058286666870117, "learning_rate": 1.519396551724138e-05, "loss": 1.2969, "step": 1567 }, { "epoch": 0.2412214914810969, "grad_norm": 3.8512139320373535, "learning_rate": 1.519088669950739e-05, "loss": 1.2495, "step": 1568 }, { "epoch": 0.24137533171801084, "grad_norm": 3.4181034564971924, "learning_rate": 1.51878078817734e-05, "loss": 1.462, "step": 1569 }, { "epoch": 0.24152917195492482, "grad_norm": 3.508768320083618, "learning_rate": 1.5184729064039409e-05, "loss": 1.3327, "step": 1570 }, { "epoch": 0.24168301219183877, "grad_norm": 3.679567813873291, "learning_rate": 1.518165024630542e-05, "loss": 1.1622, "step": 1571 }, { "epoch": 0.24183685242875275, "grad_norm": 3.2358734607696533, "learning_rate": 1.5178571428571429e-05, "loss": 1.2775, "step": 1572 }, { "epoch": 0.2419906926656667, "grad_norm": 3.751383066177368, "learning_rate": 1.517549261083744e-05, "loss": 1.7536, "step": 1573 }, { "epoch": 0.24214453290258067, "grad_norm": 3.9422683715820312, "learning_rate": 1.5172413793103448e-05, "loss": 1.5438, "step": 1574 }, { "epoch": 0.24229837313949462, "grad_norm": 3.910827159881592, "learning_rate": 1.5169334975369459e-05, "loss": 1.3221, "step": 1575 }, { "epoch": 0.2424522133764086, "grad_norm": 3.8335654735565186, "learning_rate": 1.5166256157635468e-05, "loss": 1.4402, "step": 1576 }, { "epoch": 0.24260605361332258, "grad_norm": 4.084773063659668, "learning_rate": 1.5163177339901479e-05, "loss": 1.2877, "step": 1577 }, { "epoch": 0.24275989385023652, "grad_norm": 3.196840763092041, "learning_rate": 1.5160098522167487e-05, "loss": 1.5259, "step": 1578 }, { "epoch": 0.2429137340871505, "grad_norm": 3.1274969577789307, "learning_rate": 1.5157019704433498e-05, "loss": 1.4263, "step": 1579 }, { "epoch": 0.24306757432406445, "grad_norm": 3.3273112773895264, "learning_rate": 1.515394088669951e-05, "loss": 1.3121, "step": 1580 }, { "epoch": 0.24322141456097843, "grad_norm": 3.432243585586548, "learning_rate": 1.515086206896552e-05, "loss": 1.4007, "step": 1581 }, { "epoch": 0.24337525479789238, "grad_norm": 3.6149585247039795, "learning_rate": 1.514778325123153e-05, "loss": 1.3288, "step": 1582 }, { "epoch": 0.24352909503480635, "grad_norm": 4.176764488220215, "learning_rate": 1.5144704433497539e-05, "loss": 1.5317, "step": 1583 }, { "epoch": 0.24368293527172033, "grad_norm": 3.396643877029419, "learning_rate": 1.514162561576355e-05, "loss": 1.5442, "step": 1584 }, { "epoch": 0.24383677550863428, "grad_norm": 4.27730131149292, "learning_rate": 1.5138546798029559e-05, "loss": 1.5823, "step": 1585 }, { "epoch": 0.24399061574554826, "grad_norm": 3.720349073410034, "learning_rate": 1.5135467980295568e-05, "loss": 1.5997, "step": 1586 }, { "epoch": 0.2441444559824622, "grad_norm": 3.6766321659088135, "learning_rate": 1.5132389162561578e-05, "loss": 1.3681, "step": 1587 }, { "epoch": 0.24429829621937618, "grad_norm": 3.4016358852386475, "learning_rate": 1.5129310344827587e-05, "loss": 1.5524, "step": 1588 }, { "epoch": 0.24445213645629013, "grad_norm": 3.710139751434326, "learning_rate": 1.5126231527093598e-05, "loss": 1.4357, "step": 1589 }, { "epoch": 0.2446059766932041, "grad_norm": 3.6715071201324463, "learning_rate": 1.5123152709359607e-05, "loss": 1.3393, "step": 1590 }, { "epoch": 0.24475981693011808, "grad_norm": 3.366539478302002, "learning_rate": 1.5120073891625617e-05, "loss": 1.3781, "step": 1591 }, { "epoch": 0.24491365716703203, "grad_norm": 3.172637701034546, "learning_rate": 1.5116995073891626e-05, "loss": 1.3212, "step": 1592 }, { "epoch": 0.245067497403946, "grad_norm": 3.4529435634613037, "learning_rate": 1.5113916256157637e-05, "loss": 1.3652, "step": 1593 }, { "epoch": 0.24522133764085996, "grad_norm": 3.5501294136047363, "learning_rate": 1.5110837438423646e-05, "loss": 1.4135, "step": 1594 }, { "epoch": 0.24537517787777394, "grad_norm": 3.8288538455963135, "learning_rate": 1.5107758620689657e-05, "loss": 1.4693, "step": 1595 }, { "epoch": 0.24552901811468789, "grad_norm": 2.9176480770111084, "learning_rate": 1.5104679802955666e-05, "loss": 1.3557, "step": 1596 }, { "epoch": 0.24568285835160186, "grad_norm": 4.0010881423950195, "learning_rate": 1.5101600985221676e-05, "loss": 1.4581, "step": 1597 }, { "epoch": 0.24583669858851584, "grad_norm": 4.008790969848633, "learning_rate": 1.5098522167487685e-05, "loss": 1.1651, "step": 1598 }, { "epoch": 0.2459905388254298, "grad_norm": 3.4476442337036133, "learning_rate": 1.5095443349753696e-05, "loss": 1.3599, "step": 1599 }, { "epoch": 0.24614437906234377, "grad_norm": 3.7127039432525635, "learning_rate": 1.5092364532019705e-05, "loss": 1.4776, "step": 1600 }, { "epoch": 0.24629821929925771, "grad_norm": 3.546396255493164, "learning_rate": 1.5089285714285715e-05, "loss": 1.162, "step": 1601 }, { "epoch": 0.2464520595361717, "grad_norm": 3.2111451625823975, "learning_rate": 1.5086206896551724e-05, "loss": 1.4429, "step": 1602 }, { "epoch": 0.24660589977308564, "grad_norm": 3.840181827545166, "learning_rate": 1.5083128078817735e-05, "loss": 1.6081, "step": 1603 }, { "epoch": 0.24675974000999962, "grad_norm": 4.235263824462891, "learning_rate": 1.5080049261083744e-05, "loss": 1.3937, "step": 1604 }, { "epoch": 0.24691358024691357, "grad_norm": 3.5691184997558594, "learning_rate": 1.5076970443349755e-05, "loss": 1.3949, "step": 1605 }, { "epoch": 0.24706742048382754, "grad_norm": 3.8375051021575928, "learning_rate": 1.5073891625615764e-05, "loss": 1.3671, "step": 1606 }, { "epoch": 0.24722126072074152, "grad_norm": 4.268791675567627, "learning_rate": 1.5070812807881774e-05, "loss": 1.2453, "step": 1607 }, { "epoch": 0.24737510095765547, "grad_norm": 3.6077558994293213, "learning_rate": 1.5067733990147783e-05, "loss": 1.5786, "step": 1608 }, { "epoch": 0.24752894119456945, "grad_norm": 3.5857932567596436, "learning_rate": 1.5064655172413794e-05, "loss": 1.3811, "step": 1609 }, { "epoch": 0.2476827814314834, "grad_norm": 3.7205758094787598, "learning_rate": 1.5061576354679803e-05, "loss": 1.6962, "step": 1610 }, { "epoch": 0.24783662166839737, "grad_norm": 3.5176761150360107, "learning_rate": 1.5058497536945813e-05, "loss": 1.5995, "step": 1611 }, { "epoch": 0.24799046190531132, "grad_norm": 3.3915939331054688, "learning_rate": 1.5055418719211822e-05, "loss": 1.2544, "step": 1612 }, { "epoch": 0.2481443021422253, "grad_norm": 2.91227650642395, "learning_rate": 1.5052339901477833e-05, "loss": 1.4001, "step": 1613 }, { "epoch": 0.24829814237913927, "grad_norm": 4.2693915367126465, "learning_rate": 1.5049261083743845e-05, "loss": 1.4912, "step": 1614 }, { "epoch": 0.24845198261605322, "grad_norm": 3.021843671798706, "learning_rate": 1.5046182266009854e-05, "loss": 1.2932, "step": 1615 }, { "epoch": 0.2486058228529672, "grad_norm": 3.2658209800720215, "learning_rate": 1.5043103448275865e-05, "loss": 1.3765, "step": 1616 }, { "epoch": 0.24875966308988115, "grad_norm": 3.102811813354492, "learning_rate": 1.5040024630541874e-05, "loss": 1.276, "step": 1617 }, { "epoch": 0.24891350332679513, "grad_norm": 4.329319477081299, "learning_rate": 1.5036945812807884e-05, "loss": 1.2462, "step": 1618 }, { "epoch": 0.24906734356370908, "grad_norm": 3.8946170806884766, "learning_rate": 1.5033866995073893e-05, "loss": 1.3654, "step": 1619 }, { "epoch": 0.24922118380062305, "grad_norm": 3.6784539222717285, "learning_rate": 1.5030788177339904e-05, "loss": 1.4193, "step": 1620 }, { "epoch": 0.24937502403753703, "grad_norm": 3.5492782592773438, "learning_rate": 1.5027709359605913e-05, "loss": 1.2948, "step": 1621 }, { "epoch": 0.24952886427445098, "grad_norm": 3.551835536956787, "learning_rate": 1.5024630541871924e-05, "loss": 1.5184, "step": 1622 }, { "epoch": 0.24968270451136496, "grad_norm": 4.382933616638184, "learning_rate": 1.5021551724137933e-05, "loss": 1.6235, "step": 1623 }, { "epoch": 0.2498365447482789, "grad_norm": 3.7682502269744873, "learning_rate": 1.5018472906403943e-05, "loss": 1.3953, "step": 1624 }, { "epoch": 0.24999038498519288, "grad_norm": 3.326235294342041, "learning_rate": 1.5015394088669952e-05, "loss": 1.1377, "step": 1625 }, { "epoch": 0.25014422522210683, "grad_norm": 3.976921319961548, "learning_rate": 1.5012315270935963e-05, "loss": 1.5947, "step": 1626 }, { "epoch": 0.2502980654590208, "grad_norm": 3.8207666873931885, "learning_rate": 1.5009236453201972e-05, "loss": 1.3697, "step": 1627 }, { "epoch": 0.2504519056959348, "grad_norm": 3.53593373298645, "learning_rate": 1.5006157635467982e-05, "loss": 1.3597, "step": 1628 }, { "epoch": 0.25060574593284873, "grad_norm": 3.6870675086975098, "learning_rate": 1.5003078817733991e-05, "loss": 1.5135, "step": 1629 }, { "epoch": 0.2507595861697627, "grad_norm": 3.8629777431488037, "learning_rate": 1.5000000000000002e-05, "loss": 1.3892, "step": 1630 }, { "epoch": 0.2509134264066767, "grad_norm": 3.5632429122924805, "learning_rate": 1.4996921182266011e-05, "loss": 1.533, "step": 1631 }, { "epoch": 0.25106726664359064, "grad_norm": 3.1444571018218994, "learning_rate": 1.499384236453202e-05, "loss": 1.4735, "step": 1632 }, { "epoch": 0.2512211068805046, "grad_norm": 3.5656890869140625, "learning_rate": 1.499076354679803e-05, "loss": 1.1844, "step": 1633 }, { "epoch": 0.25137494711741853, "grad_norm": 3.85335373878479, "learning_rate": 1.498768472906404e-05, "loss": 1.503, "step": 1634 }, { "epoch": 0.25152878735433254, "grad_norm": 3.7066714763641357, "learning_rate": 1.498460591133005e-05, "loss": 1.3675, "step": 1635 }, { "epoch": 0.2516826275912465, "grad_norm": 3.5247178077697754, "learning_rate": 1.498152709359606e-05, "loss": 1.4628, "step": 1636 }, { "epoch": 0.25183646782816044, "grad_norm": 3.6272976398468018, "learning_rate": 1.497844827586207e-05, "loss": 1.5312, "step": 1637 }, { "epoch": 0.25199030806507444, "grad_norm": 3.570521354675293, "learning_rate": 1.4975369458128079e-05, "loss": 1.3898, "step": 1638 }, { "epoch": 0.2521441483019884, "grad_norm": 3.7154006958007812, "learning_rate": 1.497229064039409e-05, "loss": 1.3801, "step": 1639 }, { "epoch": 0.25229798853890234, "grad_norm": 3.7218198776245117, "learning_rate": 1.4969211822660098e-05, "loss": 1.5546, "step": 1640 }, { "epoch": 0.2524518287758163, "grad_norm": 3.184976100921631, "learning_rate": 1.4966133004926109e-05, "loss": 1.1329, "step": 1641 }, { "epoch": 0.2526056690127303, "grad_norm": 3.869084596633911, "learning_rate": 1.4963054187192118e-05, "loss": 1.306, "step": 1642 }, { "epoch": 0.25275950924964424, "grad_norm": 3.6860315799713135, "learning_rate": 1.4959975369458129e-05, "loss": 1.4366, "step": 1643 }, { "epoch": 0.2529133494865582, "grad_norm": 3.3875036239624023, "learning_rate": 1.4956896551724138e-05, "loss": 1.4073, "step": 1644 }, { "epoch": 0.2530671897234722, "grad_norm": 3.9338316917419434, "learning_rate": 1.4953817733990148e-05, "loss": 1.4115, "step": 1645 }, { "epoch": 0.25322102996038615, "grad_norm": 3.7540338039398193, "learning_rate": 1.4950738916256157e-05, "loss": 1.1505, "step": 1646 }, { "epoch": 0.2533748701973001, "grad_norm": 4.3993072509765625, "learning_rate": 1.494766009852217e-05, "loss": 1.2674, "step": 1647 }, { "epoch": 0.25352871043421404, "grad_norm": 3.6769895553588867, "learning_rate": 1.494458128078818e-05, "loss": 1.3955, "step": 1648 }, { "epoch": 0.25368255067112805, "grad_norm": 3.857879877090454, "learning_rate": 1.4941502463054189e-05, "loss": 1.5653, "step": 1649 }, { "epoch": 0.253836390908042, "grad_norm": 3.6204993724823, "learning_rate": 1.49384236453202e-05, "loss": 1.3045, "step": 1650 }, { "epoch": 0.25399023114495595, "grad_norm": 4.443240165710449, "learning_rate": 1.4935344827586209e-05, "loss": 1.2401, "step": 1651 }, { "epoch": 0.25414407138186995, "grad_norm": 3.4116735458374023, "learning_rate": 1.493226600985222e-05, "loss": 1.2955, "step": 1652 }, { "epoch": 0.2542979116187839, "grad_norm": 3.7734949588775635, "learning_rate": 1.4929187192118228e-05, "loss": 1.1532, "step": 1653 }, { "epoch": 0.25445175185569785, "grad_norm": 3.6973795890808105, "learning_rate": 1.4926108374384239e-05, "loss": 1.5815, "step": 1654 }, { "epoch": 0.2546055920926118, "grad_norm": 3.730173110961914, "learning_rate": 1.4923029556650248e-05, "loss": 1.4467, "step": 1655 }, { "epoch": 0.2547594323295258, "grad_norm": 4.461993217468262, "learning_rate": 1.4919950738916259e-05, "loss": 1.4559, "step": 1656 }, { "epoch": 0.25491327256643975, "grad_norm": 3.721219062805176, "learning_rate": 1.4916871921182267e-05, "loss": 1.4717, "step": 1657 }, { "epoch": 0.2550671128033537, "grad_norm": 4.188971996307373, "learning_rate": 1.4913793103448278e-05, "loss": 1.6068, "step": 1658 }, { "epoch": 0.2552209530402677, "grad_norm": 4.089630603790283, "learning_rate": 1.4910714285714287e-05, "loss": 1.4795, "step": 1659 }, { "epoch": 0.25537479327718166, "grad_norm": 3.2931127548217773, "learning_rate": 1.4907635467980298e-05, "loss": 1.4368, "step": 1660 }, { "epoch": 0.2555286335140956, "grad_norm": 4.001580715179443, "learning_rate": 1.4904556650246307e-05, "loss": 1.4642, "step": 1661 }, { "epoch": 0.25568247375100955, "grad_norm": 3.380533218383789, "learning_rate": 1.4901477832512317e-05, "loss": 1.3858, "step": 1662 }, { "epoch": 0.25583631398792356, "grad_norm": 3.859910726547241, "learning_rate": 1.4898399014778326e-05, "loss": 1.3773, "step": 1663 }, { "epoch": 0.2559901542248375, "grad_norm": 3.919389247894287, "learning_rate": 1.4895320197044337e-05, "loss": 1.3876, "step": 1664 }, { "epoch": 0.25614399446175146, "grad_norm": 4.896490097045898, "learning_rate": 1.4892241379310346e-05, "loss": 1.6295, "step": 1665 }, { "epoch": 0.25629783469866546, "grad_norm": 3.9120428562164307, "learning_rate": 1.4889162561576357e-05, "loss": 1.4007, "step": 1666 }, { "epoch": 0.2564516749355794, "grad_norm": 3.8305234909057617, "learning_rate": 1.4886083743842365e-05, "loss": 1.47, "step": 1667 }, { "epoch": 0.25660551517249336, "grad_norm": 3.941392183303833, "learning_rate": 1.4883004926108376e-05, "loss": 1.3269, "step": 1668 }, { "epoch": 0.2567593554094073, "grad_norm": 4.438704013824463, "learning_rate": 1.4879926108374385e-05, "loss": 1.4232, "step": 1669 }, { "epoch": 0.2569131956463213, "grad_norm": 3.7991442680358887, "learning_rate": 1.4876847290640396e-05, "loss": 1.2239, "step": 1670 }, { "epoch": 0.25706703588323526, "grad_norm": 3.9246528148651123, "learning_rate": 1.4873768472906405e-05, "loss": 1.5983, "step": 1671 }, { "epoch": 0.2572208761201492, "grad_norm": 3.8901007175445557, "learning_rate": 1.4870689655172415e-05, "loss": 1.2704, "step": 1672 }, { "epoch": 0.2573747163570632, "grad_norm": 4.431098937988281, "learning_rate": 1.4867610837438424e-05, "loss": 1.4576, "step": 1673 }, { "epoch": 0.25752855659397716, "grad_norm": 3.4705235958099365, "learning_rate": 1.4864532019704435e-05, "loss": 1.0758, "step": 1674 }, { "epoch": 0.2576823968308911, "grad_norm": 3.9800617694854736, "learning_rate": 1.4861453201970444e-05, "loss": 1.2552, "step": 1675 }, { "epoch": 0.25783623706780506, "grad_norm": 3.5664961338043213, "learning_rate": 1.4858374384236453e-05, "loss": 1.3706, "step": 1676 }, { "epoch": 0.25799007730471907, "grad_norm": 3.66755747795105, "learning_rate": 1.4855295566502463e-05, "loss": 1.3699, "step": 1677 }, { "epoch": 0.258143917541633, "grad_norm": 3.550422191619873, "learning_rate": 1.4852216748768472e-05, "loss": 1.6903, "step": 1678 }, { "epoch": 0.25829775777854697, "grad_norm": 3.663458824157715, "learning_rate": 1.4849137931034483e-05, "loss": 1.3649, "step": 1679 }, { "epoch": 0.25845159801546097, "grad_norm": 3.4670028686523438, "learning_rate": 1.4846059113300492e-05, "loss": 1.4491, "step": 1680 }, { "epoch": 0.2586054382523749, "grad_norm": 4.015132427215576, "learning_rate": 1.4842980295566504e-05, "loss": 1.7044, "step": 1681 }, { "epoch": 0.25875927848928887, "grad_norm": 3.8447530269622803, "learning_rate": 1.4839901477832515e-05, "loss": 1.4605, "step": 1682 }, { "epoch": 0.2589131187262028, "grad_norm": 3.6758344173431396, "learning_rate": 1.4836822660098524e-05, "loss": 1.5409, "step": 1683 }, { "epoch": 0.2590669589631168, "grad_norm": 3.3888583183288574, "learning_rate": 1.4833743842364535e-05, "loss": 1.599, "step": 1684 }, { "epoch": 0.25922079920003077, "grad_norm": 3.3648951053619385, "learning_rate": 1.4830665024630544e-05, "loss": 1.5622, "step": 1685 }, { "epoch": 0.2593746394369447, "grad_norm": 4.025966167449951, "learning_rate": 1.4827586206896554e-05, "loss": 1.6894, "step": 1686 }, { "epoch": 0.2595284796738587, "grad_norm": 3.5936648845672607, "learning_rate": 1.4824507389162563e-05, "loss": 1.5358, "step": 1687 }, { "epoch": 0.2596823199107727, "grad_norm": 3.5527358055114746, "learning_rate": 1.4821428571428574e-05, "loss": 1.6085, "step": 1688 }, { "epoch": 0.2598361601476866, "grad_norm": 3.7977375984191895, "learning_rate": 1.4818349753694583e-05, "loss": 1.2379, "step": 1689 }, { "epoch": 0.2599900003846006, "grad_norm": 3.9900381565093994, "learning_rate": 1.4815270935960593e-05, "loss": 1.3323, "step": 1690 }, { "epoch": 0.2601438406215146, "grad_norm": 3.9863176345825195, "learning_rate": 1.4812192118226602e-05, "loss": 1.2459, "step": 1691 }, { "epoch": 0.2602976808584285, "grad_norm": 4.7672600746154785, "learning_rate": 1.4809113300492613e-05, "loss": 0.9422, "step": 1692 }, { "epoch": 0.2604515210953425, "grad_norm": 3.869899272918701, "learning_rate": 1.4806034482758622e-05, "loss": 1.265, "step": 1693 }, { "epoch": 0.2606053613322564, "grad_norm": 3.391389846801758, "learning_rate": 1.4802955665024633e-05, "loss": 1.3331, "step": 1694 }, { "epoch": 0.26075920156917043, "grad_norm": 3.545923948287964, "learning_rate": 1.4799876847290642e-05, "loss": 1.2979, "step": 1695 }, { "epoch": 0.2609130418060844, "grad_norm": 3.586357831954956, "learning_rate": 1.4796798029556652e-05, "loss": 1.207, "step": 1696 }, { "epoch": 0.2610668820429983, "grad_norm": 3.378655433654785, "learning_rate": 1.4793719211822661e-05, "loss": 1.49, "step": 1697 }, { "epoch": 0.26122072227991233, "grad_norm": 3.6288001537323, "learning_rate": 1.4790640394088672e-05, "loss": 1.2962, "step": 1698 }, { "epoch": 0.2613745625168263, "grad_norm": 4.292763710021973, "learning_rate": 1.478756157635468e-05, "loss": 1.231, "step": 1699 }, { "epoch": 0.26152840275374023, "grad_norm": 3.455512285232544, "learning_rate": 1.4784482758620691e-05, "loss": 1.5065, "step": 1700 }, { "epoch": 0.2616822429906542, "grad_norm": 2.670595407485962, "learning_rate": 1.47814039408867e-05, "loss": 1.1717, "step": 1701 }, { "epoch": 0.2618360832275682, "grad_norm": 3.6793830394744873, "learning_rate": 1.4778325123152711e-05, "loss": 1.2034, "step": 1702 }, { "epoch": 0.26198992346448213, "grad_norm": 3.822869300842285, "learning_rate": 1.477524630541872e-05, "loss": 1.4591, "step": 1703 }, { "epoch": 0.2621437637013961, "grad_norm": 3.2616565227508545, "learning_rate": 1.477216748768473e-05, "loss": 1.3155, "step": 1704 }, { "epoch": 0.2622976039383101, "grad_norm": 4.157482147216797, "learning_rate": 1.476908866995074e-05, "loss": 1.59, "step": 1705 }, { "epoch": 0.26245144417522404, "grad_norm": 3.2241592407226562, "learning_rate": 1.476600985221675e-05, "loss": 1.6123, "step": 1706 }, { "epoch": 0.262605284412138, "grad_norm": 3.4736216068267822, "learning_rate": 1.4762931034482759e-05, "loss": 1.4258, "step": 1707 }, { "epoch": 0.26275912464905193, "grad_norm": 4.394448280334473, "learning_rate": 1.475985221674877e-05, "loss": 1.2111, "step": 1708 }, { "epoch": 0.26291296488596594, "grad_norm": 3.638988733291626, "learning_rate": 1.4756773399014779e-05, "loss": 1.3007, "step": 1709 }, { "epoch": 0.2630668051228799, "grad_norm": 3.7847321033477783, "learning_rate": 1.475369458128079e-05, "loss": 1.3595, "step": 1710 }, { "epoch": 0.26322064535979384, "grad_norm": 3.4809353351593018, "learning_rate": 1.4750615763546798e-05, "loss": 1.22, "step": 1711 }, { "epoch": 0.26337448559670784, "grad_norm": 3.5716583728790283, "learning_rate": 1.4747536945812809e-05, "loss": 1.4265, "step": 1712 }, { "epoch": 0.2635283258336218, "grad_norm": 3.461261510848999, "learning_rate": 1.4744458128078818e-05, "loss": 1.3123, "step": 1713 }, { "epoch": 0.26368216607053574, "grad_norm": 3.1071527004241943, "learning_rate": 1.4741379310344829e-05, "loss": 1.492, "step": 1714 }, { "epoch": 0.2638360063074497, "grad_norm": 3.292198896408081, "learning_rate": 1.473830049261084e-05, "loss": 1.2969, "step": 1715 }, { "epoch": 0.2639898465443637, "grad_norm": 3.742532968521118, "learning_rate": 1.473522167487685e-05, "loss": 1.0497, "step": 1716 }, { "epoch": 0.26414368678127764, "grad_norm": 3.7784886360168457, "learning_rate": 1.4732142857142859e-05, "loss": 1.5594, "step": 1717 }, { "epoch": 0.2642975270181916, "grad_norm": 4.135756015777588, "learning_rate": 1.472906403940887e-05, "loss": 1.3101, "step": 1718 }, { "epoch": 0.2644513672551056, "grad_norm": 3.8492648601531982, "learning_rate": 1.4725985221674878e-05, "loss": 1.6846, "step": 1719 }, { "epoch": 0.26460520749201955, "grad_norm": 4.144170761108398, "learning_rate": 1.4722906403940889e-05, "loss": 1.4838, "step": 1720 }, { "epoch": 0.2647590477289335, "grad_norm": 3.7365622520446777, "learning_rate": 1.4719827586206898e-05, "loss": 1.3428, "step": 1721 }, { "epoch": 0.26491288796584744, "grad_norm": 3.5493524074554443, "learning_rate": 1.4716748768472909e-05, "loss": 1.3155, "step": 1722 }, { "epoch": 0.26506672820276145, "grad_norm": 4.45180606842041, "learning_rate": 1.4713669950738918e-05, "loss": 1.6095, "step": 1723 }, { "epoch": 0.2652205684396754, "grad_norm": 4.046501636505127, "learning_rate": 1.4710591133004928e-05, "loss": 1.4459, "step": 1724 }, { "epoch": 0.26537440867658935, "grad_norm": 3.7689695358276367, "learning_rate": 1.4707512315270937e-05, "loss": 1.4257, "step": 1725 }, { "epoch": 0.26552824891350335, "grad_norm": 3.860383987426758, "learning_rate": 1.4704433497536948e-05, "loss": 1.3863, "step": 1726 }, { "epoch": 0.2656820891504173, "grad_norm": 3.8568456172943115, "learning_rate": 1.4701354679802957e-05, "loss": 1.4428, "step": 1727 }, { "epoch": 0.26583592938733125, "grad_norm": 3.163337230682373, "learning_rate": 1.4698275862068967e-05, "loss": 0.9729, "step": 1728 }, { "epoch": 0.2659897696242452, "grad_norm": 3.4695630073547363, "learning_rate": 1.4695197044334976e-05, "loss": 1.4368, "step": 1729 }, { "epoch": 0.2661436098611592, "grad_norm": 3.07950758934021, "learning_rate": 1.4692118226600987e-05, "loss": 1.2593, "step": 1730 }, { "epoch": 0.26629745009807315, "grad_norm": 3.811115026473999, "learning_rate": 1.4689039408866996e-05, "loss": 1.2841, "step": 1731 }, { "epoch": 0.2664512903349871, "grad_norm": 3.7514448165893555, "learning_rate": 1.4685960591133007e-05, "loss": 1.4353, "step": 1732 }, { "epoch": 0.2666051305719011, "grad_norm": 3.2354636192321777, "learning_rate": 1.4682881773399016e-05, "loss": 1.2863, "step": 1733 }, { "epoch": 0.26675897080881505, "grad_norm": 3.4808709621429443, "learning_rate": 1.4679802955665026e-05, "loss": 1.43, "step": 1734 }, { "epoch": 0.266912811045729, "grad_norm": 3.67399263381958, "learning_rate": 1.4676724137931035e-05, "loss": 1.4163, "step": 1735 }, { "epoch": 0.26706665128264295, "grad_norm": 5.108880043029785, "learning_rate": 1.4673645320197046e-05, "loss": 1.4282, "step": 1736 }, { "epoch": 0.26722049151955696, "grad_norm": 3.6838581562042236, "learning_rate": 1.4670566502463055e-05, "loss": 1.3047, "step": 1737 }, { "epoch": 0.2673743317564709, "grad_norm": 3.8062946796417236, "learning_rate": 1.4667487684729065e-05, "loss": 1.2833, "step": 1738 }, { "epoch": 0.26752817199338486, "grad_norm": 3.9912474155426025, "learning_rate": 1.4664408866995074e-05, "loss": 1.3192, "step": 1739 }, { "epoch": 0.26768201223029886, "grad_norm": 4.169310092926025, "learning_rate": 1.4661330049261085e-05, "loss": 1.2374, "step": 1740 }, { "epoch": 0.2678358524672128, "grad_norm": 3.6631288528442383, "learning_rate": 1.4658251231527094e-05, "loss": 1.2904, "step": 1741 }, { "epoch": 0.26798969270412676, "grad_norm": 3.8360397815704346, "learning_rate": 1.4655172413793105e-05, "loss": 1.2158, "step": 1742 }, { "epoch": 0.2681435329410407, "grad_norm": 3.245422124862671, "learning_rate": 1.4652093596059114e-05, "loss": 1.1339, "step": 1743 }, { "epoch": 0.2682973731779547, "grad_norm": 3.9317758083343506, "learning_rate": 1.4649014778325124e-05, "loss": 1.48, "step": 1744 }, { "epoch": 0.26845121341486866, "grad_norm": 3.0702435970306396, "learning_rate": 1.4645935960591133e-05, "loss": 1.5883, "step": 1745 }, { "epoch": 0.2686050536517826, "grad_norm": 3.4018733501434326, "learning_rate": 1.4642857142857144e-05, "loss": 1.3504, "step": 1746 }, { "epoch": 0.2687588938886966, "grad_norm": 3.5474047660827637, "learning_rate": 1.4639778325123153e-05, "loss": 1.405, "step": 1747 }, { "epoch": 0.26891273412561056, "grad_norm": 3.4428086280822754, "learning_rate": 1.4636699507389163e-05, "loss": 1.4994, "step": 1748 }, { "epoch": 0.2690665743625245, "grad_norm": 4.144750595092773, "learning_rate": 1.4633620689655174e-05, "loss": 1.0015, "step": 1749 }, { "epoch": 0.26922041459943846, "grad_norm": 3.611351728439331, "learning_rate": 1.4630541871921185e-05, "loss": 1.4557, "step": 1750 }, { "epoch": 0.26937425483635247, "grad_norm": 4.371041774749756, "learning_rate": 1.4627463054187194e-05, "loss": 1.3639, "step": 1751 }, { "epoch": 0.2695280950732664, "grad_norm": 3.6847119331359863, "learning_rate": 1.4624384236453204e-05, "loss": 1.439, "step": 1752 }, { "epoch": 0.26968193531018037, "grad_norm": 3.629086971282959, "learning_rate": 1.4621305418719213e-05, "loss": 1.3139, "step": 1753 }, { "epoch": 0.26983577554709437, "grad_norm": 3.5147416591644287, "learning_rate": 1.4618226600985224e-05, "loss": 1.4549, "step": 1754 }, { "epoch": 0.2699896157840083, "grad_norm": 3.5198702812194824, "learning_rate": 1.4615147783251233e-05, "loss": 1.322, "step": 1755 }, { "epoch": 0.27014345602092227, "grad_norm": 4.486267566680908, "learning_rate": 1.4612068965517243e-05, "loss": 1.43, "step": 1756 }, { "epoch": 0.2702972962578362, "grad_norm": 3.0333034992218018, "learning_rate": 1.4608990147783252e-05, "loss": 1.3916, "step": 1757 }, { "epoch": 0.2704511364947502, "grad_norm": 3.8770627975463867, "learning_rate": 1.4605911330049263e-05, "loss": 1.5209, "step": 1758 }, { "epoch": 0.27060497673166417, "grad_norm": 3.7828209400177, "learning_rate": 1.4602832512315272e-05, "loss": 1.4097, "step": 1759 }, { "epoch": 0.2707588169685781, "grad_norm": 3.657285451889038, "learning_rate": 1.4599753694581283e-05, "loss": 1.2824, "step": 1760 }, { "epoch": 0.27091265720549207, "grad_norm": 3.6795270442962646, "learning_rate": 1.4596674876847292e-05, "loss": 1.4081, "step": 1761 }, { "epoch": 0.2710664974424061, "grad_norm": 3.773782730102539, "learning_rate": 1.4593596059113302e-05, "loss": 1.5345, "step": 1762 }, { "epoch": 0.27122033767932, "grad_norm": 3.4582338333129883, "learning_rate": 1.4590517241379311e-05, "loss": 1.4341, "step": 1763 }, { "epoch": 0.27137417791623397, "grad_norm": 3.623234987258911, "learning_rate": 1.4587438423645322e-05, "loss": 1.4728, "step": 1764 }, { "epoch": 0.271528018153148, "grad_norm": 4.577991485595703, "learning_rate": 1.458435960591133e-05, "loss": 1.5034, "step": 1765 }, { "epoch": 0.2716818583900619, "grad_norm": 3.5057411193847656, "learning_rate": 1.4581280788177341e-05, "loss": 1.4744, "step": 1766 }, { "epoch": 0.2718356986269759, "grad_norm": 4.389951705932617, "learning_rate": 1.457820197044335e-05, "loss": 1.3928, "step": 1767 }, { "epoch": 0.2719895388638898, "grad_norm": 4.359461784362793, "learning_rate": 1.4575123152709361e-05, "loss": 1.6091, "step": 1768 }, { "epoch": 0.27214337910080383, "grad_norm": 3.8663105964660645, "learning_rate": 1.457204433497537e-05, "loss": 1.4997, "step": 1769 }, { "epoch": 0.2722972193377178, "grad_norm": 3.2211523056030273, "learning_rate": 1.456896551724138e-05, "loss": 1.1653, "step": 1770 }, { "epoch": 0.2724510595746317, "grad_norm": 3.526759386062622, "learning_rate": 1.456588669950739e-05, "loss": 1.2662, "step": 1771 }, { "epoch": 0.27260489981154573, "grad_norm": 4.031111717224121, "learning_rate": 1.45628078817734e-05, "loss": 1.5772, "step": 1772 }, { "epoch": 0.2727587400484597, "grad_norm": 3.2483561038970947, "learning_rate": 1.4559729064039409e-05, "loss": 1.4375, "step": 1773 }, { "epoch": 0.27291258028537363, "grad_norm": 3.4457409381866455, "learning_rate": 1.455665024630542e-05, "loss": 1.3529, "step": 1774 }, { "epoch": 0.2730664205222876, "grad_norm": 3.5012238025665283, "learning_rate": 1.4553571428571429e-05, "loss": 1.5032, "step": 1775 }, { "epoch": 0.2732202607592016, "grad_norm": 3.6357712745666504, "learning_rate": 1.455049261083744e-05, "loss": 1.3091, "step": 1776 }, { "epoch": 0.27337410099611553, "grad_norm": 4.1044816970825195, "learning_rate": 1.4547413793103448e-05, "loss": 1.307, "step": 1777 }, { "epoch": 0.2735279412330295, "grad_norm": 3.5485336780548096, "learning_rate": 1.4544334975369459e-05, "loss": 1.2561, "step": 1778 }, { "epoch": 0.2736817814699435, "grad_norm": 3.7935023307800293, "learning_rate": 1.4541256157635468e-05, "loss": 1.1176, "step": 1779 }, { "epoch": 0.27383562170685743, "grad_norm": 4.162144184112549, "learning_rate": 1.4538177339901479e-05, "loss": 1.1721, "step": 1780 }, { "epoch": 0.2739894619437714, "grad_norm": 4.200039863586426, "learning_rate": 1.4535098522167488e-05, "loss": 1.3534, "step": 1781 }, { "epoch": 0.27414330218068533, "grad_norm": 3.9337363243103027, "learning_rate": 1.4532019704433498e-05, "loss": 1.4348, "step": 1782 }, { "epoch": 0.27429714241759934, "grad_norm": 3.21061635017395, "learning_rate": 1.4528940886699509e-05, "loss": 1.4861, "step": 1783 }, { "epoch": 0.2744509826545133, "grad_norm": 3.8282363414764404, "learning_rate": 1.452586206896552e-05, "loss": 1.4104, "step": 1784 }, { "epoch": 0.27460482289142724, "grad_norm": 3.226726531982422, "learning_rate": 1.4522783251231528e-05, "loss": 1.0752, "step": 1785 }, { "epoch": 0.27475866312834124, "grad_norm": 3.9309263229370117, "learning_rate": 1.4519704433497539e-05, "loss": 1.5334, "step": 1786 }, { "epoch": 0.2749125033652552, "grad_norm": 4.052085876464844, "learning_rate": 1.4516625615763548e-05, "loss": 1.3438, "step": 1787 }, { "epoch": 0.27506634360216914, "grad_norm": 4.20543098449707, "learning_rate": 1.4513546798029559e-05, "loss": 1.4806, "step": 1788 }, { "epoch": 0.2752201838390831, "grad_norm": 4.180453777313232, "learning_rate": 1.4510467980295568e-05, "loss": 1.2692, "step": 1789 }, { "epoch": 0.2753740240759971, "grad_norm": 4.42955207824707, "learning_rate": 1.4507389162561578e-05, "loss": 1.4241, "step": 1790 }, { "epoch": 0.27552786431291104, "grad_norm": 4.1153435707092285, "learning_rate": 1.4504310344827587e-05, "loss": 1.3362, "step": 1791 }, { "epoch": 0.275681704549825, "grad_norm": 3.5130670070648193, "learning_rate": 1.4501231527093598e-05, "loss": 1.5596, "step": 1792 }, { "epoch": 0.275835544786739, "grad_norm": 3.600088596343994, "learning_rate": 1.4498152709359607e-05, "loss": 1.5368, "step": 1793 }, { "epoch": 0.27598938502365294, "grad_norm": 3.8893930912017822, "learning_rate": 1.4495073891625617e-05, "loss": 1.4946, "step": 1794 }, { "epoch": 0.2761432252605669, "grad_norm": 3.0995123386383057, "learning_rate": 1.4491995073891626e-05, "loss": 1.4585, "step": 1795 }, { "epoch": 0.27629706549748084, "grad_norm": 4.04783821105957, "learning_rate": 1.4488916256157637e-05, "loss": 1.2603, "step": 1796 }, { "epoch": 0.27645090573439485, "grad_norm": 3.2921154499053955, "learning_rate": 1.4485837438423646e-05, "loss": 1.3895, "step": 1797 }, { "epoch": 0.2766047459713088, "grad_norm": 3.501704454421997, "learning_rate": 1.4482758620689657e-05, "loss": 1.3362, "step": 1798 }, { "epoch": 0.27675858620822275, "grad_norm": 3.307400703430176, "learning_rate": 1.4479679802955666e-05, "loss": 1.5824, "step": 1799 }, { "epoch": 0.27691242644513675, "grad_norm": 3.3196351528167725, "learning_rate": 1.4476600985221676e-05, "loss": 1.061, "step": 1800 }, { "epoch": 0.2770662666820507, "grad_norm": 3.8715903759002686, "learning_rate": 1.4473522167487685e-05, "loss": 1.4201, "step": 1801 }, { "epoch": 0.27722010691896465, "grad_norm": 3.1629104614257812, "learning_rate": 1.4470443349753696e-05, "loss": 1.1017, "step": 1802 }, { "epoch": 0.2773739471558786, "grad_norm": 3.5161218643188477, "learning_rate": 1.4467364532019705e-05, "loss": 1.5545, "step": 1803 }, { "epoch": 0.2775277873927926, "grad_norm": 3.858457088470459, "learning_rate": 1.4464285714285715e-05, "loss": 1.6252, "step": 1804 }, { "epoch": 0.27768162762970655, "grad_norm": 3.4501843452453613, "learning_rate": 1.4461206896551724e-05, "loss": 1.429, "step": 1805 }, { "epoch": 0.2778354678666205, "grad_norm": 2.9569599628448486, "learning_rate": 1.4458128078817735e-05, "loss": 1.2394, "step": 1806 }, { "epoch": 0.2779893081035345, "grad_norm": 4.002588748931885, "learning_rate": 1.4455049261083744e-05, "loss": 1.3788, "step": 1807 }, { "epoch": 0.27814314834044845, "grad_norm": 3.5656936168670654, "learning_rate": 1.4451970443349755e-05, "loss": 1.4282, "step": 1808 }, { "epoch": 0.2782969885773624, "grad_norm": 3.833528518676758, "learning_rate": 1.4448891625615764e-05, "loss": 1.334, "step": 1809 }, { "epoch": 0.27845082881427635, "grad_norm": 3.685378074645996, "learning_rate": 1.4445812807881774e-05, "loss": 1.2765, "step": 1810 }, { "epoch": 0.27860466905119036, "grad_norm": 3.5947747230529785, "learning_rate": 1.4442733990147783e-05, "loss": 1.265, "step": 1811 }, { "epoch": 0.2787585092881043, "grad_norm": 3.8551456928253174, "learning_rate": 1.4439655172413794e-05, "loss": 1.3949, "step": 1812 }, { "epoch": 0.27891234952501825, "grad_norm": 4.155323028564453, "learning_rate": 1.4436576354679803e-05, "loss": 1.2143, "step": 1813 }, { "epoch": 0.27906618976193226, "grad_norm": 3.948906183242798, "learning_rate": 1.4433497536945813e-05, "loss": 1.6219, "step": 1814 }, { "epoch": 0.2792200299988462, "grad_norm": 3.111165761947632, "learning_rate": 1.4430418719211822e-05, "loss": 1.4764, "step": 1815 }, { "epoch": 0.27937387023576016, "grad_norm": 4.098602771759033, "learning_rate": 1.4427339901477833e-05, "loss": 1.7867, "step": 1816 }, { "epoch": 0.2795277104726741, "grad_norm": 3.250009775161743, "learning_rate": 1.4424261083743845e-05, "loss": 1.3657, "step": 1817 }, { "epoch": 0.2796815507095881, "grad_norm": 4.520541191101074, "learning_rate": 1.4421182266009854e-05, "loss": 1.5018, "step": 1818 }, { "epoch": 0.27983539094650206, "grad_norm": 4.032090187072754, "learning_rate": 1.4418103448275865e-05, "loss": 1.5047, "step": 1819 }, { "epoch": 0.279989231183416, "grad_norm": 3.573251485824585, "learning_rate": 1.4415024630541874e-05, "loss": 1.1915, "step": 1820 }, { "epoch": 0.28014307142033, "grad_norm": 3.9665567874908447, "learning_rate": 1.4411945812807885e-05, "loss": 1.4051, "step": 1821 }, { "epoch": 0.28029691165724396, "grad_norm": 3.3372390270233154, "learning_rate": 1.4408866995073894e-05, "loss": 1.4283, "step": 1822 }, { "epoch": 0.2804507518941579, "grad_norm": 3.5350916385650635, "learning_rate": 1.4405788177339904e-05, "loss": 1.4693, "step": 1823 }, { "epoch": 0.28060459213107186, "grad_norm": 3.6230850219726562, "learning_rate": 1.4402709359605913e-05, "loss": 1.3892, "step": 1824 }, { "epoch": 0.28075843236798587, "grad_norm": 4.153363227844238, "learning_rate": 1.4399630541871922e-05, "loss": 1.2695, "step": 1825 }, { "epoch": 0.2809122726048998, "grad_norm": 3.522268533706665, "learning_rate": 1.4396551724137933e-05, "loss": 1.518, "step": 1826 }, { "epoch": 0.28106611284181376, "grad_norm": 3.847769021987915, "learning_rate": 1.4393472906403942e-05, "loss": 1.6118, "step": 1827 }, { "epoch": 0.2812199530787277, "grad_norm": 4.179295539855957, "learning_rate": 1.4390394088669952e-05, "loss": 1.4017, "step": 1828 }, { "epoch": 0.2813737933156417, "grad_norm": 3.624513626098633, "learning_rate": 1.4387315270935961e-05, "loss": 1.4874, "step": 1829 }, { "epoch": 0.28152763355255567, "grad_norm": 3.7829432487487793, "learning_rate": 1.4384236453201972e-05, "loss": 1.3965, "step": 1830 }, { "epoch": 0.2816814737894696, "grad_norm": 4.717529296875, "learning_rate": 1.438115763546798e-05, "loss": 1.4428, "step": 1831 }, { "epoch": 0.2818353140263836, "grad_norm": 3.5932016372680664, "learning_rate": 1.4378078817733991e-05, "loss": 1.3053, "step": 1832 }, { "epoch": 0.28198915426329757, "grad_norm": 3.88759183883667, "learning_rate": 1.4375e-05, "loss": 1.4243, "step": 1833 }, { "epoch": 0.2821429945002115, "grad_norm": 3.9638078212738037, "learning_rate": 1.4371921182266011e-05, "loss": 1.4498, "step": 1834 }, { "epoch": 0.28229683473712547, "grad_norm": 3.333836078643799, "learning_rate": 1.436884236453202e-05, "loss": 1.467, "step": 1835 }, { "epoch": 0.2824506749740395, "grad_norm": 3.871774673461914, "learning_rate": 1.436576354679803e-05, "loss": 1.4463, "step": 1836 }, { "epoch": 0.2826045152109534, "grad_norm": 3.7308666706085205, "learning_rate": 1.436268472906404e-05, "loss": 1.2092, "step": 1837 }, { "epoch": 0.28275835544786737, "grad_norm": 3.353088855743408, "learning_rate": 1.435960591133005e-05, "loss": 1.2804, "step": 1838 }, { "epoch": 0.2829121956847814, "grad_norm": 4.279623508453369, "learning_rate": 1.435652709359606e-05, "loss": 1.4474, "step": 1839 }, { "epoch": 0.2830660359216953, "grad_norm": 3.8809499740600586, "learning_rate": 1.435344827586207e-05, "loss": 1.5339, "step": 1840 }, { "epoch": 0.2832198761586093, "grad_norm": 4.203039169311523, "learning_rate": 1.4350369458128079e-05, "loss": 1.5559, "step": 1841 }, { "epoch": 0.2833737163955232, "grad_norm": 3.534029960632324, "learning_rate": 1.434729064039409e-05, "loss": 1.3172, "step": 1842 }, { "epoch": 0.2835275566324372, "grad_norm": 4.554759502410889, "learning_rate": 1.4344211822660098e-05, "loss": 1.5783, "step": 1843 }, { "epoch": 0.2836813968693512, "grad_norm": 3.703449249267578, "learning_rate": 1.4341133004926109e-05, "loss": 1.45, "step": 1844 }, { "epoch": 0.2838352371062651, "grad_norm": 4.208304405212402, "learning_rate": 1.4338054187192118e-05, "loss": 1.2956, "step": 1845 }, { "epoch": 0.28398907734317913, "grad_norm": 3.8135416507720947, "learning_rate": 1.4334975369458129e-05, "loss": 1.5705, "step": 1846 }, { "epoch": 0.2841429175800931, "grad_norm": 4.012787818908691, "learning_rate": 1.4331896551724138e-05, "loss": 1.5362, "step": 1847 }, { "epoch": 0.28429675781700703, "grad_norm": 3.3311562538146973, "learning_rate": 1.4328817733990148e-05, "loss": 1.2999, "step": 1848 }, { "epoch": 0.284450598053921, "grad_norm": 3.680821418762207, "learning_rate": 1.4325738916256157e-05, "loss": 1.5778, "step": 1849 }, { "epoch": 0.284604438290835, "grad_norm": 3.489856243133545, "learning_rate": 1.432266009852217e-05, "loss": 1.3428, "step": 1850 }, { "epoch": 0.28475827852774893, "grad_norm": 4.021574974060059, "learning_rate": 1.431958128078818e-05, "loss": 1.3002, "step": 1851 }, { "epoch": 0.2849121187646629, "grad_norm": 3.9016225337982178, "learning_rate": 1.4316502463054189e-05, "loss": 1.559, "step": 1852 }, { "epoch": 0.2850659590015769, "grad_norm": 4.319624900817871, "learning_rate": 1.43134236453202e-05, "loss": 1.4605, "step": 1853 }, { "epoch": 0.28521979923849083, "grad_norm": 4.024723052978516, "learning_rate": 1.4310344827586209e-05, "loss": 1.5539, "step": 1854 }, { "epoch": 0.2853736394754048, "grad_norm": 4.927731513977051, "learning_rate": 1.430726600985222e-05, "loss": 1.352, "step": 1855 }, { "epoch": 0.28552747971231873, "grad_norm": 3.6479506492614746, "learning_rate": 1.4304187192118228e-05, "loss": 1.2755, "step": 1856 }, { "epoch": 0.28568131994923274, "grad_norm": 4.627477169036865, "learning_rate": 1.4301108374384239e-05, "loss": 1.4466, "step": 1857 }, { "epoch": 0.2858351601861467, "grad_norm": 4.021594047546387, "learning_rate": 1.4298029556650248e-05, "loss": 1.5722, "step": 1858 }, { "epoch": 0.28598900042306064, "grad_norm": 4.0596160888671875, "learning_rate": 1.4294950738916259e-05, "loss": 1.5356, "step": 1859 }, { "epoch": 0.28614284065997464, "grad_norm": 3.1031014919281006, "learning_rate": 1.4291871921182268e-05, "loss": 1.2587, "step": 1860 }, { "epoch": 0.2862966808968886, "grad_norm": 3.7177939414978027, "learning_rate": 1.4288793103448278e-05, "loss": 1.5025, "step": 1861 }, { "epoch": 0.28645052113380254, "grad_norm": 3.703118085861206, "learning_rate": 1.4285714285714287e-05, "loss": 1.5866, "step": 1862 }, { "epoch": 0.2866043613707165, "grad_norm": 3.7209293842315674, "learning_rate": 1.4282635467980298e-05, "loss": 1.2088, "step": 1863 }, { "epoch": 0.2867582016076305, "grad_norm": 3.645559072494507, "learning_rate": 1.4279556650246307e-05, "loss": 1.4427, "step": 1864 }, { "epoch": 0.28691204184454444, "grad_norm": 3.7969279289245605, "learning_rate": 1.4276477832512317e-05, "loss": 1.5058, "step": 1865 }, { "epoch": 0.2870658820814584, "grad_norm": 4.014613151550293, "learning_rate": 1.4273399014778326e-05, "loss": 1.4171, "step": 1866 }, { "epoch": 0.2872197223183724, "grad_norm": 3.648106098175049, "learning_rate": 1.4270320197044337e-05, "loss": 1.469, "step": 1867 }, { "epoch": 0.28737356255528634, "grad_norm": 3.6557891368865967, "learning_rate": 1.4267241379310346e-05, "loss": 1.303, "step": 1868 }, { "epoch": 0.2875274027922003, "grad_norm": 3.358234167098999, "learning_rate": 1.4264162561576355e-05, "loss": 1.4944, "step": 1869 }, { "epoch": 0.28768124302911424, "grad_norm": 3.889171838760376, "learning_rate": 1.4261083743842366e-05, "loss": 1.2436, "step": 1870 }, { "epoch": 0.28783508326602825, "grad_norm": 3.7026610374450684, "learning_rate": 1.4258004926108374e-05, "loss": 1.4683, "step": 1871 }, { "epoch": 0.2879889235029422, "grad_norm": 4.313275337219238, "learning_rate": 1.4254926108374385e-05, "loss": 1.0796, "step": 1872 }, { "epoch": 0.28814276373985614, "grad_norm": 3.321345329284668, "learning_rate": 1.4251847290640394e-05, "loss": 1.4855, "step": 1873 }, { "epoch": 0.28829660397677015, "grad_norm": 3.296910047531128, "learning_rate": 1.4248768472906405e-05, "loss": 1.5148, "step": 1874 }, { "epoch": 0.2884504442136841, "grad_norm": 3.1409683227539062, "learning_rate": 1.4245689655172414e-05, "loss": 1.129, "step": 1875 }, { "epoch": 0.28860428445059805, "grad_norm": 3.6360843181610107, "learning_rate": 1.4242610837438424e-05, "loss": 1.5223, "step": 1876 }, { "epoch": 0.288758124687512, "grad_norm": 3.5573718547821045, "learning_rate": 1.4239532019704433e-05, "loss": 1.4496, "step": 1877 }, { "epoch": 0.288911964924426, "grad_norm": 3.6546456813812256, "learning_rate": 1.4236453201970444e-05, "loss": 1.2748, "step": 1878 }, { "epoch": 0.28906580516133995, "grad_norm": 4.100497722625732, "learning_rate": 1.4233374384236453e-05, "loss": 1.39, "step": 1879 }, { "epoch": 0.2892196453982539, "grad_norm": 3.5230696201324463, "learning_rate": 1.4230295566502463e-05, "loss": 1.4192, "step": 1880 }, { "epoch": 0.2893734856351679, "grad_norm": 3.7045276165008545, "learning_rate": 1.4227216748768472e-05, "loss": 1.477, "step": 1881 }, { "epoch": 0.28952732587208185, "grad_norm": 4.012545108795166, "learning_rate": 1.4224137931034483e-05, "loss": 1.4777, "step": 1882 }, { "epoch": 0.2896811661089958, "grad_norm": 4.051698207855225, "learning_rate": 1.4221059113300492e-05, "loss": 1.3654, "step": 1883 }, { "epoch": 0.28983500634590975, "grad_norm": 3.378345489501953, "learning_rate": 1.4217980295566504e-05, "loss": 1.3135, "step": 1884 }, { "epoch": 0.28998884658282376, "grad_norm": 3.4875643253326416, "learning_rate": 1.4214901477832515e-05, "loss": 1.4728, "step": 1885 }, { "epoch": 0.2901426868197377, "grad_norm": 3.6980350017547607, "learning_rate": 1.4211822660098524e-05, "loss": 1.4063, "step": 1886 }, { "epoch": 0.29029652705665165, "grad_norm": 3.855839490890503, "learning_rate": 1.4208743842364535e-05, "loss": 1.8165, "step": 1887 }, { "epoch": 0.29045036729356566, "grad_norm": 3.376167058944702, "learning_rate": 1.4205665024630544e-05, "loss": 1.2819, "step": 1888 }, { "epoch": 0.2906042075304796, "grad_norm": 2.936802864074707, "learning_rate": 1.4202586206896554e-05, "loss": 1.1724, "step": 1889 }, { "epoch": 0.29075804776739356, "grad_norm": 4.227983474731445, "learning_rate": 1.4199507389162563e-05, "loss": 1.2515, "step": 1890 }, { "epoch": 0.2909118880043075, "grad_norm": 3.5676374435424805, "learning_rate": 1.4196428571428574e-05, "loss": 1.4051, "step": 1891 }, { "epoch": 0.2910657282412215, "grad_norm": 3.4523370265960693, "learning_rate": 1.4193349753694583e-05, "loss": 1.2921, "step": 1892 }, { "epoch": 0.29121956847813546, "grad_norm": 4.019986152648926, "learning_rate": 1.4190270935960593e-05, "loss": 1.3226, "step": 1893 }, { "epoch": 0.2913734087150494, "grad_norm": 3.1409800052642822, "learning_rate": 1.4187192118226602e-05, "loss": 1.388, "step": 1894 }, { "epoch": 0.2915272489519634, "grad_norm": 3.648761034011841, "learning_rate": 1.4184113300492613e-05, "loss": 1.4535, "step": 1895 }, { "epoch": 0.29168108918887736, "grad_norm": 3.804759979248047, "learning_rate": 1.4181034482758622e-05, "loss": 1.1543, "step": 1896 }, { "epoch": 0.2918349294257913, "grad_norm": 4.315131664276123, "learning_rate": 1.4177955665024633e-05, "loss": 1.3122, "step": 1897 }, { "epoch": 0.29198876966270526, "grad_norm": 3.881927490234375, "learning_rate": 1.4174876847290642e-05, "loss": 1.39, "step": 1898 }, { "epoch": 0.29214260989961927, "grad_norm": 3.907054901123047, "learning_rate": 1.4171798029556652e-05, "loss": 1.534, "step": 1899 }, { "epoch": 0.2922964501365332, "grad_norm": 3.885425329208374, "learning_rate": 1.4168719211822661e-05, "loss": 1.6384, "step": 1900 }, { "epoch": 0.29245029037344716, "grad_norm": 3.9576385021209717, "learning_rate": 1.4165640394088672e-05, "loss": 1.3335, "step": 1901 }, { "epoch": 0.2926041306103611, "grad_norm": 3.9644861221313477, "learning_rate": 1.416256157635468e-05, "loss": 1.2885, "step": 1902 }, { "epoch": 0.2927579708472751, "grad_norm": 3.24666690826416, "learning_rate": 1.4159482758620691e-05, "loss": 1.3976, "step": 1903 }, { "epoch": 0.29291181108418907, "grad_norm": 4.121837139129639, "learning_rate": 1.41564039408867e-05, "loss": 1.3109, "step": 1904 }, { "epoch": 0.293065651321103, "grad_norm": 3.703005790710449, "learning_rate": 1.4153325123152711e-05, "loss": 1.4076, "step": 1905 }, { "epoch": 0.293219491558017, "grad_norm": 3.4723148345947266, "learning_rate": 1.415024630541872e-05, "loss": 1.2147, "step": 1906 }, { "epoch": 0.29337333179493097, "grad_norm": 4.097095012664795, "learning_rate": 1.414716748768473e-05, "loss": 1.0615, "step": 1907 }, { "epoch": 0.2935271720318449, "grad_norm": 3.8897101879119873, "learning_rate": 1.414408866995074e-05, "loss": 1.5827, "step": 1908 }, { "epoch": 0.29368101226875887, "grad_norm": 3.3429226875305176, "learning_rate": 1.414100985221675e-05, "loss": 1.3829, "step": 1909 }, { "epoch": 0.29383485250567287, "grad_norm": 4.099124431610107, "learning_rate": 1.4137931034482759e-05, "loss": 1.4327, "step": 1910 }, { "epoch": 0.2939886927425868, "grad_norm": 4.058679103851318, "learning_rate": 1.413485221674877e-05, "loss": 1.244, "step": 1911 }, { "epoch": 0.29414253297950077, "grad_norm": 3.214578866958618, "learning_rate": 1.4131773399014779e-05, "loss": 1.3083, "step": 1912 }, { "epoch": 0.2942963732164148, "grad_norm": 4.345895767211914, "learning_rate": 1.4128694581280788e-05, "loss": 1.4853, "step": 1913 }, { "epoch": 0.2944502134533287, "grad_norm": 4.056304931640625, "learning_rate": 1.4125615763546798e-05, "loss": 1.5438, "step": 1914 }, { "epoch": 0.2946040536902427, "grad_norm": 3.607187271118164, "learning_rate": 1.4122536945812807e-05, "loss": 1.2199, "step": 1915 }, { "epoch": 0.2947578939271566, "grad_norm": 3.7854080200195312, "learning_rate": 1.4119458128078818e-05, "loss": 1.3139, "step": 1916 }, { "epoch": 0.2949117341640706, "grad_norm": 3.289876699447632, "learning_rate": 1.4116379310344827e-05, "loss": 1.265, "step": 1917 }, { "epoch": 0.2950655744009846, "grad_norm": 4.218797206878662, "learning_rate": 1.411330049261084e-05, "loss": 1.3432, "step": 1918 }, { "epoch": 0.2952194146378985, "grad_norm": 4.118810653686523, "learning_rate": 1.411022167487685e-05, "loss": 1.2513, "step": 1919 }, { "epoch": 0.29537325487481253, "grad_norm": 2.740168333053589, "learning_rate": 1.4107142857142859e-05, "loss": 1.3069, "step": 1920 }, { "epoch": 0.2955270951117265, "grad_norm": 5.03168249130249, "learning_rate": 1.410406403940887e-05, "loss": 1.5464, "step": 1921 }, { "epoch": 0.29568093534864043, "grad_norm": 3.6174018383026123, "learning_rate": 1.4100985221674878e-05, "loss": 1.4094, "step": 1922 }, { "epoch": 0.2958347755855544, "grad_norm": 3.4296927452087402, "learning_rate": 1.4097906403940889e-05, "loss": 1.3244, "step": 1923 }, { "epoch": 0.2959886158224684, "grad_norm": 3.390673875808716, "learning_rate": 1.4094827586206898e-05, "loss": 1.5193, "step": 1924 }, { "epoch": 0.29614245605938233, "grad_norm": 3.154228925704956, "learning_rate": 1.4091748768472909e-05, "loss": 1.3099, "step": 1925 }, { "epoch": 0.2962962962962963, "grad_norm": 3.2935116291046143, "learning_rate": 1.4088669950738918e-05, "loss": 1.4493, "step": 1926 }, { "epoch": 0.2964501365332103, "grad_norm": 4.197569847106934, "learning_rate": 1.4085591133004928e-05, "loss": 1.4099, "step": 1927 }, { "epoch": 0.29660397677012423, "grad_norm": 3.347268581390381, "learning_rate": 1.4082512315270937e-05, "loss": 1.4268, "step": 1928 }, { "epoch": 0.2967578170070382, "grad_norm": 3.454773426055908, "learning_rate": 1.4079433497536948e-05, "loss": 1.4667, "step": 1929 }, { "epoch": 0.29691165724395213, "grad_norm": 3.56536865234375, "learning_rate": 1.4076354679802957e-05, "loss": 1.5689, "step": 1930 }, { "epoch": 0.29706549748086614, "grad_norm": 3.1493988037109375, "learning_rate": 1.4073275862068967e-05, "loss": 1.1999, "step": 1931 }, { "epoch": 0.2972193377177801, "grad_norm": 3.7142937183380127, "learning_rate": 1.4070197044334976e-05, "loss": 1.6342, "step": 1932 }, { "epoch": 0.29737317795469403, "grad_norm": 4.084548473358154, "learning_rate": 1.4067118226600987e-05, "loss": 1.2525, "step": 1933 }, { "epoch": 0.29752701819160804, "grad_norm": 3.5295169353485107, "learning_rate": 1.4064039408866996e-05, "loss": 1.279, "step": 1934 }, { "epoch": 0.297680858428522, "grad_norm": 4.289553165435791, "learning_rate": 1.4060960591133007e-05, "loss": 1.0566, "step": 1935 }, { "epoch": 0.29783469866543594, "grad_norm": 3.0541365146636963, "learning_rate": 1.4057881773399016e-05, "loss": 1.2069, "step": 1936 }, { "epoch": 0.2979885389023499, "grad_norm": 3.170928955078125, "learning_rate": 1.4054802955665026e-05, "loss": 1.3592, "step": 1937 }, { "epoch": 0.2981423791392639, "grad_norm": 3.2295889854431152, "learning_rate": 1.4051724137931035e-05, "loss": 1.284, "step": 1938 }, { "epoch": 0.29829621937617784, "grad_norm": 3.5200674533843994, "learning_rate": 1.4048645320197046e-05, "loss": 1.4795, "step": 1939 }, { "epoch": 0.2984500596130918, "grad_norm": 3.5479941368103027, "learning_rate": 1.4045566502463055e-05, "loss": 1.4722, "step": 1940 }, { "epoch": 0.2986038998500058, "grad_norm": 3.1673338413238525, "learning_rate": 1.4042487684729065e-05, "loss": 1.4787, "step": 1941 }, { "epoch": 0.29875774008691974, "grad_norm": 3.788586378097534, "learning_rate": 1.4039408866995074e-05, "loss": 1.3293, "step": 1942 }, { "epoch": 0.2989115803238337, "grad_norm": 3.927959680557251, "learning_rate": 1.4036330049261085e-05, "loss": 1.5891, "step": 1943 }, { "epoch": 0.29906542056074764, "grad_norm": 3.4844586849212646, "learning_rate": 1.4033251231527094e-05, "loss": 1.4024, "step": 1944 }, { "epoch": 0.29921926079766165, "grad_norm": 3.212761878967285, "learning_rate": 1.4030172413793105e-05, "loss": 1.4724, "step": 1945 }, { "epoch": 0.2993731010345756, "grad_norm": 3.891122341156006, "learning_rate": 1.4027093596059114e-05, "loss": 1.5115, "step": 1946 }, { "epoch": 0.29952694127148954, "grad_norm": 3.299804210662842, "learning_rate": 1.4024014778325124e-05, "loss": 1.3166, "step": 1947 }, { "epoch": 0.29968078150840355, "grad_norm": 3.4655745029449463, "learning_rate": 1.4020935960591133e-05, "loss": 1.0636, "step": 1948 }, { "epoch": 0.2998346217453175, "grad_norm": 3.3607077598571777, "learning_rate": 1.4017857142857144e-05, "loss": 1.0961, "step": 1949 }, { "epoch": 0.29998846198223145, "grad_norm": 3.9710888862609863, "learning_rate": 1.4014778325123153e-05, "loss": 1.392, "step": 1950 }, { "epoch": 0.3001423022191454, "grad_norm": 3.3269405364990234, "learning_rate": 1.4011699507389163e-05, "loss": 1.4001, "step": 1951 }, { "epoch": 0.3002961424560594, "grad_norm": 3.3830599784851074, "learning_rate": 1.4008620689655174e-05, "loss": 1.4048, "step": 1952 }, { "epoch": 0.30044998269297335, "grad_norm": 3.1994340419769287, "learning_rate": 1.4005541871921185e-05, "loss": 1.3345, "step": 1953 }, { "epoch": 0.3006038229298873, "grad_norm": 4.076005458831787, "learning_rate": 1.4002463054187194e-05, "loss": 1.333, "step": 1954 }, { "epoch": 0.3007576631668013, "grad_norm": 3.490450859069824, "learning_rate": 1.3999384236453204e-05, "loss": 1.5219, "step": 1955 }, { "epoch": 0.30091150340371525, "grad_norm": 3.617924213409424, "learning_rate": 1.3996305418719213e-05, "loss": 1.2026, "step": 1956 }, { "epoch": 0.3010653436406292, "grad_norm": 4.116833209991455, "learning_rate": 1.3993226600985224e-05, "loss": 1.6422, "step": 1957 }, { "epoch": 0.30121918387754315, "grad_norm": 3.7926793098449707, "learning_rate": 1.3990147783251233e-05, "loss": 1.5064, "step": 1958 }, { "epoch": 0.30137302411445716, "grad_norm": 3.2792012691497803, "learning_rate": 1.3987068965517243e-05, "loss": 1.4362, "step": 1959 }, { "epoch": 0.3015268643513711, "grad_norm": 3.9530391693115234, "learning_rate": 1.3983990147783252e-05, "loss": 1.4529, "step": 1960 }, { "epoch": 0.30168070458828505, "grad_norm": 3.8566184043884277, "learning_rate": 1.3980911330049263e-05, "loss": 1.2934, "step": 1961 }, { "epoch": 0.30183454482519906, "grad_norm": 3.5869698524475098, "learning_rate": 1.3977832512315272e-05, "loss": 1.3035, "step": 1962 }, { "epoch": 0.301988385062113, "grad_norm": 4.0414605140686035, "learning_rate": 1.3974753694581283e-05, "loss": 1.576, "step": 1963 }, { "epoch": 0.30214222529902696, "grad_norm": 3.5767219066619873, "learning_rate": 1.3971674876847292e-05, "loss": 1.3164, "step": 1964 }, { "epoch": 0.3022960655359409, "grad_norm": 3.1901323795318604, "learning_rate": 1.3968596059113302e-05, "loss": 1.5428, "step": 1965 }, { "epoch": 0.3024499057728549, "grad_norm": 4.77776575088501, "learning_rate": 1.3965517241379311e-05, "loss": 1.1993, "step": 1966 }, { "epoch": 0.30260374600976886, "grad_norm": 3.3968188762664795, "learning_rate": 1.3962438423645322e-05, "loss": 0.9893, "step": 1967 }, { "epoch": 0.3027575862466828, "grad_norm": 3.8715121746063232, "learning_rate": 1.395935960591133e-05, "loss": 1.3757, "step": 1968 }, { "epoch": 0.30291142648359676, "grad_norm": 3.762251377105713, "learning_rate": 1.3956280788177341e-05, "loss": 1.3567, "step": 1969 }, { "epoch": 0.30306526672051076, "grad_norm": 3.3599753379821777, "learning_rate": 1.395320197044335e-05, "loss": 1.2989, "step": 1970 }, { "epoch": 0.3032191069574247, "grad_norm": 4.000485897064209, "learning_rate": 1.3950123152709361e-05, "loss": 1.4039, "step": 1971 }, { "epoch": 0.30337294719433866, "grad_norm": 4.303691864013672, "learning_rate": 1.394704433497537e-05, "loss": 1.4623, "step": 1972 }, { "epoch": 0.30352678743125266, "grad_norm": 3.8349101543426514, "learning_rate": 1.394396551724138e-05, "loss": 1.2931, "step": 1973 }, { "epoch": 0.3036806276681666, "grad_norm": 3.296971559524536, "learning_rate": 1.394088669950739e-05, "loss": 1.4415, "step": 1974 }, { "epoch": 0.30383446790508056, "grad_norm": 3.4334590435028076, "learning_rate": 1.39378078817734e-05, "loss": 1.4874, "step": 1975 }, { "epoch": 0.3039883081419945, "grad_norm": 3.0606791973114014, "learning_rate": 1.393472906403941e-05, "loss": 1.3855, "step": 1976 }, { "epoch": 0.3041421483789085, "grad_norm": 4.138495445251465, "learning_rate": 1.393165024630542e-05, "loss": 1.4726, "step": 1977 }, { "epoch": 0.30429598861582247, "grad_norm": 3.406609058380127, "learning_rate": 1.3928571428571429e-05, "loss": 1.6144, "step": 1978 }, { "epoch": 0.3044498288527364, "grad_norm": 4.0309553146362305, "learning_rate": 1.392549261083744e-05, "loss": 1.1595, "step": 1979 }, { "epoch": 0.3046036690896504, "grad_norm": 3.7715392112731934, "learning_rate": 1.3922413793103448e-05, "loss": 1.3398, "step": 1980 }, { "epoch": 0.30475750932656437, "grad_norm": 4.773178577423096, "learning_rate": 1.3919334975369459e-05, "loss": 1.4072, "step": 1981 }, { "epoch": 0.3049113495634783, "grad_norm": 4.030678749084473, "learning_rate": 1.3916256157635468e-05, "loss": 1.5675, "step": 1982 }, { "epoch": 0.30506518980039227, "grad_norm": 3.3267250061035156, "learning_rate": 1.3913177339901479e-05, "loss": 1.415, "step": 1983 }, { "epoch": 0.30521903003730627, "grad_norm": 3.518174171447754, "learning_rate": 1.3910098522167488e-05, "loss": 1.5507, "step": 1984 }, { "epoch": 0.3053728702742202, "grad_norm": 3.560473680496216, "learning_rate": 1.3907019704433498e-05, "loss": 1.5094, "step": 1985 }, { "epoch": 0.30552671051113417, "grad_norm": 3.122067451477051, "learning_rate": 1.3903940886699509e-05, "loss": 1.257, "step": 1986 }, { "epoch": 0.3056805507480482, "grad_norm": 3.0288610458374023, "learning_rate": 1.390086206896552e-05, "loss": 1.5135, "step": 1987 }, { "epoch": 0.3058343909849621, "grad_norm": 4.577652931213379, "learning_rate": 1.3897783251231528e-05, "loss": 1.5041, "step": 1988 }, { "epoch": 0.3059882312218761, "grad_norm": 3.8759145736694336, "learning_rate": 1.3894704433497539e-05, "loss": 1.3677, "step": 1989 }, { "epoch": 0.30614207145879, "grad_norm": 3.692425012588501, "learning_rate": 1.3891625615763548e-05, "loss": 1.6753, "step": 1990 }, { "epoch": 0.306295911695704, "grad_norm": 4.035139560699463, "learning_rate": 1.3888546798029559e-05, "loss": 1.5437, "step": 1991 }, { "epoch": 0.306449751932618, "grad_norm": 4.174038410186768, "learning_rate": 1.3885467980295568e-05, "loss": 1.3318, "step": 1992 }, { "epoch": 0.3066035921695319, "grad_norm": 3.5821635723114014, "learning_rate": 1.3882389162561578e-05, "loss": 1.3531, "step": 1993 }, { "epoch": 0.30675743240644593, "grad_norm": 4.116874694824219, "learning_rate": 1.3879310344827587e-05, "loss": 1.4012, "step": 1994 }, { "epoch": 0.3069112726433599, "grad_norm": 4.087575435638428, "learning_rate": 1.3876231527093598e-05, "loss": 1.161, "step": 1995 }, { "epoch": 0.3070651128802738, "grad_norm": 3.4926650524139404, "learning_rate": 1.3873152709359607e-05, "loss": 1.3867, "step": 1996 }, { "epoch": 0.3072189531171878, "grad_norm": 3.683138132095337, "learning_rate": 1.3870073891625618e-05, "loss": 1.3975, "step": 1997 }, { "epoch": 0.3073727933541018, "grad_norm": 3.092221975326538, "learning_rate": 1.3866995073891626e-05, "loss": 1.2434, "step": 1998 }, { "epoch": 0.30752663359101573, "grad_norm": 2.7345800399780273, "learning_rate": 1.3863916256157637e-05, "loss": 1.3333, "step": 1999 }, { "epoch": 0.3076804738279297, "grad_norm": 3.205681562423706, "learning_rate": 1.3860837438423646e-05, "loss": 1.4936, "step": 2000 }, { "epoch": 0.3078343140648437, "grad_norm": 3.247765064239502, "learning_rate": 1.3857758620689657e-05, "loss": 1.2632, "step": 2001 }, { "epoch": 0.30798815430175763, "grad_norm": 3.430363893508911, "learning_rate": 1.3854679802955666e-05, "loss": 1.2318, "step": 2002 }, { "epoch": 0.3081419945386716, "grad_norm": 3.700575113296509, "learning_rate": 1.3851600985221676e-05, "loss": 1.2925, "step": 2003 }, { "epoch": 0.30829583477558553, "grad_norm": 3.684056043624878, "learning_rate": 1.3848522167487685e-05, "loss": 1.3502, "step": 2004 }, { "epoch": 0.30844967501249954, "grad_norm": 3.239361047744751, "learning_rate": 1.3845443349753696e-05, "loss": 1.1858, "step": 2005 }, { "epoch": 0.3086035152494135, "grad_norm": 4.521894454956055, "learning_rate": 1.3842364532019705e-05, "loss": 1.4543, "step": 2006 }, { "epoch": 0.30875735548632743, "grad_norm": 3.401822805404663, "learning_rate": 1.3839285714285715e-05, "loss": 1.5043, "step": 2007 }, { "epoch": 0.30891119572324144, "grad_norm": 3.414689302444458, "learning_rate": 1.3836206896551724e-05, "loss": 1.6825, "step": 2008 }, { "epoch": 0.3090650359601554, "grad_norm": 3.083373546600342, "learning_rate": 1.3833128078817735e-05, "loss": 1.5312, "step": 2009 }, { "epoch": 0.30921887619706934, "grad_norm": 3.3984076976776123, "learning_rate": 1.3830049261083744e-05, "loss": 1.3403, "step": 2010 }, { "epoch": 0.3093727164339833, "grad_norm": 3.789125680923462, "learning_rate": 1.3826970443349755e-05, "loss": 1.5758, "step": 2011 }, { "epoch": 0.3095265566708973, "grad_norm": 3.0866382122039795, "learning_rate": 1.3823891625615764e-05, "loss": 1.2837, "step": 2012 }, { "epoch": 0.30968039690781124, "grad_norm": 3.9595110416412354, "learning_rate": 1.3820812807881774e-05, "loss": 1.4768, "step": 2013 }, { "epoch": 0.3098342371447252, "grad_norm": 3.073685646057129, "learning_rate": 1.3817733990147783e-05, "loss": 1.3001, "step": 2014 }, { "epoch": 0.3099880773816392, "grad_norm": 3.2842726707458496, "learning_rate": 1.3814655172413794e-05, "loss": 1.3396, "step": 2015 }, { "epoch": 0.31014191761855314, "grad_norm": 3.5612952709198, "learning_rate": 1.3811576354679803e-05, "loss": 1.4545, "step": 2016 }, { "epoch": 0.3102957578554671, "grad_norm": 5.046972751617432, "learning_rate": 1.3808497536945813e-05, "loss": 1.4152, "step": 2017 }, { "epoch": 0.31044959809238104, "grad_norm": 4.534025192260742, "learning_rate": 1.3805418719211822e-05, "loss": 1.3728, "step": 2018 }, { "epoch": 0.31060343832929505, "grad_norm": 3.176973581314087, "learning_rate": 1.3802339901477833e-05, "loss": 1.2771, "step": 2019 }, { "epoch": 0.310757278566209, "grad_norm": 3.197477102279663, "learning_rate": 1.3799261083743844e-05, "loss": 1.3376, "step": 2020 }, { "epoch": 0.31091111880312294, "grad_norm": 3.5426173210144043, "learning_rate": 1.3796182266009854e-05, "loss": 1.5931, "step": 2021 }, { "epoch": 0.31106495904003695, "grad_norm": 4.058560848236084, "learning_rate": 1.3793103448275863e-05, "loss": 1.4775, "step": 2022 }, { "epoch": 0.3112187992769509, "grad_norm": 3.348811149597168, "learning_rate": 1.3790024630541874e-05, "loss": 1.591, "step": 2023 }, { "epoch": 0.31137263951386485, "grad_norm": 3.538045644760132, "learning_rate": 1.3786945812807883e-05, "loss": 1.219, "step": 2024 }, { "epoch": 0.3115264797507788, "grad_norm": 3.897977352142334, "learning_rate": 1.3783866995073894e-05, "loss": 1.2675, "step": 2025 }, { "epoch": 0.3116803199876928, "grad_norm": 4.205306053161621, "learning_rate": 1.3780788177339903e-05, "loss": 1.3399, "step": 2026 }, { "epoch": 0.31183416022460675, "grad_norm": 3.3594443798065186, "learning_rate": 1.3777709359605913e-05, "loss": 1.3206, "step": 2027 }, { "epoch": 0.3119880004615207, "grad_norm": 3.397979736328125, "learning_rate": 1.3774630541871922e-05, "loss": 1.3266, "step": 2028 }, { "epoch": 0.3121418406984347, "grad_norm": 3.7209384441375732, "learning_rate": 1.3771551724137933e-05, "loss": 1.5336, "step": 2029 }, { "epoch": 0.31229568093534865, "grad_norm": 3.6617605686187744, "learning_rate": 1.3768472906403942e-05, "loss": 1.3934, "step": 2030 }, { "epoch": 0.3124495211722626, "grad_norm": 3.68688702583313, "learning_rate": 1.3765394088669952e-05, "loss": 1.581, "step": 2031 }, { "epoch": 0.31260336140917655, "grad_norm": 3.6490654945373535, "learning_rate": 1.3762315270935961e-05, "loss": 1.3374, "step": 2032 }, { "epoch": 0.31275720164609055, "grad_norm": 4.069881439208984, "learning_rate": 1.3759236453201972e-05, "loss": 1.2249, "step": 2033 }, { "epoch": 0.3129110418830045, "grad_norm": 3.0634098052978516, "learning_rate": 1.3756157635467981e-05, "loss": 1.5204, "step": 2034 }, { "epoch": 0.31306488211991845, "grad_norm": 4.0674729347229, "learning_rate": 1.3753078817733992e-05, "loss": 1.4859, "step": 2035 }, { "epoch": 0.3132187223568324, "grad_norm": 4.684075832366943, "learning_rate": 1.375e-05, "loss": 1.5204, "step": 2036 }, { "epoch": 0.3133725625937464, "grad_norm": 3.6041526794433594, "learning_rate": 1.3746921182266011e-05, "loss": 1.2211, "step": 2037 }, { "epoch": 0.31352640283066036, "grad_norm": 3.495771646499634, "learning_rate": 1.374384236453202e-05, "loss": 1.1482, "step": 2038 }, { "epoch": 0.3136802430675743, "grad_norm": 3.667257070541382, "learning_rate": 1.374076354679803e-05, "loss": 1.4077, "step": 2039 }, { "epoch": 0.3138340833044883, "grad_norm": 3.8547613620758057, "learning_rate": 1.373768472906404e-05, "loss": 1.3679, "step": 2040 }, { "epoch": 0.31398792354140226, "grad_norm": 3.1992225646972656, "learning_rate": 1.373460591133005e-05, "loss": 1.2856, "step": 2041 }, { "epoch": 0.3141417637783162, "grad_norm": 3.285477876663208, "learning_rate": 1.373152709359606e-05, "loss": 1.3457, "step": 2042 }, { "epoch": 0.31429560401523016, "grad_norm": 3.5523195266723633, "learning_rate": 1.372844827586207e-05, "loss": 1.5558, "step": 2043 }, { "epoch": 0.31444944425214416, "grad_norm": 3.2329182624816895, "learning_rate": 1.3725369458128079e-05, "loss": 1.118, "step": 2044 }, { "epoch": 0.3146032844890581, "grad_norm": 4.319514274597168, "learning_rate": 1.372229064039409e-05, "loss": 1.3016, "step": 2045 }, { "epoch": 0.31475712472597206, "grad_norm": 3.12080979347229, "learning_rate": 1.3719211822660098e-05, "loss": 1.2396, "step": 2046 }, { "epoch": 0.31491096496288606, "grad_norm": 3.1711723804473877, "learning_rate": 1.3716133004926109e-05, "loss": 1.5367, "step": 2047 }, { "epoch": 0.3150648051998, "grad_norm": 3.4139199256896973, "learning_rate": 1.3713054187192118e-05, "loss": 1.4751, "step": 2048 }, { "epoch": 0.31521864543671396, "grad_norm": 4.1194891929626465, "learning_rate": 1.3709975369458129e-05, "loss": 1.3159, "step": 2049 }, { "epoch": 0.3153724856736279, "grad_norm": 3.739341974258423, "learning_rate": 1.3706896551724138e-05, "loss": 1.6471, "step": 2050 }, { "epoch": 0.3155263259105419, "grad_norm": 3.5306789875030518, "learning_rate": 1.3703817733990148e-05, "loss": 1.2809, "step": 2051 }, { "epoch": 0.31568016614745587, "grad_norm": 4.160990238189697, "learning_rate": 1.3700738916256157e-05, "loss": 1.6012, "step": 2052 }, { "epoch": 0.3158340063843698, "grad_norm": 3.2220187187194824, "learning_rate": 1.369766009852217e-05, "loss": 1.3054, "step": 2053 }, { "epoch": 0.3159878466212838, "grad_norm": 4.019018173217773, "learning_rate": 1.369458128078818e-05, "loss": 1.4764, "step": 2054 }, { "epoch": 0.31614168685819777, "grad_norm": 3.980111837387085, "learning_rate": 1.369150246305419e-05, "loss": 1.1618, "step": 2055 }, { "epoch": 0.3162955270951117, "grad_norm": 3.696770429611206, "learning_rate": 1.36884236453202e-05, "loss": 1.4458, "step": 2056 }, { "epoch": 0.31644936733202567, "grad_norm": 4.078425407409668, "learning_rate": 1.3685344827586209e-05, "loss": 1.3367, "step": 2057 }, { "epoch": 0.31660320756893967, "grad_norm": 4.3669867515563965, "learning_rate": 1.368226600985222e-05, "loss": 1.5136, "step": 2058 }, { "epoch": 0.3167570478058536, "grad_norm": 3.596069574356079, "learning_rate": 1.3679187192118228e-05, "loss": 1.2664, "step": 2059 }, { "epoch": 0.31691088804276757, "grad_norm": 4.336376190185547, "learning_rate": 1.3676108374384239e-05, "loss": 1.2248, "step": 2060 }, { "epoch": 0.3170647282796816, "grad_norm": 3.4553723335266113, "learning_rate": 1.3673029556650248e-05, "loss": 1.4661, "step": 2061 }, { "epoch": 0.3172185685165955, "grad_norm": 4.317612648010254, "learning_rate": 1.3669950738916259e-05, "loss": 1.4472, "step": 2062 }, { "epoch": 0.31737240875350947, "grad_norm": 3.2748513221740723, "learning_rate": 1.3666871921182268e-05, "loss": 1.4351, "step": 2063 }, { "epoch": 0.3175262489904234, "grad_norm": 3.4496700763702393, "learning_rate": 1.3663793103448277e-05, "loss": 1.2592, "step": 2064 }, { "epoch": 0.3176800892273374, "grad_norm": 3.72326922416687, "learning_rate": 1.3660714285714287e-05, "loss": 1.2847, "step": 2065 }, { "epoch": 0.3178339294642514, "grad_norm": 3.042961835861206, "learning_rate": 1.3657635467980296e-05, "loss": 1.4753, "step": 2066 }, { "epoch": 0.3179877697011653, "grad_norm": 3.881112813949585, "learning_rate": 1.3654556650246307e-05, "loss": 1.4771, "step": 2067 }, { "epoch": 0.31814160993807933, "grad_norm": 3.2238399982452393, "learning_rate": 1.3651477832512316e-05, "loss": 1.2338, "step": 2068 }, { "epoch": 0.3182954501749933, "grad_norm": 3.421109676361084, "learning_rate": 1.3648399014778326e-05, "loss": 1.507, "step": 2069 }, { "epoch": 0.3184492904119072, "grad_norm": 3.982696056365967, "learning_rate": 1.3645320197044335e-05, "loss": 1.5968, "step": 2070 }, { "epoch": 0.3186031306488212, "grad_norm": 3.476884603500366, "learning_rate": 1.3642241379310346e-05, "loss": 1.2491, "step": 2071 }, { "epoch": 0.3187569708857352, "grad_norm": 3.2657408714294434, "learning_rate": 1.3639162561576355e-05, "loss": 1.1869, "step": 2072 }, { "epoch": 0.31891081112264913, "grad_norm": 3.5472769737243652, "learning_rate": 1.3636083743842366e-05, "loss": 1.3698, "step": 2073 }, { "epoch": 0.3190646513595631, "grad_norm": 3.8768527507781982, "learning_rate": 1.3633004926108375e-05, "loss": 1.1635, "step": 2074 }, { "epoch": 0.3192184915964771, "grad_norm": 3.506801128387451, "learning_rate": 1.3629926108374385e-05, "loss": 1.1565, "step": 2075 }, { "epoch": 0.31937233183339103, "grad_norm": 3.652717351913452, "learning_rate": 1.3626847290640394e-05, "loss": 1.3881, "step": 2076 }, { "epoch": 0.319526172070305, "grad_norm": 4.066463470458984, "learning_rate": 1.3623768472906405e-05, "loss": 1.4231, "step": 2077 }, { "epoch": 0.31968001230721893, "grad_norm": 3.2590482234954834, "learning_rate": 1.3620689655172414e-05, "loss": 1.4283, "step": 2078 }, { "epoch": 0.31983385254413293, "grad_norm": 3.0227270126342773, "learning_rate": 1.3617610837438424e-05, "loss": 1.1694, "step": 2079 }, { "epoch": 0.3199876927810469, "grad_norm": 3.716784715652466, "learning_rate": 1.3614532019704433e-05, "loss": 1.205, "step": 2080 }, { "epoch": 0.32014153301796083, "grad_norm": 3.7160370349884033, "learning_rate": 1.3611453201970444e-05, "loss": 1.6574, "step": 2081 }, { "epoch": 0.32029537325487484, "grad_norm": 4.721732139587402, "learning_rate": 1.3608374384236453e-05, "loss": 1.3236, "step": 2082 }, { "epoch": 0.3204492134917888, "grad_norm": 3.675234794616699, "learning_rate": 1.3605295566502464e-05, "loss": 1.3538, "step": 2083 }, { "epoch": 0.32060305372870274, "grad_norm": 3.500849723815918, "learning_rate": 1.3602216748768472e-05, "loss": 1.2539, "step": 2084 }, { "epoch": 0.3207568939656167, "grad_norm": 3.5714845657348633, "learning_rate": 1.3599137931034483e-05, "loss": 1.5895, "step": 2085 }, { "epoch": 0.3209107342025307, "grad_norm": 4.377259254455566, "learning_rate": 1.3596059113300492e-05, "loss": 1.33, "step": 2086 }, { "epoch": 0.32106457443944464, "grad_norm": 4.291491985321045, "learning_rate": 1.3592980295566504e-05, "loss": 1.0856, "step": 2087 }, { "epoch": 0.3212184146763586, "grad_norm": 3.15621280670166, "learning_rate": 1.3589901477832515e-05, "loss": 1.0998, "step": 2088 }, { "epoch": 0.3213722549132726, "grad_norm": 3.0843634605407715, "learning_rate": 1.3586822660098524e-05, "loss": 1.3702, "step": 2089 }, { "epoch": 0.32152609515018654, "grad_norm": 4.097943305969238, "learning_rate": 1.3583743842364535e-05, "loss": 1.2247, "step": 2090 }, { "epoch": 0.3216799353871005, "grad_norm": 3.9177613258361816, "learning_rate": 1.3580665024630544e-05, "loss": 1.4593, "step": 2091 }, { "epoch": 0.32183377562401444, "grad_norm": 3.841346025466919, "learning_rate": 1.3577586206896554e-05, "loss": 1.4935, "step": 2092 }, { "epoch": 0.32198761586092844, "grad_norm": 3.503418207168579, "learning_rate": 1.3574507389162563e-05, "loss": 1.2696, "step": 2093 }, { "epoch": 0.3221414560978424, "grad_norm": 4.569052219390869, "learning_rate": 1.3571428571428574e-05, "loss": 1.9122, "step": 2094 }, { "epoch": 0.32229529633475634, "grad_norm": 3.6516082286834717, "learning_rate": 1.3568349753694583e-05, "loss": 1.3055, "step": 2095 }, { "epoch": 0.32244913657167035, "grad_norm": 3.931833505630493, "learning_rate": 1.3565270935960593e-05, "loss": 1.6036, "step": 2096 }, { "epoch": 0.3226029768085843, "grad_norm": 3.2049479484558105, "learning_rate": 1.3562192118226602e-05, "loss": 1.3832, "step": 2097 }, { "epoch": 0.32275681704549825, "grad_norm": 3.364103078842163, "learning_rate": 1.3559113300492613e-05, "loss": 1.4086, "step": 2098 }, { "epoch": 0.3229106572824122, "grad_norm": 3.9575612545013428, "learning_rate": 1.3556034482758622e-05, "loss": 1.3082, "step": 2099 }, { "epoch": 0.3230644975193262, "grad_norm": 3.457218885421753, "learning_rate": 1.3552955665024633e-05, "loss": 1.5654, "step": 2100 }, { "epoch": 0.32321833775624015, "grad_norm": 3.6924192905426025, "learning_rate": 1.3549876847290642e-05, "loss": 1.2547, "step": 2101 }, { "epoch": 0.3233721779931541, "grad_norm": 3.53767466545105, "learning_rate": 1.3546798029556652e-05, "loss": 1.7031, "step": 2102 }, { "epoch": 0.3235260182300681, "grad_norm": 3.445659875869751, "learning_rate": 1.3543719211822661e-05, "loss": 1.7039, "step": 2103 }, { "epoch": 0.32367985846698205, "grad_norm": 3.097097635269165, "learning_rate": 1.3540640394088672e-05, "loss": 1.1908, "step": 2104 }, { "epoch": 0.323833698703896, "grad_norm": 2.9750051498413086, "learning_rate": 1.353756157635468e-05, "loss": 1.3817, "step": 2105 }, { "epoch": 0.32398753894080995, "grad_norm": 3.7459731101989746, "learning_rate": 1.3534482758620691e-05, "loss": 1.4636, "step": 2106 }, { "epoch": 0.32414137917772395, "grad_norm": 3.4260432720184326, "learning_rate": 1.35314039408867e-05, "loss": 1.5003, "step": 2107 }, { "epoch": 0.3242952194146379, "grad_norm": 3.631605625152588, "learning_rate": 1.352832512315271e-05, "loss": 1.2794, "step": 2108 }, { "epoch": 0.32444905965155185, "grad_norm": 3.5266475677490234, "learning_rate": 1.352524630541872e-05, "loss": 1.5407, "step": 2109 }, { "epoch": 0.3246028998884658, "grad_norm": 3.728929281234741, "learning_rate": 1.3522167487684729e-05, "loss": 1.3421, "step": 2110 }, { "epoch": 0.3247567401253798, "grad_norm": 4.128269672393799, "learning_rate": 1.351908866995074e-05, "loss": 1.3584, "step": 2111 }, { "epoch": 0.32491058036229375, "grad_norm": 4.064525604248047, "learning_rate": 1.3516009852216749e-05, "loss": 1.2567, "step": 2112 }, { "epoch": 0.3250644205992077, "grad_norm": 3.7694077491760254, "learning_rate": 1.351293103448276e-05, "loss": 1.3566, "step": 2113 }, { "epoch": 0.3252182608361217, "grad_norm": 3.8823390007019043, "learning_rate": 1.3509852216748768e-05, "loss": 1.2743, "step": 2114 }, { "epoch": 0.32537210107303566, "grad_norm": 3.25787091255188, "learning_rate": 1.3506773399014779e-05, "loss": 1.3815, "step": 2115 }, { "epoch": 0.3255259413099496, "grad_norm": 3.52129864692688, "learning_rate": 1.3503694581280788e-05, "loss": 1.3661, "step": 2116 }, { "epoch": 0.32567978154686356, "grad_norm": 3.2653636932373047, "learning_rate": 1.3500615763546798e-05, "loss": 1.4881, "step": 2117 }, { "epoch": 0.32583362178377756, "grad_norm": 3.927966833114624, "learning_rate": 1.3497536945812807e-05, "loss": 1.1378, "step": 2118 }, { "epoch": 0.3259874620206915, "grad_norm": 3.8514456748962402, "learning_rate": 1.3494458128078818e-05, "loss": 1.2233, "step": 2119 }, { "epoch": 0.32614130225760546, "grad_norm": 3.4091529846191406, "learning_rate": 1.3491379310344827e-05, "loss": 1.4853, "step": 2120 }, { "epoch": 0.32629514249451946, "grad_norm": 4.376601696014404, "learning_rate": 1.348830049261084e-05, "loss": 1.6377, "step": 2121 }, { "epoch": 0.3264489827314334, "grad_norm": 3.6697123050689697, "learning_rate": 1.348522167487685e-05, "loss": 1.2125, "step": 2122 }, { "epoch": 0.32660282296834736, "grad_norm": 3.4058730602264404, "learning_rate": 1.3482142857142859e-05, "loss": 1.3773, "step": 2123 }, { "epoch": 0.3267566632052613, "grad_norm": 3.125453233718872, "learning_rate": 1.347906403940887e-05, "loss": 1.2029, "step": 2124 }, { "epoch": 0.3269105034421753, "grad_norm": 3.967190742492676, "learning_rate": 1.3475985221674878e-05, "loss": 1.3425, "step": 2125 }, { "epoch": 0.32706434367908926, "grad_norm": 4.018889427185059, "learning_rate": 1.3472906403940889e-05, "loss": 1.2583, "step": 2126 }, { "epoch": 0.3272181839160032, "grad_norm": 3.9033799171447754, "learning_rate": 1.3469827586206898e-05, "loss": 1.3103, "step": 2127 }, { "epoch": 0.3273720241529172, "grad_norm": 3.630159616470337, "learning_rate": 1.3466748768472909e-05, "loss": 1.4848, "step": 2128 }, { "epoch": 0.32752586438983117, "grad_norm": 4.385204315185547, "learning_rate": 1.3463669950738918e-05, "loss": 1.542, "step": 2129 }, { "epoch": 0.3276797046267451, "grad_norm": 3.378833532333374, "learning_rate": 1.3460591133004928e-05, "loss": 1.0195, "step": 2130 }, { "epoch": 0.32783354486365907, "grad_norm": 4.093601703643799, "learning_rate": 1.3457512315270937e-05, "loss": 1.4514, "step": 2131 }, { "epoch": 0.32798738510057307, "grad_norm": 4.026680946350098, "learning_rate": 1.3454433497536948e-05, "loss": 1.5178, "step": 2132 }, { "epoch": 0.328141225337487, "grad_norm": 3.4707367420196533, "learning_rate": 1.3451354679802957e-05, "loss": 1.5969, "step": 2133 }, { "epoch": 0.32829506557440097, "grad_norm": 3.5490455627441406, "learning_rate": 1.3448275862068967e-05, "loss": 1.2368, "step": 2134 }, { "epoch": 0.328448905811315, "grad_norm": 2.94102144241333, "learning_rate": 1.3445197044334976e-05, "loss": 1.2574, "step": 2135 }, { "epoch": 0.3286027460482289, "grad_norm": 3.605438709259033, "learning_rate": 1.3442118226600987e-05, "loss": 1.5974, "step": 2136 }, { "epoch": 0.32875658628514287, "grad_norm": 3.592306613922119, "learning_rate": 1.3439039408866996e-05, "loss": 1.5704, "step": 2137 }, { "epoch": 0.3289104265220568, "grad_norm": 3.7483954429626465, "learning_rate": 1.3435960591133007e-05, "loss": 1.3827, "step": 2138 }, { "epoch": 0.3290642667589708, "grad_norm": 3.417280673980713, "learning_rate": 1.3432881773399016e-05, "loss": 1.2061, "step": 2139 }, { "epoch": 0.3292181069958848, "grad_norm": 4.37647008895874, "learning_rate": 1.3429802955665026e-05, "loss": 1.3597, "step": 2140 }, { "epoch": 0.3293719472327987, "grad_norm": 3.469292402267456, "learning_rate": 1.3426724137931035e-05, "loss": 1.5239, "step": 2141 }, { "epoch": 0.3295257874697127, "grad_norm": 3.9844915866851807, "learning_rate": 1.3423645320197046e-05, "loss": 1.4827, "step": 2142 }, { "epoch": 0.3296796277066267, "grad_norm": 3.765789031982422, "learning_rate": 1.3420566502463055e-05, "loss": 1.2536, "step": 2143 }, { "epoch": 0.3298334679435406, "grad_norm": 3.843702793121338, "learning_rate": 1.3417487684729065e-05, "loss": 1.4748, "step": 2144 }, { "epoch": 0.3299873081804546, "grad_norm": 3.570352554321289, "learning_rate": 1.3414408866995074e-05, "loss": 1.3586, "step": 2145 }, { "epoch": 0.3301411484173686, "grad_norm": 3.8038370609283447, "learning_rate": 1.3411330049261085e-05, "loss": 1.2805, "step": 2146 }, { "epoch": 0.33029498865428253, "grad_norm": 4.303781986236572, "learning_rate": 1.3408251231527094e-05, "loss": 1.6511, "step": 2147 }, { "epoch": 0.3304488288911965, "grad_norm": 3.5268237590789795, "learning_rate": 1.3405172413793105e-05, "loss": 1.3096, "step": 2148 }, { "epoch": 0.3306026691281105, "grad_norm": 3.329164505004883, "learning_rate": 1.3402093596059114e-05, "loss": 1.4267, "step": 2149 }, { "epoch": 0.33075650936502443, "grad_norm": 4.191938400268555, "learning_rate": 1.3399014778325124e-05, "loss": 1.4595, "step": 2150 }, { "epoch": 0.3309103496019384, "grad_norm": 3.6703896522521973, "learning_rate": 1.3395935960591133e-05, "loss": 1.6606, "step": 2151 }, { "epoch": 0.33106418983885233, "grad_norm": 3.196444034576416, "learning_rate": 1.3392857142857142e-05, "loss": 1.708, "step": 2152 }, { "epoch": 0.33121803007576633, "grad_norm": 3.7858707904815674, "learning_rate": 1.3389778325123153e-05, "loss": 1.3969, "step": 2153 }, { "epoch": 0.3313718703126803, "grad_norm": 3.949782133102417, "learning_rate": 1.3386699507389162e-05, "loss": 1.1353, "step": 2154 }, { "epoch": 0.33152571054959423, "grad_norm": 3.663423538208008, "learning_rate": 1.3383620689655174e-05, "loss": 1.1255, "step": 2155 }, { "epoch": 0.33167955078650824, "grad_norm": 3.4738569259643555, "learning_rate": 1.3380541871921185e-05, "loss": 1.1749, "step": 2156 }, { "epoch": 0.3318333910234222, "grad_norm": 3.5198872089385986, "learning_rate": 1.3377463054187194e-05, "loss": 1.103, "step": 2157 }, { "epoch": 0.33198723126033614, "grad_norm": 3.762284517288208, "learning_rate": 1.3374384236453204e-05, "loss": 1.5432, "step": 2158 }, { "epoch": 0.3321410714972501, "grad_norm": 3.9189181327819824, "learning_rate": 1.3371305418719213e-05, "loss": 1.7045, "step": 2159 }, { "epoch": 0.3322949117341641, "grad_norm": 4.084677219390869, "learning_rate": 1.3368226600985224e-05, "loss": 1.4954, "step": 2160 }, { "epoch": 0.33244875197107804, "grad_norm": 4.237231731414795, "learning_rate": 1.3365147783251233e-05, "loss": 1.309, "step": 2161 }, { "epoch": 0.332602592207992, "grad_norm": 3.210235357284546, "learning_rate": 1.3362068965517244e-05, "loss": 1.4528, "step": 2162 }, { "epoch": 0.332756432444906, "grad_norm": 4.2209272384643555, "learning_rate": 1.3358990147783252e-05, "loss": 1.2914, "step": 2163 }, { "epoch": 0.33291027268181994, "grad_norm": 3.9197134971618652, "learning_rate": 1.3355911330049263e-05, "loss": 1.4432, "step": 2164 }, { "epoch": 0.3330641129187339, "grad_norm": 3.258680582046509, "learning_rate": 1.3352832512315272e-05, "loss": 1.4015, "step": 2165 }, { "epoch": 0.33321795315564784, "grad_norm": 3.646362066268921, "learning_rate": 1.3349753694581283e-05, "loss": 1.4194, "step": 2166 }, { "epoch": 0.33337179339256184, "grad_norm": 3.661851406097412, "learning_rate": 1.3346674876847292e-05, "loss": 1.2928, "step": 2167 }, { "epoch": 0.3335256336294758, "grad_norm": 3.50197172164917, "learning_rate": 1.3343596059113302e-05, "loss": 1.4777, "step": 2168 }, { "epoch": 0.33367947386638974, "grad_norm": 3.6202409267425537, "learning_rate": 1.3340517241379311e-05, "loss": 1.3373, "step": 2169 }, { "epoch": 0.33383331410330375, "grad_norm": 3.606990337371826, "learning_rate": 1.3337438423645322e-05, "loss": 1.3965, "step": 2170 }, { "epoch": 0.3339871543402177, "grad_norm": 3.2801804542541504, "learning_rate": 1.3334359605911331e-05, "loss": 1.3349, "step": 2171 }, { "epoch": 0.33414099457713164, "grad_norm": 3.3625571727752686, "learning_rate": 1.3331280788177342e-05, "loss": 1.3054, "step": 2172 }, { "epoch": 0.3342948348140456, "grad_norm": 3.4770030975341797, "learning_rate": 1.332820197044335e-05, "loss": 1.2697, "step": 2173 }, { "epoch": 0.3344486750509596, "grad_norm": 3.9948153495788574, "learning_rate": 1.3325123152709361e-05, "loss": 1.6929, "step": 2174 }, { "epoch": 0.33460251528787355, "grad_norm": 3.3946986198425293, "learning_rate": 1.332204433497537e-05, "loss": 1.5942, "step": 2175 }, { "epoch": 0.3347563555247875, "grad_norm": 3.3965861797332764, "learning_rate": 1.331896551724138e-05, "loss": 1.3863, "step": 2176 }, { "epoch": 0.33491019576170145, "grad_norm": 3.1804115772247314, "learning_rate": 1.331588669950739e-05, "loss": 1.3757, "step": 2177 }, { "epoch": 0.33506403599861545, "grad_norm": 3.238536834716797, "learning_rate": 1.33128078817734e-05, "loss": 1.4484, "step": 2178 }, { "epoch": 0.3352178762355294, "grad_norm": 3.71097993850708, "learning_rate": 1.330972906403941e-05, "loss": 1.3857, "step": 2179 }, { "epoch": 0.33537171647244335, "grad_norm": 3.7976937294006348, "learning_rate": 1.330665024630542e-05, "loss": 1.2992, "step": 2180 }, { "epoch": 0.33552555670935735, "grad_norm": 3.4598641395568848, "learning_rate": 1.3303571428571429e-05, "loss": 1.5164, "step": 2181 }, { "epoch": 0.3356793969462713, "grad_norm": 3.8958890438079834, "learning_rate": 1.330049261083744e-05, "loss": 1.34, "step": 2182 }, { "epoch": 0.33583323718318525, "grad_norm": 3.504054307937622, "learning_rate": 1.3297413793103448e-05, "loss": 1.3899, "step": 2183 }, { "epoch": 0.3359870774200992, "grad_norm": 3.203315258026123, "learning_rate": 1.3294334975369459e-05, "loss": 1.5143, "step": 2184 }, { "epoch": 0.3361409176570132, "grad_norm": 4.425429344177246, "learning_rate": 1.3291256157635468e-05, "loss": 1.1642, "step": 2185 }, { "epoch": 0.33629475789392715, "grad_norm": 3.4702062606811523, "learning_rate": 1.3288177339901479e-05, "loss": 1.3016, "step": 2186 }, { "epoch": 0.3364485981308411, "grad_norm": 3.447021007537842, "learning_rate": 1.3285098522167488e-05, "loss": 1.4103, "step": 2187 }, { "epoch": 0.3366024383677551, "grad_norm": 3.2628843784332275, "learning_rate": 1.3282019704433498e-05, "loss": 1.5393, "step": 2188 }, { "epoch": 0.33675627860466906, "grad_norm": 3.5256993770599365, "learning_rate": 1.3278940886699509e-05, "loss": 1.1557, "step": 2189 }, { "epoch": 0.336910118841583, "grad_norm": 3.6057355403900146, "learning_rate": 1.327586206896552e-05, "loss": 1.3464, "step": 2190 }, { "epoch": 0.33706395907849696, "grad_norm": 3.289741277694702, "learning_rate": 1.3272783251231529e-05, "loss": 1.2035, "step": 2191 }, { "epoch": 0.33721779931541096, "grad_norm": 3.281176805496216, "learning_rate": 1.326970443349754e-05, "loss": 1.3107, "step": 2192 }, { "epoch": 0.3373716395523249, "grad_norm": 3.4647035598754883, "learning_rate": 1.3266625615763548e-05, "loss": 1.3018, "step": 2193 }, { "epoch": 0.33752547978923886, "grad_norm": 3.216810464859009, "learning_rate": 1.3263546798029559e-05, "loss": 1.5379, "step": 2194 }, { "epoch": 0.33767932002615286, "grad_norm": 3.5698373317718506, "learning_rate": 1.3260467980295568e-05, "loss": 1.5221, "step": 2195 }, { "epoch": 0.3378331602630668, "grad_norm": 4.103189945220947, "learning_rate": 1.3257389162561578e-05, "loss": 1.2998, "step": 2196 }, { "epoch": 0.33798700049998076, "grad_norm": 3.5750699043273926, "learning_rate": 1.3254310344827587e-05, "loss": 1.1874, "step": 2197 }, { "epoch": 0.3381408407368947, "grad_norm": 3.1908462047576904, "learning_rate": 1.3251231527093598e-05, "loss": 1.1496, "step": 2198 }, { "epoch": 0.3382946809738087, "grad_norm": 3.273378849029541, "learning_rate": 1.3248152709359607e-05, "loss": 1.3659, "step": 2199 }, { "epoch": 0.33844852121072266, "grad_norm": 3.402289390563965, "learning_rate": 1.3245073891625618e-05, "loss": 1.3279, "step": 2200 }, { "epoch": 0.3386023614476366, "grad_norm": 3.68688702583313, "learning_rate": 1.3241995073891627e-05, "loss": 1.2146, "step": 2201 }, { "epoch": 0.3387562016845506, "grad_norm": 3.3119401931762695, "learning_rate": 1.3238916256157637e-05, "loss": 1.426, "step": 2202 }, { "epoch": 0.33891004192146457, "grad_norm": 3.3432891368865967, "learning_rate": 1.3235837438423646e-05, "loss": 1.2354, "step": 2203 }, { "epoch": 0.3390638821583785, "grad_norm": 3.454834222793579, "learning_rate": 1.3232758620689657e-05, "loss": 1.2944, "step": 2204 }, { "epoch": 0.33921772239529246, "grad_norm": 3.6326441764831543, "learning_rate": 1.3229679802955666e-05, "loss": 1.3319, "step": 2205 }, { "epoch": 0.33937156263220647, "grad_norm": 3.1543750762939453, "learning_rate": 1.3226600985221676e-05, "loss": 1.4848, "step": 2206 }, { "epoch": 0.3395254028691204, "grad_norm": 3.4370105266571045, "learning_rate": 1.3223522167487685e-05, "loss": 1.2474, "step": 2207 }, { "epoch": 0.33967924310603437, "grad_norm": 3.571171522140503, "learning_rate": 1.3220443349753696e-05, "loss": 1.3516, "step": 2208 }, { "epoch": 0.33983308334294837, "grad_norm": 3.5950264930725098, "learning_rate": 1.3217364532019705e-05, "loss": 1.391, "step": 2209 }, { "epoch": 0.3399869235798623, "grad_norm": 3.5289106369018555, "learning_rate": 1.3214285714285716e-05, "loss": 1.2686, "step": 2210 }, { "epoch": 0.34014076381677627, "grad_norm": 4.540318965911865, "learning_rate": 1.3211206896551724e-05, "loss": 1.2732, "step": 2211 }, { "epoch": 0.3402946040536902, "grad_norm": 3.5902647972106934, "learning_rate": 1.3208128078817735e-05, "loss": 1.4039, "step": 2212 }, { "epoch": 0.3404484442906042, "grad_norm": 4.120965003967285, "learning_rate": 1.3205049261083744e-05, "loss": 1.2693, "step": 2213 }, { "epoch": 0.3406022845275182, "grad_norm": 3.413710594177246, "learning_rate": 1.3201970443349755e-05, "loss": 1.4405, "step": 2214 }, { "epoch": 0.3407561247644321, "grad_norm": 3.4197096824645996, "learning_rate": 1.3198891625615764e-05, "loss": 1.3042, "step": 2215 }, { "epoch": 0.3409099650013461, "grad_norm": 4.497821807861328, "learning_rate": 1.3195812807881774e-05, "loss": 1.5316, "step": 2216 }, { "epoch": 0.3410638052382601, "grad_norm": 3.858283281326294, "learning_rate": 1.3192733990147783e-05, "loss": 1.451, "step": 2217 }, { "epoch": 0.341217645475174, "grad_norm": 3.895087242126465, "learning_rate": 1.3189655172413794e-05, "loss": 1.4387, "step": 2218 }, { "epoch": 0.341371485712088, "grad_norm": 3.5847699642181396, "learning_rate": 1.3186576354679803e-05, "loss": 1.3503, "step": 2219 }, { "epoch": 0.341525325949002, "grad_norm": 3.073845624923706, "learning_rate": 1.3183497536945814e-05, "loss": 1.2451, "step": 2220 }, { "epoch": 0.34167916618591593, "grad_norm": 3.499157428741455, "learning_rate": 1.3180418719211822e-05, "loss": 1.5432, "step": 2221 }, { "epoch": 0.3418330064228299, "grad_norm": 3.419304370880127, "learning_rate": 1.3177339901477833e-05, "loss": 1.1985, "step": 2222 }, { "epoch": 0.3419868466597439, "grad_norm": 3.081291437149048, "learning_rate": 1.3174261083743844e-05, "loss": 1.3426, "step": 2223 }, { "epoch": 0.34214068689665783, "grad_norm": 3.726656436920166, "learning_rate": 1.3171182266009854e-05, "loss": 1.2415, "step": 2224 }, { "epoch": 0.3422945271335718, "grad_norm": 3.1943960189819336, "learning_rate": 1.3168103448275863e-05, "loss": 1.405, "step": 2225 }, { "epoch": 0.34244836737048573, "grad_norm": 3.874413251876831, "learning_rate": 1.3165024630541874e-05, "loss": 1.4833, "step": 2226 }, { "epoch": 0.34260220760739973, "grad_norm": 4.314065933227539, "learning_rate": 1.3161945812807883e-05, "loss": 1.3489, "step": 2227 }, { "epoch": 0.3427560478443137, "grad_norm": 3.331798553466797, "learning_rate": 1.3158866995073894e-05, "loss": 1.283, "step": 2228 }, { "epoch": 0.34290988808122763, "grad_norm": 3.8139026165008545, "learning_rate": 1.3155788177339903e-05, "loss": 1.3476, "step": 2229 }, { "epoch": 0.34306372831814164, "grad_norm": 3.7959983348846436, "learning_rate": 1.3152709359605913e-05, "loss": 1.4526, "step": 2230 }, { "epoch": 0.3432175685550556, "grad_norm": 4.239617824554443, "learning_rate": 1.3149630541871922e-05, "loss": 1.426, "step": 2231 }, { "epoch": 0.34337140879196953, "grad_norm": 4.103034019470215, "learning_rate": 1.3146551724137933e-05, "loss": 1.5699, "step": 2232 }, { "epoch": 0.3435252490288835, "grad_norm": 3.5326144695281982, "learning_rate": 1.3143472906403942e-05, "loss": 1.5567, "step": 2233 }, { "epoch": 0.3436790892657975, "grad_norm": 4.2301859855651855, "learning_rate": 1.3140394088669952e-05, "loss": 1.5414, "step": 2234 }, { "epoch": 0.34383292950271144, "grad_norm": 3.4047534465789795, "learning_rate": 1.3137315270935961e-05, "loss": 1.3909, "step": 2235 }, { "epoch": 0.3439867697396254, "grad_norm": 3.2611310482025146, "learning_rate": 1.3134236453201972e-05, "loss": 1.3924, "step": 2236 }, { "epoch": 0.3441406099765394, "grad_norm": 3.7918007373809814, "learning_rate": 1.3131157635467981e-05, "loss": 1.3514, "step": 2237 }, { "epoch": 0.34429445021345334, "grad_norm": 3.9259581565856934, "learning_rate": 1.3128078817733992e-05, "loss": 1.2592, "step": 2238 }, { "epoch": 0.3444482904503673, "grad_norm": 3.7139546871185303, "learning_rate": 1.3125e-05, "loss": 1.3471, "step": 2239 }, { "epoch": 0.34460213068728124, "grad_norm": 3.24778151512146, "learning_rate": 1.3121921182266011e-05, "loss": 1.3534, "step": 2240 }, { "epoch": 0.34475597092419524, "grad_norm": 3.4897689819335938, "learning_rate": 1.311884236453202e-05, "loss": 1.3894, "step": 2241 }, { "epoch": 0.3449098111611092, "grad_norm": 3.1450726985931396, "learning_rate": 1.311576354679803e-05, "loss": 1.4124, "step": 2242 }, { "epoch": 0.34506365139802314, "grad_norm": 3.451467275619507, "learning_rate": 1.311268472906404e-05, "loss": 1.3402, "step": 2243 }, { "epoch": 0.3452174916349371, "grad_norm": 4.022517681121826, "learning_rate": 1.310960591133005e-05, "loss": 1.5705, "step": 2244 }, { "epoch": 0.3453713318718511, "grad_norm": 3.65034818649292, "learning_rate": 1.310652709359606e-05, "loss": 1.5739, "step": 2245 }, { "epoch": 0.34552517210876504, "grad_norm": 4.500216484069824, "learning_rate": 1.310344827586207e-05, "loss": 1.3211, "step": 2246 }, { "epoch": 0.345679012345679, "grad_norm": 3.6123197078704834, "learning_rate": 1.3100369458128079e-05, "loss": 1.2736, "step": 2247 }, { "epoch": 0.345832852582593, "grad_norm": 3.11482834815979, "learning_rate": 1.309729064039409e-05, "loss": 1.3342, "step": 2248 }, { "epoch": 0.34598669281950695, "grad_norm": 3.5677037239074707, "learning_rate": 1.3094211822660099e-05, "loss": 1.3424, "step": 2249 }, { "epoch": 0.3461405330564209, "grad_norm": 3.2945032119750977, "learning_rate": 1.309113300492611e-05, "loss": 1.3389, "step": 2250 }, { "epoch": 0.34629437329333485, "grad_norm": 4.962666034698486, "learning_rate": 1.3088054187192118e-05, "loss": 1.4267, "step": 2251 }, { "epoch": 0.34644821353024885, "grad_norm": 3.645893096923828, "learning_rate": 1.3084975369458129e-05, "loss": 1.1652, "step": 2252 }, { "epoch": 0.3466020537671628, "grad_norm": 3.7573628425598145, "learning_rate": 1.3081896551724138e-05, "loss": 1.3402, "step": 2253 }, { "epoch": 0.34675589400407675, "grad_norm": 3.767322301864624, "learning_rate": 1.3078817733990148e-05, "loss": 1.3429, "step": 2254 }, { "epoch": 0.34690973424099075, "grad_norm": 3.4884777069091797, "learning_rate": 1.3075738916256157e-05, "loss": 1.4125, "step": 2255 }, { "epoch": 0.3470635744779047, "grad_norm": 3.361145496368408, "learning_rate": 1.307266009852217e-05, "loss": 1.0384, "step": 2256 }, { "epoch": 0.34721741471481865, "grad_norm": 3.226414203643799, "learning_rate": 1.3069581280788179e-05, "loss": 1.5256, "step": 2257 }, { "epoch": 0.3473712549517326, "grad_norm": 4.477392196655273, "learning_rate": 1.306650246305419e-05, "loss": 1.452, "step": 2258 }, { "epoch": 0.3475250951886466, "grad_norm": 3.7901017665863037, "learning_rate": 1.3063423645320198e-05, "loss": 1.5311, "step": 2259 }, { "epoch": 0.34767893542556055, "grad_norm": 3.6846017837524414, "learning_rate": 1.3060344827586209e-05, "loss": 1.3222, "step": 2260 }, { "epoch": 0.3478327756624745, "grad_norm": 3.159471273422241, "learning_rate": 1.3057266009852218e-05, "loss": 1.1133, "step": 2261 }, { "epoch": 0.3479866158993885, "grad_norm": 3.6808829307556152, "learning_rate": 1.3054187192118228e-05, "loss": 1.2074, "step": 2262 }, { "epoch": 0.34814045613630246, "grad_norm": 3.6352295875549316, "learning_rate": 1.3051108374384237e-05, "loss": 1.5494, "step": 2263 }, { "epoch": 0.3482942963732164, "grad_norm": 3.8030409812927246, "learning_rate": 1.3048029556650248e-05, "loss": 1.2065, "step": 2264 }, { "epoch": 0.34844813661013035, "grad_norm": 3.739921808242798, "learning_rate": 1.3044950738916257e-05, "loss": 1.3432, "step": 2265 }, { "epoch": 0.34860197684704436, "grad_norm": 3.8283581733703613, "learning_rate": 1.3041871921182268e-05, "loss": 1.5104, "step": 2266 }, { "epoch": 0.3487558170839583, "grad_norm": 3.492676019668579, "learning_rate": 1.3038793103448277e-05, "loss": 1.1082, "step": 2267 }, { "epoch": 0.34890965732087226, "grad_norm": 4.2449421882629395, "learning_rate": 1.3035714285714287e-05, "loss": 1.3712, "step": 2268 }, { "epoch": 0.34906349755778626, "grad_norm": 3.424496650695801, "learning_rate": 1.3032635467980296e-05, "loss": 1.3865, "step": 2269 }, { "epoch": 0.3492173377947002, "grad_norm": 3.4568185806274414, "learning_rate": 1.3029556650246307e-05, "loss": 1.3256, "step": 2270 }, { "epoch": 0.34937117803161416, "grad_norm": 3.2314798831939697, "learning_rate": 1.3026477832512316e-05, "loss": 1.5993, "step": 2271 }, { "epoch": 0.3495250182685281, "grad_norm": 4.133164405822754, "learning_rate": 1.3023399014778326e-05, "loss": 1.1923, "step": 2272 }, { "epoch": 0.3496788585054421, "grad_norm": 4.680640697479248, "learning_rate": 1.3020320197044335e-05, "loss": 1.4794, "step": 2273 }, { "epoch": 0.34983269874235606, "grad_norm": 3.0645978450775146, "learning_rate": 1.3017241379310346e-05, "loss": 1.3904, "step": 2274 }, { "epoch": 0.34998653897927, "grad_norm": 3.1593806743621826, "learning_rate": 1.3014162561576355e-05, "loss": 1.4437, "step": 2275 }, { "epoch": 0.350140379216184, "grad_norm": 3.8122212886810303, "learning_rate": 1.3011083743842366e-05, "loss": 1.4937, "step": 2276 }, { "epoch": 0.35029421945309797, "grad_norm": 3.633915662765503, "learning_rate": 1.3008004926108375e-05, "loss": 1.4687, "step": 2277 }, { "epoch": 0.3504480596900119, "grad_norm": 3.1753382682800293, "learning_rate": 1.3004926108374385e-05, "loss": 1.574, "step": 2278 }, { "epoch": 0.35060189992692586, "grad_norm": 4.549596309661865, "learning_rate": 1.3001847290640394e-05, "loss": 1.2476, "step": 2279 }, { "epoch": 0.35075574016383987, "grad_norm": 4.115490913391113, "learning_rate": 1.2998768472906405e-05, "loss": 1.0986, "step": 2280 }, { "epoch": 0.3509095804007538, "grad_norm": 3.6067898273468018, "learning_rate": 1.2995689655172414e-05, "loss": 1.2612, "step": 2281 }, { "epoch": 0.35106342063766777, "grad_norm": 3.8248274326324463, "learning_rate": 1.2992610837438424e-05, "loss": 1.3756, "step": 2282 }, { "epoch": 0.35121726087458177, "grad_norm": 3.612551212310791, "learning_rate": 1.2989532019704433e-05, "loss": 1.5039, "step": 2283 }, { "epoch": 0.3513711011114957, "grad_norm": 3.857123851776123, "learning_rate": 1.2986453201970444e-05, "loss": 1.5928, "step": 2284 }, { "epoch": 0.35152494134840967, "grad_norm": 3.5190200805664062, "learning_rate": 1.2983374384236453e-05, "loss": 1.4501, "step": 2285 }, { "epoch": 0.3516787815853236, "grad_norm": 3.9294819831848145, "learning_rate": 1.2980295566502464e-05, "loss": 1.2924, "step": 2286 }, { "epoch": 0.3518326218222376, "grad_norm": 3.5009379386901855, "learning_rate": 1.2977216748768473e-05, "loss": 1.5445, "step": 2287 }, { "epoch": 0.3519864620591516, "grad_norm": 3.664306402206421, "learning_rate": 1.2974137931034483e-05, "loss": 1.0636, "step": 2288 }, { "epoch": 0.3521403022960655, "grad_norm": 3.3623392581939697, "learning_rate": 1.2971059113300492e-05, "loss": 1.337, "step": 2289 }, { "epoch": 0.3522941425329795, "grad_norm": 3.5164525508880615, "learning_rate": 1.2967980295566504e-05, "loss": 1.286, "step": 2290 }, { "epoch": 0.3524479827698935, "grad_norm": 3.825601577758789, "learning_rate": 1.2964901477832515e-05, "loss": 1.3694, "step": 2291 }, { "epoch": 0.3526018230068074, "grad_norm": 4.069369792938232, "learning_rate": 1.2961822660098524e-05, "loss": 1.1001, "step": 2292 }, { "epoch": 0.3527556632437214, "grad_norm": 3.6082990169525146, "learning_rate": 1.2958743842364535e-05, "loss": 1.3405, "step": 2293 }, { "epoch": 0.3529095034806354, "grad_norm": 3.6629772186279297, "learning_rate": 1.2955665024630544e-05, "loss": 1.2132, "step": 2294 }, { "epoch": 0.3530633437175493, "grad_norm": 3.2687227725982666, "learning_rate": 1.2952586206896554e-05, "loss": 1.1319, "step": 2295 }, { "epoch": 0.3532171839544633, "grad_norm": 3.7438018321990967, "learning_rate": 1.2949507389162563e-05, "loss": 1.4626, "step": 2296 }, { "epoch": 0.3533710241913773, "grad_norm": 3.4787936210632324, "learning_rate": 1.2946428571428574e-05, "loss": 1.3716, "step": 2297 }, { "epoch": 0.35352486442829123, "grad_norm": 3.613171339035034, "learning_rate": 1.2943349753694583e-05, "loss": 1.3922, "step": 2298 }, { "epoch": 0.3536787046652052, "grad_norm": 3.0020856857299805, "learning_rate": 1.2940270935960594e-05, "loss": 1.6656, "step": 2299 }, { "epoch": 0.35383254490211913, "grad_norm": 3.9377646446228027, "learning_rate": 1.2937192118226602e-05, "loss": 1.2728, "step": 2300 }, { "epoch": 0.35398638513903313, "grad_norm": 3.5155863761901855, "learning_rate": 1.2934113300492611e-05, "loss": 1.4091, "step": 2301 }, { "epoch": 0.3541402253759471, "grad_norm": 3.4845752716064453, "learning_rate": 1.2931034482758622e-05, "loss": 1.2923, "step": 2302 }, { "epoch": 0.35429406561286103, "grad_norm": 3.652402400970459, "learning_rate": 1.2927955665024631e-05, "loss": 1.1017, "step": 2303 }, { "epoch": 0.35444790584977504, "grad_norm": 4.158341884613037, "learning_rate": 1.2924876847290642e-05, "loss": 1.399, "step": 2304 }, { "epoch": 0.354601746086689, "grad_norm": 3.850301504135132, "learning_rate": 1.292179802955665e-05, "loss": 1.222, "step": 2305 }, { "epoch": 0.35475558632360293, "grad_norm": 3.2049543857574463, "learning_rate": 1.2918719211822661e-05, "loss": 1.31, "step": 2306 }, { "epoch": 0.3549094265605169, "grad_norm": 3.3335483074188232, "learning_rate": 1.291564039408867e-05, "loss": 1.4184, "step": 2307 }, { "epoch": 0.3550632667974309, "grad_norm": 3.936014175415039, "learning_rate": 1.2912561576354681e-05, "loss": 1.0796, "step": 2308 }, { "epoch": 0.35521710703434484, "grad_norm": 3.3328375816345215, "learning_rate": 1.290948275862069e-05, "loss": 1.4868, "step": 2309 }, { "epoch": 0.3553709472712588, "grad_norm": 3.6514790058135986, "learning_rate": 1.29064039408867e-05, "loss": 1.3552, "step": 2310 }, { "epoch": 0.35552478750817273, "grad_norm": 3.138251543045044, "learning_rate": 1.290332512315271e-05, "loss": 1.2645, "step": 2311 }, { "epoch": 0.35567862774508674, "grad_norm": 4.170193195343018, "learning_rate": 1.290024630541872e-05, "loss": 1.1317, "step": 2312 }, { "epoch": 0.3558324679820007, "grad_norm": 4.3254899978637695, "learning_rate": 1.2897167487684729e-05, "loss": 1.4997, "step": 2313 }, { "epoch": 0.35598630821891464, "grad_norm": 3.701279640197754, "learning_rate": 1.289408866995074e-05, "loss": 1.5707, "step": 2314 }, { "epoch": 0.35614014845582864, "grad_norm": 3.406378746032715, "learning_rate": 1.2891009852216749e-05, "loss": 1.3259, "step": 2315 }, { "epoch": 0.3562939886927426, "grad_norm": 2.950089693069458, "learning_rate": 1.288793103448276e-05, "loss": 1.2872, "step": 2316 }, { "epoch": 0.35644782892965654, "grad_norm": 3.065791130065918, "learning_rate": 1.2884852216748768e-05, "loss": 1.3255, "step": 2317 }, { "epoch": 0.3566016691665705, "grad_norm": 3.4935059547424316, "learning_rate": 1.2881773399014779e-05, "loss": 1.4257, "step": 2318 }, { "epoch": 0.3567555094034845, "grad_norm": 3.593597650527954, "learning_rate": 1.2878694581280788e-05, "loss": 1.4316, "step": 2319 }, { "epoch": 0.35690934964039844, "grad_norm": 3.1431198120117188, "learning_rate": 1.2875615763546798e-05, "loss": 1.4558, "step": 2320 }, { "epoch": 0.3570631898773124, "grad_norm": 3.659219980239868, "learning_rate": 1.2872536945812807e-05, "loss": 1.4068, "step": 2321 }, { "epoch": 0.3572170301142264, "grad_norm": 4.52938985824585, "learning_rate": 1.2869458128078818e-05, "loss": 1.7553, "step": 2322 }, { "epoch": 0.35737087035114035, "grad_norm": 3.5488929748535156, "learning_rate": 1.2866379310344827e-05, "loss": 1.4838, "step": 2323 }, { "epoch": 0.3575247105880543, "grad_norm": 4.245187282562256, "learning_rate": 1.286330049261084e-05, "loss": 1.4564, "step": 2324 }, { "epoch": 0.35767855082496824, "grad_norm": 2.932161331176758, "learning_rate": 1.286022167487685e-05, "loss": 1.4583, "step": 2325 }, { "epoch": 0.35783239106188225, "grad_norm": 3.5596187114715576, "learning_rate": 1.2857142857142859e-05, "loss": 1.2693, "step": 2326 }, { "epoch": 0.3579862312987962, "grad_norm": 2.9314703941345215, "learning_rate": 1.285406403940887e-05, "loss": 1.4019, "step": 2327 }, { "epoch": 0.35814007153571015, "grad_norm": 3.6028006076812744, "learning_rate": 1.2850985221674879e-05, "loss": 1.2722, "step": 2328 }, { "epoch": 0.35829391177262415, "grad_norm": 3.175947904586792, "learning_rate": 1.284790640394089e-05, "loss": 1.3957, "step": 2329 }, { "epoch": 0.3584477520095381, "grad_norm": 3.4517698287963867, "learning_rate": 1.2844827586206898e-05, "loss": 1.0067, "step": 2330 }, { "epoch": 0.35860159224645205, "grad_norm": 3.253894567489624, "learning_rate": 1.2841748768472909e-05, "loss": 1.1811, "step": 2331 }, { "epoch": 0.358755432483366, "grad_norm": 3.093505620956421, "learning_rate": 1.2838669950738918e-05, "loss": 1.3272, "step": 2332 }, { "epoch": 0.35890927272028, "grad_norm": 3.3479690551757812, "learning_rate": 1.2835591133004928e-05, "loss": 1.4074, "step": 2333 }, { "epoch": 0.35906311295719395, "grad_norm": 3.4179439544677734, "learning_rate": 1.2832512315270937e-05, "loss": 1.1656, "step": 2334 }, { "epoch": 0.3592169531941079, "grad_norm": 3.7834572792053223, "learning_rate": 1.2829433497536948e-05, "loss": 1.3304, "step": 2335 }, { "epoch": 0.3593707934310219, "grad_norm": 3.5656578540802, "learning_rate": 1.2826354679802957e-05, "loss": 1.5933, "step": 2336 }, { "epoch": 0.35952463366793586, "grad_norm": 3.783646583557129, "learning_rate": 1.2823275862068968e-05, "loss": 1.2735, "step": 2337 }, { "epoch": 0.3596784739048498, "grad_norm": 3.90604829788208, "learning_rate": 1.2820197044334976e-05, "loss": 1.6043, "step": 2338 }, { "epoch": 0.35983231414176375, "grad_norm": 3.7551846504211426, "learning_rate": 1.2817118226600987e-05, "loss": 1.2421, "step": 2339 }, { "epoch": 0.35998615437867776, "grad_norm": 3.7252352237701416, "learning_rate": 1.2814039408866996e-05, "loss": 1.386, "step": 2340 }, { "epoch": 0.3601399946155917, "grad_norm": 4.2908525466918945, "learning_rate": 1.2810960591133007e-05, "loss": 1.3587, "step": 2341 }, { "epoch": 0.36029383485250566, "grad_norm": 4.229485034942627, "learning_rate": 1.2807881773399016e-05, "loss": 1.3003, "step": 2342 }, { "epoch": 0.36044767508941966, "grad_norm": 3.3527750968933105, "learning_rate": 1.2804802955665026e-05, "loss": 1.453, "step": 2343 }, { "epoch": 0.3606015153263336, "grad_norm": 3.54838228225708, "learning_rate": 1.2801724137931035e-05, "loss": 1.4627, "step": 2344 }, { "epoch": 0.36075535556324756, "grad_norm": 3.160006046295166, "learning_rate": 1.2798645320197044e-05, "loss": 1.4409, "step": 2345 }, { "epoch": 0.3609091958001615, "grad_norm": 3.693466901779175, "learning_rate": 1.2795566502463055e-05, "loss": 1.4422, "step": 2346 }, { "epoch": 0.3610630360370755, "grad_norm": 3.235471725463867, "learning_rate": 1.2792487684729064e-05, "loss": 1.4191, "step": 2347 }, { "epoch": 0.36121687627398946, "grad_norm": 3.677654266357422, "learning_rate": 1.2789408866995074e-05, "loss": 1.3206, "step": 2348 }, { "epoch": 0.3613707165109034, "grad_norm": 4.094639778137207, "learning_rate": 1.2786330049261083e-05, "loss": 1.1875, "step": 2349 }, { "epoch": 0.3615245567478174, "grad_norm": 3.8744888305664062, "learning_rate": 1.2783251231527094e-05, "loss": 1.2893, "step": 2350 }, { "epoch": 0.36167839698473137, "grad_norm": 3.3547987937927246, "learning_rate": 1.2780172413793103e-05, "loss": 1.1944, "step": 2351 }, { "epoch": 0.3618322372216453, "grad_norm": 3.4391674995422363, "learning_rate": 1.2777093596059114e-05, "loss": 1.2349, "step": 2352 }, { "epoch": 0.36198607745855926, "grad_norm": 4.107833385467529, "learning_rate": 1.2774014778325123e-05, "loss": 1.4516, "step": 2353 }, { "epoch": 0.36213991769547327, "grad_norm": 3.4384164810180664, "learning_rate": 1.2770935960591133e-05, "loss": 1.4935, "step": 2354 }, { "epoch": 0.3622937579323872, "grad_norm": 4.111291885375977, "learning_rate": 1.2767857142857142e-05, "loss": 1.2248, "step": 2355 }, { "epoch": 0.36244759816930117, "grad_norm": 3.337296724319458, "learning_rate": 1.2764778325123153e-05, "loss": 1.658, "step": 2356 }, { "epoch": 0.36260143840621517, "grad_norm": 3.322225332260132, "learning_rate": 1.2761699507389162e-05, "loss": 1.367, "step": 2357 }, { "epoch": 0.3627552786431291, "grad_norm": 3.1336560249328613, "learning_rate": 1.2758620689655174e-05, "loss": 1.4017, "step": 2358 }, { "epoch": 0.36290911888004307, "grad_norm": 3.868727922439575, "learning_rate": 1.2755541871921185e-05, "loss": 1.292, "step": 2359 }, { "epoch": 0.363062959116957, "grad_norm": 4.337617874145508, "learning_rate": 1.2752463054187194e-05, "loss": 1.4525, "step": 2360 }, { "epoch": 0.363216799353871, "grad_norm": 4.1160078048706055, "learning_rate": 1.2749384236453204e-05, "loss": 1.5949, "step": 2361 }, { "epoch": 0.36337063959078497, "grad_norm": 3.9746294021606445, "learning_rate": 1.2746305418719213e-05, "loss": 1.4022, "step": 2362 }, { "epoch": 0.3635244798276989, "grad_norm": 4.057015419006348, "learning_rate": 1.2743226600985224e-05, "loss": 1.2426, "step": 2363 }, { "epoch": 0.3636783200646129, "grad_norm": 4.077888488769531, "learning_rate": 1.2740147783251233e-05, "loss": 1.053, "step": 2364 }, { "epoch": 0.3638321603015269, "grad_norm": 3.8087456226348877, "learning_rate": 1.2737068965517244e-05, "loss": 1.2894, "step": 2365 }, { "epoch": 0.3639860005384408, "grad_norm": 3.8720901012420654, "learning_rate": 1.2733990147783253e-05, "loss": 1.315, "step": 2366 }, { "epoch": 0.3641398407753548, "grad_norm": 3.7720277309417725, "learning_rate": 1.2730911330049263e-05, "loss": 1.6087, "step": 2367 }, { "epoch": 0.3642936810122688, "grad_norm": 3.5054798126220703, "learning_rate": 1.2727832512315272e-05, "loss": 1.3969, "step": 2368 }, { "epoch": 0.3644475212491827, "grad_norm": 4.172918319702148, "learning_rate": 1.2724753694581283e-05, "loss": 1.5759, "step": 2369 }, { "epoch": 0.3646013614860967, "grad_norm": 3.517814874649048, "learning_rate": 1.2721674876847292e-05, "loss": 1.5138, "step": 2370 }, { "epoch": 0.3647552017230107, "grad_norm": 3.225661277770996, "learning_rate": 1.2718596059113302e-05, "loss": 1.321, "step": 2371 }, { "epoch": 0.36490904195992463, "grad_norm": 3.9812862873077393, "learning_rate": 1.2715517241379311e-05, "loss": 1.638, "step": 2372 }, { "epoch": 0.3650628821968386, "grad_norm": 4.260756015777588, "learning_rate": 1.2712438423645322e-05, "loss": 1.4148, "step": 2373 }, { "epoch": 0.3652167224337525, "grad_norm": 3.7773168087005615, "learning_rate": 1.2709359605911331e-05, "loss": 1.6918, "step": 2374 }, { "epoch": 0.36537056267066653, "grad_norm": 3.3205862045288086, "learning_rate": 1.2706280788177342e-05, "loss": 0.9639, "step": 2375 }, { "epoch": 0.3655244029075805, "grad_norm": 3.5355517864227295, "learning_rate": 1.270320197044335e-05, "loss": 1.524, "step": 2376 }, { "epoch": 0.36567824314449443, "grad_norm": 3.5417492389678955, "learning_rate": 1.2700123152709361e-05, "loss": 1.3954, "step": 2377 }, { "epoch": 0.36583208338140843, "grad_norm": 3.5005080699920654, "learning_rate": 1.269704433497537e-05, "loss": 1.495, "step": 2378 }, { "epoch": 0.3659859236183224, "grad_norm": 4.272229194641113, "learning_rate": 1.269396551724138e-05, "loss": 1.3418, "step": 2379 }, { "epoch": 0.36613976385523633, "grad_norm": 3.7407398223876953, "learning_rate": 1.269088669950739e-05, "loss": 1.4059, "step": 2380 }, { "epoch": 0.3662936040921503, "grad_norm": 3.546755075454712, "learning_rate": 1.26878078817734e-05, "loss": 1.2112, "step": 2381 }, { "epoch": 0.3664474443290643, "grad_norm": 3.283841609954834, "learning_rate": 1.268472906403941e-05, "loss": 1.2625, "step": 2382 }, { "epoch": 0.36660128456597824, "grad_norm": 3.6112241744995117, "learning_rate": 1.268165024630542e-05, "loss": 1.2894, "step": 2383 }, { "epoch": 0.3667551248028922, "grad_norm": 3.725982904434204, "learning_rate": 1.2678571428571429e-05, "loss": 1.4261, "step": 2384 }, { "epoch": 0.36690896503980613, "grad_norm": 3.24251651763916, "learning_rate": 1.267549261083744e-05, "loss": 1.5771, "step": 2385 }, { "epoch": 0.36706280527672014, "grad_norm": 3.1508471965789795, "learning_rate": 1.2672413793103449e-05, "loss": 1.2441, "step": 2386 }, { "epoch": 0.3672166455136341, "grad_norm": 3.5125975608825684, "learning_rate": 1.266933497536946e-05, "loss": 1.4324, "step": 2387 }, { "epoch": 0.36737048575054804, "grad_norm": 3.643439531326294, "learning_rate": 1.2666256157635468e-05, "loss": 1.3467, "step": 2388 }, { "epoch": 0.36752432598746204, "grad_norm": 4.006181240081787, "learning_rate": 1.2663177339901479e-05, "loss": 1.519, "step": 2389 }, { "epoch": 0.367678166224376, "grad_norm": 3.823758602142334, "learning_rate": 1.2660098522167488e-05, "loss": 1.6404, "step": 2390 }, { "epoch": 0.36783200646128994, "grad_norm": 3.194472551345825, "learning_rate": 1.2657019704433497e-05, "loss": 1.519, "step": 2391 }, { "epoch": 0.3679858466982039, "grad_norm": 4.248172760009766, "learning_rate": 1.2653940886699509e-05, "loss": 1.365, "step": 2392 }, { "epoch": 0.3681396869351179, "grad_norm": 3.535768508911133, "learning_rate": 1.265086206896552e-05, "loss": 1.3975, "step": 2393 }, { "epoch": 0.36829352717203184, "grad_norm": 3.8718724250793457, "learning_rate": 1.2647783251231529e-05, "loss": 1.3855, "step": 2394 }, { "epoch": 0.3684473674089458, "grad_norm": 3.8083505630493164, "learning_rate": 1.264470443349754e-05, "loss": 1.5849, "step": 2395 }, { "epoch": 0.3686012076458598, "grad_norm": 3.9153478145599365, "learning_rate": 1.2641625615763548e-05, "loss": 1.2725, "step": 2396 }, { "epoch": 0.36875504788277375, "grad_norm": 4.665472507476807, "learning_rate": 1.2638546798029559e-05, "loss": 1.6083, "step": 2397 }, { "epoch": 0.3689088881196877, "grad_norm": 4.196680068969727, "learning_rate": 1.2635467980295568e-05, "loss": 1.1725, "step": 2398 }, { "epoch": 0.36906272835660164, "grad_norm": 3.5776829719543457, "learning_rate": 1.2632389162561578e-05, "loss": 1.4114, "step": 2399 }, { "epoch": 0.36921656859351565, "grad_norm": 3.762925863265991, "learning_rate": 1.2629310344827587e-05, "loss": 1.1627, "step": 2400 }, { "epoch": 0.3693704088304296, "grad_norm": 3.739635467529297, "learning_rate": 1.2626231527093598e-05, "loss": 1.4201, "step": 2401 }, { "epoch": 0.36952424906734355, "grad_norm": 3.8998899459838867, "learning_rate": 1.2623152709359607e-05, "loss": 1.3596, "step": 2402 }, { "epoch": 0.36967808930425755, "grad_norm": 3.4602925777435303, "learning_rate": 1.2620073891625618e-05, "loss": 1.4888, "step": 2403 }, { "epoch": 0.3698319295411715, "grad_norm": 3.502048969268799, "learning_rate": 1.2616995073891627e-05, "loss": 1.2692, "step": 2404 }, { "epoch": 0.36998576977808545, "grad_norm": 3.325401544570923, "learning_rate": 1.2613916256157637e-05, "loss": 1.6002, "step": 2405 }, { "epoch": 0.3701396100149994, "grad_norm": 3.9566667079925537, "learning_rate": 1.2610837438423646e-05, "loss": 1.4125, "step": 2406 }, { "epoch": 0.3702934502519134, "grad_norm": 3.793257236480713, "learning_rate": 1.2607758620689657e-05, "loss": 1.4422, "step": 2407 }, { "epoch": 0.37044729048882735, "grad_norm": 3.5822038650512695, "learning_rate": 1.2604679802955666e-05, "loss": 1.234, "step": 2408 }, { "epoch": 0.3706011307257413, "grad_norm": 3.5192131996154785, "learning_rate": 1.2601600985221676e-05, "loss": 1.3074, "step": 2409 }, { "epoch": 0.3707549709626553, "grad_norm": 3.640085220336914, "learning_rate": 1.2598522167487685e-05, "loss": 1.3481, "step": 2410 }, { "epoch": 0.37090881119956925, "grad_norm": 3.249838352203369, "learning_rate": 1.2595443349753696e-05, "loss": 1.3134, "step": 2411 }, { "epoch": 0.3710626514364832, "grad_norm": 3.446685314178467, "learning_rate": 1.2592364532019705e-05, "loss": 1.3466, "step": 2412 }, { "epoch": 0.37121649167339715, "grad_norm": 3.9658849239349365, "learning_rate": 1.2589285714285716e-05, "loss": 1.2202, "step": 2413 }, { "epoch": 0.37137033191031116, "grad_norm": 3.4898552894592285, "learning_rate": 1.2586206896551725e-05, "loss": 1.3235, "step": 2414 }, { "epoch": 0.3715241721472251, "grad_norm": 3.343365430831909, "learning_rate": 1.2583128078817735e-05, "loss": 1.518, "step": 2415 }, { "epoch": 0.37167801238413906, "grad_norm": 4.118545055389404, "learning_rate": 1.2580049261083744e-05, "loss": 1.6226, "step": 2416 }, { "epoch": 0.37183185262105306, "grad_norm": 3.638556718826294, "learning_rate": 1.2576970443349755e-05, "loss": 1.3013, "step": 2417 }, { "epoch": 0.371985692857967, "grad_norm": 2.9886837005615234, "learning_rate": 1.2573891625615764e-05, "loss": 1.2976, "step": 2418 }, { "epoch": 0.37213953309488096, "grad_norm": 4.112362384796143, "learning_rate": 1.2570812807881774e-05, "loss": 1.5312, "step": 2419 }, { "epoch": 0.3722933733317949, "grad_norm": 3.1529958248138428, "learning_rate": 1.2567733990147783e-05, "loss": 1.4356, "step": 2420 }, { "epoch": 0.3724472135687089, "grad_norm": 3.3621323108673096, "learning_rate": 1.2564655172413794e-05, "loss": 1.3184, "step": 2421 }, { "epoch": 0.37260105380562286, "grad_norm": 3.3260982036590576, "learning_rate": 1.2561576354679803e-05, "loss": 1.384, "step": 2422 }, { "epoch": 0.3727548940425368, "grad_norm": 4.347748756408691, "learning_rate": 1.2558497536945814e-05, "loss": 1.1518, "step": 2423 }, { "epoch": 0.3729087342794508, "grad_norm": 3.5868566036224365, "learning_rate": 1.2555418719211823e-05, "loss": 1.4075, "step": 2424 }, { "epoch": 0.37306257451636476, "grad_norm": 4.127396106719971, "learning_rate": 1.2552339901477833e-05, "loss": 1.2041, "step": 2425 }, { "epoch": 0.3732164147532787, "grad_norm": 3.4144771099090576, "learning_rate": 1.2549261083743844e-05, "loss": 1.5494, "step": 2426 }, { "epoch": 0.37337025499019266, "grad_norm": 4.569610595703125, "learning_rate": 1.2546182266009854e-05, "loss": 1.4558, "step": 2427 }, { "epoch": 0.37352409522710667, "grad_norm": 3.960606813430786, "learning_rate": 1.2543103448275863e-05, "loss": 1.295, "step": 2428 }, { "epoch": 0.3736779354640206, "grad_norm": 3.780780792236328, "learning_rate": 1.2540024630541874e-05, "loss": 1.6279, "step": 2429 }, { "epoch": 0.37383177570093457, "grad_norm": 3.554248094558716, "learning_rate": 1.2536945812807883e-05, "loss": 1.4292, "step": 2430 }, { "epoch": 0.37398561593784857, "grad_norm": 4.764266014099121, "learning_rate": 1.2533866995073894e-05, "loss": 1.4832, "step": 2431 }, { "epoch": 0.3741394561747625, "grad_norm": 4.181463718414307, "learning_rate": 1.2530788177339903e-05, "loss": 1.4164, "step": 2432 }, { "epoch": 0.37429329641167647, "grad_norm": 4.309161186218262, "learning_rate": 1.2527709359605913e-05, "loss": 1.5356, "step": 2433 }, { "epoch": 0.3744471366485904, "grad_norm": 4.009593963623047, "learning_rate": 1.2524630541871922e-05, "loss": 1.3324, "step": 2434 }, { "epoch": 0.3746009768855044, "grad_norm": 3.949592351913452, "learning_rate": 1.2521551724137933e-05, "loss": 1.3637, "step": 2435 }, { "epoch": 0.37475481712241837, "grad_norm": 3.6542038917541504, "learning_rate": 1.2518472906403942e-05, "loss": 1.3864, "step": 2436 }, { "epoch": 0.3749086573593323, "grad_norm": 3.9056079387664795, "learning_rate": 1.2515394088669952e-05, "loss": 1.2445, "step": 2437 }, { "epoch": 0.3750624975962463, "grad_norm": 3.695784568786621, "learning_rate": 1.2512315270935961e-05, "loss": 1.3692, "step": 2438 }, { "epoch": 0.3752163378331603, "grad_norm": 3.5114593505859375, "learning_rate": 1.2509236453201972e-05, "loss": 1.1517, "step": 2439 }, { "epoch": 0.3753701780700742, "grad_norm": 4.28928279876709, "learning_rate": 1.2506157635467981e-05, "loss": 1.3337, "step": 2440 }, { "epoch": 0.37552401830698817, "grad_norm": 3.7538743019104004, "learning_rate": 1.2503078817733992e-05, "loss": 1.2618, "step": 2441 }, { "epoch": 0.3756778585439022, "grad_norm": 4.184116840362549, "learning_rate": 1.25e-05, "loss": 1.0094, "step": 2442 }, { "epoch": 0.3758316987808161, "grad_norm": 3.9512112140655518, "learning_rate": 1.2496921182266011e-05, "loss": 1.374, "step": 2443 }, { "epoch": 0.3759855390177301, "grad_norm": 3.5648505687713623, "learning_rate": 1.249384236453202e-05, "loss": 1.1583, "step": 2444 }, { "epoch": 0.3761393792546441, "grad_norm": 3.4184861183166504, "learning_rate": 1.249076354679803e-05, "loss": 1.3311, "step": 2445 }, { "epoch": 0.37629321949155803, "grad_norm": 3.575958490371704, "learning_rate": 1.248768472906404e-05, "loss": 1.4266, "step": 2446 }, { "epoch": 0.376447059728472, "grad_norm": 3.662048101425171, "learning_rate": 1.248460591133005e-05, "loss": 1.3551, "step": 2447 }, { "epoch": 0.3766008999653859, "grad_norm": 3.925600528717041, "learning_rate": 1.248152709359606e-05, "loss": 1.1858, "step": 2448 }, { "epoch": 0.37675474020229993, "grad_norm": 3.6239960193634033, "learning_rate": 1.247844827586207e-05, "loss": 1.4086, "step": 2449 }, { "epoch": 0.3769085804392139, "grad_norm": 3.3153276443481445, "learning_rate": 1.2475369458128079e-05, "loss": 1.4745, "step": 2450 }, { "epoch": 0.37706242067612783, "grad_norm": 3.5096800327301025, "learning_rate": 1.247229064039409e-05, "loss": 1.486, "step": 2451 }, { "epoch": 0.3772162609130418, "grad_norm": 4.02315092086792, "learning_rate": 1.2469211822660099e-05, "loss": 1.3224, "step": 2452 }, { "epoch": 0.3773701011499558, "grad_norm": 3.67626690864563, "learning_rate": 1.246613300492611e-05, "loss": 1.4653, "step": 2453 }, { "epoch": 0.37752394138686973, "grad_norm": 3.21374249458313, "learning_rate": 1.2463054187192118e-05, "loss": 1.4173, "step": 2454 }, { "epoch": 0.3776777816237837, "grad_norm": 3.411957263946533, "learning_rate": 1.2459975369458129e-05, "loss": 1.2605, "step": 2455 }, { "epoch": 0.3778316218606977, "grad_norm": 3.276128053665161, "learning_rate": 1.2456896551724138e-05, "loss": 1.4486, "step": 2456 }, { "epoch": 0.37798546209761164, "grad_norm": 4.017685890197754, "learning_rate": 1.2453817733990148e-05, "loss": 1.2589, "step": 2457 }, { "epoch": 0.3781393023345256, "grad_norm": 3.1536383628845215, "learning_rate": 1.2450738916256157e-05, "loss": 1.4245, "step": 2458 }, { "epoch": 0.37829314257143953, "grad_norm": 3.5900206565856934, "learning_rate": 1.244766009852217e-05, "loss": 1.1835, "step": 2459 }, { "epoch": 0.37844698280835354, "grad_norm": 3.1832258701324463, "learning_rate": 1.2444581280788179e-05, "loss": 1.29, "step": 2460 }, { "epoch": 0.3786008230452675, "grad_norm": 4.431289196014404, "learning_rate": 1.244150246305419e-05, "loss": 1.2715, "step": 2461 }, { "epoch": 0.37875466328218144, "grad_norm": 3.3249874114990234, "learning_rate": 1.2438423645320198e-05, "loss": 1.2446, "step": 2462 }, { "epoch": 0.37890850351909544, "grad_norm": 4.159059047698975, "learning_rate": 1.2435344827586209e-05, "loss": 1.4457, "step": 2463 }, { "epoch": 0.3790623437560094, "grad_norm": 3.637664318084717, "learning_rate": 1.2432266009852218e-05, "loss": 1.4921, "step": 2464 }, { "epoch": 0.37921618399292334, "grad_norm": 4.246047019958496, "learning_rate": 1.2429187192118228e-05, "loss": 1.3616, "step": 2465 }, { "epoch": 0.3793700242298373, "grad_norm": 4.066906929016113, "learning_rate": 1.2426108374384237e-05, "loss": 1.3995, "step": 2466 }, { "epoch": 0.3795238644667513, "grad_norm": 3.549710273742676, "learning_rate": 1.2423029556650248e-05, "loss": 1.1515, "step": 2467 }, { "epoch": 0.37967770470366524, "grad_norm": 3.7493975162506104, "learning_rate": 1.2419950738916257e-05, "loss": 1.3205, "step": 2468 }, { "epoch": 0.3798315449405792, "grad_norm": 3.0045688152313232, "learning_rate": 1.2416871921182268e-05, "loss": 1.3605, "step": 2469 }, { "epoch": 0.3799853851774932, "grad_norm": 4.445807456970215, "learning_rate": 1.2413793103448277e-05, "loss": 1.4618, "step": 2470 }, { "epoch": 0.38013922541440714, "grad_norm": 3.595507860183716, "learning_rate": 1.2410714285714287e-05, "loss": 1.2152, "step": 2471 }, { "epoch": 0.3802930656513211, "grad_norm": 3.6952409744262695, "learning_rate": 1.2407635467980296e-05, "loss": 1.4084, "step": 2472 }, { "epoch": 0.38044690588823504, "grad_norm": 3.8258743286132812, "learning_rate": 1.2404556650246307e-05, "loss": 1.6302, "step": 2473 }, { "epoch": 0.38060074612514905, "grad_norm": 3.7863712310791016, "learning_rate": 1.2401477832512316e-05, "loss": 1.2186, "step": 2474 }, { "epoch": 0.380754586362063, "grad_norm": 3.330824136734009, "learning_rate": 1.2398399014778326e-05, "loss": 1.3135, "step": 2475 }, { "epoch": 0.38090842659897695, "grad_norm": 3.6992833614349365, "learning_rate": 1.2395320197044335e-05, "loss": 1.5083, "step": 2476 }, { "epoch": 0.38106226683589095, "grad_norm": 3.539036273956299, "learning_rate": 1.2392241379310346e-05, "loss": 1.5436, "step": 2477 }, { "epoch": 0.3812161070728049, "grad_norm": 3.804394483566284, "learning_rate": 1.2389162561576355e-05, "loss": 1.4968, "step": 2478 }, { "epoch": 0.38136994730971885, "grad_norm": 3.703711986541748, "learning_rate": 1.2386083743842366e-05, "loss": 1.621, "step": 2479 }, { "epoch": 0.3815237875466328, "grad_norm": 3.6685900688171387, "learning_rate": 1.2383004926108375e-05, "loss": 1.3571, "step": 2480 }, { "epoch": 0.3816776277835468, "grad_norm": 3.7342445850372314, "learning_rate": 1.2379926108374385e-05, "loss": 1.4033, "step": 2481 }, { "epoch": 0.38183146802046075, "grad_norm": 3.6289141178131104, "learning_rate": 1.2376847290640394e-05, "loss": 1.4737, "step": 2482 }, { "epoch": 0.3819853082573747, "grad_norm": 3.4385781288146973, "learning_rate": 1.2373768472906405e-05, "loss": 1.1015, "step": 2483 }, { "epoch": 0.3821391484942887, "grad_norm": 3.0618858337402344, "learning_rate": 1.2370689655172414e-05, "loss": 1.2089, "step": 2484 }, { "epoch": 0.38229298873120265, "grad_norm": 4.492072582244873, "learning_rate": 1.2367610837438424e-05, "loss": 1.5107, "step": 2485 }, { "epoch": 0.3824468289681166, "grad_norm": 4.136460304260254, "learning_rate": 1.2364532019704433e-05, "loss": 1.0918, "step": 2486 }, { "epoch": 0.38260066920503055, "grad_norm": 3.324430227279663, "learning_rate": 1.2361453201970444e-05, "loss": 1.2465, "step": 2487 }, { "epoch": 0.38275450944194456, "grad_norm": 3.435983180999756, "learning_rate": 1.2358374384236453e-05, "loss": 1.3334, "step": 2488 }, { "epoch": 0.3829083496788585, "grad_norm": 3.7393829822540283, "learning_rate": 1.2355295566502464e-05, "loss": 1.4793, "step": 2489 }, { "epoch": 0.38306218991577246, "grad_norm": 3.279642105102539, "learning_rate": 1.2352216748768473e-05, "loss": 1.3082, "step": 2490 }, { "epoch": 0.38321603015268646, "grad_norm": 3.2990562915802, "learning_rate": 1.2349137931034483e-05, "loss": 0.9824, "step": 2491 }, { "epoch": 0.3833698703896004, "grad_norm": 3.982840061187744, "learning_rate": 1.2346059113300492e-05, "loss": 1.4973, "step": 2492 }, { "epoch": 0.38352371062651436, "grad_norm": 3.3712337017059326, "learning_rate": 1.2342980295566505e-05, "loss": 1.2223, "step": 2493 }, { "epoch": 0.3836775508634283, "grad_norm": 4.1690897941589355, "learning_rate": 1.2339901477832515e-05, "loss": 1.3895, "step": 2494 }, { "epoch": 0.3838313911003423, "grad_norm": 3.4906411170959473, "learning_rate": 1.2336822660098524e-05, "loss": 1.3602, "step": 2495 }, { "epoch": 0.38398523133725626, "grad_norm": 3.6741082668304443, "learning_rate": 1.2333743842364533e-05, "loss": 1.3406, "step": 2496 }, { "epoch": 0.3841390715741702, "grad_norm": 4.044918537139893, "learning_rate": 1.2330665024630544e-05, "loss": 1.0869, "step": 2497 }, { "epoch": 0.3842929118110842, "grad_norm": 4.104861259460449, "learning_rate": 1.2327586206896553e-05, "loss": 1.2735, "step": 2498 }, { "epoch": 0.38444675204799816, "grad_norm": 3.6523280143737793, "learning_rate": 1.2324507389162563e-05, "loss": 1.4151, "step": 2499 }, { "epoch": 0.3846005922849121, "grad_norm": 4.087815761566162, "learning_rate": 1.2321428571428572e-05, "loss": 1.2762, "step": 2500 }, { "epoch": 0.38475443252182606, "grad_norm": 4.089863300323486, "learning_rate": 1.2318349753694583e-05, "loss": 1.4695, "step": 2501 }, { "epoch": 0.38490827275874007, "grad_norm": 4.004120349884033, "learning_rate": 1.2315270935960592e-05, "loss": 1.3536, "step": 2502 }, { "epoch": 0.385062112995654, "grad_norm": 3.31768536567688, "learning_rate": 1.2312192118226603e-05, "loss": 1.504, "step": 2503 }, { "epoch": 0.38521595323256796, "grad_norm": 4.0671539306640625, "learning_rate": 1.2309113300492611e-05, "loss": 1.1457, "step": 2504 }, { "epoch": 0.38536979346948197, "grad_norm": 3.0047411918640137, "learning_rate": 1.2306034482758622e-05, "loss": 1.1814, "step": 2505 }, { "epoch": 0.3855236337063959, "grad_norm": 3.7352864742279053, "learning_rate": 1.2302955665024631e-05, "loss": 1.5151, "step": 2506 }, { "epoch": 0.38567747394330987, "grad_norm": 3.769263505935669, "learning_rate": 1.2299876847290642e-05, "loss": 1.2386, "step": 2507 }, { "epoch": 0.3858313141802238, "grad_norm": 3.4430925846099854, "learning_rate": 1.229679802955665e-05, "loss": 1.541, "step": 2508 }, { "epoch": 0.3859851544171378, "grad_norm": 3.621147632598877, "learning_rate": 1.2293719211822661e-05, "loss": 1.3761, "step": 2509 }, { "epoch": 0.38613899465405177, "grad_norm": 3.9197371006011963, "learning_rate": 1.229064039408867e-05, "loss": 1.3489, "step": 2510 }, { "epoch": 0.3862928348909657, "grad_norm": 3.488473892211914, "learning_rate": 1.2287561576354681e-05, "loss": 1.5501, "step": 2511 }, { "epoch": 0.3864466751278797, "grad_norm": 4.081318378448486, "learning_rate": 1.228448275862069e-05, "loss": 1.4764, "step": 2512 }, { "epoch": 0.3866005153647937, "grad_norm": 3.726106643676758, "learning_rate": 1.22814039408867e-05, "loss": 1.3491, "step": 2513 }, { "epoch": 0.3867543556017076, "grad_norm": 4.39818000793457, "learning_rate": 1.227832512315271e-05, "loss": 1.5407, "step": 2514 }, { "epoch": 0.38690819583862157, "grad_norm": 3.6024177074432373, "learning_rate": 1.227524630541872e-05, "loss": 1.338, "step": 2515 }, { "epoch": 0.3870620360755356, "grad_norm": 3.820890426635742, "learning_rate": 1.2272167487684729e-05, "loss": 1.5064, "step": 2516 }, { "epoch": 0.3872158763124495, "grad_norm": 3.0376603603363037, "learning_rate": 1.226908866995074e-05, "loss": 1.1119, "step": 2517 }, { "epoch": 0.3873697165493635, "grad_norm": 3.7203359603881836, "learning_rate": 1.2266009852216749e-05, "loss": 1.1505, "step": 2518 }, { "epoch": 0.3875235567862774, "grad_norm": 3.5354816913604736, "learning_rate": 1.226293103448276e-05, "loss": 1.4683, "step": 2519 }, { "epoch": 0.38767739702319143, "grad_norm": 3.3963613510131836, "learning_rate": 1.2259852216748768e-05, "loss": 1.2896, "step": 2520 }, { "epoch": 0.3878312372601054, "grad_norm": 3.8849618434906006, "learning_rate": 1.2256773399014779e-05, "loss": 1.1623, "step": 2521 }, { "epoch": 0.3879850774970193, "grad_norm": 3.9918339252471924, "learning_rate": 1.2253694581280788e-05, "loss": 1.1742, "step": 2522 }, { "epoch": 0.38813891773393333, "grad_norm": 3.5989620685577393, "learning_rate": 1.2250615763546798e-05, "loss": 1.6108, "step": 2523 }, { "epoch": 0.3882927579708473, "grad_norm": 4.060835838317871, "learning_rate": 1.2247536945812807e-05, "loss": 1.0881, "step": 2524 }, { "epoch": 0.38844659820776123, "grad_norm": 3.7979977130889893, "learning_rate": 1.2244458128078818e-05, "loss": 1.2355, "step": 2525 }, { "epoch": 0.3886004384446752, "grad_norm": 3.758209705352783, "learning_rate": 1.2241379310344827e-05, "loss": 1.3113, "step": 2526 }, { "epoch": 0.3887542786815892, "grad_norm": 3.274446487426758, "learning_rate": 1.223830049261084e-05, "loss": 1.283, "step": 2527 }, { "epoch": 0.38890811891850313, "grad_norm": 3.2027909755706787, "learning_rate": 1.223522167487685e-05, "loss": 1.1593, "step": 2528 }, { "epoch": 0.3890619591554171, "grad_norm": 3.410581350326538, "learning_rate": 1.2232142857142859e-05, "loss": 1.4337, "step": 2529 }, { "epoch": 0.3892157993923311, "grad_norm": 3.829186201095581, "learning_rate": 1.222906403940887e-05, "loss": 1.4709, "step": 2530 }, { "epoch": 0.38936963962924503, "grad_norm": 5.2031683921813965, "learning_rate": 1.2225985221674879e-05, "loss": 1.121, "step": 2531 }, { "epoch": 0.389523479866159, "grad_norm": 3.592776298522949, "learning_rate": 1.222290640394089e-05, "loss": 1.2232, "step": 2532 }, { "epoch": 0.38967732010307293, "grad_norm": 3.3917500972747803, "learning_rate": 1.2219827586206898e-05, "loss": 1.1676, "step": 2533 }, { "epoch": 0.38983116033998694, "grad_norm": 3.3149023056030273, "learning_rate": 1.2216748768472909e-05, "loss": 1.4321, "step": 2534 }, { "epoch": 0.3899850005769009, "grad_norm": 3.4351089000701904, "learning_rate": 1.2213669950738918e-05, "loss": 1.2273, "step": 2535 }, { "epoch": 0.39013884081381484, "grad_norm": 3.6414201259613037, "learning_rate": 1.2210591133004928e-05, "loss": 1.639, "step": 2536 }, { "epoch": 0.39029268105072884, "grad_norm": 2.980595827102661, "learning_rate": 1.2207512315270937e-05, "loss": 1.3359, "step": 2537 }, { "epoch": 0.3904465212876428, "grad_norm": 3.5816810131073, "learning_rate": 1.2204433497536948e-05, "loss": 1.3705, "step": 2538 }, { "epoch": 0.39060036152455674, "grad_norm": 3.174661159515381, "learning_rate": 1.2201354679802957e-05, "loss": 1.2351, "step": 2539 }, { "epoch": 0.3907542017614707, "grad_norm": 3.8180816173553467, "learning_rate": 1.2198275862068966e-05, "loss": 1.2042, "step": 2540 }, { "epoch": 0.3909080419983847, "grad_norm": 3.9635348320007324, "learning_rate": 1.2195197044334977e-05, "loss": 1.1897, "step": 2541 }, { "epoch": 0.39106188223529864, "grad_norm": 3.378241777420044, "learning_rate": 1.2192118226600986e-05, "loss": 1.4128, "step": 2542 }, { "epoch": 0.3912157224722126, "grad_norm": 4.133207321166992, "learning_rate": 1.2189039408866996e-05, "loss": 1.3981, "step": 2543 }, { "epoch": 0.3913695627091266, "grad_norm": 3.811264991760254, "learning_rate": 1.2185960591133005e-05, "loss": 1.275, "step": 2544 }, { "epoch": 0.39152340294604054, "grad_norm": 3.196258068084717, "learning_rate": 1.2182881773399016e-05, "loss": 1.1374, "step": 2545 }, { "epoch": 0.3916772431829545, "grad_norm": 3.3965280055999756, "learning_rate": 1.2179802955665025e-05, "loss": 1.4818, "step": 2546 }, { "epoch": 0.39183108341986844, "grad_norm": 3.8993616104125977, "learning_rate": 1.2176724137931035e-05, "loss": 1.4016, "step": 2547 }, { "epoch": 0.39198492365678245, "grad_norm": 3.2729437351226807, "learning_rate": 1.2173645320197044e-05, "loss": 1.3848, "step": 2548 }, { "epoch": 0.3921387638936964, "grad_norm": 3.7852487564086914, "learning_rate": 1.2170566502463055e-05, "loss": 1.4525, "step": 2549 }, { "epoch": 0.39229260413061035, "grad_norm": 3.5421383380889893, "learning_rate": 1.2167487684729064e-05, "loss": 1.371, "step": 2550 }, { "epoch": 0.39244644436752435, "grad_norm": 4.025891304016113, "learning_rate": 1.2164408866995075e-05, "loss": 1.1656, "step": 2551 }, { "epoch": 0.3926002846044383, "grad_norm": 4.573488235473633, "learning_rate": 1.2161330049261083e-05, "loss": 1.2932, "step": 2552 }, { "epoch": 0.39275412484135225, "grad_norm": 3.8667407035827637, "learning_rate": 1.2158251231527094e-05, "loss": 1.2484, "step": 2553 }, { "epoch": 0.3929079650782662, "grad_norm": 3.763251543045044, "learning_rate": 1.2155172413793103e-05, "loss": 1.3938, "step": 2554 }, { "epoch": 0.3930618053151802, "grad_norm": 4.093389987945557, "learning_rate": 1.2152093596059114e-05, "loss": 1.4477, "step": 2555 }, { "epoch": 0.39321564555209415, "grad_norm": 3.6935112476348877, "learning_rate": 1.2149014778325123e-05, "loss": 1.2287, "step": 2556 }, { "epoch": 0.3933694857890081, "grad_norm": 4.160289764404297, "learning_rate": 1.2145935960591133e-05, "loss": 1.4614, "step": 2557 }, { "epoch": 0.3935233260259221, "grad_norm": 4.1636199951171875, "learning_rate": 1.2142857142857142e-05, "loss": 1.5314, "step": 2558 }, { "epoch": 0.39367716626283605, "grad_norm": 4.2027268409729, "learning_rate": 1.2139778325123153e-05, "loss": 1.3076, "step": 2559 }, { "epoch": 0.39383100649975, "grad_norm": 3.9824349880218506, "learning_rate": 1.2136699507389162e-05, "loss": 1.1815, "step": 2560 }, { "epoch": 0.39398484673666395, "grad_norm": 3.388561725616455, "learning_rate": 1.2133620689655174e-05, "loss": 1.4565, "step": 2561 }, { "epoch": 0.39413868697357796, "grad_norm": 4.461021900177002, "learning_rate": 1.2130541871921185e-05, "loss": 1.4988, "step": 2562 }, { "epoch": 0.3942925272104919, "grad_norm": 4.288104057312012, "learning_rate": 1.2127463054187194e-05, "loss": 1.4714, "step": 2563 }, { "epoch": 0.39444636744740585, "grad_norm": 3.435209274291992, "learning_rate": 1.2124384236453204e-05, "loss": 1.4734, "step": 2564 }, { "epoch": 0.39460020768431986, "grad_norm": 4.607309341430664, "learning_rate": 1.2121305418719213e-05, "loss": 1.336, "step": 2565 }, { "epoch": 0.3947540479212338, "grad_norm": 3.8330817222595215, "learning_rate": 1.2118226600985224e-05, "loss": 1.3219, "step": 2566 }, { "epoch": 0.39490788815814776, "grad_norm": 3.633734941482544, "learning_rate": 1.2115147783251233e-05, "loss": 1.3268, "step": 2567 }, { "epoch": 0.3950617283950617, "grad_norm": 3.83561635017395, "learning_rate": 1.2112068965517244e-05, "loss": 1.3308, "step": 2568 }, { "epoch": 0.3952155686319757, "grad_norm": 3.2392706871032715, "learning_rate": 1.2108990147783253e-05, "loss": 1.3403, "step": 2569 }, { "epoch": 0.39536940886888966, "grad_norm": 2.9032132625579834, "learning_rate": 1.2105911330049263e-05, "loss": 1.4135, "step": 2570 }, { "epoch": 0.3955232491058036, "grad_norm": 3.7284090518951416, "learning_rate": 1.2102832512315272e-05, "loss": 1.3374, "step": 2571 }, { "epoch": 0.3956770893427176, "grad_norm": 2.879809856414795, "learning_rate": 1.2099753694581283e-05, "loss": 1.3934, "step": 2572 }, { "epoch": 0.39583092957963156, "grad_norm": 4.020562648773193, "learning_rate": 1.2096674876847292e-05, "loss": 1.4776, "step": 2573 }, { "epoch": 0.3959847698165455, "grad_norm": 3.326030969619751, "learning_rate": 1.2093596059113302e-05, "loss": 1.3162, "step": 2574 }, { "epoch": 0.39613861005345946, "grad_norm": 4.079524040222168, "learning_rate": 1.2090517241379311e-05, "loss": 1.167, "step": 2575 }, { "epoch": 0.39629245029037347, "grad_norm": 3.447927951812744, "learning_rate": 1.2087438423645322e-05, "loss": 1.4201, "step": 2576 }, { "epoch": 0.3964462905272874, "grad_norm": 3.848771572113037, "learning_rate": 1.2084359605911331e-05, "loss": 1.3433, "step": 2577 }, { "epoch": 0.39660013076420136, "grad_norm": 3.3872487545013428, "learning_rate": 1.2081280788177342e-05, "loss": 1.5197, "step": 2578 }, { "epoch": 0.39675397100111537, "grad_norm": 3.8335680961608887, "learning_rate": 1.207820197044335e-05, "loss": 1.4062, "step": 2579 }, { "epoch": 0.3969078112380293, "grad_norm": 3.317188024520874, "learning_rate": 1.2075123152709361e-05, "loss": 1.3605, "step": 2580 }, { "epoch": 0.39706165147494327, "grad_norm": 3.6295316219329834, "learning_rate": 1.207204433497537e-05, "loss": 1.1854, "step": 2581 }, { "epoch": 0.3972154917118572, "grad_norm": 3.6349246501922607, "learning_rate": 1.206896551724138e-05, "loss": 1.3331, "step": 2582 }, { "epoch": 0.3973693319487712, "grad_norm": 4.001370429992676, "learning_rate": 1.206588669950739e-05, "loss": 1.3897, "step": 2583 }, { "epoch": 0.39752317218568517, "grad_norm": 3.422581672668457, "learning_rate": 1.2062807881773399e-05, "loss": 1.1219, "step": 2584 }, { "epoch": 0.3976770124225991, "grad_norm": 4.202059268951416, "learning_rate": 1.205972906403941e-05, "loss": 1.4032, "step": 2585 }, { "epoch": 0.3978308526595131, "grad_norm": 4.108837604522705, "learning_rate": 1.2056650246305418e-05, "loss": 1.3617, "step": 2586 }, { "epoch": 0.3979846928964271, "grad_norm": 3.2718329429626465, "learning_rate": 1.2053571428571429e-05, "loss": 0.9543, "step": 2587 }, { "epoch": 0.398138533133341, "grad_norm": 3.383632183074951, "learning_rate": 1.2050492610837438e-05, "loss": 1.1991, "step": 2588 }, { "epoch": 0.39829237337025497, "grad_norm": 3.4659135341644287, "learning_rate": 1.2047413793103449e-05, "loss": 1.2981, "step": 2589 }, { "epoch": 0.398446213607169, "grad_norm": 3.822810411453247, "learning_rate": 1.2044334975369458e-05, "loss": 1.4383, "step": 2590 }, { "epoch": 0.3986000538440829, "grad_norm": 3.598536968231201, "learning_rate": 1.2041256157635468e-05, "loss": 1.2054, "step": 2591 }, { "epoch": 0.3987538940809969, "grad_norm": 4.197989463806152, "learning_rate": 1.2038177339901477e-05, "loss": 1.2068, "step": 2592 }, { "epoch": 0.3989077343179108, "grad_norm": 3.668950319290161, "learning_rate": 1.2035098522167488e-05, "loss": 1.0677, "step": 2593 }, { "epoch": 0.3990615745548248, "grad_norm": 2.996645927429199, "learning_rate": 1.2032019704433497e-05, "loss": 1.3264, "step": 2594 }, { "epoch": 0.3992154147917388, "grad_norm": 3.366743564605713, "learning_rate": 1.2028940886699509e-05, "loss": 1.3516, "step": 2595 }, { "epoch": 0.3993692550286527, "grad_norm": 3.5858750343322754, "learning_rate": 1.202586206896552e-05, "loss": 1.3593, "step": 2596 }, { "epoch": 0.39952309526556673, "grad_norm": 4.093145370483398, "learning_rate": 1.2022783251231529e-05, "loss": 1.7536, "step": 2597 }, { "epoch": 0.3996769355024807, "grad_norm": 3.5973641872406006, "learning_rate": 1.201970443349754e-05, "loss": 1.7732, "step": 2598 }, { "epoch": 0.39983077573939463, "grad_norm": 4.289833068847656, "learning_rate": 1.2016625615763548e-05, "loss": 1.4658, "step": 2599 }, { "epoch": 0.3999846159763086, "grad_norm": 3.0239968299865723, "learning_rate": 1.2013546798029559e-05, "loss": 1.3255, "step": 2600 }, { "epoch": 0.4001384562132226, "grad_norm": 4.328644275665283, "learning_rate": 1.2010467980295568e-05, "loss": 1.3851, "step": 2601 }, { "epoch": 0.40029229645013653, "grad_norm": 4.581676959991455, "learning_rate": 1.2007389162561578e-05, "loss": 1.3316, "step": 2602 }, { "epoch": 0.4004461366870505, "grad_norm": 3.2215356826782227, "learning_rate": 1.2004310344827587e-05, "loss": 1.085, "step": 2603 }, { "epoch": 0.4005999769239645, "grad_norm": 3.6783287525177, "learning_rate": 1.2001231527093598e-05, "loss": 1.2166, "step": 2604 }, { "epoch": 0.40075381716087843, "grad_norm": 3.9133107662200928, "learning_rate": 1.1998152709359607e-05, "loss": 1.5421, "step": 2605 }, { "epoch": 0.4009076573977924, "grad_norm": 3.4062929153442383, "learning_rate": 1.1995073891625618e-05, "loss": 1.3264, "step": 2606 }, { "epoch": 0.40106149763470633, "grad_norm": 4.570960521697998, "learning_rate": 1.1991995073891627e-05, "loss": 1.3675, "step": 2607 }, { "epoch": 0.40121533787162034, "grad_norm": 3.718080759048462, "learning_rate": 1.1988916256157637e-05, "loss": 1.3711, "step": 2608 }, { "epoch": 0.4013691781085343, "grad_norm": 3.4043359756469727, "learning_rate": 1.1985837438423646e-05, "loss": 1.2991, "step": 2609 }, { "epoch": 0.40152301834544823, "grad_norm": 4.0561017990112305, "learning_rate": 1.1982758620689657e-05, "loss": 1.4251, "step": 2610 }, { "epoch": 0.40167685858236224, "grad_norm": 4.1149492263793945, "learning_rate": 1.1979679802955666e-05, "loss": 1.4419, "step": 2611 }, { "epoch": 0.4018306988192762, "grad_norm": 3.4915971755981445, "learning_rate": 1.1976600985221676e-05, "loss": 1.3647, "step": 2612 }, { "epoch": 0.40198453905619014, "grad_norm": 4.655318737030029, "learning_rate": 1.1973522167487685e-05, "loss": 1.4787, "step": 2613 }, { "epoch": 0.4021383792931041, "grad_norm": 3.365931510925293, "learning_rate": 1.1970443349753696e-05, "loss": 1.2163, "step": 2614 }, { "epoch": 0.4022922195300181, "grad_norm": 3.279581069946289, "learning_rate": 1.1967364532019705e-05, "loss": 1.3485, "step": 2615 }, { "epoch": 0.40244605976693204, "grad_norm": 3.800912380218506, "learning_rate": 1.1964285714285716e-05, "loss": 1.2789, "step": 2616 }, { "epoch": 0.402599900003846, "grad_norm": 3.8149356842041016, "learning_rate": 1.1961206896551725e-05, "loss": 1.3084, "step": 2617 }, { "epoch": 0.40275374024076, "grad_norm": 3.394660234451294, "learning_rate": 1.1958128078817735e-05, "loss": 1.1881, "step": 2618 }, { "epoch": 0.40290758047767394, "grad_norm": 3.4528884887695312, "learning_rate": 1.1955049261083744e-05, "loss": 1.2639, "step": 2619 }, { "epoch": 0.4030614207145879, "grad_norm": 4.337576866149902, "learning_rate": 1.1951970443349755e-05, "loss": 1.2514, "step": 2620 }, { "epoch": 0.40321526095150184, "grad_norm": 4.160109043121338, "learning_rate": 1.1948891625615764e-05, "loss": 1.2228, "step": 2621 }, { "epoch": 0.40336910118841585, "grad_norm": 3.3700003623962402, "learning_rate": 1.1945812807881774e-05, "loss": 1.575, "step": 2622 }, { "epoch": 0.4035229414253298, "grad_norm": 3.699594736099243, "learning_rate": 1.1942733990147783e-05, "loss": 1.5031, "step": 2623 }, { "epoch": 0.40367678166224374, "grad_norm": 4.513765811920166, "learning_rate": 1.1939655172413794e-05, "loss": 1.5451, "step": 2624 }, { "epoch": 0.40383062189915775, "grad_norm": 3.64223313331604, "learning_rate": 1.1936576354679803e-05, "loss": 1.0992, "step": 2625 }, { "epoch": 0.4039844621360717, "grad_norm": 3.1511740684509277, "learning_rate": 1.1933497536945814e-05, "loss": 1.2259, "step": 2626 }, { "epoch": 0.40413830237298565, "grad_norm": 3.8288872241973877, "learning_rate": 1.1930418719211823e-05, "loss": 1.3475, "step": 2627 }, { "epoch": 0.4042921426098996, "grad_norm": 3.739227294921875, "learning_rate": 1.1927339901477832e-05, "loss": 1.5319, "step": 2628 }, { "epoch": 0.4044459828468136, "grad_norm": 3.7679266929626465, "learning_rate": 1.1924261083743844e-05, "loss": 1.2763, "step": 2629 }, { "epoch": 0.40459982308372755, "grad_norm": 3.815605640411377, "learning_rate": 1.1921182266009855e-05, "loss": 1.3646, "step": 2630 }, { "epoch": 0.4047536633206415, "grad_norm": 4.3263468742370605, "learning_rate": 1.1918103448275863e-05, "loss": 1.3768, "step": 2631 }, { "epoch": 0.4049075035575555, "grad_norm": 3.895521640777588, "learning_rate": 1.1915024630541874e-05, "loss": 1.1365, "step": 2632 }, { "epoch": 0.40506134379446945, "grad_norm": 4.289046764373779, "learning_rate": 1.1911945812807883e-05, "loss": 1.5014, "step": 2633 }, { "epoch": 0.4052151840313834, "grad_norm": 3.1686432361602783, "learning_rate": 1.1908866995073894e-05, "loss": 1.2199, "step": 2634 }, { "epoch": 0.40536902426829735, "grad_norm": 3.7674615383148193, "learning_rate": 1.1905788177339903e-05, "loss": 1.3053, "step": 2635 }, { "epoch": 0.40552286450521136, "grad_norm": 3.7035436630249023, "learning_rate": 1.1902709359605913e-05, "loss": 1.5409, "step": 2636 }, { "epoch": 0.4056767047421253, "grad_norm": 3.958827495574951, "learning_rate": 1.1899630541871922e-05, "loss": 1.2817, "step": 2637 }, { "epoch": 0.40583054497903925, "grad_norm": 3.7271673679351807, "learning_rate": 1.1896551724137933e-05, "loss": 1.5451, "step": 2638 }, { "epoch": 0.40598438521595326, "grad_norm": 3.7750470638275146, "learning_rate": 1.1893472906403942e-05, "loss": 1.2483, "step": 2639 }, { "epoch": 0.4061382254528672, "grad_norm": 4.138463973999023, "learning_rate": 1.1890394088669953e-05, "loss": 1.0887, "step": 2640 }, { "epoch": 0.40629206568978116, "grad_norm": 4.017940998077393, "learning_rate": 1.1887315270935961e-05, "loss": 1.6554, "step": 2641 }, { "epoch": 0.4064459059266951, "grad_norm": 3.3145811557769775, "learning_rate": 1.1884236453201972e-05, "loss": 1.4597, "step": 2642 }, { "epoch": 0.4065997461636091, "grad_norm": 4.029409885406494, "learning_rate": 1.1881157635467981e-05, "loss": 1.4403, "step": 2643 }, { "epoch": 0.40675358640052306, "grad_norm": 3.2496914863586426, "learning_rate": 1.1878078817733992e-05, "loss": 1.3197, "step": 2644 }, { "epoch": 0.406907426637437, "grad_norm": 3.9007668495178223, "learning_rate": 1.1875e-05, "loss": 1.5211, "step": 2645 }, { "epoch": 0.407061266874351, "grad_norm": 3.364492893218994, "learning_rate": 1.1871921182266011e-05, "loss": 1.209, "step": 2646 }, { "epoch": 0.40721510711126496, "grad_norm": 3.396493673324585, "learning_rate": 1.186884236453202e-05, "loss": 1.2478, "step": 2647 }, { "epoch": 0.4073689473481789, "grad_norm": 3.367718458175659, "learning_rate": 1.1865763546798031e-05, "loss": 1.1845, "step": 2648 }, { "epoch": 0.40752278758509286, "grad_norm": 3.626375198364258, "learning_rate": 1.186268472906404e-05, "loss": 1.2051, "step": 2649 }, { "epoch": 0.40767662782200687, "grad_norm": 3.4499266147613525, "learning_rate": 1.185960591133005e-05, "loss": 1.4099, "step": 2650 }, { "epoch": 0.4078304680589208, "grad_norm": 3.9365897178649902, "learning_rate": 1.185652709359606e-05, "loss": 1.4157, "step": 2651 }, { "epoch": 0.40798430829583476, "grad_norm": 4.187070369720459, "learning_rate": 1.185344827586207e-05, "loss": 1.2188, "step": 2652 }, { "epoch": 0.40813814853274877, "grad_norm": 3.048301935195923, "learning_rate": 1.1850369458128079e-05, "loss": 0.9064, "step": 2653 }, { "epoch": 0.4082919887696627, "grad_norm": 3.473632335662842, "learning_rate": 1.184729064039409e-05, "loss": 1.3215, "step": 2654 }, { "epoch": 0.40844582900657667, "grad_norm": 3.4247093200683594, "learning_rate": 1.1844211822660099e-05, "loss": 1.3334, "step": 2655 }, { "epoch": 0.4085996692434906, "grad_norm": 3.801255464553833, "learning_rate": 1.184113300492611e-05, "loss": 1.5391, "step": 2656 }, { "epoch": 0.4087535094804046, "grad_norm": 3.6367993354797363, "learning_rate": 1.1838054187192118e-05, "loss": 1.4053, "step": 2657 }, { "epoch": 0.40890734971731857, "grad_norm": 3.734229564666748, "learning_rate": 1.1834975369458129e-05, "loss": 1.4153, "step": 2658 }, { "epoch": 0.4090611899542325, "grad_norm": 3.290869951248169, "learning_rate": 1.1831896551724138e-05, "loss": 1.2533, "step": 2659 }, { "epoch": 0.40921503019114647, "grad_norm": 4.802485942840576, "learning_rate": 1.1828817733990148e-05, "loss": 1.0808, "step": 2660 }, { "epoch": 0.40936887042806047, "grad_norm": 4.194234848022461, "learning_rate": 1.1825738916256157e-05, "loss": 1.4699, "step": 2661 }, { "epoch": 0.4095227106649744, "grad_norm": 3.9378437995910645, "learning_rate": 1.182266009852217e-05, "loss": 1.4881, "step": 2662 }, { "epoch": 0.40967655090188837, "grad_norm": 3.6606850624084473, "learning_rate": 1.1819581280788179e-05, "loss": 1.0886, "step": 2663 }, { "epoch": 0.4098303911388024, "grad_norm": 4.475246429443359, "learning_rate": 1.181650246305419e-05, "loss": 1.1534, "step": 2664 }, { "epoch": 0.4099842313757163, "grad_norm": 3.4596669673919678, "learning_rate": 1.1813423645320198e-05, "loss": 1.3436, "step": 2665 }, { "epoch": 0.4101380716126303, "grad_norm": 3.6764307022094727, "learning_rate": 1.1810344827586209e-05, "loss": 1.1941, "step": 2666 }, { "epoch": 0.4102919118495442, "grad_norm": 3.8943169116973877, "learning_rate": 1.1807266009852218e-05, "loss": 1.3175, "step": 2667 }, { "epoch": 0.4104457520864582, "grad_norm": 3.214003562927246, "learning_rate": 1.1804187192118229e-05, "loss": 1.4679, "step": 2668 }, { "epoch": 0.4105995923233722, "grad_norm": 3.535630702972412, "learning_rate": 1.1801108374384238e-05, "loss": 1.3741, "step": 2669 }, { "epoch": 0.4107534325602861, "grad_norm": 3.785585641860962, "learning_rate": 1.1798029556650248e-05, "loss": 1.1987, "step": 2670 }, { "epoch": 0.41090727279720013, "grad_norm": 3.2741944789886475, "learning_rate": 1.1794950738916257e-05, "loss": 1.3542, "step": 2671 }, { "epoch": 0.4110611130341141, "grad_norm": 3.753436803817749, "learning_rate": 1.1791871921182268e-05, "loss": 1.2264, "step": 2672 }, { "epoch": 0.411214953271028, "grad_norm": 3.8349218368530273, "learning_rate": 1.1788793103448277e-05, "loss": 1.5893, "step": 2673 }, { "epoch": 0.411368793507942, "grad_norm": 3.5671420097351074, "learning_rate": 1.1785714285714287e-05, "loss": 1.2945, "step": 2674 }, { "epoch": 0.411522633744856, "grad_norm": 5.2349042892456055, "learning_rate": 1.1782635467980296e-05, "loss": 1.3541, "step": 2675 }, { "epoch": 0.41167647398176993, "grad_norm": 4.174690246582031, "learning_rate": 1.1779556650246307e-05, "loss": 1.5086, "step": 2676 }, { "epoch": 0.4118303142186839, "grad_norm": 3.867372751235962, "learning_rate": 1.1776477832512316e-05, "loss": 1.5645, "step": 2677 }, { "epoch": 0.4119841544555979, "grad_norm": 3.456388235092163, "learning_rate": 1.1773399014778327e-05, "loss": 1.5595, "step": 2678 }, { "epoch": 0.41213799469251183, "grad_norm": 3.002079963684082, "learning_rate": 1.1770320197044335e-05, "loss": 1.5802, "step": 2679 }, { "epoch": 0.4122918349294258, "grad_norm": 3.1031582355499268, "learning_rate": 1.1767241379310346e-05, "loss": 1.5051, "step": 2680 }, { "epoch": 0.41244567516633973, "grad_norm": 4.553328514099121, "learning_rate": 1.1764162561576355e-05, "loss": 1.4553, "step": 2681 }, { "epoch": 0.41259951540325374, "grad_norm": 3.674499273300171, "learning_rate": 1.1761083743842366e-05, "loss": 1.5158, "step": 2682 }, { "epoch": 0.4127533556401677, "grad_norm": 3.4379630088806152, "learning_rate": 1.1758004926108375e-05, "loss": 1.329, "step": 2683 }, { "epoch": 0.41290719587708163, "grad_norm": 3.4743902683258057, "learning_rate": 1.1754926108374385e-05, "loss": 1.1464, "step": 2684 }, { "epoch": 0.41306103611399564, "grad_norm": 4.038331985473633, "learning_rate": 1.1751847290640394e-05, "loss": 1.196, "step": 2685 }, { "epoch": 0.4132148763509096, "grad_norm": 3.262916326522827, "learning_rate": 1.1748768472906405e-05, "loss": 1.5289, "step": 2686 }, { "epoch": 0.41336871658782354, "grad_norm": 3.607856512069702, "learning_rate": 1.1745689655172414e-05, "loss": 1.3595, "step": 2687 }, { "epoch": 0.4135225568247375, "grad_norm": 3.8900983333587646, "learning_rate": 1.1742610837438425e-05, "loss": 1.5261, "step": 2688 }, { "epoch": 0.4136763970616515, "grad_norm": 3.337707996368408, "learning_rate": 1.1739532019704433e-05, "loss": 1.4905, "step": 2689 }, { "epoch": 0.41383023729856544, "grad_norm": 3.8576109409332275, "learning_rate": 1.1736453201970444e-05, "loss": 1.5143, "step": 2690 }, { "epoch": 0.4139840775354794, "grad_norm": 3.4091227054595947, "learning_rate": 1.1733374384236453e-05, "loss": 1.105, "step": 2691 }, { "epoch": 0.4141379177723934, "grad_norm": 3.7472989559173584, "learning_rate": 1.1730295566502464e-05, "loss": 1.332, "step": 2692 }, { "epoch": 0.41429175800930734, "grad_norm": 3.4136481285095215, "learning_rate": 1.1727216748768473e-05, "loss": 1.243, "step": 2693 }, { "epoch": 0.4144455982462213, "grad_norm": 3.75655198097229, "learning_rate": 1.1724137931034483e-05, "loss": 1.2905, "step": 2694 }, { "epoch": 0.41459943848313524, "grad_norm": 3.412562131881714, "learning_rate": 1.1721059113300492e-05, "loss": 1.2876, "step": 2695 }, { "epoch": 0.41475327872004925, "grad_norm": 4.470505714416504, "learning_rate": 1.1717980295566505e-05, "loss": 1.3419, "step": 2696 }, { "epoch": 0.4149071189569632, "grad_norm": 3.475151300430298, "learning_rate": 1.1714901477832514e-05, "loss": 1.7173, "step": 2697 }, { "epoch": 0.41506095919387714, "grad_norm": 3.7724814414978027, "learning_rate": 1.1711822660098524e-05, "loss": 1.4649, "step": 2698 }, { "epoch": 0.41521479943079115, "grad_norm": 3.3223371505737305, "learning_rate": 1.1708743842364533e-05, "loss": 1.4632, "step": 2699 }, { "epoch": 0.4153686396677051, "grad_norm": 3.759002447128296, "learning_rate": 1.1705665024630544e-05, "loss": 1.3236, "step": 2700 }, { "epoch": 0.41552247990461905, "grad_norm": 3.2495224475860596, "learning_rate": 1.1702586206896553e-05, "loss": 1.2995, "step": 2701 }, { "epoch": 0.415676320141533, "grad_norm": 3.970095157623291, "learning_rate": 1.1699507389162563e-05, "loss": 1.5369, "step": 2702 }, { "epoch": 0.415830160378447, "grad_norm": 4.061479568481445, "learning_rate": 1.1696428571428572e-05, "loss": 1.1931, "step": 2703 }, { "epoch": 0.41598400061536095, "grad_norm": 3.30692458152771, "learning_rate": 1.1693349753694583e-05, "loss": 1.4555, "step": 2704 }, { "epoch": 0.4161378408522749, "grad_norm": 3.8379969596862793, "learning_rate": 1.1690270935960592e-05, "loss": 1.2926, "step": 2705 }, { "epoch": 0.4162916810891889, "grad_norm": 4.019631385803223, "learning_rate": 1.1687192118226603e-05, "loss": 1.1755, "step": 2706 }, { "epoch": 0.41644552132610285, "grad_norm": 3.246554136276245, "learning_rate": 1.1684113300492612e-05, "loss": 1.4, "step": 2707 }, { "epoch": 0.4165993615630168, "grad_norm": 3.309922456741333, "learning_rate": 1.1681034482758622e-05, "loss": 1.3903, "step": 2708 }, { "epoch": 0.41675320179993075, "grad_norm": 3.599820852279663, "learning_rate": 1.1677955665024631e-05, "loss": 1.3917, "step": 2709 }, { "epoch": 0.41690704203684475, "grad_norm": 4.172718524932861, "learning_rate": 1.1674876847290642e-05, "loss": 1.4707, "step": 2710 }, { "epoch": 0.4170608822737587, "grad_norm": 4.247345924377441, "learning_rate": 1.167179802955665e-05, "loss": 1.4263, "step": 2711 }, { "epoch": 0.41721472251067265, "grad_norm": 4.635224342346191, "learning_rate": 1.1668719211822661e-05, "loss": 1.4324, "step": 2712 }, { "epoch": 0.41736856274758666, "grad_norm": 3.136453866958618, "learning_rate": 1.166564039408867e-05, "loss": 1.334, "step": 2713 }, { "epoch": 0.4175224029845006, "grad_norm": 3.6523382663726807, "learning_rate": 1.1662561576354681e-05, "loss": 1.387, "step": 2714 }, { "epoch": 0.41767624322141456, "grad_norm": 4.040719032287598, "learning_rate": 1.165948275862069e-05, "loss": 1.455, "step": 2715 }, { "epoch": 0.4178300834583285, "grad_norm": 3.5009653568267822, "learning_rate": 1.16564039408867e-05, "loss": 1.1176, "step": 2716 }, { "epoch": 0.4179839236952425, "grad_norm": 3.577908754348755, "learning_rate": 1.165332512315271e-05, "loss": 1.6231, "step": 2717 }, { "epoch": 0.41813776393215646, "grad_norm": 3.0234251022338867, "learning_rate": 1.165024630541872e-05, "loss": 0.9262, "step": 2718 }, { "epoch": 0.4182916041690704, "grad_norm": 3.6130447387695312, "learning_rate": 1.1647167487684729e-05, "loss": 1.3082, "step": 2719 }, { "epoch": 0.4184454444059844, "grad_norm": 3.3768255710601807, "learning_rate": 1.164408866995074e-05, "loss": 1.3133, "step": 2720 }, { "epoch": 0.41859928464289836, "grad_norm": 3.9348926544189453, "learning_rate": 1.1641009852216749e-05, "loss": 1.1996, "step": 2721 }, { "epoch": 0.4187531248798123, "grad_norm": 3.403130531311035, "learning_rate": 1.163793103448276e-05, "loss": 1.4462, "step": 2722 }, { "epoch": 0.41890696511672626, "grad_norm": 3.3778350353240967, "learning_rate": 1.1634852216748768e-05, "loss": 1.3054, "step": 2723 }, { "epoch": 0.41906080535364026, "grad_norm": 4.233469009399414, "learning_rate": 1.1631773399014779e-05, "loss": 1.1495, "step": 2724 }, { "epoch": 0.4192146455905542, "grad_norm": 3.591193199157715, "learning_rate": 1.1628694581280788e-05, "loss": 1.3647, "step": 2725 }, { "epoch": 0.41936848582746816, "grad_norm": 2.924799680709839, "learning_rate": 1.1625615763546799e-05, "loss": 1.2099, "step": 2726 }, { "epoch": 0.4195223260643821, "grad_norm": 3.4914355278015137, "learning_rate": 1.1622536945812807e-05, "loss": 1.2813, "step": 2727 }, { "epoch": 0.4196761663012961, "grad_norm": 3.5312883853912354, "learning_rate": 1.1619458128078818e-05, "loss": 1.3969, "step": 2728 }, { "epoch": 0.41983000653821007, "grad_norm": 3.8190793991088867, "learning_rate": 1.1616379310344827e-05, "loss": 1.2067, "step": 2729 }, { "epoch": 0.419983846775124, "grad_norm": 3.22216796875, "learning_rate": 1.161330049261084e-05, "loss": 1.2905, "step": 2730 }, { "epoch": 0.420137687012038, "grad_norm": 3.841982126235962, "learning_rate": 1.161022167487685e-05, "loss": 1.3353, "step": 2731 }, { "epoch": 0.42029152724895197, "grad_norm": 3.987891435623169, "learning_rate": 1.1607142857142859e-05, "loss": 1.3059, "step": 2732 }, { "epoch": 0.4204453674858659, "grad_norm": 3.62908673286438, "learning_rate": 1.160406403940887e-05, "loss": 1.1733, "step": 2733 }, { "epoch": 0.42059920772277987, "grad_norm": 3.4038641452789307, "learning_rate": 1.1600985221674879e-05, "loss": 1.3527, "step": 2734 }, { "epoch": 0.42075304795969387, "grad_norm": 3.917527914047241, "learning_rate": 1.1597906403940888e-05, "loss": 1.0086, "step": 2735 }, { "epoch": 0.4209068881966078, "grad_norm": 4.156436920166016, "learning_rate": 1.1594827586206898e-05, "loss": 1.3134, "step": 2736 }, { "epoch": 0.42106072843352177, "grad_norm": 3.198888063430786, "learning_rate": 1.1591748768472907e-05, "loss": 1.3617, "step": 2737 }, { "epoch": 0.4212145686704358, "grad_norm": 3.754054307937622, "learning_rate": 1.1588669950738918e-05, "loss": 1.3451, "step": 2738 }, { "epoch": 0.4213684089073497, "grad_norm": 3.59293794631958, "learning_rate": 1.1585591133004927e-05, "loss": 1.3793, "step": 2739 }, { "epoch": 0.42152224914426367, "grad_norm": 3.11907696723938, "learning_rate": 1.1582512315270937e-05, "loss": 1.3396, "step": 2740 }, { "epoch": 0.4216760893811776, "grad_norm": 3.9743075370788574, "learning_rate": 1.1579433497536946e-05, "loss": 1.4826, "step": 2741 }, { "epoch": 0.4218299296180916, "grad_norm": 4.07059383392334, "learning_rate": 1.1576354679802957e-05, "loss": 1.1806, "step": 2742 }, { "epoch": 0.4219837698550056, "grad_norm": 3.4909284114837646, "learning_rate": 1.1573275862068966e-05, "loss": 1.4722, "step": 2743 }, { "epoch": 0.4221376100919195, "grad_norm": 3.417750120162964, "learning_rate": 1.1570197044334977e-05, "loss": 1.4839, "step": 2744 }, { "epoch": 0.42229145032883353, "grad_norm": 3.691490888595581, "learning_rate": 1.1567118226600986e-05, "loss": 1.1769, "step": 2745 }, { "epoch": 0.4224452905657475, "grad_norm": 3.6626415252685547, "learning_rate": 1.1564039408866996e-05, "loss": 1.2778, "step": 2746 }, { "epoch": 0.4225991308026614, "grad_norm": 3.145789384841919, "learning_rate": 1.1560960591133005e-05, "loss": 1.2325, "step": 2747 }, { "epoch": 0.4227529710395754, "grad_norm": 3.7511537075042725, "learning_rate": 1.1557881773399016e-05, "loss": 1.3038, "step": 2748 }, { "epoch": 0.4229068112764894, "grad_norm": 3.355536937713623, "learning_rate": 1.1554802955665025e-05, "loss": 1.3554, "step": 2749 }, { "epoch": 0.42306065151340333, "grad_norm": 3.2702863216400146, "learning_rate": 1.1551724137931035e-05, "loss": 1.3804, "step": 2750 }, { "epoch": 0.4232144917503173, "grad_norm": 3.4387385845184326, "learning_rate": 1.1548645320197044e-05, "loss": 1.3663, "step": 2751 }, { "epoch": 0.4233683319872313, "grad_norm": 3.176652669906616, "learning_rate": 1.1545566502463055e-05, "loss": 1.3893, "step": 2752 }, { "epoch": 0.42352217222414523, "grad_norm": 3.2557179927825928, "learning_rate": 1.1542487684729064e-05, "loss": 1.5369, "step": 2753 }, { "epoch": 0.4236760124610592, "grad_norm": 3.3345868587493896, "learning_rate": 1.1539408866995075e-05, "loss": 1.2419, "step": 2754 }, { "epoch": 0.42382985269797313, "grad_norm": 3.922175884246826, "learning_rate": 1.1536330049261084e-05, "loss": 1.2338, "step": 2755 }, { "epoch": 0.42398369293488714, "grad_norm": 4.293175220489502, "learning_rate": 1.1533251231527094e-05, "loss": 1.2158, "step": 2756 }, { "epoch": 0.4241375331718011, "grad_norm": 4.6851277351379395, "learning_rate": 1.1530172413793103e-05, "loss": 1.5734, "step": 2757 }, { "epoch": 0.42429137340871503, "grad_norm": 3.1505556106567383, "learning_rate": 1.1527093596059114e-05, "loss": 1.4219, "step": 2758 }, { "epoch": 0.42444521364562904, "grad_norm": 3.7167747020721436, "learning_rate": 1.1524014778325123e-05, "loss": 1.1321, "step": 2759 }, { "epoch": 0.424599053882543, "grad_norm": 4.245323657989502, "learning_rate": 1.1520935960591133e-05, "loss": 1.3593, "step": 2760 }, { "epoch": 0.42475289411945694, "grad_norm": 4.040613174438477, "learning_rate": 1.1517857142857142e-05, "loss": 1.1045, "step": 2761 }, { "epoch": 0.4249067343563709, "grad_norm": 3.9247262477874756, "learning_rate": 1.1514778325123153e-05, "loss": 1.4427, "step": 2762 }, { "epoch": 0.4250605745932849, "grad_norm": 3.6406030654907227, "learning_rate": 1.1511699507389162e-05, "loss": 1.2915, "step": 2763 }, { "epoch": 0.42521441483019884, "grad_norm": 4.025470733642578, "learning_rate": 1.1508620689655174e-05, "loss": 1.3856, "step": 2764 }, { "epoch": 0.4253682550671128, "grad_norm": 3.7868454456329346, "learning_rate": 1.1505541871921185e-05, "loss": 1.6579, "step": 2765 }, { "epoch": 0.4255220953040268, "grad_norm": 3.3589019775390625, "learning_rate": 1.1502463054187194e-05, "loss": 1.5582, "step": 2766 }, { "epoch": 0.42567593554094074, "grad_norm": 3.572655439376831, "learning_rate": 1.1499384236453205e-05, "loss": 1.6051, "step": 2767 }, { "epoch": 0.4258297757778547, "grad_norm": 3.4362854957580566, "learning_rate": 1.1496305418719213e-05, "loss": 1.4058, "step": 2768 }, { "epoch": 0.42598361601476864, "grad_norm": 2.8669755458831787, "learning_rate": 1.1493226600985224e-05, "loss": 1.2155, "step": 2769 }, { "epoch": 0.42613745625168264, "grad_norm": 3.638023614883423, "learning_rate": 1.1490147783251233e-05, "loss": 1.3142, "step": 2770 }, { "epoch": 0.4262912964885966, "grad_norm": 3.717529773712158, "learning_rate": 1.1487068965517244e-05, "loss": 1.2889, "step": 2771 }, { "epoch": 0.42644513672551054, "grad_norm": 3.5954573154449463, "learning_rate": 1.1483990147783253e-05, "loss": 1.4403, "step": 2772 }, { "epoch": 0.42659897696242455, "grad_norm": 4.164998531341553, "learning_rate": 1.1480911330049263e-05, "loss": 1.4565, "step": 2773 }, { "epoch": 0.4267528171993385, "grad_norm": 3.182495355606079, "learning_rate": 1.1477832512315272e-05, "loss": 1.3094, "step": 2774 }, { "epoch": 0.42690665743625245, "grad_norm": 3.0814733505249023, "learning_rate": 1.1474753694581283e-05, "loss": 1.4342, "step": 2775 }, { "epoch": 0.4270604976731664, "grad_norm": 3.89493727684021, "learning_rate": 1.1471674876847292e-05, "loss": 1.0954, "step": 2776 }, { "epoch": 0.4272143379100804, "grad_norm": 3.215125322341919, "learning_rate": 1.1468596059113302e-05, "loss": 1.4298, "step": 2777 }, { "epoch": 0.42736817814699435, "grad_norm": 4.759877681732178, "learning_rate": 1.1465517241379311e-05, "loss": 1.2071, "step": 2778 }, { "epoch": 0.4275220183839083, "grad_norm": 3.4476144313812256, "learning_rate": 1.146243842364532e-05, "loss": 1.3901, "step": 2779 }, { "epoch": 0.4276758586208223, "grad_norm": 4.188092231750488, "learning_rate": 1.1459359605911331e-05, "loss": 1.424, "step": 2780 }, { "epoch": 0.42782969885773625, "grad_norm": 3.575876235961914, "learning_rate": 1.145628078817734e-05, "loss": 1.4344, "step": 2781 }, { "epoch": 0.4279835390946502, "grad_norm": 3.2272121906280518, "learning_rate": 1.145320197044335e-05, "loss": 1.2427, "step": 2782 }, { "epoch": 0.42813737933156415, "grad_norm": 3.917387008666992, "learning_rate": 1.145012315270936e-05, "loss": 1.2252, "step": 2783 }, { "epoch": 0.42829121956847815, "grad_norm": 4.102906227111816, "learning_rate": 1.144704433497537e-05, "loss": 1.3457, "step": 2784 }, { "epoch": 0.4284450598053921, "grad_norm": 4.02213716506958, "learning_rate": 1.144396551724138e-05, "loss": 1.5955, "step": 2785 }, { "epoch": 0.42859890004230605, "grad_norm": 3.871583938598633, "learning_rate": 1.144088669950739e-05, "loss": 1.2465, "step": 2786 }, { "epoch": 0.42875274027922006, "grad_norm": 3.3546833992004395, "learning_rate": 1.1437807881773399e-05, "loss": 1.3967, "step": 2787 }, { "epoch": 0.428906580516134, "grad_norm": 4.247845649719238, "learning_rate": 1.143472906403941e-05, "loss": 1.386, "step": 2788 }, { "epoch": 0.42906042075304796, "grad_norm": 4.192868232727051, "learning_rate": 1.1431650246305418e-05, "loss": 1.4644, "step": 2789 }, { "epoch": 0.4292142609899619, "grad_norm": 3.9590063095092773, "learning_rate": 1.1428571428571429e-05, "loss": 1.3626, "step": 2790 }, { "epoch": 0.4293681012268759, "grad_norm": 3.484983205795288, "learning_rate": 1.1425492610837438e-05, "loss": 1.3868, "step": 2791 }, { "epoch": 0.42952194146378986, "grad_norm": 3.529444932937622, "learning_rate": 1.1422413793103449e-05, "loss": 1.2091, "step": 2792 }, { "epoch": 0.4296757817007038, "grad_norm": 3.946737289428711, "learning_rate": 1.1419334975369458e-05, "loss": 1.5207, "step": 2793 }, { "epoch": 0.42982962193761776, "grad_norm": 3.7436165809631348, "learning_rate": 1.1416256157635468e-05, "loss": 1.2217, "step": 2794 }, { "epoch": 0.42998346217453176, "grad_norm": 3.30067777633667, "learning_rate": 1.1413177339901477e-05, "loss": 1.2328, "step": 2795 }, { "epoch": 0.4301373024114457, "grad_norm": 3.883223056793213, "learning_rate": 1.1410098522167488e-05, "loss": 1.2515, "step": 2796 }, { "epoch": 0.43029114264835966, "grad_norm": 3.4414637088775635, "learning_rate": 1.1407019704433497e-05, "loss": 1.38, "step": 2797 }, { "epoch": 0.43044498288527366, "grad_norm": 3.501282215118408, "learning_rate": 1.1403940886699509e-05, "loss": 1.1867, "step": 2798 }, { "epoch": 0.4305988231221876, "grad_norm": 3.6516177654266357, "learning_rate": 1.140086206896552e-05, "loss": 1.5395, "step": 2799 }, { "epoch": 0.43075266335910156, "grad_norm": 4.522702693939209, "learning_rate": 1.1397783251231529e-05, "loss": 1.234, "step": 2800 }, { "epoch": 0.4309065035960155, "grad_norm": 4.032157897949219, "learning_rate": 1.139470443349754e-05, "loss": 1.4483, "step": 2801 }, { "epoch": 0.4310603438329295, "grad_norm": 3.6673455238342285, "learning_rate": 1.1391625615763548e-05, "loss": 1.5807, "step": 2802 }, { "epoch": 0.43121418406984346, "grad_norm": 4.038232326507568, "learning_rate": 1.1388546798029559e-05, "loss": 1.3402, "step": 2803 }, { "epoch": 0.4313680243067574, "grad_norm": 3.1752076148986816, "learning_rate": 1.1385467980295568e-05, "loss": 1.3286, "step": 2804 }, { "epoch": 0.4315218645436714, "grad_norm": 3.4857676029205322, "learning_rate": 1.1382389162561579e-05, "loss": 1.3385, "step": 2805 }, { "epoch": 0.43167570478058537, "grad_norm": 3.795988082885742, "learning_rate": 1.1379310344827587e-05, "loss": 1.42, "step": 2806 }, { "epoch": 0.4318295450174993, "grad_norm": 2.8590409755706787, "learning_rate": 1.1376231527093598e-05, "loss": 1.2313, "step": 2807 }, { "epoch": 0.43198338525441327, "grad_norm": 3.8475489616394043, "learning_rate": 1.1373152709359607e-05, "loss": 1.4213, "step": 2808 }, { "epoch": 0.43213722549132727, "grad_norm": 3.387155771255493, "learning_rate": 1.1370073891625618e-05, "loss": 1.4399, "step": 2809 }, { "epoch": 0.4322910657282412, "grad_norm": 3.655609130859375, "learning_rate": 1.1366995073891627e-05, "loss": 1.2688, "step": 2810 }, { "epoch": 0.43244490596515517, "grad_norm": 3.8140976428985596, "learning_rate": 1.1363916256157637e-05, "loss": 1.593, "step": 2811 }, { "epoch": 0.4325987462020692, "grad_norm": 4.750949382781982, "learning_rate": 1.1360837438423646e-05, "loss": 1.1874, "step": 2812 }, { "epoch": 0.4327525864389831, "grad_norm": 3.284365653991699, "learning_rate": 1.1357758620689657e-05, "loss": 1.1894, "step": 2813 }, { "epoch": 0.43290642667589707, "grad_norm": 3.5676097869873047, "learning_rate": 1.1354679802955666e-05, "loss": 1.2111, "step": 2814 }, { "epoch": 0.433060266912811, "grad_norm": 4.284585952758789, "learning_rate": 1.1351600985221677e-05, "loss": 1.241, "step": 2815 }, { "epoch": 0.433214107149725, "grad_norm": 3.7175090312957764, "learning_rate": 1.1348522167487685e-05, "loss": 1.2968, "step": 2816 }, { "epoch": 0.433367947386639, "grad_norm": 3.8177056312561035, "learning_rate": 1.1345443349753696e-05, "loss": 1.5141, "step": 2817 }, { "epoch": 0.4335217876235529, "grad_norm": 3.327308416366577, "learning_rate": 1.1342364532019705e-05, "loss": 1.2483, "step": 2818 }, { "epoch": 0.43367562786046693, "grad_norm": 3.4665369987487793, "learning_rate": 1.1339285714285716e-05, "loss": 1.4549, "step": 2819 }, { "epoch": 0.4338294680973809, "grad_norm": 3.765531063079834, "learning_rate": 1.1336206896551725e-05, "loss": 1.3685, "step": 2820 }, { "epoch": 0.4339833083342948, "grad_norm": 4.597011566162109, "learning_rate": 1.1333128078817735e-05, "loss": 1.1993, "step": 2821 }, { "epoch": 0.4341371485712088, "grad_norm": 3.7644309997558594, "learning_rate": 1.1330049261083744e-05, "loss": 1.1248, "step": 2822 }, { "epoch": 0.4342909888081228, "grad_norm": 3.3510284423828125, "learning_rate": 1.1326970443349753e-05, "loss": 1.3636, "step": 2823 }, { "epoch": 0.43444482904503673, "grad_norm": 3.625579595565796, "learning_rate": 1.1323891625615764e-05, "loss": 1.3858, "step": 2824 }, { "epoch": 0.4345986692819507, "grad_norm": 3.490809440612793, "learning_rate": 1.1320812807881773e-05, "loss": 1.0887, "step": 2825 }, { "epoch": 0.4347525095188647, "grad_norm": 3.2280144691467285, "learning_rate": 1.1317733990147783e-05, "loss": 1.2997, "step": 2826 }, { "epoch": 0.43490634975577863, "grad_norm": 3.271505832672119, "learning_rate": 1.1314655172413792e-05, "loss": 0.9627, "step": 2827 }, { "epoch": 0.4350601899926926, "grad_norm": 3.384744882583618, "learning_rate": 1.1311576354679803e-05, "loss": 1.3659, "step": 2828 }, { "epoch": 0.43521403022960653, "grad_norm": 4.559953689575195, "learning_rate": 1.1308497536945812e-05, "loss": 1.2747, "step": 2829 }, { "epoch": 0.43536787046652053, "grad_norm": 3.622725009918213, "learning_rate": 1.1305418719211823e-05, "loss": 1.3154, "step": 2830 }, { "epoch": 0.4355217107034345, "grad_norm": 3.4873688220977783, "learning_rate": 1.1302339901477832e-05, "loss": 1.2502, "step": 2831 }, { "epoch": 0.43567555094034843, "grad_norm": 3.6088244915008545, "learning_rate": 1.1299261083743844e-05, "loss": 1.2765, "step": 2832 }, { "epoch": 0.43582939117726244, "grad_norm": 4.015312671661377, "learning_rate": 1.1296182266009855e-05, "loss": 1.1124, "step": 2833 }, { "epoch": 0.4359832314141764, "grad_norm": 3.365811347961426, "learning_rate": 1.1293103448275864e-05, "loss": 1.4141, "step": 2834 }, { "epoch": 0.43613707165109034, "grad_norm": 3.5250132083892822, "learning_rate": 1.1290024630541874e-05, "loss": 1.2027, "step": 2835 }, { "epoch": 0.4362909118880043, "grad_norm": 3.6314828395843506, "learning_rate": 1.1286945812807883e-05, "loss": 1.4016, "step": 2836 }, { "epoch": 0.4364447521249183, "grad_norm": 3.8920419216156006, "learning_rate": 1.1283866995073894e-05, "loss": 1.3559, "step": 2837 }, { "epoch": 0.43659859236183224, "grad_norm": 3.828662157058716, "learning_rate": 1.1280788177339903e-05, "loss": 1.2853, "step": 2838 }, { "epoch": 0.4367524325987462, "grad_norm": 3.6039440631866455, "learning_rate": 1.1277709359605913e-05, "loss": 1.2799, "step": 2839 }, { "epoch": 0.4369062728356602, "grad_norm": 3.492359161376953, "learning_rate": 1.1274630541871922e-05, "loss": 1.3342, "step": 2840 }, { "epoch": 0.43706011307257414, "grad_norm": 4.018831729888916, "learning_rate": 1.1271551724137933e-05, "loss": 1.4051, "step": 2841 }, { "epoch": 0.4372139533094881, "grad_norm": 3.883441209793091, "learning_rate": 1.1268472906403942e-05, "loss": 1.3912, "step": 2842 }, { "epoch": 0.43736779354640204, "grad_norm": 4.3098859786987305, "learning_rate": 1.1265394088669953e-05, "loss": 1.3891, "step": 2843 }, { "epoch": 0.43752163378331604, "grad_norm": 4.769084930419922, "learning_rate": 1.1262315270935962e-05, "loss": 1.3245, "step": 2844 }, { "epoch": 0.43767547402023, "grad_norm": 3.4285919666290283, "learning_rate": 1.1259236453201972e-05, "loss": 1.3444, "step": 2845 }, { "epoch": 0.43782931425714394, "grad_norm": 3.591118812561035, "learning_rate": 1.1256157635467981e-05, "loss": 1.3673, "step": 2846 }, { "epoch": 0.43798315449405795, "grad_norm": 4.497280597686768, "learning_rate": 1.1253078817733992e-05, "loss": 1.4274, "step": 2847 }, { "epoch": 0.4381369947309719, "grad_norm": 3.9309608936309814, "learning_rate": 1.125e-05, "loss": 1.3754, "step": 2848 }, { "epoch": 0.43829083496788585, "grad_norm": 3.10937762260437, "learning_rate": 1.1246921182266011e-05, "loss": 1.2624, "step": 2849 }, { "epoch": 0.4384446752047998, "grad_norm": 3.552839517593384, "learning_rate": 1.124384236453202e-05, "loss": 1.334, "step": 2850 }, { "epoch": 0.4385985154417138, "grad_norm": 3.430114269256592, "learning_rate": 1.1240763546798031e-05, "loss": 1.4313, "step": 2851 }, { "epoch": 0.43875235567862775, "grad_norm": 3.4754252433776855, "learning_rate": 1.123768472906404e-05, "loss": 1.5305, "step": 2852 }, { "epoch": 0.4389061959155417, "grad_norm": 3.9245049953460693, "learning_rate": 1.123460591133005e-05, "loss": 1.444, "step": 2853 }, { "epoch": 0.4390600361524557, "grad_norm": 3.1495041847229004, "learning_rate": 1.123152709359606e-05, "loss": 1.1605, "step": 2854 }, { "epoch": 0.43921387638936965, "grad_norm": 3.0807228088378906, "learning_rate": 1.122844827586207e-05, "loss": 1.2037, "step": 2855 }, { "epoch": 0.4393677166262836, "grad_norm": 3.1352736949920654, "learning_rate": 1.1225369458128079e-05, "loss": 1.1454, "step": 2856 }, { "epoch": 0.43952155686319755, "grad_norm": 3.513258695602417, "learning_rate": 1.122229064039409e-05, "loss": 1.3853, "step": 2857 }, { "epoch": 0.43967539710011155, "grad_norm": 3.299225091934204, "learning_rate": 1.1219211822660099e-05, "loss": 1.1706, "step": 2858 }, { "epoch": 0.4398292373370255, "grad_norm": 3.6430349349975586, "learning_rate": 1.121613300492611e-05, "loss": 1.4117, "step": 2859 }, { "epoch": 0.43998307757393945, "grad_norm": 3.9998228549957275, "learning_rate": 1.1213054187192118e-05, "loss": 1.461, "step": 2860 }, { "epoch": 0.44013691781085346, "grad_norm": 3.4214584827423096, "learning_rate": 1.1209975369458129e-05, "loss": 1.4824, "step": 2861 }, { "epoch": 0.4402907580477674, "grad_norm": 3.5498366355895996, "learning_rate": 1.1206896551724138e-05, "loss": 1.5052, "step": 2862 }, { "epoch": 0.44044459828468135, "grad_norm": 3.627943277359009, "learning_rate": 1.1203817733990149e-05, "loss": 1.3785, "step": 2863 }, { "epoch": 0.4405984385215953, "grad_norm": 4.636753082275391, "learning_rate": 1.1200738916256157e-05, "loss": 1.3379, "step": 2864 }, { "epoch": 0.4407522787585093, "grad_norm": 3.083212375640869, "learning_rate": 1.119766009852217e-05, "loss": 1.2926, "step": 2865 }, { "epoch": 0.44090611899542326, "grad_norm": 3.8892221450805664, "learning_rate": 1.1194581280788179e-05, "loss": 1.1736, "step": 2866 }, { "epoch": 0.4410599592323372, "grad_norm": 3.391965627670288, "learning_rate": 1.119150246305419e-05, "loss": 1.2928, "step": 2867 }, { "epoch": 0.44121379946925116, "grad_norm": 3.5357131958007812, "learning_rate": 1.1188423645320198e-05, "loss": 1.3916, "step": 2868 }, { "epoch": 0.44136763970616516, "grad_norm": 3.535108804702759, "learning_rate": 1.1185344827586209e-05, "loss": 1.0665, "step": 2869 }, { "epoch": 0.4415214799430791, "grad_norm": 2.7913308143615723, "learning_rate": 1.1182266009852218e-05, "loss": 1.2159, "step": 2870 }, { "epoch": 0.44167532017999306, "grad_norm": 3.9281723499298096, "learning_rate": 1.1179187192118229e-05, "loss": 1.1789, "step": 2871 }, { "epoch": 0.44182916041690706, "grad_norm": 3.71431040763855, "learning_rate": 1.1176108374384238e-05, "loss": 1.7108, "step": 2872 }, { "epoch": 0.441983000653821, "grad_norm": 4.172939300537109, "learning_rate": 1.1173029556650248e-05, "loss": 1.4722, "step": 2873 }, { "epoch": 0.44213684089073496, "grad_norm": 3.364716053009033, "learning_rate": 1.1169950738916257e-05, "loss": 1.2073, "step": 2874 }, { "epoch": 0.4422906811276489, "grad_norm": 3.3506669998168945, "learning_rate": 1.1166871921182268e-05, "loss": 1.088, "step": 2875 }, { "epoch": 0.4424445213645629, "grad_norm": 3.3794045448303223, "learning_rate": 1.1163793103448277e-05, "loss": 1.4799, "step": 2876 }, { "epoch": 0.44259836160147686, "grad_norm": 3.930748224258423, "learning_rate": 1.1160714285714287e-05, "loss": 1.469, "step": 2877 }, { "epoch": 0.4427522018383908, "grad_norm": 3.9974405765533447, "learning_rate": 1.1157635467980296e-05, "loss": 1.3784, "step": 2878 }, { "epoch": 0.4429060420753048, "grad_norm": 4.825000762939453, "learning_rate": 1.1154556650246307e-05, "loss": 1.3427, "step": 2879 }, { "epoch": 0.44305988231221877, "grad_norm": 4.0307416915893555, "learning_rate": 1.1151477832512316e-05, "loss": 1.2299, "step": 2880 }, { "epoch": 0.4432137225491327, "grad_norm": 3.518789529800415, "learning_rate": 1.1148399014778327e-05, "loss": 1.4506, "step": 2881 }, { "epoch": 0.44336756278604667, "grad_norm": 4.1243791580200195, "learning_rate": 1.1145320197044336e-05, "loss": 1.4458, "step": 2882 }, { "epoch": 0.44352140302296067, "grad_norm": 3.6561474800109863, "learning_rate": 1.1142241379310346e-05, "loss": 1.1636, "step": 2883 }, { "epoch": 0.4436752432598746, "grad_norm": 3.1474902629852295, "learning_rate": 1.1139162561576355e-05, "loss": 1.2112, "step": 2884 }, { "epoch": 0.44382908349678857, "grad_norm": 3.673750400543213, "learning_rate": 1.1136083743842366e-05, "loss": 1.2158, "step": 2885 }, { "epoch": 0.4439829237337026, "grad_norm": 3.8565289974212646, "learning_rate": 1.1133004926108375e-05, "loss": 1.5496, "step": 2886 }, { "epoch": 0.4441367639706165, "grad_norm": 3.215207815170288, "learning_rate": 1.1129926108374385e-05, "loss": 1.5207, "step": 2887 }, { "epoch": 0.44429060420753047, "grad_norm": 3.3613967895507812, "learning_rate": 1.1126847290640394e-05, "loss": 1.2322, "step": 2888 }, { "epoch": 0.4444444444444444, "grad_norm": 3.09062123298645, "learning_rate": 1.1123768472906405e-05, "loss": 1.3308, "step": 2889 }, { "epoch": 0.4445982846813584, "grad_norm": 3.0222206115722656, "learning_rate": 1.1120689655172414e-05, "loss": 1.3563, "step": 2890 }, { "epoch": 0.4447521249182724, "grad_norm": 3.5832464694976807, "learning_rate": 1.1117610837438425e-05, "loss": 1.3229, "step": 2891 }, { "epoch": 0.4449059651551863, "grad_norm": 4.061063289642334, "learning_rate": 1.1114532019704434e-05, "loss": 1.3863, "step": 2892 }, { "epoch": 0.4450598053921003, "grad_norm": 3.445241928100586, "learning_rate": 1.1111453201970444e-05, "loss": 1.3992, "step": 2893 }, { "epoch": 0.4452136456290143, "grad_norm": 3.758150339126587, "learning_rate": 1.1108374384236453e-05, "loss": 1.2272, "step": 2894 }, { "epoch": 0.4453674858659282, "grad_norm": 3.1926021575927734, "learning_rate": 1.1105295566502464e-05, "loss": 1.4851, "step": 2895 }, { "epoch": 0.4455213261028422, "grad_norm": 3.402218818664551, "learning_rate": 1.1102216748768473e-05, "loss": 1.198, "step": 2896 }, { "epoch": 0.4456751663397562, "grad_norm": 3.3126683235168457, "learning_rate": 1.1099137931034483e-05, "loss": 1.3615, "step": 2897 }, { "epoch": 0.44582900657667013, "grad_norm": 4.245430946350098, "learning_rate": 1.1096059113300492e-05, "loss": 1.372, "step": 2898 }, { "epoch": 0.4459828468135841, "grad_norm": 3.1075809001922607, "learning_rate": 1.1092980295566505e-05, "loss": 1.0299, "step": 2899 }, { "epoch": 0.4461366870504981, "grad_norm": 3.2704641819000244, "learning_rate": 1.1089901477832514e-05, "loss": 1.374, "step": 2900 }, { "epoch": 0.44629052728741203, "grad_norm": 4.276775360107422, "learning_rate": 1.1086822660098524e-05, "loss": 1.2014, "step": 2901 }, { "epoch": 0.446444367524326, "grad_norm": 3.1024913787841797, "learning_rate": 1.1083743842364533e-05, "loss": 1.0845, "step": 2902 }, { "epoch": 0.44659820776123993, "grad_norm": 3.4829301834106445, "learning_rate": 1.1080665024630544e-05, "loss": 1.3252, "step": 2903 }, { "epoch": 0.44675204799815393, "grad_norm": 3.481266736984253, "learning_rate": 1.1077586206896553e-05, "loss": 1.4346, "step": 2904 }, { "epoch": 0.4469058882350679, "grad_norm": 3.859168529510498, "learning_rate": 1.1074507389162563e-05, "loss": 1.1385, "step": 2905 }, { "epoch": 0.44705972847198183, "grad_norm": 3.3129608631134033, "learning_rate": 1.1071428571428572e-05, "loss": 1.2762, "step": 2906 }, { "epoch": 0.44721356870889584, "grad_norm": 3.9522337913513184, "learning_rate": 1.1068349753694583e-05, "loss": 1.3535, "step": 2907 }, { "epoch": 0.4473674089458098, "grad_norm": 2.9989724159240723, "learning_rate": 1.1065270935960592e-05, "loss": 1.4645, "step": 2908 }, { "epoch": 0.44752124918272373, "grad_norm": 3.3367490768432617, "learning_rate": 1.1062192118226603e-05, "loss": 1.2347, "step": 2909 }, { "epoch": 0.4476750894196377, "grad_norm": 3.1881961822509766, "learning_rate": 1.1059113300492612e-05, "loss": 1.3479, "step": 2910 }, { "epoch": 0.4478289296565517, "grad_norm": 3.378718614578247, "learning_rate": 1.1056034482758622e-05, "loss": 1.2967, "step": 2911 }, { "epoch": 0.44798276989346564, "grad_norm": 3.552325963973999, "learning_rate": 1.1052955665024631e-05, "loss": 1.3859, "step": 2912 }, { "epoch": 0.4481366101303796, "grad_norm": 3.2354910373687744, "learning_rate": 1.1049876847290642e-05, "loss": 1.402, "step": 2913 }, { "epoch": 0.4482904503672936, "grad_norm": 3.2106573581695557, "learning_rate": 1.104679802955665e-05, "loss": 1.3508, "step": 2914 }, { "epoch": 0.44844429060420754, "grad_norm": 3.1390748023986816, "learning_rate": 1.1043719211822661e-05, "loss": 1.7315, "step": 2915 }, { "epoch": 0.4485981308411215, "grad_norm": 3.855853796005249, "learning_rate": 1.104064039408867e-05, "loss": 1.5488, "step": 2916 }, { "epoch": 0.44875197107803544, "grad_norm": 3.2952592372894287, "learning_rate": 1.1037561576354681e-05, "loss": 1.3778, "step": 2917 }, { "epoch": 0.44890581131494944, "grad_norm": 3.5178685188293457, "learning_rate": 1.103448275862069e-05, "loss": 1.4885, "step": 2918 }, { "epoch": 0.4490596515518634, "grad_norm": 3.6454451084136963, "learning_rate": 1.10314039408867e-05, "loss": 1.4106, "step": 2919 }, { "epoch": 0.44921349178877734, "grad_norm": 4.203024387359619, "learning_rate": 1.102832512315271e-05, "loss": 1.2796, "step": 2920 }, { "epoch": 0.44936733202569135, "grad_norm": 3.6373870372772217, "learning_rate": 1.102524630541872e-05, "loss": 1.3594, "step": 2921 }, { "epoch": 0.4495211722626053, "grad_norm": 3.786041259765625, "learning_rate": 1.102216748768473e-05, "loss": 1.3113, "step": 2922 }, { "epoch": 0.44967501249951924, "grad_norm": 3.584146499633789, "learning_rate": 1.101908866995074e-05, "loss": 1.4647, "step": 2923 }, { "epoch": 0.4498288527364332, "grad_norm": 3.343543291091919, "learning_rate": 1.1016009852216749e-05, "loss": 1.2679, "step": 2924 }, { "epoch": 0.4499826929733472, "grad_norm": 3.4148056507110596, "learning_rate": 1.101293103448276e-05, "loss": 1.3806, "step": 2925 }, { "epoch": 0.45013653321026115, "grad_norm": 4.635516166687012, "learning_rate": 1.1009852216748768e-05, "loss": 1.4304, "step": 2926 }, { "epoch": 0.4502903734471751, "grad_norm": 4.397712707519531, "learning_rate": 1.1006773399014779e-05, "loss": 1.4331, "step": 2927 }, { "epoch": 0.4504442136840891, "grad_norm": 3.513829231262207, "learning_rate": 1.1003694581280788e-05, "loss": 1.2526, "step": 2928 }, { "epoch": 0.45059805392100305, "grad_norm": 3.1380417346954346, "learning_rate": 1.1000615763546799e-05, "loss": 1.4116, "step": 2929 }, { "epoch": 0.450751894157917, "grad_norm": 3.044226884841919, "learning_rate": 1.0997536945812808e-05, "loss": 1.3454, "step": 2930 }, { "epoch": 0.45090573439483095, "grad_norm": 3.0392587184906006, "learning_rate": 1.0994458128078818e-05, "loss": 1.1701, "step": 2931 }, { "epoch": 0.45105957463174495, "grad_norm": 3.72540545463562, "learning_rate": 1.0991379310344827e-05, "loss": 1.3124, "step": 2932 }, { "epoch": 0.4512134148686589, "grad_norm": 3.5517330169677734, "learning_rate": 1.098830049261084e-05, "loss": 1.4309, "step": 2933 }, { "epoch": 0.45136725510557285, "grad_norm": 3.7391090393066406, "learning_rate": 1.0985221674876848e-05, "loss": 1.2903, "step": 2934 }, { "epoch": 0.4515210953424868, "grad_norm": 3.7876369953155518, "learning_rate": 1.0982142857142859e-05, "loss": 1.2891, "step": 2935 }, { "epoch": 0.4516749355794008, "grad_norm": 4.124865531921387, "learning_rate": 1.0979064039408868e-05, "loss": 1.4133, "step": 2936 }, { "epoch": 0.45182877581631475, "grad_norm": 3.9809799194335938, "learning_rate": 1.0975985221674879e-05, "loss": 1.6072, "step": 2937 }, { "epoch": 0.4519826160532287, "grad_norm": 3.438931465148926, "learning_rate": 1.0972906403940888e-05, "loss": 1.2931, "step": 2938 }, { "epoch": 0.4521364562901427, "grad_norm": 3.6841020584106445, "learning_rate": 1.0969827586206898e-05, "loss": 1.0516, "step": 2939 }, { "epoch": 0.45229029652705666, "grad_norm": 3.418792247772217, "learning_rate": 1.0966748768472907e-05, "loss": 0.9125, "step": 2940 }, { "epoch": 0.4524441367639706, "grad_norm": 3.8091347217559814, "learning_rate": 1.0963669950738918e-05, "loss": 1.6189, "step": 2941 }, { "epoch": 0.45259797700088455, "grad_norm": 3.7814972400665283, "learning_rate": 1.0960591133004927e-05, "loss": 1.2888, "step": 2942 }, { "epoch": 0.45275181723779856, "grad_norm": 3.6630783081054688, "learning_rate": 1.0957512315270937e-05, "loss": 1.4152, "step": 2943 }, { "epoch": 0.4529056574747125, "grad_norm": 3.7752857208251953, "learning_rate": 1.0954433497536946e-05, "loss": 1.339, "step": 2944 }, { "epoch": 0.45305949771162646, "grad_norm": 3.2730624675750732, "learning_rate": 1.0951354679802957e-05, "loss": 1.6261, "step": 2945 }, { "epoch": 0.45321333794854046, "grad_norm": 4.307313442230225, "learning_rate": 1.0948275862068966e-05, "loss": 1.2116, "step": 2946 }, { "epoch": 0.4533671781854544, "grad_norm": 3.2392733097076416, "learning_rate": 1.0945197044334977e-05, "loss": 1.1784, "step": 2947 }, { "epoch": 0.45352101842236836, "grad_norm": 4.2749714851379395, "learning_rate": 1.0942118226600986e-05, "loss": 1.4092, "step": 2948 }, { "epoch": 0.4536748586592823, "grad_norm": 4.1338067054748535, "learning_rate": 1.0939039408866996e-05, "loss": 1.1717, "step": 2949 }, { "epoch": 0.4538286988961963, "grad_norm": 3.5887832641601562, "learning_rate": 1.0935960591133005e-05, "loss": 1.2735, "step": 2950 }, { "epoch": 0.45398253913311026, "grad_norm": 4.2222700119018555, "learning_rate": 1.0932881773399016e-05, "loss": 1.2626, "step": 2951 }, { "epoch": 0.4541363793700242, "grad_norm": 3.8305346965789795, "learning_rate": 1.0929802955665025e-05, "loss": 1.2123, "step": 2952 }, { "epoch": 0.4542902196069382, "grad_norm": 3.743492603302002, "learning_rate": 1.0926724137931035e-05, "loss": 1.1295, "step": 2953 }, { "epoch": 0.45444405984385217, "grad_norm": 4.500133514404297, "learning_rate": 1.0923645320197044e-05, "loss": 1.3354, "step": 2954 }, { "epoch": 0.4545979000807661, "grad_norm": 3.4460055828094482, "learning_rate": 1.0920566502463055e-05, "loss": 1.3949, "step": 2955 }, { "epoch": 0.45475174031768006, "grad_norm": 3.86533260345459, "learning_rate": 1.0917487684729064e-05, "loss": 1.4086, "step": 2956 }, { "epoch": 0.45490558055459407, "grad_norm": 3.7340173721313477, "learning_rate": 1.0914408866995075e-05, "loss": 1.2528, "step": 2957 }, { "epoch": 0.455059420791508, "grad_norm": 4.4023637771606445, "learning_rate": 1.0911330049261084e-05, "loss": 1.1444, "step": 2958 }, { "epoch": 0.45521326102842197, "grad_norm": 3.5400354862213135, "learning_rate": 1.0908251231527094e-05, "loss": 1.6076, "step": 2959 }, { "epoch": 0.45536710126533597, "grad_norm": 4.0289306640625, "learning_rate": 1.0905172413793103e-05, "loss": 1.3701, "step": 2960 }, { "epoch": 0.4555209415022499, "grad_norm": 3.259247064590454, "learning_rate": 1.0902093596059114e-05, "loss": 1.2984, "step": 2961 }, { "epoch": 0.45567478173916387, "grad_norm": 3.406341075897217, "learning_rate": 1.0899014778325123e-05, "loss": 1.3836, "step": 2962 }, { "epoch": 0.4558286219760778, "grad_norm": 3.5700690746307373, "learning_rate": 1.0895935960591133e-05, "loss": 1.3284, "step": 2963 }, { "epoch": 0.4559824622129918, "grad_norm": 4.294737339019775, "learning_rate": 1.0892857142857142e-05, "loss": 1.344, "step": 2964 }, { "epoch": 0.4561363024499058, "grad_norm": 3.7030718326568604, "learning_rate": 1.0889778325123153e-05, "loss": 1.4342, "step": 2965 }, { "epoch": 0.4562901426868197, "grad_norm": 3.6420085430145264, "learning_rate": 1.0886699507389162e-05, "loss": 1.586, "step": 2966 }, { "epoch": 0.4564439829237337, "grad_norm": 3.3954296112060547, "learning_rate": 1.0883620689655174e-05, "loss": 1.482, "step": 2967 }, { "epoch": 0.4565978231606477, "grad_norm": 4.218811988830566, "learning_rate": 1.0880541871921185e-05, "loss": 1.449, "step": 2968 }, { "epoch": 0.4567516633975616, "grad_norm": 3.49074387550354, "learning_rate": 1.0877463054187194e-05, "loss": 1.3519, "step": 2969 }, { "epoch": 0.4569055036344756, "grad_norm": 3.190031051635742, "learning_rate": 1.0874384236453205e-05, "loss": 1.3667, "step": 2970 }, { "epoch": 0.4570593438713896, "grad_norm": 3.2492449283599854, "learning_rate": 1.0871305418719214e-05, "loss": 1.3894, "step": 2971 }, { "epoch": 0.4572131841083035, "grad_norm": 4.607098579406738, "learning_rate": 1.0868226600985222e-05, "loss": 1.5765, "step": 2972 }, { "epoch": 0.4573670243452175, "grad_norm": 4.801025867462158, "learning_rate": 1.0865147783251233e-05, "loss": 1.5929, "step": 2973 }, { "epoch": 0.4575208645821315, "grad_norm": 4.211153030395508, "learning_rate": 1.0862068965517242e-05, "loss": 1.4447, "step": 2974 }, { "epoch": 0.45767470481904543, "grad_norm": 4.210996627807617, "learning_rate": 1.0858990147783253e-05, "loss": 1.3576, "step": 2975 }, { "epoch": 0.4578285450559594, "grad_norm": 3.391200542449951, "learning_rate": 1.0855911330049262e-05, "loss": 1.5263, "step": 2976 }, { "epoch": 0.45798238529287333, "grad_norm": 3.6169941425323486, "learning_rate": 1.0852832512315272e-05, "loss": 1.4315, "step": 2977 }, { "epoch": 0.45813622552978733, "grad_norm": 3.4195914268493652, "learning_rate": 1.0849753694581281e-05, "loss": 1.3968, "step": 2978 }, { "epoch": 0.4582900657667013, "grad_norm": 3.4967305660247803, "learning_rate": 1.0846674876847292e-05, "loss": 1.5299, "step": 2979 }, { "epoch": 0.45844390600361523, "grad_norm": 4.736257553100586, "learning_rate": 1.0843596059113301e-05, "loss": 1.152, "step": 2980 }, { "epoch": 0.45859774624052924, "grad_norm": 3.696354389190674, "learning_rate": 1.0840517241379311e-05, "loss": 1.2617, "step": 2981 }, { "epoch": 0.4587515864774432, "grad_norm": 4.5708909034729, "learning_rate": 1.083743842364532e-05, "loss": 1.3856, "step": 2982 }, { "epoch": 0.45890542671435713, "grad_norm": 3.3381645679473877, "learning_rate": 1.0834359605911331e-05, "loss": 1.6287, "step": 2983 }, { "epoch": 0.4590592669512711, "grad_norm": 3.4024693965911865, "learning_rate": 1.083128078817734e-05, "loss": 1.2857, "step": 2984 }, { "epoch": 0.4592131071881851, "grad_norm": 4.0638298988342285, "learning_rate": 1.082820197044335e-05, "loss": 1.3841, "step": 2985 }, { "epoch": 0.45936694742509904, "grad_norm": 3.2948803901672363, "learning_rate": 1.082512315270936e-05, "loss": 1.2063, "step": 2986 }, { "epoch": 0.459520787662013, "grad_norm": 3.611267566680908, "learning_rate": 1.082204433497537e-05, "loss": 1.4196, "step": 2987 }, { "epoch": 0.459674627898927, "grad_norm": 3.0987050533294678, "learning_rate": 1.081896551724138e-05, "loss": 1.2664, "step": 2988 }, { "epoch": 0.45982846813584094, "grad_norm": 3.5443315505981445, "learning_rate": 1.081588669950739e-05, "loss": 1.5558, "step": 2989 }, { "epoch": 0.4599823083727549, "grad_norm": 3.571272850036621, "learning_rate": 1.0812807881773399e-05, "loss": 1.3424, "step": 2990 }, { "epoch": 0.46013614860966884, "grad_norm": 3.195192575454712, "learning_rate": 1.080972906403941e-05, "loss": 1.2758, "step": 2991 }, { "epoch": 0.46028998884658284, "grad_norm": 3.9649856090545654, "learning_rate": 1.0806650246305418e-05, "loss": 1.2753, "step": 2992 }, { "epoch": 0.4604438290834968, "grad_norm": 3.016108512878418, "learning_rate": 1.0803571428571429e-05, "loss": 1.2766, "step": 2993 }, { "epoch": 0.46059766932041074, "grad_norm": 3.294790506362915, "learning_rate": 1.0800492610837438e-05, "loss": 1.3525, "step": 2994 }, { "epoch": 0.46075150955732475, "grad_norm": 3.229152202606201, "learning_rate": 1.0797413793103449e-05, "loss": 1.3524, "step": 2995 }, { "epoch": 0.4609053497942387, "grad_norm": 3.386598825454712, "learning_rate": 1.0794334975369458e-05, "loss": 1.2537, "step": 2996 }, { "epoch": 0.46105919003115264, "grad_norm": 3.6610007286071777, "learning_rate": 1.0791256157635468e-05, "loss": 1.3728, "step": 2997 }, { "epoch": 0.4612130302680666, "grad_norm": 3.427093029022217, "learning_rate": 1.0788177339901477e-05, "loss": 1.3091, "step": 2998 }, { "epoch": 0.4613668705049806, "grad_norm": 3.6897451877593994, "learning_rate": 1.0785098522167488e-05, "loss": 1.2955, "step": 2999 }, { "epoch": 0.46152071074189455, "grad_norm": 3.2935006618499756, "learning_rate": 1.0782019704433497e-05, "loss": 1.4593, "step": 3000 }, { "epoch": 0.4616745509788085, "grad_norm": 3.7218847274780273, "learning_rate": 1.077894088669951e-05, "loss": 1.3709, "step": 3001 }, { "epoch": 0.46182839121572244, "grad_norm": 3.5142011642456055, "learning_rate": 1.077586206896552e-05, "loss": 1.3858, "step": 3002 }, { "epoch": 0.46198223145263645, "grad_norm": 2.950960874557495, "learning_rate": 1.0772783251231529e-05, "loss": 1.4108, "step": 3003 }, { "epoch": 0.4621360716895504, "grad_norm": 3.878803014755249, "learning_rate": 1.076970443349754e-05, "loss": 1.6405, "step": 3004 }, { "epoch": 0.46228991192646435, "grad_norm": 3.817823648452759, "learning_rate": 1.0766625615763548e-05, "loss": 1.264, "step": 3005 }, { "epoch": 0.46244375216337835, "grad_norm": 3.432072162628174, "learning_rate": 1.0763546798029559e-05, "loss": 1.5397, "step": 3006 }, { "epoch": 0.4625975924002923, "grad_norm": 3.181751012802124, "learning_rate": 1.0760467980295568e-05, "loss": 1.254, "step": 3007 }, { "epoch": 0.46275143263720625, "grad_norm": 3.294992685317993, "learning_rate": 1.0757389162561579e-05, "loss": 1.2727, "step": 3008 }, { "epoch": 0.4629052728741202, "grad_norm": 3.504276990890503, "learning_rate": 1.0754310344827588e-05, "loss": 1.2609, "step": 3009 }, { "epoch": 0.4630591131110342, "grad_norm": 4.251397609710693, "learning_rate": 1.0751231527093598e-05, "loss": 1.421, "step": 3010 }, { "epoch": 0.46321295334794815, "grad_norm": 4.217993259429932, "learning_rate": 1.0748152709359607e-05, "loss": 1.443, "step": 3011 }, { "epoch": 0.4633667935848621, "grad_norm": 3.650758743286133, "learning_rate": 1.0745073891625618e-05, "loss": 1.1771, "step": 3012 }, { "epoch": 0.4635206338217761, "grad_norm": 3.478748083114624, "learning_rate": 1.0741995073891627e-05, "loss": 1.2558, "step": 3013 }, { "epoch": 0.46367447405869006, "grad_norm": 4.005462169647217, "learning_rate": 1.0738916256157637e-05, "loss": 1.1481, "step": 3014 }, { "epoch": 0.463828314295604, "grad_norm": 3.2759549617767334, "learning_rate": 1.0735837438423646e-05, "loss": 1.1451, "step": 3015 }, { "epoch": 0.46398215453251795, "grad_norm": 4.196432113647461, "learning_rate": 1.0732758620689655e-05, "loss": 1.2123, "step": 3016 }, { "epoch": 0.46413599476943196, "grad_norm": 3.951021194458008, "learning_rate": 1.0729679802955666e-05, "loss": 1.4115, "step": 3017 }, { "epoch": 0.4642898350063459, "grad_norm": 3.2084014415740967, "learning_rate": 1.0726600985221675e-05, "loss": 1.1859, "step": 3018 }, { "epoch": 0.46444367524325986, "grad_norm": 3.819201946258545, "learning_rate": 1.0723522167487686e-05, "loss": 1.369, "step": 3019 }, { "epoch": 0.46459751548017386, "grad_norm": 4.006355285644531, "learning_rate": 1.0720443349753694e-05, "loss": 1.4876, "step": 3020 }, { "epoch": 0.4647513557170878, "grad_norm": 3.5379416942596436, "learning_rate": 1.0717364532019705e-05, "loss": 1.4036, "step": 3021 }, { "epoch": 0.46490519595400176, "grad_norm": 3.359144687652588, "learning_rate": 1.0714285714285714e-05, "loss": 1.3725, "step": 3022 }, { "epoch": 0.4650590361909157, "grad_norm": 4.154046058654785, "learning_rate": 1.0711206896551725e-05, "loss": 1.4053, "step": 3023 }, { "epoch": 0.4652128764278297, "grad_norm": 3.373924970626831, "learning_rate": 1.0708128078817734e-05, "loss": 1.1975, "step": 3024 }, { "epoch": 0.46536671666474366, "grad_norm": 3.730172872543335, "learning_rate": 1.0705049261083744e-05, "loss": 1.3418, "step": 3025 }, { "epoch": 0.4655205569016576, "grad_norm": 4.011640548706055, "learning_rate": 1.0701970443349753e-05, "loss": 1.3838, "step": 3026 }, { "epoch": 0.4656743971385716, "grad_norm": 3.7678744792938232, "learning_rate": 1.0698891625615764e-05, "loss": 1.1439, "step": 3027 }, { "epoch": 0.46582823737548557, "grad_norm": 3.7315261363983154, "learning_rate": 1.0695812807881773e-05, "loss": 1.219, "step": 3028 }, { "epoch": 0.4659820776123995, "grad_norm": 4.073310852050781, "learning_rate": 1.0692733990147784e-05, "loss": 1.4908, "step": 3029 }, { "epoch": 0.46613591784931346, "grad_norm": 3.9079806804656982, "learning_rate": 1.0689655172413792e-05, "loss": 1.3045, "step": 3030 }, { "epoch": 0.46628975808622747, "grad_norm": 4.239899635314941, "learning_rate": 1.0686576354679803e-05, "loss": 1.4523, "step": 3031 }, { "epoch": 0.4664435983231414, "grad_norm": 3.804060459136963, "learning_rate": 1.0683497536945812e-05, "loss": 1.4675, "step": 3032 }, { "epoch": 0.46659743856005537, "grad_norm": 4.887894630432129, "learning_rate": 1.0680418719211823e-05, "loss": 1.2287, "step": 3033 }, { "epoch": 0.46675127879696937, "grad_norm": 3.992823600769043, "learning_rate": 1.0677339901477832e-05, "loss": 1.2045, "step": 3034 }, { "epoch": 0.4669051190338833, "grad_norm": 3.432208299636841, "learning_rate": 1.0674261083743844e-05, "loss": 1.3044, "step": 3035 }, { "epoch": 0.46705895927079727, "grad_norm": 3.174785852432251, "learning_rate": 1.0671182266009855e-05, "loss": 1.2195, "step": 3036 }, { "epoch": 0.4672127995077112, "grad_norm": 3.46950626373291, "learning_rate": 1.0668103448275864e-05, "loss": 1.3323, "step": 3037 }, { "epoch": 0.4673666397446252, "grad_norm": 3.1127891540527344, "learning_rate": 1.0665024630541874e-05, "loss": 1.1389, "step": 3038 }, { "epoch": 0.46752047998153917, "grad_norm": 3.287275552749634, "learning_rate": 1.0661945812807883e-05, "loss": 1.471, "step": 3039 }, { "epoch": 0.4676743202184531, "grad_norm": 3.173236608505249, "learning_rate": 1.0658866995073894e-05, "loss": 1.3214, "step": 3040 }, { "epoch": 0.4678281604553671, "grad_norm": 4.739632606506348, "learning_rate": 1.0655788177339903e-05, "loss": 1.4535, "step": 3041 }, { "epoch": 0.4679820006922811, "grad_norm": 3.3620688915252686, "learning_rate": 1.0652709359605913e-05, "loss": 1.3138, "step": 3042 }, { "epoch": 0.468135840929195, "grad_norm": 3.5729525089263916, "learning_rate": 1.0649630541871922e-05, "loss": 1.3455, "step": 3043 }, { "epoch": 0.468289681166109, "grad_norm": 3.900418519973755, "learning_rate": 1.0646551724137933e-05, "loss": 1.0696, "step": 3044 }, { "epoch": 0.468443521403023, "grad_norm": 3.4071602821350098, "learning_rate": 1.0643472906403942e-05, "loss": 1.3615, "step": 3045 }, { "epoch": 0.4685973616399369, "grad_norm": 3.354374408721924, "learning_rate": 1.0640394088669953e-05, "loss": 1.3395, "step": 3046 }, { "epoch": 0.4687512018768509, "grad_norm": 4.003669261932373, "learning_rate": 1.0637315270935962e-05, "loss": 1.276, "step": 3047 }, { "epoch": 0.4689050421137649, "grad_norm": 3.7577340602874756, "learning_rate": 1.0634236453201972e-05, "loss": 1.4376, "step": 3048 }, { "epoch": 0.46905888235067883, "grad_norm": 3.274725914001465, "learning_rate": 1.0631157635467981e-05, "loss": 1.359, "step": 3049 }, { "epoch": 0.4692127225875928, "grad_norm": 3.5149168968200684, "learning_rate": 1.0628078817733992e-05, "loss": 1.3496, "step": 3050 }, { "epoch": 0.46936656282450673, "grad_norm": 3.5972344875335693, "learning_rate": 1.0625e-05, "loss": 1.4506, "step": 3051 }, { "epoch": 0.46952040306142073, "grad_norm": 3.5227863788604736, "learning_rate": 1.0621921182266011e-05, "loss": 1.3823, "step": 3052 }, { "epoch": 0.4696742432983347, "grad_norm": 4.173227310180664, "learning_rate": 1.061884236453202e-05, "loss": 1.3146, "step": 3053 }, { "epoch": 0.46982808353524863, "grad_norm": 3.71002197265625, "learning_rate": 1.0615763546798031e-05, "loss": 1.2678, "step": 3054 }, { "epoch": 0.46998192377216264, "grad_norm": 4.46245813369751, "learning_rate": 1.061268472906404e-05, "loss": 1.2845, "step": 3055 }, { "epoch": 0.4701357640090766, "grad_norm": 3.7174489498138428, "learning_rate": 1.060960591133005e-05, "loss": 1.2731, "step": 3056 }, { "epoch": 0.47028960424599053, "grad_norm": 4.117593765258789, "learning_rate": 1.060652709359606e-05, "loss": 1.3488, "step": 3057 }, { "epoch": 0.4704434444829045, "grad_norm": 3.45670747756958, "learning_rate": 1.060344827586207e-05, "loss": 1.2836, "step": 3058 }, { "epoch": 0.4705972847198185, "grad_norm": 4.009284019470215, "learning_rate": 1.0600369458128079e-05, "loss": 1.4741, "step": 3059 }, { "epoch": 0.47075112495673244, "grad_norm": 3.9151759147644043, "learning_rate": 1.0597290640394088e-05, "loss": 1.5796, "step": 3060 }, { "epoch": 0.4709049651936464, "grad_norm": 3.0281572341918945, "learning_rate": 1.0594211822660099e-05, "loss": 1.3896, "step": 3061 }, { "epoch": 0.4710588054305604, "grad_norm": 3.593747854232788, "learning_rate": 1.0591133004926108e-05, "loss": 1.4168, "step": 3062 }, { "epoch": 0.47121264566747434, "grad_norm": 3.413100004196167, "learning_rate": 1.0588054187192118e-05, "loss": 1.27, "step": 3063 }, { "epoch": 0.4713664859043883, "grad_norm": 3.924940347671509, "learning_rate": 1.0584975369458127e-05, "loss": 1.4359, "step": 3064 }, { "epoch": 0.47152032614130224, "grad_norm": 3.793003559112549, "learning_rate": 1.0581896551724138e-05, "loss": 1.5521, "step": 3065 }, { "epoch": 0.47167416637821624, "grad_norm": 4.007007598876953, "learning_rate": 1.0578817733990147e-05, "loss": 1.2875, "step": 3066 }, { "epoch": 0.4718280066151302, "grad_norm": 4.143755912780762, "learning_rate": 1.0575738916256158e-05, "loss": 1.3974, "step": 3067 }, { "epoch": 0.47198184685204414, "grad_norm": 3.6356539726257324, "learning_rate": 1.057266009852217e-05, "loss": 1.512, "step": 3068 }, { "epoch": 0.47213568708895814, "grad_norm": 3.471424102783203, "learning_rate": 1.0569581280788179e-05, "loss": 1.265, "step": 3069 }, { "epoch": 0.4722895273258721, "grad_norm": 3.281649351119995, "learning_rate": 1.056650246305419e-05, "loss": 1.2869, "step": 3070 }, { "epoch": 0.47244336756278604, "grad_norm": 4.146361827850342, "learning_rate": 1.0563423645320198e-05, "loss": 1.5349, "step": 3071 }, { "epoch": 0.4725972077997, "grad_norm": 4.3964433670043945, "learning_rate": 1.0560344827586209e-05, "loss": 1.4485, "step": 3072 }, { "epoch": 0.472751048036614, "grad_norm": 3.646211862564087, "learning_rate": 1.0557266009852218e-05, "loss": 1.3973, "step": 3073 }, { "epoch": 0.47290488827352795, "grad_norm": 2.999878406524658, "learning_rate": 1.0554187192118229e-05, "loss": 0.7818, "step": 3074 }, { "epoch": 0.4730587285104419, "grad_norm": 3.327836036682129, "learning_rate": 1.0551108374384238e-05, "loss": 1.3774, "step": 3075 }, { "epoch": 0.47321256874735584, "grad_norm": 3.4747469425201416, "learning_rate": 1.0548029556650248e-05, "loss": 1.2534, "step": 3076 }, { "epoch": 0.47336640898426985, "grad_norm": 3.7219011783599854, "learning_rate": 1.0544950738916257e-05, "loss": 1.0958, "step": 3077 }, { "epoch": 0.4735202492211838, "grad_norm": 3.707811117172241, "learning_rate": 1.0541871921182268e-05, "loss": 1.4729, "step": 3078 }, { "epoch": 0.47367408945809775, "grad_norm": 3.481592893600464, "learning_rate": 1.0538793103448277e-05, "loss": 1.2233, "step": 3079 }, { "epoch": 0.47382792969501175, "grad_norm": 3.561833620071411, "learning_rate": 1.0535714285714287e-05, "loss": 1.2474, "step": 3080 }, { "epoch": 0.4739817699319257, "grad_norm": 4.017879009246826, "learning_rate": 1.0532635467980296e-05, "loss": 1.5226, "step": 3081 }, { "epoch": 0.47413561016883965, "grad_norm": 3.327597141265869, "learning_rate": 1.0529556650246307e-05, "loss": 1.3542, "step": 3082 }, { "epoch": 0.4742894504057536, "grad_norm": 3.585747718811035, "learning_rate": 1.0526477832512316e-05, "loss": 1.2144, "step": 3083 }, { "epoch": 0.4744432906426676, "grad_norm": 3.1962127685546875, "learning_rate": 1.0523399014778327e-05, "loss": 1.4238, "step": 3084 }, { "epoch": 0.47459713087958155, "grad_norm": 3.579183340072632, "learning_rate": 1.0520320197044336e-05, "loss": 1.4746, "step": 3085 }, { "epoch": 0.4747509711164955, "grad_norm": 3.498715400695801, "learning_rate": 1.0517241379310346e-05, "loss": 1.2581, "step": 3086 }, { "epoch": 0.4749048113534095, "grad_norm": 3.5551295280456543, "learning_rate": 1.0514162561576355e-05, "loss": 1.345, "step": 3087 }, { "epoch": 0.47505865159032346, "grad_norm": 3.9004197120666504, "learning_rate": 1.0511083743842366e-05, "loss": 1.4601, "step": 3088 }, { "epoch": 0.4752124918272374, "grad_norm": 4.052772521972656, "learning_rate": 1.0508004926108375e-05, "loss": 1.4394, "step": 3089 }, { "epoch": 0.47536633206415135, "grad_norm": 3.476818561553955, "learning_rate": 1.0504926108374385e-05, "loss": 1.7102, "step": 3090 }, { "epoch": 0.47552017230106536, "grad_norm": 4.458371162414551, "learning_rate": 1.0501847290640394e-05, "loss": 1.2981, "step": 3091 }, { "epoch": 0.4756740125379793, "grad_norm": 3.688897132873535, "learning_rate": 1.0498768472906405e-05, "loss": 1.2653, "step": 3092 }, { "epoch": 0.47582785277489326, "grad_norm": 3.4507954120635986, "learning_rate": 1.0495689655172414e-05, "loss": 1.3906, "step": 3093 }, { "epoch": 0.47598169301180726, "grad_norm": 3.098156452178955, "learning_rate": 1.0492610837438425e-05, "loss": 1.298, "step": 3094 }, { "epoch": 0.4761355332487212, "grad_norm": 4.081457614898682, "learning_rate": 1.0489532019704434e-05, "loss": 1.5869, "step": 3095 }, { "epoch": 0.47628937348563516, "grad_norm": 3.3122241497039795, "learning_rate": 1.0486453201970444e-05, "loss": 1.4338, "step": 3096 }, { "epoch": 0.4764432137225491, "grad_norm": 4.038021087646484, "learning_rate": 1.0483374384236453e-05, "loss": 1.5212, "step": 3097 }, { "epoch": 0.4765970539594631, "grad_norm": 3.235858917236328, "learning_rate": 1.0480295566502464e-05, "loss": 1.434, "step": 3098 }, { "epoch": 0.47675089419637706, "grad_norm": 3.4368505477905273, "learning_rate": 1.0477216748768473e-05, "loss": 1.275, "step": 3099 }, { "epoch": 0.476904734433291, "grad_norm": 3.6012251377105713, "learning_rate": 1.0474137931034483e-05, "loss": 1.3726, "step": 3100 }, { "epoch": 0.477058574670205, "grad_norm": 3.8861916065216064, "learning_rate": 1.0471059113300492e-05, "loss": 1.3746, "step": 3101 }, { "epoch": 0.47721241490711896, "grad_norm": 3.655478000640869, "learning_rate": 1.0467980295566505e-05, "loss": 1.1571, "step": 3102 }, { "epoch": 0.4773662551440329, "grad_norm": 3.8467164039611816, "learning_rate": 1.0464901477832514e-05, "loss": 0.9757, "step": 3103 }, { "epoch": 0.47752009538094686, "grad_norm": 3.171663284301758, "learning_rate": 1.0461822660098524e-05, "loss": 1.1882, "step": 3104 }, { "epoch": 0.47767393561786087, "grad_norm": 3.8721189498901367, "learning_rate": 1.0458743842364533e-05, "loss": 1.1718, "step": 3105 }, { "epoch": 0.4778277758547748, "grad_norm": 4.183864593505859, "learning_rate": 1.0455665024630544e-05, "loss": 1.3068, "step": 3106 }, { "epoch": 0.47798161609168877, "grad_norm": 3.3770647048950195, "learning_rate": 1.0452586206896553e-05, "loss": 1.3265, "step": 3107 }, { "epoch": 0.47813545632860277, "grad_norm": 4.358190536499023, "learning_rate": 1.0449507389162563e-05, "loss": 1.3779, "step": 3108 }, { "epoch": 0.4782892965655167, "grad_norm": 3.4598751068115234, "learning_rate": 1.0446428571428572e-05, "loss": 1.2158, "step": 3109 }, { "epoch": 0.47844313680243067, "grad_norm": 3.9195783138275146, "learning_rate": 1.0443349753694583e-05, "loss": 1.2351, "step": 3110 }, { "epoch": 0.4785969770393446, "grad_norm": 3.6668338775634766, "learning_rate": 1.0440270935960592e-05, "loss": 1.4087, "step": 3111 }, { "epoch": 0.4787508172762586, "grad_norm": 3.5521912574768066, "learning_rate": 1.0437192118226603e-05, "loss": 1.3419, "step": 3112 }, { "epoch": 0.47890465751317257, "grad_norm": 3.1084325313568115, "learning_rate": 1.0434113300492612e-05, "loss": 1.4057, "step": 3113 }, { "epoch": 0.4790584977500865, "grad_norm": 3.358013391494751, "learning_rate": 1.0431034482758622e-05, "loss": 1.3294, "step": 3114 }, { "epoch": 0.4792123379870005, "grad_norm": 3.3994486331939697, "learning_rate": 1.0427955665024631e-05, "loss": 1.4072, "step": 3115 }, { "epoch": 0.4793661782239145, "grad_norm": 3.2192814350128174, "learning_rate": 1.0424876847290642e-05, "loss": 1.2902, "step": 3116 }, { "epoch": 0.4795200184608284, "grad_norm": 3.748107433319092, "learning_rate": 1.042179802955665e-05, "loss": 1.3774, "step": 3117 }, { "epoch": 0.4796738586977424, "grad_norm": 3.1056854724884033, "learning_rate": 1.0418719211822661e-05, "loss": 1.3469, "step": 3118 }, { "epoch": 0.4798276989346564, "grad_norm": 3.6932384967803955, "learning_rate": 1.041564039408867e-05, "loss": 1.5184, "step": 3119 }, { "epoch": 0.4799815391715703, "grad_norm": 3.8474345207214355, "learning_rate": 1.0412561576354681e-05, "loss": 1.1987, "step": 3120 }, { "epoch": 0.4801353794084843, "grad_norm": 3.47526216506958, "learning_rate": 1.040948275862069e-05, "loss": 1.4468, "step": 3121 }, { "epoch": 0.4802892196453983, "grad_norm": 3.644619941711426, "learning_rate": 1.04064039408867e-05, "loss": 1.2772, "step": 3122 }, { "epoch": 0.48044305988231223, "grad_norm": 3.396306037902832, "learning_rate": 1.040332512315271e-05, "loss": 1.3924, "step": 3123 }, { "epoch": 0.4805969001192262, "grad_norm": 3.0629944801330566, "learning_rate": 1.040024630541872e-05, "loss": 1.4492, "step": 3124 }, { "epoch": 0.4807507403561401, "grad_norm": 3.8052737712860107, "learning_rate": 1.039716748768473e-05, "loss": 1.3287, "step": 3125 }, { "epoch": 0.48090458059305413, "grad_norm": 3.0324320793151855, "learning_rate": 1.039408866995074e-05, "loss": 1.461, "step": 3126 }, { "epoch": 0.4810584208299681, "grad_norm": 3.924257278442383, "learning_rate": 1.0391009852216749e-05, "loss": 1.2746, "step": 3127 }, { "epoch": 0.48121226106688203, "grad_norm": 3.812286138534546, "learning_rate": 1.038793103448276e-05, "loss": 1.1408, "step": 3128 }, { "epoch": 0.48136610130379603, "grad_norm": 3.4331753253936768, "learning_rate": 1.0384852216748768e-05, "loss": 1.2835, "step": 3129 }, { "epoch": 0.48151994154071, "grad_norm": 2.721932888031006, "learning_rate": 1.0381773399014779e-05, "loss": 1.3017, "step": 3130 }, { "epoch": 0.48167378177762393, "grad_norm": 4.224338531494141, "learning_rate": 1.0378694581280788e-05, "loss": 1.3058, "step": 3131 }, { "epoch": 0.4818276220145379, "grad_norm": 3.4823505878448486, "learning_rate": 1.0375615763546799e-05, "loss": 1.4906, "step": 3132 }, { "epoch": 0.4819814622514519, "grad_norm": 3.242877721786499, "learning_rate": 1.0372536945812808e-05, "loss": 1.2536, "step": 3133 }, { "epoch": 0.48213530248836584, "grad_norm": 3.776179790496826, "learning_rate": 1.0369458128078818e-05, "loss": 1.4732, "step": 3134 }, { "epoch": 0.4822891427252798, "grad_norm": 3.791757583618164, "learning_rate": 1.0366379310344827e-05, "loss": 1.5874, "step": 3135 }, { "epoch": 0.4824429829621938, "grad_norm": 3.4868311882019043, "learning_rate": 1.036330049261084e-05, "loss": 1.4665, "step": 3136 }, { "epoch": 0.48259682319910774, "grad_norm": 3.9867489337921143, "learning_rate": 1.0360221674876848e-05, "loss": 1.3806, "step": 3137 }, { "epoch": 0.4827506634360217, "grad_norm": 4.240407943725586, "learning_rate": 1.0357142857142859e-05, "loss": 1.3769, "step": 3138 }, { "epoch": 0.48290450367293564, "grad_norm": 4.036710739135742, "learning_rate": 1.0354064039408868e-05, "loss": 1.187, "step": 3139 }, { "epoch": 0.48305834390984964, "grad_norm": 3.1133055686950684, "learning_rate": 1.0350985221674879e-05, "loss": 1.3179, "step": 3140 }, { "epoch": 0.4832121841467636, "grad_norm": 3.6885392665863037, "learning_rate": 1.0347906403940888e-05, "loss": 1.426, "step": 3141 }, { "epoch": 0.48336602438367754, "grad_norm": 3.5748472213745117, "learning_rate": 1.0344827586206898e-05, "loss": 1.1993, "step": 3142 }, { "epoch": 0.4835198646205915, "grad_norm": 2.9978291988372803, "learning_rate": 1.0341748768472907e-05, "loss": 1.1129, "step": 3143 }, { "epoch": 0.4836737048575055, "grad_norm": 3.948183059692383, "learning_rate": 1.0338669950738918e-05, "loss": 1.4689, "step": 3144 }, { "epoch": 0.48382754509441944, "grad_norm": 3.725205659866333, "learning_rate": 1.0335591133004927e-05, "loss": 1.1492, "step": 3145 }, { "epoch": 0.4839813853313334, "grad_norm": 3.4261972904205322, "learning_rate": 1.0332512315270938e-05, "loss": 1.553, "step": 3146 }, { "epoch": 0.4841352255682474, "grad_norm": 4.054103851318359, "learning_rate": 1.0329433497536946e-05, "loss": 1.3185, "step": 3147 }, { "epoch": 0.48428906580516135, "grad_norm": 3.6644489765167236, "learning_rate": 1.0326354679802957e-05, "loss": 1.5387, "step": 3148 }, { "epoch": 0.4844429060420753, "grad_norm": 3.144280195236206, "learning_rate": 1.0323275862068966e-05, "loss": 1.4136, "step": 3149 }, { "epoch": 0.48459674627898924, "grad_norm": 2.904719352722168, "learning_rate": 1.0320197044334977e-05, "loss": 1.3383, "step": 3150 }, { "epoch": 0.48475058651590325, "grad_norm": 4.001522541046143, "learning_rate": 1.0317118226600986e-05, "loss": 1.4185, "step": 3151 }, { "epoch": 0.4849044267528172, "grad_norm": 4.337460517883301, "learning_rate": 1.0314039408866996e-05, "loss": 1.4647, "step": 3152 }, { "epoch": 0.48505826698973115, "grad_norm": 3.1840262413024902, "learning_rate": 1.0310960591133005e-05, "loss": 1.328, "step": 3153 }, { "epoch": 0.48521210722664515, "grad_norm": 3.4696249961853027, "learning_rate": 1.0307881773399016e-05, "loss": 1.4166, "step": 3154 }, { "epoch": 0.4853659474635591, "grad_norm": 3.4789745807647705, "learning_rate": 1.0304802955665025e-05, "loss": 1.177, "step": 3155 }, { "epoch": 0.48551978770047305, "grad_norm": 3.1126387119293213, "learning_rate": 1.0301724137931036e-05, "loss": 1.4722, "step": 3156 }, { "epoch": 0.485673627937387, "grad_norm": 3.7918148040771484, "learning_rate": 1.0298645320197044e-05, "loss": 1.5528, "step": 3157 }, { "epoch": 0.485827468174301, "grad_norm": 3.7020230293273926, "learning_rate": 1.0295566502463055e-05, "loss": 1.162, "step": 3158 }, { "epoch": 0.48598130841121495, "grad_norm": 3.2801437377929688, "learning_rate": 1.0292487684729064e-05, "loss": 1.4364, "step": 3159 }, { "epoch": 0.4861351486481289, "grad_norm": 4.074179172515869, "learning_rate": 1.0289408866995075e-05, "loss": 1.4513, "step": 3160 }, { "epoch": 0.4862889888850429, "grad_norm": 3.323613405227661, "learning_rate": 1.0286330049261084e-05, "loss": 1.0494, "step": 3161 }, { "epoch": 0.48644282912195685, "grad_norm": 4.479113578796387, "learning_rate": 1.0283251231527094e-05, "loss": 1.3426, "step": 3162 }, { "epoch": 0.4865966693588708, "grad_norm": 3.872401475906372, "learning_rate": 1.0280172413793103e-05, "loss": 1.3229, "step": 3163 }, { "epoch": 0.48675050959578475, "grad_norm": 4.355154514312744, "learning_rate": 1.0277093596059114e-05, "loss": 1.4145, "step": 3164 }, { "epoch": 0.48690434983269876, "grad_norm": 3.2474818229675293, "learning_rate": 1.0274014778325123e-05, "loss": 1.3684, "step": 3165 }, { "epoch": 0.4870581900696127, "grad_norm": 3.178168296813965, "learning_rate": 1.0270935960591133e-05, "loss": 1.3747, "step": 3166 }, { "epoch": 0.48721203030652666, "grad_norm": 3.909468173980713, "learning_rate": 1.0267857142857142e-05, "loss": 1.294, "step": 3167 }, { "epoch": 0.48736587054344066, "grad_norm": 3.7506701946258545, "learning_rate": 1.0264778325123153e-05, "loss": 1.332, "step": 3168 }, { "epoch": 0.4875197107803546, "grad_norm": 3.9080023765563965, "learning_rate": 1.0261699507389162e-05, "loss": 1.359, "step": 3169 }, { "epoch": 0.48767355101726856, "grad_norm": 3.5823493003845215, "learning_rate": 1.0258620689655174e-05, "loss": 1.2804, "step": 3170 }, { "epoch": 0.4878273912541825, "grad_norm": 2.873002052307129, "learning_rate": 1.0255541871921183e-05, "loss": 1.1511, "step": 3171 }, { "epoch": 0.4879812314910965, "grad_norm": 4.0480637550354, "learning_rate": 1.0252463054187194e-05, "loss": 1.36, "step": 3172 }, { "epoch": 0.48813507172801046, "grad_norm": 4.37941312789917, "learning_rate": 1.0249384236453203e-05, "loss": 0.9757, "step": 3173 }, { "epoch": 0.4882889119649244, "grad_norm": 3.1612234115600586, "learning_rate": 1.0246305418719214e-05, "loss": 1.1803, "step": 3174 }, { "epoch": 0.4884427522018384, "grad_norm": 3.738952875137329, "learning_rate": 1.0243226600985223e-05, "loss": 1.4432, "step": 3175 }, { "epoch": 0.48859659243875236, "grad_norm": 3.7822065353393555, "learning_rate": 1.0240147783251233e-05, "loss": 1.3525, "step": 3176 }, { "epoch": 0.4887504326756663, "grad_norm": 3.332858085632324, "learning_rate": 1.0237068965517242e-05, "loss": 1.0396, "step": 3177 }, { "epoch": 0.48890427291258026, "grad_norm": 4.643192768096924, "learning_rate": 1.0233990147783253e-05, "loss": 1.1549, "step": 3178 }, { "epoch": 0.48905811314949427, "grad_norm": 3.927025318145752, "learning_rate": 1.0230911330049262e-05, "loss": 1.1706, "step": 3179 }, { "epoch": 0.4892119533864082, "grad_norm": 3.768707513809204, "learning_rate": 1.0227832512315272e-05, "loss": 1.2993, "step": 3180 }, { "epoch": 0.48936579362332217, "grad_norm": 4.491823196411133, "learning_rate": 1.0224753694581281e-05, "loss": 1.3161, "step": 3181 }, { "epoch": 0.48951963386023617, "grad_norm": 4.339175701141357, "learning_rate": 1.0221674876847292e-05, "loss": 1.3132, "step": 3182 }, { "epoch": 0.4896734740971501, "grad_norm": 3.88405179977417, "learning_rate": 1.0218596059113301e-05, "loss": 1.3511, "step": 3183 }, { "epoch": 0.48982731433406407, "grad_norm": 3.167097806930542, "learning_rate": 1.0215517241379312e-05, "loss": 1.377, "step": 3184 }, { "epoch": 0.489981154570978, "grad_norm": 4.429118633270264, "learning_rate": 1.021243842364532e-05, "loss": 1.1531, "step": 3185 }, { "epoch": 0.490134994807892, "grad_norm": 3.916961431503296, "learning_rate": 1.0209359605911331e-05, "loss": 1.2604, "step": 3186 }, { "epoch": 0.49028883504480597, "grad_norm": 3.725792169570923, "learning_rate": 1.020628078817734e-05, "loss": 1.23, "step": 3187 }, { "epoch": 0.4904426752817199, "grad_norm": 3.2256710529327393, "learning_rate": 1.020320197044335e-05, "loss": 1.1, "step": 3188 }, { "epoch": 0.4905965155186339, "grad_norm": 3.5121102333068848, "learning_rate": 1.020012315270936e-05, "loss": 1.3069, "step": 3189 }, { "epoch": 0.4907503557555479, "grad_norm": 3.302928924560547, "learning_rate": 1.019704433497537e-05, "loss": 1.4219, "step": 3190 }, { "epoch": 0.4909041959924618, "grad_norm": 3.3242995738983154, "learning_rate": 1.019396551724138e-05, "loss": 1.1434, "step": 3191 }, { "epoch": 0.49105803622937577, "grad_norm": 4.276485919952393, "learning_rate": 1.019088669950739e-05, "loss": 1.3315, "step": 3192 }, { "epoch": 0.4912118764662898, "grad_norm": 3.368184804916382, "learning_rate": 1.0187807881773399e-05, "loss": 1.4508, "step": 3193 }, { "epoch": 0.4913657167032037, "grad_norm": 3.399334192276001, "learning_rate": 1.018472906403941e-05, "loss": 1.3102, "step": 3194 }, { "epoch": 0.4915195569401177, "grad_norm": 3.2503509521484375, "learning_rate": 1.0181650246305418e-05, "loss": 1.3183, "step": 3195 }, { "epoch": 0.4916733971770317, "grad_norm": 3.2495765686035156, "learning_rate": 1.0178571428571429e-05, "loss": 1.0026, "step": 3196 }, { "epoch": 0.49182723741394563, "grad_norm": 4.550004959106445, "learning_rate": 1.0175492610837438e-05, "loss": 1.4063, "step": 3197 }, { "epoch": 0.4919810776508596, "grad_norm": 4.081529140472412, "learning_rate": 1.0172413793103449e-05, "loss": 1.5061, "step": 3198 }, { "epoch": 0.4921349178877735, "grad_norm": 3.2562153339385986, "learning_rate": 1.0169334975369458e-05, "loss": 1.4121, "step": 3199 }, { "epoch": 0.49228875812468753, "grad_norm": 5.4161481857299805, "learning_rate": 1.0166256157635468e-05, "loss": 1.2032, "step": 3200 }, { "epoch": 0.4924425983616015, "grad_norm": 3.3806426525115967, "learning_rate": 1.0163177339901477e-05, "loss": 1.4919, "step": 3201 }, { "epoch": 0.49259643859851543, "grad_norm": 3.8711371421813965, "learning_rate": 1.0160098522167488e-05, "loss": 1.4629, "step": 3202 }, { "epoch": 0.49275027883542943, "grad_norm": 3.6120405197143555, "learning_rate": 1.0157019704433497e-05, "loss": 1.1574, "step": 3203 }, { "epoch": 0.4929041190723434, "grad_norm": 4.042300224304199, "learning_rate": 1.015394088669951e-05, "loss": 1.5631, "step": 3204 }, { "epoch": 0.49305795930925733, "grad_norm": 3.2918708324432373, "learning_rate": 1.015086206896552e-05, "loss": 1.2013, "step": 3205 }, { "epoch": 0.4932117995461713, "grad_norm": 3.5593059062957764, "learning_rate": 1.0147783251231529e-05, "loss": 1.1338, "step": 3206 }, { "epoch": 0.4933656397830853, "grad_norm": 4.0498046875, "learning_rate": 1.014470443349754e-05, "loss": 1.4811, "step": 3207 }, { "epoch": 0.49351948001999923, "grad_norm": 3.4891347885131836, "learning_rate": 1.0141625615763548e-05, "loss": 1.3679, "step": 3208 }, { "epoch": 0.4936733202569132, "grad_norm": 3.6278772354125977, "learning_rate": 1.0138546798029559e-05, "loss": 1.2694, "step": 3209 }, { "epoch": 0.49382716049382713, "grad_norm": 3.478347063064575, "learning_rate": 1.0135467980295568e-05, "loss": 1.353, "step": 3210 }, { "epoch": 0.49398100073074114, "grad_norm": 3.154160499572754, "learning_rate": 1.0132389162561577e-05, "loss": 1.3018, "step": 3211 }, { "epoch": 0.4941348409676551, "grad_norm": 3.1367788314819336, "learning_rate": 1.0129310344827588e-05, "loss": 1.1596, "step": 3212 }, { "epoch": 0.49428868120456904, "grad_norm": 3.5821094512939453, "learning_rate": 1.0126231527093597e-05, "loss": 1.4581, "step": 3213 }, { "epoch": 0.49444252144148304, "grad_norm": 3.8320088386535645, "learning_rate": 1.0123152709359607e-05, "loss": 1.2877, "step": 3214 }, { "epoch": 0.494596361678397, "grad_norm": 3.911836624145508, "learning_rate": 1.0120073891625616e-05, "loss": 1.2525, "step": 3215 }, { "epoch": 0.49475020191531094, "grad_norm": 3.6573166847229004, "learning_rate": 1.0116995073891627e-05, "loss": 1.3668, "step": 3216 }, { "epoch": 0.4949040421522249, "grad_norm": 3.423146963119507, "learning_rate": 1.0113916256157636e-05, "loss": 0.9921, "step": 3217 }, { "epoch": 0.4950578823891389, "grad_norm": 3.4230096340179443, "learning_rate": 1.0110837438423646e-05, "loss": 1.1724, "step": 3218 }, { "epoch": 0.49521172262605284, "grad_norm": 3.9115939140319824, "learning_rate": 1.0107758620689655e-05, "loss": 1.2925, "step": 3219 }, { "epoch": 0.4953655628629668, "grad_norm": 3.1430611610412598, "learning_rate": 1.0104679802955666e-05, "loss": 1.2917, "step": 3220 }, { "epoch": 0.4955194030998808, "grad_norm": 3.6897871494293213, "learning_rate": 1.0101600985221675e-05, "loss": 1.4308, "step": 3221 }, { "epoch": 0.49567324333679474, "grad_norm": 4.921484470367432, "learning_rate": 1.0098522167487686e-05, "loss": 1.3455, "step": 3222 }, { "epoch": 0.4958270835737087, "grad_norm": 4.330341815948486, "learning_rate": 1.0095443349753695e-05, "loss": 1.454, "step": 3223 }, { "epoch": 0.49598092381062264, "grad_norm": 3.3574087619781494, "learning_rate": 1.0092364532019705e-05, "loss": 1.2549, "step": 3224 }, { "epoch": 0.49613476404753665, "grad_norm": 3.244455099105835, "learning_rate": 1.0089285714285714e-05, "loss": 1.3264, "step": 3225 }, { "epoch": 0.4962886042844506, "grad_norm": 3.7436561584472656, "learning_rate": 1.0086206896551725e-05, "loss": 1.2868, "step": 3226 }, { "epoch": 0.49644244452136455, "grad_norm": 3.3366281986236572, "learning_rate": 1.0083128078817734e-05, "loss": 1.2881, "step": 3227 }, { "epoch": 0.49659628475827855, "grad_norm": 4.042980670928955, "learning_rate": 1.0080049261083744e-05, "loss": 1.2408, "step": 3228 }, { "epoch": 0.4967501249951925, "grad_norm": 3.3136909008026123, "learning_rate": 1.0076970443349753e-05, "loss": 1.3945, "step": 3229 }, { "epoch": 0.49690396523210645, "grad_norm": 3.93772029876709, "learning_rate": 1.0073891625615764e-05, "loss": 1.3114, "step": 3230 }, { "epoch": 0.4970578054690204, "grad_norm": 3.3969368934631348, "learning_rate": 1.0070812807881773e-05, "loss": 1.4291, "step": 3231 }, { "epoch": 0.4972116457059344, "grad_norm": 3.9554429054260254, "learning_rate": 1.0067733990147784e-05, "loss": 1.505, "step": 3232 }, { "epoch": 0.49736548594284835, "grad_norm": 4.021063804626465, "learning_rate": 1.0064655172413793e-05, "loss": 1.336, "step": 3233 }, { "epoch": 0.4975193261797623, "grad_norm": 4.314566612243652, "learning_rate": 1.0061576354679803e-05, "loss": 1.3148, "step": 3234 }, { "epoch": 0.4976731664166763, "grad_norm": 4.266286849975586, "learning_rate": 1.0058497536945812e-05, "loss": 1.3657, "step": 3235 }, { "epoch": 0.49782700665359025, "grad_norm": 3.5568861961364746, "learning_rate": 1.0055418719211823e-05, "loss": 1.2694, "step": 3236 }, { "epoch": 0.4979808468905042, "grad_norm": 3.4143950939178467, "learning_rate": 1.0052339901477832e-05, "loss": 1.3969, "step": 3237 }, { "epoch": 0.49813468712741815, "grad_norm": 3.7830662727355957, "learning_rate": 1.0049261083743844e-05, "loss": 1.2902, "step": 3238 }, { "epoch": 0.49828852736433216, "grad_norm": 4.7166032791137695, "learning_rate": 1.0046182266009855e-05, "loss": 1.4687, "step": 3239 }, { "epoch": 0.4984423676012461, "grad_norm": 3.8002989292144775, "learning_rate": 1.0043103448275864e-05, "loss": 1.3121, "step": 3240 }, { "epoch": 0.49859620783816005, "grad_norm": 4.230720520019531, "learning_rate": 1.0040024630541874e-05, "loss": 1.2898, "step": 3241 }, { "epoch": 0.49875004807507406, "grad_norm": 3.371946334838867, "learning_rate": 1.0036945812807883e-05, "loss": 1.0847, "step": 3242 }, { "epoch": 0.498903888311988, "grad_norm": 3.371387004852295, "learning_rate": 1.0033866995073894e-05, "loss": 1.538, "step": 3243 }, { "epoch": 0.49905772854890196, "grad_norm": 3.500823497772217, "learning_rate": 1.0030788177339903e-05, "loss": 1.3139, "step": 3244 }, { "epoch": 0.4992115687858159, "grad_norm": 4.0938873291015625, "learning_rate": 1.0027709359605913e-05, "loss": 1.2738, "step": 3245 }, { "epoch": 0.4993654090227299, "grad_norm": 3.1110055446624756, "learning_rate": 1.0024630541871922e-05, "loss": 1.4932, "step": 3246 }, { "epoch": 0.49951924925964386, "grad_norm": 3.7636520862579346, "learning_rate": 1.0021551724137933e-05, "loss": 1.3912, "step": 3247 }, { "epoch": 0.4996730894965578, "grad_norm": 3.5894789695739746, "learning_rate": 1.0018472906403942e-05, "loss": 1.193, "step": 3248 }, { "epoch": 0.4998269297334718, "grad_norm": 4.210067272186279, "learning_rate": 1.0015394088669953e-05, "loss": 1.4906, "step": 3249 }, { "epoch": 0.49998076997038576, "grad_norm": 3.34395170211792, "learning_rate": 1.0012315270935962e-05, "loss": 1.1879, "step": 3250 }, { "epoch": 0.5001346102072998, "grad_norm": 3.4157721996307373, "learning_rate": 1.0009236453201972e-05, "loss": 1.3936, "step": 3251 }, { "epoch": 0.5002884504442137, "grad_norm": 3.6859328746795654, "learning_rate": 1.0006157635467981e-05, "loss": 1.2691, "step": 3252 }, { "epoch": 0.5004422906811277, "grad_norm": 3.266538143157959, "learning_rate": 1.0003078817733992e-05, "loss": 1.4932, "step": 3253 }, { "epoch": 0.5005961309180416, "grad_norm": 3.749131202697754, "learning_rate": 1e-05, "loss": 1.3492, "step": 3254 }, { "epoch": 0.5007499711549556, "grad_norm": 3.076359510421753, "learning_rate": 9.99692118226601e-06, "loss": 1.4319, "step": 3255 }, { "epoch": 0.5009038113918696, "grad_norm": 3.269036293029785, "learning_rate": 9.99384236453202e-06, "loss": 1.2001, "step": 3256 }, { "epoch": 0.5010576516287835, "grad_norm": 4.343016624450684, "learning_rate": 9.99076354679803e-06, "loss": 1.2444, "step": 3257 }, { "epoch": 0.5012114918656975, "grad_norm": 3.861266851425171, "learning_rate": 9.98768472906404e-06, "loss": 1.0753, "step": 3258 }, { "epoch": 0.5013653321026115, "grad_norm": 3.3832316398620605, "learning_rate": 9.984605911330049e-06, "loss": 1.3085, "step": 3259 }, { "epoch": 0.5015191723395254, "grad_norm": 3.9286999702453613, "learning_rate": 9.98152709359606e-06, "loss": 1.4738, "step": 3260 }, { "epoch": 0.5016730125764394, "grad_norm": 3.3426475524902344, "learning_rate": 9.978448275862069e-06, "loss": 1.4036, "step": 3261 }, { "epoch": 0.5018268528133534, "grad_norm": 3.677931547164917, "learning_rate": 9.97536945812808e-06, "loss": 1.4948, "step": 3262 }, { "epoch": 0.5019806930502673, "grad_norm": 4.847990036010742, "learning_rate": 9.97229064039409e-06, "loss": 1.22, "step": 3263 }, { "epoch": 0.5021345332871813, "grad_norm": 3.4761993885040283, "learning_rate": 9.9692118226601e-06, "loss": 1.1325, "step": 3264 }, { "epoch": 0.5022883735240953, "grad_norm": 3.5259721279144287, "learning_rate": 9.96613300492611e-06, "loss": 1.4925, "step": 3265 }, { "epoch": 0.5024422137610092, "grad_norm": 3.1041946411132812, "learning_rate": 9.96305418719212e-06, "loss": 1.415, "step": 3266 }, { "epoch": 0.5025960539979232, "grad_norm": 3.884690046310425, "learning_rate": 9.959975369458129e-06, "loss": 1.4815, "step": 3267 }, { "epoch": 0.5027498942348371, "grad_norm": 3.3878960609436035, "learning_rate": 9.95689655172414e-06, "loss": 1.2465, "step": 3268 }, { "epoch": 0.5029037344717511, "grad_norm": 2.9668173789978027, "learning_rate": 9.953817733990149e-06, "loss": 1.2667, "step": 3269 }, { "epoch": 0.5030575747086651, "grad_norm": 3.455934762954712, "learning_rate": 9.95073891625616e-06, "loss": 1.1634, "step": 3270 }, { "epoch": 0.503211414945579, "grad_norm": 3.875016450881958, "learning_rate": 9.947660098522168e-06, "loss": 1.3022, "step": 3271 }, { "epoch": 0.503365255182493, "grad_norm": 3.747222423553467, "learning_rate": 9.944581280788179e-06, "loss": 1.2358, "step": 3272 }, { "epoch": 0.503519095419407, "grad_norm": 4.181863784790039, "learning_rate": 9.941502463054188e-06, "loss": 1.3137, "step": 3273 }, { "epoch": 0.5036729356563209, "grad_norm": 4.2770466804504395, "learning_rate": 9.938423645320198e-06, "loss": 1.2608, "step": 3274 }, { "epoch": 0.5038267758932349, "grad_norm": 3.2302072048187256, "learning_rate": 9.935344827586207e-06, "loss": 1.2392, "step": 3275 }, { "epoch": 0.5039806161301489, "grad_norm": 3.7037529945373535, "learning_rate": 9.932266009852218e-06, "loss": 1.3596, "step": 3276 }, { "epoch": 0.5041344563670628, "grad_norm": 3.4247095584869385, "learning_rate": 9.929187192118227e-06, "loss": 1.4567, "step": 3277 }, { "epoch": 0.5042882966039768, "grad_norm": 3.928101062774658, "learning_rate": 9.926108374384236e-06, "loss": 1.5717, "step": 3278 }, { "epoch": 0.5044421368408908, "grad_norm": 3.9834046363830566, "learning_rate": 9.923029556650247e-06, "loss": 1.2859, "step": 3279 }, { "epoch": 0.5045959770778047, "grad_norm": 4.522737979888916, "learning_rate": 9.919950738916257e-06, "loss": 1.3693, "step": 3280 }, { "epoch": 0.5047498173147187, "grad_norm": 3.520845890045166, "learning_rate": 9.916871921182268e-06, "loss": 1.4548, "step": 3281 }, { "epoch": 0.5049036575516326, "grad_norm": 3.6388001441955566, "learning_rate": 9.913793103448277e-06, "loss": 1.254, "step": 3282 }, { "epoch": 0.5050574977885466, "grad_norm": 3.3327901363372803, "learning_rate": 9.910714285714288e-06, "loss": 1.2878, "step": 3283 }, { "epoch": 0.5052113380254606, "grad_norm": 3.7846741676330566, "learning_rate": 9.907635467980296e-06, "loss": 1.2786, "step": 3284 }, { "epoch": 0.5053651782623745, "grad_norm": 3.455054759979248, "learning_rate": 9.904556650246307e-06, "loss": 1.4105, "step": 3285 }, { "epoch": 0.5055190184992885, "grad_norm": 3.729130506515503, "learning_rate": 9.901477832512316e-06, "loss": 1.3955, "step": 3286 }, { "epoch": 0.5056728587362025, "grad_norm": 3.6509883403778076, "learning_rate": 9.898399014778327e-06, "loss": 1.331, "step": 3287 }, { "epoch": 0.5058266989731164, "grad_norm": 3.2256574630737305, "learning_rate": 9.895320197044336e-06, "loss": 1.4164, "step": 3288 }, { "epoch": 0.5059805392100304, "grad_norm": 2.9685819149017334, "learning_rate": 9.892241379310346e-06, "loss": 1.0779, "step": 3289 }, { "epoch": 0.5061343794469444, "grad_norm": 3.6588878631591797, "learning_rate": 9.889162561576355e-06, "loss": 1.3999, "step": 3290 }, { "epoch": 0.5062882196838583, "grad_norm": 4.417690753936768, "learning_rate": 9.886083743842366e-06, "loss": 2.1019, "step": 3291 }, { "epoch": 0.5064420599207723, "grad_norm": 3.6053900718688965, "learning_rate": 9.883004926108375e-06, "loss": 1.2793, "step": 3292 }, { "epoch": 0.5065959001576863, "grad_norm": 4.808923721313477, "learning_rate": 9.879926108374385e-06, "loss": 1.3175, "step": 3293 }, { "epoch": 0.5067497403946002, "grad_norm": 3.6897006034851074, "learning_rate": 9.876847290640394e-06, "loss": 1.5132, "step": 3294 }, { "epoch": 0.5069035806315142, "grad_norm": 3.9405012130737305, "learning_rate": 9.873768472906405e-06, "loss": 1.4686, "step": 3295 }, { "epoch": 0.5070574208684281, "grad_norm": 3.9257543087005615, "learning_rate": 9.870689655172414e-06, "loss": 1.3543, "step": 3296 }, { "epoch": 0.5072112611053421, "grad_norm": 4.228929042816162, "learning_rate": 9.867610837438425e-06, "loss": 1.1562, "step": 3297 }, { "epoch": 0.5073651013422561, "grad_norm": 3.3917431831359863, "learning_rate": 9.864532019704435e-06, "loss": 1.4021, "step": 3298 }, { "epoch": 0.50751894157917, "grad_norm": 3.343113899230957, "learning_rate": 9.861453201970444e-06, "loss": 1.2687, "step": 3299 }, { "epoch": 0.507672781816084, "grad_norm": 3.5934715270996094, "learning_rate": 9.858374384236455e-06, "loss": 1.3754, "step": 3300 }, { "epoch": 0.507826622052998, "grad_norm": 3.499523162841797, "learning_rate": 9.855295566502464e-06, "loss": 1.3849, "step": 3301 }, { "epoch": 0.5079804622899119, "grad_norm": 4.372005462646484, "learning_rate": 9.852216748768475e-06, "loss": 1.4822, "step": 3302 }, { "epoch": 0.5081343025268259, "grad_norm": 4.12865686416626, "learning_rate": 9.849137931034483e-06, "loss": 1.0413, "step": 3303 }, { "epoch": 0.5082881427637399, "grad_norm": 3.8755767345428467, "learning_rate": 9.846059113300494e-06, "loss": 1.438, "step": 3304 }, { "epoch": 0.5084419830006538, "grad_norm": 3.3592915534973145, "learning_rate": 9.842980295566503e-06, "loss": 1.3009, "step": 3305 }, { "epoch": 0.5085958232375678, "grad_norm": 3.14878511428833, "learning_rate": 9.839901477832514e-06, "loss": 1.0678, "step": 3306 }, { "epoch": 0.5087496634744818, "grad_norm": 3.4825279712677, "learning_rate": 9.836822660098523e-06, "loss": 1.4829, "step": 3307 }, { "epoch": 0.5089035037113957, "grad_norm": 4.354147434234619, "learning_rate": 9.833743842364533e-06, "loss": 1.3372, "step": 3308 }, { "epoch": 0.5090573439483097, "grad_norm": 4.404567718505859, "learning_rate": 9.830665024630542e-06, "loss": 1.3615, "step": 3309 }, { "epoch": 0.5092111841852236, "grad_norm": 3.5876636505126953, "learning_rate": 9.827586206896553e-06, "loss": 1.1983, "step": 3310 }, { "epoch": 0.5093650244221376, "grad_norm": 3.879549503326416, "learning_rate": 9.824507389162562e-06, "loss": 1.3906, "step": 3311 }, { "epoch": 0.5095188646590516, "grad_norm": 3.958773612976074, "learning_rate": 9.821428571428573e-06, "loss": 1.4394, "step": 3312 }, { "epoch": 0.5096727048959655, "grad_norm": 4.119036674499512, "learning_rate": 9.818349753694581e-06, "loss": 1.4576, "step": 3313 }, { "epoch": 0.5098265451328795, "grad_norm": 3.203617811203003, "learning_rate": 9.815270935960592e-06, "loss": 1.0894, "step": 3314 }, { "epoch": 0.5099803853697935, "grad_norm": 4.349696159362793, "learning_rate": 9.812192118226603e-06, "loss": 1.4219, "step": 3315 }, { "epoch": 0.5101342256067074, "grad_norm": 3.7660202980041504, "learning_rate": 9.809113300492612e-06, "loss": 1.2395, "step": 3316 }, { "epoch": 0.5102880658436214, "grad_norm": 3.467620611190796, "learning_rate": 9.806034482758622e-06, "loss": 1.4594, "step": 3317 }, { "epoch": 0.5104419060805354, "grad_norm": 3.591196298599243, "learning_rate": 9.802955665024631e-06, "loss": 1.3695, "step": 3318 }, { "epoch": 0.5105957463174493, "grad_norm": 3.2733631134033203, "learning_rate": 9.799876847290642e-06, "loss": 1.5546, "step": 3319 }, { "epoch": 0.5107495865543633, "grad_norm": 3.1443190574645996, "learning_rate": 9.796798029556651e-06, "loss": 1.2371, "step": 3320 }, { "epoch": 0.5109034267912772, "grad_norm": 3.4966273307800293, "learning_rate": 9.793719211822662e-06, "loss": 1.3704, "step": 3321 }, { "epoch": 0.5110572670281912, "grad_norm": 2.9706871509552, "learning_rate": 9.79064039408867e-06, "loss": 1.1984, "step": 3322 }, { "epoch": 0.5112111072651052, "grad_norm": 3.2456717491149902, "learning_rate": 9.787561576354681e-06, "loss": 1.4944, "step": 3323 }, { "epoch": 0.5113649475020191, "grad_norm": 3.7694056034088135, "learning_rate": 9.78448275862069e-06, "loss": 1.3032, "step": 3324 }, { "epoch": 0.5115187877389331, "grad_norm": 3.766306161880493, "learning_rate": 9.7814039408867e-06, "loss": 1.3309, "step": 3325 }, { "epoch": 0.5116726279758471, "grad_norm": 3.5681843757629395, "learning_rate": 9.77832512315271e-06, "loss": 1.2049, "step": 3326 }, { "epoch": 0.511826468212761, "grad_norm": 3.932727336883545, "learning_rate": 9.77524630541872e-06, "loss": 1.4243, "step": 3327 }, { "epoch": 0.511980308449675, "grad_norm": 3.2614970207214355, "learning_rate": 9.77216748768473e-06, "loss": 1.1308, "step": 3328 }, { "epoch": 0.512134148686589, "grad_norm": 3.0404484272003174, "learning_rate": 9.76908866995074e-06, "loss": 1.2453, "step": 3329 }, { "epoch": 0.5122879889235029, "grad_norm": 3.07330584526062, "learning_rate": 9.766009852216749e-06, "loss": 1.4877, "step": 3330 }, { "epoch": 0.5124418291604169, "grad_norm": 4.151969909667969, "learning_rate": 9.76293103448276e-06, "loss": 1.3868, "step": 3331 }, { "epoch": 0.5125956693973309, "grad_norm": 3.1996662616729736, "learning_rate": 9.75985221674877e-06, "loss": 1.2643, "step": 3332 }, { "epoch": 0.5127495096342448, "grad_norm": 3.4852044582366943, "learning_rate": 9.756773399014779e-06, "loss": 1.2767, "step": 3333 }, { "epoch": 0.5129033498711588, "grad_norm": 3.6051578521728516, "learning_rate": 9.75369458128079e-06, "loss": 1.18, "step": 3334 }, { "epoch": 0.5130571901080727, "grad_norm": 3.6448771953582764, "learning_rate": 9.750615763546799e-06, "loss": 1.2929, "step": 3335 }, { "epoch": 0.5132110303449867, "grad_norm": 3.6480770111083984, "learning_rate": 9.74753694581281e-06, "loss": 1.5092, "step": 3336 }, { "epoch": 0.5133648705819007, "grad_norm": 3.06877064704895, "learning_rate": 9.744458128078818e-06, "loss": 1.4334, "step": 3337 }, { "epoch": 0.5135187108188146, "grad_norm": 3.401691436767578, "learning_rate": 9.741379310344829e-06, "loss": 1.3209, "step": 3338 }, { "epoch": 0.5136725510557286, "grad_norm": 3.0973219871520996, "learning_rate": 9.738300492610838e-06, "loss": 1.2584, "step": 3339 }, { "epoch": 0.5138263912926426, "grad_norm": 3.3370614051818848, "learning_rate": 9.735221674876849e-06, "loss": 1.3149, "step": 3340 }, { "epoch": 0.5139802315295565, "grad_norm": 2.914862632751465, "learning_rate": 9.732142857142858e-06, "loss": 1.2904, "step": 3341 }, { "epoch": 0.5141340717664705, "grad_norm": 3.337226629257202, "learning_rate": 9.729064039408868e-06, "loss": 1.3014, "step": 3342 }, { "epoch": 0.5142879120033845, "grad_norm": 3.6035993099212646, "learning_rate": 9.725985221674877e-06, "loss": 1.3114, "step": 3343 }, { "epoch": 0.5144417522402984, "grad_norm": 3.0523746013641357, "learning_rate": 9.722906403940888e-06, "loss": 1.2889, "step": 3344 }, { "epoch": 0.5145955924772124, "grad_norm": 3.437119722366333, "learning_rate": 9.719827586206897e-06, "loss": 1.2837, "step": 3345 }, { "epoch": 0.5147494327141264, "grad_norm": 3.2714715003967285, "learning_rate": 9.716748768472907e-06, "loss": 1.3978, "step": 3346 }, { "epoch": 0.5149032729510403, "grad_norm": 3.4404377937316895, "learning_rate": 9.713669950738916e-06, "loss": 1.3021, "step": 3347 }, { "epoch": 0.5150571131879543, "grad_norm": 3.299565315246582, "learning_rate": 9.710591133004927e-06, "loss": 1.3324, "step": 3348 }, { "epoch": 0.5152109534248682, "grad_norm": 3.6466469764709473, "learning_rate": 9.707512315270938e-06, "loss": 1.3353, "step": 3349 }, { "epoch": 0.5153647936617822, "grad_norm": 3.962258815765381, "learning_rate": 9.704433497536947e-06, "loss": 1.1741, "step": 3350 }, { "epoch": 0.5155186338986962, "grad_norm": 3.756204605102539, "learning_rate": 9.701354679802957e-06, "loss": 1.1948, "step": 3351 }, { "epoch": 0.5156724741356101, "grad_norm": 3.5059287548065186, "learning_rate": 9.698275862068966e-06, "loss": 1.2931, "step": 3352 }, { "epoch": 0.5158263143725241, "grad_norm": 4.082690715789795, "learning_rate": 9.695197044334977e-06, "loss": 1.5369, "step": 3353 }, { "epoch": 0.5159801546094381, "grad_norm": 3.4887850284576416, "learning_rate": 9.692118226600986e-06, "loss": 1.347, "step": 3354 }, { "epoch": 0.516133994846352, "grad_norm": 3.6701886653900146, "learning_rate": 9.689039408866996e-06, "loss": 1.2198, "step": 3355 }, { "epoch": 0.516287835083266, "grad_norm": 3.497047185897827, "learning_rate": 9.685960591133005e-06, "loss": 1.353, "step": 3356 }, { "epoch": 0.51644167532018, "grad_norm": 4.025396347045898, "learning_rate": 9.682881773399016e-06, "loss": 1.4469, "step": 3357 }, { "epoch": 0.5165955155570939, "grad_norm": 3.3086893558502197, "learning_rate": 9.679802955665025e-06, "loss": 1.1877, "step": 3358 }, { "epoch": 0.5167493557940079, "grad_norm": 3.7698426246643066, "learning_rate": 9.676724137931036e-06, "loss": 1.4039, "step": 3359 }, { "epoch": 0.5169031960309219, "grad_norm": 4.199314117431641, "learning_rate": 9.673645320197045e-06, "loss": 1.3645, "step": 3360 }, { "epoch": 0.5170570362678358, "grad_norm": 3.4153878688812256, "learning_rate": 9.670566502463055e-06, "loss": 1.37, "step": 3361 }, { "epoch": 0.5172108765047498, "grad_norm": 3.1481685638427734, "learning_rate": 9.667487684729064e-06, "loss": 1.371, "step": 3362 }, { "epoch": 0.5173647167416637, "grad_norm": 3.868403196334839, "learning_rate": 9.664408866995075e-06, "loss": 1.2547, "step": 3363 }, { "epoch": 0.5175185569785777, "grad_norm": 3.0228543281555176, "learning_rate": 9.661330049261085e-06, "loss": 1.2566, "step": 3364 }, { "epoch": 0.5176723972154917, "grad_norm": 5.595076560974121, "learning_rate": 9.658251231527094e-06, "loss": 1.3676, "step": 3365 }, { "epoch": 0.5178262374524056, "grad_norm": 3.280932903289795, "learning_rate": 9.655172413793105e-06, "loss": 1.1733, "step": 3366 }, { "epoch": 0.5179800776893196, "grad_norm": 4.474147319793701, "learning_rate": 9.652093596059114e-06, "loss": 1.4044, "step": 3367 }, { "epoch": 0.5181339179262336, "grad_norm": 2.9009451866149902, "learning_rate": 9.649014778325125e-06, "loss": 1.3526, "step": 3368 }, { "epoch": 0.5182877581631475, "grad_norm": 3.175607919692993, "learning_rate": 9.645935960591134e-06, "loss": 1.2526, "step": 3369 }, { "epoch": 0.5184415984000615, "grad_norm": 4.319260120391846, "learning_rate": 9.642857142857144e-06, "loss": 1.4387, "step": 3370 }, { "epoch": 0.5185954386369755, "grad_norm": 3.951695680618286, "learning_rate": 9.639778325123153e-06, "loss": 1.2069, "step": 3371 }, { "epoch": 0.5187492788738894, "grad_norm": 3.8627676963806152, "learning_rate": 9.636699507389164e-06, "loss": 1.2055, "step": 3372 }, { "epoch": 0.5189031191108034, "grad_norm": 4.2547125816345215, "learning_rate": 9.633620689655173e-06, "loss": 1.4392, "step": 3373 }, { "epoch": 0.5190569593477175, "grad_norm": 3.9463672637939453, "learning_rate": 9.630541871921183e-06, "loss": 1.3626, "step": 3374 }, { "epoch": 0.5192107995846313, "grad_norm": 3.782515048980713, "learning_rate": 9.627463054187192e-06, "loss": 1.1697, "step": 3375 }, { "epoch": 0.5193646398215453, "grad_norm": 3.691983461380005, "learning_rate": 9.624384236453203e-06, "loss": 1.5211, "step": 3376 }, { "epoch": 0.5195184800584592, "grad_norm": 3.9507882595062256, "learning_rate": 9.621305418719212e-06, "loss": 1.3608, "step": 3377 }, { "epoch": 0.5196723202953732, "grad_norm": 3.0825095176696777, "learning_rate": 9.618226600985223e-06, "loss": 1.5086, "step": 3378 }, { "epoch": 0.5198261605322873, "grad_norm": 3.353193521499634, "learning_rate": 9.615147783251232e-06, "loss": 1.4169, "step": 3379 }, { "epoch": 0.5199800007692011, "grad_norm": 3.0859532356262207, "learning_rate": 9.612068965517242e-06, "loss": 1.4925, "step": 3380 }, { "epoch": 0.5201338410061151, "grad_norm": 3.2132437229156494, "learning_rate": 9.608990147783253e-06, "loss": 1.2773, "step": 3381 }, { "epoch": 0.5202876812430292, "grad_norm": 3.5525805950164795, "learning_rate": 9.605911330049262e-06, "loss": 1.3178, "step": 3382 }, { "epoch": 0.520441521479943, "grad_norm": 4.075992584228516, "learning_rate": 9.602832512315272e-06, "loss": 1.2392, "step": 3383 }, { "epoch": 0.520595361716857, "grad_norm": 3.2504374980926514, "learning_rate": 9.599753694581281e-06, "loss": 1.3288, "step": 3384 }, { "epoch": 0.5207492019537711, "grad_norm": 3.6122608184814453, "learning_rate": 9.596674876847292e-06, "loss": 1.428, "step": 3385 }, { "epoch": 0.520903042190685, "grad_norm": 3.3716371059417725, "learning_rate": 9.593596059113301e-06, "loss": 1.225, "step": 3386 }, { "epoch": 0.521056882427599, "grad_norm": 3.324760675430298, "learning_rate": 9.590517241379312e-06, "loss": 1.5605, "step": 3387 }, { "epoch": 0.5212107226645128, "grad_norm": 4.196281909942627, "learning_rate": 9.58743842364532e-06, "loss": 1.4518, "step": 3388 }, { "epoch": 0.5213645629014269, "grad_norm": 3.0999045372009277, "learning_rate": 9.584359605911331e-06, "loss": 1.2273, "step": 3389 }, { "epoch": 0.5215184031383409, "grad_norm": 3.6559367179870605, "learning_rate": 9.58128078817734e-06, "loss": 1.148, "step": 3390 }, { "epoch": 0.5216722433752548, "grad_norm": 3.456848621368408, "learning_rate": 9.57820197044335e-06, "loss": 1.3514, "step": 3391 }, { "epoch": 0.5218260836121688, "grad_norm": 3.721698045730591, "learning_rate": 9.57512315270936e-06, "loss": 1.3236, "step": 3392 }, { "epoch": 0.5219799238490828, "grad_norm": 3.747634172439575, "learning_rate": 9.57204433497537e-06, "loss": 1.4349, "step": 3393 }, { "epoch": 0.5221337640859967, "grad_norm": 3.334101915359497, "learning_rate": 9.56896551724138e-06, "loss": 1.5025, "step": 3394 }, { "epoch": 0.5222876043229107, "grad_norm": 3.6736817359924316, "learning_rate": 9.56588669950739e-06, "loss": 1.3496, "step": 3395 }, { "epoch": 0.5224414445598247, "grad_norm": 3.886545181274414, "learning_rate": 9.562807881773399e-06, "loss": 1.3963, "step": 3396 }, { "epoch": 0.5225952847967386, "grad_norm": 3.7930312156677246, "learning_rate": 9.55972906403941e-06, "loss": 1.2797, "step": 3397 }, { "epoch": 0.5227491250336526, "grad_norm": 3.0563273429870605, "learning_rate": 9.55665024630542e-06, "loss": 1.3287, "step": 3398 }, { "epoch": 0.5229029652705666, "grad_norm": 3.8201310634613037, "learning_rate": 9.55357142857143e-06, "loss": 1.369, "step": 3399 }, { "epoch": 0.5230568055074805, "grad_norm": 4.296203136444092, "learning_rate": 9.55049261083744e-06, "loss": 1.6908, "step": 3400 }, { "epoch": 0.5232106457443945, "grad_norm": 3.756959915161133, "learning_rate": 9.547413793103449e-06, "loss": 1.3631, "step": 3401 }, { "epoch": 0.5233644859813084, "grad_norm": 3.971907615661621, "learning_rate": 9.54433497536946e-06, "loss": 1.1653, "step": 3402 }, { "epoch": 0.5235183262182224, "grad_norm": 3.440662384033203, "learning_rate": 9.541256157635468e-06, "loss": 1.1506, "step": 3403 }, { "epoch": 0.5236721664551364, "grad_norm": 2.8640849590301514, "learning_rate": 9.538177339901479e-06, "loss": 1.4211, "step": 3404 }, { "epoch": 0.5238260066920503, "grad_norm": 3.936631679534912, "learning_rate": 9.535098522167488e-06, "loss": 1.4577, "step": 3405 }, { "epoch": 0.5239798469289643, "grad_norm": 3.5179812908172607, "learning_rate": 9.532019704433499e-06, "loss": 1.1864, "step": 3406 }, { "epoch": 0.5241336871658783, "grad_norm": 3.8031468391418457, "learning_rate": 9.528940886699508e-06, "loss": 1.2919, "step": 3407 }, { "epoch": 0.5242875274027922, "grad_norm": 3.7246479988098145, "learning_rate": 9.525862068965518e-06, "loss": 1.3666, "step": 3408 }, { "epoch": 0.5244413676397062, "grad_norm": 3.74118709564209, "learning_rate": 9.522783251231527e-06, "loss": 1.1237, "step": 3409 }, { "epoch": 0.5245952078766202, "grad_norm": 4.072653770446777, "learning_rate": 9.519704433497538e-06, "loss": 1.5446, "step": 3410 }, { "epoch": 0.5247490481135341, "grad_norm": 4.064450740814209, "learning_rate": 9.516625615763547e-06, "loss": 1.2378, "step": 3411 }, { "epoch": 0.5249028883504481, "grad_norm": 3.521205186843872, "learning_rate": 9.513546798029557e-06, "loss": 1.463, "step": 3412 }, { "epoch": 0.5250567285873621, "grad_norm": 4.060727596282959, "learning_rate": 9.510467980295566e-06, "loss": 1.3891, "step": 3413 }, { "epoch": 0.525210568824276, "grad_norm": 3.8193790912628174, "learning_rate": 9.507389162561577e-06, "loss": 1.6356, "step": 3414 }, { "epoch": 0.52536440906119, "grad_norm": 3.700585126876831, "learning_rate": 9.504310344827588e-06, "loss": 1.2156, "step": 3415 }, { "epoch": 0.5255182492981039, "grad_norm": 3.3637537956237793, "learning_rate": 9.501231527093597e-06, "loss": 1.2411, "step": 3416 }, { "epoch": 0.5256720895350179, "grad_norm": 3.8039181232452393, "learning_rate": 9.498152709359607e-06, "loss": 1.3649, "step": 3417 }, { "epoch": 0.5258259297719319, "grad_norm": 3.284330129623413, "learning_rate": 9.495073891625616e-06, "loss": 1.2751, "step": 3418 }, { "epoch": 0.5259797700088458, "grad_norm": 4.036962509155273, "learning_rate": 9.491995073891627e-06, "loss": 1.4192, "step": 3419 }, { "epoch": 0.5261336102457598, "grad_norm": 3.8217451572418213, "learning_rate": 9.488916256157636e-06, "loss": 1.5669, "step": 3420 }, { "epoch": 0.5262874504826738, "grad_norm": 4.170456886291504, "learning_rate": 9.485837438423646e-06, "loss": 1.5345, "step": 3421 }, { "epoch": 0.5264412907195877, "grad_norm": 3.281050682067871, "learning_rate": 9.482758620689655e-06, "loss": 1.0957, "step": 3422 }, { "epoch": 0.5265951309565017, "grad_norm": 3.691599130630493, "learning_rate": 9.479679802955666e-06, "loss": 1.1856, "step": 3423 }, { "epoch": 0.5267489711934157, "grad_norm": 3.223356246948242, "learning_rate": 9.476600985221675e-06, "loss": 1.3791, "step": 3424 }, { "epoch": 0.5269028114303296, "grad_norm": 3.247073173522949, "learning_rate": 9.473522167487686e-06, "loss": 1.2142, "step": 3425 }, { "epoch": 0.5270566516672436, "grad_norm": 3.5214123725891113, "learning_rate": 9.470443349753695e-06, "loss": 1.4035, "step": 3426 }, { "epoch": 0.5272104919041576, "grad_norm": 3.2368361949920654, "learning_rate": 9.467364532019705e-06, "loss": 1.1971, "step": 3427 }, { "epoch": 0.5273643321410715, "grad_norm": 3.0126848220825195, "learning_rate": 9.464285714285714e-06, "loss": 1.2563, "step": 3428 }, { "epoch": 0.5275181723779855, "grad_norm": 3.6099441051483154, "learning_rate": 9.461206896551725e-06, "loss": 1.3534, "step": 3429 }, { "epoch": 0.5276720126148994, "grad_norm": 3.55608868598938, "learning_rate": 9.458128078817734e-06, "loss": 1.6048, "step": 3430 }, { "epoch": 0.5278258528518134, "grad_norm": 3.3665616512298584, "learning_rate": 9.455049261083744e-06, "loss": 1.248, "step": 3431 }, { "epoch": 0.5279796930887274, "grad_norm": 3.439061403274536, "learning_rate": 9.451970443349755e-06, "loss": 1.2527, "step": 3432 }, { "epoch": 0.5281335333256413, "grad_norm": 4.515983581542969, "learning_rate": 9.448891625615764e-06, "loss": 1.511, "step": 3433 }, { "epoch": 0.5282873735625553, "grad_norm": 3.2301225662231445, "learning_rate": 9.445812807881775e-06, "loss": 1.4313, "step": 3434 }, { "epoch": 0.5284412137994693, "grad_norm": 3.392554759979248, "learning_rate": 9.442733990147784e-06, "loss": 1.4263, "step": 3435 }, { "epoch": 0.5285950540363832, "grad_norm": 3.547074556350708, "learning_rate": 9.439655172413794e-06, "loss": 1.3123, "step": 3436 }, { "epoch": 0.5287488942732972, "grad_norm": 3.8464016914367676, "learning_rate": 9.436576354679803e-06, "loss": 1.3581, "step": 3437 }, { "epoch": 0.5289027345102112, "grad_norm": 3.542283296585083, "learning_rate": 9.433497536945814e-06, "loss": 1.5887, "step": 3438 }, { "epoch": 0.5290565747471251, "grad_norm": 3.537409543991089, "learning_rate": 9.430418719211823e-06, "loss": 1.0772, "step": 3439 }, { "epoch": 0.5292104149840391, "grad_norm": 3.3041985034942627, "learning_rate": 9.427339901477833e-06, "loss": 1.2116, "step": 3440 }, { "epoch": 0.5293642552209531, "grad_norm": 3.267949104309082, "learning_rate": 9.424261083743842e-06, "loss": 1.2388, "step": 3441 }, { "epoch": 0.529518095457867, "grad_norm": 3.8093671798706055, "learning_rate": 9.421182266009853e-06, "loss": 1.3507, "step": 3442 }, { "epoch": 0.529671935694781, "grad_norm": 4.092608451843262, "learning_rate": 9.418103448275862e-06, "loss": 1.2931, "step": 3443 }, { "epoch": 0.5298257759316949, "grad_norm": 4.306981086730957, "learning_rate": 9.415024630541873e-06, "loss": 1.657, "step": 3444 }, { "epoch": 0.5299796161686089, "grad_norm": 3.436920166015625, "learning_rate": 9.411945812807882e-06, "loss": 1.4357, "step": 3445 }, { "epoch": 0.5301334564055229, "grad_norm": 3.384511709213257, "learning_rate": 9.408866995073892e-06, "loss": 1.5546, "step": 3446 }, { "epoch": 0.5302872966424368, "grad_norm": 3.7156906127929688, "learning_rate": 9.405788177339901e-06, "loss": 1.3539, "step": 3447 }, { "epoch": 0.5304411368793508, "grad_norm": 4.190361976623535, "learning_rate": 9.402709359605912e-06, "loss": 1.1878, "step": 3448 }, { "epoch": 0.5305949771162648, "grad_norm": 4.1100172996521, "learning_rate": 9.399630541871922e-06, "loss": 1.6052, "step": 3449 }, { "epoch": 0.5307488173531787, "grad_norm": 3.6669671535491943, "learning_rate": 9.396551724137931e-06, "loss": 1.2812, "step": 3450 }, { "epoch": 0.5309026575900927, "grad_norm": 3.434502363204956, "learning_rate": 9.393472906403942e-06, "loss": 1.4878, "step": 3451 }, { "epoch": 0.5310564978270067, "grad_norm": 3.2233126163482666, "learning_rate": 9.390394088669951e-06, "loss": 1.3273, "step": 3452 }, { "epoch": 0.5312103380639206, "grad_norm": 5.286413669586182, "learning_rate": 9.387315270935962e-06, "loss": 1.7206, "step": 3453 }, { "epoch": 0.5313641783008346, "grad_norm": 3.6511106491088867, "learning_rate": 9.38423645320197e-06, "loss": 1.2791, "step": 3454 }, { "epoch": 0.5315180185377485, "grad_norm": 4.099713325500488, "learning_rate": 9.381157635467981e-06, "loss": 1.4258, "step": 3455 }, { "epoch": 0.5316718587746625, "grad_norm": 3.933811664581299, "learning_rate": 9.37807881773399e-06, "loss": 1.4378, "step": 3456 }, { "epoch": 0.5318256990115765, "grad_norm": 3.015986204147339, "learning_rate": 9.375000000000001e-06, "loss": 1.0676, "step": 3457 }, { "epoch": 0.5319795392484904, "grad_norm": 3.455348014831543, "learning_rate": 9.37192118226601e-06, "loss": 1.5148, "step": 3458 }, { "epoch": 0.5321333794854044, "grad_norm": 3.060213088989258, "learning_rate": 9.36884236453202e-06, "loss": 1.2552, "step": 3459 }, { "epoch": 0.5322872197223184, "grad_norm": 3.4181954860687256, "learning_rate": 9.36576354679803e-06, "loss": 1.4406, "step": 3460 }, { "epoch": 0.5324410599592323, "grad_norm": 4.032406806945801, "learning_rate": 9.36268472906404e-06, "loss": 1.2766, "step": 3461 }, { "epoch": 0.5325949001961463, "grad_norm": 4.394097328186035, "learning_rate": 9.359605911330049e-06, "loss": 1.5435, "step": 3462 }, { "epoch": 0.5327487404330603, "grad_norm": 4.0099687576293945, "learning_rate": 9.35652709359606e-06, "loss": 1.38, "step": 3463 }, { "epoch": 0.5329025806699742, "grad_norm": 3.711998701095581, "learning_rate": 9.353448275862069e-06, "loss": 1.4952, "step": 3464 }, { "epoch": 0.5330564209068882, "grad_norm": 2.874385356903076, "learning_rate": 9.35036945812808e-06, "loss": 1.2368, "step": 3465 }, { "epoch": 0.5332102611438022, "grad_norm": 3.401904344558716, "learning_rate": 9.34729064039409e-06, "loss": 1.2331, "step": 3466 }, { "epoch": 0.5333641013807161, "grad_norm": 4.05726957321167, "learning_rate": 9.3442118226601e-06, "loss": 1.1634, "step": 3467 }, { "epoch": 0.5335179416176301, "grad_norm": 3.476160764694214, "learning_rate": 9.34113300492611e-06, "loss": 1.3066, "step": 3468 }, { "epoch": 0.533671781854544, "grad_norm": 3.922974109649658, "learning_rate": 9.33805418719212e-06, "loss": 1.3088, "step": 3469 }, { "epoch": 0.533825622091458, "grad_norm": 3.7085282802581787, "learning_rate": 9.334975369458129e-06, "loss": 1.0928, "step": 3470 }, { "epoch": 0.533979462328372, "grad_norm": 2.72578501701355, "learning_rate": 9.331896551724138e-06, "loss": 1.2739, "step": 3471 }, { "epoch": 0.5341333025652859, "grad_norm": 3.949820041656494, "learning_rate": 9.328817733990149e-06, "loss": 1.4616, "step": 3472 }, { "epoch": 0.5342871428021999, "grad_norm": 3.3810858726501465, "learning_rate": 9.325738916256158e-06, "loss": 1.3667, "step": 3473 }, { "epoch": 0.5344409830391139, "grad_norm": 3.418229103088379, "learning_rate": 9.322660098522168e-06, "loss": 1.4308, "step": 3474 }, { "epoch": 0.5345948232760278, "grad_norm": 3.121852159500122, "learning_rate": 9.319581280788177e-06, "loss": 1.0666, "step": 3475 }, { "epoch": 0.5347486635129418, "grad_norm": 3.437713146209717, "learning_rate": 9.316502463054188e-06, "loss": 1.4688, "step": 3476 }, { "epoch": 0.5349025037498558, "grad_norm": 3.8934543132781982, "learning_rate": 9.313423645320197e-06, "loss": 1.3018, "step": 3477 }, { "epoch": 0.5350563439867697, "grad_norm": 3.1300928592681885, "learning_rate": 9.310344827586207e-06, "loss": 1.238, "step": 3478 }, { "epoch": 0.5352101842236837, "grad_norm": 3.567540407180786, "learning_rate": 9.307266009852216e-06, "loss": 1.1944, "step": 3479 }, { "epoch": 0.5353640244605977, "grad_norm": 3.915663003921509, "learning_rate": 9.304187192118227e-06, "loss": 1.4131, "step": 3480 }, { "epoch": 0.5355178646975116, "grad_norm": 3.306020975112915, "learning_rate": 9.301108374384236e-06, "loss": 1.5006, "step": 3481 }, { "epoch": 0.5356717049344256, "grad_norm": 3.988647222518921, "learning_rate": 9.298029556650247e-06, "loss": 1.082, "step": 3482 }, { "epoch": 0.5358255451713395, "grad_norm": 3.1196420192718506, "learning_rate": 9.294950738916257e-06, "loss": 1.2649, "step": 3483 }, { "epoch": 0.5359793854082535, "grad_norm": 3.6049160957336426, "learning_rate": 9.291871921182268e-06, "loss": 1.2913, "step": 3484 }, { "epoch": 0.5361332256451675, "grad_norm": 3.368394613265991, "learning_rate": 9.288793103448277e-06, "loss": 1.1667, "step": 3485 }, { "epoch": 0.5362870658820814, "grad_norm": 3.6843984127044678, "learning_rate": 9.285714285714288e-06, "loss": 1.4379, "step": 3486 }, { "epoch": 0.5364409061189954, "grad_norm": 3.6497254371643066, "learning_rate": 9.282635467980297e-06, "loss": 1.2307, "step": 3487 }, { "epoch": 0.5365947463559094, "grad_norm": 4.3068060874938965, "learning_rate": 9.279556650246307e-06, "loss": 1.3814, "step": 3488 }, { "epoch": 0.5367485865928233, "grad_norm": 3.9851315021514893, "learning_rate": 9.276477832512316e-06, "loss": 1.1562, "step": 3489 }, { "epoch": 0.5369024268297373, "grad_norm": 3.4890079498291016, "learning_rate": 9.273399014778327e-06, "loss": 1.4536, "step": 3490 }, { "epoch": 0.5370562670666513, "grad_norm": 3.5040905475616455, "learning_rate": 9.270320197044336e-06, "loss": 1.3617, "step": 3491 }, { "epoch": 0.5372101073035652, "grad_norm": 3.249941825866699, "learning_rate": 9.267241379310346e-06, "loss": 1.2409, "step": 3492 }, { "epoch": 0.5373639475404792, "grad_norm": 3.9499523639678955, "learning_rate": 9.264162561576355e-06, "loss": 1.3108, "step": 3493 }, { "epoch": 0.5375177877773932, "grad_norm": 4.34908390045166, "learning_rate": 9.261083743842364e-06, "loss": 1.5532, "step": 3494 }, { "epoch": 0.5376716280143071, "grad_norm": 3.4046549797058105, "learning_rate": 9.258004926108375e-06, "loss": 1.3511, "step": 3495 }, { "epoch": 0.5378254682512211, "grad_norm": 4.383420467376709, "learning_rate": 9.254926108374384e-06, "loss": 1.1591, "step": 3496 }, { "epoch": 0.537979308488135, "grad_norm": 2.986661434173584, "learning_rate": 9.251847290640394e-06, "loss": 1.1686, "step": 3497 }, { "epoch": 0.538133148725049, "grad_norm": 3.6481335163116455, "learning_rate": 9.248768472906403e-06, "loss": 1.3078, "step": 3498 }, { "epoch": 0.538286988961963, "grad_norm": 3.5710158348083496, "learning_rate": 9.245689655172414e-06, "loss": 1.4126, "step": 3499 }, { "epoch": 0.5384408291988769, "grad_norm": 3.682429313659668, "learning_rate": 9.242610837438425e-06, "loss": 1.339, "step": 3500 }, { "epoch": 0.5385946694357909, "grad_norm": 3.231109857559204, "learning_rate": 9.239532019704435e-06, "loss": 1.4034, "step": 3501 }, { "epoch": 0.5387485096727049, "grad_norm": 3.7497506141662598, "learning_rate": 9.236453201970444e-06, "loss": 1.1607, "step": 3502 }, { "epoch": 0.5389023499096188, "grad_norm": 3.800417900085449, "learning_rate": 9.233374384236455e-06, "loss": 1.6926, "step": 3503 }, { "epoch": 0.5390561901465328, "grad_norm": 3.4992921352386475, "learning_rate": 9.230295566502464e-06, "loss": 1.5274, "step": 3504 }, { "epoch": 0.5392100303834468, "grad_norm": 4.389989852905273, "learning_rate": 9.227216748768475e-06, "loss": 1.3636, "step": 3505 }, { "epoch": 0.5393638706203607, "grad_norm": 3.369168281555176, "learning_rate": 9.224137931034484e-06, "loss": 1.3121, "step": 3506 }, { "epoch": 0.5395177108572747, "grad_norm": 2.788666009902954, "learning_rate": 9.221059113300494e-06, "loss": 1.0834, "step": 3507 }, { "epoch": 0.5396715510941887, "grad_norm": 4.059689998626709, "learning_rate": 9.217980295566503e-06, "loss": 1.3638, "step": 3508 }, { "epoch": 0.5398253913311026, "grad_norm": 3.3848366737365723, "learning_rate": 9.214901477832514e-06, "loss": 1.4569, "step": 3509 }, { "epoch": 0.5399792315680166, "grad_norm": 3.4282655715942383, "learning_rate": 9.211822660098523e-06, "loss": 1.2939, "step": 3510 }, { "epoch": 0.5401330718049305, "grad_norm": 3.781740427017212, "learning_rate": 9.208743842364533e-06, "loss": 1.3141, "step": 3511 }, { "epoch": 0.5402869120418445, "grad_norm": 2.9434850215911865, "learning_rate": 9.205665024630542e-06, "loss": 1.134, "step": 3512 }, { "epoch": 0.5404407522787585, "grad_norm": 3.893066167831421, "learning_rate": 9.202586206896553e-06, "loss": 1.1864, "step": 3513 }, { "epoch": 0.5405945925156724, "grad_norm": 3.0091981887817383, "learning_rate": 9.199507389162562e-06, "loss": 1.3914, "step": 3514 }, { "epoch": 0.5407484327525864, "grad_norm": 3.7539517879486084, "learning_rate": 9.196428571428571e-06, "loss": 1.4341, "step": 3515 }, { "epoch": 0.5409022729895004, "grad_norm": 3.4269776344299316, "learning_rate": 9.193349753694582e-06, "loss": 1.3127, "step": 3516 }, { "epoch": 0.5410561132264143, "grad_norm": 2.991769313812256, "learning_rate": 9.190270935960592e-06, "loss": 1.3125, "step": 3517 }, { "epoch": 0.5412099534633283, "grad_norm": 3.6744041442871094, "learning_rate": 9.187192118226603e-06, "loss": 1.4631, "step": 3518 }, { "epoch": 0.5413637937002423, "grad_norm": 3.6822474002838135, "learning_rate": 9.184113300492612e-06, "loss": 1.4123, "step": 3519 }, { "epoch": 0.5415176339371562, "grad_norm": 3.3018438816070557, "learning_rate": 9.181034482758622e-06, "loss": 1.4999, "step": 3520 }, { "epoch": 0.5416714741740702, "grad_norm": 3.3993475437164307, "learning_rate": 9.177955665024631e-06, "loss": 1.3988, "step": 3521 }, { "epoch": 0.5418253144109841, "grad_norm": 3.565580368041992, "learning_rate": 9.174876847290642e-06, "loss": 1.3438, "step": 3522 }, { "epoch": 0.5419791546478981, "grad_norm": 4.155184268951416, "learning_rate": 9.171798029556651e-06, "loss": 1.3902, "step": 3523 }, { "epoch": 0.5421329948848121, "grad_norm": 3.7304024696350098, "learning_rate": 9.168719211822662e-06, "loss": 1.3585, "step": 3524 }, { "epoch": 0.542286835121726, "grad_norm": 3.4380218982696533, "learning_rate": 9.16564039408867e-06, "loss": 1.2614, "step": 3525 }, { "epoch": 0.54244067535864, "grad_norm": 3.161146640777588, "learning_rate": 9.162561576354681e-06, "loss": 1.4831, "step": 3526 }, { "epoch": 0.542594515595554, "grad_norm": 4.655671119689941, "learning_rate": 9.15948275862069e-06, "loss": 1.8582, "step": 3527 }, { "epoch": 0.5427483558324679, "grad_norm": 3.424332857131958, "learning_rate": 9.1564039408867e-06, "loss": 1.504, "step": 3528 }, { "epoch": 0.542902196069382, "grad_norm": 3.258298635482788, "learning_rate": 9.15332512315271e-06, "loss": 1.2469, "step": 3529 }, { "epoch": 0.543056036306296, "grad_norm": 4.3779449462890625, "learning_rate": 9.15024630541872e-06, "loss": 1.325, "step": 3530 }, { "epoch": 0.5432098765432098, "grad_norm": 3.6275107860565186, "learning_rate": 9.14716748768473e-06, "loss": 1.3587, "step": 3531 }, { "epoch": 0.5433637167801239, "grad_norm": 3.5423285961151123, "learning_rate": 9.14408866995074e-06, "loss": 1.3077, "step": 3532 }, { "epoch": 0.5435175570170379, "grad_norm": 3.0628786087036133, "learning_rate": 9.141009852216749e-06, "loss": 1.2941, "step": 3533 }, { "epoch": 0.5436713972539517, "grad_norm": 3.732879877090454, "learning_rate": 9.13793103448276e-06, "loss": 1.2343, "step": 3534 }, { "epoch": 0.5438252374908658, "grad_norm": 4.277620792388916, "learning_rate": 9.13485221674877e-06, "loss": 1.2638, "step": 3535 }, { "epoch": 0.5439790777277796, "grad_norm": 4.438801288604736, "learning_rate": 9.13177339901478e-06, "loss": 1.3477, "step": 3536 }, { "epoch": 0.5441329179646937, "grad_norm": 4.157886981964111, "learning_rate": 9.12869458128079e-06, "loss": 1.4036, "step": 3537 }, { "epoch": 0.5442867582016077, "grad_norm": 3.5731210708618164, "learning_rate": 9.125615763546799e-06, "loss": 1.4504, "step": 3538 }, { "epoch": 0.5444405984385216, "grad_norm": 3.3336501121520996, "learning_rate": 9.12253694581281e-06, "loss": 1.1582, "step": 3539 }, { "epoch": 0.5445944386754356, "grad_norm": 4.246294975280762, "learning_rate": 9.119458128078818e-06, "loss": 0.9223, "step": 3540 }, { "epoch": 0.5447482789123496, "grad_norm": 3.468317747116089, "learning_rate": 9.116379310344829e-06, "loss": 1.4266, "step": 3541 }, { "epoch": 0.5449021191492635, "grad_norm": 3.325530529022217, "learning_rate": 9.113300492610838e-06, "loss": 1.5004, "step": 3542 }, { "epoch": 0.5450559593861775, "grad_norm": 3.8801474571228027, "learning_rate": 9.110221674876849e-06, "loss": 1.3379, "step": 3543 }, { "epoch": 0.5452097996230915, "grad_norm": 3.178492307662964, "learning_rate": 9.107142857142858e-06, "loss": 1.3751, "step": 3544 }, { "epoch": 0.5453636398600054, "grad_norm": 3.1846377849578857, "learning_rate": 9.104064039408868e-06, "loss": 1.2132, "step": 3545 }, { "epoch": 0.5455174800969194, "grad_norm": 3.3802857398986816, "learning_rate": 9.100985221674877e-06, "loss": 1.5826, "step": 3546 }, { "epoch": 0.5456713203338334, "grad_norm": 3.306863784790039, "learning_rate": 9.097906403940888e-06, "loss": 1.1616, "step": 3547 }, { "epoch": 0.5458251605707473, "grad_norm": 3.5090184211730957, "learning_rate": 9.094827586206897e-06, "loss": 1.4415, "step": 3548 }, { "epoch": 0.5459790008076613, "grad_norm": 3.275782823562622, "learning_rate": 9.091748768472907e-06, "loss": 1.1239, "step": 3549 }, { "epoch": 0.5461328410445752, "grad_norm": 3.998577117919922, "learning_rate": 9.088669950738916e-06, "loss": 1.2688, "step": 3550 }, { "epoch": 0.5462866812814892, "grad_norm": 3.5752789974212646, "learning_rate": 9.085591133004927e-06, "loss": 1.5409, "step": 3551 }, { "epoch": 0.5464405215184032, "grad_norm": 4.181230545043945, "learning_rate": 9.082512315270938e-06, "loss": 1.2092, "step": 3552 }, { "epoch": 0.5465943617553171, "grad_norm": 3.2739651203155518, "learning_rate": 9.079433497536947e-06, "loss": 1.428, "step": 3553 }, { "epoch": 0.5467482019922311, "grad_norm": 3.5499706268310547, "learning_rate": 9.076354679802957e-06, "loss": 1.0458, "step": 3554 }, { "epoch": 0.5469020422291451, "grad_norm": 3.1813507080078125, "learning_rate": 9.073275862068966e-06, "loss": 1.3832, "step": 3555 }, { "epoch": 0.547055882466059, "grad_norm": 3.88196063041687, "learning_rate": 9.070197044334977e-06, "loss": 0.9745, "step": 3556 }, { "epoch": 0.547209722702973, "grad_norm": 3.3344764709472656, "learning_rate": 9.067118226600986e-06, "loss": 1.3541, "step": 3557 }, { "epoch": 0.547363562939887, "grad_norm": 3.653745651245117, "learning_rate": 9.064039408866996e-06, "loss": 1.1273, "step": 3558 }, { "epoch": 0.5475174031768009, "grad_norm": 4.123040676116943, "learning_rate": 9.060960591133005e-06, "loss": 1.6801, "step": 3559 }, { "epoch": 0.5476712434137149, "grad_norm": 3.241154909133911, "learning_rate": 9.057881773399016e-06, "loss": 1.2427, "step": 3560 }, { "epoch": 0.5478250836506289, "grad_norm": 4.451097011566162, "learning_rate": 9.054802955665025e-06, "loss": 1.5263, "step": 3561 }, { "epoch": 0.5479789238875428, "grad_norm": 3.805267810821533, "learning_rate": 9.051724137931036e-06, "loss": 1.1946, "step": 3562 }, { "epoch": 0.5481327641244568, "grad_norm": 3.6376001834869385, "learning_rate": 9.048645320197045e-06, "loss": 1.4255, "step": 3563 }, { "epoch": 0.5482866043613707, "grad_norm": 3.520690441131592, "learning_rate": 9.045566502463055e-06, "loss": 1.218, "step": 3564 }, { "epoch": 0.5484404445982847, "grad_norm": 3.0577337741851807, "learning_rate": 9.042487684729064e-06, "loss": 1.0261, "step": 3565 }, { "epoch": 0.5485942848351987, "grad_norm": 3.5769026279449463, "learning_rate": 9.039408866995075e-06, "loss": 1.3283, "step": 3566 }, { "epoch": 0.5487481250721126, "grad_norm": 3.3907461166381836, "learning_rate": 9.036330049261085e-06, "loss": 1.4515, "step": 3567 }, { "epoch": 0.5489019653090266, "grad_norm": 3.55068039894104, "learning_rate": 9.033251231527094e-06, "loss": 1.3969, "step": 3568 }, { "epoch": 0.5490558055459406, "grad_norm": 4.214853763580322, "learning_rate": 9.030172413793105e-06, "loss": 1.1653, "step": 3569 }, { "epoch": 0.5492096457828545, "grad_norm": 3.3984928131103516, "learning_rate": 9.027093596059114e-06, "loss": 1.2548, "step": 3570 }, { "epoch": 0.5493634860197685, "grad_norm": 3.0598294734954834, "learning_rate": 9.024014778325125e-06, "loss": 1.1739, "step": 3571 }, { "epoch": 0.5495173262566825, "grad_norm": 3.4405035972595215, "learning_rate": 9.020935960591134e-06, "loss": 1.3573, "step": 3572 }, { "epoch": 0.5496711664935964, "grad_norm": 3.485731840133667, "learning_rate": 9.017857142857144e-06, "loss": 1.5058, "step": 3573 }, { "epoch": 0.5498250067305104, "grad_norm": 3.822007417678833, "learning_rate": 9.014778325123153e-06, "loss": 1.0624, "step": 3574 }, { "epoch": 0.5499788469674244, "grad_norm": 3.9782490730285645, "learning_rate": 9.011699507389164e-06, "loss": 1.5491, "step": 3575 }, { "epoch": 0.5501326872043383, "grad_norm": 3.299978494644165, "learning_rate": 9.008620689655173e-06, "loss": 1.262, "step": 3576 }, { "epoch": 0.5502865274412523, "grad_norm": 3.9761343002319336, "learning_rate": 9.005541871921183e-06, "loss": 1.3068, "step": 3577 }, { "epoch": 0.5504403676781662, "grad_norm": 3.0843563079833984, "learning_rate": 9.002463054187192e-06, "loss": 1.2634, "step": 3578 }, { "epoch": 0.5505942079150802, "grad_norm": 4.32820463180542, "learning_rate": 8.999384236453203e-06, "loss": 1.2512, "step": 3579 }, { "epoch": 0.5507480481519942, "grad_norm": 3.556795597076416, "learning_rate": 8.996305418719212e-06, "loss": 1.5467, "step": 3580 }, { "epoch": 0.5509018883889081, "grad_norm": 3.2335691452026367, "learning_rate": 8.993226600985223e-06, "loss": 1.3381, "step": 3581 }, { "epoch": 0.5510557286258221, "grad_norm": 3.629345178604126, "learning_rate": 8.990147783251232e-06, "loss": 1.2055, "step": 3582 }, { "epoch": 0.5512095688627361, "grad_norm": 2.897188901901245, "learning_rate": 8.987068965517242e-06, "loss": 1.3105, "step": 3583 }, { "epoch": 0.55136340909965, "grad_norm": 3.4464962482452393, "learning_rate": 8.983990147783253e-06, "loss": 1.1327, "step": 3584 }, { "epoch": 0.551517249336564, "grad_norm": 2.9523980617523193, "learning_rate": 8.980911330049262e-06, "loss": 1.2962, "step": 3585 }, { "epoch": 0.551671089573478, "grad_norm": 3.544611930847168, "learning_rate": 8.977832512315272e-06, "loss": 1.147, "step": 3586 }, { "epoch": 0.5518249298103919, "grad_norm": 3.6061697006225586, "learning_rate": 8.974753694581281e-06, "loss": 1.4021, "step": 3587 }, { "epoch": 0.5519787700473059, "grad_norm": 3.6446304321289062, "learning_rate": 8.971674876847292e-06, "loss": 1.2521, "step": 3588 }, { "epoch": 0.5521326102842198, "grad_norm": 3.05806827545166, "learning_rate": 8.968596059113301e-06, "loss": 1.1749, "step": 3589 }, { "epoch": 0.5522864505211338, "grad_norm": 3.688326597213745, "learning_rate": 8.965517241379312e-06, "loss": 1.3734, "step": 3590 }, { "epoch": 0.5524402907580478, "grad_norm": 3.6764626502990723, "learning_rate": 8.96243842364532e-06, "loss": 1.2787, "step": 3591 }, { "epoch": 0.5525941309949617, "grad_norm": 4.30204963684082, "learning_rate": 8.959359605911331e-06, "loss": 1.5102, "step": 3592 }, { "epoch": 0.5527479712318757, "grad_norm": 3.8202435970306396, "learning_rate": 8.95628078817734e-06, "loss": 1.2922, "step": 3593 }, { "epoch": 0.5529018114687897, "grad_norm": 3.631420135498047, "learning_rate": 8.953201970443351e-06, "loss": 1.3967, "step": 3594 }, { "epoch": 0.5530556517057036, "grad_norm": 4.404860973358154, "learning_rate": 8.95012315270936e-06, "loss": 1.535, "step": 3595 }, { "epoch": 0.5532094919426176, "grad_norm": 3.361480474472046, "learning_rate": 8.94704433497537e-06, "loss": 1.1293, "step": 3596 }, { "epoch": 0.5533633321795316, "grad_norm": 4.775444030761719, "learning_rate": 8.94396551724138e-06, "loss": 1.2615, "step": 3597 }, { "epoch": 0.5535171724164455, "grad_norm": 3.9331579208374023, "learning_rate": 8.94088669950739e-06, "loss": 1.3074, "step": 3598 }, { "epoch": 0.5536710126533595, "grad_norm": 3.128840208053589, "learning_rate": 8.937807881773399e-06, "loss": 1.3262, "step": 3599 }, { "epoch": 0.5538248528902735, "grad_norm": 3.9784140586853027, "learning_rate": 8.93472906403941e-06, "loss": 1.7952, "step": 3600 }, { "epoch": 0.5539786931271874, "grad_norm": 3.8980491161346436, "learning_rate": 8.93165024630542e-06, "loss": 1.0837, "step": 3601 }, { "epoch": 0.5541325333641014, "grad_norm": 3.654690742492676, "learning_rate": 8.92857142857143e-06, "loss": 1.3247, "step": 3602 }, { "epoch": 0.5542863736010153, "grad_norm": 3.638394832611084, "learning_rate": 8.92549261083744e-06, "loss": 1.0567, "step": 3603 }, { "epoch": 0.5544402138379293, "grad_norm": 3.4926955699920654, "learning_rate": 8.922413793103449e-06, "loss": 1.4621, "step": 3604 }, { "epoch": 0.5545940540748433, "grad_norm": 3.7965548038482666, "learning_rate": 8.91933497536946e-06, "loss": 1.1472, "step": 3605 }, { "epoch": 0.5547478943117572, "grad_norm": 4.149654865264893, "learning_rate": 8.916256157635468e-06, "loss": 1.268, "step": 3606 }, { "epoch": 0.5549017345486712, "grad_norm": 3.384660005569458, "learning_rate": 8.913177339901479e-06, "loss": 1.3402, "step": 3607 }, { "epoch": 0.5550555747855852, "grad_norm": 3.8285415172576904, "learning_rate": 8.910098522167488e-06, "loss": 1.2706, "step": 3608 }, { "epoch": 0.5552094150224991, "grad_norm": 3.530561685562134, "learning_rate": 8.907019704433499e-06, "loss": 1.3704, "step": 3609 }, { "epoch": 0.5553632552594131, "grad_norm": 3.6203978061676025, "learning_rate": 8.903940886699508e-06, "loss": 1.6127, "step": 3610 }, { "epoch": 0.5555170954963271, "grad_norm": 3.5496811866760254, "learning_rate": 8.900862068965518e-06, "loss": 1.256, "step": 3611 }, { "epoch": 0.555670935733241, "grad_norm": 3.3701703548431396, "learning_rate": 8.897783251231527e-06, "loss": 1.332, "step": 3612 }, { "epoch": 0.555824775970155, "grad_norm": 4.607083797454834, "learning_rate": 8.894704433497538e-06, "loss": 1.599, "step": 3613 }, { "epoch": 0.555978616207069, "grad_norm": 3.2740375995635986, "learning_rate": 8.891625615763547e-06, "loss": 1.2273, "step": 3614 }, { "epoch": 0.5561324564439829, "grad_norm": 4.115485191345215, "learning_rate": 8.888546798029557e-06, "loss": 1.4542, "step": 3615 }, { "epoch": 0.5562862966808969, "grad_norm": 3.5186893939971924, "learning_rate": 8.885467980295566e-06, "loss": 1.2587, "step": 3616 }, { "epoch": 0.5564401369178108, "grad_norm": 3.2699620723724365, "learning_rate": 8.882389162561577e-06, "loss": 1.1987, "step": 3617 }, { "epoch": 0.5565939771547248, "grad_norm": 2.9813785552978516, "learning_rate": 8.879310344827588e-06, "loss": 1.4339, "step": 3618 }, { "epoch": 0.5567478173916388, "grad_norm": 3.147096633911133, "learning_rate": 8.876231527093597e-06, "loss": 1.1852, "step": 3619 }, { "epoch": 0.5569016576285527, "grad_norm": 4.102357387542725, "learning_rate": 8.873152709359607e-06, "loss": 1.3373, "step": 3620 }, { "epoch": 0.5570554978654667, "grad_norm": 3.4811320304870605, "learning_rate": 8.870073891625616e-06, "loss": 1.3797, "step": 3621 }, { "epoch": 0.5572093381023807, "grad_norm": 3.097801923751831, "learning_rate": 8.866995073891627e-06, "loss": 1.2021, "step": 3622 }, { "epoch": 0.5573631783392946, "grad_norm": 3.525888442993164, "learning_rate": 8.863916256157636e-06, "loss": 1.1124, "step": 3623 }, { "epoch": 0.5575170185762086, "grad_norm": 3.656705141067505, "learning_rate": 8.860837438423646e-06, "loss": 1.2326, "step": 3624 }, { "epoch": 0.5576708588131226, "grad_norm": 4.2068562507629395, "learning_rate": 8.857758620689655e-06, "loss": 1.2274, "step": 3625 }, { "epoch": 0.5578246990500365, "grad_norm": 3.3438024520874023, "learning_rate": 8.854679802955666e-06, "loss": 1.3084, "step": 3626 }, { "epoch": 0.5579785392869505, "grad_norm": 3.3861582279205322, "learning_rate": 8.851600985221675e-06, "loss": 1.5919, "step": 3627 }, { "epoch": 0.5581323795238645, "grad_norm": 4.2191996574401855, "learning_rate": 8.848522167487686e-06, "loss": 1.2413, "step": 3628 }, { "epoch": 0.5582862197607784, "grad_norm": 3.939181327819824, "learning_rate": 8.845443349753695e-06, "loss": 1.1065, "step": 3629 }, { "epoch": 0.5584400599976924, "grad_norm": 4.126258373260498, "learning_rate": 8.842364532019705e-06, "loss": 1.2474, "step": 3630 }, { "epoch": 0.5585939002346063, "grad_norm": 3.724064350128174, "learning_rate": 8.839285714285714e-06, "loss": 1.5788, "step": 3631 }, { "epoch": 0.5587477404715203, "grad_norm": 3.9678738117218018, "learning_rate": 8.836206896551725e-06, "loss": 1.4461, "step": 3632 }, { "epoch": 0.5589015807084343, "grad_norm": 3.268228054046631, "learning_rate": 8.833128078817734e-06, "loss": 1.4206, "step": 3633 }, { "epoch": 0.5590554209453482, "grad_norm": 2.90409255027771, "learning_rate": 8.830049261083744e-06, "loss": 1.054, "step": 3634 }, { "epoch": 0.5592092611822622, "grad_norm": 3.569767475128174, "learning_rate": 8.826970443349755e-06, "loss": 1.4347, "step": 3635 }, { "epoch": 0.5593631014191762, "grad_norm": 3.791353464126587, "learning_rate": 8.823891625615764e-06, "loss": 1.1704, "step": 3636 }, { "epoch": 0.5595169416560901, "grad_norm": 4.251866340637207, "learning_rate": 8.820812807881775e-06, "loss": 1.1394, "step": 3637 }, { "epoch": 0.5596707818930041, "grad_norm": 3.744577169418335, "learning_rate": 8.817733990147784e-06, "loss": 1.307, "step": 3638 }, { "epoch": 0.5598246221299181, "grad_norm": 3.4787678718566895, "learning_rate": 8.814655172413794e-06, "loss": 1.1356, "step": 3639 }, { "epoch": 0.559978462366832, "grad_norm": 3.697922468185425, "learning_rate": 8.811576354679803e-06, "loss": 1.2844, "step": 3640 }, { "epoch": 0.560132302603746, "grad_norm": 3.9024550914764404, "learning_rate": 8.808497536945814e-06, "loss": 1.581, "step": 3641 }, { "epoch": 0.56028614284066, "grad_norm": 4.129692077636719, "learning_rate": 8.805418719211823e-06, "loss": 1.0072, "step": 3642 }, { "epoch": 0.5604399830775739, "grad_norm": 3.7371151447296143, "learning_rate": 8.802339901477834e-06, "loss": 1.4485, "step": 3643 }, { "epoch": 0.5605938233144879, "grad_norm": 4.010958194732666, "learning_rate": 8.799261083743842e-06, "loss": 1.283, "step": 3644 }, { "epoch": 0.5607476635514018, "grad_norm": 4.857125282287598, "learning_rate": 8.796182266009853e-06, "loss": 1.2095, "step": 3645 }, { "epoch": 0.5609015037883158, "grad_norm": 4.478651523590088, "learning_rate": 8.793103448275862e-06, "loss": 1.2108, "step": 3646 }, { "epoch": 0.5610553440252298, "grad_norm": 3.105128288269043, "learning_rate": 8.790024630541873e-06, "loss": 1.1237, "step": 3647 }, { "epoch": 0.5612091842621437, "grad_norm": 4.200789928436279, "learning_rate": 8.786945812807882e-06, "loss": 1.4449, "step": 3648 }, { "epoch": 0.5613630244990577, "grad_norm": 3.830742597579956, "learning_rate": 8.783866995073892e-06, "loss": 1.3515, "step": 3649 }, { "epoch": 0.5615168647359717, "grad_norm": 3.689323663711548, "learning_rate": 8.780788177339901e-06, "loss": 1.2976, "step": 3650 }, { "epoch": 0.5616707049728856, "grad_norm": 3.4630682468414307, "learning_rate": 8.777709359605912e-06, "loss": 1.3134, "step": 3651 }, { "epoch": 0.5618245452097996, "grad_norm": 4.154780387878418, "learning_rate": 8.774630541871923e-06, "loss": 1.5025, "step": 3652 }, { "epoch": 0.5619783854467136, "grad_norm": 3.2880473136901855, "learning_rate": 8.771551724137931e-06, "loss": 1.2873, "step": 3653 }, { "epoch": 0.5621322256836275, "grad_norm": 2.899075984954834, "learning_rate": 8.768472906403942e-06, "loss": 1.2088, "step": 3654 }, { "epoch": 0.5622860659205415, "grad_norm": 3.636247396469116, "learning_rate": 8.765394088669951e-06, "loss": 1.3824, "step": 3655 }, { "epoch": 0.5624399061574554, "grad_norm": 2.8991570472717285, "learning_rate": 8.762315270935962e-06, "loss": 1.244, "step": 3656 }, { "epoch": 0.5625937463943694, "grad_norm": 3.261141777038574, "learning_rate": 8.75923645320197e-06, "loss": 1.3927, "step": 3657 }, { "epoch": 0.5627475866312834, "grad_norm": 3.597116708755493, "learning_rate": 8.756157635467981e-06, "loss": 1.3007, "step": 3658 }, { "epoch": 0.5629014268681973, "grad_norm": 3.3638319969177246, "learning_rate": 8.75307881773399e-06, "loss": 1.235, "step": 3659 }, { "epoch": 0.5630552671051113, "grad_norm": 3.2747983932495117, "learning_rate": 8.750000000000001e-06, "loss": 1.3709, "step": 3660 }, { "epoch": 0.5632091073420253, "grad_norm": 2.9520387649536133, "learning_rate": 8.74692118226601e-06, "loss": 1.2265, "step": 3661 }, { "epoch": 0.5633629475789392, "grad_norm": 3.1833810806274414, "learning_rate": 8.74384236453202e-06, "loss": 1.0816, "step": 3662 }, { "epoch": 0.5635167878158532, "grad_norm": 3.195343255996704, "learning_rate": 8.74076354679803e-06, "loss": 1.1342, "step": 3663 }, { "epoch": 0.5636706280527672, "grad_norm": 3.065039873123169, "learning_rate": 8.73768472906404e-06, "loss": 1.0653, "step": 3664 }, { "epoch": 0.5638244682896811, "grad_norm": 3.313079357147217, "learning_rate": 8.734605911330049e-06, "loss": 1.302, "step": 3665 }, { "epoch": 0.5639783085265951, "grad_norm": 3.0198276042938232, "learning_rate": 8.73152709359606e-06, "loss": 1.1787, "step": 3666 }, { "epoch": 0.5641321487635091, "grad_norm": 3.8748185634613037, "learning_rate": 8.728448275862069e-06, "loss": 1.2671, "step": 3667 }, { "epoch": 0.564285989000423, "grad_norm": 3.6391284465789795, "learning_rate": 8.72536945812808e-06, "loss": 1.4416, "step": 3668 }, { "epoch": 0.564439829237337, "grad_norm": 3.9547488689422607, "learning_rate": 8.72229064039409e-06, "loss": 1.2184, "step": 3669 }, { "epoch": 0.5645936694742509, "grad_norm": 3.2153189182281494, "learning_rate": 8.719211822660099e-06, "loss": 1.3259, "step": 3670 }, { "epoch": 0.5647475097111649, "grad_norm": 3.5689821243286133, "learning_rate": 8.71613300492611e-06, "loss": 1.5291, "step": 3671 }, { "epoch": 0.564901349948079, "grad_norm": 4.1975178718566895, "learning_rate": 8.713054187192119e-06, "loss": 1.3711, "step": 3672 }, { "epoch": 0.5650551901849928, "grad_norm": 3.617056369781494, "learning_rate": 8.709975369458129e-06, "loss": 1.537, "step": 3673 }, { "epoch": 0.5652090304219068, "grad_norm": 3.3375864028930664, "learning_rate": 8.706896551724138e-06, "loss": 1.2404, "step": 3674 }, { "epoch": 0.5653628706588208, "grad_norm": 4.2039008140563965, "learning_rate": 8.703817733990149e-06, "loss": 0.9292, "step": 3675 }, { "epoch": 0.5655167108957347, "grad_norm": 2.966653347015381, "learning_rate": 8.700738916256158e-06, "loss": 0.9932, "step": 3676 }, { "epoch": 0.5656705511326487, "grad_norm": 4.253618240356445, "learning_rate": 8.697660098522168e-06, "loss": 1.3685, "step": 3677 }, { "epoch": 0.5658243913695628, "grad_norm": 3.6547226905822754, "learning_rate": 8.694581280788177e-06, "loss": 1.154, "step": 3678 }, { "epoch": 0.5659782316064766, "grad_norm": 3.378990411758423, "learning_rate": 8.691502463054188e-06, "loss": 1.4913, "step": 3679 }, { "epoch": 0.5661320718433906, "grad_norm": 2.8527376651763916, "learning_rate": 8.688423645320197e-06, "loss": 1.4446, "step": 3680 }, { "epoch": 0.5662859120803047, "grad_norm": 3.785733461380005, "learning_rate": 8.685344827586208e-06, "loss": 1.7587, "step": 3681 }, { "epoch": 0.5664397523172185, "grad_norm": 4.469133377075195, "learning_rate": 8.682266009852216e-06, "loss": 1.0563, "step": 3682 }, { "epoch": 0.5665935925541326, "grad_norm": 4.2398247718811035, "learning_rate": 8.679187192118227e-06, "loss": 1.5556, "step": 3683 }, { "epoch": 0.5667474327910464, "grad_norm": 3.928947687149048, "learning_rate": 8.676108374384236e-06, "loss": 1.4498, "step": 3684 }, { "epoch": 0.5669012730279605, "grad_norm": 3.2784793376922607, "learning_rate": 8.673029556650247e-06, "loss": 1.0273, "step": 3685 }, { "epoch": 0.5670551132648745, "grad_norm": 3.245258331298828, "learning_rate": 8.669950738916257e-06, "loss": 1.3835, "step": 3686 }, { "epoch": 0.5672089535017883, "grad_norm": 3.1174256801605225, "learning_rate": 8.666871921182266e-06, "loss": 1.2981, "step": 3687 }, { "epoch": 0.5673627937387024, "grad_norm": 3.8784127235412598, "learning_rate": 8.663793103448277e-06, "loss": 1.611, "step": 3688 }, { "epoch": 0.5675166339756164, "grad_norm": 4.096696853637695, "learning_rate": 8.660714285714286e-06, "loss": 1.6171, "step": 3689 }, { "epoch": 0.5676704742125303, "grad_norm": 4.301656723022461, "learning_rate": 8.657635467980297e-06, "loss": 1.1382, "step": 3690 }, { "epoch": 0.5678243144494443, "grad_norm": 4.720737457275391, "learning_rate": 8.654556650246306e-06, "loss": 1.3661, "step": 3691 }, { "epoch": 0.5679781546863583, "grad_norm": 3.1651179790496826, "learning_rate": 8.651477832512316e-06, "loss": 1.168, "step": 3692 }, { "epoch": 0.5681319949232722, "grad_norm": 4.456598281860352, "learning_rate": 8.648399014778325e-06, "loss": 1.15, "step": 3693 }, { "epoch": 0.5682858351601862, "grad_norm": 3.9370720386505127, "learning_rate": 8.645320197044336e-06, "loss": 1.4289, "step": 3694 }, { "epoch": 0.5684396753971002, "grad_norm": 3.503192186355591, "learning_rate": 8.642241379310345e-06, "loss": 1.3625, "step": 3695 }, { "epoch": 0.5685935156340141, "grad_norm": 3.8648271560668945, "learning_rate": 8.639162561576355e-06, "loss": 1.1341, "step": 3696 }, { "epoch": 0.5687473558709281, "grad_norm": 3.7897448539733887, "learning_rate": 8.636083743842364e-06, "loss": 1.3872, "step": 3697 }, { "epoch": 0.568901196107842, "grad_norm": 2.91101336479187, "learning_rate": 8.633004926108375e-06, "loss": 1.4138, "step": 3698 }, { "epoch": 0.569055036344756, "grad_norm": 3.7678048610687256, "learning_rate": 8.629926108374384e-06, "loss": 1.1079, "step": 3699 }, { "epoch": 0.56920887658167, "grad_norm": 3.8528947830200195, "learning_rate": 8.626847290640395e-06, "loss": 1.2659, "step": 3700 }, { "epoch": 0.5693627168185839, "grad_norm": 3.48052978515625, "learning_rate": 8.623768472906404e-06, "loss": 1.1502, "step": 3701 }, { "epoch": 0.5695165570554979, "grad_norm": 4.460871696472168, "learning_rate": 8.620689655172414e-06, "loss": 1.3092, "step": 3702 }, { "epoch": 0.5696703972924119, "grad_norm": 4.819615364074707, "learning_rate": 8.617610837438425e-06, "loss": 1.4453, "step": 3703 }, { "epoch": 0.5698242375293258, "grad_norm": 3.5771632194519043, "learning_rate": 8.614532019704435e-06, "loss": 1.5721, "step": 3704 }, { "epoch": 0.5699780777662398, "grad_norm": 3.4720945358276367, "learning_rate": 8.611453201970444e-06, "loss": 1.506, "step": 3705 }, { "epoch": 0.5701319180031538, "grad_norm": 3.5212600231170654, "learning_rate": 8.608374384236455e-06, "loss": 1.0368, "step": 3706 }, { "epoch": 0.5702857582400677, "grad_norm": 3.4447078704833984, "learning_rate": 8.605295566502464e-06, "loss": 1.0285, "step": 3707 }, { "epoch": 0.5704395984769817, "grad_norm": 3.458491563796997, "learning_rate": 8.602216748768475e-06, "loss": 1.4689, "step": 3708 }, { "epoch": 0.5705934387138957, "grad_norm": 4.018477439880371, "learning_rate": 8.599137931034484e-06, "loss": 1.5007, "step": 3709 }, { "epoch": 0.5707472789508096, "grad_norm": 3.9154574871063232, "learning_rate": 8.596059113300493e-06, "loss": 1.6034, "step": 3710 }, { "epoch": 0.5709011191877236, "grad_norm": 3.3328888416290283, "learning_rate": 8.592980295566503e-06, "loss": 1.2778, "step": 3711 }, { "epoch": 0.5710549594246375, "grad_norm": 3.543489933013916, "learning_rate": 8.589901477832512e-06, "loss": 1.3301, "step": 3712 }, { "epoch": 0.5712087996615515, "grad_norm": 2.9856808185577393, "learning_rate": 8.586822660098523e-06, "loss": 0.9015, "step": 3713 }, { "epoch": 0.5713626398984655, "grad_norm": 3.6196391582489014, "learning_rate": 8.583743842364532e-06, "loss": 1.3649, "step": 3714 }, { "epoch": 0.5715164801353794, "grad_norm": 3.6245059967041016, "learning_rate": 8.580665024630542e-06, "loss": 1.3824, "step": 3715 }, { "epoch": 0.5716703203722934, "grad_norm": 3.2833945751190186, "learning_rate": 8.577586206896551e-06, "loss": 1.2279, "step": 3716 }, { "epoch": 0.5718241606092074, "grad_norm": 3.911736488342285, "learning_rate": 8.574507389162562e-06, "loss": 1.4541, "step": 3717 }, { "epoch": 0.5719780008461213, "grad_norm": 3.6008377075195312, "learning_rate": 8.571428571428571e-06, "loss": 0.9765, "step": 3718 }, { "epoch": 0.5721318410830353, "grad_norm": 3.583498477935791, "learning_rate": 8.568349753694582e-06, "loss": 1.3883, "step": 3719 }, { "epoch": 0.5722856813199493, "grad_norm": 3.8242571353912354, "learning_rate": 8.565270935960592e-06, "loss": 1.5149, "step": 3720 }, { "epoch": 0.5724395215568632, "grad_norm": 3.1427557468414307, "learning_rate": 8.562192118226603e-06, "loss": 1.4581, "step": 3721 }, { "epoch": 0.5725933617937772, "grad_norm": 4.81333589553833, "learning_rate": 8.559113300492612e-06, "loss": 1.3909, "step": 3722 }, { "epoch": 0.5727472020306912, "grad_norm": 3.5330257415771484, "learning_rate": 8.556034482758622e-06, "loss": 1.4264, "step": 3723 }, { "epoch": 0.5729010422676051, "grad_norm": 3.6046509742736816, "learning_rate": 8.552955665024631e-06, "loss": 1.4143, "step": 3724 }, { "epoch": 0.5730548825045191, "grad_norm": 3.16353178024292, "learning_rate": 8.549876847290642e-06, "loss": 1.436, "step": 3725 }, { "epoch": 0.573208722741433, "grad_norm": 3.4729251861572266, "learning_rate": 8.546798029556651e-06, "loss": 1.5093, "step": 3726 }, { "epoch": 0.573362562978347, "grad_norm": 3.9786183834075928, "learning_rate": 8.543719211822662e-06, "loss": 1.1436, "step": 3727 }, { "epoch": 0.573516403215261, "grad_norm": 4.013355731964111, "learning_rate": 8.54064039408867e-06, "loss": 1.4746, "step": 3728 }, { "epoch": 0.5736702434521749, "grad_norm": 3.6760149002075195, "learning_rate": 8.537561576354681e-06, "loss": 1.3169, "step": 3729 }, { "epoch": 0.5738240836890889, "grad_norm": 3.0057544708251953, "learning_rate": 8.53448275862069e-06, "loss": 1.1666, "step": 3730 }, { "epoch": 0.5739779239260029, "grad_norm": 3.7999935150146484, "learning_rate": 8.531403940886699e-06, "loss": 1.3992, "step": 3731 }, { "epoch": 0.5741317641629168, "grad_norm": 3.493464469909668, "learning_rate": 8.52832512315271e-06, "loss": 1.2265, "step": 3732 }, { "epoch": 0.5742856043998308, "grad_norm": 3.3198912143707275, "learning_rate": 8.525246305418719e-06, "loss": 1.5186, "step": 3733 }, { "epoch": 0.5744394446367448, "grad_norm": 3.3353817462921143, "learning_rate": 8.52216748768473e-06, "loss": 1.3312, "step": 3734 }, { "epoch": 0.5745932848736587, "grad_norm": 3.428443193435669, "learning_rate": 8.519088669950738e-06, "loss": 1.3548, "step": 3735 }, { "epoch": 0.5747471251105727, "grad_norm": 3.2878880500793457, "learning_rate": 8.516009852216749e-06, "loss": 1.3608, "step": 3736 }, { "epoch": 0.5749009653474866, "grad_norm": 3.420107364654541, "learning_rate": 8.51293103448276e-06, "loss": 1.3236, "step": 3737 }, { "epoch": 0.5750548055844006, "grad_norm": 4.162716388702393, "learning_rate": 8.50985221674877e-06, "loss": 1.2749, "step": 3738 }, { "epoch": 0.5752086458213146, "grad_norm": 3.3693785667419434, "learning_rate": 8.50677339901478e-06, "loss": 1.455, "step": 3739 }, { "epoch": 0.5753624860582285, "grad_norm": 3.6877503395080566, "learning_rate": 8.50369458128079e-06, "loss": 1.0417, "step": 3740 }, { "epoch": 0.5755163262951425, "grad_norm": 3.5871894359588623, "learning_rate": 8.500615763546799e-06, "loss": 1.4223, "step": 3741 }, { "epoch": 0.5756701665320565, "grad_norm": 4.526018142700195, "learning_rate": 8.49753694581281e-06, "loss": 1.3393, "step": 3742 }, { "epoch": 0.5758240067689704, "grad_norm": 4.242246627807617, "learning_rate": 8.494458128078818e-06, "loss": 1.2513, "step": 3743 }, { "epoch": 0.5759778470058844, "grad_norm": 4.605808258056641, "learning_rate": 8.491379310344829e-06, "loss": 1.4729, "step": 3744 }, { "epoch": 0.5761316872427984, "grad_norm": 3.167325019836426, "learning_rate": 8.488300492610838e-06, "loss": 1.5456, "step": 3745 }, { "epoch": 0.5762855274797123, "grad_norm": 3.670630931854248, "learning_rate": 8.485221674876849e-06, "loss": 1.4626, "step": 3746 }, { "epoch": 0.5764393677166263, "grad_norm": 3.0130455493927, "learning_rate": 8.482142857142858e-06, "loss": 1.2976, "step": 3747 }, { "epoch": 0.5765932079535403, "grad_norm": 3.0444037914276123, "learning_rate": 8.479064039408868e-06, "loss": 1.3822, "step": 3748 }, { "epoch": 0.5767470481904542, "grad_norm": 4.084183692932129, "learning_rate": 8.475985221674877e-06, "loss": 1.3675, "step": 3749 }, { "epoch": 0.5769008884273682, "grad_norm": 3.197315216064453, "learning_rate": 8.472906403940888e-06, "loss": 1.5732, "step": 3750 }, { "epoch": 0.5770547286642821, "grad_norm": 4.0955939292907715, "learning_rate": 8.469827586206897e-06, "loss": 1.4435, "step": 3751 }, { "epoch": 0.5772085689011961, "grad_norm": 3.156761407852173, "learning_rate": 8.466748768472907e-06, "loss": 1.2663, "step": 3752 }, { "epoch": 0.5773624091381101, "grad_norm": 4.8126301765441895, "learning_rate": 8.463669950738916e-06, "loss": 1.2061, "step": 3753 }, { "epoch": 0.577516249375024, "grad_norm": 3.598048210144043, "learning_rate": 8.460591133004927e-06, "loss": 1.3106, "step": 3754 }, { "epoch": 0.577670089611938, "grad_norm": 3.582846164703369, "learning_rate": 8.457512315270938e-06, "loss": 1.5984, "step": 3755 }, { "epoch": 0.577823929848852, "grad_norm": 4.373093605041504, "learning_rate": 8.454433497536947e-06, "loss": 0.9907, "step": 3756 }, { "epoch": 0.5779777700857659, "grad_norm": 3.2321441173553467, "learning_rate": 8.451354679802957e-06, "loss": 1.1622, "step": 3757 }, { "epoch": 0.5781316103226799, "grad_norm": 3.1421544551849365, "learning_rate": 8.448275862068966e-06, "loss": 1.4455, "step": 3758 }, { "epoch": 0.5782854505595939, "grad_norm": 4.115896701812744, "learning_rate": 8.445197044334977e-06, "loss": 1.3487, "step": 3759 }, { "epoch": 0.5784392907965078, "grad_norm": 3.7781436443328857, "learning_rate": 8.442118226600986e-06, "loss": 1.5491, "step": 3760 }, { "epoch": 0.5785931310334218, "grad_norm": 3.4128570556640625, "learning_rate": 8.439039408866996e-06, "loss": 1.429, "step": 3761 }, { "epoch": 0.5787469712703358, "grad_norm": 3.1753103733062744, "learning_rate": 8.435960591133005e-06, "loss": 1.4518, "step": 3762 }, { "epoch": 0.5789008115072497, "grad_norm": 3.1705195903778076, "learning_rate": 8.432881773399016e-06, "loss": 1.4115, "step": 3763 }, { "epoch": 0.5790546517441637, "grad_norm": 4.350098133087158, "learning_rate": 8.429802955665025e-06, "loss": 1.4207, "step": 3764 }, { "epoch": 0.5792084919810776, "grad_norm": 3.6042349338531494, "learning_rate": 8.426724137931036e-06, "loss": 1.1838, "step": 3765 }, { "epoch": 0.5793623322179916, "grad_norm": 3.251664161682129, "learning_rate": 8.423645320197045e-06, "loss": 1.2995, "step": 3766 }, { "epoch": 0.5795161724549056, "grad_norm": 3.983079671859741, "learning_rate": 8.420566502463055e-06, "loss": 1.1875, "step": 3767 }, { "epoch": 0.5796700126918195, "grad_norm": 3.2287862300872803, "learning_rate": 8.417487684729064e-06, "loss": 1.1428, "step": 3768 }, { "epoch": 0.5798238529287335, "grad_norm": 3.2171175479888916, "learning_rate": 8.414408866995075e-06, "loss": 1.4744, "step": 3769 }, { "epoch": 0.5799776931656475, "grad_norm": 3.801624298095703, "learning_rate": 8.411330049261086e-06, "loss": 1.2657, "step": 3770 }, { "epoch": 0.5801315334025614, "grad_norm": 3.580848217010498, "learning_rate": 8.408251231527094e-06, "loss": 1.2557, "step": 3771 }, { "epoch": 0.5802853736394754, "grad_norm": 4.222900867462158, "learning_rate": 8.405172413793105e-06, "loss": 1.2889, "step": 3772 }, { "epoch": 0.5804392138763894, "grad_norm": 4.413760185241699, "learning_rate": 8.402093596059114e-06, "loss": 1.2594, "step": 3773 }, { "epoch": 0.5805930541133033, "grad_norm": 3.470771074295044, "learning_rate": 8.399014778325125e-06, "loss": 1.5047, "step": 3774 }, { "epoch": 0.5807468943502173, "grad_norm": 3.5555129051208496, "learning_rate": 8.395935960591134e-06, "loss": 1.2985, "step": 3775 }, { "epoch": 0.5809007345871313, "grad_norm": 3.945756435394287, "learning_rate": 8.392857142857144e-06, "loss": 1.27, "step": 3776 }, { "epoch": 0.5810545748240452, "grad_norm": 4.566468715667725, "learning_rate": 8.389778325123153e-06, "loss": 1.6649, "step": 3777 }, { "epoch": 0.5812084150609592, "grad_norm": 4.102572441101074, "learning_rate": 8.386699507389164e-06, "loss": 0.9089, "step": 3778 }, { "epoch": 0.5813622552978731, "grad_norm": 3.688861131668091, "learning_rate": 8.383620689655173e-06, "loss": 1.3193, "step": 3779 }, { "epoch": 0.5815160955347871, "grad_norm": 3.4813523292541504, "learning_rate": 8.380541871921183e-06, "loss": 1.3171, "step": 3780 }, { "epoch": 0.5816699357717011, "grad_norm": 4.120160102844238, "learning_rate": 8.377463054187192e-06, "loss": 1.2264, "step": 3781 }, { "epoch": 0.581823776008615, "grad_norm": 3.941091299057007, "learning_rate": 8.374384236453203e-06, "loss": 1.158, "step": 3782 }, { "epoch": 0.581977616245529, "grad_norm": 3.949050188064575, "learning_rate": 8.371305418719212e-06, "loss": 1.1081, "step": 3783 }, { "epoch": 0.582131456482443, "grad_norm": 3.504904270172119, "learning_rate": 8.368226600985223e-06, "loss": 1.2102, "step": 3784 }, { "epoch": 0.5822852967193569, "grad_norm": 3.537792682647705, "learning_rate": 8.365147783251232e-06, "loss": 1.4581, "step": 3785 }, { "epoch": 0.5824391369562709, "grad_norm": 3.8261678218841553, "learning_rate": 8.362068965517242e-06, "loss": 1.1654, "step": 3786 }, { "epoch": 0.5825929771931849, "grad_norm": 4.006704807281494, "learning_rate": 8.358990147783253e-06, "loss": 1.131, "step": 3787 }, { "epoch": 0.5827468174300988, "grad_norm": 3.5826478004455566, "learning_rate": 8.355911330049262e-06, "loss": 1.5055, "step": 3788 }, { "epoch": 0.5829006576670128, "grad_norm": 4.119540214538574, "learning_rate": 8.352832512315273e-06, "loss": 1.3458, "step": 3789 }, { "epoch": 0.5830544979039268, "grad_norm": 3.7768497467041016, "learning_rate": 8.349753694581281e-06, "loss": 1.5295, "step": 3790 }, { "epoch": 0.5832083381408407, "grad_norm": 3.340550661087036, "learning_rate": 8.346674876847292e-06, "loss": 1.2718, "step": 3791 }, { "epoch": 0.5833621783777547, "grad_norm": 3.4060745239257812, "learning_rate": 8.343596059113301e-06, "loss": 1.1942, "step": 3792 }, { "epoch": 0.5835160186146686, "grad_norm": 4.131002426147461, "learning_rate": 8.340517241379312e-06, "loss": 1.3857, "step": 3793 }, { "epoch": 0.5836698588515826, "grad_norm": 3.6168806552886963, "learning_rate": 8.33743842364532e-06, "loss": 1.4908, "step": 3794 }, { "epoch": 0.5838236990884966, "grad_norm": 4.26018762588501, "learning_rate": 8.334359605911331e-06, "loss": 1.2735, "step": 3795 }, { "epoch": 0.5839775393254105, "grad_norm": 3.5491809844970703, "learning_rate": 8.33128078817734e-06, "loss": 1.2737, "step": 3796 }, { "epoch": 0.5841313795623245, "grad_norm": 3.5920214653015137, "learning_rate": 8.328201970443351e-06, "loss": 1.5351, "step": 3797 }, { "epoch": 0.5842852197992385, "grad_norm": 4.134166240692139, "learning_rate": 8.32512315270936e-06, "loss": 1.1774, "step": 3798 }, { "epoch": 0.5844390600361524, "grad_norm": 3.341287612915039, "learning_rate": 8.32204433497537e-06, "loss": 1.4052, "step": 3799 }, { "epoch": 0.5845929002730664, "grad_norm": 4.046838760375977, "learning_rate": 8.31896551724138e-06, "loss": 1.4824, "step": 3800 }, { "epoch": 0.5847467405099804, "grad_norm": 3.4708473682403564, "learning_rate": 8.31588669950739e-06, "loss": 0.9116, "step": 3801 }, { "epoch": 0.5849005807468943, "grad_norm": 3.508059024810791, "learning_rate": 8.312807881773399e-06, "loss": 1.4319, "step": 3802 }, { "epoch": 0.5850544209838083, "grad_norm": 4.317107200622559, "learning_rate": 8.30972906403941e-06, "loss": 1.2829, "step": 3803 }, { "epoch": 0.5852082612207222, "grad_norm": 3.8122615814208984, "learning_rate": 8.30665024630542e-06, "loss": 1.3424, "step": 3804 }, { "epoch": 0.5853621014576362, "grad_norm": 3.811617851257324, "learning_rate": 8.30357142857143e-06, "loss": 1.068, "step": 3805 }, { "epoch": 0.5855159416945502, "grad_norm": 3.8336808681488037, "learning_rate": 8.30049261083744e-06, "loss": 1.3414, "step": 3806 }, { "epoch": 0.5856697819314641, "grad_norm": 3.360623359680176, "learning_rate": 8.297413793103449e-06, "loss": 1.2405, "step": 3807 }, { "epoch": 0.5858236221683781, "grad_norm": 3.6855032444000244, "learning_rate": 8.29433497536946e-06, "loss": 1.5525, "step": 3808 }, { "epoch": 0.5859774624052921, "grad_norm": 3.239333391189575, "learning_rate": 8.291256157635468e-06, "loss": 1.3126, "step": 3809 }, { "epoch": 0.586131302642206, "grad_norm": 3.3212339878082275, "learning_rate": 8.288177339901479e-06, "loss": 1.3836, "step": 3810 }, { "epoch": 0.58628514287912, "grad_norm": 3.6613640785217285, "learning_rate": 8.285098522167488e-06, "loss": 1.3278, "step": 3811 }, { "epoch": 0.586438983116034, "grad_norm": 4.014803409576416, "learning_rate": 8.282019704433499e-06, "loss": 1.1864, "step": 3812 }, { "epoch": 0.5865928233529479, "grad_norm": 3.5286331176757812, "learning_rate": 8.278940886699508e-06, "loss": 1.3908, "step": 3813 }, { "epoch": 0.5867466635898619, "grad_norm": 3.6104774475097656, "learning_rate": 8.275862068965518e-06, "loss": 1.233, "step": 3814 }, { "epoch": 0.5869005038267759, "grad_norm": 4.175090312957764, "learning_rate": 8.272783251231527e-06, "loss": 1.2421, "step": 3815 }, { "epoch": 0.5870543440636898, "grad_norm": 4.533034801483154, "learning_rate": 8.269704433497538e-06, "loss": 1.3947, "step": 3816 }, { "epoch": 0.5872081843006038, "grad_norm": 4.413244724273682, "learning_rate": 8.266625615763547e-06, "loss": 1.5629, "step": 3817 }, { "epoch": 0.5873620245375177, "grad_norm": 3.2929766178131104, "learning_rate": 8.263546798029558e-06, "loss": 1.3696, "step": 3818 }, { "epoch": 0.5875158647744317, "grad_norm": 3.9342758655548096, "learning_rate": 8.260467980295566e-06, "loss": 1.507, "step": 3819 }, { "epoch": 0.5876697050113457, "grad_norm": 3.513458490371704, "learning_rate": 8.257389162561577e-06, "loss": 1.4399, "step": 3820 }, { "epoch": 0.5878235452482596, "grad_norm": 4.088686466217041, "learning_rate": 8.254310344827588e-06, "loss": 1.3048, "step": 3821 }, { "epoch": 0.5879773854851736, "grad_norm": 3.6506261825561523, "learning_rate": 8.251231527093597e-06, "loss": 1.5239, "step": 3822 }, { "epoch": 0.5881312257220876, "grad_norm": 3.7213010787963867, "learning_rate": 8.248152709359607e-06, "loss": 1.1856, "step": 3823 }, { "epoch": 0.5882850659590015, "grad_norm": 4.58113956451416, "learning_rate": 8.245073891625616e-06, "loss": 1.3427, "step": 3824 }, { "epoch": 0.5884389061959155, "grad_norm": 4.567739963531494, "learning_rate": 8.241995073891627e-06, "loss": 1.2742, "step": 3825 }, { "epoch": 0.5885927464328295, "grad_norm": 3.1107184886932373, "learning_rate": 8.238916256157636e-06, "loss": 1.2899, "step": 3826 }, { "epoch": 0.5887465866697434, "grad_norm": 3.5199553966522217, "learning_rate": 8.235837438423647e-06, "loss": 1.2558, "step": 3827 }, { "epoch": 0.5889004269066574, "grad_norm": 3.687392234802246, "learning_rate": 8.232758620689656e-06, "loss": 1.1545, "step": 3828 }, { "epoch": 0.5890542671435715, "grad_norm": 2.9396111965179443, "learning_rate": 8.229679802955666e-06, "loss": 1.4524, "step": 3829 }, { "epoch": 0.5892081073804853, "grad_norm": 3.566375970840454, "learning_rate": 8.226600985221675e-06, "loss": 1.4391, "step": 3830 }, { "epoch": 0.5893619476173994, "grad_norm": 3.8195526599884033, "learning_rate": 8.223522167487686e-06, "loss": 1.2153, "step": 3831 }, { "epoch": 0.5895157878543132, "grad_norm": 3.6107394695281982, "learning_rate": 8.220443349753695e-06, "loss": 1.2697, "step": 3832 }, { "epoch": 0.5896696280912272, "grad_norm": 4.199881076812744, "learning_rate": 8.217364532019705e-06, "loss": 1.2176, "step": 3833 }, { "epoch": 0.5898234683281413, "grad_norm": 4.173239707946777, "learning_rate": 8.214285714285714e-06, "loss": 1.4554, "step": 3834 }, { "epoch": 0.5899773085650551, "grad_norm": 3.207479953765869, "learning_rate": 8.211206896551725e-06, "loss": 1.3172, "step": 3835 }, { "epoch": 0.5901311488019692, "grad_norm": 3.8390252590179443, "learning_rate": 8.208128078817734e-06, "loss": 1.178, "step": 3836 }, { "epoch": 0.5902849890388832, "grad_norm": 3.9025464057922363, "learning_rate": 8.205049261083745e-06, "loss": 1.5147, "step": 3837 }, { "epoch": 0.590438829275797, "grad_norm": 3.8665807247161865, "learning_rate": 8.201970443349755e-06, "loss": 1.3544, "step": 3838 }, { "epoch": 0.590592669512711, "grad_norm": 3.2034332752227783, "learning_rate": 8.198891625615764e-06, "loss": 1.4817, "step": 3839 }, { "epoch": 0.5907465097496251, "grad_norm": 4.225642681121826, "learning_rate": 8.195812807881775e-06, "loss": 1.2253, "step": 3840 }, { "epoch": 0.590900349986539, "grad_norm": 4.015765190124512, "learning_rate": 8.192733990147784e-06, "loss": 1.2499, "step": 3841 }, { "epoch": 0.591054190223453, "grad_norm": 4.616541862487793, "learning_rate": 8.189655172413794e-06, "loss": 1.5653, "step": 3842 }, { "epoch": 0.591208030460367, "grad_norm": 3.3363471031188965, "learning_rate": 8.186576354679803e-06, "loss": 1.3817, "step": 3843 }, { "epoch": 0.5913618706972809, "grad_norm": 3.3905529975891113, "learning_rate": 8.183497536945814e-06, "loss": 1.3841, "step": 3844 }, { "epoch": 0.5915157109341949, "grad_norm": 3.2826457023620605, "learning_rate": 8.180418719211823e-06, "loss": 1.1621, "step": 3845 }, { "epoch": 0.5916695511711088, "grad_norm": 3.4116709232330322, "learning_rate": 8.177339901477834e-06, "loss": 1.4108, "step": 3846 }, { "epoch": 0.5918233914080228, "grad_norm": 3.862013578414917, "learning_rate": 8.174261083743843e-06, "loss": 1.391, "step": 3847 }, { "epoch": 0.5919772316449368, "grad_norm": 3.7073423862457275, "learning_rate": 8.171182266009853e-06, "loss": 1.4201, "step": 3848 }, { "epoch": 0.5921310718818507, "grad_norm": 4.094496250152588, "learning_rate": 8.168103448275862e-06, "loss": 1.3594, "step": 3849 }, { "epoch": 0.5922849121187647, "grad_norm": 3.9271724224090576, "learning_rate": 8.165024630541873e-06, "loss": 1.522, "step": 3850 }, { "epoch": 0.5924387523556787, "grad_norm": 4.044558048248291, "learning_rate": 8.161945812807882e-06, "loss": 1.325, "step": 3851 }, { "epoch": 0.5925925925925926, "grad_norm": 3.2004103660583496, "learning_rate": 8.158866995073892e-06, "loss": 1.3421, "step": 3852 }, { "epoch": 0.5927464328295066, "grad_norm": 4.258060455322266, "learning_rate": 8.155788177339901e-06, "loss": 1.2244, "step": 3853 }, { "epoch": 0.5929002730664206, "grad_norm": 3.4691128730773926, "learning_rate": 8.152709359605912e-06, "loss": 1.2421, "step": 3854 }, { "epoch": 0.5930541133033345, "grad_norm": 3.218965768814087, "learning_rate": 8.149630541871923e-06, "loss": 1.3426, "step": 3855 }, { "epoch": 0.5932079535402485, "grad_norm": 3.4510905742645264, "learning_rate": 8.146551724137932e-06, "loss": 1.4329, "step": 3856 }, { "epoch": 0.5933617937771625, "grad_norm": 3.321136236190796, "learning_rate": 8.143472906403942e-06, "loss": 1.2924, "step": 3857 }, { "epoch": 0.5935156340140764, "grad_norm": 2.992079496383667, "learning_rate": 8.140394088669951e-06, "loss": 1.2695, "step": 3858 }, { "epoch": 0.5936694742509904, "grad_norm": 3.9076309204101562, "learning_rate": 8.137315270935962e-06, "loss": 1.1942, "step": 3859 }, { "epoch": 0.5938233144879043, "grad_norm": 3.7386231422424316, "learning_rate": 8.13423645320197e-06, "loss": 1.4028, "step": 3860 }, { "epoch": 0.5939771547248183, "grad_norm": 3.645371675491333, "learning_rate": 8.131157635467981e-06, "loss": 1.2618, "step": 3861 }, { "epoch": 0.5941309949617323, "grad_norm": 3.394533157348633, "learning_rate": 8.12807881773399e-06, "loss": 1.2676, "step": 3862 }, { "epoch": 0.5942848351986462, "grad_norm": 3.7373979091644287, "learning_rate": 8.125000000000001e-06, "loss": 1.3628, "step": 3863 }, { "epoch": 0.5944386754355602, "grad_norm": 4.325443267822266, "learning_rate": 8.12192118226601e-06, "loss": 1.3615, "step": 3864 }, { "epoch": 0.5945925156724742, "grad_norm": 3.2960450649261475, "learning_rate": 8.11884236453202e-06, "loss": 1.4716, "step": 3865 }, { "epoch": 0.5947463559093881, "grad_norm": 3.4225714206695557, "learning_rate": 8.11576354679803e-06, "loss": 1.2782, "step": 3866 }, { "epoch": 0.5949001961463021, "grad_norm": 3.832231044769287, "learning_rate": 8.11268472906404e-06, "loss": 1.1499, "step": 3867 }, { "epoch": 0.5950540363832161, "grad_norm": 3.513230323791504, "learning_rate": 8.109605911330049e-06, "loss": 1.2234, "step": 3868 }, { "epoch": 0.59520787662013, "grad_norm": 2.8532662391662598, "learning_rate": 8.10652709359606e-06, "loss": 1.092, "step": 3869 }, { "epoch": 0.595361716857044, "grad_norm": 3.4062423706054688, "learning_rate": 8.103448275862069e-06, "loss": 1.3667, "step": 3870 }, { "epoch": 0.5955155570939579, "grad_norm": 3.5652050971984863, "learning_rate": 8.10036945812808e-06, "loss": 1.5173, "step": 3871 }, { "epoch": 0.5956693973308719, "grad_norm": 3.4917564392089844, "learning_rate": 8.09729064039409e-06, "loss": 1.4442, "step": 3872 }, { "epoch": 0.5958232375677859, "grad_norm": 3.6197662353515625, "learning_rate": 8.094211822660099e-06, "loss": 1.2111, "step": 3873 }, { "epoch": 0.5959770778046998, "grad_norm": 3.0412042140960693, "learning_rate": 8.09113300492611e-06, "loss": 1.4959, "step": 3874 }, { "epoch": 0.5961309180416138, "grad_norm": 3.362492322921753, "learning_rate": 8.088054187192119e-06, "loss": 1.3789, "step": 3875 }, { "epoch": 0.5962847582785278, "grad_norm": 4.176177501678467, "learning_rate": 8.08497536945813e-06, "loss": 1.7379, "step": 3876 }, { "epoch": 0.5964385985154417, "grad_norm": 4.0647807121276855, "learning_rate": 8.081896551724138e-06, "loss": 1.2603, "step": 3877 }, { "epoch": 0.5965924387523557, "grad_norm": 4.235104560852051, "learning_rate": 8.078817733990149e-06, "loss": 1.3975, "step": 3878 }, { "epoch": 0.5967462789892697, "grad_norm": 3.483391523361206, "learning_rate": 8.075738916256158e-06, "loss": 1.4404, "step": 3879 }, { "epoch": 0.5969001192261836, "grad_norm": 3.5003697872161865, "learning_rate": 8.072660098522168e-06, "loss": 1.3566, "step": 3880 }, { "epoch": 0.5970539594630976, "grad_norm": 4.056633949279785, "learning_rate": 8.069581280788177e-06, "loss": 1.3802, "step": 3881 }, { "epoch": 0.5972077997000116, "grad_norm": 3.188624858856201, "learning_rate": 8.066502463054188e-06, "loss": 1.2815, "step": 3882 }, { "epoch": 0.5973616399369255, "grad_norm": 3.5860462188720703, "learning_rate": 8.063423645320197e-06, "loss": 1.2332, "step": 3883 }, { "epoch": 0.5975154801738395, "grad_norm": 3.5148537158966064, "learning_rate": 8.060344827586208e-06, "loss": 1.4714, "step": 3884 }, { "epoch": 0.5976693204107534, "grad_norm": 2.9731056690216064, "learning_rate": 8.057266009852217e-06, "loss": 1.2332, "step": 3885 }, { "epoch": 0.5978231606476674, "grad_norm": 4.32147741317749, "learning_rate": 8.054187192118227e-06, "loss": 1.296, "step": 3886 }, { "epoch": 0.5979770008845814, "grad_norm": 3.372213840484619, "learning_rate": 8.051108374384236e-06, "loss": 1.5046, "step": 3887 }, { "epoch": 0.5981308411214953, "grad_norm": 3.645888328552246, "learning_rate": 8.048029556650247e-06, "loss": 1.3854, "step": 3888 }, { "epoch": 0.5982846813584093, "grad_norm": 2.9452013969421387, "learning_rate": 8.044950738916257e-06, "loss": 1.3021, "step": 3889 }, { "epoch": 0.5984385215953233, "grad_norm": 3.7111282348632812, "learning_rate": 8.041871921182266e-06, "loss": 1.3222, "step": 3890 }, { "epoch": 0.5985923618322372, "grad_norm": 4.1150593757629395, "learning_rate": 8.038793103448277e-06, "loss": 1.3631, "step": 3891 }, { "epoch": 0.5987462020691512, "grad_norm": 3.296330690383911, "learning_rate": 8.035714285714286e-06, "loss": 1.4301, "step": 3892 }, { "epoch": 0.5989000423060652, "grad_norm": 3.4386844635009766, "learning_rate": 8.032635467980297e-06, "loss": 1.2389, "step": 3893 }, { "epoch": 0.5990538825429791, "grad_norm": 3.680966377258301, "learning_rate": 8.029556650246306e-06, "loss": 1.3115, "step": 3894 }, { "epoch": 0.5992077227798931, "grad_norm": 3.3939173221588135, "learning_rate": 8.026477832512316e-06, "loss": 1.1719, "step": 3895 }, { "epoch": 0.5993615630168071, "grad_norm": 3.7940938472747803, "learning_rate": 8.023399014778325e-06, "loss": 1.1212, "step": 3896 }, { "epoch": 0.599515403253721, "grad_norm": 3.6397926807403564, "learning_rate": 8.020320197044336e-06, "loss": 1.2271, "step": 3897 }, { "epoch": 0.599669243490635, "grad_norm": 3.7637927532196045, "learning_rate": 8.017241379310345e-06, "loss": 1.4371, "step": 3898 }, { "epoch": 0.5998230837275489, "grad_norm": 3.2648744583129883, "learning_rate": 8.014162561576355e-06, "loss": 1.1167, "step": 3899 }, { "epoch": 0.5999769239644629, "grad_norm": 3.0749826431274414, "learning_rate": 8.011083743842364e-06, "loss": 1.4019, "step": 3900 }, { "epoch": 0.6001307642013769, "grad_norm": 3.535590648651123, "learning_rate": 8.008004926108375e-06, "loss": 1.4401, "step": 3901 }, { "epoch": 0.6002846044382908, "grad_norm": 3.9604711532592773, "learning_rate": 8.004926108374384e-06, "loss": 1.3091, "step": 3902 }, { "epoch": 0.6004384446752048, "grad_norm": 4.016407012939453, "learning_rate": 8.001847290640395e-06, "loss": 1.3471, "step": 3903 }, { "epoch": 0.6005922849121188, "grad_norm": 3.8620247840881348, "learning_rate": 7.998768472906404e-06, "loss": 1.3109, "step": 3904 }, { "epoch": 0.6007461251490327, "grad_norm": 3.6882412433624268, "learning_rate": 7.995689655172414e-06, "loss": 1.2983, "step": 3905 }, { "epoch": 0.6008999653859467, "grad_norm": 3.594326972961426, "learning_rate": 7.992610837438425e-06, "loss": 1.2736, "step": 3906 }, { "epoch": 0.6010538056228607, "grad_norm": 3.6350314617156982, "learning_rate": 7.989532019704434e-06, "loss": 1.2353, "step": 3907 }, { "epoch": 0.6012076458597746, "grad_norm": 3.806795597076416, "learning_rate": 7.986453201970444e-06, "loss": 1.1665, "step": 3908 }, { "epoch": 0.6013614860966886, "grad_norm": 3.641134738922119, "learning_rate": 7.983374384236453e-06, "loss": 1.42, "step": 3909 }, { "epoch": 0.6015153263336026, "grad_norm": 3.312514305114746, "learning_rate": 7.980295566502464e-06, "loss": 1.0084, "step": 3910 }, { "epoch": 0.6016691665705165, "grad_norm": 3.6958158016204834, "learning_rate": 7.977216748768473e-06, "loss": 1.3103, "step": 3911 }, { "epoch": 0.6018230068074305, "grad_norm": 3.8358194828033447, "learning_rate": 7.974137931034484e-06, "loss": 1.1536, "step": 3912 }, { "epoch": 0.6019768470443444, "grad_norm": 3.3940041065216064, "learning_rate": 7.971059113300493e-06, "loss": 1.2601, "step": 3913 }, { "epoch": 0.6021306872812584, "grad_norm": 3.6492936611175537, "learning_rate": 7.967980295566503e-06, "loss": 1.4631, "step": 3914 }, { "epoch": 0.6022845275181724, "grad_norm": 3.5883896350860596, "learning_rate": 7.964901477832512e-06, "loss": 1.2014, "step": 3915 }, { "epoch": 0.6024383677550863, "grad_norm": 3.2243857383728027, "learning_rate": 7.961822660098523e-06, "loss": 1.2082, "step": 3916 }, { "epoch": 0.6025922079920003, "grad_norm": 3.1686346530914307, "learning_rate": 7.958743842364532e-06, "loss": 1.4195, "step": 3917 }, { "epoch": 0.6027460482289143, "grad_norm": 3.2026803493499756, "learning_rate": 7.955665024630542e-06, "loss": 1.3216, "step": 3918 }, { "epoch": 0.6028998884658282, "grad_norm": 3.215559959411621, "learning_rate": 7.952586206896551e-06, "loss": 1.392, "step": 3919 }, { "epoch": 0.6030537287027422, "grad_norm": 3.4751534461975098, "learning_rate": 7.949507389162562e-06, "loss": 1.1867, "step": 3920 }, { "epoch": 0.6032075689396562, "grad_norm": 3.3592300415039062, "learning_rate": 7.946428571428571e-06, "loss": 1.4885, "step": 3921 }, { "epoch": 0.6033614091765701, "grad_norm": 4.069348335266113, "learning_rate": 7.943349753694582e-06, "loss": 1.2189, "step": 3922 }, { "epoch": 0.6035152494134841, "grad_norm": 3.4855549335479736, "learning_rate": 7.940270935960592e-06, "loss": 1.4906, "step": 3923 }, { "epoch": 0.6036690896503981, "grad_norm": 3.6341657638549805, "learning_rate": 7.937192118226603e-06, "loss": 1.1484, "step": 3924 }, { "epoch": 0.603822929887312, "grad_norm": 4.35700798034668, "learning_rate": 7.934113300492612e-06, "loss": 1.262, "step": 3925 }, { "epoch": 0.603976770124226, "grad_norm": 3.711977958679199, "learning_rate": 7.93103448275862e-06, "loss": 1.314, "step": 3926 }, { "epoch": 0.6041306103611399, "grad_norm": 3.8785035610198975, "learning_rate": 7.927955665024631e-06, "loss": 1.385, "step": 3927 }, { "epoch": 0.6042844505980539, "grad_norm": 3.67765474319458, "learning_rate": 7.92487684729064e-06, "loss": 1.2759, "step": 3928 }, { "epoch": 0.6044382908349679, "grad_norm": 3.482264518737793, "learning_rate": 7.921798029556651e-06, "loss": 1.4179, "step": 3929 }, { "epoch": 0.6045921310718818, "grad_norm": 3.256786823272705, "learning_rate": 7.91871921182266e-06, "loss": 1.4632, "step": 3930 }, { "epoch": 0.6047459713087958, "grad_norm": 3.35915207862854, "learning_rate": 7.91564039408867e-06, "loss": 1.297, "step": 3931 }, { "epoch": 0.6048998115457098, "grad_norm": 3.278069019317627, "learning_rate": 7.91256157635468e-06, "loss": 1.2498, "step": 3932 }, { "epoch": 0.6050536517826237, "grad_norm": 3.6823172569274902, "learning_rate": 7.90948275862069e-06, "loss": 1.3667, "step": 3933 }, { "epoch": 0.6052074920195377, "grad_norm": 3.4129140377044678, "learning_rate": 7.9064039408867e-06, "loss": 1.2829, "step": 3934 }, { "epoch": 0.6053613322564517, "grad_norm": 3.308425188064575, "learning_rate": 7.90332512315271e-06, "loss": 1.5332, "step": 3935 }, { "epoch": 0.6055151724933656, "grad_norm": 3.3844380378723145, "learning_rate": 7.900246305418719e-06, "loss": 1.4949, "step": 3936 }, { "epoch": 0.6056690127302796, "grad_norm": 3.4703073501586914, "learning_rate": 7.89716748768473e-06, "loss": 1.281, "step": 3937 }, { "epoch": 0.6058228529671935, "grad_norm": 3.922241687774658, "learning_rate": 7.894088669950738e-06, "loss": 1.4283, "step": 3938 }, { "epoch": 0.6059766932041075, "grad_norm": 3.5069196224212646, "learning_rate": 7.891009852216749e-06, "loss": 1.3304, "step": 3939 }, { "epoch": 0.6061305334410215, "grad_norm": 3.847454786300659, "learning_rate": 7.88793103448276e-06, "loss": 1.5023, "step": 3940 }, { "epoch": 0.6062843736779354, "grad_norm": 3.5091190338134766, "learning_rate": 7.88485221674877e-06, "loss": 1.1633, "step": 3941 }, { "epoch": 0.6064382139148494, "grad_norm": 3.37742018699646, "learning_rate": 7.88177339901478e-06, "loss": 1.2914, "step": 3942 }, { "epoch": 0.6065920541517634, "grad_norm": 3.3461666107177734, "learning_rate": 7.87869458128079e-06, "loss": 1.4218, "step": 3943 }, { "epoch": 0.6067458943886773, "grad_norm": 3.542658805847168, "learning_rate": 7.875615763546799e-06, "loss": 1.2448, "step": 3944 }, { "epoch": 0.6068997346255913, "grad_norm": 3.5395607948303223, "learning_rate": 7.87253694581281e-06, "loss": 1.2851, "step": 3945 }, { "epoch": 0.6070535748625053, "grad_norm": 3.767577886581421, "learning_rate": 7.869458128078818e-06, "loss": 1.395, "step": 3946 }, { "epoch": 0.6072074150994192, "grad_norm": 3.5489501953125, "learning_rate": 7.866379310344827e-06, "loss": 1.0448, "step": 3947 }, { "epoch": 0.6073612553363332, "grad_norm": 3.9382855892181396, "learning_rate": 7.863300492610838e-06, "loss": 1.3686, "step": 3948 }, { "epoch": 0.6075150955732472, "grad_norm": 3.9173452854156494, "learning_rate": 7.860221674876847e-06, "loss": 1.3247, "step": 3949 }, { "epoch": 0.6076689358101611, "grad_norm": 3.446643114089966, "learning_rate": 7.857142857142858e-06, "loss": 1.1367, "step": 3950 }, { "epoch": 0.6078227760470751, "grad_norm": 3.335496187210083, "learning_rate": 7.854064039408867e-06, "loss": 1.4133, "step": 3951 }, { "epoch": 0.607976616283989, "grad_norm": 3.517936944961548, "learning_rate": 7.850985221674877e-06, "loss": 1.1582, "step": 3952 }, { "epoch": 0.608130456520903, "grad_norm": 4.10294246673584, "learning_rate": 7.847906403940886e-06, "loss": 1.3676, "step": 3953 }, { "epoch": 0.608284296757817, "grad_norm": 3.1250956058502197, "learning_rate": 7.844827586206897e-06, "loss": 1.3865, "step": 3954 }, { "epoch": 0.6084381369947309, "grad_norm": 2.811211347579956, "learning_rate": 7.841748768472906e-06, "loss": 1.1984, "step": 3955 }, { "epoch": 0.6085919772316449, "grad_norm": 3.370637893676758, "learning_rate": 7.838669950738916e-06, "loss": 1.2314, "step": 3956 }, { "epoch": 0.6087458174685589, "grad_norm": 3.5358572006225586, "learning_rate": 7.835591133004927e-06, "loss": 1.3402, "step": 3957 }, { "epoch": 0.6088996577054728, "grad_norm": 3.0104591846466064, "learning_rate": 7.832512315270938e-06, "loss": 1.1574, "step": 3958 }, { "epoch": 0.6090534979423868, "grad_norm": 3.3854429721832275, "learning_rate": 7.829433497536947e-06, "loss": 1.4889, "step": 3959 }, { "epoch": 0.6092073381793008, "grad_norm": 3.6115596294403076, "learning_rate": 7.826354679802957e-06, "loss": 1.3508, "step": 3960 }, { "epoch": 0.6093611784162147, "grad_norm": 3.63556170463562, "learning_rate": 7.823275862068966e-06, "loss": 1.3465, "step": 3961 }, { "epoch": 0.6095150186531287, "grad_norm": 3.786574125289917, "learning_rate": 7.820197044334977e-06, "loss": 1.2518, "step": 3962 }, { "epoch": 0.6096688588900427, "grad_norm": 3.405333995819092, "learning_rate": 7.817118226600986e-06, "loss": 1.4248, "step": 3963 }, { "epoch": 0.6098226991269566, "grad_norm": 3.1319427490234375, "learning_rate": 7.814039408866997e-06, "loss": 1.2588, "step": 3964 }, { "epoch": 0.6099765393638706, "grad_norm": 3.4096572399139404, "learning_rate": 7.810960591133005e-06, "loss": 1.4954, "step": 3965 }, { "epoch": 0.6101303796007845, "grad_norm": 3.7407093048095703, "learning_rate": 7.807881773399016e-06, "loss": 1.4006, "step": 3966 }, { "epoch": 0.6102842198376985, "grad_norm": 3.366384983062744, "learning_rate": 7.804802955665025e-06, "loss": 1.3828, "step": 3967 }, { "epoch": 0.6104380600746125, "grad_norm": 3.581559181213379, "learning_rate": 7.801724137931036e-06, "loss": 1.3747, "step": 3968 }, { "epoch": 0.6105919003115264, "grad_norm": 3.7576467990875244, "learning_rate": 7.798645320197045e-06, "loss": 1.4494, "step": 3969 }, { "epoch": 0.6107457405484404, "grad_norm": 3.579653263092041, "learning_rate": 7.795566502463054e-06, "loss": 1.2333, "step": 3970 }, { "epoch": 0.6108995807853544, "grad_norm": 3.5747170448303223, "learning_rate": 7.792487684729064e-06, "loss": 1.3172, "step": 3971 }, { "epoch": 0.6110534210222683, "grad_norm": 3.722682476043701, "learning_rate": 7.789408866995073e-06, "loss": 1.2431, "step": 3972 }, { "epoch": 0.6112072612591823, "grad_norm": 4.766950607299805, "learning_rate": 7.786330049261086e-06, "loss": 1.1924, "step": 3973 }, { "epoch": 0.6113611014960963, "grad_norm": 4.0804619789123535, "learning_rate": 7.783251231527095e-06, "loss": 1.3262, "step": 3974 }, { "epoch": 0.6115149417330102, "grad_norm": 3.6913130283355713, "learning_rate": 7.780172413793105e-06, "loss": 1.2019, "step": 3975 }, { "epoch": 0.6116687819699242, "grad_norm": 3.6338605880737305, "learning_rate": 7.777093596059114e-06, "loss": 1.3282, "step": 3976 }, { "epoch": 0.6118226222068383, "grad_norm": 3.6356852054595947, "learning_rate": 7.774014778325125e-06, "loss": 1.4472, "step": 3977 }, { "epoch": 0.6119764624437521, "grad_norm": 3.8960137367248535, "learning_rate": 7.770935960591134e-06, "loss": 1.3923, "step": 3978 }, { "epoch": 0.6121303026806661, "grad_norm": 3.3789706230163574, "learning_rate": 7.767857142857144e-06, "loss": 1.2586, "step": 3979 }, { "epoch": 0.61228414291758, "grad_norm": 3.0490264892578125, "learning_rate": 7.764778325123153e-06, "loss": 1.3327, "step": 3980 }, { "epoch": 0.612437983154494, "grad_norm": 3.5274007320404053, "learning_rate": 7.761699507389164e-06, "loss": 1.4388, "step": 3981 }, { "epoch": 0.612591823391408, "grad_norm": 3.607422351837158, "learning_rate": 7.758620689655173e-06, "loss": 1.1917, "step": 3982 }, { "epoch": 0.612745663628322, "grad_norm": 3.486722946166992, "learning_rate": 7.755541871921184e-06, "loss": 1.0752, "step": 3983 }, { "epoch": 0.612899503865236, "grad_norm": 3.9163053035736084, "learning_rate": 7.752463054187192e-06, "loss": 1.7493, "step": 3984 }, { "epoch": 0.61305334410215, "grad_norm": 3.5070135593414307, "learning_rate": 7.749384236453203e-06, "loss": 1.2442, "step": 3985 }, { "epoch": 0.6132071843390638, "grad_norm": 3.8932008743286133, "learning_rate": 7.746305418719212e-06, "loss": 1.1767, "step": 3986 }, { "epoch": 0.6133610245759779, "grad_norm": 3.9677462577819824, "learning_rate": 7.743226600985223e-06, "loss": 1.4083, "step": 3987 }, { "epoch": 0.6135148648128919, "grad_norm": 3.2216920852661133, "learning_rate": 7.740147783251232e-06, "loss": 1.3047, "step": 3988 }, { "epoch": 0.6136687050498058, "grad_norm": 4.08355188369751, "learning_rate": 7.737068965517242e-06, "loss": 1.3052, "step": 3989 }, { "epoch": 0.6138225452867198, "grad_norm": 3.3358049392700195, "learning_rate": 7.733990147783253e-06, "loss": 1.5629, "step": 3990 }, { "epoch": 0.6139763855236338, "grad_norm": 2.9419960975646973, "learning_rate": 7.730911330049262e-06, "loss": 1.2396, "step": 3991 }, { "epoch": 0.6141302257605477, "grad_norm": 4.469606399536133, "learning_rate": 7.727832512315273e-06, "loss": 1.3514, "step": 3992 }, { "epoch": 0.6142840659974617, "grad_norm": 3.5984697341918945, "learning_rate": 7.724753694581282e-06, "loss": 1.3236, "step": 3993 }, { "epoch": 0.6144379062343756, "grad_norm": 3.233426094055176, "learning_rate": 7.721674876847292e-06, "loss": 1.4129, "step": 3994 }, { "epoch": 0.6145917464712896, "grad_norm": 3.8909170627593994, "learning_rate": 7.718596059113301e-06, "loss": 1.2652, "step": 3995 }, { "epoch": 0.6147455867082036, "grad_norm": 3.032965660095215, "learning_rate": 7.715517241379312e-06, "loss": 1.6093, "step": 3996 }, { "epoch": 0.6148994269451175, "grad_norm": 4.025203227996826, "learning_rate": 7.71243842364532e-06, "loss": 1.4751, "step": 3997 }, { "epoch": 0.6150532671820315, "grad_norm": 3.319833278656006, "learning_rate": 7.709359605911331e-06, "loss": 1.4557, "step": 3998 }, { "epoch": 0.6152071074189455, "grad_norm": 3.1980020999908447, "learning_rate": 7.70628078817734e-06, "loss": 1.2557, "step": 3999 }, { "epoch": 0.6153609476558594, "grad_norm": 3.3428871631622314, "learning_rate": 7.703201970443351e-06, "loss": 1.4475, "step": 4000 }, { "epoch": 0.6155147878927734, "grad_norm": 3.6555566787719727, "learning_rate": 7.70012315270936e-06, "loss": 1.4552, "step": 4001 }, { "epoch": 0.6156686281296874, "grad_norm": 3.660794496536255, "learning_rate": 7.69704433497537e-06, "loss": 1.3373, "step": 4002 }, { "epoch": 0.6158224683666013, "grad_norm": 3.123695135116577, "learning_rate": 7.69396551724138e-06, "loss": 1.1754, "step": 4003 }, { "epoch": 0.6159763086035153, "grad_norm": 3.449287176132202, "learning_rate": 7.69088669950739e-06, "loss": 1.3275, "step": 4004 }, { "epoch": 0.6161301488404292, "grad_norm": 3.7568650245666504, "learning_rate": 7.687807881773399e-06, "loss": 1.3423, "step": 4005 }, { "epoch": 0.6162839890773432, "grad_norm": 3.346796989440918, "learning_rate": 7.68472906403941e-06, "loss": 1.2883, "step": 4006 }, { "epoch": 0.6164378293142572, "grad_norm": 3.013744592666626, "learning_rate": 7.68165024630542e-06, "loss": 1.2739, "step": 4007 }, { "epoch": 0.6165916695511711, "grad_norm": 3.5353012084960938, "learning_rate": 7.67857142857143e-06, "loss": 1.4328, "step": 4008 }, { "epoch": 0.6167455097880851, "grad_norm": 3.416872262954712, "learning_rate": 7.67549261083744e-06, "loss": 1.3788, "step": 4009 }, { "epoch": 0.6168993500249991, "grad_norm": 4.698660373687744, "learning_rate": 7.672413793103449e-06, "loss": 1.2235, "step": 4010 }, { "epoch": 0.617053190261913, "grad_norm": 3.3038647174835205, "learning_rate": 7.66933497536946e-06, "loss": 1.1788, "step": 4011 }, { "epoch": 0.617207030498827, "grad_norm": 3.215970993041992, "learning_rate": 7.666256157635469e-06, "loss": 1.4336, "step": 4012 }, { "epoch": 0.617360870735741, "grad_norm": 3.2100977897644043, "learning_rate": 7.66317733990148e-06, "loss": 1.3239, "step": 4013 }, { "epoch": 0.6175147109726549, "grad_norm": 3.5866549015045166, "learning_rate": 7.660098522167488e-06, "loss": 1.55, "step": 4014 }, { "epoch": 0.6176685512095689, "grad_norm": 3.0666956901550293, "learning_rate": 7.657019704433499e-06, "loss": 1.4472, "step": 4015 }, { "epoch": 0.6178223914464829, "grad_norm": 2.7328696250915527, "learning_rate": 7.653940886699508e-06, "loss": 1.3309, "step": 4016 }, { "epoch": 0.6179762316833968, "grad_norm": 3.3268089294433594, "learning_rate": 7.650862068965518e-06, "loss": 1.3733, "step": 4017 }, { "epoch": 0.6181300719203108, "grad_norm": 3.0830254554748535, "learning_rate": 7.647783251231527e-06, "loss": 1.0475, "step": 4018 }, { "epoch": 0.6182839121572247, "grad_norm": 4.326805591583252, "learning_rate": 7.644704433497538e-06, "loss": 1.2246, "step": 4019 }, { "epoch": 0.6184377523941387, "grad_norm": 3.734654426574707, "learning_rate": 7.641625615763547e-06, "loss": 1.2766, "step": 4020 }, { "epoch": 0.6185915926310527, "grad_norm": 3.1090762615203857, "learning_rate": 7.638546798029558e-06, "loss": 1.3945, "step": 4021 }, { "epoch": 0.6187454328679666, "grad_norm": 3.2214455604553223, "learning_rate": 7.635467980295567e-06, "loss": 1.3361, "step": 4022 }, { "epoch": 0.6188992731048806, "grad_norm": 2.7600786685943604, "learning_rate": 7.632389162561577e-06, "loss": 1.3739, "step": 4023 }, { "epoch": 0.6190531133417946, "grad_norm": 3.2080674171447754, "learning_rate": 7.629310344827587e-06, "loss": 1.5119, "step": 4024 }, { "epoch": 0.6192069535787085, "grad_norm": 3.5697340965270996, "learning_rate": 7.626231527093597e-06, "loss": 1.5006, "step": 4025 }, { "epoch": 0.6193607938156225, "grad_norm": 3.441315174102783, "learning_rate": 7.6231527093596066e-06, "loss": 1.4769, "step": 4026 }, { "epoch": 0.6195146340525365, "grad_norm": 4.332177639007568, "learning_rate": 7.620073891625616e-06, "loss": 0.9918, "step": 4027 }, { "epoch": 0.6196684742894504, "grad_norm": 4.035407066345215, "learning_rate": 7.616995073891626e-06, "loss": 1.401, "step": 4028 }, { "epoch": 0.6198223145263644, "grad_norm": 3.897083044052124, "learning_rate": 7.613916256157636e-06, "loss": 1.3842, "step": 4029 }, { "epoch": 0.6199761547632784, "grad_norm": 3.1777472496032715, "learning_rate": 7.610837438423646e-06, "loss": 1.0646, "step": 4030 }, { "epoch": 0.6201299950001923, "grad_norm": 3.7424204349517822, "learning_rate": 7.6077586206896556e-06, "loss": 1.4485, "step": 4031 }, { "epoch": 0.6202838352371063, "grad_norm": 3.9236671924591064, "learning_rate": 7.604679802955665e-06, "loss": 1.2972, "step": 4032 }, { "epoch": 0.6204376754740202, "grad_norm": 3.792119264602661, "learning_rate": 7.601600985221675e-06, "loss": 1.2914, "step": 4033 }, { "epoch": 0.6205915157109342, "grad_norm": 3.5450329780578613, "learning_rate": 7.598522167487685e-06, "loss": 1.2131, "step": 4034 }, { "epoch": 0.6207453559478482, "grad_norm": 3.0684189796447754, "learning_rate": 7.595443349753695e-06, "loss": 1.5202, "step": 4035 }, { "epoch": 0.6208991961847621, "grad_norm": 3.7406508922576904, "learning_rate": 7.5923645320197045e-06, "loss": 1.1814, "step": 4036 }, { "epoch": 0.6210530364216761, "grad_norm": 4.040831089019775, "learning_rate": 7.589285714285714e-06, "loss": 1.2812, "step": 4037 }, { "epoch": 0.6212068766585901, "grad_norm": 3.73996639251709, "learning_rate": 7.586206896551724e-06, "loss": 1.2747, "step": 4038 }, { "epoch": 0.621360716895504, "grad_norm": 3.529444694519043, "learning_rate": 7.583128078817734e-06, "loss": 1.2189, "step": 4039 }, { "epoch": 0.621514557132418, "grad_norm": 3.5306198596954346, "learning_rate": 7.580049261083744e-06, "loss": 1.3819, "step": 4040 }, { "epoch": 0.621668397369332, "grad_norm": 3.6207199096679688, "learning_rate": 7.576970443349755e-06, "loss": 1.1398, "step": 4041 }, { "epoch": 0.6218222376062459, "grad_norm": 3.379323959350586, "learning_rate": 7.573891625615765e-06, "loss": 1.1813, "step": 4042 }, { "epoch": 0.6219760778431599, "grad_norm": 3.808743715286255, "learning_rate": 7.570812807881775e-06, "loss": 1.2864, "step": 4043 }, { "epoch": 0.6221299180800739, "grad_norm": 3.38959002494812, "learning_rate": 7.567733990147784e-06, "loss": 1.4321, "step": 4044 }, { "epoch": 0.6222837583169878, "grad_norm": 3.5666234493255615, "learning_rate": 7.564655172413794e-06, "loss": 1.3672, "step": 4045 }, { "epoch": 0.6224375985539018, "grad_norm": 3.841388702392578, "learning_rate": 7.561576354679803e-06, "loss": 1.3541, "step": 4046 }, { "epoch": 0.6225914387908157, "grad_norm": 3.512354612350464, "learning_rate": 7.558497536945813e-06, "loss": 1.3065, "step": 4047 }, { "epoch": 0.6227452790277297, "grad_norm": 3.9534380435943604, "learning_rate": 7.555418719211823e-06, "loss": 1.1667, "step": 4048 }, { "epoch": 0.6228991192646437, "grad_norm": 3.3911380767822266, "learning_rate": 7.552339901477833e-06, "loss": 1.4328, "step": 4049 }, { "epoch": 0.6230529595015576, "grad_norm": 4.18373441696167, "learning_rate": 7.5492610837438426e-06, "loss": 1.4958, "step": 4050 }, { "epoch": 0.6232067997384716, "grad_norm": 3.644294023513794, "learning_rate": 7.546182266009852e-06, "loss": 1.2565, "step": 4051 }, { "epoch": 0.6233606399753856, "grad_norm": 3.817415237426758, "learning_rate": 7.543103448275862e-06, "loss": 1.05, "step": 4052 }, { "epoch": 0.6235144802122995, "grad_norm": 3.223681688308716, "learning_rate": 7.540024630541872e-06, "loss": 1.1407, "step": 4053 }, { "epoch": 0.6236683204492135, "grad_norm": 3.6370203495025635, "learning_rate": 7.536945812807882e-06, "loss": 1.4434, "step": 4054 }, { "epoch": 0.6238221606861275, "grad_norm": 3.2846839427948, "learning_rate": 7.5338669950738916e-06, "loss": 1.4545, "step": 4055 }, { "epoch": 0.6239760009230414, "grad_norm": 4.449133396148682, "learning_rate": 7.530788177339901e-06, "loss": 1.2584, "step": 4056 }, { "epoch": 0.6241298411599554, "grad_norm": 3.424785852432251, "learning_rate": 7.527709359605911e-06, "loss": 1.4348, "step": 4057 }, { "epoch": 0.6242836813968694, "grad_norm": 3.2045907974243164, "learning_rate": 7.524630541871923e-06, "loss": 1.4058, "step": 4058 }, { "epoch": 0.6244375216337833, "grad_norm": 3.160569429397583, "learning_rate": 7.5215517241379324e-06, "loss": 1.2765, "step": 4059 }, { "epoch": 0.6245913618706973, "grad_norm": 3.766857385635376, "learning_rate": 7.518472906403942e-06, "loss": 1.1893, "step": 4060 }, { "epoch": 0.6247452021076112, "grad_norm": 3.769496440887451, "learning_rate": 7.515394088669952e-06, "loss": 1.3351, "step": 4061 }, { "epoch": 0.6248990423445252, "grad_norm": 3.619755268096924, "learning_rate": 7.512315270935962e-06, "loss": 1.3084, "step": 4062 }, { "epoch": 0.6250528825814392, "grad_norm": 4.210471153259277, "learning_rate": 7.509236453201972e-06, "loss": 1.4397, "step": 4063 }, { "epoch": 0.6252067228183531, "grad_norm": 3.5081770420074463, "learning_rate": 7.5061576354679814e-06, "loss": 1.3978, "step": 4064 }, { "epoch": 0.6253605630552671, "grad_norm": 3.3452963829040527, "learning_rate": 7.503078817733991e-06, "loss": 1.4266, "step": 4065 }, { "epoch": 0.6255144032921811, "grad_norm": 3.345733404159546, "learning_rate": 7.500000000000001e-06, "loss": 1.2585, "step": 4066 }, { "epoch": 0.625668243529095, "grad_norm": 4.62701416015625, "learning_rate": 7.49692118226601e-06, "loss": 1.3878, "step": 4067 }, { "epoch": 0.625822083766009, "grad_norm": 3.543466091156006, "learning_rate": 7.49384236453202e-06, "loss": 0.9096, "step": 4068 }, { "epoch": 0.625975924002923, "grad_norm": 3.9592232704162598, "learning_rate": 7.49076354679803e-06, "loss": 1.3297, "step": 4069 }, { "epoch": 0.6261297642398369, "grad_norm": 3.099329948425293, "learning_rate": 7.487684729064039e-06, "loss": 1.3749, "step": 4070 }, { "epoch": 0.6262836044767509, "grad_norm": 3.384570598602295, "learning_rate": 7.484605911330049e-06, "loss": 1.4753, "step": 4071 }, { "epoch": 0.6264374447136648, "grad_norm": 3.3069896697998047, "learning_rate": 7.481527093596059e-06, "loss": 1.3122, "step": 4072 }, { "epoch": 0.6265912849505788, "grad_norm": 3.2420754432678223, "learning_rate": 7.478448275862069e-06, "loss": 1.3819, "step": 4073 }, { "epoch": 0.6267451251874928, "grad_norm": 3.7156200408935547, "learning_rate": 7.4753694581280786e-06, "loss": 1.168, "step": 4074 }, { "epoch": 0.6268989654244067, "grad_norm": 3.960949659347534, "learning_rate": 7.47229064039409e-06, "loss": 1.3598, "step": 4075 }, { "epoch": 0.6270528056613207, "grad_norm": 3.4375522136688232, "learning_rate": 7.4692118226601e-06, "loss": 1.3233, "step": 4076 }, { "epoch": 0.6272066458982347, "grad_norm": 3.3056485652923584, "learning_rate": 7.46613300492611e-06, "loss": 1.6344, "step": 4077 }, { "epoch": 0.6273604861351486, "grad_norm": 3.856384038925171, "learning_rate": 7.4630541871921195e-06, "loss": 1.3134, "step": 4078 }, { "epoch": 0.6275143263720626, "grad_norm": 3.684459686279297, "learning_rate": 7.459975369458129e-06, "loss": 1.2194, "step": 4079 }, { "epoch": 0.6276681666089766, "grad_norm": 3.6767683029174805, "learning_rate": 7.456896551724139e-06, "loss": 1.3708, "step": 4080 }, { "epoch": 0.6278220068458905, "grad_norm": 3.637697458267212, "learning_rate": 7.453817733990149e-06, "loss": 0.9379, "step": 4081 }, { "epoch": 0.6279758470828045, "grad_norm": 3.5993008613586426, "learning_rate": 7.450738916256159e-06, "loss": 1.4414, "step": 4082 }, { "epoch": 0.6281296873197185, "grad_norm": 3.306098699569702, "learning_rate": 7.4476600985221685e-06, "loss": 1.2941, "step": 4083 }, { "epoch": 0.6282835275566324, "grad_norm": 4.3411760330200195, "learning_rate": 7.444581280788178e-06, "loss": 1.2731, "step": 4084 }, { "epoch": 0.6284373677935464, "grad_norm": 3.222716808319092, "learning_rate": 7.441502463054188e-06, "loss": 1.3146, "step": 4085 }, { "epoch": 0.6285912080304603, "grad_norm": 3.2814383506774902, "learning_rate": 7.438423645320198e-06, "loss": 1.566, "step": 4086 }, { "epoch": 0.6287450482673743, "grad_norm": 3.3815016746520996, "learning_rate": 7.435344827586208e-06, "loss": 1.2971, "step": 4087 }, { "epoch": 0.6288988885042883, "grad_norm": 4.221499919891357, "learning_rate": 7.4322660098522174e-06, "loss": 1.4008, "step": 4088 }, { "epoch": 0.6290527287412022, "grad_norm": 3.4946861267089844, "learning_rate": 7.429187192118226e-06, "loss": 1.358, "step": 4089 }, { "epoch": 0.6292065689781162, "grad_norm": 3.223294734954834, "learning_rate": 7.426108374384236e-06, "loss": 1.2423, "step": 4090 }, { "epoch": 0.6293604092150302, "grad_norm": 3.4920945167541504, "learning_rate": 7.423029556650246e-06, "loss": 1.5177, "step": 4091 }, { "epoch": 0.6295142494519441, "grad_norm": 4.099567890167236, "learning_rate": 7.4199507389162575e-06, "loss": 1.3765, "step": 4092 }, { "epoch": 0.6296680896888581, "grad_norm": 3.203533172607422, "learning_rate": 7.416871921182267e-06, "loss": 0.9704, "step": 4093 }, { "epoch": 0.6298219299257721, "grad_norm": 3.352999210357666, "learning_rate": 7.413793103448277e-06, "loss": 1.1734, "step": 4094 }, { "epoch": 0.629975770162686, "grad_norm": 3.8276681900024414, "learning_rate": 7.410714285714287e-06, "loss": 1.1353, "step": 4095 }, { "epoch": 0.6301296103996, "grad_norm": 3.7515079975128174, "learning_rate": 7.407635467980297e-06, "loss": 1.1391, "step": 4096 }, { "epoch": 0.630283450636514, "grad_norm": 3.9583702087402344, "learning_rate": 7.4045566502463065e-06, "loss": 1.535, "step": 4097 }, { "epoch": 0.6304372908734279, "grad_norm": 2.894320011138916, "learning_rate": 7.401477832512316e-06, "loss": 1.3656, "step": 4098 }, { "epoch": 0.6305911311103419, "grad_norm": 3.932299852371216, "learning_rate": 7.398399014778326e-06, "loss": 1.2974, "step": 4099 }, { "epoch": 0.6307449713472558, "grad_norm": 3.7756218910217285, "learning_rate": 7.395320197044336e-06, "loss": 1.4306, "step": 4100 }, { "epoch": 0.6308988115841698, "grad_norm": 3.1641602516174316, "learning_rate": 7.392241379310346e-06, "loss": 1.1582, "step": 4101 }, { "epoch": 0.6310526518210838, "grad_norm": 3.5676350593566895, "learning_rate": 7.3891625615763555e-06, "loss": 1.3671, "step": 4102 }, { "epoch": 0.6312064920579977, "grad_norm": 4.297637462615967, "learning_rate": 7.386083743842365e-06, "loss": 1.0855, "step": 4103 }, { "epoch": 0.6313603322949117, "grad_norm": 3.6572117805480957, "learning_rate": 7.383004926108375e-06, "loss": 1.4025, "step": 4104 }, { "epoch": 0.6315141725318257, "grad_norm": 4.033413410186768, "learning_rate": 7.379926108374385e-06, "loss": 1.4205, "step": 4105 }, { "epoch": 0.6316680127687396, "grad_norm": 3.654505729675293, "learning_rate": 7.376847290640395e-06, "loss": 1.2418, "step": 4106 }, { "epoch": 0.6318218530056536, "grad_norm": 3.298661708831787, "learning_rate": 7.3737684729064045e-06, "loss": 1.2633, "step": 4107 }, { "epoch": 0.6319756932425676, "grad_norm": 3.6031675338745117, "learning_rate": 7.370689655172414e-06, "loss": 1.4213, "step": 4108 }, { "epoch": 0.6321295334794815, "grad_norm": 3.354746103286743, "learning_rate": 7.367610837438425e-06, "loss": 1.3654, "step": 4109 }, { "epoch": 0.6322833737163955, "grad_norm": 4.135150909423828, "learning_rate": 7.364532019704435e-06, "loss": 1.4738, "step": 4110 }, { "epoch": 0.6324372139533095, "grad_norm": 3.6455307006835938, "learning_rate": 7.3614532019704445e-06, "loss": 1.186, "step": 4111 }, { "epoch": 0.6325910541902234, "grad_norm": 3.219573497772217, "learning_rate": 7.358374384236454e-06, "loss": 1.4625, "step": 4112 }, { "epoch": 0.6327448944271374, "grad_norm": 3.4046976566314697, "learning_rate": 7.355295566502464e-06, "loss": 1.4066, "step": 4113 }, { "epoch": 0.6328987346640513, "grad_norm": 4.080909252166748, "learning_rate": 7.352216748768474e-06, "loss": 1.0149, "step": 4114 }, { "epoch": 0.6330525749009653, "grad_norm": 3.675624132156372, "learning_rate": 7.349137931034484e-06, "loss": 1.7144, "step": 4115 }, { "epoch": 0.6332064151378793, "grad_norm": 3.5234971046447754, "learning_rate": 7.3460591133004935e-06, "loss": 1.1497, "step": 4116 }, { "epoch": 0.6333602553747932, "grad_norm": 3.798657178878784, "learning_rate": 7.342980295566503e-06, "loss": 1.2823, "step": 4117 }, { "epoch": 0.6335140956117072, "grad_norm": 4.0523223876953125, "learning_rate": 7.339901477832513e-06, "loss": 1.3998, "step": 4118 }, { "epoch": 0.6336679358486212, "grad_norm": 5.689726829528809, "learning_rate": 7.336822660098523e-06, "loss": 1.0803, "step": 4119 }, { "epoch": 0.6338217760855351, "grad_norm": 3.670863628387451, "learning_rate": 7.333743842364533e-06, "loss": 1.2865, "step": 4120 }, { "epoch": 0.6339756163224491, "grad_norm": 3.653999090194702, "learning_rate": 7.3306650246305425e-06, "loss": 1.2805, "step": 4121 }, { "epoch": 0.6341294565593631, "grad_norm": 3.8281993865966797, "learning_rate": 7.327586206896552e-06, "loss": 1.2492, "step": 4122 }, { "epoch": 0.634283296796277, "grad_norm": 3.293733596801758, "learning_rate": 7.324507389162562e-06, "loss": 1.2971, "step": 4123 }, { "epoch": 0.634437137033191, "grad_norm": 3.2563974857330322, "learning_rate": 7.321428571428572e-06, "loss": 1.0768, "step": 4124 }, { "epoch": 0.634590977270105, "grad_norm": 3.0837228298187256, "learning_rate": 7.318349753694582e-06, "loss": 1.1637, "step": 4125 }, { "epoch": 0.6347448175070189, "grad_norm": 4.08994197845459, "learning_rate": 7.315270935960592e-06, "loss": 1.2785, "step": 4126 }, { "epoch": 0.634898657743933, "grad_norm": 3.430542469024658, "learning_rate": 7.312192118226602e-06, "loss": 1.402, "step": 4127 }, { "epoch": 0.6350524979808468, "grad_norm": 4.136353969573975, "learning_rate": 7.309113300492612e-06, "loss": 1.2567, "step": 4128 }, { "epoch": 0.6352063382177608, "grad_norm": 3.8043744564056396, "learning_rate": 7.306034482758622e-06, "loss": 1.4381, "step": 4129 }, { "epoch": 0.6353601784546749, "grad_norm": 3.8010952472686768, "learning_rate": 7.3029556650246315e-06, "loss": 1.3604, "step": 4130 }, { "epoch": 0.6355140186915887, "grad_norm": 4.209910869598389, "learning_rate": 7.299876847290641e-06, "loss": 1.41, "step": 4131 }, { "epoch": 0.6356678589285027, "grad_norm": 3.6800336837768555, "learning_rate": 7.296798029556651e-06, "loss": 1.1597, "step": 4132 }, { "epoch": 0.6358216991654168, "grad_norm": 3.783446788787842, "learning_rate": 7.293719211822661e-06, "loss": 1.2829, "step": 4133 }, { "epoch": 0.6359755394023306, "grad_norm": 4.38191032409668, "learning_rate": 7.290640394088671e-06, "loss": 1.2548, "step": 4134 }, { "epoch": 0.6361293796392447, "grad_norm": 3.737917900085449, "learning_rate": 7.2875615763546805e-06, "loss": 1.3802, "step": 4135 }, { "epoch": 0.6362832198761587, "grad_norm": 3.4355523586273193, "learning_rate": 7.28448275862069e-06, "loss": 1.3899, "step": 4136 }, { "epoch": 0.6364370601130726, "grad_norm": 3.7273924350738525, "learning_rate": 7.2814039408867e-06, "loss": 1.3768, "step": 4137 }, { "epoch": 0.6365909003499866, "grad_norm": 3.2030093669891357, "learning_rate": 7.27832512315271e-06, "loss": 1.3815, "step": 4138 }, { "epoch": 0.6367447405869004, "grad_norm": 4.5288472175598145, "learning_rate": 7.27524630541872e-06, "loss": 1.3096, "step": 4139 }, { "epoch": 0.6368985808238145, "grad_norm": 3.826589584350586, "learning_rate": 7.2721674876847295e-06, "loss": 1.408, "step": 4140 }, { "epoch": 0.6370524210607285, "grad_norm": 3.3415520191192627, "learning_rate": 7.269088669950739e-06, "loss": 1.2264, "step": 4141 }, { "epoch": 0.6372062612976424, "grad_norm": 3.1588263511657715, "learning_rate": 7.266009852216749e-06, "loss": 1.1084, "step": 4142 }, { "epoch": 0.6373601015345564, "grad_norm": 3.1275835037231445, "learning_rate": 7.26293103448276e-06, "loss": 1.2085, "step": 4143 }, { "epoch": 0.6375139417714704, "grad_norm": 3.2859699726104736, "learning_rate": 7.2598522167487695e-06, "loss": 1.1138, "step": 4144 }, { "epoch": 0.6376677820083843, "grad_norm": 3.609970808029175, "learning_rate": 7.256773399014779e-06, "loss": 1.2465, "step": 4145 }, { "epoch": 0.6378216222452983, "grad_norm": 2.9350948333740234, "learning_rate": 7.253694581280789e-06, "loss": 1.5109, "step": 4146 }, { "epoch": 0.6379754624822123, "grad_norm": 3.595932960510254, "learning_rate": 7.250615763546799e-06, "loss": 1.2932, "step": 4147 }, { "epoch": 0.6381293027191262, "grad_norm": 3.601435422897339, "learning_rate": 7.247536945812809e-06, "loss": 1.1743, "step": 4148 }, { "epoch": 0.6382831429560402, "grad_norm": 3.501757860183716, "learning_rate": 7.2444581280788185e-06, "loss": 1.3524, "step": 4149 }, { "epoch": 0.6384369831929542, "grad_norm": 3.848778486251831, "learning_rate": 7.241379310344828e-06, "loss": 1.3555, "step": 4150 }, { "epoch": 0.6385908234298681, "grad_norm": 3.662433385848999, "learning_rate": 7.238300492610838e-06, "loss": 1.3507, "step": 4151 }, { "epoch": 0.6387446636667821, "grad_norm": 3.1311116218566895, "learning_rate": 7.235221674876848e-06, "loss": 1.4491, "step": 4152 }, { "epoch": 0.638898503903696, "grad_norm": 3.306713342666626, "learning_rate": 7.232142857142858e-06, "loss": 1.28, "step": 4153 }, { "epoch": 0.63905234414061, "grad_norm": 3.419861316680908, "learning_rate": 7.2290640394088675e-06, "loss": 1.2382, "step": 4154 }, { "epoch": 0.639206184377524, "grad_norm": 3.5424249172210693, "learning_rate": 7.225985221674877e-06, "loss": 1.2482, "step": 4155 }, { "epoch": 0.6393600246144379, "grad_norm": 3.3217952251434326, "learning_rate": 7.222906403940887e-06, "loss": 1.151, "step": 4156 }, { "epoch": 0.6395138648513519, "grad_norm": 3.428143262863159, "learning_rate": 7.219827586206897e-06, "loss": 1.1962, "step": 4157 }, { "epoch": 0.6396677050882659, "grad_norm": 3.1923277378082275, "learning_rate": 7.216748768472907e-06, "loss": 1.2659, "step": 4158 }, { "epoch": 0.6398215453251798, "grad_norm": 3.357661008834839, "learning_rate": 7.2136699507389165e-06, "loss": 1.3656, "step": 4159 }, { "epoch": 0.6399753855620938, "grad_norm": 3.3405301570892334, "learning_rate": 7.210591133004927e-06, "loss": 1.236, "step": 4160 }, { "epoch": 0.6401292257990078, "grad_norm": 3.07485032081604, "learning_rate": 7.207512315270937e-06, "loss": 1.3478, "step": 4161 }, { "epoch": 0.6402830660359217, "grad_norm": 3.5579845905303955, "learning_rate": 7.204433497536947e-06, "loss": 1.1944, "step": 4162 }, { "epoch": 0.6404369062728357, "grad_norm": 3.3755552768707275, "learning_rate": 7.2013546798029565e-06, "loss": 1.403, "step": 4163 }, { "epoch": 0.6405907465097497, "grad_norm": 4.011425971984863, "learning_rate": 7.198275862068966e-06, "loss": 1.429, "step": 4164 }, { "epoch": 0.6407445867466636, "grad_norm": 3.663466453552246, "learning_rate": 7.195197044334976e-06, "loss": 1.4173, "step": 4165 }, { "epoch": 0.6408984269835776, "grad_norm": 3.368156909942627, "learning_rate": 7.192118226600986e-06, "loss": 1.3846, "step": 4166 }, { "epoch": 0.6410522672204915, "grad_norm": 3.4592080116271973, "learning_rate": 7.189039408866996e-06, "loss": 1.1298, "step": 4167 }, { "epoch": 0.6412061074574055, "grad_norm": 3.308711528778076, "learning_rate": 7.1859605911330055e-06, "loss": 1.2984, "step": 4168 }, { "epoch": 0.6413599476943195, "grad_norm": 3.4955992698669434, "learning_rate": 7.182881773399015e-06, "loss": 1.3993, "step": 4169 }, { "epoch": 0.6415137879312334, "grad_norm": 3.523813486099243, "learning_rate": 7.179802955665025e-06, "loss": 1.2809, "step": 4170 }, { "epoch": 0.6416676281681474, "grad_norm": 3.081090211868286, "learning_rate": 7.176724137931035e-06, "loss": 1.4751, "step": 4171 }, { "epoch": 0.6418214684050614, "grad_norm": 3.711393356323242, "learning_rate": 7.173645320197045e-06, "loss": 1.3754, "step": 4172 }, { "epoch": 0.6419753086419753, "grad_norm": 3.711150884628296, "learning_rate": 7.1705665024630545e-06, "loss": 1.2787, "step": 4173 }, { "epoch": 0.6421291488788893, "grad_norm": 3.201106548309326, "learning_rate": 7.167487684729064e-06, "loss": 1.2668, "step": 4174 }, { "epoch": 0.6422829891158033, "grad_norm": 3.251452684402466, "learning_rate": 7.164408866995074e-06, "loss": 1.2645, "step": 4175 }, { "epoch": 0.6424368293527172, "grad_norm": 4.3393683433532715, "learning_rate": 7.161330049261085e-06, "loss": 1.3543, "step": 4176 }, { "epoch": 0.6425906695896312, "grad_norm": 3.6386327743530273, "learning_rate": 7.1582512315270946e-06, "loss": 1.4406, "step": 4177 }, { "epoch": 0.6427445098265452, "grad_norm": 3.500943422317505, "learning_rate": 7.155172413793104e-06, "loss": 1.3746, "step": 4178 }, { "epoch": 0.6428983500634591, "grad_norm": 2.8618950843811035, "learning_rate": 7.152093596059114e-06, "loss": 1.2003, "step": 4179 }, { "epoch": 0.6430521903003731, "grad_norm": 3.4900214672088623, "learning_rate": 7.149014778325124e-06, "loss": 1.3622, "step": 4180 }, { "epoch": 0.643206030537287, "grad_norm": 3.0381243228912354, "learning_rate": 7.145935960591134e-06, "loss": 1.4041, "step": 4181 }, { "epoch": 0.643359870774201, "grad_norm": 3.0653367042541504, "learning_rate": 7.1428571428571436e-06, "loss": 1.1627, "step": 4182 }, { "epoch": 0.643513711011115, "grad_norm": 3.450474500656128, "learning_rate": 7.139778325123153e-06, "loss": 1.3949, "step": 4183 }, { "epoch": 0.6436675512480289, "grad_norm": 4.452366828918457, "learning_rate": 7.136699507389163e-06, "loss": 1.2882, "step": 4184 }, { "epoch": 0.6438213914849429, "grad_norm": 3.4808480739593506, "learning_rate": 7.133620689655173e-06, "loss": 1.2778, "step": 4185 }, { "epoch": 0.6439752317218569, "grad_norm": 4.338043689727783, "learning_rate": 7.130541871921183e-06, "loss": 1.3486, "step": 4186 }, { "epoch": 0.6441290719587708, "grad_norm": 3.9591424465179443, "learning_rate": 7.1274630541871926e-06, "loss": 1.5047, "step": 4187 }, { "epoch": 0.6442829121956848, "grad_norm": 3.673368215560913, "learning_rate": 7.124384236453202e-06, "loss": 1.2406, "step": 4188 }, { "epoch": 0.6444367524325988, "grad_norm": 3.74666166305542, "learning_rate": 7.121305418719212e-06, "loss": 1.2977, "step": 4189 }, { "epoch": 0.6445905926695127, "grad_norm": 3.545855760574341, "learning_rate": 7.118226600985222e-06, "loss": 1.4477, "step": 4190 }, { "epoch": 0.6447444329064267, "grad_norm": 3.463977098464966, "learning_rate": 7.115147783251232e-06, "loss": 1.2647, "step": 4191 }, { "epoch": 0.6448982731433407, "grad_norm": 3.482876777648926, "learning_rate": 7.1120689655172415e-06, "loss": 1.2216, "step": 4192 }, { "epoch": 0.6450521133802546, "grad_norm": 3.822120428085327, "learning_rate": 7.108990147783252e-06, "loss": 1.1485, "step": 4193 }, { "epoch": 0.6452059536171686, "grad_norm": 3.4617919921875, "learning_rate": 7.105911330049262e-06, "loss": 1.1583, "step": 4194 }, { "epoch": 0.6453597938540825, "grad_norm": 4.194601535797119, "learning_rate": 7.102832512315272e-06, "loss": 1.4263, "step": 4195 }, { "epoch": 0.6455136340909965, "grad_norm": 3.8963449001312256, "learning_rate": 7.099753694581282e-06, "loss": 1.405, "step": 4196 }, { "epoch": 0.6456674743279105, "grad_norm": 3.9902889728546143, "learning_rate": 7.096674876847291e-06, "loss": 1.2795, "step": 4197 }, { "epoch": 0.6458213145648244, "grad_norm": 3.58475661277771, "learning_rate": 7.093596059113301e-06, "loss": 1.4341, "step": 4198 }, { "epoch": 0.6459751548017384, "grad_norm": 3.620103120803833, "learning_rate": 7.090517241379311e-06, "loss": 1.3398, "step": 4199 }, { "epoch": 0.6461289950386524, "grad_norm": 3.234849452972412, "learning_rate": 7.087438423645321e-06, "loss": 1.1668, "step": 4200 }, { "epoch": 0.6462828352755663, "grad_norm": 3.7447690963745117, "learning_rate": 7.0843596059113306e-06, "loss": 1.3835, "step": 4201 }, { "epoch": 0.6464366755124803, "grad_norm": 3.353086471557617, "learning_rate": 7.08128078817734e-06, "loss": 1.2595, "step": 4202 }, { "epoch": 0.6465905157493943, "grad_norm": 3.548417091369629, "learning_rate": 7.07820197044335e-06, "loss": 1.2914, "step": 4203 }, { "epoch": 0.6467443559863082, "grad_norm": 3.217862606048584, "learning_rate": 7.07512315270936e-06, "loss": 1.2958, "step": 4204 }, { "epoch": 0.6468981962232222, "grad_norm": 3.678868532180786, "learning_rate": 7.07204433497537e-06, "loss": 1.2626, "step": 4205 }, { "epoch": 0.6470520364601362, "grad_norm": 3.6982522010803223, "learning_rate": 7.0689655172413796e-06, "loss": 1.2192, "step": 4206 }, { "epoch": 0.6472058766970501, "grad_norm": 3.2784035205841064, "learning_rate": 7.065886699507389e-06, "loss": 1.1889, "step": 4207 }, { "epoch": 0.6473597169339641, "grad_norm": 4.133390426635742, "learning_rate": 7.062807881773399e-06, "loss": 1.7281, "step": 4208 }, { "epoch": 0.647513557170878, "grad_norm": 3.47686505317688, "learning_rate": 7.059729064039409e-06, "loss": 1.2487, "step": 4209 }, { "epoch": 0.647667397407792, "grad_norm": 3.4933526515960693, "learning_rate": 7.05665024630542e-06, "loss": 1.1421, "step": 4210 }, { "epoch": 0.647821237644706, "grad_norm": 2.993772029876709, "learning_rate": 7.053571428571429e-06, "loss": 1.4866, "step": 4211 }, { "epoch": 0.6479750778816199, "grad_norm": 3.054316997528076, "learning_rate": 7.050492610837439e-06, "loss": 1.3827, "step": 4212 }, { "epoch": 0.6481289181185339, "grad_norm": 3.7264835834503174, "learning_rate": 7.047413793103449e-06, "loss": 1.2416, "step": 4213 }, { "epoch": 0.6482827583554479, "grad_norm": 3.6189587116241455, "learning_rate": 7.044334975369459e-06, "loss": 1.5429, "step": 4214 }, { "epoch": 0.6484365985923618, "grad_norm": 3.009774684906006, "learning_rate": 7.041256157635469e-06, "loss": 1.2441, "step": 4215 }, { "epoch": 0.6485904388292758, "grad_norm": 3.2992141246795654, "learning_rate": 7.038177339901478e-06, "loss": 1.4795, "step": 4216 }, { "epoch": 0.6487442790661898, "grad_norm": 4.462273120880127, "learning_rate": 7.035098522167488e-06, "loss": 1.454, "step": 4217 }, { "epoch": 0.6488981193031037, "grad_norm": 3.9138739109039307, "learning_rate": 7.032019704433498e-06, "loss": 1.0947, "step": 4218 }, { "epoch": 0.6490519595400177, "grad_norm": 3.791147470474243, "learning_rate": 7.028940886699508e-06, "loss": 1.451, "step": 4219 }, { "epoch": 0.6492057997769316, "grad_norm": 3.4731719493865967, "learning_rate": 7.025862068965518e-06, "loss": 1.2983, "step": 4220 }, { "epoch": 0.6493596400138456, "grad_norm": 3.3962666988372803, "learning_rate": 7.022783251231527e-06, "loss": 1.3036, "step": 4221 }, { "epoch": 0.6495134802507596, "grad_norm": 3.4415013790130615, "learning_rate": 7.019704433497537e-06, "loss": 1.2423, "step": 4222 }, { "epoch": 0.6496673204876735, "grad_norm": 3.5785071849823, "learning_rate": 7.016625615763547e-06, "loss": 1.3791, "step": 4223 }, { "epoch": 0.6498211607245875, "grad_norm": 3.158794403076172, "learning_rate": 7.013546798029557e-06, "loss": 1.4692, "step": 4224 }, { "epoch": 0.6499750009615015, "grad_norm": 3.864440679550171, "learning_rate": 7.010467980295567e-06, "loss": 1.4509, "step": 4225 }, { "epoch": 0.6501288411984154, "grad_norm": 3.5619373321533203, "learning_rate": 7.007389162561576e-06, "loss": 1.1814, "step": 4226 }, { "epoch": 0.6502826814353294, "grad_norm": 3.9073588848114014, "learning_rate": 7.004310344827587e-06, "loss": 1.4089, "step": 4227 }, { "epoch": 0.6504365216722434, "grad_norm": 3.561739444732666, "learning_rate": 7.001231527093597e-06, "loss": 1.2148, "step": 4228 }, { "epoch": 0.6505903619091573, "grad_norm": 3.5931742191314697, "learning_rate": 6.998152709359607e-06, "loss": 1.3167, "step": 4229 }, { "epoch": 0.6507442021460713, "grad_norm": 3.5346038341522217, "learning_rate": 6.995073891625616e-06, "loss": 1.0243, "step": 4230 }, { "epoch": 0.6508980423829853, "grad_norm": 3.4135794639587402, "learning_rate": 6.991995073891626e-06, "loss": 1.3038, "step": 4231 }, { "epoch": 0.6510518826198992, "grad_norm": 3.770589828491211, "learning_rate": 6.988916256157636e-06, "loss": 1.2659, "step": 4232 }, { "epoch": 0.6512057228568132, "grad_norm": 4.071718215942383, "learning_rate": 6.985837438423646e-06, "loss": 1.4331, "step": 4233 }, { "epoch": 0.6513595630937271, "grad_norm": 3.6399691104888916, "learning_rate": 6.982758620689656e-06, "loss": 1.4966, "step": 4234 }, { "epoch": 0.6515134033306411, "grad_norm": 4.03931999206543, "learning_rate": 6.979679802955665e-06, "loss": 1.2694, "step": 4235 }, { "epoch": 0.6516672435675551, "grad_norm": 4.097228527069092, "learning_rate": 6.976600985221675e-06, "loss": 1.2898, "step": 4236 }, { "epoch": 0.651821083804469, "grad_norm": 3.7689526081085205, "learning_rate": 6.973522167487685e-06, "loss": 1.4198, "step": 4237 }, { "epoch": 0.651974924041383, "grad_norm": 3.9654362201690674, "learning_rate": 6.970443349753695e-06, "loss": 1.5758, "step": 4238 }, { "epoch": 0.652128764278297, "grad_norm": 3.9826929569244385, "learning_rate": 6.967364532019705e-06, "loss": 1.3957, "step": 4239 }, { "epoch": 0.6522826045152109, "grad_norm": 4.191890239715576, "learning_rate": 6.964285714285714e-06, "loss": 1.326, "step": 4240 }, { "epoch": 0.6524364447521249, "grad_norm": 3.3551087379455566, "learning_rate": 6.961206896551724e-06, "loss": 1.4019, "step": 4241 }, { "epoch": 0.6525902849890389, "grad_norm": 3.536519765853882, "learning_rate": 6.958128078817734e-06, "loss": 1.3483, "step": 4242 }, { "epoch": 0.6527441252259528, "grad_norm": 3.7399415969848633, "learning_rate": 6.955049261083744e-06, "loss": 1.3318, "step": 4243 }, { "epoch": 0.6528979654628668, "grad_norm": 3.5404322147369385, "learning_rate": 6.9519704433497544e-06, "loss": 1.3445, "step": 4244 }, { "epoch": 0.6530518056997808, "grad_norm": 3.980051040649414, "learning_rate": 6.948891625615764e-06, "loss": 1.3642, "step": 4245 }, { "epoch": 0.6532056459366947, "grad_norm": 4.844604015350342, "learning_rate": 6.945812807881774e-06, "loss": 1.3, "step": 4246 }, { "epoch": 0.6533594861736087, "grad_norm": 3.7194247245788574, "learning_rate": 6.942733990147784e-06, "loss": 1.4587, "step": 4247 }, { "epoch": 0.6535133264105226, "grad_norm": 3.004945755004883, "learning_rate": 6.939655172413794e-06, "loss": 1.5262, "step": 4248 }, { "epoch": 0.6536671666474366, "grad_norm": 3.28540301322937, "learning_rate": 6.9365763546798034e-06, "loss": 1.227, "step": 4249 }, { "epoch": 0.6538210068843506, "grad_norm": 4.075019359588623, "learning_rate": 6.933497536945813e-06, "loss": 1.2762, "step": 4250 }, { "epoch": 0.6539748471212645, "grad_norm": 3.664207935333252, "learning_rate": 6.930418719211823e-06, "loss": 1.0834, "step": 4251 }, { "epoch": 0.6541286873581785, "grad_norm": 3.2443618774414062, "learning_rate": 6.927339901477833e-06, "loss": 1.3973, "step": 4252 }, { "epoch": 0.6542825275950925, "grad_norm": 3.53936767578125, "learning_rate": 6.924261083743843e-06, "loss": 1.1248, "step": 4253 }, { "epoch": 0.6544363678320064, "grad_norm": 3.2531304359436035, "learning_rate": 6.9211822660098524e-06, "loss": 1.3243, "step": 4254 }, { "epoch": 0.6545902080689204, "grad_norm": 4.027378559112549, "learning_rate": 6.918103448275862e-06, "loss": 1.2906, "step": 4255 }, { "epoch": 0.6547440483058344, "grad_norm": 3.54645037651062, "learning_rate": 6.915024630541872e-06, "loss": 1.1241, "step": 4256 }, { "epoch": 0.6548978885427483, "grad_norm": 4.485415935516357, "learning_rate": 6.911945812807882e-06, "loss": 1.5016, "step": 4257 }, { "epoch": 0.6550517287796623, "grad_norm": 4.598642826080322, "learning_rate": 6.908866995073892e-06, "loss": 1.5466, "step": 4258 }, { "epoch": 0.6552055690165763, "grad_norm": 3.4209682941436768, "learning_rate": 6.905788177339901e-06, "loss": 1.1907, "step": 4259 }, { "epoch": 0.6553594092534902, "grad_norm": 3.458214521408081, "learning_rate": 6.902709359605911e-06, "loss": 1.4849, "step": 4260 }, { "epoch": 0.6555132494904042, "grad_norm": 3.3536453247070312, "learning_rate": 6.899630541871922e-06, "loss": 1.0533, "step": 4261 }, { "epoch": 0.6556670897273181, "grad_norm": 3.7586681842803955, "learning_rate": 6.896551724137932e-06, "loss": 1.5745, "step": 4262 }, { "epoch": 0.6558209299642321, "grad_norm": 3.421654462814331, "learning_rate": 6.8934729064039415e-06, "loss": 1.1772, "step": 4263 }, { "epoch": 0.6559747702011461, "grad_norm": 4.935487270355225, "learning_rate": 6.890394088669951e-06, "loss": 1.1315, "step": 4264 }, { "epoch": 0.65612861043806, "grad_norm": 3.715625047683716, "learning_rate": 6.887315270935961e-06, "loss": 1.0045, "step": 4265 }, { "epoch": 0.656282450674974, "grad_norm": 3.617384672164917, "learning_rate": 6.884236453201971e-06, "loss": 1.4031, "step": 4266 }, { "epoch": 0.656436290911888, "grad_norm": 3.6703763008117676, "learning_rate": 6.881157635467981e-06, "loss": 1.3278, "step": 4267 }, { "epoch": 0.6565901311488019, "grad_norm": 3.5356204509735107, "learning_rate": 6.8780788177339904e-06, "loss": 1.1939, "step": 4268 }, { "epoch": 0.6567439713857159, "grad_norm": 3.625809669494629, "learning_rate": 6.875e-06, "loss": 1.1144, "step": 4269 }, { "epoch": 0.65689781162263, "grad_norm": 3.3562824726104736, "learning_rate": 6.87192118226601e-06, "loss": 1.4266, "step": 4270 }, { "epoch": 0.6570516518595438, "grad_norm": 3.3208084106445312, "learning_rate": 6.86884236453202e-06, "loss": 1.4609, "step": 4271 }, { "epoch": 0.6572054920964578, "grad_norm": 3.3559041023254395, "learning_rate": 6.86576354679803e-06, "loss": 1.265, "step": 4272 }, { "epoch": 0.6573593323333718, "grad_norm": 3.590773105621338, "learning_rate": 6.8626847290640394e-06, "loss": 1.2614, "step": 4273 }, { "epoch": 0.6575131725702857, "grad_norm": 3.098362922668457, "learning_rate": 6.859605911330049e-06, "loss": 1.439, "step": 4274 }, { "epoch": 0.6576670128071997, "grad_norm": 3.519710063934326, "learning_rate": 6.856527093596059e-06, "loss": 1.3021, "step": 4275 }, { "epoch": 0.6578208530441136, "grad_norm": 3.3470118045806885, "learning_rate": 6.853448275862069e-06, "loss": 1.6006, "step": 4276 }, { "epoch": 0.6579746932810276, "grad_norm": 3.123444080352783, "learning_rate": 6.850369458128079e-06, "loss": 0.9811, "step": 4277 }, { "epoch": 0.6581285335179416, "grad_norm": 3.3874995708465576, "learning_rate": 6.84729064039409e-06, "loss": 1.2819, "step": 4278 }, { "epoch": 0.6582823737548555, "grad_norm": 3.3573648929595947, "learning_rate": 6.8442118226601e-06, "loss": 1.2944, "step": 4279 }, { "epoch": 0.6584362139917695, "grad_norm": 3.4409759044647217, "learning_rate": 6.84113300492611e-06, "loss": 1.1144, "step": 4280 }, { "epoch": 0.6585900542286836, "grad_norm": 4.587446212768555, "learning_rate": 6.8380541871921195e-06, "loss": 0.9609, "step": 4281 }, { "epoch": 0.6587438944655974, "grad_norm": 3.6660072803497314, "learning_rate": 6.834975369458129e-06, "loss": 1.4757, "step": 4282 }, { "epoch": 0.6588977347025115, "grad_norm": 4.303161144256592, "learning_rate": 6.831896551724138e-06, "loss": 1.4927, "step": 4283 }, { "epoch": 0.6590515749394255, "grad_norm": 4.370614051818848, "learning_rate": 6.828817733990148e-06, "loss": 1.4659, "step": 4284 }, { "epoch": 0.6592054151763393, "grad_norm": 3.3846991062164307, "learning_rate": 6.825738916256158e-06, "loss": 1.03, "step": 4285 }, { "epoch": 0.6593592554132534, "grad_norm": 3.804290533065796, "learning_rate": 6.822660098522168e-06, "loss": 1.1943, "step": 4286 }, { "epoch": 0.6595130956501672, "grad_norm": 3.7132487297058105, "learning_rate": 6.8195812807881775e-06, "loss": 1.4539, "step": 4287 }, { "epoch": 0.6596669358870813, "grad_norm": 3.4386653900146484, "learning_rate": 6.816502463054187e-06, "loss": 1.4132, "step": 4288 }, { "epoch": 0.6598207761239953, "grad_norm": 4.168827533721924, "learning_rate": 6.813423645320197e-06, "loss": 1.3957, "step": 4289 }, { "epoch": 0.6599746163609091, "grad_norm": 3.247124195098877, "learning_rate": 6.810344827586207e-06, "loss": 1.2972, "step": 4290 }, { "epoch": 0.6601284565978232, "grad_norm": 3.0761756896972656, "learning_rate": 6.807266009852217e-06, "loss": 1.5653, "step": 4291 }, { "epoch": 0.6602822968347372, "grad_norm": 3.2927753925323486, "learning_rate": 6.8041871921182265e-06, "loss": 1.395, "step": 4292 }, { "epoch": 0.660436137071651, "grad_norm": 4.101349830627441, "learning_rate": 6.801108374384236e-06, "loss": 1.3611, "step": 4293 }, { "epoch": 0.6605899773085651, "grad_norm": 3.7958850860595703, "learning_rate": 6.798029556650246e-06, "loss": 1.1394, "step": 4294 }, { "epoch": 0.6607438175454791, "grad_norm": 4.138857364654541, "learning_rate": 6.7949507389162575e-06, "loss": 1.357, "step": 4295 }, { "epoch": 0.660897657782393, "grad_norm": 4.297423362731934, "learning_rate": 6.791871921182267e-06, "loss": 1.3741, "step": 4296 }, { "epoch": 0.661051498019307, "grad_norm": 3.7771942615509033, "learning_rate": 6.788793103448277e-06, "loss": 1.1576, "step": 4297 }, { "epoch": 0.661205338256221, "grad_norm": 3.5918688774108887, "learning_rate": 6.785714285714287e-06, "loss": 1.6062, "step": 4298 }, { "epoch": 0.6613591784931349, "grad_norm": 4.0101542472839355, "learning_rate": 6.782635467980297e-06, "loss": 1.2035, "step": 4299 }, { "epoch": 0.6615130187300489, "grad_norm": 3.7205379009246826, "learning_rate": 6.7795566502463065e-06, "loss": 1.2805, "step": 4300 }, { "epoch": 0.6616668589669628, "grad_norm": 3.571761131286621, "learning_rate": 6.776477832512316e-06, "loss": 1.2456, "step": 4301 }, { "epoch": 0.6618206992038768, "grad_norm": 3.402435302734375, "learning_rate": 6.773399014778326e-06, "loss": 1.1719, "step": 4302 }, { "epoch": 0.6619745394407908, "grad_norm": 3.666700601577759, "learning_rate": 6.770320197044336e-06, "loss": 1.3047, "step": 4303 }, { "epoch": 0.6621283796777047, "grad_norm": 3.4510538578033447, "learning_rate": 6.767241379310346e-06, "loss": 1.4212, "step": 4304 }, { "epoch": 0.6622822199146187, "grad_norm": 3.9574954509735107, "learning_rate": 6.764162561576355e-06, "loss": 1.0779, "step": 4305 }, { "epoch": 0.6624360601515327, "grad_norm": 3.5396475791931152, "learning_rate": 6.7610837438423645e-06, "loss": 1.1529, "step": 4306 }, { "epoch": 0.6625899003884466, "grad_norm": 3.2988393306732178, "learning_rate": 6.758004926108374e-06, "loss": 1.1759, "step": 4307 }, { "epoch": 0.6627437406253606, "grad_norm": 3.3986992835998535, "learning_rate": 6.754926108374384e-06, "loss": 1.254, "step": 4308 }, { "epoch": 0.6628975808622746, "grad_norm": 3.1765196323394775, "learning_rate": 6.751847290640394e-06, "loss": 1.2417, "step": 4309 }, { "epoch": 0.6630514210991885, "grad_norm": 2.88883638381958, "learning_rate": 6.748768472906404e-06, "loss": 1.2018, "step": 4310 }, { "epoch": 0.6632052613361025, "grad_norm": 3.392367362976074, "learning_rate": 6.7456896551724135e-06, "loss": 1.0947, "step": 4311 }, { "epoch": 0.6633591015730165, "grad_norm": 3.9670913219451904, "learning_rate": 6.742610837438425e-06, "loss": 1.1359, "step": 4312 }, { "epoch": 0.6635129418099304, "grad_norm": 4.080730438232422, "learning_rate": 6.739532019704435e-06, "loss": 1.3676, "step": 4313 }, { "epoch": 0.6636667820468444, "grad_norm": 4.0075249671936035, "learning_rate": 6.7364532019704446e-06, "loss": 1.3592, "step": 4314 }, { "epoch": 0.6638206222837583, "grad_norm": 3.8757503032684326, "learning_rate": 6.733374384236454e-06, "loss": 1.1175, "step": 4315 }, { "epoch": 0.6639744625206723, "grad_norm": 3.519955635070801, "learning_rate": 6.730295566502464e-06, "loss": 1.4089, "step": 4316 }, { "epoch": 0.6641283027575863, "grad_norm": 3.653351306915283, "learning_rate": 6.727216748768474e-06, "loss": 1.4484, "step": 4317 }, { "epoch": 0.6642821429945002, "grad_norm": 3.2339253425598145, "learning_rate": 6.724137931034484e-06, "loss": 1.4945, "step": 4318 }, { "epoch": 0.6644359832314142, "grad_norm": 3.6404812335968018, "learning_rate": 6.7210591133004935e-06, "loss": 1.2436, "step": 4319 }, { "epoch": 0.6645898234683282, "grad_norm": 3.2728140354156494, "learning_rate": 6.717980295566503e-06, "loss": 1.2683, "step": 4320 }, { "epoch": 0.6647436637052421, "grad_norm": 4.337833881378174, "learning_rate": 6.714901477832513e-06, "loss": 1.2106, "step": 4321 }, { "epoch": 0.6648975039421561, "grad_norm": 4.013204097747803, "learning_rate": 6.711822660098523e-06, "loss": 1.4292, "step": 4322 }, { "epoch": 0.6650513441790701, "grad_norm": 3.531597375869751, "learning_rate": 6.708743842364533e-06, "loss": 1.3022, "step": 4323 }, { "epoch": 0.665205184415984, "grad_norm": 4.166599273681641, "learning_rate": 6.7056650246305425e-06, "loss": 1.7423, "step": 4324 }, { "epoch": 0.665359024652898, "grad_norm": 3.4837260246276855, "learning_rate": 6.702586206896552e-06, "loss": 1.4618, "step": 4325 }, { "epoch": 0.665512864889812, "grad_norm": 3.916710376739502, "learning_rate": 6.699507389162562e-06, "loss": 1.3189, "step": 4326 }, { "epoch": 0.6656667051267259, "grad_norm": 3.435546398162842, "learning_rate": 6.696428571428571e-06, "loss": 1.5632, "step": 4327 }, { "epoch": 0.6658205453636399, "grad_norm": 4.192488670349121, "learning_rate": 6.693349753694581e-06, "loss": 1.2523, "step": 4328 }, { "epoch": 0.6659743856005538, "grad_norm": 3.6067442893981934, "learning_rate": 6.690270935960592e-06, "loss": 1.2886, "step": 4329 }, { "epoch": 0.6661282258374678, "grad_norm": 3.37530779838562, "learning_rate": 6.687192118226602e-06, "loss": 1.2537, "step": 4330 }, { "epoch": 0.6662820660743818, "grad_norm": 4.074058532714844, "learning_rate": 6.684113300492612e-06, "loss": 1.1831, "step": 4331 }, { "epoch": 0.6664359063112957, "grad_norm": 3.3191885948181152, "learning_rate": 6.681034482758622e-06, "loss": 1.1906, "step": 4332 }, { "epoch": 0.6665897465482097, "grad_norm": 3.574855089187622, "learning_rate": 6.6779556650246316e-06, "loss": 1.1954, "step": 4333 }, { "epoch": 0.6667435867851237, "grad_norm": 4.0464701652526855, "learning_rate": 6.674876847290641e-06, "loss": 1.113, "step": 4334 }, { "epoch": 0.6668974270220376, "grad_norm": 3.6974050998687744, "learning_rate": 6.671798029556651e-06, "loss": 1.3949, "step": 4335 }, { "epoch": 0.6670512672589516, "grad_norm": 3.9117047786712646, "learning_rate": 6.668719211822661e-06, "loss": 1.0679, "step": 4336 }, { "epoch": 0.6672051074958656, "grad_norm": 4.082865238189697, "learning_rate": 6.665640394088671e-06, "loss": 1.0834, "step": 4337 }, { "epoch": 0.6673589477327795, "grad_norm": 3.2226264476776123, "learning_rate": 6.6625615763546806e-06, "loss": 1.3228, "step": 4338 }, { "epoch": 0.6675127879696935, "grad_norm": 3.3084969520568848, "learning_rate": 6.65948275862069e-06, "loss": 1.2875, "step": 4339 }, { "epoch": 0.6676666282066075, "grad_norm": 3.3035497665405273, "learning_rate": 6.6564039408867e-06, "loss": 1.2204, "step": 4340 }, { "epoch": 0.6678204684435214, "grad_norm": 3.9066545963287354, "learning_rate": 6.65332512315271e-06, "loss": 1.208, "step": 4341 }, { "epoch": 0.6679743086804354, "grad_norm": 3.836580753326416, "learning_rate": 6.65024630541872e-06, "loss": 1.3072, "step": 4342 }, { "epoch": 0.6681281489173493, "grad_norm": 3.1451330184936523, "learning_rate": 6.6471674876847295e-06, "loss": 1.2639, "step": 4343 }, { "epoch": 0.6682819891542633, "grad_norm": 3.948220729827881, "learning_rate": 6.644088669950739e-06, "loss": 1.2447, "step": 4344 }, { "epoch": 0.6684358293911773, "grad_norm": 3.5384438037872314, "learning_rate": 6.641009852216749e-06, "loss": 1.392, "step": 4345 }, { "epoch": 0.6685896696280912, "grad_norm": 3.8136589527130127, "learning_rate": 6.63793103448276e-06, "loss": 1.5754, "step": 4346 }, { "epoch": 0.6687435098650052, "grad_norm": 3.4612059593200684, "learning_rate": 6.63485221674877e-06, "loss": 1.3427, "step": 4347 }, { "epoch": 0.6688973501019192, "grad_norm": 3.427870988845825, "learning_rate": 6.631773399014779e-06, "loss": 1.4568, "step": 4348 }, { "epoch": 0.6690511903388331, "grad_norm": 3.7344889640808105, "learning_rate": 6.628694581280789e-06, "loss": 1.3482, "step": 4349 }, { "epoch": 0.6692050305757471, "grad_norm": 3.4334256649017334, "learning_rate": 6.625615763546799e-06, "loss": 1.3985, "step": 4350 }, { "epoch": 0.6693588708126611, "grad_norm": 4.0210371017456055, "learning_rate": 6.622536945812809e-06, "loss": 1.5068, "step": 4351 }, { "epoch": 0.669512711049575, "grad_norm": 3.763087511062622, "learning_rate": 6.619458128078819e-06, "loss": 1.2553, "step": 4352 }, { "epoch": 0.669666551286489, "grad_norm": 3.6862804889678955, "learning_rate": 6.616379310344828e-06, "loss": 1.2655, "step": 4353 }, { "epoch": 0.6698203915234029, "grad_norm": 3.646174430847168, "learning_rate": 6.613300492610838e-06, "loss": 1.5222, "step": 4354 }, { "epoch": 0.6699742317603169, "grad_norm": 3.193089485168457, "learning_rate": 6.610221674876848e-06, "loss": 1.0702, "step": 4355 }, { "epoch": 0.6701280719972309, "grad_norm": 3.313185453414917, "learning_rate": 6.607142857142858e-06, "loss": 1.2972, "step": 4356 }, { "epoch": 0.6702819122341448, "grad_norm": 3.7423219680786133, "learning_rate": 6.6040640394088676e-06, "loss": 1.2442, "step": 4357 }, { "epoch": 0.6704357524710588, "grad_norm": 3.864845037460327, "learning_rate": 6.600985221674877e-06, "loss": 1.1778, "step": 4358 }, { "epoch": 0.6705895927079728, "grad_norm": 3.24433970451355, "learning_rate": 6.597906403940887e-06, "loss": 1.1219, "step": 4359 }, { "epoch": 0.6707434329448867, "grad_norm": 3.633843421936035, "learning_rate": 6.594827586206897e-06, "loss": 1.7032, "step": 4360 }, { "epoch": 0.6708972731818007, "grad_norm": 3.318826675415039, "learning_rate": 6.591748768472907e-06, "loss": 1.2911, "step": 4361 }, { "epoch": 0.6710511134187147, "grad_norm": 3.45732045173645, "learning_rate": 6.5886699507389166e-06, "loss": 1.5034, "step": 4362 }, { "epoch": 0.6712049536556286, "grad_norm": 3.6858623027801514, "learning_rate": 6.585591133004927e-06, "loss": 1.3434, "step": 4363 }, { "epoch": 0.6713587938925426, "grad_norm": 2.9641730785369873, "learning_rate": 6.582512315270937e-06, "loss": 1.0894, "step": 4364 }, { "epoch": 0.6715126341294566, "grad_norm": 3.646285057067871, "learning_rate": 6.579433497536947e-06, "loss": 1.3786, "step": 4365 }, { "epoch": 0.6716664743663705, "grad_norm": 4.110287666320801, "learning_rate": 6.576354679802957e-06, "loss": 1.2226, "step": 4366 }, { "epoch": 0.6718203146032845, "grad_norm": 3.6776509284973145, "learning_rate": 6.573275862068966e-06, "loss": 1.3102, "step": 4367 }, { "epoch": 0.6719741548401984, "grad_norm": 2.8904824256896973, "learning_rate": 6.570197044334976e-06, "loss": 1.1747, "step": 4368 }, { "epoch": 0.6721279950771124, "grad_norm": 3.488538980484009, "learning_rate": 6.567118226600986e-06, "loss": 1.2966, "step": 4369 }, { "epoch": 0.6722818353140264, "grad_norm": 3.2305800914764404, "learning_rate": 6.564039408866996e-06, "loss": 1.4971, "step": 4370 }, { "epoch": 0.6724356755509403, "grad_norm": 2.8683736324310303, "learning_rate": 6.560960591133006e-06, "loss": 1.2928, "step": 4371 }, { "epoch": 0.6725895157878543, "grad_norm": 3.4114363193511963, "learning_rate": 6.557881773399015e-06, "loss": 1.2876, "step": 4372 }, { "epoch": 0.6727433560247683, "grad_norm": 2.8850855827331543, "learning_rate": 6.554802955665025e-06, "loss": 1.3795, "step": 4373 }, { "epoch": 0.6728971962616822, "grad_norm": 3.7631442546844482, "learning_rate": 6.551724137931035e-06, "loss": 1.2214, "step": 4374 }, { "epoch": 0.6730510364985962, "grad_norm": 3.2895655632019043, "learning_rate": 6.548645320197045e-06, "loss": 1.4734, "step": 4375 }, { "epoch": 0.6732048767355102, "grad_norm": 3.296320676803589, "learning_rate": 6.545566502463055e-06, "loss": 1.0921, "step": 4376 }, { "epoch": 0.6733587169724241, "grad_norm": 3.0840044021606445, "learning_rate": 6.542487684729064e-06, "loss": 1.277, "step": 4377 }, { "epoch": 0.6735125572093381, "grad_norm": 3.06144642829895, "learning_rate": 6.539408866995074e-06, "loss": 1.4016, "step": 4378 }, { "epoch": 0.6736663974462521, "grad_norm": 3.7764313220977783, "learning_rate": 6.536330049261085e-06, "loss": 1.3432, "step": 4379 }, { "epoch": 0.673820237683166, "grad_norm": 3.8158974647521973, "learning_rate": 6.533251231527095e-06, "loss": 1.1452, "step": 4380 }, { "epoch": 0.67397407792008, "grad_norm": 3.3002877235412598, "learning_rate": 6.5301724137931044e-06, "loss": 1.3376, "step": 4381 }, { "epoch": 0.6741279181569939, "grad_norm": 3.577460289001465, "learning_rate": 6.527093596059114e-06, "loss": 1.0147, "step": 4382 }, { "epoch": 0.6742817583939079, "grad_norm": 3.9274425506591797, "learning_rate": 6.524014778325124e-06, "loss": 1.3406, "step": 4383 }, { "epoch": 0.6744355986308219, "grad_norm": 4.157759189605713, "learning_rate": 6.520935960591134e-06, "loss": 1.3746, "step": 4384 }, { "epoch": 0.6745894388677358, "grad_norm": 3.5779130458831787, "learning_rate": 6.517857142857144e-06, "loss": 1.2198, "step": 4385 }, { "epoch": 0.6747432791046498, "grad_norm": 3.993509531021118, "learning_rate": 6.514778325123153e-06, "loss": 1.235, "step": 4386 }, { "epoch": 0.6748971193415638, "grad_norm": 3.666024923324585, "learning_rate": 6.511699507389163e-06, "loss": 1.3498, "step": 4387 }, { "epoch": 0.6750509595784777, "grad_norm": 3.9154820442199707, "learning_rate": 6.508620689655173e-06, "loss": 1.5758, "step": 4388 }, { "epoch": 0.6752047998153917, "grad_norm": 3.5167407989501953, "learning_rate": 6.505541871921183e-06, "loss": 1.5033, "step": 4389 }, { "epoch": 0.6753586400523057, "grad_norm": 3.0825510025024414, "learning_rate": 6.502463054187193e-06, "loss": 1.2402, "step": 4390 }, { "epoch": 0.6755124802892196, "grad_norm": 3.348881483078003, "learning_rate": 6.499384236453202e-06, "loss": 1.5866, "step": 4391 }, { "epoch": 0.6756663205261336, "grad_norm": 4.562715530395508, "learning_rate": 6.496305418719212e-06, "loss": 1.4911, "step": 4392 }, { "epoch": 0.6758201607630476, "grad_norm": 3.683121681213379, "learning_rate": 6.493226600985222e-06, "loss": 1.3444, "step": 4393 }, { "epoch": 0.6759740009999615, "grad_norm": 4.033665180206299, "learning_rate": 6.490147783251232e-06, "loss": 1.2762, "step": 4394 }, { "epoch": 0.6761278412368755, "grad_norm": 3.0879712104797363, "learning_rate": 6.487068965517242e-06, "loss": 1.2832, "step": 4395 }, { "epoch": 0.6762816814737894, "grad_norm": 3.56278133392334, "learning_rate": 6.483990147783252e-06, "loss": 1.3743, "step": 4396 }, { "epoch": 0.6764355217107034, "grad_norm": 3.478571891784668, "learning_rate": 6.480911330049262e-06, "loss": 1.2937, "step": 4397 }, { "epoch": 0.6765893619476174, "grad_norm": 3.397218704223633, "learning_rate": 6.477832512315272e-06, "loss": 1.1628, "step": 4398 }, { "epoch": 0.6767432021845313, "grad_norm": 3.136679172515869, "learning_rate": 6.474753694581282e-06, "loss": 1.3422, "step": 4399 }, { "epoch": 0.6768970424214453, "grad_norm": 3.7144603729248047, "learning_rate": 6.4716748768472914e-06, "loss": 1.3178, "step": 4400 }, { "epoch": 0.6770508826583593, "grad_norm": 4.123449802398682, "learning_rate": 6.468596059113301e-06, "loss": 1.6255, "step": 4401 }, { "epoch": 0.6772047228952732, "grad_norm": 4.0016069412231445, "learning_rate": 6.465517241379311e-06, "loss": 1.347, "step": 4402 }, { "epoch": 0.6773585631321872, "grad_norm": 3.8844027519226074, "learning_rate": 6.462438423645321e-06, "loss": 1.2146, "step": 4403 }, { "epoch": 0.6775124033691012, "grad_norm": 3.1951560974121094, "learning_rate": 6.459359605911331e-06, "loss": 1.1117, "step": 4404 }, { "epoch": 0.6776662436060151, "grad_norm": 3.4631569385528564, "learning_rate": 6.4562807881773404e-06, "loss": 1.2105, "step": 4405 }, { "epoch": 0.6778200838429291, "grad_norm": 3.2107489109039307, "learning_rate": 6.45320197044335e-06, "loss": 1.333, "step": 4406 }, { "epoch": 0.6779739240798431, "grad_norm": 3.3414065837860107, "learning_rate": 6.45012315270936e-06, "loss": 1.367, "step": 4407 }, { "epoch": 0.678127764316757, "grad_norm": 3.327730894088745, "learning_rate": 6.44704433497537e-06, "loss": 1.3815, "step": 4408 }, { "epoch": 0.678281604553671, "grad_norm": 3.276191234588623, "learning_rate": 6.44396551724138e-06, "loss": 1.2108, "step": 4409 }, { "epoch": 0.6784354447905849, "grad_norm": 4.226249694824219, "learning_rate": 6.440886699507389e-06, "loss": 1.2037, "step": 4410 } ], "logging_steps": 1, "max_steps": 6501, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 30, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.169475829510554e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }