Hugging Face's logo

Sefika
/
model_fewrel_1_5

Transformers
Safetensors
t5
text2text-generation
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
Community
model_fewrel_1_5
File size: 4,689 Bytes
e81706f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
 
{
  "best_metric": 0.0484619140625,
  "best_model_checkpoint": "model_fewrel_1_6-task7/checkpoint-1470",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.1253662109375,
      "eval_rouge1": 93.102,
      "eval_rouge2": 89.1364,
      "eval_rougeL": 92.1128,
      "eval_rougeLsum": 93.0898,
      "eval_runtime": 30.5369,
      "eval_samples_per_second": 36.677,
      "eval_steps_per_second": 1.146,
      "step": 210
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.07708740234375,
      "eval_rouge1": 94.6253,
      "eval_rouge2": 91.7196,
      "eval_rougeL": 93.9284,
      "eval_rougeLsum": 94.6153,
      "eval_runtime": 29.0183,
      "eval_samples_per_second": 38.596,
      "eval_steps_per_second": 1.206,
      "step": 420
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.4770593047142029,
      "learning_rate": 0.0008665259359149131,
      "loss": 0.1042,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.05633544921875,
      "eval_rouge1": 95.1246,
      "eval_rouge2": 92.2081,
      "eval_rougeL": 94.3701,
      "eval_rougeLsum": 95.1249,
      "eval_runtime": 28.82,
      "eval_samples_per_second": 38.862,
      "eval_steps_per_second": 1.214,
      "step": 630
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.052490234375,
      "eval_rouge1": 95.9748,
      "eval_rouge2": 93.6071,
      "eval_rougeL": 95.3787,
      "eval_rougeLsum": 95.9622,
      "eval_runtime": 28.7568,
      "eval_samples_per_second": 38.947,
      "eval_steps_per_second": 1.217,
      "step": 840
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 0.2157868593931198,
      "learning_rate": 0.0005373650467932121,
      "loss": 0.0397,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.052734375,
      "eval_rouge1": 96.4573,
      "eval_rouge2": 94.4045,
      "eval_rougeL": 95.96,
      "eval_rougeLsum": 96.4689,
      "eval_runtime": 28.2262,
      "eval_samples_per_second": 39.679,
      "eval_steps_per_second": 1.24,
      "step": 1050
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.053009033203125,
      "eval_rouge1": 96.692,
      "eval_rouge2": 94.7143,
      "eval_rougeL": 96.2205,
      "eval_rougeLsum": 96.6725,
      "eval_runtime": 28.1396,
      "eval_samples_per_second": 39.802,
      "eval_steps_per_second": 1.244,
      "step": 1260
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.0484619140625,
      "eval_rouge1": 96.2898,
      "eval_rouge2": 94.1342,
      "eval_rougeL": 95.7357,
      "eval_rougeLsum": 96.2989,
      "eval_runtime": 28.7901,
      "eval_samples_per_second": 38.902,
      "eval_steps_per_second": 1.216,
      "step": 1470
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 0.13793426752090454,
      "learning_rate": 0.00018825509907063325,
      "loss": 0.0253,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.050872802734375,
      "eval_rouge1": 96.419,
      "eval_rouge2": 94.2908,
      "eval_rougeL": 95.887,
      "eval_rougeLsum": 96.431,
      "eval_runtime": 28.8197,
      "eval_samples_per_second": 38.862,
      "eval_steps_per_second": 1.214,
      "step": 1680
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.050994873046875,
      "eval_rouge1": 96.5301,
      "eval_rouge2": 94.465,
      "eval_rougeL": 96.014,
      "eval_rougeLsum": 96.5445,
      "eval_runtime": 28.8499,
      "eval_samples_per_second": 38.822,
      "eval_steps_per_second": 1.213,
      "step": 1890
    },
    {
      "epoch": 9.523809523809524,
      "grad_norm": 0.44433069229125977,
      "learning_rate": 5.5845868874357386e-06,
      "loss": 0.0172,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.05072021484375,
      "eval_rouge1": 96.5339,
      "eval_rouge2": 94.4734,
      "eval_rougeL": 96.0133,
      "eval_rougeLsum": 96.5439,
      "eval_runtime": 28.8295,
      "eval_samples_per_second": 38.849,
      "eval_steps_per_second": 1.214,
      "step": 2100
    }
  ],
  "logging_steps": 500,
  "max_steps": 2100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3099168784384e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}