Training in progress, epoch 1
Browse files
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: gemma-text-to-js
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- trl
|
| 8 |
- sft
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 4 |
model_name: gemma-text-to-js
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- sft
|
| 8 |
+
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
adapter_config.json
CHANGED
|
@@ -28,35 +28,35 @@
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"o_proj",
|
| 35 |
-
"altup_unembed_projections.1",
|
| 36 |
-
"altup_projections.0",
|
| 37 |
"altup_unembed_projections.0",
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"altup_projections.2",
|
| 41 |
"input_proj_linear",
|
|
|
|
| 42 |
"altup_unembed_projections.2",
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"up_proj",
|
| 47 |
"per_layer_projection",
|
| 48 |
-
"
|
| 49 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
"linear_end",
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"modality_router",
|
| 54 |
"correction_coefs",
|
| 55 |
-
"
|
| 56 |
-
"post",
|
| 57 |
"down_proj",
|
| 58 |
-
"
|
| 59 |
-
"
|
|
|
|
|
|
|
| 60 |
],
|
| 61 |
"target_parameters": null,
|
| 62 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
+
"post",
|
| 32 |
+
"ffw_layer_2",
|
| 33 |
+
"per_layer_model_projection",
|
|
|
|
|
|
|
|
|
|
| 34 |
"altup_unembed_projections.0",
|
| 35 |
+
"altup_unembed_projections.1",
|
| 36 |
+
"embedding_projection",
|
|
|
|
| 37 |
"input_proj_linear",
|
| 38 |
+
"pos_proj",
|
| 39 |
"altup_unembed_projections.2",
|
| 40 |
+
"q_proj",
|
| 41 |
+
"gate_proj",
|
| 42 |
+
"modality_router",
|
|
|
|
| 43 |
"per_layer_projection",
|
| 44 |
+
"linear_right",
|
| 45 |
+
"v_proj",
|
| 46 |
+
"altup_projections.1",
|
| 47 |
+
"altup_projections.0",
|
| 48 |
+
"o_proj",
|
| 49 |
+
"altup_projections.2",
|
| 50 |
"linear_end",
|
| 51 |
+
"prediction_coefs",
|
| 52 |
+
"linear_start",
|
|
|
|
| 53 |
"correction_coefs",
|
| 54 |
+
"linear_left",
|
|
|
|
| 55 |
"down_proj",
|
| 56 |
+
"k_proj",
|
| 57 |
+
"ffw_layer_1",
|
| 58 |
+
"per_layer_input_gate",
|
| 59 |
+
"up_proj"
|
| 60 |
],
|
| 61 |
"target_parameters": null,
|
| 62 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2299383480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dea90a659719d70a7a5299aa23b254a0fa745b90390782703d5e3153f797bf9
|
| 3 |
size 2299383480
|
runs/Oct23_20-00-12_PiastriRacer/events.out.tfevents.1761264033.PiastriRacer.4493.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99c0948f67aea2ab6af76ef730a3c9581917b673f5e93fcb95191685b98b109c
|
| 3 |
+
size 28676
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6289
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5ea56deec3de6a2816a5738d9802be6ee83813c3778214c2c95bdc912a3b9f5
|
| 3 |
size 6289
|