Model save
Browse files
README.md
CHANGED
|
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.05
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.05
|
| 46 |
+
- num_epochs: 6
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
last_checkpoint/adapter_config.json
CHANGED
|
@@ -26,12 +26,12 @@
|
|
| 26 |
"target_modules": [
|
| 27 |
"up_proj",
|
| 28 |
"q_proj",
|
|
|
|
| 29 |
"o_proj",
|
| 30 |
-
"k_proj",
|
| 31 |
"gate_proj",
|
|
|
|
| 32 |
"v_proj",
|
| 33 |
-
"
|
| 34 |
-
"lm_head"
|
| 35 |
],
|
| 36 |
"task_type": "CAUSAL_LM",
|
| 37 |
"trainable_token_indices": null,
|
|
|
|
| 26 |
"target_modules": [
|
| 27 |
"up_proj",
|
| 28 |
"q_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
"o_proj",
|
|
|
|
| 31 |
"gate_proj",
|
| 32 |
+
"lm_head",
|
| 33 |
"v_proj",
|
| 34 |
+
"k_proj"
|
|
|
|
| 35 |
],
|
| 36 |
"task_type": "CAUSAL_LM",
|
| 37 |
"trainable_token_indices": null,
|
last_checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 411536704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6df498d1041489cc613969a68cf93b1cfbe3e3530fbc6cb2842fbbbf726c40af
|
| 3 |
size 411536704
|
last_checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5649
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f94a5d8c1fd55ce00b568a4d234761ea9edc7e3a01220894231c981544d2250a
|
| 3 |
size 5649
|