Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +51 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3235581408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf3cc04d6393572bcf2da90e592b8d2fb0d9ed3dde7561ce2142f6768bc02de5
|
| 3 |
size 3235581408
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0097aaa703d20e12edd301251f2c9e93e0c1e04d3eb2e77189cc66859ad650ea
|
| 3 |
+
size 209862090
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:772146ff2848317f2d87dbf95d7441d5432004865820ea365df60be0de2a0748
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58ac5f60dd1dc69ced2700f9b75a7c66f6ab2e306ef0e6ee9da84acb56552df2
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 48,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 2.5385825634002686,
|
| 14 |
+
"learning_rate": 0.00017142857142857143,
|
| 15 |
+
"loss": 1.637,
|
| 16 |
+
"step": 24
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_loss": 0.1714123785495758,
|
| 21 |
+
"eval_runtime": 394.108,
|
| 22 |
+
"eval_samples_per_second": 1.462,
|
| 23 |
+
"eval_steps_per_second": 1.462,
|
| 24 |
+
"step": 24
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"grad_norm": 0.946814775466919,
|
| 29 |
+
"learning_rate": 0.00014285714285714287,
|
| 30 |
+
"loss": 0.1624,
|
| 31 |
+
"step": 48
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_loss": 0.14965203404426575,
|
| 36 |
+
"eval_runtime": 392.7243,
|
| 37 |
+
"eval_samples_per_second": 1.467,
|
| 38 |
+
"eval_steps_per_second": 1.467,
|
| 39 |
+
"step": 48
|
| 40 |
+
}
|
| 41 |
+
],
|
| 42 |
+
"logging_steps": 500,
|
| 43 |
+
"max_steps": 168,
|
| 44 |
+
"num_input_tokens_seen": 0,
|
| 45 |
+
"num_train_epochs": 7,
|
| 46 |
+
"save_steps": 500,
|
| 47 |
+
"total_flos": 1.96410372784128e+18,
|
| 48 |
+
"train_batch_size": 6,
|
| 49 |
+
"trial_name": null,
|
| 50 |
+
"trial_params": null
|
| 51 |
+
}
|