Training in progress, step 4640, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a3c015579fbd60a19dba64088865fddaaa59411165b7d679f5062bfd73f96f
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e9fd21da3c5143e10d75870d3e398286d30ed7daeb92549e3df7a281f6ad641
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b96ff7ea935dea4b1f5b93627ad26af93736f97e9be345daba5ecfc358f3be1
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 35.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -8342,6 +8342,24 @@
|
|
| 8342 |
"mean_token_accuracy": 0.6451707929372787,
|
| 8343 |
"num_tokens": 16885165.0,
|
| 8344 |
"step": 4630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8345 |
}
|
| 8346 |
],
|
| 8347 |
"logging_steps": 5,
|
|
@@ -8361,7 +8379,7 @@
|
|
| 8361 |
"attributes": {}
|
| 8362 |
}
|
| 8363 |
},
|
| 8364 |
-
"total_flos": 8.
|
| 8365 |
"train_batch_size": 4,
|
| 8366 |
"trial_name": null,
|
| 8367 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8342 |
"mean_token_accuracy": 0.6451707929372787,
|
| 8343 |
"num_tokens": 16885165.0,
|
| 8344 |
"step": 4630
|
| 8345 |
+
},
|
| 8346 |
+
{
|
| 8347 |
+
"epoch": 35.65384615384615,
|
| 8348 |
+
"grad_norm": 0.0,
|
| 8349 |
+
"learning_rate": 2.683e-05,
|
| 8350 |
+
"loss": 1.6848,
|
| 8351 |
+
"mean_token_accuracy": 0.660153791308403,
|
| 8352 |
+
"num_tokens": 16904043.0,
|
| 8353 |
+
"step": 4635
|
| 8354 |
+
},
|
| 8355 |
+
{
|
| 8356 |
+
"epoch": 35.69230769230769,
|
| 8357 |
+
"grad_norm": 0.0,
|
| 8358 |
+
"learning_rate": 2.6805000000000002e-05,
|
| 8359 |
+
"loss": 1.7564,
|
| 8360 |
+
"mean_token_accuracy": 0.6473292171955108,
|
| 8361 |
+
"num_tokens": 16921974.0,
|
| 8362 |
+
"step": 4640
|
| 8363 |
}
|
| 8364 |
],
|
| 8365 |
"logging_steps": 5,
|
|
|
|
| 8379 |
"attributes": {}
|
| 8380 |
}
|
| 8381 |
},
|
| 8382 |
+
"total_flos": 8.576180896230605e+17,
|
| 8383 |
"train_batch_size": 4,
|
| 8384 |
"trial_name": null,
|
| 8385 |
"trial_params": null
|