Training in progress, step 230, 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 sha256:92476018ba9322e1b82fdccfa00ebd12736f1011d34187509da2195e0e6c1e97
|
| 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 sha256:7341a2414551b301d96b623306a56a8b3aeda50c96fda8d99b810720ea43b077
|
| 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:e4b84263afaebf89f6c2b3697095e1fc03751e5fb25520d97ac63f45a3d29f0d
|
| 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": 1.
|
| 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,
|
|
@@ -404,6 +404,24 @@
|
|
| 404 |
"mean_token_accuracy": 0.6559958964586258,
|
| 405 |
"num_tokens": 802295.0,
|
| 406 |
"step": 220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 407 |
}
|
| 408 |
],
|
| 409 |
"logging_steps": 5,
|
|
@@ -423,7 +441,7 @@
|
|
| 423 |
"attributes": {}
|
| 424 |
}
|
| 425 |
},
|
| 426 |
-
"total_flos": 4.
|
| 427 |
"train_batch_size": 4,
|
| 428 |
"trial_name": null,
|
| 429 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.7692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 404 |
"mean_token_accuracy": 0.6559958964586258,
|
| 405 |
"num_tokens": 802295.0,
|
| 406 |
"step": 220
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.7307692307692308,
|
| 410 |
+
"grad_norm": 0.0,
|
| 411 |
+
"learning_rate": 4.8880000000000006e-05,
|
| 412 |
+
"loss": 1.7534,
|
| 413 |
+
"mean_token_accuracy": 0.647523045539856,
|
| 414 |
+
"num_tokens": 820482.0,
|
| 415 |
+
"step": 225
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.7692307692307692,
|
| 419 |
+
"grad_norm": 0.0,
|
| 420 |
+
"learning_rate": 4.8855e-05,
|
| 421 |
+
"loss": 1.7675,
|
| 422 |
+
"mean_token_accuracy": 0.6462311297655106,
|
| 423 |
+
"num_tokens": 838437.0,
|
| 424 |
+
"step": 230
|
| 425 |
}
|
| 426 |
],
|
| 427 |
"logging_steps": 5,
|
|
|
|
| 441 |
"attributes": {}
|
| 442 |
}
|
| 443 |
},
|
| 444 |
+
"total_flos": 4.250549500674048e+16,
|
| 445 |
"train_batch_size": 4,
|
| 446 |
"trial_name": null,
|
| 447 |
"trial_params": null
|