Training in progress, step 260, 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:f4f4152914fadf3a87b1a0642a7846c537f701bc59dd786f0fc39d270282f90e
|
| 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:c1ba177f9353fee1f011256f81b50041ae9d0bd3244041598e97914273b7921a
|
| 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 sha256:17105b25296373d87cd8d38a9c394a3d37fe331cab19153140498e56bd3a69b2
|
| 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":
|
| 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,
|
|
@@ -458,6 +458,24 @@
|
|
| 458 |
"mean_token_accuracy": 0.6448923200368881,
|
| 459 |
"num_tokens": 911604.0,
|
| 460 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 461 |
}
|
| 462 |
],
|
| 463 |
"logging_steps": 5,
|
|
@@ -477,7 +495,7 @@
|
|
| 477 |
"attributes": {}
|
| 478 |
}
|
| 479 |
},
|
| 480 |
-
"total_flos": 4.
|
| 481 |
"train_batch_size": 4,
|
| 482 |
"trial_name": null,
|
| 483 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 458 |
"mean_token_accuracy": 0.6448923200368881,
|
| 459 |
"num_tokens": 911604.0,
|
| 460 |
"step": 250
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.9615384615384617,
|
| 464 |
+
"grad_norm": 0.0,
|
| 465 |
+
"learning_rate": 4.873e-05,
|
| 466 |
+
"loss": 1.7326,
|
| 467 |
+
"mean_token_accuracy": 0.6498657464981079,
|
| 468 |
+
"num_tokens": 929944.0,
|
| 469 |
+
"step": 255
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.0,
|
| 473 |
+
"grad_norm": 0.0,
|
| 474 |
+
"learning_rate": 4.8705e-05,
|
| 475 |
+
"loss": 1.6613,
|
| 476 |
+
"mean_token_accuracy": 0.6733784437179565,
|
| 477 |
+
"num_tokens": 948210.0,
|
| 478 |
+
"step": 260
|
| 479 |
}
|
| 480 |
],
|
| 481 |
"logging_steps": 5,
|
|
|
|
| 495 |
"attributes": {}
|
| 496 |
}
|
| 497 |
},
|
| 498 |
+
"total_flos": 4.810023700365312e+16,
|
| 499 |
"train_batch_size": 4,
|
| 500 |
"trial_name": null,
|
| 501 |
"trial_params": null
|