Training in progress, step 320, 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 sha256:584ae6ba2e733b76e71f4ff33d0b8acc47f60148f7a1c060ea0c3fe48afa74c9
|
| 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 sha256:22cc2594c96bfc814b54ba47191dc3fb1b61cae4f024b39f6412b53ccc74ebe4
|
| 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 sha256:74d776b627d54f627251a06f9683e6a15c49b0d09b53f453b068854b61c21555
|
| 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": 2.
|
| 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,
|
|
@@ -566,6 +566,24 @@
|
|
| 566 |
"mean_token_accuracy": 0.6483295440673829,
|
| 567 |
"num_tokens": 1132366.0,
|
| 568 |
"step": 310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 569 |
}
|
| 570 |
],
|
| 571 |
"logging_steps": 5,
|
|
@@ -585,7 +603,7 @@
|
|
| 585 |
"attributes": {}
|
| 586 |
}
|
| 587 |
},
|
| 588 |
-
"total_flos": 5.
|
| 589 |
"train_batch_size": 4,
|
| 590 |
"trial_name": null,
|
| 591 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.4615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 566 |
"mean_token_accuracy": 0.6483295440673829,
|
| 567 |
"num_tokens": 1132366.0,
|
| 568 |
"step": 310
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.423076923076923,
|
| 572 |
+
"grad_norm": 0.0,
|
| 573 |
+
"learning_rate": 4.843e-05,
|
| 574 |
+
"loss": 1.6774,
|
| 575 |
+
"mean_token_accuracy": 0.660743135213852,
|
| 576 |
+
"num_tokens": 1151832.0,
|
| 577 |
+
"step": 315
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.4615384615384617,
|
| 581 |
+
"grad_norm": 0.0,
|
| 582 |
+
"learning_rate": 4.8405e-05,
|
| 583 |
+
"loss": 1.8422,
|
| 584 |
+
"mean_token_accuracy": 0.6320727407932282,
|
| 585 |
+
"num_tokens": 1168795.0,
|
| 586 |
+
"step": 320
|
| 587 |
}
|
| 588 |
],
|
| 589 |
"logging_steps": 5,
|
|
|
|
| 603 |
"attributes": {}
|
| 604 |
}
|
| 605 |
},
|
| 606 |
+
"total_flos": 5.923240172568576e+16,
|
| 607 |
"train_batch_size": 4,
|
| 608 |
"trial_name": null,
|
| 609 |
"trial_params": null
|