Training in progress, step 330, 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:c825eb70da5e7dfdda9e486d0767307360f062c9805f76b2b068aaed1f2e7b5c
|
| 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 sha256:3bcac4814ed1b12bad6b869ba149e1d4c89e85ee15e81e9b75929601400545dd
|
| 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:fcde8db9aa34ec6fa4aa633349236f50dbe05ff0f6a95544868c4cd5c7aa067d
|
| 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,
|
|
@@ -584,6 +584,24 @@
|
|
| 584 |
"mean_token_accuracy": 0.6320727407932282,
|
| 585 |
"num_tokens": 1168795.0,
|
| 586 |
"step": 320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 587 |
}
|
| 588 |
],
|
| 589 |
"logging_steps": 5,
|
|
@@ -603,7 +621,7 @@
|
|
| 603 |
"attributes": {}
|
| 604 |
}
|
| 605 |
},
|
| 606 |
-
"total_flos":
|
| 607 |
"train_batch_size": 4,
|
| 608 |
"trial_name": null,
|
| 609 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.5384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 584 |
"mean_token_accuracy": 0.6320727407932282,
|
| 585 |
"num_tokens": 1168795.0,
|
| 586 |
"step": 320
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.5,
|
| 590 |
+
"grad_norm": 0.0,
|
| 591 |
+
"learning_rate": 4.838e-05,
|
| 592 |
+
"loss": 1.7624,
|
| 593 |
+
"mean_token_accuracy": 0.6471054494380951,
|
| 594 |
+
"num_tokens": 1186567.0,
|
| 595 |
+
"step": 325
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.5384615384615383,
|
| 599 |
+
"grad_norm": 0.0,
|
| 600 |
+
"learning_rate": 4.8355e-05,
|
| 601 |
+
"loss": 1.7518,
|
| 602 |
+
"mean_token_accuracy": 0.6520386338233948,
|
| 603 |
+
"num_tokens": 1204773.0,
|
| 604 |
+
"step": 330
|
| 605 |
}
|
| 606 |
],
|
| 607 |
"logging_steps": 5,
|
|
|
|
| 621 |
"attributes": {}
|
| 622 |
}
|
| 623 |
},
|
| 624 |
+
"total_flos": 6.103581526867968e+16,
|
| 625 |
"train_batch_size": 4,
|
| 626 |
"trial_name": null,
|
| 627 |
"trial_params": null
|