Training in progress, step 360, 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:a957c8c3230a9617117a1096e37af0266e5eb9bfe6ed61b00e2e296dca158d72
|
| 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:a4e726ec57c73da4e8719747f2f6d48735d88a3295dd20dcbad4257f367f7621
|
| 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 sha256:95244204ac094f1fb6f546d84e70bee11e7e4090c3aec17b88496045d62c0bab
|
| 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,
|
|
@@ -638,6 +638,24 @@
|
|
| 638 |
"mean_token_accuracy": 0.6524255007505417,
|
| 639 |
"num_tokens": 1277367.0,
|
| 640 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 641 |
}
|
| 642 |
],
|
| 643 |
"logging_steps": 5,
|
|
@@ -657,7 +675,7 @@
|
|
| 657 |
"attributes": {}
|
| 658 |
}
|
| 659 |
},
|
| 660 |
-
"total_flos": 6.
|
| 661 |
"train_batch_size": 4,
|
| 662 |
"trial_name": null,
|
| 663 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 638 |
"mean_token_accuracy": 0.6524255007505417,
|
| 639 |
"num_tokens": 1277367.0,
|
| 640 |
"step": 350
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.730769230769231,
|
| 644 |
+
"grad_norm": 0.0,
|
| 645 |
+
"learning_rate": 4.8230000000000004e-05,
|
| 646 |
+
"loss": 1.6652,
|
| 647 |
+
"mean_token_accuracy": 0.6617098182439805,
|
| 648 |
+
"num_tokens": 1296866.0,
|
| 649 |
+
"step": 355
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.769230769230769,
|
| 653 |
+
"grad_norm": 0.0,
|
| 654 |
+
"learning_rate": 4.8205000000000003e-05,
|
| 655 |
+
"loss": 1.6834,
|
| 656 |
+
"mean_token_accuracy": 0.662646809220314,
|
| 657 |
+
"num_tokens": 1315690.0,
|
| 658 |
+
"step": 360
|
| 659 |
}
|
| 660 |
],
|
| 661 |
"logging_steps": 5,
|
|
|
|
| 675 |
"attributes": {}
|
| 676 |
}
|
| 677 |
},
|
| 678 |
+
"total_flos": 6.659880143634432e+16,
|
| 679 |
"train_batch_size": 4,
|
| 680 |
"trial_name": null,
|
| 681 |
"trial_params": null
|