Training in progress, step 5850, 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 sha256:75221e402268744cd9a6b7d50d30e215faf91cbe055a74679e6864e3cd40cba0
|
| 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 sha256:498ba289175b74396347e604b2d186fa94673b684fcd61cc9a3aa7e0710a7a05
|
| 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 sha256:99c7ba9b73448abf3da4236f76197924ff72b687f0f1d899a4f0c8738f210b1d
|
| 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,
|
|
@@ -10520,6 +10520,24 @@
|
|
| 10520 |
"mean_token_accuracy": 0.6573170632123947,
|
| 10521 |
"num_tokens": 21298845.0,
|
| 10522 |
"step": 5840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10523 |
}
|
| 10524 |
],
|
| 10525 |
"logging_steps": 5,
|
|
@@ -10539,7 +10557,7 @@
|
|
| 10539 |
"attributes": {}
|
| 10540 |
}
|
| 10541 |
},
|
| 10542 |
-
"total_flos": 1.
|
| 10543 |
"train_batch_size": 4,
|
| 10544 |
"trial_name": null,
|
| 10545 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10520 |
"mean_token_accuracy": 0.6573170632123947,
|
| 10521 |
"num_tokens": 21298845.0,
|
| 10522 |
"step": 5840
|
| 10523 |
+
},
|
| 10524 |
+
{
|
| 10525 |
+
"epoch": 44.96153846153846,
|
| 10526 |
+
"grad_norm": 0.0,
|
| 10527 |
+
"learning_rate": 2.078e-05,
|
| 10528 |
+
"loss": 1.6992,
|
| 10529 |
+
"mean_token_accuracy": 0.6632038950920105,
|
| 10530 |
+
"num_tokens": 21317164.0,
|
| 10531 |
+
"step": 5845
|
| 10532 |
+
},
|
| 10533 |
+
{
|
| 10534 |
+
"epoch": 45.0,
|
| 10535 |
+
"grad_norm": 0.0,
|
| 10536 |
+
"learning_rate": 2.0755000000000004e-05,
|
| 10537 |
+
"loss": 1.7663,
|
| 10538 |
+
"mean_token_accuracy": 0.6449836879968643,
|
| 10539 |
+
"num_tokens": 21334725.0,
|
| 10540 |
+
"step": 5850
|
| 10541 |
}
|
| 10542 |
],
|
| 10543 |
"logging_steps": 5,
|
|
|
|
| 10557 |
"attributes": {}
|
| 10558 |
}
|
| 10559 |
},
|
| 10560 |
+
"total_flos": 1.0810919577776947e+18,
|
| 10561 |
"train_batch_size": 4,
|
| 10562 |
"trial_name": null,
|
| 10563 |
"trial_params": null
|