Training in progress, step 2030, 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 sha256:809b55cc34b6357350791ead8226e9c585de48d9e48bc30a7a24f2bc1e4ea9f3
|
| 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:e29e388fb3c1c2f8b8469572c18d2d4c53325db0381a222cae27f0a8e330153f
|
| 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:df7eba1e349c8ee6f9bba78412a13a383ff489e816ec7d43ccfb1fcbf8d0b362
|
| 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": 15.
|
| 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,
|
|
@@ -3644,6 +3644,24 @@
|
|
| 3644 |
"mean_token_accuracy": 0.6394775450229645,
|
| 3645 |
"num_tokens": 7364128.0,
|
| 3646 |
"step": 2020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3647 |
}
|
| 3648 |
],
|
| 3649 |
"logging_steps": 5,
|
|
@@ -3663,7 +3681,7 @@
|
|
| 3663 |
"attributes": {}
|
| 3664 |
}
|
| 3665 |
},
|
| 3666 |
-
"total_flos": 3.
|
| 3667 |
"train_batch_size": 4,
|
| 3668 |
"trial_name": null,
|
| 3669 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3644 |
"mean_token_accuracy": 0.6394775450229645,
|
| 3645 |
"num_tokens": 7364128.0,
|
| 3646 |
"step": 2020
|
| 3647 |
+
},
|
| 3648 |
+
{
|
| 3649 |
+
"epoch": 15.576923076923077,
|
| 3650 |
+
"grad_norm": 0.0,
|
| 3651 |
+
"learning_rate": 3.988e-05,
|
| 3652 |
+
"loss": 1.7062,
|
| 3653 |
+
"mean_token_accuracy": 0.6575020164251327,
|
| 3654 |
+
"num_tokens": 7382926.0,
|
| 3655 |
+
"step": 2025
|
| 3656 |
+
},
|
| 3657 |
+
{
|
| 3658 |
+
"epoch": 15.615384615384615,
|
| 3659 |
+
"grad_norm": 0.0,
|
| 3660 |
+
"learning_rate": 3.9855000000000004e-05,
|
| 3661 |
+
"loss": 1.6781,
|
| 3662 |
+
"mean_token_accuracy": 0.6595021516084671,
|
| 3663 |
+
"num_tokens": 7402054.0,
|
| 3664 |
+
"step": 2030
|
| 3665 |
}
|
| 3666 |
],
|
| 3667 |
"logging_steps": 5,
|
|
|
|
| 3681 |
"attributes": {}
|
| 3682 |
}
|
| 3683 |
},
|
| 3684 |
+
"total_flos": 3.749756897850163e+17,
|
| 3685 |
"train_batch_size": 4,
|
| 3686 |
"trial_name": null,
|
| 3687 |
"trial_params": null
|