Training in progress, step 400, 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 sha256:166654b5e4fdbd49516ba4efd4f0229bed5fc0d69ddfd4536300fd36f19b0f5a
|
| 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:f8ac6dc170dba88f4e2642c086eea553fcc3f5dfc355d9e6ba6e86c637ed9152
|
| 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:c073fd043fa59e8d48e195347d64bc8f10282a030af053887eb35beebd49bafc
|
| 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": 3.
|
| 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,
|
|
@@ -710,6 +710,24 @@
|
|
| 710 |
"mean_token_accuracy": 0.636838635802269,
|
| 711 |
"num_tokens": 1422315.0,
|
| 712 |
"step": 390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 713 |
}
|
| 714 |
],
|
| 715 |
"logging_steps": 5,
|
|
@@ -729,7 +747,7 @@
|
|
| 729 |
"attributes": {}
|
| 730 |
}
|
| 731 |
},
|
| 732 |
-
"total_flos": 7.
|
| 733 |
"train_batch_size": 4,
|
| 734 |
"trial_name": null,
|
| 735 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 710 |
"mean_token_accuracy": 0.636838635802269,
|
| 711 |
"num_tokens": 1422315.0,
|
| 712 |
"step": 390
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 3.0384615384615383,
|
| 716 |
+
"grad_norm": 0.0,
|
| 717 |
+
"learning_rate": 4.8030000000000006e-05,
|
| 718 |
+
"loss": 1.7325,
|
| 719 |
+
"mean_token_accuracy": 0.6527264744043351,
|
| 720 |
+
"num_tokens": 1440658.0,
|
| 721 |
+
"step": 395
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.076923076923077,
|
| 725 |
+
"grad_norm": 0.0,
|
| 726 |
+
"learning_rate": 4.8005e-05,
|
| 727 |
+
"loss": 1.7647,
|
| 728 |
+
"mean_token_accuracy": 0.6484371930360794,
|
| 729 |
+
"num_tokens": 1458704.0,
|
| 730 |
+
"step": 400
|
| 731 |
}
|
| 732 |
],
|
| 733 |
"logging_steps": 5,
|
|
|
|
| 747 |
"attributes": {}
|
| 748 |
}
|
| 749 |
},
|
| 750 |
+
"total_flos": 7.381975944904704e+16,
|
| 751 |
"train_batch_size": 4,
|
| 752 |
"trial_name": null,
|
| 753 |
"trial_params": null
|