Training in progress, step 420, 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 sha256:7272eb6ba37af45679077a2128f477be3072c75d2d534dee49740c7e5a898326
|
| 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 sha256:7d4e6eac87c4245ca5905959c91f887b5ae7a251c036b33bb44d7156bbb88c9d
|
| 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 sha256:6eac7169f6918774cba961c4176c0084c35ee2a3c7da7fb51201a036160bf424
|
| 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,
|
|
@@ -746,6 +746,24 @@
|
|
| 746 |
"mean_token_accuracy": 0.6573891878128052,
|
| 747 |
"num_tokens": 1494800.0,
|
| 748 |
"step": 410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 749 |
}
|
| 750 |
],
|
| 751 |
"logging_steps": 5,
|
|
@@ -765,7 +783,7 @@
|
|
| 765 |
"attributes": {}
|
| 766 |
}
|
| 767 |
},
|
| 768 |
-
"total_flos": 7.
|
| 769 |
"train_batch_size": 4,
|
| 770 |
"trial_name": null,
|
| 771 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.230769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 746 |
"mean_token_accuracy": 0.6573891878128052,
|
| 747 |
"num_tokens": 1494800.0,
|
| 748 |
"step": 410
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 3.1923076923076925,
|
| 752 |
+
"grad_norm": 0.0,
|
| 753 |
+
"learning_rate": 4.7930000000000004e-05,
|
| 754 |
+
"loss": 1.8141,
|
| 755 |
+
"mean_token_accuracy": 0.6418175488710404,
|
| 756 |
+
"num_tokens": 1512686.0,
|
| 757 |
+
"step": 415
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.230769230769231,
|
| 761 |
+
"grad_norm": 0.0,
|
| 762 |
+
"learning_rate": 4.7905e-05,
|
| 763 |
+
"loss": 1.7422,
|
| 764 |
+
"mean_token_accuracy": 0.6511821269989013,
|
| 765 |
+
"num_tokens": 1530549.0,
|
| 766 |
+
"step": 420
|
| 767 |
}
|
| 768 |
],
|
| 769 |
"logging_steps": 5,
|
|
|
|
| 783 |
"attributes": {}
|
| 784 |
}
|
| 785 |
},
|
| 786 |
+
"total_flos": 7.741626589052928e+16,
|
| 787 |
"train_batch_size": 4,
|
| 788 |
"trial_name": null,
|
| 789 |
"trial_params": null
|