Training in progress, step 430, 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:a83285cb38d2068ad7c095a82fb0ef252b511c4f8d4c9dc34e9159614b2dc493
|
| 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:fb2e33cf1e54defec9dd4755f107a9405ab28c494b1b59d30dd9a96ad2f24eef
|
| 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 sha256:6c269cf1f3b9ac7377e0ab78c5f26e83038949f681e47ebc19d3ee7d8f99f1b8
|
| 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,
|
|
@@ -764,6 +764,24 @@
|
|
| 764 |
"mean_token_accuracy": 0.6511821269989013,
|
| 765 |
"num_tokens": 1530549.0,
|
| 766 |
"step": 420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 767 |
}
|
| 768 |
],
|
| 769 |
"logging_steps": 5,
|
|
@@ -783,7 +801,7 @@
|
|
| 783 |
"attributes": {}
|
| 784 |
}
|
| 785 |
},
|
| 786 |
-
"total_flos": 7.
|
| 787 |
"train_batch_size": 4,
|
| 788 |
"trial_name": null,
|
| 789 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.3076923076923075,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 764 |
"mean_token_accuracy": 0.6511821269989013,
|
| 765 |
"num_tokens": 1530549.0,
|
| 766 |
"step": 420
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 3.269230769230769,
|
| 770 |
+
"grad_norm": 0.0,
|
| 771 |
+
"learning_rate": 4.788e-05,
|
| 772 |
+
"loss": 1.7655,
|
| 773 |
+
"mean_token_accuracy": 0.6506276488304138,
|
| 774 |
+
"num_tokens": 1548502.0,
|
| 775 |
+
"step": 425
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 3.3076923076923075,
|
| 779 |
+
"grad_norm": 0.0,
|
| 780 |
+
"learning_rate": 4.7855e-05,
|
| 781 |
+
"loss": 1.6594,
|
| 782 |
+
"mean_token_accuracy": 0.6622169464826584,
|
| 783 |
+
"num_tokens": 1568042.0,
|
| 784 |
+
"step": 430
|
| 785 |
}
|
| 786 |
],
|
| 787 |
"logging_steps": 5,
|
|
|
|
| 801 |
"attributes": {}
|
| 802 |
}
|
| 803 |
},
|
| 804 |
+
"total_flos": 7.941561289998336e+16,
|
| 805 |
"train_batch_size": 4,
|
| 806 |
"trial_name": null,
|
| 807 |
"trial_params": null
|