Training in progress, step 3180, 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 sha256:553653259263d02a2d35df786511783190214b9f494764af7148dd5c48d1b932
|
| 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 sha256:78a2524cd750154c13fa27cc1da6f3d01323b8fb20459759ab77aea469aa7661
|
| 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 sha256:7333cfdad3d5ca6170cda218b9b06e4d311dfb603e8b9e018c8e163ee41c8cf8
|
| 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": 24.
|
| 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,
|
|
@@ -5714,6 +5714,24 @@
|
|
| 5714 |
"mean_token_accuracy": 0.6424742221832276,
|
| 5715 |
"num_tokens": 11560367.0,
|
| 5716 |
"step": 3170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5717 |
}
|
| 5718 |
],
|
| 5719 |
"logging_steps": 5,
|
|
@@ -5733,7 +5751,7 @@
|
|
| 5733 |
"attributes": {}
|
| 5734 |
}
|
| 5735 |
},
|
| 5736 |
-
"total_flos": 5.
|
| 5737 |
"train_batch_size": 4,
|
| 5738 |
"trial_name": null,
|
| 5739 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5714 |
"mean_token_accuracy": 0.6424742221832276,
|
| 5715 |
"num_tokens": 11560367.0,
|
| 5716 |
"step": 3170
|
| 5717 |
+
},
|
| 5718 |
+
{
|
| 5719 |
+
"epoch": 24.423076923076923,
|
| 5720 |
+
"grad_norm": 0.0,
|
| 5721 |
+
"learning_rate": 3.413e-05,
|
| 5722 |
+
"loss": 1.7211,
|
| 5723 |
+
"mean_token_accuracy": 0.6575414210557937,
|
| 5724 |
+
"num_tokens": 11578662.0,
|
| 5725 |
+
"step": 3175
|
| 5726 |
+
},
|
| 5727 |
+
{
|
| 5728 |
+
"epoch": 24.46153846153846,
|
| 5729 |
+
"grad_norm": 0.0,
|
| 5730 |
+
"learning_rate": 3.4105000000000006e-05,
|
| 5731 |
+
"loss": 1.7301,
|
| 5732 |
+
"mean_token_accuracy": 0.6548975586891175,
|
| 5733 |
+
"num_tokens": 11597057.0,
|
| 5734 |
+
"step": 3180
|
| 5735 |
}
|
| 5736 |
],
|
| 5737 |
"logging_steps": 5,
|
|
|
|
| 5751 |
"attributes": {}
|
| 5752 |
}
|
| 5753 |
},
|
| 5754 |
+
"total_flos": 5.875738215387955e+17,
|
| 5755 |
"train_batch_size": 4,
|
| 5756 |
"trial_name": null,
|
| 5757 |
"trial_params": null
|