Training in progress, step 8260, 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 sha256:730a4874016b50c2c25ff11b53aba4b17c2f72c84d84e931f5ee23080e8bb913
|
| 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 sha256:4f047d07f908abd5231dd87a8c7b53842ce296917881dbf9207dc853a384cdfc
|
| 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 sha256:4a32d61a61706ca3ef21124caccd0cd70250026b651876e1b7963e78104c1f21
|
| 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": 63.
|
| 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,
|
|
@@ -14858,6 +14858,24 @@
|
|
| 14858 |
"mean_token_accuracy": 0.6421218931674957,
|
| 14859 |
"num_tokens": 30087772.0,
|
| 14860 |
"step": 8250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14861 |
}
|
| 14862 |
],
|
| 14863 |
"logging_steps": 5,
|
|
@@ -14877,7 +14895,7 @@
|
|
| 14877 |
"attributes": {}
|
| 14878 |
}
|
| 14879 |
},
|
| 14880 |
-
"total_flos": 1.
|
| 14881 |
"train_batch_size": 4,
|
| 14882 |
"trial_name": null,
|
| 14883 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14858 |
"mean_token_accuracy": 0.6421218931674957,
|
| 14859 |
"num_tokens": 30087772.0,
|
| 14860 |
"step": 8250
|
| 14861 |
+
},
|
| 14862 |
+
{
|
| 14863 |
+
"epoch": 63.5,
|
| 14864 |
+
"grad_norm": 0.0,
|
| 14865 |
+
"learning_rate": 8.730000000000001e-06,
|
| 14866 |
+
"loss": 1.7815,
|
| 14867 |
+
"mean_token_accuracy": 0.6430323421955109,
|
| 14868 |
+
"num_tokens": 30105880.0,
|
| 14869 |
+
"step": 8255
|
| 14870 |
+
},
|
| 14871 |
+
{
|
| 14872 |
+
"epoch": 63.53846153846154,
|
| 14873 |
+
"grad_norm": 0.0,
|
| 14874 |
+
"learning_rate": 8.705e-06,
|
| 14875 |
+
"loss": 1.7272,
|
| 14876 |
+
"mean_token_accuracy": 0.6486560940742493,
|
| 14877 |
+
"num_tokens": 30124841.0,
|
| 14878 |
+
"step": 8260
|
| 14879 |
}
|
| 14880 |
],
|
| 14881 |
"logging_steps": 5,
|
|
|
|
| 14895 |
"attributes": {}
|
| 14896 |
}
|
| 14897 |
},
|
| 14898 |
+
"total_flos": 1.5274344279814963e+18,
|
| 14899 |
"train_batch_size": 4,
|
| 14900 |
"trial_name": null,
|
| 14901 |
"trial_params": null
|