Training in progress, step 7720, 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:fe98677f368ddef4c286c07c5a41a5cd7d70c14dc1b5ebb0b13012df2ea97739
|
| 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 sha256:857304c757d8a10f47af3962e69991d4025783619ea26e1c94df8347c6c90cde
|
| 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:fca39b64a4491468ee665e55a8fa74eace879f632e1cfa1920586da59c324e84
|
| 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": 59.
|
| 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,
|
|
@@ -13886,6 +13886,24 @@
|
|
| 13886 |
"mean_token_accuracy": 0.6390215069055557,
|
| 13887 |
"num_tokens": 28117982.0,
|
| 13888 |
"step": 7710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13889 |
}
|
| 13890 |
],
|
| 13891 |
"logging_steps": 5,
|
|
@@ -13905,7 +13923,7 @@
|
|
| 13905 |
"attributes": {}
|
| 13906 |
}
|
| 13907 |
},
|
| 13908 |
-
"total_flos": 1.
|
| 13909 |
"train_batch_size": 4,
|
| 13910 |
"trial_name": null,
|
| 13911 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13886 |
"mean_token_accuracy": 0.6390215069055557,
|
| 13887 |
"num_tokens": 28117982.0,
|
| 13888 |
"step": 7710
|
| 13889 |
+
},
|
| 13890 |
+
{
|
| 13891 |
+
"epoch": 59.34615384615385,
|
| 13892 |
+
"grad_norm": 0.0,
|
| 13893 |
+
"learning_rate": 1.143e-05,
|
| 13894 |
+
"loss": 1.7389,
|
| 13895 |
+
"mean_token_accuracy": 0.6523732364177703,
|
| 13896 |
+
"num_tokens": 28136640.0,
|
| 13897 |
+
"step": 7715
|
| 13898 |
+
},
|
| 13899 |
+
{
|
| 13900 |
+
"epoch": 59.38461538461539,
|
| 13901 |
+
"grad_norm": 0.0,
|
| 13902 |
+
"learning_rate": 1.1405e-05,
|
| 13903 |
+
"loss": 1.7337,
|
| 13904 |
+
"mean_token_accuracy": 0.6487939029932022,
|
| 13905 |
+
"num_tokens": 28155122.0,
|
| 13906 |
+
"step": 7720
|
| 13907 |
}
|
| 13908 |
],
|
| 13909 |
"logging_steps": 5,
|
|
|
|
| 13923 |
"attributes": {}
|
| 13924 |
}
|
| 13925 |
},
|
| 13926 |
+
"total_flos": 1.4275639327879987e+18,
|
| 13927 |
"train_batch_size": 4,
|
| 13928 |
"trial_name": null,
|
| 13929 |
"trial_params": null
|