Training in progress, step 3820, 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 sha256:13d901453f0bda00e3b933bf234862d0f26984d0f46428c859b3474d51b155af
|
| 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 sha256:81a1edd710af51049ae4c9189d7ef80c68d566f739dfe452ad88d3713794ee3a
|
| 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:d349097a45ec0806465fbd7242c03d64c65712eadf84a425679d05d00e9252b3
|
| 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": 29.
|
| 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,
|
|
@@ -6866,6 +6866,24 @@
|
|
| 6866 |
"mean_token_accuracy": 0.6589089602231979,
|
| 6867 |
"num_tokens": 13896941.0,
|
| 6868 |
"step": 3810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6869 |
}
|
| 6870 |
],
|
| 6871 |
"logging_steps": 5,
|
|
@@ -6885,7 +6903,7 @@
|
|
| 6885 |
"attributes": {}
|
| 6886 |
}
|
| 6887 |
},
|
| 6888 |
-
"total_flos": 7.
|
| 6889 |
"train_batch_size": 4,
|
| 6890 |
"trial_name": null,
|
| 6891 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6866 |
"mean_token_accuracy": 0.6589089602231979,
|
| 6867 |
"num_tokens": 13896941.0,
|
| 6868 |
"step": 3810
|
| 6869 |
+
},
|
| 6870 |
+
{
|
| 6871 |
+
"epoch": 29.346153846153847,
|
| 6872 |
+
"grad_norm": 0.0,
|
| 6873 |
+
"learning_rate": 3.0930000000000004e-05,
|
| 6874 |
+
"loss": 1.7573,
|
| 6875 |
+
"mean_token_accuracy": 0.64599030315876,
|
| 6876 |
+
"num_tokens": 13915563.0,
|
| 6877 |
+
"step": 3815
|
| 6878 |
+
},
|
| 6879 |
+
{
|
| 6880 |
+
"epoch": 29.384615384615383,
|
| 6881 |
+
"grad_norm": 0.0,
|
| 6882 |
+
"learning_rate": 3.0905e-05,
|
| 6883 |
+
"loss": 1.7548,
|
| 6884 |
+
"mean_token_accuracy": 0.6496599853038788,
|
| 6885 |
+
"num_tokens": 13933531.0,
|
| 6886 |
+
"step": 3820
|
| 6887 |
}
|
| 6888 |
],
|
| 6889 |
"logging_steps": 5,
|
|
|
|
| 6903 |
"attributes": {}
|
| 6904 |
}
|
| 6905 |
},
|
| 6906 |
+
"total_flos": 7.06166918540329e+17,
|
| 6907 |
"train_batch_size": 4,
|
| 6908 |
"trial_name": null,
|
| 6909 |
"trial_params": null
|