Training in progress, step 6040, 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:aa22cec0cc9f6bad262e32eac3a570bc1a3be69ce9e56178ce950a31191db76f
|
| 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 sha256:8da512cb59b04fcccdd56dc69866deaf0ad8fd343c19d7d27cb92846bf0c49ab
|
| 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 sha256:1b68606a24fba70697101c683a08db5c568c597e9dafc4d52b8ca7dd740ec61c
|
| 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": 46.
|
| 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,
|
|
@@ -10862,6 +10862,24 @@
|
|
| 10862 |
"mean_token_accuracy": 0.658588969707489,
|
| 10863 |
"num_tokens": 21991074.0,
|
| 10864 |
"step": 6030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10865 |
}
|
| 10866 |
],
|
| 10867 |
"logging_steps": 5,
|
|
@@ -10881,7 +10899,7 @@
|
|
| 10881 |
"attributes": {}
|
| 10882 |
}
|
| 10883 |
},
|
| 10884 |
-
"total_flos": 1.
|
| 10885 |
"train_batch_size": 4,
|
| 10886 |
"trial_name": null,
|
| 10887 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6040,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10862 |
"mean_token_accuracy": 0.658588969707489,
|
| 10863 |
"num_tokens": 21991074.0,
|
| 10864 |
"step": 6030
|
| 10865 |
+
},
|
| 10866 |
+
{
|
| 10867 |
+
"epoch": 46.42307692307692,
|
| 10868 |
+
"grad_norm": 0.0,
|
| 10869 |
+
"learning_rate": 1.983e-05,
|
| 10870 |
+
"loss": 1.7319,
|
| 10871 |
+
"mean_token_accuracy": 0.6501603156328202,
|
| 10872 |
+
"num_tokens": 22009260.0,
|
| 10873 |
+
"step": 6035
|
| 10874 |
+
},
|
| 10875 |
+
{
|
| 10876 |
+
"epoch": 46.46153846153846,
|
| 10877 |
+
"grad_norm": 0.0,
|
| 10878 |
+
"learning_rate": 1.9805e-05,
|
| 10879 |
+
"loss": 1.6804,
|
| 10880 |
+
"mean_token_accuracy": 0.65768404006958,
|
| 10881 |
+
"num_tokens": 22028277.0,
|
| 10882 |
+
"step": 6040
|
| 10883 |
}
|
| 10884 |
],
|
| 10885 |
"logging_steps": 5,
|
|
|
|
| 10899 |
"attributes": {}
|
| 10900 |
}
|
| 10901 |
},
|
| 10902 |
+
"total_flos": 1.1163631573234483e+18,
|
| 10903 |
"train_batch_size": 4,
|
| 10904 |
"trial_name": null,
|
| 10905 |
"trial_params": null
|