Training in progress, step 7730, 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 sha256:7ba9a4325d9cb3a777041c7510be0ae71b9e22afb7c3d00d5991db1c87174224
|
| 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 sha256:412b8031bfa16b03ad1b7dbc98b5a157dfc2a924fd398c7096c5bdc502a7c8df
|
| 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 sha256:2e30665bbbfc652e466e5374a2c2eaef82a18ec71e6fac8dc691ea6905e7363a
|
| 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,
|
|
@@ -13904,6 +13904,24 @@
|
|
| 13904 |
"mean_token_accuracy": 0.6487939029932022,
|
| 13905 |
"num_tokens": 28155122.0,
|
| 13906 |
"step": 7720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13907 |
}
|
| 13908 |
],
|
| 13909 |
"logging_steps": 5,
|
|
@@ -13923,7 +13941,7 @@
|
|
| 13923 |
"attributes": {}
|
| 13924 |
}
|
| 13925 |
},
|
| 13926 |
-
"total_flos": 1.
|
| 13927 |
"train_batch_size": 4,
|
| 13928 |
"trial_name": null,
|
| 13929 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13904 |
"mean_token_accuracy": 0.6487939029932022,
|
| 13905 |
"num_tokens": 28155122.0,
|
| 13906 |
"step": 7720
|
| 13907 |
+
},
|
| 13908 |
+
{
|
| 13909 |
+
"epoch": 59.42307692307692,
|
| 13910 |
+
"grad_norm": 0.0,
|
| 13911 |
+
"learning_rate": 1.1380000000000001e-05,
|
| 13912 |
+
"loss": 1.7896,
|
| 13913 |
+
"mean_token_accuracy": 0.6361289143562316,
|
| 13914 |
+
"num_tokens": 28173409.0,
|
| 13915 |
+
"step": 7725
|
| 13916 |
+
},
|
| 13917 |
+
{
|
| 13918 |
+
"epoch": 59.46153846153846,
|
| 13919 |
+
"grad_norm": 0.0,
|
| 13920 |
+
"learning_rate": 1.1355e-05,
|
| 13921 |
+
"loss": 1.6714,
|
| 13922 |
+
"mean_token_accuracy": 0.6632986754179001,
|
| 13923 |
+
"num_tokens": 28191671.0,
|
| 13924 |
+
"step": 7730
|
| 13925 |
}
|
| 13926 |
],
|
| 13927 |
"logging_steps": 5,
|
|
|
|
| 13941 |
"attributes": {}
|
| 13942 |
}
|
| 13943 |
},
|
| 13944 |
+
"total_flos": 1.4295027849427354e+18,
|
| 13945 |
"train_batch_size": 4,
|
| 13946 |
"trial_name": null,
|
| 13947 |
"trial_params": null
|