Training in progress, step 8270, 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 sha256:1b757e21afe34971d60fb7c16cc1e3cf34dafbbb8ab65520d14338eaa0f7ab0c
|
| 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:da76e406d188513f85f89988acb6a4992943abf9301d83f5e15e46d1a093a34a
|
| 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 sha256:2cf7e458fc298b6081d638271b957d6902f75f9eb5ca8f5c3632f33de3f5343e
|
| 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,
|
|
@@ -14876,6 +14876,24 @@
|
|
| 14876 |
"mean_token_accuracy": 0.6486560940742493,
|
| 14877 |
"num_tokens": 30124841.0,
|
| 14878 |
"step": 8260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14879 |
}
|
| 14880 |
],
|
| 14881 |
"logging_steps": 5,
|
|
@@ -14895,7 +14913,7 @@
|
|
| 14895 |
"attributes": {}
|
| 14896 |
}
|
| 14897 |
},
|
| 14898 |
-
"total_flos": 1.
|
| 14899 |
"train_batch_size": 4,
|
| 14900 |
"trial_name": null,
|
| 14901 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14876 |
"mean_token_accuracy": 0.6486560940742493,
|
| 14877 |
"num_tokens": 30124841.0,
|
| 14878 |
"step": 8260
|
| 14879 |
+
},
|
| 14880 |
+
{
|
| 14881 |
+
"epoch": 63.57692307692308,
|
| 14882 |
+
"grad_norm": 0.0,
|
| 14883 |
+
"learning_rate": 8.68e-06,
|
| 14884 |
+
"loss": 1.757,
|
| 14885 |
+
"mean_token_accuracy": 0.6492252767086029,
|
| 14886 |
+
"num_tokens": 30142267.0,
|
| 14887 |
+
"step": 8265
|
| 14888 |
+
},
|
| 14889 |
+
{
|
| 14890 |
+
"epoch": 63.61538461538461,
|
| 14891 |
+
"grad_norm": 0.0,
|
| 14892 |
+
"learning_rate": 8.655000000000001e-06,
|
| 14893 |
+
"loss": 1.7874,
|
| 14894 |
+
"mean_token_accuracy": 0.6347816586494446,
|
| 14895 |
+
"num_tokens": 30160045.0,
|
| 14896 |
+
"step": 8270
|
| 14897 |
}
|
| 14898 |
],
|
| 14899 |
"logging_steps": 5,
|
|
|
|
| 14913 |
"attributes": {}
|
| 14914 |
}
|
| 14915 |
},
|
| 14916 |
+
"total_flos": 1.529227679659131e+18,
|
| 14917 |
"train_batch_size": 4,
|
| 14918 |
"trial_name": null,
|
| 14919 |
"trial_params": null
|