Training in progress, step 9370, 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:aa94145b1826389d1072e9831ccf6a1bff9e4ee17cb00841bdd7d7828b73ed29
|
| 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:ca0191027f98c8e57df92882f1af4f546bdb3f10aef24e65cbcf01964cf12ccf
|
| 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:d2d5fd3d36369a0f830caaf8d9d2516806bb17af6b2c545209ff673b4478ce38
|
| 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": 72.
|
| 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,
|
|
@@ -16856,6 +16856,24 @@
|
|
| 16856 |
"mean_token_accuracy": 0.6458366394042969,
|
| 16857 |
"num_tokens": 34135560.0,
|
| 16858 |
"step": 9360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16859 |
}
|
| 16860 |
],
|
| 16861 |
"logging_steps": 5,
|
|
@@ -16875,7 +16893,7 @@
|
|
| 16875 |
"attributes": {}
|
| 16876 |
}
|
| 16877 |
},
|
| 16878 |
-
"total_flos": 1.
|
| 16879 |
"train_batch_size": 4,
|
| 16880 |
"trial_name": null,
|
| 16881 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16856 |
"mean_token_accuracy": 0.6458366394042969,
|
| 16857 |
"num_tokens": 34135560.0,
|
| 16858 |
"step": 9360
|
| 16859 |
+
},
|
| 16860 |
+
{
|
| 16861 |
+
"epoch": 72.03846153846153,
|
| 16862 |
+
"grad_norm": 0.0,
|
| 16863 |
+
"learning_rate": 3.1800000000000005e-06,
|
| 16864 |
+
"loss": 1.7497,
|
| 16865 |
+
"mean_token_accuracy": 0.6472752332687378,
|
| 16866 |
+
"num_tokens": 34153754.0,
|
| 16867 |
+
"step": 9365
|
| 16868 |
+
},
|
| 16869 |
+
{
|
| 16870 |
+
"epoch": 72.07692307692308,
|
| 16871 |
+
"grad_norm": 0.0,
|
| 16872 |
+
"learning_rate": 3.1550000000000003e-06,
|
| 16873 |
+
"loss": 1.7499,
|
| 16874 |
+
"mean_token_accuracy": 0.6482025504112243,
|
| 16875 |
+
"num_tokens": 34172147.0,
|
| 16876 |
+
"step": 9370
|
| 16877 |
}
|
| 16878 |
],
|
| 16879 |
"logging_steps": 5,
|
|
|
|
| 16893 |
"attributes": {}
|
| 16894 |
}
|
| 16895 |
},
|
| 16896 |
+
"total_flos": 1.7327487251806618e+18,
|
| 16897 |
"train_batch_size": 4,
|
| 16898 |
"trial_name": null,
|
| 16899 |
"trial_params": null
|