Training in progress, step 9930, 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 sha256:8cf2b2692bd437523e84d15e36f9ab617d11e127d6c59b0dcec8c128f0a0287b
|
| 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 sha256:165be38fd18fbee14a94b0ef0b0f4ca61e34e0cdf4d4eea2d670a80d97dc37e9
|
| 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 sha256:256bd28d09808220fc486c0b3f1471b8492dcd6c2c8c440dc19925088713e0a1
|
| 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": 76.
|
| 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,
|
|
@@ -17864,6 +17864,24 @@
|
|
| 17864 |
"mean_token_accuracy": 0.6330039739608765,
|
| 17865 |
"num_tokens": 36177566.0,
|
| 17866 |
"step": 9920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17867 |
}
|
| 17868 |
],
|
| 17869 |
"logging_steps": 5,
|
|
@@ -17883,7 +17901,7 @@
|
|
| 17883 |
"attributes": {}
|
| 17884 |
}
|
| 17885 |
},
|
| 17886 |
-
"total_flos": 1.
|
| 17887 |
"train_batch_size": 4,
|
| 17888 |
"trial_name": null,
|
| 17889 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 76.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17864 |
"mean_token_accuracy": 0.6330039739608765,
|
| 17865 |
"num_tokens": 36177566.0,
|
| 17866 |
"step": 9920
|
| 17867 |
+
},
|
| 17868 |
+
{
|
| 17869 |
+
"epoch": 76.34615384615384,
|
| 17870 |
+
"grad_norm": 0.0,
|
| 17871 |
+
"learning_rate": 3.8e-07,
|
| 17872 |
+
"loss": 1.7486,
|
| 17873 |
+
"mean_token_accuracy": 0.6493139892816544,
|
| 17874 |
+
"num_tokens": 36195783.0,
|
| 17875 |
+
"step": 9925
|
| 17876 |
+
},
|
| 17877 |
+
{
|
| 17878 |
+
"epoch": 76.38461538461539,
|
| 17879 |
+
"grad_norm": 0.0,
|
| 17880 |
+
"learning_rate": 3.5500000000000004e-07,
|
| 17881 |
+
"loss": 1.7019,
|
| 17882 |
+
"mean_token_accuracy": 0.6548255890607834,
|
| 17883 |
+
"num_tokens": 36214515.0,
|
| 17884 |
+
"step": 9930
|
| 17885 |
}
|
| 17886 |
],
|
| 17887 |
"logging_steps": 5,
|
|
|
|
| 17901 |
"attributes": {}
|
| 17902 |
}
|
| 17903 |
},
|
| 17904 |
+
"total_flos": 1.8363737120661504e+18,
|
| 17905 |
"train_batch_size": 4,
|
| 17906 |
"trial_name": null,
|
| 17907 |
"trial_params": null
|