Training in progress, step 6030, 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:e1ed5be6f37b375ee83da4d1b53923e41b6af2e03f37966cafcdbb2a05864445
|
| 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 sha256:07efedcfed1c5f2c7a19cc95f4eea45731295856f7bf8833bc1e355ccdaab0a2
|
| 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 sha256:6b031afd2a0601c9174e09d5c2dad79b600f0302fab45d58c28b722b6206e5e8
|
| 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,
|
|
@@ -10844,6 +10844,24 @@
|
|
| 10844 |
"mean_token_accuracy": 0.6457954943180084,
|
| 10845 |
"num_tokens": 21954031.0,
|
| 10846 |
"step": 6020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10847 |
}
|
| 10848 |
],
|
| 10849 |
"logging_steps": 5,
|
|
@@ -10863,7 +10881,7 @@
|
|
| 10863 |
"attributes": {}
|
| 10864 |
}
|
| 10865 |
},
|
| 10866 |
-
"total_flos": 1.
|
| 10867 |
"train_batch_size": 4,
|
| 10868 |
"trial_name": null,
|
| 10869 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10844 |
"mean_token_accuracy": 0.6457954943180084,
|
| 10845 |
"num_tokens": 21954031.0,
|
| 10846 |
"step": 6020
|
| 10847 |
+
},
|
| 10848 |
+
{
|
| 10849 |
+
"epoch": 46.34615384615385,
|
| 10850 |
+
"grad_norm": 0.0,
|
| 10851 |
+
"learning_rate": 1.9880000000000003e-05,
|
| 10852 |
+
"loss": 1.7037,
|
| 10853 |
+
"mean_token_accuracy": 0.6573837339878082,
|
| 10854 |
+
"num_tokens": 21972598.0,
|
| 10855 |
+
"step": 6025
|
| 10856 |
+
},
|
| 10857 |
+
{
|
| 10858 |
+
"epoch": 46.38461538461539,
|
| 10859 |
+
"grad_norm": 0.0,
|
| 10860 |
+
"learning_rate": 1.9855000000000002e-05,
|
| 10861 |
+
"loss": 1.7076,
|
| 10862 |
+
"mean_token_accuracy": 0.658588969707489,
|
| 10863 |
+
"num_tokens": 21991074.0,
|
| 10864 |
+
"step": 6030
|
| 10865 |
}
|
| 10866 |
],
|
| 10867 |
"logging_steps": 5,
|
|
|
|
| 10881 |
"attributes": {}
|
| 10882 |
}
|
| 10883 |
},
|
| 10884 |
+
"total_flos": 1.1144655877467341e+18,
|
| 10885 |
"train_batch_size": 4,
|
| 10886 |
"trial_name": null,
|
| 10887 |
"trial_params": null
|