Training in progress, step 9280, 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:bc5692b986646669402f4208594acbcd3ddf80db8faf0e988f7837e6d9ee1021
|
| 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:fb94b7e7335fa45d16bd0fde80ea9481e9ec1e9b412cc7befc5bfdb90cb4a824
|
| 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 sha256:6cb3ffea098ebdff1bad4cf5a6b03c9f11eb9d285b1e5e2b3c418a6bb00efa62
|
| 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": 71.
|
| 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,
|
|
@@ -16694,6 +16694,24 @@
|
|
| 16694 |
"mean_token_accuracy": 0.6486911535263061,
|
| 16695 |
"num_tokens": 33807428.0,
|
| 16696 |
"step": 9270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16697 |
}
|
| 16698 |
],
|
| 16699 |
"logging_steps": 5,
|
|
@@ -16713,7 +16731,7 @@
|
|
| 16713 |
"attributes": {}
|
| 16714 |
}
|
| 16715 |
},
|
| 16716 |
-
"total_flos": 1.
|
| 16717 |
"train_batch_size": 4,
|
| 16718 |
"trial_name": null,
|
| 16719 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16694 |
"mean_token_accuracy": 0.6486911535263061,
|
| 16695 |
"num_tokens": 33807428.0,
|
| 16696 |
"step": 9270
|
| 16697 |
+
},
|
| 16698 |
+
{
|
| 16699 |
+
"epoch": 71.34615384615384,
|
| 16700 |
+
"grad_norm": 0.0,
|
| 16701 |
+
"learning_rate": 3.63e-06,
|
| 16702 |
+
"loss": 1.7888,
|
| 16703 |
+
"mean_token_accuracy": 0.6441873848438263,
|
| 16704 |
+
"num_tokens": 33825382.0,
|
| 16705 |
+
"step": 9275
|
| 16706 |
+
},
|
| 16707 |
+
{
|
| 16708 |
+
"epoch": 71.38461538461539,
|
| 16709 |
+
"grad_norm": 0.0,
|
| 16710 |
+
"learning_rate": 3.6050000000000002e-06,
|
| 16711 |
+
"loss": 1.7271,
|
| 16712 |
+
"mean_token_accuracy": 0.6498310655355454,
|
| 16713 |
+
"num_tokens": 33844179.0,
|
| 16714 |
+
"step": 9280
|
| 16715 |
}
|
| 16716 |
],
|
| 16717 |
"logging_steps": 5,
|
|
|
|
| 16731 |
"attributes": {}
|
| 16732 |
}
|
| 16733 |
},
|
| 16734 |
+
"total_flos": 1.716148524220416e+18,
|
| 16735 |
"train_batch_size": 4,
|
| 16736 |
"trial_name": null,
|
| 16737 |
"trial_params": null
|