Training in progress, step 9290, 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 sha256:460772aa9ecfae989b55efdc980797e5f69f21182ff3e4e5d5755f94b9b7305c
|
| 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 sha256:9433a926d1b90201a239a276b86014d0a4123408109ca286471590b3f27d3ed9
|
| 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:aaf2cf09660de43b2f516657f5f4359bf33d86dc3d7ecca593a4f75523a5ade1
|
| 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,
|
|
@@ -16712,6 +16712,24 @@
|
|
| 16712 |
"mean_token_accuracy": 0.6498310655355454,
|
| 16713 |
"num_tokens": 33844179.0,
|
| 16714 |
"step": 9280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16715 |
}
|
| 16716 |
],
|
| 16717 |
"logging_steps": 5,
|
|
@@ -16731,7 +16749,7 @@
|
|
| 16731 |
"attributes": {}
|
| 16732 |
}
|
| 16733 |
},
|
| 16734 |
-
"total_flos": 1.
|
| 16735 |
"train_batch_size": 4,
|
| 16736 |
"trial_name": null,
|
| 16737 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16712 |
"mean_token_accuracy": 0.6498310655355454,
|
| 16713 |
"num_tokens": 33844179.0,
|
| 16714 |
"step": 9280
|
| 16715 |
+
},
|
| 16716 |
+
{
|
| 16717 |
+
"epoch": 71.42307692307692,
|
| 16718 |
+
"grad_norm": 0.0,
|
| 16719 |
+
"learning_rate": 3.58e-06,
|
| 16720 |
+
"loss": 1.7322,
|
| 16721 |
+
"mean_token_accuracy": 0.6521621882915497,
|
| 16722 |
+
"num_tokens": 33862565.0,
|
| 16723 |
+
"step": 9285
|
| 16724 |
+
},
|
| 16725 |
+
{
|
| 16726 |
+
"epoch": 71.46153846153847,
|
| 16727 |
+
"grad_norm": 0.0,
|
| 16728 |
+
"learning_rate": 3.555e-06,
|
| 16729 |
+
"loss": 1.7472,
|
| 16730 |
+
"mean_token_accuracy": 0.6527814954519272,
|
| 16731 |
+
"num_tokens": 33881172.0,
|
| 16732 |
+
"step": 9290
|
| 16733 |
}
|
| 16734 |
],
|
| 16735 |
"logging_steps": 5,
|
|
|
|
| 16749 |
"attributes": {}
|
| 16750 |
}
|
| 16751 |
},
|
| 16752 |
+
"total_flos": 1.718081660325888e+18,
|
| 16753 |
"train_batch_size": 4,
|
| 16754 |
"trial_name": null,
|
| 16755 |
"trial_params": null
|