Training in progress, step 8180, 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:c9ecfe5c055a85fe0addc6ece237315a62ed582a7df4809dbc2e50014de37575
|
| 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:a5a8dd6d07f7e548ced6a887554b37a14a93e60c42dea17e350b9ae05926327f
|
| 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 sha256:615d7de00c1f1e0babfede99b17fcc18bdb67477cb41e124eaa7dbe5946dccef
|
| 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": 62.
|
| 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,
|
|
@@ -14714,6 +14714,24 @@
|
|
| 14714 |
"mean_token_accuracy": 0.6586943835020065,
|
| 14715 |
"num_tokens": 29796604.0,
|
| 14716 |
"step": 8170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14717 |
}
|
| 14718 |
],
|
| 14719 |
"logging_steps": 5,
|
|
@@ -14733,7 +14751,7 @@
|
|
| 14733 |
"attributes": {}
|
| 14734 |
}
|
| 14735 |
},
|
| 14736 |
-
"total_flos": 1.
|
| 14737 |
"train_batch_size": 4,
|
| 14738 |
"trial_name": null,
|
| 14739 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14714 |
"mean_token_accuracy": 0.6586943835020065,
|
| 14715 |
"num_tokens": 29796604.0,
|
| 14716 |
"step": 8170
|
| 14717 |
+
},
|
| 14718 |
+
{
|
| 14719 |
+
"epoch": 62.88461538461539,
|
| 14720 |
+
"grad_norm": 0.0,
|
| 14721 |
+
"learning_rate": 9.13e-06,
|
| 14722 |
+
"loss": 1.8185,
|
| 14723 |
+
"mean_token_accuracy": 0.6354205548763275,
|
| 14724 |
+
"num_tokens": 29813853.0,
|
| 14725 |
+
"step": 8175
|
| 14726 |
+
},
|
| 14727 |
+
{
|
| 14728 |
+
"epoch": 62.92307692307692,
|
| 14729 |
+
"grad_norm": 0.0,
|
| 14730 |
+
"learning_rate": 9.105000000000002e-06,
|
| 14731 |
+
"loss": 1.7358,
|
| 14732 |
+
"mean_token_accuracy": 0.6511748641729355,
|
| 14733 |
+
"num_tokens": 29832138.0,
|
| 14734 |
+
"step": 8180
|
| 14735 |
}
|
| 14736 |
],
|
| 14737 |
"logging_steps": 5,
|
|
|
|
| 14751 |
"attributes": {}
|
| 14752 |
}
|
| 14753 |
},
|
| 14754 |
+
"total_flos": 1.5125345928983347e+18,
|
| 14755 |
"train_batch_size": 4,
|
| 14756 |
"trial_name": null,
|
| 14757 |
"trial_params": null
|