Training in progress, step 7100, 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 sha256:42ebcdbfbcf2ab607f1d85d5fcee0400c78741f06cbe3f4e5534921b4df1bf86
|
| 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:b8a6f9786d2164a6ceb166b82e18132e1a74cc116428da6f11c3e1fd70ec97e1
|
| 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 sha256:9ae2ac99dfa7f59c453b2752ba375be2b7509d5291ec19ea8f5e95676417a12e
|
| 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": 54.
|
| 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,
|
|
@@ -12770,6 +12770,24 @@
|
|
| 12770 |
"mean_token_accuracy": 0.6489378064870834,
|
| 12771 |
"num_tokens": 25860639.0,
|
| 12772 |
"step": 7090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12773 |
}
|
| 12774 |
],
|
| 12775 |
"logging_steps": 5,
|
|
@@ -12789,7 +12807,7 @@
|
|
| 12789 |
"attributes": {}
|
| 12790 |
}
|
| 12791 |
},
|
| 12792 |
-
"total_flos": 1.
|
| 12793 |
"train_batch_size": 4,
|
| 12794 |
"trial_name": null,
|
| 12795 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12770 |
"mean_token_accuracy": 0.6489378064870834,
|
| 12771 |
"num_tokens": 25860639.0,
|
| 12772 |
"step": 7090
|
| 12773 |
+
},
|
| 12774 |
+
{
|
| 12775 |
+
"epoch": 54.57692307692308,
|
| 12776 |
+
"grad_norm": 0.0,
|
| 12777 |
+
"learning_rate": 1.4530000000000001e-05,
|
| 12778 |
+
"loss": 1.721,
|
| 12779 |
+
"mean_token_accuracy": 0.6531164467334747,
|
| 12780 |
+
"num_tokens": 25878985.0,
|
| 12781 |
+
"step": 7095
|
| 12782 |
+
},
|
| 12783 |
+
{
|
| 12784 |
+
"epoch": 54.61538461538461,
|
| 12785 |
+
"grad_norm": 0.0,
|
| 12786 |
+
"learning_rate": 1.4505000000000003e-05,
|
| 12787 |
+
"loss": 1.7618,
|
| 12788 |
+
"mean_token_accuracy": 0.6497918337583541,
|
| 12789 |
+
"num_tokens": 25896813.0,
|
| 12790 |
+
"step": 7100
|
| 12791 |
}
|
| 12792 |
],
|
| 12793 |
"logging_steps": 5,
|
|
|
|
| 12807 |
"attributes": {}
|
| 12808 |
}
|
| 12809 |
},
|
| 12810 |
+
"total_flos": 1.3130752767167693e+18,
|
| 12811 |
"train_batch_size": 4,
|
| 12812 |
"trial_name": null,
|
| 12813 |
"trial_params": null
|