Training in progress, step 2640, 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 sha256:0d59cfba6786165def9f21b6418420d6b49446c3741d3bb6a97b4fb0f50b8afe
|
| 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:d479d51cbf4b6f3fc241cc6cdbffeb5dc4768281a1363cf985709dc2e3e3b2e4
|
| 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 sha256:368082d99cc259e63046850c717b325703e85f90e5ec83a6f038de7a4bc3ee96
|
| 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": 20.
|
| 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,
|
|
@@ -4742,6 +4742,24 @@
|
|
| 4742 |
"mean_token_accuracy": 0.6516992777585984,
|
| 4743 |
"num_tokens": 9590370.0,
|
| 4744 |
"step": 2630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4745 |
}
|
| 4746 |
],
|
| 4747 |
"logging_steps": 5,
|
|
@@ -4761,7 +4779,7 @@
|
|
| 4761 |
"attributes": {}
|
| 4762 |
}
|
| 4763 |
},
|
| 4764 |
-
"total_flos": 4.
|
| 4765 |
"train_batch_size": 4,
|
| 4766 |
"trial_name": null,
|
| 4767 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4742 |
"mean_token_accuracy": 0.6516992777585984,
|
| 4743 |
"num_tokens": 9590370.0,
|
| 4744 |
"step": 2630
|
| 4745 |
+
},
|
| 4746 |
+
{
|
| 4747 |
+
"epoch": 20.26923076923077,
|
| 4748 |
+
"grad_norm": 0.0,
|
| 4749 |
+
"learning_rate": 3.6830000000000005e-05,
|
| 4750 |
+
"loss": 1.7493,
|
| 4751 |
+
"mean_token_accuracy": 0.6508445411920547,
|
| 4752 |
+
"num_tokens": 9608387.0,
|
| 4753 |
+
"step": 2635
|
| 4754 |
+
},
|
| 4755 |
+
{
|
| 4756 |
+
"epoch": 20.307692307692307,
|
| 4757 |
+
"grad_norm": 0.0,
|
| 4758 |
+
"learning_rate": 3.6805e-05,
|
| 4759 |
+
"loss": 1.754,
|
| 4760 |
+
"mean_token_accuracy": 0.6476915091276169,
|
| 4761 |
+
"num_tokens": 9626593.0,
|
| 4762 |
+
"step": 2640
|
| 4763 |
}
|
| 4764 |
],
|
| 4765 |
"logging_steps": 5,
|
|
|
|
| 4779 |
"attributes": {}
|
| 4780 |
}
|
| 4781 |
},
|
| 4782 |
+
"total_flos": 4.878541665342259e+17,
|
| 4783 |
"train_batch_size": 4,
|
| 4784 |
"trial_name": null,
|
| 4785 |
"trial_params": null
|