Training in progress, step 100, 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 202110330
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8081028a2940755a6faa9c59ccfc7cb9531bb6cfd8aba2f05ca3141bf54b8c2c
|
3 |
size 202110330
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35bc8ca4dca07fe40ce15b094216393095b0eb44044dd8c9aa6869228af8c169
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5416093c744b622c4436f38b8545546a70241fb2d36e53a533c7ae67d7ced8b6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -716,6 +716,21 @@
|
|
716 |
"learning_rate": 5.7822281945782424e-08,
|
717 |
"loss": 0.0,
|
718 |
"step": 99
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
719 |
}
|
720 |
],
|
721 |
"logging_steps": 1,
|
@@ -730,12 +745,12 @@
|
|
730 |
"should_evaluate": false,
|
731 |
"should_log": false,
|
732 |
"should_save": true,
|
733 |
-
"should_training_stop":
|
734 |
},
|
735 |
"attributes": {}
|
736 |
}
|
737 |
},
|
738 |
-
"total_flos": 8.
|
739 |
"train_batch_size": 2,
|
740 |
"trial_name": null,
|
741 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.08356400480493027,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
716 |
"learning_rate": 5.7822281945782424e-08,
|
717 |
"loss": 0.0,
|
718 |
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.08356400480493027,
|
722 |
+
"grad_norm": NaN,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 0.0,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.08356400480493027,
|
729 |
+
"eval_loss": NaN,
|
730 |
+
"eval_runtime": 135.6081,
|
731 |
+
"eval_samples_per_second": 29.725,
|
732 |
+
"eval_steps_per_second": 14.866,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
745 |
"should_evaluate": false,
|
746 |
"should_log": false,
|
747 |
"should_save": true,
|
748 |
+
"should_training_stop": true
|
749 |
},
|
750 |
"attributes": {}
|
751 |
}
|
752 |
},
|
753 |
+
"total_flos": 8.33416392081408e+16,
|
754 |
"train_batch_size": 2,
|
755 |
"trial_name": null,
|
756 |
"trial_params": null
|