Training in progress, step 50000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40926200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41cf6769f44cd6a657afae0c8402c8dbf1b536b3eba990b730b132fd02e4d647
|
3 |
size 40926200
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 81990394
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1aeed63c55381006b708fadef7ba65db8fc71c2a65df197de79c5b30a96cc01
|
3 |
size 81990394
|
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 sha256:18ae099313552a7e12d4087c77c3938fc8f955a9878ed3913dabd879f564b0dd
|
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:b50d5a3f42d5dc4c81ec976c404c24a8b1bdccb2e72a02a310eb722387dc5353
|
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": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -742,6 +742,21 @@
|
|
742 |
"eval_samples_per_second": 53.615,
|
743 |
"eval_steps_per_second": 13.404,
|
744 |
"step": 49000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
745 |
}
|
746 |
],
|
747 |
"logging_steps": 1000,
|
@@ -756,12 +771,12 @@
|
|
756 |
"should_evaluate": false,
|
757 |
"should_log": false,
|
758 |
"should_save": true,
|
759 |
-
"should_training_stop":
|
760 |
},
|
761 |
"attributes": {}
|
762 |
}
|
763 |
},
|
764 |
-
"total_flos": 8.
|
765 |
"train_batch_size": 4,
|
766 |
"trial_name": null,
|
767 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 50000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
742 |
"eval_samples_per_second": 53.615,
|
743 |
"eval_steps_per_second": 13.404,
|
744 |
"step": 49000
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 1.0,
|
748 |
+
"grad_norm": 1.4387354850769043,
|
749 |
+
"learning_rate": 0.0,
|
750 |
+
"loss": 1.1727,
|
751 |
+
"step": 50000
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 1.0,
|
755 |
+
"eval_loss": 1.1708616018295288,
|
756 |
+
"eval_runtime": 118.0864,
|
757 |
+
"eval_samples_per_second": 53.689,
|
758 |
+
"eval_steps_per_second": 13.422,
|
759 |
+
"step": 50000
|
760 |
}
|
761 |
],
|
762 |
"logging_steps": 1000,
|
|
|
771 |
"should_evaluate": false,
|
772 |
"should_log": false,
|
773 |
"should_save": true,
|
774 |
+
"should_training_stop": true
|
775 |
},
|
776 |
"attributes": {}
|
777 |
}
|
778 |
},
|
779 |
+
"total_flos": 8.132424105984e+17,
|
780 |
"train_batch_size": 4,
|
781 |
"trial_name": null,
|
782 |
"trial_params": null
|