Training in progress, epoch 9, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2682482800
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a664102d1b3ac5fecaadaaf9968da194c74be4d99b0e5648fc5ba6e5edbbd53
|
3 |
size 2682482800
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5365108834
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d77595fb689b5c663dc6d92d024119a8b254d933443aff4cf5d2c4e893f1277
|
3 |
size 5365108834
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15006
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecdbbc81f1577c58564d520539f0ecd1e3c63b150d117eedae0016db0ec8a85c
|
3 |
size 15006
|
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 sha256:6602c18a1ebe894c1d51ce5c9cea3744db091c466423f123d4fa8b7754d9378a
|
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":
|
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,
|
@@ -727,6 +727,96 @@
|
|
727 |
"eval_samples_per_second": 41.601,
|
728 |
"eval_steps_per_second": 20.801,
|
729 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
730 |
}
|
731 |
],
|
732 |
"logging_steps": 50,
|
@@ -741,12 +831,12 @@
|
|
741 |
"should_evaluate": false,
|
742 |
"should_log": false,
|
743 |
"should_save": true,
|
744 |
-
"should_training_stop":
|
745 |
},
|
746 |
"attributes": {}
|
747 |
}
|
748 |
},
|
749 |
-
"total_flos":
|
750 |
"train_batch_size": 2,
|
751 |
"trial_name": null,
|
752 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.998851234922459,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 2720,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
727 |
"eval_samples_per_second": 41.601,
|
728 |
"eval_steps_per_second": 20.801,
|
729 |
"step": 2400
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 9.00631820792648,
|
733 |
+
"grad_norm": 69.84994506835938,
|
734 |
+
"learning_rate": 9.926470588235293e-06,
|
735 |
+
"loss": 0.8202,
|
736 |
+
"step": 2450
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 9.00631820792648,
|
740 |
+
"eval_loss": 1.2383702993392944,
|
741 |
+
"eval_runtime": 116.7345,
|
742 |
+
"eval_samples_per_second": 41.342,
|
743 |
+
"eval_steps_per_second": 20.671,
|
744 |
+
"step": 2450
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 9.190120620333142,
|
748 |
+
"grad_norm": 75.23961639404297,
|
749 |
+
"learning_rate": 8.088235294117648e-06,
|
750 |
+
"loss": 0.8143,
|
751 |
+
"step": 2500
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 9.190120620333142,
|
755 |
+
"eval_loss": 1.236066460609436,
|
756 |
+
"eval_runtime": 115.996,
|
757 |
+
"eval_samples_per_second": 41.605,
|
758 |
+
"eval_steps_per_second": 20.802,
|
759 |
+
"step": 2500
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 9.373923032739805,
|
763 |
+
"grad_norm": 62.9267692565918,
|
764 |
+
"learning_rate": 6.25e-06,
|
765 |
+
"loss": 0.8106,
|
766 |
+
"step": 2550
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 9.373923032739805,
|
770 |
+
"eval_loss": 1.23640775680542,
|
771 |
+
"eval_runtime": 115.848,
|
772 |
+
"eval_samples_per_second": 41.658,
|
773 |
+
"eval_steps_per_second": 20.829,
|
774 |
+
"step": 2550
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 9.557725445146467,
|
778 |
+
"grad_norm": 54.76566696166992,
|
779 |
+
"learning_rate": 4.411764705882353e-06,
|
780 |
+
"loss": 0.8144,
|
781 |
+
"step": 2600
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 9.557725445146467,
|
785 |
+
"eval_loss": 1.2419943809509277,
|
786 |
+
"eval_runtime": 116.0232,
|
787 |
+
"eval_samples_per_second": 41.595,
|
788 |
+
"eval_steps_per_second": 20.798,
|
789 |
+
"step": 2600
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 9.74152785755313,
|
793 |
+
"grad_norm": 51.20401382446289,
|
794 |
+
"learning_rate": 2.573529411764706e-06,
|
795 |
+
"loss": 0.8061,
|
796 |
+
"step": 2650
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 9.74152785755313,
|
800 |
+
"eval_loss": 1.2368206977844238,
|
801 |
+
"eval_runtime": 116.069,
|
802 |
+
"eval_samples_per_second": 41.579,
|
803 |
+
"eval_steps_per_second": 20.789,
|
804 |
+
"step": 2650
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 9.925330269959794,
|
808 |
+
"grad_norm": 52.51292419433594,
|
809 |
+
"learning_rate": 7.352941176470589e-07,
|
810 |
+
"loss": 0.8122,
|
811 |
+
"step": 2700
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 9.925330269959794,
|
815 |
+
"eval_loss": 1.2355531454086304,
|
816 |
+
"eval_runtime": 116.1057,
|
817 |
+
"eval_samples_per_second": 41.566,
|
818 |
+
"eval_steps_per_second": 20.783,
|
819 |
+
"step": 2700
|
820 |
}
|
821 |
],
|
822 |
"logging_steps": 50,
|
|
|
831 |
"should_evaluate": false,
|
832 |
"should_log": false,
|
833 |
"should_save": true,
|
834 |
+
"should_training_stop": true
|
835 |
},
|
836 |
"attributes": {}
|
837 |
}
|
838 |
},
|
839 |
+
"total_flos": 7.018175725001769e+17,
|
840 |
"train_batch_size": 2,
|
841 |
"trial_name": null,
|
842 |
"trial_params": null
|