Training in progress, step 100, 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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a79d6468f9a8226984a35f278d2afc4996fc80bf229f9e9f4696b88b0244d70
|
3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 170920084
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eed3ef08c89e9a07cd3218a687a41dd717cf80833936a581ab6db0cd1f2aabdf
|
3 |
size 170920084
|
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 sha256:6fa0933e237e365bbcbd10bdc7014a011ec526d46395768542a06f4bd5bcda7b
|
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:d5c84ec0ff3c8c6aa13b25568668096db118f67ce80a9fa015a625446606f15d
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.2894105911254883,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-80",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -717,6 +717,84 @@
|
|
717 |
"eval_samples_per_second": 1.774,
|
718 |
"eval_steps_per_second": 1.774,
|
719 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
720 |
}
|
721 |
],
|
722 |
"logging_steps": 1,
|
@@ -731,7 +809,7 @@
|
|
731 |
"early_stopping_threshold": 0.0
|
732 |
},
|
733 |
"attributes": {
|
734 |
-
"early_stopping_patience_counter":
|
735 |
}
|
736 |
},
|
737 |
"TrainerControl": {
|
@@ -745,7 +823,7 @@
|
|
745 |
"attributes": {}
|
746 |
}
|
747 |
},
|
748 |
-
"total_flos":
|
749 |
"train_batch_size": 1,
|
750 |
"trial_name": null,
|
751 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.2894105911254883,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-80",
|
4 |
+
"epoch": 0.028238616307800918,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
717 |
"eval_samples_per_second": 1.774,
|
718 |
"eval_steps_per_second": 1.774,
|
719 |
"step": 90
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.025697140840098835,
|
723 |
+
"grad_norm": 0.922839343547821,
|
724 |
+
"learning_rate": 0.00018681546242521786,
|
725 |
+
"loss": 2.2968,
|
726 |
+
"step": 91
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.025979527003176843,
|
730 |
+
"grad_norm": 0.9457669258117676,
|
731 |
+
"learning_rate": 0.00018649548579446936,
|
732 |
+
"loss": 1.5159,
|
733 |
+
"step": 92
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.026261913166254855,
|
737 |
+
"grad_norm": 1.3212480545043945,
|
738 |
+
"learning_rate": 0.0001861719536730795,
|
739 |
+
"loss": 1.8084,
|
740 |
+
"step": 93
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.026544299329332863,
|
744 |
+
"grad_norm": 1.1744962930679321,
|
745 |
+
"learning_rate": 0.00018584487936018661,
|
746 |
+
"loss": 2.3983,
|
747 |
+
"step": 94
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.026826685492410872,
|
751 |
+
"grad_norm": 0.9709725379943848,
|
752 |
+
"learning_rate": 0.00018551427630053463,
|
753 |
+
"loss": 1.8034,
|
754 |
+
"step": 95
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.02710907165548888,
|
758 |
+
"grad_norm": 0.878976047039032,
|
759 |
+
"learning_rate": 0.00018518015808392045,
|
760 |
+
"loss": 1.2276,
|
761 |
+
"step": 96
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.02739145781856689,
|
765 |
+
"grad_norm": 1.220984935760498,
|
766 |
+
"learning_rate": 0.00018484253844463526,
|
767 |
+
"loss": 1.0919,
|
768 |
+
"step": 97
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.0276738439816449,
|
772 |
+
"grad_norm": 0.41714727878570557,
|
773 |
+
"learning_rate": 0.00018450143126090015,
|
774 |
+
"loss": 1.0902,
|
775 |
+
"step": 98
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.02795623014472291,
|
779 |
+
"grad_norm": 0.9148246049880981,
|
780 |
+
"learning_rate": 0.00018415685055429533,
|
781 |
+
"loss": 2.1429,
|
782 |
+
"step": 99
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.028238616307800918,
|
786 |
+
"grad_norm": 0.8029168844223022,
|
787 |
+
"learning_rate": 0.00018380881048918405,
|
788 |
+
"loss": 1.5813,
|
789 |
+
"step": 100
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.028238616307800918,
|
793 |
+
"eval_loss": 1.3071253299713135,
|
794 |
+
"eval_runtime": 421.1658,
|
795 |
+
"eval_samples_per_second": 1.771,
|
796 |
+
"eval_steps_per_second": 1.771,
|
797 |
+
"step": 100
|
798 |
}
|
799 |
],
|
800 |
"logging_steps": 1,
|
|
|
809 |
"early_stopping_threshold": 0.0
|
810 |
},
|
811 |
"attributes": {
|
812 |
+
"early_stopping_patience_counter": 2
|
813 |
}
|
814 |
},
|
815 |
"TrainerControl": {
|
|
|
823 |
"attributes": {}
|
824 |
}
|
825 |
},
|
826 |
+
"total_flos": 7.46010452164608e+16,
|
827 |
"train_batch_size": 1,
|
828 |
"trial_name": null,
|
829 |
"trial_params": null
|