Commit
•
ded3105
1
Parent(s):
45f998c
Training in progress, step 5500, 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 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ff54a2686f1521c58b6326970f7c5b97a763b773d8cd479cdfad1ec0c3cac5
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d03e40c8e5adedc33fcd43006e3bcf12cc5a6bb8492a828e2befbf798eee8cb0
|
3 |
size 1155772233
|
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 sha256:11239057f5c6fb1530932439ec947450720ad110d35f7557e8d43f46512ee240
|
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 sha256:62d5b182b6f9100f7e6ff34153d4c2b85b65abf8d0d73f828512d9772061b995
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.39598318934440613,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -787,6 +787,84 @@
|
|
787 |
"eval_samples_per_second": 25.915,
|
788 |
"eval_steps_per_second": 3.311,
|
789 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 50,
|
@@ -806,7 +884,7 @@
|
|
806 |
"attributes": {}
|
807 |
}
|
808 |
},
|
809 |
-
"total_flos": 5.
|
810 |
"train_batch_size": 16,
|
811 |
"trial_name": null,
|
812 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.39598318934440613,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
|
4 |
+
"epoch": 217.82178217821783,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
787 |
"eval_samples_per_second": 25.915,
|
788 |
"eval_steps_per_second": 3.311,
|
789 |
"step": 5000
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 200.0,
|
793 |
+
"grad_norm": 1.864687442779541,
|
794 |
+
"learning_rate": 4.9183333333333334e-05,
|
795 |
+
"loss": 0.3484,
|
796 |
+
"step": 5050
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 201.98019801980197,
|
800 |
+
"grad_norm": 1.406449556350708,
|
801 |
+
"learning_rate": 4.835e-05,
|
802 |
+
"loss": 0.345,
|
803 |
+
"step": 5100
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 203.96039603960395,
|
807 |
+
"grad_norm": 0.7522682547569275,
|
808 |
+
"learning_rate": 4.751666666666667e-05,
|
809 |
+
"loss": 0.3468,
|
810 |
+
"step": 5150
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 205.94059405940595,
|
814 |
+
"grad_norm": 0.5859296321868896,
|
815 |
+
"learning_rate": 4.6683333333333334e-05,
|
816 |
+
"loss": 0.3432,
|
817 |
+
"step": 5200
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 207.92079207920793,
|
821 |
+
"grad_norm": 0.6594001054763794,
|
822 |
+
"learning_rate": 4.585e-05,
|
823 |
+
"loss": 0.3417,
|
824 |
+
"step": 5250
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 209.9009900990099,
|
828 |
+
"grad_norm": 1.0125696659088135,
|
829 |
+
"learning_rate": 4.5016666666666665e-05,
|
830 |
+
"loss": 0.3428,
|
831 |
+
"step": 5300
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 211.88118811881188,
|
835 |
+
"grad_norm": 0.8519133925437927,
|
836 |
+
"learning_rate": 4.4183333333333334e-05,
|
837 |
+
"loss": 0.3424,
|
838 |
+
"step": 5350
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 213.86138613861385,
|
842 |
+
"grad_norm": 0.8138070106506348,
|
843 |
+
"learning_rate": 4.335e-05,
|
844 |
+
"loss": 0.3411,
|
845 |
+
"step": 5400
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 215.84158415841586,
|
849 |
+
"grad_norm": 1.7046844959259033,
|
850 |
+
"learning_rate": 4.251666666666667e-05,
|
851 |
+
"loss": 0.3418,
|
852 |
+
"step": 5450
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 217.82178217821783,
|
856 |
+
"grad_norm": 0.8346728682518005,
|
857 |
+
"learning_rate": 4.1683333333333335e-05,
|
858 |
+
"loss": 0.3439,
|
859 |
+
"step": 5500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 217.82178217821783,
|
863 |
+
"eval_loss": 0.40201354026794434,
|
864 |
+
"eval_runtime": 7.7869,
|
865 |
+
"eval_samples_per_second": 23.116,
|
866 |
+
"eval_steps_per_second": 2.954,
|
867 |
+
"step": 5500
|
868 |
}
|
869 |
],
|
870 |
"logging_steps": 50,
|
|
|
884 |
"attributes": {}
|
885 |
}
|
886 |
},
|
887 |
+
"total_flos": 5.943523141225296e+16,
|
888 |
"train_batch_size": 16,
|
889 |
"trial_name": null,
|
890 |
"trial_params": null
|