Training in progress, step 120000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893439185
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcc09d22e5596eeac7cbb0a1dabfeacc19af29a548e591c9f749208980b7916a
|
3 |
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3c3ce97bc1c8862c7db669723fd31e2c4926cda5ff7010a6c07f89d409cca1
|
3 |
size 449471589
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fc306b40ea32fc4b974d92fa4436f6126d03d93634b99c4944393049e4dd34d
|
3 |
+
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83b1dc502294b82568367d2e77a4231f6fb11b7296d845de6be2991e1953c467
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90c7dcc243e1aa80b2e25ba58bbf11ac2e612d08701ac3bc19fe812cf11394f0
|
3 |
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b63f502697a67e82fe85208c9b5cb87051cc2490893eb283cf394fd4c0f8586c
|
3 |
+
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27556e6e847d06ad2f934e5a134bda54baf3ade1f4eea8c1e651de3a5e1bb425
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -820,11 +820,85 @@
|
|
820 |
"eval_samples_per_second": 984.91,
|
821 |
"eval_steps_per_second": 15.759,
|
822 |
"step": 110000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
823 |
}
|
824 |
],
|
825 |
"max_steps": 1000000,
|
826 |
"num_train_epochs": 16,
|
827 |
-
"total_flos":
|
828 |
"trial_name": null,
|
829 |
"trial_params": null
|
830 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.8324247560584543,
|
5 |
+
"global_step": 120000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
820 |
"eval_samples_per_second": 984.91,
|
821 |
"eval_steps_per_second": 15.759,
|
822 |
"step": 110000
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 1.69,
|
826 |
+
"learning_rate": 0.00014858059266190327,
|
827 |
+
"loss": 0.3552,
|
828 |
+
"step": 111000
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 1.71,
|
832 |
+
"learning_rate": 0.00014853383772619612,
|
833 |
+
"loss": 0.3544,
|
834 |
+
"step": 112000
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 1.73,
|
838 |
+
"learning_rate": 0.00014848633331541967,
|
839 |
+
"loss": 0.3537,
|
840 |
+
"step": 113000
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 1.74,
|
844 |
+
"learning_rate": 0.0001484380799490746,
|
845 |
+
"loss": 0.3524,
|
846 |
+
"step": 114000
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 1.76,
|
850 |
+
"learning_rate": 0.00014838907815485194,
|
851 |
+
"loss": 0.3519,
|
852 |
+
"step": 115000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 1.76,
|
856 |
+
"eval_runtime": 1.003,
|
857 |
+
"eval_samples_per_second": 997.001,
|
858 |
+
"eval_steps_per_second": 15.952,
|
859 |
+
"step": 115000
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 1.77,
|
863 |
+
"learning_rate": 0.00014833932846862748,
|
864 |
+
"loss": 0.3511,
|
865 |
+
"step": 116000
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 1.79,
|
869 |
+
"learning_rate": 0.00014828883143445582,
|
870 |
+
"loss": 0.3502,
|
871 |
+
"step": 117000
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 1.8,
|
875 |
+
"learning_rate": 0.0001482375876045644,
|
876 |
+
"loss": 0.3493,
|
877 |
+
"step": 118000
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 1.82,
|
881 |
+
"learning_rate": 0.0001481855975393476,
|
882 |
+
"loss": 0.3489,
|
883 |
+
"step": 119000
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 1.83,
|
887 |
+
"learning_rate": 0.0001481328618073604,
|
888 |
+
"loss": 0.3482,
|
889 |
+
"step": 120000
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 1.83,
|
893 |
+
"eval_runtime": 1.0596,
|
894 |
+
"eval_samples_per_second": 943.744,
|
895 |
+
"eval_steps_per_second": 15.1,
|
896 |
+
"step": 120000
|
897 |
}
|
898 |
],
|
899 |
"max_steps": 1000000,
|
900 |
"num_train_epochs": 16,
|
901 |
+
"total_flos": 8.41202475296017e+21,
|
902 |
"trial_name": null,
|
903 |
"trial_params": null
|
904 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3c3ce97bc1c8862c7db669723fd31e2c4926cda5ff7010a6c07f89d409cca1
|
3 |
size 449471589
|