Commit
•
daa9427
1
Parent(s):
f1f3e0a
Training in progress, step 6000, 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 sha256:8d2b3399969fb74960ee01ffd897aef3b9bf5e7209f6f0ea877a12153f361408
|
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 sha256:7746ae2b28b16ee5e4dc0d43c7ed500663b9d82298a7c15d1500a39d65d9d274
|
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 sha256:8b78a35397517539ceb5abaec4c078472043c61c90e9313f43ee762be5908798
|
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 sha256:5cc3a4f205edd4add2b834d8b0c7057cd9c53044c257143116c01897f3cb6067
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-
|
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,
|
@@ -865,6 +865,84 @@
|
|
865 |
"eval_samples_per_second": 31.057,
|
866 |
"eval_steps_per_second": 3.885,
|
867 |
"step": 5500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
868 |
}
|
869 |
],
|
870 |
"logging_steps": 50,
|
@@ -884,7 +962,7 @@
|
|
884 |
"attributes": {}
|
885 |
}
|
886 |
},
|
887 |
-
"total_flos":
|
888 |
"train_batch_size": 16,
|
889 |
"trial_name": null,
|
890 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3189197778701782,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-6000",
|
4 |
+
"epoch": 10.052356020942408,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 6000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
865 |
"eval_samples_per_second": 31.057,
|
866 |
"eval_steps_per_second": 3.885,
|
867 |
"step": 5500
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 9.298429319371728,
|
871 |
+
"grad_norm": 2.127049446105957,
|
872 |
+
"learning_rate": 4.086666666666667e-05,
|
873 |
+
"loss": 0.3547,
|
874 |
+
"step": 5550
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 9.38219895287958,
|
878 |
+
"grad_norm": 1.5531483888626099,
|
879 |
+
"learning_rate": 4.0033333333333335e-05,
|
880 |
+
"loss": 0.3576,
|
881 |
+
"step": 5600
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 9.465968586387435,
|
885 |
+
"grad_norm": 1.5712753534317017,
|
886 |
+
"learning_rate": 3.9200000000000004e-05,
|
887 |
+
"loss": 0.3492,
|
888 |
+
"step": 5650
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 9.549738219895287,
|
892 |
+
"grad_norm": 1.1668370962142944,
|
893 |
+
"learning_rate": 3.8366666666666666e-05,
|
894 |
+
"loss": 0.3529,
|
895 |
+
"step": 5700
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 9.633507853403142,
|
899 |
+
"grad_norm": 1.1639858484268188,
|
900 |
+
"learning_rate": 3.7533333333333335e-05,
|
901 |
+
"loss": 0.3526,
|
902 |
+
"step": 5750
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 9.717277486910994,
|
906 |
+
"grad_norm": 1.4188268184661865,
|
907 |
+
"learning_rate": 3.6700000000000004e-05,
|
908 |
+
"loss": 0.3527,
|
909 |
+
"step": 5800
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 9.801047120418849,
|
913 |
+
"grad_norm": 1.8606890439987183,
|
914 |
+
"learning_rate": 3.586666666666667e-05,
|
915 |
+
"loss": 0.3517,
|
916 |
+
"step": 5850
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 9.884816753926701,
|
920 |
+
"grad_norm": 1.2933155298233032,
|
921 |
+
"learning_rate": 3.5033333333333336e-05,
|
922 |
+
"loss": 0.3463,
|
923 |
+
"step": 5900
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 9.968586387434556,
|
927 |
+
"grad_norm": 1.4728389978408813,
|
928 |
+
"learning_rate": 3.4200000000000005e-05,
|
929 |
+
"loss": 0.3505,
|
930 |
+
"step": 5950
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 10.052356020942408,
|
934 |
+
"grad_norm": 1.6055335998535156,
|
935 |
+
"learning_rate": 3.336666666666667e-05,
|
936 |
+
"loss": 0.3471,
|
937 |
+
"step": 6000
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 10.052356020942408,
|
941 |
+
"eval_loss": 0.3189197778701782,
|
942 |
+
"eval_runtime": 273.3525,
|
943 |
+
"eval_samples_per_second": 31.055,
|
944 |
+
"eval_steps_per_second": 3.885,
|
945 |
+
"step": 6000
|
946 |
}
|
947 |
],
|
948 |
"logging_steps": 50,
|
|
|
962 |
"attributes": {}
|
963 |
}
|
964 |
},
|
965 |
+
"total_flos": 1.0748974547355264e+17,
|
966 |
"train_batch_size": 16,
|
967 |
"trial_name": null,
|
968 |
"trial_params": null
|