mikhail-panzo
commited on
Commit
•
eabb90b
1
Parent(s):
1596c6a
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:fb514424646e7839682dd9dae8b997e057d871af06a5e7e929271aaaa2e7c88d
|
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 sha256:4fb4cccce2cf2fb4228373ebd75bc513ed9c699a9a015d27c99253ddaeab739f
|
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:cdc16f96a129b2f8ebddb713f251b55486ac014357ce4aedef1d542306c34e74
|
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_le5_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": 32.812,
|
866 |
"eval_steps_per_second": 4.105,
|
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": 0.3696598410606384,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/zlm_b128_le5_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": 32.812,
|
866 |
"eval_steps_per_second": 4.105,
|
867 |
"step": 5500
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 9.298429319371728,
|
871 |
+
"grad_norm": 1.0570714473724365,
|
872 |
+
"learning_rate": 4.088333333333334e-06,
|
873 |
+
"loss": 0.4144,
|
874 |
+
"step": 5550
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 9.38219895287958,
|
878 |
+
"grad_norm": 1.1278653144836426,
|
879 |
+
"learning_rate": 4.005000000000001e-06,
|
880 |
+
"loss": 0.4154,
|
881 |
+
"step": 5600
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 9.465968586387435,
|
885 |
+
"grad_norm": 5.811945915222168,
|
886 |
+
"learning_rate": 3.921666666666667e-06,
|
887 |
+
"loss": 0.4085,
|
888 |
+
"step": 5650
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 9.549738219895287,
|
892 |
+
"grad_norm": 1.6973522901535034,
|
893 |
+
"learning_rate": 3.8383333333333336e-06,
|
894 |
+
"loss": 0.4133,
|
895 |
+
"step": 5700
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 9.633507853403142,
|
899 |
+
"grad_norm": 1.209333062171936,
|
900 |
+
"learning_rate": 3.7550000000000005e-06,
|
901 |
+
"loss": 0.4123,
|
902 |
+
"step": 5750
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 9.717277486910994,
|
906 |
+
"grad_norm": 3.592991590499878,
|
907 |
+
"learning_rate": 3.6716666666666665e-06,
|
908 |
+
"loss": 0.4126,
|
909 |
+
"step": 5800
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 9.801047120418849,
|
913 |
+
"grad_norm": 1.152239203453064,
|
914 |
+
"learning_rate": 3.588333333333334e-06,
|
915 |
+
"loss": 0.4115,
|
916 |
+
"step": 5850
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 9.884816753926701,
|
920 |
+
"grad_norm": 1.6118751764297485,
|
921 |
+
"learning_rate": 3.505e-06,
|
922 |
+
"loss": 0.4036,
|
923 |
+
"step": 5900
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 9.968586387434556,
|
927 |
+
"grad_norm": 1.4384329319000244,
|
928 |
+
"learning_rate": 3.4216666666666672e-06,
|
929 |
+
"loss": 0.4103,
|
930 |
+
"step": 5950
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 10.052356020942408,
|
934 |
+
"grad_norm": 1.447549819946289,
|
935 |
+
"learning_rate": 3.3383333333333333e-06,
|
936 |
+
"loss": 0.4056,
|
937 |
+
"step": 6000
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 10.052356020942408,
|
941 |
+
"eval_loss": 0.3696598410606384,
|
942 |
+
"eval_runtime": 256.5857,
|
943 |
+
"eval_samples_per_second": 33.084,
|
944 |
+
"eval_steps_per_second": 4.139,
|
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
|