Commit
•
15f7cf5
1
Parent(s):
d39f040
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:a4dfbf5d6e4b1919fd21b2c53d7a723a096c281b4d69231fc5d376272ecf657a
|
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:d6d3d7872d4b541c4fe16c783304a15ec781a39e428ef39089562b85553731ff
|
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:a6b70c749d9fca7368a712c6e25aa110afedb1cf4d0c2fe8a0417ce2389e1f86
|
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:ea4cdeda39ba2136e592d70ee5cca1961eef743b3307c81d32a1dfebf7fdaaa7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.4069381058216095,
|
3 |
"best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-5500",
|
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": 11.867,
|
866 |
"eval_steps_per_second": 1.548,
|
867 |
"step": 5500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
868 |
}
|
869 |
],
|
870 |
"logging_steps": 50,
|
@@ -884,7 +962,7 @@
|
|
884 |
"attributes": {}
|
885 |
}
|
886 |
},
|
887 |
-
"total_flos":
|
888 |
"train_batch_size": 32,
|
889 |
"trial_name": null,
|
890 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.4069381058216095,
|
3 |
"best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-5500",
|
4 |
+
"epoch": 260.8695652173913,
|
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": 11.867,
|
866 |
"eval_steps_per_second": 1.548,
|
867 |
"step": 5500
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 241.30434782608697,
|
871 |
+
"grad_norm": 0.866113007068634,
|
872 |
+
"learning_rate": 4.086666666666667e-06,
|
873 |
+
"loss": 0.4117,
|
874 |
+
"step": 5550
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 243.47826086956522,
|
878 |
+
"grad_norm": 0.8896365165710449,
|
879 |
+
"learning_rate": 4.003333333333334e-06,
|
880 |
+
"loss": 0.4161,
|
881 |
+
"step": 5600
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 245.65217391304347,
|
885 |
+
"grad_norm": 0.8311805129051208,
|
886 |
+
"learning_rate": 3.920000000000001e-06,
|
887 |
+
"loss": 0.4094,
|
888 |
+
"step": 5650
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 247.82608695652175,
|
892 |
+
"grad_norm": 1.686919927597046,
|
893 |
+
"learning_rate": 3.836666666666667e-06,
|
894 |
+
"loss": 0.4128,
|
895 |
+
"step": 5700
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 250.0,
|
899 |
+
"grad_norm": 1.9034643173217773,
|
900 |
+
"learning_rate": 3.753333333333334e-06,
|
901 |
+
"loss": 0.4143,
|
902 |
+
"step": 5750
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 252.17391304347825,
|
906 |
+
"grad_norm": 0.8296219706535339,
|
907 |
+
"learning_rate": 3.6700000000000004e-06,
|
908 |
+
"loss": 0.4123,
|
909 |
+
"step": 5800
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 254.34782608695653,
|
913 |
+
"grad_norm": 0.6855341792106628,
|
914 |
+
"learning_rate": 3.5866666666666673e-06,
|
915 |
+
"loss": 0.4099,
|
916 |
+
"step": 5850
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 256.5217391304348,
|
920 |
+
"grad_norm": 1.0125635862350464,
|
921 |
+
"learning_rate": 3.5033333333333334e-06,
|
922 |
+
"loss": 0.4104,
|
923 |
+
"step": 5900
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 258.69565217391306,
|
927 |
+
"grad_norm": 0.8589877486228943,
|
928 |
+
"learning_rate": 3.4200000000000007e-06,
|
929 |
+
"loss": 0.4069,
|
930 |
+
"step": 5950
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 260.8695652173913,
|
934 |
+
"grad_norm": 0.9898667931556702,
|
935 |
+
"learning_rate": 3.3366666666666668e-06,
|
936 |
+
"loss": 0.4113,
|
937 |
+
"step": 6000
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 260.8695652173913,
|
941 |
+
"eval_loss": 0.40804117918014526,
|
942 |
+
"eval_runtime": 13.2074,
|
943 |
+
"eval_samples_per_second": 12.19,
|
944 |
+
"eval_steps_per_second": 1.59,
|
945 |
+
"step": 6000
|
946 |
}
|
947 |
],
|
948 |
"logging_steps": 50,
|
|
|
962 |
"attributes": {}
|
963 |
}
|
964 |
},
|
965 |
+
"total_flos": 7.271570164893091e+16,
|
966 |
"train_batch_size": 32,
|
967 |
"trial_name": null,
|
968 |
"trial_params": null
|