Training in progress, step 127, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a70e7d8dd278744b60ca4159ecfff7762940f147790373a743f0ef6441820c1
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7292f7962f2d3bf69af5bc3180b16972a7cd2fba11d078322db75824335d7c2c
|
3 |
size 37430836
|
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 sha256:71986891b164cad93c3400a2602acded2ea76001e341a5249025bbfc11b34339
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
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,
|
@@ -875,6 +875,27 @@
|
|
875 |
"learning_rate": 0.00018181818181818183,
|
876 |
"loss": 1.1856,
|
877 |
"step": 124
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
878 |
}
|
879 |
],
|
880 |
"logging_steps": 1,
|
@@ -894,7 +915,7 @@
|
|
894 |
"attributes": {}
|
895 |
}
|
896 |
},
|
897 |
-
"total_flos": 1.
|
898 |
"train_batch_size": 4,
|
899 |
"trial_name": null,
|
900 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3484224965706447,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 127,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
875 |
"learning_rate": 0.00018181818181818183,
|
876 |
"loss": 1.1856,
|
877 |
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.3429355281207133,
|
881 |
+
"grad_norm": 0.13697242736816406,
|
882 |
+
"learning_rate": 0.00018106060606060606,
|
883 |
+
"loss": 1.3235,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.345679012345679,
|
888 |
+
"grad_norm": 0.15304319560527802,
|
889 |
+
"learning_rate": 0.0001803030303030303,
|
890 |
+
"loss": 1.2457,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.3484224965706447,
|
895 |
+
"grad_norm": 0.1399148851633072,
|
896 |
+
"learning_rate": 0.00017954545454545456,
|
897 |
+
"loss": 1.2907,
|
898 |
+
"step": 127
|
899 |
}
|
900 |
],
|
901 |
"logging_steps": 1,
|
|
|
915 |
"attributes": {}
|
916 |
}
|
917 |
},
|
918 |
+
"total_flos": 1.5768949238325658e+17,
|
919 |
"train_batch_size": 4,
|
920 |
"trial_name": null,
|
921 |
"trial_params": null
|