TachyHealthResearch
commited on
Commit
•
63c4ca7
1
Parent(s):
b98c004
Training in progress, step 150, 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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28c450e1cbd58b94ecfd0d5841141af8b9d2f6ba3693b70255f4c2a5b4619d7e
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af750fbc05a2b5076b24d77beec26c5b1860ec8b6c3a972094231de06cde822
|
3 |
size 63350356
|
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 sha256:95dc05f6dfab536d3e64ecf5dd424669b694c67a3c5ef2d5784f1d7efa03cff3
|
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 sha256:194456d3c9e165255d5406a0f3f62973b0bede79d91784f72431350783e27ae7
|
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": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -877,13 +877,43 @@
|
|
877 |
"learning_rate": 6.802721088435375e-06,
|
878 |
"loss": 1.4445,
|
879 |
"step": 145
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
880 |
}
|
881 |
],
|
882 |
"logging_steps": 1,
|
883 |
"max_steps": 150,
|
884 |
"num_train_epochs": 1,
|
885 |
"save_steps": 5,
|
886 |
-
"total_flos": 1.
|
887 |
"trial_name": null,
|
888 |
"trial_params": null
|
889 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.06,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 150,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
877 |
"learning_rate": 6.802721088435375e-06,
|
878 |
"loss": 1.4445,
|
879 |
"step": 145
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.06,
|
883 |
+
"learning_rate": 5.4421768707483e-06,
|
884 |
+
"loss": 1.2193,
|
885 |
+
"step": 146
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.06,
|
889 |
+
"learning_rate": 4.081632653061224e-06,
|
890 |
+
"loss": 1.5606,
|
891 |
+
"step": 147
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.06,
|
895 |
+
"learning_rate": 2.72108843537415e-06,
|
896 |
+
"loss": 1.5721,
|
897 |
+
"step": 148
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.06,
|
901 |
+
"learning_rate": 1.360544217687075e-06,
|
902 |
+
"loss": 1.8318,
|
903 |
+
"step": 149
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.06,
|
907 |
+
"learning_rate": 0.0,
|
908 |
+
"loss": 1.4401,
|
909 |
+
"step": 150
|
910 |
}
|
911 |
],
|
912 |
"logging_steps": 1,
|
913 |
"max_steps": 150,
|
914 |
"num_train_epochs": 1,
|
915 |
"save_steps": 5,
|
916 |
+
"total_flos": 1.863424689143808e+16,
|
917 |
"trial_name": null,
|
918 |
"trial_params": null
|
919 |
}
|