TachyHealthResearch
commited on
Commit
•
2ee944d
1
Parent(s):
ae9043c
Training in progress, step 140, 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 65309632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f167e9c776981f1c22ea8e02bd3d6330f283765cdc95160c57bf1aa04b11fc3
|
3 |
size 65309632
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 32995412
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1a24463f21742aa34fbe27e76072eddf69fe74138488e58902342a74fbf36c7
|
3 |
size 32995412
|
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 sha256:7f0cb6895b198d17891374cd93d94b45d251baef41691c82d99fe270719eae2d
|
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 sha256:9702192071987640411db8cd497f9de57450f22a9586d9cce5affbc116fe7983
|
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,
|
@@ -787,13 +787,73 @@
|
|
787 |
"learning_rate": 2.7586206896551727e-05,
|
788 |
"loss": 2.6004,
|
789 |
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
790 |
}
|
791 |
],
|
792 |
"logging_steps": 1,
|
793 |
"max_steps": 150,
|
794 |
"num_train_epochs": 1,
|
795 |
"save_steps": 10,
|
796 |
-
"total_flos":
|
797 |
"trial_name": null,
|
798 |
"trial_params": null
|
799 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.056,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 140,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
787 |
"learning_rate": 2.7586206896551727e-05,
|
788 |
"loss": 2.6004,
|
789 |
"step": 130
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.05,
|
793 |
+
"learning_rate": 2.620689655172414e-05,
|
794 |
+
"loss": 2.0711,
|
795 |
+
"step": 131
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.05,
|
799 |
+
"learning_rate": 2.4827586206896553e-05,
|
800 |
+
"loss": 1.3493,
|
801 |
+
"step": 132
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.05,
|
805 |
+
"learning_rate": 2.3448275862068967e-05,
|
806 |
+
"loss": 1.5959,
|
807 |
+
"step": 133
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.05,
|
811 |
+
"learning_rate": 2.206896551724138e-05,
|
812 |
+
"loss": 1.8896,
|
813 |
+
"step": 134
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.05,
|
817 |
+
"learning_rate": 2.0689655172413793e-05,
|
818 |
+
"loss": 2.2874,
|
819 |
+
"step": 135
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.05,
|
823 |
+
"learning_rate": 1.9310344827586207e-05,
|
824 |
+
"loss": 2.1101,
|
825 |
+
"step": 136
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.05,
|
829 |
+
"learning_rate": 1.793103448275862e-05,
|
830 |
+
"loss": 1.9485,
|
831 |
+
"step": 137
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.06,
|
835 |
+
"learning_rate": 1.6551724137931037e-05,
|
836 |
+
"loss": 1.7614,
|
837 |
+
"step": 138
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.06,
|
841 |
+
"learning_rate": 1.5172413793103448e-05,
|
842 |
+
"loss": 2.0501,
|
843 |
+
"step": 139
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.06,
|
847 |
+
"learning_rate": 1.3793103448275863e-05,
|
848 |
+
"loss": 2.1258,
|
849 |
+
"step": 140
|
850 |
}
|
851 |
],
|
852 |
"logging_steps": 1,
|
853 |
"max_steps": 150,
|
854 |
"num_train_epochs": 1,
|
855 |
"save_steps": 10,
|
856 |
+
"total_flos": 7472731954317312.0,
|
857 |
"trial_name": null,
|
858 |
"trial_params": null
|
859 |
}
|