Training in progress, step 119, 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:fef3f8baa4134cb9cddabaa47986a147a59c574a1cb55120e9f93e69d20564de
|
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:bbdff3376536518012fa9b5bc0d5250d64268e0a5a9be206e1e77ddc4bb9055c
|
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 sha256:05f0eb4129a1d19a29c7f0816f6285669724c1288045b3023451ea705da25d8a
|
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,
|
@@ -826,6 +826,20 @@
|
|
826 |
"learning_rate": 0.00018712121212121212,
|
827 |
"loss": 1.3258,
|
828 |
"step": 117
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
829 |
}
|
830 |
],
|
831 |
"logging_steps": 1,
|
@@ -845,7 +859,7 @@
|
|
845 |
"attributes": {}
|
846 |
}
|
847 |
},
|
848 |
-
"total_flos": 1.
|
849 |
"train_batch_size": 4,
|
850 |
"trial_name": null,
|
851 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.32647462277091904,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 119,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
826 |
"learning_rate": 0.00018712121212121212,
|
827 |
"loss": 1.3258,
|
828 |
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.32373113854595337,
|
832 |
+
"grad_norm": 0.13772045075893402,
|
833 |
+
"learning_rate": 0.00018636363636363636,
|
834 |
+
"loss": 1.3305,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.32647462277091904,
|
839 |
+
"grad_norm": 0.1165667474269867,
|
840 |
+
"learning_rate": 0.00018560606060606061,
|
841 |
+
"loss": 1.2473,
|
842 |
+
"step": 119
|
843 |
}
|
844 |
],
|
845 |
"logging_steps": 1,
|
|
|
859 |
"attributes": {}
|
860 |
}
|
861 |
},
|
862 |
+
"total_flos": 1.477261017235292e+17,
|
863 |
"train_batch_size": 4,
|
864 |
"trial_name": null,
|
865 |
"trial_params": null
|