Training in progress, step 115, 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 sha256:7bdbb740496dc2a7f3c0f6f02d269d15e42820dee4870aed7c52aa1bfd807fd2
|
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 sha256:19aea021c17d22587f9f50dc0bd30b3284a28d1ab85db70a8c705c5ef04b8d19
|
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:f9741594e204ffb908586b8ab5263be1fd7e41110b9026fc1281a70d1b1b6557
|
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,
|
@@ -798,6 +798,20 @@
|
|
798 |
"learning_rate": 0.00019015151515151517,
|
799 |
"loss": 1.2836,
|
800 |
"step": 113
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
801 |
}
|
802 |
],
|
803 |
"logging_steps": 1,
|
@@ -817,7 +831,7 @@
|
|
817 |
"attributes": {}
|
818 |
}
|
819 |
},
|
820 |
-
"total_flos": 1.
|
821 |
"train_batch_size": 4,
|
822 |
"trial_name": null,
|
823 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.31550068587105623,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 115,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
798 |
"learning_rate": 0.00019015151515151517,
|
799 |
"loss": 1.2836,
|
800 |
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.31275720164609055,
|
804 |
+
"grad_norm": 0.1297687143087387,
|
805 |
+
"learning_rate": 0.00018939393939393942,
|
806 |
+
"loss": 1.2813,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.31550068587105623,
|
811 |
+
"grad_norm": 0.13718412816524506,
|
812 |
+
"learning_rate": 0.00018863636363636364,
|
813 |
+
"loss": 1.3138,
|
814 |
+
"step": 115
|
815 |
}
|
816 |
],
|
817 |
"logging_steps": 1,
|
|
|
831 |
"attributes": {}
|
832 |
}
|
833 |
},
|
834 |
+
"total_flos": 1.4257615970761114e+17,
|
835 |
"train_batch_size": 4,
|
836 |
"trial_name": null,
|
837 |
"trial_params": null
|