Training in progress, step 113, 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:c529a85454a3d96a5940fa5d781d9577b35d06f3dc016844d7b8b300f297013a
|
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:ebe248069e09f4931f12d918e0d5b47cbf7e6f6c3a440eed76b31cd6eacbb695
|
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 sha256:74a8f3454c415665d0358e152faea0ef684bc7b623fa35ef64763c0af976fed2
|
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,
|
@@ -784,6 +784,20 @@
|
|
784 |
"learning_rate": 0.00019166666666666667,
|
785 |
"loss": 1.2829,
|
786 |
"step": 111
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
787 |
}
|
788 |
],
|
789 |
"logging_steps": 1,
|
@@ -803,7 +817,7 @@
|
|
803 |
"attributes": {}
|
804 |
}
|
805 |
},
|
806 |
-
"total_flos": 1.
|
807 |
"train_batch_size": 4,
|
808 |
"trial_name": null,
|
809 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3100137174211248,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 113,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
784 |
"learning_rate": 0.00019166666666666667,
|
785 |
"loss": 1.2829,
|
786 |
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.30727023319615915,
|
790 |
+
"grad_norm": 0.12115694582462311,
|
791 |
+
"learning_rate": 0.00019090909090909092,
|
792 |
+
"loss": 1.3109,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.3100137174211248,
|
797 |
+
"grad_norm": 0.12799453735351562,
|
798 |
+
"learning_rate": 0.00019015151515151517,
|
799 |
+
"loss": 1.2836,
|
800 |
+
"step": 113
|
801 |
}
|
802 |
],
|
803 |
"logging_steps": 1,
|
|
|
817 |
"attributes": {}
|
818 |
}
|
819 |
},
|
820 |
+
"total_flos": 1.4010395508772454e+17,
|
821 |
"train_batch_size": 4,
|
822 |
"trial_name": null,
|
823 |
"trial_params": null
|