Training in progress, step 111, 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 sha256:462e144bcab7491a70358c1f4a875b6c27d67b6cc92caed5a4e5742768be49ed
|
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 sha256:83c6c05071edf86108c1c7cf96712e1797e3856536617579a4fd809cd5d683ff
|
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 sha256:52d52fc2543a3ca6e1f42845f53001bf363359931a890c3cf7363ae9b686adbc
|
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,
|
@@ -777,6 +777,13 @@
|
|
777 |
"learning_rate": 0.00019242424242424245,
|
778 |
"loss": 1.2051,
|
779 |
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
780 |
}
|
781 |
],
|
782 |
"logging_steps": 1,
|
@@ -796,7 +803,7 @@
|
|
796 |
"attributes": {}
|
797 |
}
|
798 |
},
|
799 |
-
"total_flos": 1.
|
800 |
"train_batch_size": 4,
|
801 |
"trial_name": null,
|
802 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3045267489711934,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 111,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
777 |
"learning_rate": 0.00019242424242424245,
|
778 |
"loss": 1.2051,
|
779 |
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.3045267489711934,
|
783 |
+
"grad_norm": 0.15397988259792328,
|
784 |
+
"learning_rate": 0.00019166666666666667,
|
785 |
+
"loss": 1.2829,
|
786 |
+
"step": 111
|
787 |
}
|
788 |
],
|
789 |
"logging_steps": 1,
|
|
|
803 |
"attributes": {}
|
804 |
}
|
805 |
},
|
806 |
+
"total_flos": 1.3736075613985997e+17,
|
807 |
"train_batch_size": 4,
|
808 |
"trial_name": null,
|
809 |
"trial_params": null
|