Training in progress, step 100, 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 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4326d9e9cd7df7709958391360f637eb41dd4ec82b9fcd33d76de9b73df7a90d
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2284ed33f74c42129e7cc27ae7973159bb5ba902f37e9a26670d30a63663a39
|
3 |
size 640009682
|
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:d29fb71ba6ec0bce34883a9064209516e4805d8e320390dc35f39e3766ac3d49
|
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 sha256:5416093c744b622c4436f38b8545546a70241fb2d36e53a533c7ae67d7ced8b6
|
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": 2.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -716,6 +716,21 @@
|
|
716 |
"learning_rate": 5.7822281945782424e-08,
|
717 |
"loss": 23.99,
|
718 |
"step": 99
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
719 |
}
|
720 |
],
|
721 |
"logging_steps": 1,
|
@@ -730,12 +745,12 @@
|
|
730 |
"should_evaluate": false,
|
731 |
"should_log": false,
|
732 |
"should_save": true,
|
733 |
-
"should_training_stop":
|
734 |
},
|
735 |
"attributes": {}
|
736 |
}
|
737 |
},
|
738 |
-
"total_flos": 5.
|
739 |
"train_batch_size": 2,
|
740 |
"trial_name": null,
|
741 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.151983860121049,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
716 |
"learning_rate": 5.7822281945782424e-08,
|
717 |
"loss": 23.99,
|
718 |
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.151983860121049,
|
722 |
+
"grad_norm": 24.13272476196289,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 21.7676,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.151983860121049,
|
729 |
+
"eval_loss": 0.7184841632843018,
|
730 |
+
"eval_runtime": 26.5292,
|
731 |
+
"eval_samples_per_second": 5.918,
|
732 |
+
"eval_steps_per_second": 2.978,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
745 |
"should_evaluate": false,
|
746 |
"should_log": false,
|
747 |
"should_save": true,
|
748 |
+
"should_training_stop": true
|
749 |
},
|
750 |
"attributes": {}
|
751 |
}
|
752 |
},
|
753 |
+
"total_flos": 5.259156315439104e+17,
|
754 |
"train_batch_size": 2,
|
755 |
"trial_name": null,
|
756 |
"trial_params": null
|