Training in progress, step 90, 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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a78d831bede7dd40e477fa7694ee5041a6c2a1c4dd47884d69631517e3003db
|
3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671466706
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74f814dbc6958de56222e4762ab077120e81b798376d576addd94b33fb7cc3bf
|
3 |
size 671466706
|
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:ea1a5d23166df3ab9a48a77c1526bd281c12abab800d03cded5eed551cd4bb0c
|
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:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
|
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":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -655,6 +655,20 @@
|
|
655 |
"learning_rate": 4.025706004760932e-07,
|
656 |
"loss": 2.6286,
|
657 |
"step": 88
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
658 |
}
|
659 |
],
|
660 |
"logging_steps": 1,
|
@@ -669,12 +683,12 @@
|
|
669 |
"should_evaluate": false,
|
670 |
"should_log": false,
|
671 |
"should_save": true,
|
672 |
-
"should_training_stop":
|
673 |
},
|
674 |
"attributes": {}
|
675 |
}
|
676 |
},
|
677 |
-
"total_flos": 1.
|
678 |
"train_batch_size": 2,
|
679 |
"trial_name": null,
|
680 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0631578947368423,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
655 |
"learning_rate": 4.025706004760932e-07,
|
656 |
"loss": 2.6286,
|
657 |
"step": 88
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 3.0294736842105263,
|
661 |
+
"grad_norm": 0.3721281886100769,
|
662 |
+
"learning_rate": 1.0069334586854107e-07,
|
663 |
+
"loss": 2.1659,
|
664 |
+
"step": 89
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 3.0631578947368423,
|
668 |
+
"grad_norm": 0.2612936794757843,
|
669 |
+
"learning_rate": 0.0,
|
670 |
+
"loss": 1.8654,
|
671 |
+
"step": 90
|
672 |
}
|
673 |
],
|
674 |
"logging_steps": 1,
|
|
|
683 |
"should_evaluate": false,
|
684 |
"should_log": false,
|
685 |
"should_save": true,
|
686 |
+
"should_training_stop": true
|
687 |
},
|
688 |
"attributes": {}
|
689 |
}
|
690 |
},
|
691 |
+
"total_flos": 1.0742550511170355e+18,
|
692 |
"train_batch_size": 2,
|
693 |
"trial_name": null,
|
694 |
"trial_params": null
|