Training in progress, step 5130, 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 25271744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0ff0f17e9477554b95d7b8b9645bf8881d7d66d8bb60aa0203c8588ec6b7a65
|
3 |
size 25271744
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13685836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:646a634e95194ed4bb6e177b3c72ff5ec73777bb24cbd8064bdcb3dfe4244cc4
|
3 |
size 13685836
|
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:bdf2deb0bfd772b0af3d54bfa96b905de9797cd61d86ad22f3775dbbd3b6e070
|
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 sha256:53b96d7c5488649967d63309339d02de27cab5657995c3fb8c7e46217d2d189b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.700386643409729,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-4788",
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 114,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -675,6 +675,21 @@
|
|
675 |
"eval_samples_per_second": 88.057,
|
676 |
"eval_steps_per_second": 2.752,
|
677 |
"step": 5016
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
678 |
}
|
679 |
],
|
680 |
"logging_steps": 114,
|
@@ -689,7 +704,7 @@
|
|
689 |
"early_stopping_threshold": 0.0
|
690 |
},
|
691 |
"attributes": {
|
692 |
-
"early_stopping_patience_counter":
|
693 |
}
|
694 |
},
|
695 |
"TrainerControl": {
|
@@ -698,12 +713,12 @@
|
|
698 |
"should_evaluate": false,
|
699 |
"should_log": false,
|
700 |
"should_save": true,
|
701 |
-
"should_training_stop":
|
702 |
},
|
703 |
"attributes": {}
|
704 |
}
|
705 |
},
|
706 |
-
"total_flos": 9.
|
707 |
"train_batch_size": 16,
|
708 |
"trial_name": null,
|
709 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.700386643409729,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-4788",
|
4 |
+
"epoch": 2.14330478378943,
|
5 |
"eval_steps": 114,
|
6 |
+
"global_step": 5130,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
675 |
"eval_samples_per_second": 88.057,
|
676 |
"eval_steps_per_second": 2.752,
|
677 |
"step": 5016
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 2.14330478378943,
|
681 |
+
"grad_norm": 0.4279311001300812,
|
682 |
+
"learning_rate": 0.00039956372993929837,
|
683 |
+
"loss": 0.6282,
|
684 |
+
"step": 5130
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 2.14330478378943,
|
688 |
+
"eval_loss": 0.7085138559341431,
|
689 |
+
"eval_runtime": 46.1621,
|
690 |
+
"eval_samples_per_second": 87.323,
|
691 |
+
"eval_steps_per_second": 2.73,
|
692 |
+
"step": 5130
|
693 |
}
|
694 |
],
|
695 |
"logging_steps": 114,
|
|
|
704 |
"early_stopping_threshold": 0.0
|
705 |
},
|
706 |
"attributes": {
|
707 |
+
"early_stopping_patience_counter": 3
|
708 |
}
|
709 |
},
|
710 |
"TrainerControl": {
|
|
|
713 |
"should_evaluate": false,
|
714 |
"should_log": false,
|
715 |
"should_save": true,
|
716 |
+
"should_training_stop": true
|
717 |
},
|
718 |
"attributes": {}
|
719 |
}
|
720 |
},
|
721 |
+
"total_flos": 9.78979848758231e+17,
|
722 |
"train_batch_size": 16,
|
723 |
"trial_name": null,
|
724 |
"trial_params": null
|