Training in progress, step 84, 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:f243f6b3616c8433386fc88ddf6327a577ba6287c4ed295e830c228fda35beb6
|
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:e4f72706d984d21bee0f467c65e8399002645accd78908dfaafc210e8643a0d2
|
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 sha256:55d1c8adee9796452e76469ace59653b3f2ebccea698756c2275e8b6cf74ba43
|
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,
|
@@ -574,6 +574,27 @@
|
|
574 |
"learning_rate": 0.000162,
|
575 |
"loss": 1.3322,
|
576 |
"step": 81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
577 |
}
|
578 |
],
|
579 |
"logging_steps": 1,
|
@@ -593,7 +614,7 @@
|
|
593 |
"attributes": {}
|
594 |
}
|
595 |
},
|
596 |
-
"total_flos": 1.
|
597 |
"train_batch_size": 4,
|
598 |
"trial_name": null,
|
599 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.23045267489711935,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 84,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
574 |
"learning_rate": 0.000162,
|
575 |
"loss": 1.3322,
|
576 |
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.22496570644718794,
|
580 |
+
"grad_norm": 0.09528470784425735,
|
581 |
+
"learning_rate": 0.000164,
|
582 |
+
"loss": 1.2384,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.22770919067215364,
|
587 |
+
"grad_norm": 0.0997876301407814,
|
588 |
+
"learning_rate": 0.000166,
|
589 |
+
"loss": 1.3646,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.23045267489711935,
|
594 |
+
"grad_norm": 0.09820306301116943,
|
595 |
+
"learning_rate": 0.000168,
|
596 |
+
"loss": 1.1982,
|
597 |
+
"step": 84
|
598 |
}
|
599 |
],
|
600 |
"logging_steps": 1,
|
|
|
614 |
"attributes": {}
|
615 |
}
|
616 |
},
|
617 |
+
"total_flos": 1.0405766029849805e+17,
|
618 |
"train_batch_size": 4,
|
619 |
"trial_name": null,
|
620 |
"trial_params": null
|