DuongTrongChi
commited on
Commit
•
b664cb2
1
Parent(s):
dd5d6da
Training in progress, step 83, 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 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c997ba06eb3c43b4beeaddc7da4021790886b44b0d7da5f2d90a4488a82d9d66
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50675156
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90e5a5fa2804c3f250c6b3046be48e9a28dc91a2bd321a4a53cebc3472ff01ca
|
3 |
size 50675156
|
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:b6c2c803e63719a38ab78de645a182ebd31fb27bd73de5f12bc1f2831c268ff7
|
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,
|
@@ -567,6 +567,27 @@
|
|
567 |
"learning_rate": 0.00016,
|
568 |
"loss": 1.1684,
|
569 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 1,
|
@@ -586,7 +607,7 @@
|
|
586 |
"attributes": {}
|
587 |
}
|
588 |
},
|
589 |
-
"total_flos": 2.
|
590 |
"train_batch_size": 16,
|
591 |
"trial_name": null,
|
592 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.22770919067215364,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 83,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
567 |
"learning_rate": 0.00016,
|
568 |
"loss": 1.1684,
|
569 |
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.2222222222222222,
|
573 |
+
"grad_norm": 0.06477335095405579,
|
574 |
+
"learning_rate": 0.000162,
|
575 |
+
"loss": 1.1851,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.22496570644718794,
|
580 |
+
"grad_norm": 0.0677405372262001,
|
581 |
+
"learning_rate": 0.000164,
|
582 |
+
"loss": 1.093,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.22770919067215364,
|
587 |
+
"grad_norm": 0.06988447159528732,
|
588 |
+
"learning_rate": 0.000166,
|
589 |
+
"loss": 1.2542,
|
590 |
+
"step": 83
|
591 |
}
|
592 |
],
|
593 |
"logging_steps": 1,
|
|
|
607 |
"attributes": {}
|
608 |
}
|
609 |
},
|
610 |
+
"total_flos": 2.3801435722727424e+17,
|
611 |
"train_batch_size": 16,
|
612 |
"trial_name": null,
|
613 |
"trial_params": null
|