DuongTrongChi
commited on
Commit
•
39914e5
1
Parent(s):
4ae02e7
Training in progress, step 75, 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 60010048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba5c35b56393b95564db59360507a54858541adf545ebe10fb116414cfd21cea
|
3 |
size 60010048
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 30427860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d543dc78d44d8e59e453da07deb9433f6557148b5084c7ad9970bea9d834bf1a
|
3 |
size 30427860
|
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 sha256:4ba73f47acd9a9aad290406ed61846c9f0fda0f7b5e8d4bbd1ee8fefd3fb9816
|
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,
|
@@ -525,6 +525,13 @@
|
|
525 |
"learning_rate": 0.000148,
|
526 |
"loss": 1.304,
|
527 |
"step": 74
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
528 |
}
|
529 |
],
|
530 |
"logging_steps": 1,
|
@@ -544,7 +551,7 @@
|
|
544 |
"attributes": {}
|
545 |
}
|
546 |
},
|
547 |
-
"total_flos": 9.
|
548 |
"train_batch_size": 4,
|
549 |
"trial_name": null,
|
550 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.205761316872428,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 75,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
525 |
"learning_rate": 0.000148,
|
526 |
"loss": 1.304,
|
527 |
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.205761316872428,
|
531 |
+
"grad_norm": 0.12175633758306503,
|
532 |
+
"learning_rate": 0.00015000000000000001,
|
533 |
+
"loss": 1.3144,
|
534 |
+
"step": 75
|
535 |
}
|
536 |
],
|
537 |
"logging_steps": 1,
|
|
|
551 |
"attributes": {}
|
552 |
}
|
553 |
},
|
554 |
+
"total_flos": 9.139644296272282e+16,
|
555 |
"train_batch_size": 4,
|
556 |
"trial_name": null,
|
557 |
"trial_params": null
|