DuongTrongChi
commited on
Commit
•
333e818
1
Parent(s):
8b76147
Training in progress, step 77, 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 sha256:0cb0496349c7b965d5745b83667dddba6d9df375bcaa24821f880398882683c0
|
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:a0888da8e641e6eaedf98307dcd8e2a8af3dfb612ef7f810d4e6ca8bcadf0e4e
|
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 sha256:725ee499aaa0bc04b490ac3af0c734c514c976dd8cd2f204b00fdb43d2a90bf8
|
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 +525,27 @@
|
|
525 |
"learning_rate": 0.000148,
|
526 |
"loss": 1.1915,
|
527 |
"step": 74
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
528 |
}
|
529 |
],
|
530 |
"logging_steps": 1,
|
@@ -544,7 +565,7 @@
|
|
544 |
"attributes": {}
|
545 |
}
|
546 |
},
|
547 |
-
"total_flos": 2.
|
548 |
"train_batch_size": 16,
|
549 |
"trial_name": null,
|
550 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2112482853223594,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 77,
|
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": 1.1915,
|
527 |
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.205761316872428,
|
531 |
+
"grad_norm": 0.0682872086763382,
|
532 |
+
"learning_rate": 0.00015000000000000001,
|
533 |
+
"loss": 1.2017,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.2085048010973937,
|
538 |
+
"grad_norm": 0.07075867056846619,
|
539 |
+
"learning_rate": 0.000152,
|
540 |
+
"loss": 1.1562,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.2112482853223594,
|
545 |
+
"grad_norm": 0.06364033371210098,
|
546 |
+
"learning_rate": 0.000154,
|
547 |
+
"loss": 1.1936,
|
548 |
+
"step": 77
|
549 |
}
|
550 |
],
|
551 |
"logging_steps": 1,
|
|
|
565 |
"attributes": {}
|
566 |
}
|
567 |
},
|
568 |
+
"total_flos": 2.202346458742948e+17,
|
569 |
"train_batch_size": 16,
|
570 |
"trial_name": null,
|
571 |
"trial_params": null
|