ramdhanfirdaus
commited on
Commit
•
2db3d4f
1
Parent(s):
ea890b1
Training in progress, step 3800, 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4a0be6179474b77c4f901f87ee098da86361f7badcaf455e50448c67538c7f
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100691721
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd7efbe1ad3f0abf54495b9a704a20e5c1675ebdb224841eaf7cf75fa2ceb0ab
|
3 |
size 100691721
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a161e00ab25573dd553d2410ed15a310a4aaac2b7db73ad1b76c9c75404f8fda
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.2722229957580566,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3500",
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -525,13 +525,27 @@
|
|
525 |
"eval_samples_per_second": 46.715,
|
526 |
"eval_steps_per_second": 5.845,
|
527 |
"step": 3700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
528 |
}
|
529 |
],
|
530 |
"logging_steps": 100,
|
531 |
"max_steps": 4116,
|
532 |
"num_train_epochs": 3,
|
533 |
"save_steps": 100,
|
534 |
-
"total_flos": 2.
|
535 |
"trial_name": null,
|
536 |
"trial_params": null
|
537 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.2722229957580566,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3500",
|
4 |
+
"epoch": 2.769398907103825,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
525 |
"eval_samples_per_second": 46.715,
|
526 |
"eval_steps_per_second": 5.845,
|
527 |
"step": 3700
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 2.77,
|
531 |
+
"learning_rate": 0.0002,
|
532 |
+
"loss": 1.2528,
|
533 |
+
"step": 3800
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 2.77,
|
537 |
+
"eval_loss": 1.2842642068862915,
|
538 |
+
"eval_runtime": 133.1291,
|
539 |
+
"eval_samples_per_second": 47.127,
|
540 |
+
"eval_steps_per_second": 5.897,
|
541 |
+
"step": 3800
|
542 |
}
|
543 |
],
|
544 |
"logging_steps": 100,
|
545 |
"max_steps": 4116,
|
546 |
"num_train_epochs": 3,
|
547 |
"save_steps": 100,
|
548 |
+
"total_flos": 2.265239844086661e+17,
|
549 |
"trial_name": null,
|
550 |
"trial_params": null
|
551 |
}
|