smilemikan
commited on
Commit
•
169cb28
1
Parent(s):
7c8ca1b
Training in progress, step 22500, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5125261
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0139f2a51cdbbf4b8df09fcb7dc9c14c48a79913d3da772558179042ac751d16
|
3 |
size 5125261
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2460465086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78f674971a2185d95091adac6fcff1e3e55127e87cd78b011c5a629372b3077f
|
3 |
size 2460465086
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ad0abb71d4cdba143f424ef39b5d3ad3cd4970491244dff0c4e9d1a2fff5ae0
|
3 |
size 14244
|
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:aff8772b6306d4fb8716f88668180e186ea40fc113c8f9e88e62a3914ab2592a
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-
|
4 |
-
"epoch": 4.
|
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,
|
@@ -623,13 +623,27 @@
|
|
623 |
"eval_samples_per_second": 209.77,
|
624 |
"eval_steps_per_second": 13.125,
|
625 |
"step": 22000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
626 |
}
|
627 |
],
|
628 |
"logging_steps": 500,
|
629 |
"max_steps": 60000,
|
630 |
"num_train_epochs": 14,
|
631 |
"save_steps": 500,
|
632 |
-
"total_flos": 2.
|
633 |
"trial_name": null,
|
634 |
"trial_params": null
|
635 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.452415108680725,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-22500",
|
4 |
+
"epoch": 4.957038995373431,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 22500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
623 |
"eval_samples_per_second": 209.77,
|
624 |
"eval_steps_per_second": 13.125,
|
625 |
"step": 22000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 4.96,
|
629 |
+
"learning_rate": 1.2502666666666668e-05,
|
630 |
+
"loss": 1.4093,
|
631 |
+
"step": 22500
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 4.96,
|
635 |
+
"eval_loss": 1.452415108680725,
|
636 |
+
"eval_runtime": 43.4383,
|
637 |
+
"eval_samples_per_second": 208.986,
|
638 |
+
"eval_steps_per_second": 13.076,
|
639 |
+
"step": 22500
|
640 |
}
|
641 |
],
|
642 |
"logging_steps": 500,
|
643 |
"max_steps": 60000,
|
644 |
"num_train_epochs": 14,
|
645 |
"save_steps": 500,
|
646 |
+
"total_flos": 2.283115806444749e+16,
|
647 |
"trial_name": null,
|
648 |
"trial_params": null
|
649 |
}
|