smilemikan
commited on
Commit
•
555f775
1
Parent(s):
c145ba6
Training in progress, step 20500, 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 sha256:245c98e0d04ea116d9f4c8104f7abf1428f7d3663a58acc3f00b215d65c7844d
|
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:aea00709e462e96fe448f991df8b661b341798c491fc7874c081b3571381daec
|
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:cd34a70a57c7edd7b2d61dcf32a825b851d6393642456c0bbddfaa5eef14b2a6
|
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:f996421c6fa5bd9101a9ea30b4085e3f14ac40ecc62c043ff0d36b92d20c4015
|
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,
|
@@ -567,13 +567,27 @@
|
|
567 |
"eval_samples_per_second": 208.093,
|
568 |
"eval_steps_per_second": 13.02,
|
569 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 500,
|
573 |
"max_steps": 60000,
|
574 |
"num_train_epochs": 14,
|
575 |
"save_steps": 500,
|
576 |
-
"total_flos": 2.
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|
579 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4834085702896118,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-20500",
|
4 |
+
"epoch": 4.516413306895792,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
567 |
"eval_samples_per_second": 208.093,
|
568 |
"eval_steps_per_second": 13.02,
|
569 |
"step": 20000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 4.52,
|
573 |
+
"learning_rate": 1.3169e-05,
|
574 |
+
"loss": 1.46,
|
575 |
+
"step": 20500
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 4.52,
|
579 |
+
"eval_loss": 1.4834085702896118,
|
580 |
+
"eval_runtime": 43.9437,
|
581 |
+
"eval_samples_per_second": 206.583,
|
582 |
+
"eval_steps_per_second": 12.926,
|
583 |
+
"step": 20500
|
584 |
}
|
585 |
],
|
586 |
"logging_steps": 500,
|
587 |
"max_steps": 60000,
|
588 |
"num_train_epochs": 14,
|
589 |
"save_steps": 500,
|
590 |
+
"total_flos": 2.0803933292199936e+16,
|
591 |
"trial_name": null,
|
592 |
"trial_params": null
|
593 |
}
|