smilemikan
commited on
Commit
•
5c489c2
1
Parent(s):
fd617ec
Training in progress, step 18500, 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:ee8d14031344632f9a83d65cbeb334fd222e2206788562f1d0ef7f92f6755dc5
|
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 sha256:9c9b66246e212762c9bce54efe452a5660f3a27fc5f3db25a15258d1b546cd7e
|
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:b3a5307f1b9f3a753ffca16a6487033857c954277ede0e43f06c48d6e6e506a1
|
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 sha256:54e83d3d1c149aaff4f610278a355ef4e3e24cd2d1673a5e4041c0a10c815d4e
|
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":
|
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,
|
@@ -511,13 +511,27 @@
|
|
511 |
"eval_samples_per_second": 209.477,
|
512 |
"eval_steps_per_second": 13.107,
|
513 |
"step": 18000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
514 |
}
|
515 |
],
|
516 |
"logging_steps": 500,
|
517 |
"max_steps": 60000,
|
518 |
"num_train_epochs": 14,
|
519 |
"save_steps": 500,
|
520 |
-
"total_flos": 1.
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
523 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.519882082939148,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-18500",
|
4 |
+
"epoch": 4.075787618418154,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 18500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
511 |
"eval_samples_per_second": 209.477,
|
512 |
"eval_steps_per_second": 13.107,
|
513 |
"step": 18000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 4.08,
|
517 |
+
"learning_rate": 1.3835666666666667e-05,
|
518 |
+
"loss": 1.4771,
|
519 |
+
"step": 18500
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 4.08,
|
523 |
+
"eval_loss": 1.519882082939148,
|
524 |
+
"eval_runtime": 43.8272,
|
525 |
+
"eval_samples_per_second": 207.132,
|
526 |
+
"eval_steps_per_second": 12.96,
|
527 |
+
"step": 18500
|
528 |
}
|
529 |
],
|
530 |
"logging_steps": 500,
|
531 |
"max_steps": 60000,
|
532 |
"num_train_epochs": 14,
|
533 |
"save_steps": 500,
|
534 |
+
"total_flos": 1.8773830334152704e+16,
|
535 |
"trial_name": null,
|
536 |
"trial_params": null
|
537 |
}
|