smilemikan
commited on
Commit
•
0f1acba
1
Parent(s):
a4d106c
Training in progress, step 23000, 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:e0266a8a3dca96a0991e0f8227b776b2465d53b4076610920fe55fa400b73d62
|
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 sha256:6098cf86a2c326970b5ec5b98d6cb81beaafbfd692923f7910d181cd4b211c7a
|
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 sha256:313b59c81cd481a9990bc3df1bc6d8537b8c373ab865f11fdeeb77db5cb8489b
|
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:a532235df6adca43705297d05a00b0238294408e024df73149fee8663d9f9c8c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.452415108680725,
|
3 |
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-22500",
|
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,
|
@@ -637,13 +637,27 @@
|
|
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.
|
647 |
"trial_name": null,
|
648 |
"trial_params": null
|
649 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.452415108680725,
|
3 |
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-22500",
|
4 |
+
"epoch": 5.06719541749284,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 23000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
637 |
"eval_samples_per_second": 208.986,
|
638 |
"eval_steps_per_second": 13.076,
|
639 |
"step": 22500
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 5.07,
|
643 |
+
"learning_rate": 1.2336000000000002e-05,
|
644 |
+
"loss": 1.3688,
|
645 |
+
"step": 23000
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 5.07,
|
649 |
+
"eval_loss": 1.4525853395462036,
|
650 |
+
"eval_runtime": 44.7597,
|
651 |
+
"eval_samples_per_second": 202.816,
|
652 |
+
"eval_steps_per_second": 12.69,
|
653 |
+
"step": 23000
|
654 |
}
|
655 |
],
|
656 |
"logging_steps": 500,
|
657 |
"max_steps": 60000,
|
658 |
"num_train_epochs": 14,
|
659 |
"save_steps": 500,
|
660 |
+
"total_flos": 2.3353667300622336e+16,
|
661 |
"trial_name": null,
|
662 |
"trial_params": null
|
663 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86e1a3ffe918127105cdbab0a504e0f8d45bb23733aa213dfdd7c21a6e7056fb
|
3 |
size 4664
|