smilemikan
commited on
Commit
•
1673fb6
1
Parent(s):
cfc0726
Training in progress, step 26500, 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:adf4e50dda4cb657fdd9326019a5ac4dfe101fe1f1d54c81dd1e2f9bd58cc6ae
|
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 sha256:2a1c2a7bf1797d8381f811e8d5b57cb53445d83023583a9be3d1901475ff9a8b
|
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:e33b23a382b76d3f8df9ae107cac6a750d3f276c2ea7a165ea614ef013adf748
|
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 sha256:3d777d6448139ae79a697ebe243c190b59aedffd5d0034167213bf79bb8b1257
|
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.
|
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,
|
@@ -735,13 +735,27 @@
|
|
735 |
"eval_samples_per_second": 205.07,
|
736 |
"eval_steps_per_second": 12.831,
|
737 |
"step": 26000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
738 |
}
|
739 |
],
|
740 |
"logging_steps": 500,
|
741 |
"max_steps": 60000,
|
742 |
"num_train_epochs": 14,
|
743 |
"save_steps": 500,
|
744 |
-
"total_flos": 2.
|
745 |
"trial_name": null,
|
746 |
"trial_params": null
|
747 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4215062856674194,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-26500",
|
4 |
+
"epoch": 5.838290372328707,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 26500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
735 |
"eval_samples_per_second": 205.07,
|
736 |
"eval_steps_per_second": 12.831,
|
737 |
"step": 26000
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 5.84,
|
741 |
+
"learning_rate": 1.1169666666666667e-05,
|
742 |
+
"loss": 1.3061,
|
743 |
+
"step": 26500
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 5.84,
|
747 |
+
"eval_loss": 1.4215062856674194,
|
748 |
+
"eval_runtime": 44.2542,
|
749 |
+
"eval_samples_per_second": 205.133,
|
750 |
+
"eval_steps_per_second": 12.835,
|
751 |
+
"step": 26500
|
752 |
}
|
753 |
],
|
754 |
"logging_steps": 500,
|
755 |
"max_steps": 60000,
|
756 |
"num_train_epochs": 14,
|
757 |
"save_steps": 500,
|
758 |
+
"total_flos": 2.688631869014016e+16,
|
759 |
"trial_name": null,
|
760 |
"trial_params": null
|
761 |
}
|