smilemikan
commited on
Commit
•
6cfb342
1
Parent(s):
a8dcebd
Training in progress, step 27500, 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:d2d62619775d43d2cf93a194a2a910892f3f39b1242bb6dd667e55c7fb3ce154
|
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 sha256:4e95017e5a4ad86b5ff0851a391da824ab31a84d84f421619c20317622e372cc
|
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 sha256:7f0dac653bfe2c7aee298f646a77251b127b2e2f957796f6b24e4bc4d9bfd5a0
|
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 sha256:53253dd0116d956eefc0d21d01703cac3649246a63f7114fac3cf4f5a9c9cf97
|
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,
|
@@ -763,13 +763,27 @@
|
|
763 |
"eval_samples_per_second": 204.547,
|
764 |
"eval_steps_per_second": 12.798,
|
765 |
"step": 27000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
766 |
}
|
767 |
],
|
768 |
"logging_steps": 500,
|
769 |
"max_steps": 60000,
|
770 |
"num_train_epochs": 14,
|
771 |
"save_steps": 500,
|
772 |
-
"total_flos": 2.
|
773 |
"trial_name": null,
|
774 |
"trial_params": null
|
775 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4157874584197998,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-27500",
|
4 |
+
"epoch": 6.058603216567526,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 27500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
763 |
"eval_samples_per_second": 204.547,
|
764 |
"eval_steps_per_second": 12.798,
|
765 |
"step": 27000
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 6.06,
|
769 |
+
"learning_rate": 1.0836333333333333e-05,
|
770 |
+
"loss": 1.2689,
|
771 |
+
"step": 27500
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 6.06,
|
775 |
+
"eval_loss": 1.4157874584197998,
|
776 |
+
"eval_runtime": 44.2987,
|
777 |
+
"eval_samples_per_second": 204.927,
|
778 |
+
"eval_steps_per_second": 12.822,
|
779 |
+
"step": 27500
|
780 |
}
|
781 |
],
|
782 |
"logging_steps": 500,
|
783 |
"max_steps": 60000,
|
784 |
"num_train_epochs": 14,
|
785 |
"save_steps": 500,
|
786 |
+
"total_flos": 2.789669734986547e+16,
|
787 |
"trial_name": null,
|
788 |
"trial_params": null
|
789 |
}
|