smilemikan
commited on
Commit
•
3bf6461
1
Parent(s):
84a13e0
Training in progress, step 26000, 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 sha256:0812e33c4cee242c53d685e799a533c66bf64de5575c11ae22279911b67a6f5d
|
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 sha256:5946e0c490c59b947cffe1fb16e30a04e884d03d8919c8f02fff1aeb1b8567d5
|
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 sha256:9bce9dcd8ddd12c687413b694336f4f01115a178677c5e940754a09238d0df7d
|
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:c40cacb770ccca3bea22826c3d316644efdc7649940a1fc7f0c6332061e5dbb9
|
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,
|
@@ -721,13 +721,27 @@
|
|
721 |
"eval_samples_per_second": 201.134,
|
722 |
"eval_steps_per_second": 12.585,
|
723 |
"step": 25500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
724 |
}
|
725 |
],
|
726 |
"logging_steps": 500,
|
727 |
"max_steps": 60000,
|
728 |
"num_train_epochs": 14,
|
729 |
"save_steps": 500,
|
730 |
-
"total_flos": 2.
|
731 |
"trial_name": null,
|
732 |
"trial_params": null
|
733 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.424834132194519,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-26000",
|
4 |
+
"epoch": 5.728133950209298,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 26000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
721 |
"eval_samples_per_second": 201.134,
|
722 |
"eval_steps_per_second": 12.585,
|
723 |
"step": 25500
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 5.73,
|
727 |
+
"learning_rate": 1.1336333333333334e-05,
|
728 |
+
"loss": 1.3236,
|
729 |
+
"step": 26000
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 5.73,
|
733 |
+
"eval_loss": 1.424834132194519,
|
734 |
+
"eval_runtime": 44.2677,
|
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": 2.637870829810483e+16,
|
745 |
"trial_name": null,
|
746 |
"trial_params": null
|
747 |
}
|
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 sha256:3e3f80fbe7aa2ced1195759a9a79a4a6a1c77c295c21fc90affe4bbb9114a987
|
3 |
size 4664
|