smilemikan
commited on
Commit
•
b89f5e7
1
Parent(s):
4902390
Training in progress, step 25500, 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:a2d93ac65bf0c82f15a96f67cefa25f73a148134b956b473f7b623ef64a81c5a
|
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 sha256:005300a5884b5c94b6987e507254b3663f6bab94584194feec9a79a91dec78a0
|
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 sha256:819aa1bfb07444926e89d193fb5ace72b67ca649b4962e35691204a34917d723
|
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:ce561dd36784a6022b412facce600919ab30be4222f5f2eb418a4fe928539a3e
|
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,
|
@@ -707,13 +707,27 @@
|
|
707 |
"eval_samples_per_second": 202.689,
|
708 |
"eval_steps_per_second": 12.682,
|
709 |
"step": 25000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
710 |
}
|
711 |
],
|
712 |
"logging_steps": 500,
|
713 |
"max_steps": 60000,
|
714 |
"num_train_epochs": 14,
|
715 |
"save_steps": 500,
|
716 |
-
"total_flos": 2.
|
717 |
"trial_name": null,
|
718 |
"trial_params": null
|
719 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4315000772476196,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-25500",
|
4 |
+
"epoch": 5.617977528089888,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 25500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
707 |
"eval_samples_per_second": 202.689,
|
708 |
"eval_steps_per_second": 12.682,
|
709 |
"step": 25000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 5.62,
|
713 |
+
"learning_rate": 1.1503000000000002e-05,
|
714 |
+
"loss": 1.3445,
|
715 |
+
"step": 25500
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 5.62,
|
719 |
+
"eval_loss": 1.4315000772476196,
|
720 |
+
"eval_runtime": 45.134,
|
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": 2.5881222347882496e+16,
|
731 |
"trial_name": null,
|
732 |
"trial_params": null
|
733 |
}
|