smilemikan
commited on
Commit
•
deb055b
1
Parent(s):
ff44ad1
Training in progress, step 36000, 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 sha256:0823af30b457b21d03622b0e5ec607830ad3eb4931531ef4e66fdd7b5d848945
|
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:e560e12102cb30c8844e9201276e5e4411a817ddf7088c208b2d192b75a8786e
|
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 sha256:26c038200f4f8a74c11a8785b8e167d9df1bbab710a7e672e0abeafc1b98201d
|
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 sha256:2b506a29889e6812ebf3d570fcad99df58085bc924b25685203b74a2b743ec3a
|
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": 7.
|
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,
|
@@ -1001,13 +1001,27 @@
|
|
1001 |
"eval_samples_per_second": 199.792,
|
1002 |
"eval_steps_per_second": 12.501,
|
1003 |
"step": 35500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1004 |
}
|
1005 |
],
|
1006 |
"logging_steps": 500,
|
1007 |
"max_steps": 60000,
|
1008 |
"num_train_epochs": 14,
|
1009 |
"save_steps": 500,
|
1010 |
-
"total_flos": 3.
|
1011 |
"trial_name": null,
|
1012 |
"trial_params": null
|
1013 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.357163429260254,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-36000",
|
4 |
+
"epoch": 7.931262392597488,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 36000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1001 |
"eval_samples_per_second": 199.792,
|
1002 |
"eval_steps_per_second": 12.501,
|
1003 |
"step": 35500
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 7.93,
|
1007 |
+
"learning_rate": 8.004e-06,
|
1008 |
+
"loss": 1.2261,
|
1009 |
+
"step": 36000
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 7.93,
|
1013 |
+
"eval_loss": 1.357163429260254,
|
1014 |
+
"eval_runtime": 45.4325,
|
1015 |
+
"eval_samples_per_second": 199.813,
|
1016 |
+
"eval_steps_per_second": 12.502,
|
1017 |
+
"step": 36000
|
1018 |
}
|
1019 |
],
|
1020 |
"logging_steps": 500,
|
1021 |
"max_steps": 60000,
|
1022 |
"num_train_epochs": 14,
|
1023 |
"save_steps": 500,
|
1024 |
+
"total_flos": 3.650436910743552e+16,
|
1025 |
"trial_name": null,
|
1026 |
"trial_params": null
|
1027 |
}
|