smilemikan
commited on
Commit
•
fa64e59
1
Parent(s):
6ca8a6e
Training in progress, step 31000, 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 sha256:393b96c43419e3b12718fa721e523c7e91937727cf35dbe58fe5780c4d886f2a
|
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:d050fc160a73679aa7ba8b157b876b36a924317fb2a6134a5293079139bf34c6
|
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 sha256:9505f5dd72fa4d194cad71f35a13d6b3965c81cf4f1cda7257a2ec288f5b3b0c
|
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 sha256:159b1077fd21e4ce65e0ad54b644df696bbd85758527fc7e60213c87c06204a0
|
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": 6.
|
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,
|
@@ -861,13 +861,27 @@
|
|
861 |
"eval_samples_per_second": 203.345,
|
862 |
"eval_steps_per_second": 12.723,
|
863 |
"step": 30500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
864 |
}
|
865 |
],
|
866 |
"logging_steps": 500,
|
867 |
"max_steps": 60000,
|
868 |
"num_train_epochs": 14,
|
869 |
"save_steps": 500,
|
870 |
-
"total_flos": 3.
|
871 |
"trial_name": null,
|
872 |
"trial_params": null
|
873 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.387181043624878,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-31000",
|
4 |
+
"epoch": 6.829698171403393,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 31000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
861 |
"eval_samples_per_second": 203.345,
|
862 |
"eval_steps_per_second": 12.723,
|
863 |
"step": 30500
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 6.83,
|
867 |
+
"learning_rate": 9.67e-06,
|
868 |
+
"loss": 1.2626,
|
869 |
+
"step": 31000
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 6.83,
|
873 |
+
"eval_loss": 1.387181043624878,
|
874 |
+
"eval_runtime": 44.4948,
|
875 |
+
"eval_samples_per_second": 204.024,
|
876 |
+
"eval_steps_per_second": 12.766,
|
877 |
+
"step": 31000
|
878 |
}
|
879 |
],
|
880 |
"logging_steps": 500,
|
881 |
"max_steps": 60000,
|
882 |
"num_train_epochs": 14,
|
883 |
"save_steps": 500,
|
884 |
+
"total_flos": 3.1433615226568704e+16,
|
885 |
"trial_name": null,
|
886 |
"trial_params": null
|
887 |
}
|