smilemikan
commited on
Commit
•
d69bdd4
1
Parent(s):
7f61a30
Training in progress, step 29000, 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 sha256:0aa2668846e9a33a8090234cd39de2dd4cf301d2d756547d380c8c278a06f2e2
|
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:ed7faccf2d02094ad99fa5065d8df9c269984dc2f0eb60b8072bd5dc20fd021a
|
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 sha256:3c02898f79565e6b2e91b1b935fbf97b8f7a90a66b89afbadcd5206758c4ffb9
|
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 sha256:89ad63f4a333c21f00cebde42b984d54181b343653ad6324c844f565a0e396d1
|
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,
|
@@ -805,13 +805,27 @@
|
|
805 |
"eval_samples_per_second": 203.242,
|
806 |
"eval_steps_per_second": 12.717,
|
807 |
"step": 28500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
808 |
}
|
809 |
],
|
810 |
"logging_steps": 500,
|
811 |
"max_steps": 60000,
|
812 |
"num_train_epochs": 14,
|
813 |
"save_steps": 500,
|
814 |
-
"total_flos": 2.
|
815 |
"trial_name": null,
|
816 |
"trial_params": null
|
817 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.403244972229004,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-29000",
|
4 |
+
"epoch": 6.389072482925755,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 29000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
805 |
"eval_samples_per_second": 203.242,
|
806 |
"eval_steps_per_second": 12.717,
|
807 |
"step": 28500
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 6.39,
|
811 |
+
"learning_rate": 1.0336666666666669e-05,
|
812 |
+
"loss": 1.2668,
|
813 |
+
"step": 29000
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 6.39,
|
817 |
+
"eval_loss": 1.403244972229004,
|
818 |
+
"eval_runtime": 44.6624,
|
819 |
+
"eval_samples_per_second": 203.258,
|
820 |
+
"eval_steps_per_second": 12.718,
|
821 |
+
"step": 29000
|
822 |
}
|
823 |
],
|
824 |
"logging_steps": 500,
|
825 |
"max_steps": 60000,
|
826 |
"num_train_epochs": 14,
|
827 |
"save_steps": 500,
|
828 |
+
"total_flos": 2.941184207683584e+16,
|
829 |
"trial_name": null,
|
830 |
"trial_params": null
|
831 |
}
|