smilemikan
commited on
Commit
•
5340fa3
1
Parent(s):
dc76c73
Training in progress, step 30000, 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:e83f95e833ebc0fac33a36e2859a6b4893a2b7f9867429104cfd5e76d140edca
|
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 sha256:2c0e1aa4d5b5ec7426f7806aeb61f201da66676e692609f020795a78f98d4995
|
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:fa2298c9c9372b63b8cb7113ee6aee3e024cd04f6dda66f3e6ec5e9733db478a
|
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 sha256:37b72b90219219968867948591225ed4b411e69d8be9e9095e600cf8b7a0ed9e
|
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,
|
@@ -833,13 +833,27 @@
|
|
833 |
"eval_samples_per_second": 201.792,
|
834 |
"eval_steps_per_second": 12.626,
|
835 |
"step": 29500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
836 |
}
|
837 |
],
|
838 |
"logging_steps": 500,
|
839 |
"max_steps": 60000,
|
840 |
"num_train_epochs": 14,
|
841 |
"save_steps": 500,
|
842 |
-
"total_flos":
|
843 |
"trial_name": null,
|
844 |
"trial_params": null
|
845 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3968815803527832,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-30000",
|
4 |
+
"epoch": 6.609385327164574,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 30000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
833 |
"eval_samples_per_second": 201.792,
|
834 |
"eval_steps_per_second": 12.626,
|
835 |
"step": 29500
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 6.61,
|
839 |
+
"learning_rate": 1.0003333333333333e-05,
|
840 |
+
"loss": 1.2543,
|
841 |
+
"step": 30000
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 6.61,
|
845 |
+
"eval_loss": 1.3968815803527832,
|
846 |
+
"eval_runtime": 45.3856,
|
847 |
+
"eval_samples_per_second": 200.019,
|
848 |
+
"eval_steps_per_second": 12.515,
|
849 |
+
"step": 30000
|
850 |
}
|
851 |
],
|
852 |
"logging_steps": 500,
|
853 |
"max_steps": 60000,
|
854 |
"num_train_epochs": 14,
|
855 |
"save_steps": 500,
|
856 |
+
"total_flos": 3.040688169929933e+16,
|
857 |
"trial_name": null,
|
858 |
"trial_params": null
|
859 |
}
|