smilemikan
commited on
Commit
•
afd9306
1
Parent(s):
a9cddf8
Training in progress, step 30500, 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 sha256:9bbc2f423bfdfc958778d54d43c8daba7cf491a6ea7e74a18e243e167314b25b
|
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 sha256:5d979730c0af6b3d2a6424b3cd96a7fd62dc02a9a8e56bc6674599a9cb4cb6e5
|
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 sha256:3797e6ce35368b8e4a570fd8fe9f7a0b3847b477c20ada57bcb024f3c74b801d
|
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:b546ac2f7f64ce28fa1ffac57d8e8ccbb593107a2d6eeee000fc631bb011fff7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.3968815803527832,
|
3 |
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-30000",
|
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,
|
@@ -847,13 +847,27 @@
|
|
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.
|
857 |
"trial_name": null,
|
858 |
"trial_params": null
|
859 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.3968815803527832,
|
3 |
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-30000",
|
4 |
+
"epoch": 6.719541749283984,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 30500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
847 |
"eval_samples_per_second": 200.019,
|
848 |
"eval_steps_per_second": 12.515,
|
849 |
"step": 30000
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 6.72,
|
853 |
+
"learning_rate": 9.836666666666668e-06,
|
854 |
+
"loss": 1.2552,
|
855 |
+
"step": 30500
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 6.72,
|
859 |
+
"eval_loss": 1.3993921279907227,
|
860 |
+
"eval_runtime": 44.6433,
|
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": 3.0927054525825024e+16,
|
871 |
"trial_name": null,
|
872 |
"trial_params": null
|
873 |
}
|