smilemikan
commited on
Commit
•
3900147
1
Parent(s):
ba12a6f
Training in progress, step 13500, 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 sha256:86cfbda9500d9fa815610ac526e15ac59017c011ab852a8d213fe369e2c87264
|
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 sha256:797b0c667f1da4b858bbb1ee44c67e059568d00802694b682626ab1637074e27
|
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 sha256:68e94687f2321daa5ab010d3ad0f01731437e5893f8fb090bda50165155ecfbd
|
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 sha256:6bad3162e73fe33bc16c82c735842e363e840b493e85ecb0197fcc604f79f916
|
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": 2.
|
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,
|
@@ -371,13 +371,27 @@
|
|
371 |
"eval_samples_per_second": 210.292,
|
372 |
"eval_steps_per_second": 13.158,
|
373 |
"step": 13000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 500,
|
377 |
"max_steps": 60000,
|
378 |
"num_train_epochs": 14,
|
379 |
"save_steps": 500,
|
380 |
-
"total_flos": 1.
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.6240772008895874,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-13500",
|
4 |
+
"epoch": 2.9742233972240584,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 13500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
371 |
"eval_samples_per_second": 210.292,
|
372 |
"eval_steps_per_second": 13.158,
|
373 |
"step": 13000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.97,
|
377 |
+
"learning_rate": 1.5501666666666668e-05,
|
378 |
+
"loss": 1.6384,
|
379 |
+
"step": 13500
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 2.97,
|
383 |
+
"eval_loss": 1.6240772008895874,
|
384 |
+
"eval_runtime": 43.2327,
|
385 |
+
"eval_samples_per_second": 209.98,
|
386 |
+
"eval_steps_per_second": 13.138,
|
387 |
+
"step": 13500
|
388 |
}
|
389 |
],
|
390 |
"logging_steps": 500,
|
391 |
"max_steps": 60000,
|
392 |
"num_train_epochs": 14,
|
393 |
"save_steps": 500,
|
394 |
+
"total_flos": 1.3701383402815488e+16,
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|