smilemikan
commited on
Commit
•
a41497e
1
Parent(s):
bec05df
Training in progress, step 14000, 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 sha256:08e62e1d907de6e13703c06269ae211079a067af431e84171420afebacc1db1e
|
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 sha256:6f06f09e6735c2c42525ec8cdb3cc7f28944ed4e48bee00a36ef6bd2ec390875
|
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 sha256:7d6b752ded1d95c4c9060fd0d8e2103d4197782abf53ce90c1e09961db418400
|
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:fe789f43fc2c6f3714ad5234e7fa28d162538759dd048ff1df0690fb4b7c5e82
|
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":
|
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,
|
@@ -385,13 +385,27 @@
|
|
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.
|
395 |
"trial_name": null,
|
396 |
"trial_params": null
|
397 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.6128900051116943,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-14000",
|
4 |
+
"epoch": 3.084379819343468,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 14000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
385 |
"eval_samples_per_second": 209.98,
|
386 |
"eval_steps_per_second": 13.138,
|
387 |
"step": 13500
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 3.08,
|
391 |
+
"learning_rate": 1.5335e-05,
|
392 |
+
"loss": 1.5917,
|
393 |
+
"step": 14000
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 3.08,
|
397 |
+
"eval_loss": 1.6128900051116943,
|
398 |
+
"eval_runtime": 42.9712,
|
399 |
+
"eval_samples_per_second": 211.258,
|
400 |
+
"eval_steps_per_second": 13.218,
|
401 |
+
"step": 14000
|
402 |
}
|
403 |
],
|
404 |
"logging_steps": 500,
|
405 |
"max_steps": 60000,
|
406 |
"num_train_epochs": 14,
|
407 |
"save_steps": 500,
|
408 |
+
"total_flos": 1.4186984138735616e+16,
|
409 |
"trial_name": null,
|
410 |
"trial_params": null
|
411 |
}
|