smilemikan
commited on
Commit
•
9e24153
1
Parent(s):
a8c03bd
Training in progress, step 17000, 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 sha256:9175805630a622e73ca492f94b77d5dc0ea902b37d9ae17705b651e16ecd20ef
|
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:b740d51e796b9fd3c0d8d46f10c04c82c5e93abc46c869fa9a1d904c212f3e7e
|
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:a985964cfb7e0952c952fbeb01ab98aa97733bf482e8840e1ddd41a5024b841d
|
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 sha256:4486a6ff141c5a7c9b6e4200912bd46df4bc7b3ef69c22a34e38b4eb3cc8332f
|
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": 3.
|
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,
|
@@ -469,13 +469,27 @@
|
|
469 |
"eval_samples_per_second": 207.908,
|
470 |
"eval_steps_per_second": 13.009,
|
471 |
"step": 16500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
472 |
}
|
473 |
],
|
474 |
"logging_steps": 500,
|
475 |
"max_steps": 60000,
|
476 |
"num_train_epochs": 14,
|
477 |
"save_steps": 500,
|
478 |
-
"total_flos": 1.
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|
481 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.544019103050232,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-17000",
|
4 |
+
"epoch": 3.7453183520599254,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 17000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
469 |
"eval_samples_per_second": 207.908,
|
470 |
"eval_steps_per_second": 13.009,
|
471 |
"step": 16500
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 3.75,
|
475 |
+
"learning_rate": 1.4335666666666667e-05,
|
476 |
+
"loss": 1.5219,
|
477 |
+
"step": 17000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 3.75,
|
481 |
+
"eval_loss": 1.544019103050232,
|
482 |
+
"eval_runtime": 43.4005,
|
483 |
+
"eval_samples_per_second": 209.168,
|
484 |
+
"eval_steps_per_second": 13.087,
|
485 |
+
"step": 17000
|
486 |
}
|
487 |
],
|
488 |
"logging_steps": 500,
|
489 |
"max_steps": 60000,
|
490 |
"num_train_epochs": 14,
|
491 |
"save_steps": 500,
|
492 |
+
"total_flos": 1.7257839081947136e+16,
|
493 |
"trial_name": null,
|
494 |
"trial_params": null
|
495 |
}
|