smilemikan
commited on
Commit
•
663e203
1
Parent(s):
bf6406d
Training in progress, step 16500, 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 sha256:3c48cffa2aee75c50f2769e5a27e103fb1208a667ce4ef9c1ec217d43f718232
|
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:cd93eead5db22ed7511a6e711ebe12dceec9da217a07aa6ef5d0eecbaa060da7
|
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:dfb5c4a03551949fcf48bba2bec36f3e7e3b8146fd809d03227a751e6199f92f
|
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:eec233f0702ccbc8f35f54687c96099a02f88403b45595309c416466a5e5b699
|
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,
|
@@ -455,13 +455,27 @@
|
|
455 |
"eval_samples_per_second": 211.645,
|
456 |
"eval_steps_per_second": 13.242,
|
457 |
"step": 16000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
458 |
}
|
459 |
],
|
460 |
"logging_steps": 500,
|
461 |
"max_steps": 60000,
|
462 |
"num_train_epochs": 14,
|
463 |
"save_steps": 500,
|
464 |
-
"total_flos": 1.
|
465 |
"trial_name": null,
|
466 |
"trial_params": null
|
467 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5577419996261597,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-16500",
|
4 |
+
"epoch": 3.635161929940516,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 16500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
455 |
"eval_samples_per_second": 211.645,
|
456 |
"eval_steps_per_second": 13.242,
|
457 |
"step": 16000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 3.64,
|
461 |
+
"learning_rate": 1.4502000000000001e-05,
|
462 |
+
"loss": 1.5284,
|
463 |
+
"step": 16500
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 3.64,
|
467 |
+
"eval_loss": 1.5577419996261597,
|
468 |
+
"eval_runtime": 43.6635,
|
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": 1.6744303013265408e+16,
|
479 |
"trial_name": null,
|
480 |
"trial_params": null
|
481 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d56fc78378352a6a12f0a73a10e788b6b95f518afd687b8fce8852e93af1f6d
|
3 |
size 4664
|