smilemikan
commited on
Commit
•
339d524
1
Parent(s):
d7542e7
Training in progress, step 22000, 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:c0dfda5a328597ce50c98efb86c2eab6f4b7be6c2c7a1fcbbd0f9085f32d445d
|
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 sha256:1168462a3b8fbb986b1cd2c616eb18d034f9988f9baec72dec2f4e220ffbb918
|
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 sha256:61659212645012ca0bbb4e2fe1a8708ed86f0460189cac269df53fd49de42b5a
|
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 sha256:1054890f863539a2ea22e94222159c84e1457fbc9ffc8f211613e27139972d69
|
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": 4.
|
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,
|
@@ -609,13 +609,27 @@
|
|
609 |
"eval_samples_per_second": 207.276,
|
610 |
"eval_steps_per_second": 12.969,
|
611 |
"step": 21500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
612 |
}
|
613 |
],
|
614 |
"logging_steps": 500,
|
615 |
"max_steps": 60000,
|
616 |
"num_train_epochs": 14,
|
617 |
"save_steps": 500,
|
618 |
-
"total_flos": 2.
|
619 |
"trial_name": null,
|
620 |
"trial_params": null
|
621 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4648058414459229,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-22000",
|
4 |
+
"epoch": 4.846882573254021,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 22000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
609 |
"eval_samples_per_second": 207.276,
|
610 |
"eval_steps_per_second": 12.969,
|
611 |
"step": 21500
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 4.85,
|
615 |
+
"learning_rate": 1.2669333333333334e-05,
|
616 |
+
"loss": 1.4375,
|
617 |
+
"step": 22000
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 4.85,
|
621 |
+
"eval_loss": 1.4648058414459229,
|
622 |
+
"eval_runtime": 43.2759,
|
623 |
+
"eval_samples_per_second": 209.77,
|
624 |
+
"eval_steps_per_second": 13.125,
|
625 |
+
"step": 22000
|
626 |
}
|
627 |
],
|
628 |
"logging_steps": 500,
|
629 |
"max_steps": 60000,
|
630 |
"num_train_epochs": 14,
|
631 |
"save_steps": 500,
|
632 |
+
"total_flos": 2.23262565531648e+16,
|
633 |
"trial_name": null,
|
634 |
"trial_params": null
|
635 |
}
|