smilemikan
commited on
Commit
•
b7c68fc
1
Parent(s):
17e3f6e
Training in progress, step 24000, 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 sha256:75521d5c95e544b58efe27cae1b05613913aedb7fb3fd2587b30541c6ea79d39
|
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:f19a935d1c6fe49a12b4c8670f0d53c68e7416233abaeeeaddb7185cdbbbef01
|
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:f138f3ad6bdd935027bc7a15fa8f66489c34e9ca83573106addf32330e6c5fd4
|
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:e7089430075c4f4f179c1dba9dd54566fc41d7a7f96f6a8b86e296aa305360f2
|
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.
|
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,
|
@@ -665,13 +665,27 @@
|
|
665 |
"eval_samples_per_second": 201.575,
|
666 |
"eval_steps_per_second": 12.612,
|
667 |
"step": 23500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
668 |
}
|
669 |
],
|
670 |
"logging_steps": 500,
|
671 |
"max_steps": 60000,
|
672 |
"num_train_epochs": 14,
|
673 |
"save_steps": 500,
|
674 |
-
"total_flos": 2.
|
675 |
"trial_name": null,
|
676 |
"trial_params": null
|
677 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4429727792739868,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-24000",
|
4 |
+
"epoch": 5.287508261731659,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 24000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
665 |
"eval_samples_per_second": 201.575,
|
666 |
"eval_steps_per_second": 12.612,
|
667 |
"step": 23500
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 5.29,
|
671 |
+
"learning_rate": 1.2003e-05,
|
672 |
+
"loss": 1.3672,
|
673 |
+
"step": 24000
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 5.29,
|
677 |
+
"eval_loss": 1.4429727792739868,
|
678 |
+
"eval_runtime": 48.0671,
|
679 |
+
"eval_samples_per_second": 188.861,
|
680 |
+
"eval_steps_per_second": 11.817,
|
681 |
+
"step": 24000
|
682 |
}
|
683 |
],
|
684 |
"logging_steps": 500,
|
685 |
"max_steps": 60000,
|
686 |
"num_train_epochs": 14,
|
687 |
"save_steps": 500,
|
688 |
+
"total_flos": 2.4362217465839616e+16,
|
689 |
"trial_name": null,
|
690 |
"trial_params": null
|
691 |
}
|