End of training
Browse files- README.md +1 -1
- model.safetensors +1 -1
- sparsification_sftt.py +2 -2
README.md
CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 10.
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 10.3729
|
17 |
|
18 |
## Model description
|
19 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16567728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5c447da43183c5ec31a944e37d7519ace58e6fafd1316f0b609a5092e4a471
|
3 |
size 16567728
|
sparsification_sftt.py
CHANGED
@@ -571,13 +571,13 @@ class GracefulRegularizationScheduler(TrainerCallback):
|
|
571 |
if is_mainprocess():
|
572 |
current_steps = self.start_steps + state.global_step
|
573 |
ds_print(
|
574 |
-
f"Saving to /scr/lukeai/{self.model_name}_{current_steps}.pt",
|
575 |
)
|
576 |
# save_state_dict(model, f"/scr/lukeai/{self.model_name}_{state.global_step}.pt")
|
577 |
print("Saving a model...")
|
578 |
torch.save(
|
579 |
model.state_dict(),
|
580 |
-
f"/scr/lukeai/{self.model_name}_{current_steps}.pt",
|
581 |
)
|
582 |
|
583 |
|
|
|
571 |
if is_mainprocess():
|
572 |
current_steps = self.start_steps + state.global_step
|
573 |
ds_print(
|
574 |
+
f"Saving to /scr/lukeai/{self.model_name}_{current_steps}_ckpt.pt",
|
575 |
)
|
576 |
# save_state_dict(model, f"/scr/lukeai/{self.model_name}_{state.global_step}.pt")
|
577 |
print("Saving a model...")
|
578 |
torch.save(
|
579 |
model.state_dict(),
|
580 |
+
f"/scr/lukeai/{self.model_name}_{current_steps}_ckpt.pt",
|
581 |
)
|
582 |
|
583 |
|