Downloads · 30 days
3
8% of all-time downloads
KD-LoRA-T4.0-A0.9
raniiaa17/KD-LoRA-T4.0-A0.9
KD-LoRA-T4.0-A0.9 is a machine learning model from raniiaa17. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
All-time downloads
39
Public
Repo size
177 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11 MB · 77%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jan 26, 2026
- Updated
- Jan 26, 2026
- SHA
- 266b2a1e
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
KD-LoRA-T4.0-A0.9
This model is a fine-tuned version of Wikidepia/IndoT5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 237.9334
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 363.0986 | 1.0 | 188 | 289.3970 |
| 334.5984 | 2.0 | 376 | 267.4710 |
| 317.9965 | 3.0 | 564 | 256.0125 |
| 310.3223 | 4.0 | 752 | 255.6415 |
| 300.4693 | 5.0 | 940 | 250.6423 |
| 302.0586 | 6.0 | 1128 | 251.1227 |
| 295.1349 | 7.0 | 1316 | 250.3875 |
| 297.7311 | 8.0 | 1504 | 250.5828 |
| 294.1046 | 9.0 | 1692 | 246.3612 |
| 289.5825 | 10.0 | 1880 | 240.3174 |
| 289.5868 | 11.0 | 2068 | 238.3742 |
| 285.0579 | 12.0 | 2256 | 241.6641 |
| 286.2686 | 13.0 | 2444 | 237.1008 |
| 287.4378 | 14.0 | 2632 | 238.5668 |
| 282.7072 | 15.0 | 2820 | 240.1148 |
| 280.9084 | 16.0 | 3008 | 237.9334 |
Framework versions
- PEFT 0.18.1
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Library
- peft
- Created
- Jan 26, 2026
- Updated
- Jan 26, 2026