Downloads · 30 days
10
38% of all-time downloads
gemma-qa-finetuned
aespitiar/gemma-qa-finetuned
gemma-qa-finetuned is a text generation model from aespitiar. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as gemma.
should probably proofread and complete it, then remove this comment. --
All-time downloads
26
Public
Repo size
53.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json34.4 MB · 64%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- gemma
- Access
- Public
- Created
- Sep 22, 2025
- Updated
- Sep 22, 2025
- SHA
- 825f3da2
Try a prompt
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. -->
gemma-qa-finetuned
This model is a fine-tuned version of google/gemma-2b-it on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2147
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3552 | 2.2222 | 100 | 0.3599 |
| 0.2197 | 4.4444 | 200 | 0.2645 |
| 0.1901 | 6.6667 | 300 | 0.2247 |
| 0.1784 | 8.8889 | 400 | 0.2147 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.22.0
- Task
- Text Generation
- Library
- peft
- License
- gemma
- Created
- Sep 22, 2025
- Updated
- Sep 22, 2025