---
library_name: peft
license: gemma
base_model: google/gemma-3-1b-pt
tags:
- generated_from_trainer
model-index:
- name: gemma_3_1b_causal_finetune_lora
  results: []
---

<!-- 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_3_1b_causal_finetune_lora

This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5270

## 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: 6.5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6969        | 1.0   | 12   | 0.9517          |
| 0.7666        | 2.0   | 24   | 0.6638          |
| 0.5743        | 3.0   | 36   | 0.5845          |
| 0.4948        | 4.0   | 48   | 0.5431          |
| 0.436         | 5.0   | 60   | 0.5176          |
| 0.4011        | 6.0   | 72   | 0.5075          |
| 0.3743        | 7.0   | 84   | 0.5028          |
| 0.3507        | 8.0   | 96   | 0.5099          |
| 0.3313        | 9.0   | 108  | 0.5267          |
| 0.3121        | 10.0  | 120  | 0.5270          |


### Framework versions

- PEFT 0.15.2.dev0
- Transformers 4.51.0.dev0
- Pytorch 2.6.0
- Datasets 3.4.0
- Tokenizers 0.21.1