metadata
library_name: peft
license: gemma
base_model: google/gemma-3-270m
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of google/gemma-3-270m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8940
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- 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
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.149 | 1.0 | 360 | 1.9154 |
| 2.0852 | 2.0 | 720 | 1.8930 |
| 2.0449 | 3.0 | 1080 | 1.8940 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2