gemma-finetune-d1
This model is a fine-tuned version of google/gemma-3-27b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1715
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: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- 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: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.709 | 0.4008 | 100 | 0.2020 |
| 1.4114 | 0.8016 | 200 | 0.1829 |
| 1.3051 | 1.2004 | 300 | 0.1783 |
| 1.2553 | 1.6012 | 400 | 0.1725 |
| 1.1126 | 2.0 | 500 | 0.1677 |
| 1.05 | 2.4008 | 600 | 0.1712 |
| 0.9771 | 2.8016 | 700 | 0.1715 |
Framework versions
- PEFT 0.17.1
- Transformers 4.56.2
- Pytorch 2.8.0+cu128
- Datasets 4.1.1
- Tokenizers 0.22.1
- Downloads last month
- 8