football-rebuttal-model-gemma-2b-qlora-final
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: 1.1626
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.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_steps: 100
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.3371 | 1.0 | 12 | 6.7905 |
| 5.9182 | 2.0 | 24 | 4.7175 |
| 3.8343 | 3.0 | 36 | 2.7713 |
| 2.2414 | 4.0 | 48 | 1.8114 |
| 1.5838 | 5.0 | 60 | 1.4620 |
| 1.1942 | 6.0 | 72 | 1.2538 |
| 0.8435 | 7.0 | 84 | 1.1454 |
| 0.6401 | 8.0 | 96 | 1.0875 |
| 0.4437 | 9.0 | 108 | 1.0881 |
| 0.3296 | 10.0 | 120 | 1.1262 |
| 0.2319 | 11.0 | 132 | 1.1626 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2