TinyLlama-1.1B-Chat-v1.0-qlora-modular
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8009
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 |
|---|---|---|---|
| 2.1013 | 4.1778 | 50 | 0.9244 |
| 0.5726 | 8.3556 | 100 | 0.7864 |
| 0.1759 | 12.5333 | 150 | 0.8009 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.1
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2