mistral-7b-sft-lora-ha
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.3798
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2779 | 1.0 | 15 | 1.9971 |
| 1.8274 | 2.0 | 30 | 1.6368 |
| 1.5549 | 3.0 | 45 | 1.4508 |
| 1.4289 | 4.0 | 60 | 1.3850 |
| 1.3983 | 5.0 | 75 | 1.3798 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for HachiML/mistral-7b-sft-lora-ha-v0.2_cleaned
Base model
mistralai/Mistral-7B-Instruct-v0.2