Trial_mistral_peft1
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.1756
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: 1e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4277 | 1.0 | 10 | 1.1765 |
| 1.2805 | 2.0 | 20 | 1.1762 |
| 1.3768 | 3.0 | 30 | 1.1755 |
| 1.1784 | 4.0 | 40 | 1.1756 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for Aishwarya-r/trial_mistral_fine_tuned
Base model
mistralai/Mistral-7B-v0.1