Trial_mistral_class1-8
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: 0.7730
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9419 | 0.9863 | 18 | 0.8789 |
| 0.8087 | 1.9726 | 36 | 0.8034 |
| 0.7813 | 2.9589 | 54 | 0.7808 |
| 0.7764 | 4.0 | 73 | 0.7736 |
| 0.7691 | 4.9315 | 90 | 0.7730 |
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
- 9
Model tree for Aishwarya-r/trial_mistral_fine_tuned_class1-8
Base model
mistralai/Mistral-7B-v0.1