Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
CMS-Results
This model is a fine-tuned version of PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6764
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3035 | 0.8571 | 3 | 1.8262 |
| 1.2484 | 2.0 | 7 | 1.2039 |
| 1.158 | 2.8571 | 10 | 1.0290 |
| 0.7415 | 4.0 | 14 | 0.8352 |
| 0.7861 | 4.8571 | 17 | 0.7549 |
| 0.5122 | 6.0 | 21 | 0.6964 |
| 0.6129 | 6.8571 | 24 | 0.6842 |
| 0.4332 | 8.0 | 28 | 0.6770 |
| 0.4938 | 8.5714 | 30 | 0.6764 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support