Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
mistral_instruct_generation
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: 0.8332
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.512 | 1.0 | 54 | 0.6552 |
| 0.4596 | 2.0 | 108 | 0.6418 |
| 0.4171 | 3.0 | 162 | 0.6418 |
| 0.365 | 4.0 | 216 | 0.6537 |
| 0.3229 | 5.0 | 270 | 0.6853 |
| 0.2619 | 6.0 | 324 | 0.7207 |
| 0.208 | 7.0 | 378 | 0.7621 |
| 0.191 | 8.0 | 432 | 0.8332 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Model tree for Soaky/tmp
Base model
mistralai/Mistral-7B-Instruct-v0.2