Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
mistral_instruct_generation_own_data
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.4734
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
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6476 | 2.5 | 20 | 0.4816 |
| 0.3414 | 5.0 | 40 | 0.3842 |
| 0.2565 | 7.5 | 60 | 0.3931 |
| 0.1973 | 10.0 | 80 | 0.4198 |
| 0.1245 | 12.5 | 100 | 0.4734 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for abdullahfurquan/mistral_instruct_generation_own_data
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1