Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
mixtral-id-finetune
This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1219
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: 2.5e-05
- train_batch_size: 1
- eval_batch_size: 8
- 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: 5
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2409 | 0.8 | 100 | 1.2049 |
| 0.8688 | 1.61 | 200 | 0.9088 |
| 0.4839 | 2.41 | 300 | 0.7087 |
| 0.3185 | 3.21 | 400 | 0.4974 |
| 0.2613 | 4.02 | 500 | 0.3109 |
| 0.1669 | 4.82 | 600 | 0.2226 |
| 0.1152 | 5.62 | 700 | 0.1797 |
| 0.0965 | 6.43 | 800 | 0.1413 |
| 0.072 | 7.23 | 900 | 0.1307 |
| 0.0822 | 8.03 | 1000 | 0.1219 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Krisbiantoro/mixtral-id-finetune
Base model
mistralai/Mixtral-8x7B-v0.1