mistral_cot_simplest_qlora
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: 0.7150
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
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8904 | 1.0 | 3 | 0.8287 |
| 1.4592 | 2.0 | 6 | 0.7422 |
| 1.4592 | 3.0 | 9 | 0.7162 |
| 1.0477 | 3.4 | 10 | 0.7150 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.1.2
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for CharlesLi/mistral_cot_simplest_qlora
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1