mistral-QLORA-FT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2209
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.4143 | 0.1 | 135 | 1.2817 |
1.2203 | 0.2 | 270 | 1.2299 |
1.2193 | 0.3 | 405 | 1.2281 |
1.2127 | 0.4 | 540 | 1.2252 |
1.1912 | 0.5 | 675 | 1.2238 |
1.1855 | 0.6 | 810 | 1.2236 |
1.1998 | 0.7 | 945 | 1.2216 |
1.1959 | 0.8 | 1080 | 1.2219 |
1.1884 | 0.9 | 1215 | 1.2210 |
1.1988 | 1.0 | 1350 | 1.2209 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0
Model tree for eperim/mistral-QLORA-FT
Base model
mistralai/Mistral-7B-v0.1
Finetuned
mistralai/Mistral-7B-Instruct-v0.1