Mistral Summarization
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the scitldr dataset. It achieves the following results on the evaluation set:
- Loss: 2.1059
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0732 | 0.1 | 200 | 2.1863 |
| 2.1324 | 0.2 | 400 | 2.1925 |
| 2.103 | 0.3 | 600 | 2.1876 |
| 2.0766 | 0.4 | 800 | 2.1737 |
| 2.0825 | 0.5 | 1000 | 2.1555 |
| 2.0731 | 0.6 | 1200 | 2.1465 |
| 2.0819 | 0.7 | 1400 | 2.1355 |
| 1.9802 | 0.8 | 1600 | 2.1223 |
| 2.0466 | 0.9 | 1800 | 2.1059 |
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
- 8
Inference API (serverless) does not yet support peft models for this pipeline type.
Model tree for pkbiswas/Mistral-7B-Summarization-QLoRa
Base model
mistralai/Mistral-7B-Instruct-v0.2