Software engineering Chatbot English
Collection
This collection will hold the models and dataset that has been used to developed the investigation. Specifically the ones that are in English
•
6 items
•
Updated
Mistral-7B-Instruct-v0.2-finetune-SWE_70_30_EN
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0943
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8789 | 1.0 | 1443 | 1.4980 |
| 1.141 | 2.0 | 2886 | 1.5139 |
| 0.941 | 3.0 | 4329 | 1.6951 |
| 1.2378 | 4.0 | 5772 | 1.8812 |
| 0.3967 | 5.0 | 7215 | 2.0943 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for JuanjoLopez19/Mistral-7B-Instruct-v0.2-finetune-SWE_70_30_EN
Base model
mistralai/Mistral-7B-Instruct-v0.2