metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: mistral-sql-finetune
results: []
mistral-sql-finetune
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: 1.7687
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.349 | 0.52 | 25 | 1.5889 |
| 1.1213 | 1.04 | 50 | 1.3232 |
| 0.6369 | 1.56 | 75 | 1.3226 |
| 0.525 | 2.08 | 100 | 1.3375 |
| 0.256 | 2.6 | 125 | 1.5105 |
| 0.2127 | 3.12 | 150 | 1.4755 |
| 0.145 | 3.65 | 175 | 1.6525 |
| 0.1388 | 4.17 | 200 | 1.7168 |
| 0.114 | 4.69 | 225 | 1.7377 |
| 0.1076 | 5.21 | 250 | 1.7087 |
| 0.0986 | 5.73 | 275 | 1.7649 |
| 0.0912 | 6.25 | 300 | 1.7687 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.0