metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: sqlm
results: []
sqlm
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3178
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.539 | 0.0333 | 20 | 0.4674 |
| 0.3767 | 0.0667 | 40 | 0.3872 |
| 0.3646 | 0.1 | 60 | 0.3610 |
| 0.3425 | 0.1333 | 80 | 0.3428 |
| 0.3554 | 0.1667 | 100 | 0.3416 |
| 0.3363 | 0.2 | 120 | 0.3343 |
| 0.2963 | 0.2333 | 140 | 0.3316 |
| 0.3263 | 0.2667 | 160 | 0.3278 |
| 0.3226 | 0.3 | 180 | 0.3222 |
| 0.3217 | 0.3333 | 200 | 0.3178 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1