metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: shawgpt-ft
results: []
shawgpt-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6530
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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.357 | 0.8696 | 5 | 3.0087 |
| 2.4657 | 1.9130 | 11 | 1.9289 |
| 1.4759 | 2.9565 | 17 | 1.1384 |
| 0.9201 | 4.0 | 23 | 0.8529 |
| 0.8763 | 4.8696 | 28 | 0.7490 |
| 0.6308 | 5.9130 | 34 | 0.6914 |
| 0.5899 | 6.9565 | 40 | 0.6642 |
| 0.566 | 8.0 | 46 | 0.6556 |
| 0.5894 | 8.6957 | 50 | 0.6530 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1