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-lr0.0002-wd0.001
results: []
shawgpt-ft-lr0.0002-wd0.001
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: 1.7845
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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6121 | 0.9231 | 3 | 4.0587 |
| 4.2126 | 1.8462 | 6 | 3.6493 |
| 3.7297 | 2.7692 | 9 | 3.2522 |
| 2.4733 | 4.0 | 13 | 2.8156 |
| 2.9598 | 4.9231 | 16 | 2.5689 |
| 2.6551 | 5.8462 | 19 | 2.3614 |
| 2.3985 | 6.7692 | 22 | 2.1826 |
| 1.6623 | 8.0 | 26 | 1.9991 |
| 2.0403 | 8.9231 | 29 | 1.8808 |
| 1.9001 | 9.8462 | 32 | 1.8158 |
| 1.8688 | 10.7692 | 35 | 1.7877 |
| 0.3703 | 11.0769 | 36 | 1.7845 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.19.1