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: 3.1333
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 |
|---|---|---|---|
| 5.1816 | 1.0 | 15 | 3.7507 |
| 3.3719 | 2.0 | 30 | 3.2293 |
| 2.9505 | 3.0 | 45 | 3.0788 |
| 2.8035 | 4.0 | 60 | 3.0585 |
| 2.7233 | 5.0 | 75 | 3.0513 |
| 2.6164 | 6.0 | 90 | 3.0617 |
| 2.536 | 7.0 | 105 | 3.0923 |
| 2.492 | 8.0 | 120 | 3.1055 |
| 2.4345 | 9.0 | 135 | 3.1233 |
| 2.391 | 10.0 | 150 | 3.1333 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1