metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
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: 1.8978
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 |
|---|---|---|---|
| 3.4004 | 0.92 | 9 | 2.6415 |
| 2.5356 | 1.95 | 19 | 2.3921 |
| 2.2429 | 2.97 | 29 | 2.2271 |
| 2.0182 | 4.0 | 39 | 2.0984 |
| 2.0963 | 4.92 | 48 | 2.0157 |
| 1.7926 | 5.95 | 58 | 1.9555 |
| 1.7221 | 6.97 | 68 | 1.9214 |
| 1.6816 | 8.0 | 78 | 1.9057 |
| 1.8335 | 8.92 | 87 | 1.8983 |
| 1.2605 | 9.23 | 90 | 1.8978 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2