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: 1.3256
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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.595 | 0.9231 | 3 | 3.9759 |
| 4.0506 | 1.8462 | 6 | 3.4371 |
| 3.4359 | 2.7692 | 9 | 2.9322 |
| 2.1831 | 4.0 | 13 | 2.4351 |
| 2.4838 | 4.9231 | 16 | 2.1189 |
| 2.0545 | 5.8462 | 19 | 1.8192 |
| 1.7214 | 6.7692 | 22 | 1.6274 |
| 1.1606 | 8.0 | 26 | 1.4483 |
| 1.4113 | 8.9231 | 29 | 1.4009 |
| 1.3405 | 9.8462 | 32 | 1.3765 |
| 1.3347 | 10.7692 | 35 | 1.3599 |
| 0.9488 | 12.0 | 39 | 1.3411 |
| 1.2643 | 12.9231 | 42 | 1.3325 |
| 1.2198 | 13.8462 | 45 | 1.3287 |
| 1.2212 | 14.7692 | 48 | 1.3284 |
| 0.9143 | 16.0 | 52 | 1.3271 |
| 1.1902 | 16.9231 | 55 | 1.3265 |
| 1.173 | 17.8462 | 58 | 1.3258 |
| 0.8301 | 18.4615 | 60 | 1.3256 |
Framework versions
- PEFT 0.13.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1