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: 1.7223
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 |
|---|---|---|---|
| 4.5924 | 0.9231 | 3 | 3.9679 |
| 4.0409 | 1.8462 | 6 | 3.4397 |
| 3.4533 | 2.7692 | 9 | 2.9787 |
| 2.2369 | 4.0 | 13 | 2.5334 |
| 2.6207 | 4.9231 | 16 | 2.2558 |
| 2.2754 | 5.8462 | 19 | 2.0435 |
| 2.0148 | 6.7692 | 22 | 1.8828 |
| 1.4114 | 8.0 | 26 | 1.7663 |
| 1.7947 | 8.9231 | 29 | 1.7272 |
| 1.2532 | 9.2308 | 30 | 1.7223 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1