metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: TMJgpt-ft
results: []
TMJgpt-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: 3.3234
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 |
|---|---|---|---|
| 1.9423 | 1.0 | 1 | 3.9858 |
| 1.9404 | 2.0 | 2 | 3.9314 |
| 1.974 | 3.0 | 3 | 3.8068 |
| 1.8247 | 4.0 | 4 | 3.6860 |
| 1.7804 | 5.0 | 5 | 3.5791 |
| 1.6929 | 6.0 | 6 | 3.4900 |
| 1.6617 | 7.0 | 7 | 3.4212 |
| 1.5972 | 8.0 | 8 | 3.3715 |
| 1.5936 | 9.0 | 9 | 3.3391 |
| 1.5556 | 10.0 | 10 | 3.3234 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2