metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: fine-tuned-models
results: []
fine-tuned-models
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: 0.6877
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 |
|---|---|---|---|
| 3.3763 | 1.0 | 9 | 2.6717 |
| 2.0147 | 2.0 | 18 | 1.5139 |
| 1.0198 | 3.0 | 27 | 0.8928 |
| 0.6552 | 4.0 | 36 | 0.7814 |
| 0.5873 | 5.0 | 45 | 0.7472 |
| 0.547 | 6.0 | 54 | 0.7261 |
| 0.5265 | 7.0 | 63 | 0.7083 |
| 0.5026 | 8.0 | 72 | 0.6918 |
| 0.4908 | 9.0 | 81 | 0.6896 |
| 0.4732 | 10.0 | 90 | 0.6877 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1