metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: mistral-ft
results: []
mistral-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9210
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 |
|---|---|---|---|
| 1.9822 | 0.99 | 42 | 1.5521 |
| 1.4408 | 1.99 | 84 | 1.3540 |
| 1.2501 | 2.98 | 126 | 1.2406 |
| 1.0744 | 4.0 | 169 | 1.1296 |
| 0.9751 | 4.99 | 211 | 1.0512 |
| 0.8817 | 5.99 | 253 | 0.9931 |
| 0.8158 | 6.98 | 295 | 0.9602 |
| 0.7383 | 8.0 | 338 | 0.9393 |
| 0.7179 | 8.99 | 380 | 0.9236 |
| 0.6866 | 9.94 | 420 | 0.9210 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2