metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: HuTaoBot-ft
results: []
HuTaoBot-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: 1.0727
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 |
|---|---|---|---|
| 1.558 | 0.9895 | 47 | 1.3035 |
| 1.0713 | 2.0 | 95 | 1.0835 |
| 0.895 | 2.9895 | 142 | 0.9973 |
| 0.7621 | 4.0 | 190 | 0.9700 |
| 0.7046 | 4.9895 | 237 | 0.9687 |
| 0.6208 | 6.0 | 285 | 0.9818 |
| 0.578 | 6.9895 | 332 | 1.0058 |
| 0.5257 | 8.0 | 380 | 1.0421 |
| 0.5017 | 8.9895 | 427 | 1.0556 |
| 0.4695 | 9.8947 | 470 | 1.0727 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1