|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
model-index: |
|
- name: Mistral-7B-Instruct-v0.2-GPTQ_retrained_IoV |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Mistral-7B-Instruct-v0.2-GPTQ_retrained_IoV |
|
|
|
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.3976 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 4.1739 | 0.9412 | 4 | 3.4659 | |
|
| 4.0195 | 1.8824 | 8 | 3.3893 | |
|
| 3.2322 | 2.8235 | 12 | 3.2363 | |
|
| 2.0625 | 4.0 | 17 | 3.0555 | |
|
| 2.2884 | 4.9412 | 21 | 2.9109 | |
|
| 2.1576 | 5.8824 | 25 | 2.7795 | |
|
| 2.0546 | 6.8235 | 29 | 2.6220 | |
|
| 1.5652 | 8.0 | 34 | 2.4955 | |
|
| 1.8893 | 8.9412 | 38 | 2.4207 | |
|
| 1.6427 | 9.4118 | 40 | 2.3976 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
