|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
model-index: |
|
- name: Finetune-test3 |
|
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. --> |
|
|
|
# Finetune-test3 |
|
|
|
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 the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6143 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.1515 | 0.9956 | 56 | 0.7617 | |
|
| 0.7099 | 1.9911 | 112 | 0.6591 | |
|
| 0.6427 | 2.9867 | 168 | 0.6336 | |
|
| 0.5897 | 4.0 | 225 | 0.6145 | |
|
| 0.5634 | 4.9956 | 281 | 0.6038 | |
|
| 0.5328 | 5.9911 | 337 | 0.6003 | |
|
| 0.5084 | 6.9867 | 393 | 0.6019 | |
|
| 0.4793 | 8.0 | 450 | 0.6030 | |
|
| 0.4718 | 8.9956 | 506 | 0.6088 | |
|
| 0.4559 | 9.9556 | 560 | 0.6143 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
