|
--- |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: aiHumangpt-ft |
|
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. --> |
|
|
|
# aiHumangpt-ft |
|
|
|
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: 1.4106 |
|
|
|
## 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: 12 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.5789 | 1.0 | 9 | 2.5621 | |
|
| 2.167 | 2.0 | 18 | 1.7742 | |
|
| 1.6487 | 3.0 | 27 | 1.5763 | |
|
| 1.5012 | 4.0 | 36 | 1.5012 | |
|
| 1.4015 | 5.0 | 45 | 1.4344 | |
|
| 1.3308 | 6.0 | 54 | 1.4161 | |
|
| 1.2814 | 7.0 | 63 | 1.4146 | |
|
| 1.2415 | 8.0 | 72 | 1.3996 | |
|
| 1.2038 | 9.0 | 81 | 1.4044 | |
|
| 1.1733 | 10.0 | 90 | 1.4044 | |
|
| 1.1414 | 11.0 | 99 | 1.4122 | |
|
| 1.1275 | 12.0 | 108 | 1.4106 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.42.4 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
