|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
model-index: |
|
- name: balagpt-ft2 |
|
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. --> |
|
|
|
# balagpt-ft2 |
|
|
|
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: 0.6050 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3314 | 1.0 | 5 | 1.9312 | |
|
| 1.7381 | 2.0 | 10 | 1.4899 | |
|
| 1.3108 | 3.0 | 15 | 1.1581 | |
|
| 0.9634 | 4.0 | 20 | 0.9015 | |
|
| 0.718 | 5.0 | 25 | 0.7503 | |
|
| 0.5738 | 6.0 | 30 | 0.6664 | |
|
| 0.4784 | 7.0 | 35 | 0.6163 | |
|
| 0.4266 | 8.0 | 40 | 0.6102 | |
|
| 0.4016 | 9.0 | 45 | 0.6052 | |
|
| 0.3864 | 10.0 | 50 | 0.6050 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.15.2 |
