---
license: mit
library_name: peft
tags:
- trl
- reward-trainer
- generated_from_trainer
base_model: openai-community/gpt2-large
metrics:
- accuracy
model-index:
- name: RM-HH-Human_helpful_human_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse
  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. -->

# RM-HH-Human_helpful_human_loraR64_40000_gpt2-large_shuffleTrue_extractchosenFalse

This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co./openai-community/gpt2-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6036
- Accuracy: 0.6751

## 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: 1.41e-05
- train_batch_size: 1
- eval_batch_size: 8
- 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
- num_epochs: 2.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.7205        | 0.03  | 250   | 0.7030          | 0.5251   |
| 0.6845        | 0.06  | 500   | 0.6752          | 0.5739   |
| 0.6715        | 0.08  | 750   | 0.6636          | 0.5934   |
| 0.6632        | 0.11  | 1000  | 0.6542          | 0.6102   |
| 0.6432        | 0.14  | 1250  | 0.6492          | 0.6125   |
| 0.635         | 0.17  | 1500  | 0.6462          | 0.6200   |
| 0.6708        | 0.19  | 1750  | 0.6413          | 0.6240   |
| 0.6565        | 0.22  | 2000  | 0.6394          | 0.6285   |
| 0.6194        | 0.25  | 2250  | 0.6355          | 0.6315   |
| 0.6405        | 0.28  | 2500  | 0.6326          | 0.6380   |
| 0.6431        | 0.31  | 2750  | 0.6285          | 0.6428   |
| 0.6526        | 0.33  | 3000  | 0.6254          | 0.6415   |
| 0.639         | 0.36  | 3250  | 0.6246          | 0.6433   |
| 0.621         | 0.39  | 3500  | 0.6217          | 0.6501   |
| 0.6305        | 0.42  | 3750  | 0.6200          | 0.6488   |
| 0.6146        | 0.45  | 4000  | 0.6194          | 0.6501   |
| 0.6382        | 0.47  | 4250  | 0.6166          | 0.6558   |
| 0.6211        | 0.5   | 4500  | 0.6143          | 0.6606   |
| 0.6141        | 0.53  | 4750  | 0.6135          | 0.6601   |
| 0.6272        | 0.56  | 5000  | 0.6119          | 0.6591   |
| 0.6242        | 0.58  | 5250  | 0.6103          | 0.6608   |
| 0.6202        | 0.61  | 5500  | 0.6087          | 0.6658   |
| 0.6205        | 0.64  | 5750  | 0.6080          | 0.6666   |
| 0.6268        | 0.67  | 6000  | 0.6069          | 0.6663   |
| 0.6017        | 0.7   | 6250  | 0.6064          | 0.6638   |
| 0.5942        | 0.72  | 6500  | 0.6060          | 0.6656   |
| 0.6186        | 0.75  | 6750  | 0.6053          | 0.6668   |
| 0.6316        | 0.78  | 7000  | 0.6040          | 0.6688   |
| 0.6031        | 0.81  | 7250  | 0.6039          | 0.6738   |
| 0.6143        | 0.84  | 7500  | 0.6021          | 0.6703   |
| 0.6217        | 0.86  | 7750  | 0.6020          | 0.6759   |
| 0.6099        | 0.89  | 8000  | 0.6017          | 0.6754   |
| 0.5951        | 0.92  | 8250  | 0.6010          | 0.6748   |
| 0.603         | 0.95  | 8500  | 0.6005          | 0.6721   |
| 0.6098        | 0.97  | 8750  | 0.6005          | 0.6769   |
| 0.6222        | 1.0   | 9000  | 0.5991          | 0.6741   |
| 0.6005        | 1.03  | 9250  | 0.5991          | 0.6743   |
| 0.5972        | 1.06  | 9500  | 0.5998          | 0.6706   |
| 0.582         | 1.09  | 9750  | 0.6043          | 0.6691   |
| 0.6004        | 1.11  | 10000 | 0.6187          | 0.6711   |
| 0.5985        | 1.14  | 10250 | 0.6195          | 0.6663   |
| 0.6206        | 1.17  | 10500 | 0.6122          | 0.6693   |
| 0.6216        | 1.2   | 10750 | 0.6069          | 0.6741   |
| 0.6091        | 1.22  | 11000 | 0.6236          | 0.6691   |
| 0.5863        | 1.25  | 11250 | 0.6209          | 0.6713   |
| 0.641         | 1.28  | 11500 | 0.6184          | 0.6698   |
| 0.6144        | 1.31  | 11750 | 0.6051          | 0.6713   |
| 0.6527        | 1.34  | 12000 | 0.6067          | 0.6703   |
| 0.6059        | 1.36  | 12250 | 0.6048          | 0.6711   |
| 0.6138        | 1.39  | 12500 | 0.6015          | 0.6741   |
| 0.6376        | 1.42  | 12750 | 0.6002          | 0.6726   |
| 0.6273        | 1.45  | 13000 | 0.5989          | 0.6721   |
| 0.6028        | 1.48  | 13250 | 0.6011          | 0.6713   |
| 0.6116        | 1.5   | 13500 | 0.5999          | 0.6723   |
| 0.6201        | 1.53  | 13750 | 0.5990          | 0.6733   |
| 0.606         | 1.56  | 14000 | 0.6024          | 0.6733   |
| 0.5985        | 1.59  | 14250 | 0.6079          | 0.6716   |
| 0.664         | 1.61  | 14500 | 0.6019          | 0.6748   |
| 0.5859        | 1.64  | 14750 | 0.6039          | 0.6743   |
| 0.6231        | 1.67  | 15000 | 0.6002          | 0.6733   |
| 0.5984        | 1.7   | 15250 | 0.6020          | 0.6741   |
| 0.602         | 1.73  | 15500 | 0.6037          | 0.6741   |
| 0.5817        | 1.75  | 15750 | 0.6031          | 0.6748   |
| 0.6128        | 1.78  | 16000 | 0.6040          | 0.6743   |
| 0.6415        | 1.81  | 16250 | 0.6047          | 0.6748   |
| 0.6084        | 1.84  | 16500 | 0.6041          | 0.6743   |
| 0.6103        | 1.87  | 16750 | 0.6040          | 0.6746   |
| 0.6289        | 1.89  | 17000 | 0.6033          | 0.6746   |
| 0.5948        | 1.92  | 17250 | 0.6030          | 0.6759   |
| 0.5655        | 1.95  | 17500 | 0.6033          | 0.6748   |
| 0.6125        | 1.98  | 17750 | 0.6036          | 0.6751   |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2