metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: gpt2-rm-tldr
results: []
gpt2-rm-tldr
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0106
- Accuracy: 0.5547
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6765 | 1.0 | 2626 | 0.6814 | 0.5654 |
| 0.6797 | 2.0 | 5252 | 0.6723 | 0.5821 |
| 0.6248 | 3.0 | 7878 | 0.6872 | 0.5774 |
| 0.5794 | 4.0 | 10504 | 0.7225 | 0.5658 |
| 0.4361 | 5.0 | 13130 | 0.7765 | 0.5583 |
| 0.4558 | 6.0 | 15756 | 0.7988 | 0.5635 |
| 0.5247 | 7.0 | 18382 | 0.8247 | 0.5581 |
| 0.4311 | 8.0 | 21008 | 0.8917 | 0.5545 |
| 0.426 | 9.0 | 23634 | 0.9631 | 0.5527 |
| 0.3895 | 10.0 | 26260 | 1.0106 | 0.5547 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0