gpt2-rm-tldr
This model was trained from scratch on the summarize_from_feedback dataset. It achieves the following results on the evaluation set:
- Loss: 2.3421
- Accuracy: 0.5240
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.89 | 1.0 | 92858 | 2.1223 | 0.5385 |
1.7813 | 2.0 | 185716 | 2.2080 | 0.5263 |
1.6242 | 3.0 | 278574 | 2.3421 | 0.5240 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 0
Evaluation results
- Accuracy on summarize_from_feedbackvalidation set self-reported0.524