BERT2BERT_Model
This model is a fine-tuned version of patrickvonplaten/bert2bert_cnn_daily_mail on the cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 1.9217
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 63 | 1.9514 |
| No log | 2.0 | 126 | 1.9279 |
| No log | 3.0 | 189 | 1.9223 |
| No log | 4.0 | 252 | 1.9217 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3