04-20-14-55-32
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6289
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: 4
- eval_batch_size: 8
- 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 |
---|---|---|---|
0.6969 | 0.21 | 10 | 0.7061 |
0.6804 | 0.42 | 20 | 0.6963 |
0.6893 | 0.62 | 30 | 0.6743 |
0.6645 | 0.83 | 40 | 0.6494 |
0.671 | 1.04 | 50 | 0.6519 |
0.6783 | 1.25 | 60 | 0.6416 |
0.669 | 1.46 | 70 | 0.6353 |
0.6687 | 1.67 | 80 | 0.6313 |
0.6324 | 1.88 | 90 | 0.6274 |
0.5749 | 2.08 | 100 | 0.6299 |
0.694 | 2.29 | 110 | 0.6284 |
0.6727 | 2.5 | 120 | 0.6279 |
0.6529 | 2.71 | 130 | 0.6279 |
0.6182 | 2.92 | 140 | 0.6289 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3
Model tree for reeddg/04-20-14-55-32
Base model
facebook/bart-base