roberta-large-pp-500000-1e-06-128
This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6630
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-06
- train_batch_size: 512
- eval_batch_size: 1024
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6867 | 1.0 | 977 | 0.6761 |
0.6819 | 2.0 | 1954 | 0.6705 |
0.6769 | 3.0 | 2931 | 0.6666 |
0.6766 | 4.0 | 3908 | 0.6638 |
0.6737 | 5.0 | 4885 | 0.6641 |
0.6718 | 6.0 | 5862 | 0.6618 |
0.6716 | 7.0 | 6839 | 0.6616 |
0.6696 | 8.0 | 7816 | 0.6611 |
0.6678 | 9.0 | 8793 | 0.6617 |
0.6665 | 10.0 | 9770 | 0.6621 |
0.664 | 11.0 | 10747 | 0.6622 |
0.6634 | 12.0 | 11724 | 0.6656 |
0.6625 | 13.0 | 12701 | 0.6630 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 22