<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-base-unlabeled-TAPT-1
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.4796
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|
6.717 | 1.0 | 11745 | 6.4991 |
6.4748 | 2.0 | 23490 | 6.4190 |
6.4206 | 3.0 | 35235 | 6.3913 |
6.3812 | 4.0 | 46980 | 6.3563 |
6.3519 | 5.0 | 58725 | 6.3469 |
6.3213 | 6.0 | 70470 | 6.3090 |
6.2171 | 7.0 | 82215 | 6.0984 |
6.02 | 8.0 | 93960 | 5.8050 |
5.7684 | 9.0 | 105705 | 5.5697 |
5.6202 | 10.0 | 117450 | 5.4783 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3