<!-- 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. -->
BERiT_14500
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 8.0316
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: 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: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
8.3825 | 0.19 | 500 | 8.3006 |
8.2426 | 0.39 | 1000 | 8.2751 |
8.1622 | 0.58 | 1500 | 8.2504 |
8.1673 | 0.77 | 2000 | 8.1935 |
8.1597 | 0.97 | 2500 | 8.1928 |
8.0644 | 1.16 | 3000 | 8.1111 |
8.0724 | 1.36 | 3500 | 8.0820 |
8.0654 | 1.55 | 4000 | 8.0655 |
8.0649 | 1.74 | 4500 | 8.0896 |
8.051 | 1.94 | 5000 | 8.0838 |
8.0003 | 2.13 | 5500 | 8.0989 |
7.9795 | 2.32 | 6000 | 8.0729 |
7.9984 | 2.52 | 6500 | 8.0566 |
7.9935 | 2.71 | 7000 | 8.0757 |
7.9652 | 2.9 | 7500 | 8.0316 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2