roberta-base-finetuned-semeval24
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7332
- Accuracy: 0.8425
- F1: 0.8423
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 7485 | 1.0596 | 0.8307 | 0.8304 |
0.0205 | 2.0 | 14970 | 1.1700 | 0.8619 | 0.8620 |
0.0205 | 3.0 | 22455 | 1.1577 | 0.8704 | 0.8704 |
0.0041 | 4.0 | 29940 | 1.4886 | 0.8308 | 0.8300 |
0.0041 | 5.0 | 37425 | 1.7332 | 0.8425 | 0.8423 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1,335
Model tree for andricValdez/roberta-base-finetuned-semeval24
Base model
FacebookAI/roberta-base