roberta-base-isarcasm
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6208
- Accuracy: 0.7982
- F1: 0.4317
- Precision: 0.4304
- Recall: 0.4331
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
No log | 1.0 | 215 | 0.7162 | 0.8286 | 0.0 | 0.0 | 0.0 |
No log | 2.0 | 430 | 0.9168 | 0.7143 | 0.1667 | 0.1667 | 0.1667 |
0.6391 | 3.0 | 645 | 1.2142 | 0.6857 | 0.1538 | 0.1429 | 0.1667 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 109
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for w11wo/roberta-base-isarcasm
Base model
FacebookAI/roberta-base