xlm-roberta-base-english-sentweet-targeted-insult
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5427
- Accuracy: 0.7986
- Precision: 0.8227
- Recall: 0.8117
- F1: 0.7980
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.5726 | 0.7917 | 0.7978 | 0.7985 | 0.7917 |
| No log | 2.0 | 162 | 0.4808 | 0.8056 | 0.8274 | 0.8180 | 0.8051 |
| No log | 3.0 | 243 | 0.4858 | 0.7951 | 0.8108 | 0.8058 | 0.7949 |
| No log | 4.0 | 324 | 0.4680 | 0.8090 | 0.8230 | 0.8191 | 0.8089 |
| No log | 5.0 | 405 | 0.5224 | 0.8056 | 0.8092 | 0.8112 | 0.8055 |
| No log | 6.0 | 486 | 0.5427 | 0.7986 | 0.8227 | 0.8117 | 0.7980 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0