social-behavior-emotions
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2910
- Precision: 0.9233
- Recall: 0.9175
- F1: 0.9190
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 1.5671 | 1.0 | 800 | 0.5302 | 0.8664 | 0.8469 | 0.8502 |
| 0.4396 | 2.0 | 1600 | 0.3693 | 0.9118 | 0.9 | 0.9019 |
| 0.3103 | 3.0 | 2400 | 0.2973 | 0.9230 | 0.9125 | 0.9146 |
| 0.1984 | 4.0 | 3200 | 0.3098 | 0.9191 | 0.9125 | 0.9132 |
| 0.1283 | 5.0 | 4000 | 0.2910 | 0.9233 | 0.9175 | 0.9190 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2