metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: emotion_classifier_roberta_optimized
results: []
emotion_classifier_roberta_optimized
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1972
- Macro F1: 0.4889
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 |
|---|---|---|---|---|
| 0.2093 | 1.0 | 2614 | 0.2019 | 0.4586 |
| 0.1941 | 2.0 | 5228 | 0.1938 | 0.4815 |
| 0.1845 | 3.0 | 7842 | 0.1916 | 0.4921 |
| 0.1764 | 4.0 | 10456 | 0.1928 | 0.4918 |
| 0.1699 | 5.0 | 13070 | 0.1936 | 0.4963 |
| 0.1639 | 6.0 | 15684 | 0.1964 | 0.4872 |
| 0.1608 | 7.0 | 18298 | 0.1972 | 0.4889 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1