metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: goemotions-roberta-model
results: []
goemotions-roberta-model
This model is a fine-tuned version of roberta-base on an geoemotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.0817
- F1 Micro: 0.5864
- F1 Macro: 0.4282
- Precision Micro: 0.7067
- Recall Micro: 0.5010
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: 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Precision Micro | Recall Micro |
|---|---|---|---|---|---|---|---|
| 0.091 | 1.0 | 2714 | 0.0895 | 0.5482 | 0.3293 | 0.7346 | 0.4373 |
| 0.0822 | 2.0 | 5428 | 0.0837 | 0.5653 | 0.4060 | 0.7312 | 0.4608 |
| 0.0757 | 3.0 | 8142 | 0.0832 | 0.5803 | 0.4263 | 0.7003 | 0.4955 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1