metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: emotion_roberta_weighted
results: []
emotion_roberta_weighted
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2084
- Accuracy: 0.9315
- Precision: 0.9379
- Recall: 0.9315
- F1: 0.9331
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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3177 | 1.0 | 1000 | 0.2423 | 0.918 | 0.9245 | 0.918 | 0.9195 |
| 0.1804 | 2.0 | 2000 | 0.1776 | 0.931 | 0.9366 | 0.931 | 0.9317 |
| 0.1504 | 3.0 | 3000 | 0.1740 | 0.935 | 0.9410 | 0.935 | 0.9362 |
| 0.1203 | 4.0 | 4000 | 0.1723 | 0.9405 | 0.9438 | 0.9405 | 0.9413 |
| 0.0889 | 5.0 | 5000 | 0.2068 | 0.939 | 0.9420 | 0.939 | 0.9398 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1