metadata
library_name: transformers
license: mit
base_model: SamLowe/roberta-base-go_emotions
tags:
- generated_from_trainer
datasets:
- sem_eval_2018_task_1
metrics:
- f1
- accuracy
- precision
- recall
model-index:
- name: roberta-finetuned-sem_eval-english
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: sem_eval_2018_task_1
type: sem_eval_2018_task_1
config: subtask5.english
split: validation
args: subtask5.english
metrics:
- name: F1
type: f1
value: 0.7211585665193913
- name: Accuracy
type: accuracy
value: 0.29232505643340856
- name: Precision
type: precision
value: 0.7679038159958181
- name: Recall
type: recall
value: 0.6797778806108283
roberta-finetuned-sem_eval-english
This model is a fine-tuned version of SamLowe/roberta-base-go_emotions on the sem_eval_2018_task_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2916
- F1: 0.7212
- Roc Auc: 0.8106
- Accuracy: 0.2923
- Precision: 0.7679
- Recall: 0.6798
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: 8
- eval_batch_size: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|---|
| 0.2744 | 1.0 | 855 | 0.2948 | 0.7061 | 0.7988 | 0.2957 | 0.7668 | 0.6543 |
| 0.2593 | 2.0 | 1710 | 0.2917 | 0.7144 | 0.8033 | 0.2968 | 0.7781 | 0.6603 |
| 0.2315 | 3.0 | 2565 | 0.2916 | 0.7212 | 0.8106 | 0.2923 | 0.7679 | 0.6798 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.21.0