README.md

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: 0.7207163601161665
          - name: Accuracy
            type: accuracy
            value: 0.2799097065462754
          - name: Precision
            type: precision
            value: 0.7554540842212075
          - name: Recall
            type: recall
            value: 0.6890328551596483

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: 0.3097
• F1: 0.7207
• Roc Auc: 0.8127
• Accuracy: 0.2799
• Precision: 0.7555
• Recall: 0.6890

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy	Precision	Recall
0.3684	1.0	855	0.3003	0.7060	0.7973	0.3070	0.7749	0.6483
0.2776	2.0	1710	0.2930	0.7082	0.7978	0.3025	0.7823	0.6469
0.2441	3.0	2565	0.3019	0.7111	0.8025	0.2968	0.7684	0.6617
0.2205	4.0	3420	0.3008	0.7140	0.8060	0.2698	0.7618	0.6719
0.2002	5.0	4275	0.3058	0.7184	0.8109	0.2709	0.7555	0.6849
0.1844	6.0	5130	0.3097	0.7207	0.8127	0.2799	0.7555	0.6890
0.1692	7.0	5985	0.3110	0.7159	0.8102	0.2709	0.7482	0.6863

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0