metadata
library_name: transformers
license: apache-2.0
base_model: bhadresh-savani/roberta-base-emotion
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CS221-roberta-base-emotion-finetuned-semeval
results: []
CS221-roberta-base-emotion-finetuned-semeval
This model is a fine-tuned version of bhadresh-savani/roberta-base-emotion on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4054
- F1: 0.7527
- Roc Auc: 0.8133
- Accuracy: 0.4585
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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4444 | 1.0 | 139 | 0.4241 | 0.6890 | 0.7666 | 0.3484 |
| 0.3719 | 2.0 | 278 | 0.3867 | 0.7102 | 0.7800 | 0.4079 |
| 0.2955 | 3.0 | 417 | 0.3791 | 0.7279 | 0.7953 | 0.4152 |
| 0.2207 | 4.0 | 556 | 0.3936 | 0.7515 | 0.8134 | 0.4477 |
| 0.1655 | 5.0 | 695 | 0.4155 | 0.7527 | 0.8170 | 0.4278 |
| 0.1111 | 6.0 | 834 | 0.4054 | 0.7527 | 0.8133 | 0.4585 |
| 0.0844 | 7.0 | 973 | 0.4482 | 0.7353 | 0.7976 | 0.4711 |
| 0.0655 | 8.0 | 1112 | 0.4649 | 0.7523 | 0.8118 | 0.4783 |
| 0.0475 | 9.0 | 1251 | 0.4960 | 0.7482 | 0.8107 | 0.4621 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0