metadata
base_model: lupobricco/feel_it_finetuned_pro_emit_multilabel2
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: multilabel_emotion_classification_finetuned_multimodal
results: []
multilabel_emotion_classification_finetuned_multimodal
This model is a fine-tuned version of lupobricco/feel_it_finetuned_pro_emit_multilabel2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2360
- F1: 0.5623
- Roc Auc: 0.7470
- Accuracy: 0.3913
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
No log | 1.0 | 35 | 0.2273 | 0.5136 | 0.6927 | 0.3188 |
No log | 2.0 | 70 | 0.2323 | 0.5474 | 0.7234 | 0.3768 |
No log | 3.0 | 105 | 0.2337 | 0.5017 | 0.7033 | 0.3478 |
No log | 4.0 | 140 | 0.2330 | 0.5432 | 0.7425 | 0.3623 |
No log | 5.0 | 175 | 0.2282 | 0.5592 | 0.7402 | 0.3768 |
No log | 6.0 | 210 | 0.2392 | 0.5431 | 0.7365 | 0.3768 |
No log | 7.0 | 245 | 0.2357 | 0.5281 | 0.7230 | 0.3551 |
No log | 8.0 | 280 | 0.2342 | 0.5526 | 0.7367 | 0.3623 |
No log | 9.0 | 315 | 0.2360 | 0.5623 | 0.7470 | 0.3913 |
No log | 10.0 | 350 | 0.2348 | 0.5478 | 0.7396 | 0.3768 |
Framework versions
- Transformers 4.39.3
- Pytorch 1.11.0
- Datasets 2.18.0
- Tokenizers 0.15.2