feel_it_finetuned_pro_emit_multilabel
This model is a fine-tuned version of MilaNLProc/feel-it-italian-emotion on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2721
- F1: 0.3969
- Roc Auc: 0.6350
- Accuracy: 0.2715
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
0.3541 | 1.0 | 521 | 0.3107 | 0.1097 | 0.5273 | 0.1787 |
0.2737 | 2.0 | 1042 | 0.2823 | 0.2870 | 0.5859 | 0.2405 |
0.2345 | 3.0 | 1563 | 0.2756 | 0.3665 | 0.6203 | 0.2646 |
0.2089 | 4.0 | 2084 | 0.2786 | 0.3760 | 0.6257 | 0.2715 |
0.1939 | 5.0 | 2605 | 0.2721 | 0.3969 | 0.6350 | 0.2715 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2