feel_it_finetuned_pro_multilbel_corr_prompt
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: 0.2933
- F1: 0.3525
- Roc Auc: 0.6148
- Accuracy: 0.2354
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 |
---|---|---|---|---|---|---|
No log | 1.0 | 146 | 0.3572 | 0.0 | 0.5 | 0.1254 |
No log | 2.0 | 292 | 0.3331 | 0.0465 | 0.5109 | 0.1271 |
No log | 3.0 | 438 | 0.3051 | 0.2798 | 0.5830 | 0.2045 |
0.351 | 4.0 | 584 | 0.2950 | 0.3059 | 0.5938 | 0.2199 |
0.351 | 5.0 | 730 | 0.2933 | 0.3525 | 0.6148 | 0.2354 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1