metadata
base_model: lupobricco/irony_classification_single_label_base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: ironita_finetuned_singlelabel_prompet
results: []
ironita_finetuned_singlelabel_prompet
This model is a fine-tuned version of lupobricco/irony_classification_single_label_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2508
- Accuracy: 0.8436
- F1: 0.5211
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: 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4657 | 1.0 | 715 | 0.7454 | 0.8110 | 0.5087 |
| 0.2039 | 2.0 | 1430 | 0.8910 | 0.8265 | 0.4871 |
| 0.0559 | 3.0 | 2145 | 1.0045 | 0.8282 | 0.4603 |
| 0.0434 | 4.0 | 2860 | 1.0742 | 0.8454 | 0.5008 |
| 0.0297 | 5.0 | 3575 | 1.2070 | 0.8436 | 0.4886 |
| 0.0108 | 6.0 | 4290 | 1.2899 | 0.8368 | 0.5006 |
| 0.0154 | 7.0 | 5005 | 1.1797 | 0.8540 | 0.5073 |
| 0.0081 | 8.0 | 5720 | 1.1496 | 0.8436 | 0.5047 |
| 0.0092 | 9.0 | 6435 | 1.2508 | 0.8436 | 0.5211 |
| 0.0052 | 10.0 | 7150 | 1.2359 | 0.8471 | 0.4992 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1