ironita_finetuned_singlelabel_no_correlations
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: 1.0734
- Accuracy: 0.8162
- F1: 0.4358
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 |
---|---|---|---|---|---|
0.4699 | 1.0 | 715 | 0.6672 | 0.8316 | 0.4141 |
0.2082 | 2.0 | 1430 | 1.0734 | 0.8162 | 0.4358 |
0.0699 | 3.0 | 2145 | 1.2288 | 0.8179 | 0.4059 |
0.0356 | 4.0 | 2860 | 1.2345 | 0.8213 | 0.4194 |
0.0245 | 5.0 | 3575 | 1.3995 | 0.8265 | 0.4007 |
0.0137 | 6.0 | 4290 | 1.4029 | 0.8230 | 0.4222 |
0.0166 | 7.0 | 5005 | 1.4924 | 0.8213 | 0.4000 |
0.0079 | 8.0 | 5720 | 1.5032 | 0.8299 | 0.3961 |
0.0126 | 9.0 | 6435 | 1.5878 | 0.8213 | 0.4285 |
0.0046 | 10.0 | 7150 | 1.5537 | 0.8213 | 0.4050 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 16
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for lupobricco/ironita_finetuned_singlelabel_no_correlations
Base model
Musixmatch/umberto-commoncrawl-cased-v1
Finetuned
this model