irony_en_Australia
This model is a fine-tuned version of roberta-base on part of the EPIC dataset. It achieves the following results on the evaluation set:
- Loss: 0.0036
- Accuracy: 0.7201
- Precision: 0.5758
- Recall: 0.4318
- F1: 0.4935
Model description
The model is trained considering the annotation of annotators from Australia only. The annotations from these annotators are aggregated using majority voting and then used to train the model.
Training and evaluation data
The model has been trained on the annotation from annotators from Australia from the EPIC dataset. The data has been randomly split into a train and a validation set.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.0044 | 1.0 | 79 | 0.0042 | 0.6866 | 0.5455 | 0.0455 | 0.0839 |
0.004 | 2.0 | 158 | 0.0038 | 0.5120 | 0.3831 | 0.8939 | 0.5364 |
0.0036 | 3.0 | 237 | 0.0037 | 0.6890 | 0.5139 | 0.2803 | 0.3627 |
0.0028 | 4.0 | 316 | 0.0027 | 0.6699 | 0.4803 | 0.5530 | 0.5141 |
0.0022 | 5.0 | 395 | 0.0025 | 0.6651 | 0.4759 | 0.5985 | 0.5302 |
0.0014 | 6.0 | 474 | 0.0041 | 0.7081 | 0.5625 | 0.3409 | 0.4245 |
0.0009 | 7.0 | 553 | 0.0036 | 0.7201 | 0.5758 | 0.4318 | 0.4935 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 3
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 Multilingual-Perspectivist-NLU/irony_en_Australia
Base model
FacebookAI/roberta-base
Finetuned
this model