metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BERT_trainer_irony
results: []
BERT_trainer_irony
This model is a fine-tuned version of bert-base-uncased on the irony dataset. It achieves the following results on the evaluation set:
- Loss: 2.3282
- Accuracy: 0.7015
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 358 | 1.4982 | 0.7005 |
| 0.1652 | 2.0 | 716 | 1.9033 | 0.7047 |
| 0.0643 | 3.0 | 1074 | 2.0941 | 0.7079 |
| 0.0643 | 4.0 | 1432 | 2.3087 | 0.7016 |
| 0.0161 | 5.0 | 1790 | 2.3704 | 0.7026 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2