PAN-2024-transformer-base_bert-base-cased_K1
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7468
- F1 Macro: 0.3333
- F1: 0.6667
- F1 Neg: 0.0
- Acc: 0.5
- Prec: 0.5
- Recall: 1.0
- Mcc: 0.0
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 0.7356 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -1.0 |
| No log | 2.0 | 2 | 0.7468 | 0.3333 | 0.6667 | 0.0 | 0.5 | 0.5 | 1.0 | 0.0 |
| No log | 3.0 | 3 | 0.7527 | 0.3333 | 0.6667 | 0.0 | 0.5 | 0.5 | 1.0 | 0.0 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2