albert-xxlarge-v2-disaster-twitter-preprocess_data
This model is a fine-tuned version of albert-xxlarge-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4819
- F1: 0.7818
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.603 | 1.0 | 762 | 0.6956 | 0.0 |
| 0.5915 | 2.0 | 1524 | 0.7287 | 0.7011 |
| 0.5551 | 3.0 | 2286 | 0.5446 | 0.7629 |
| 0.4994 | 4.0 | 3048 | 0.4434 | 0.7722 |
| 0.4244 | 5.0 | 3810 | 0.4622 | 0.7840 |
| 0.4126 | 6.0 | 4572 | 0.4819 | 0.7818 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2