edos-2023-baseline-albert-base-v2-label_vector
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8762
- F1: 0.1946
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 2.1002 | 1.18 | 100 | 1.9982 | 0.1023 |
| 1.7832 | 2.35 | 200 | 1.8435 | 0.1310 |
| 1.57 | 3.53 | 300 | 1.8097 | 0.1552 |
| 1.3719 | 4.71 | 400 | 1.8216 | 0.1631 |
| 1.2072 | 5.88 | 500 | 1.8138 | 0.1811 |
| 1.0186 | 7.06 | 600 | 1.8762 | 0.1946 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2