CRAB_albert_base_finetuned
This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0693
- F1: 0.7264
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.1559 | 1.0 | 2880 | 1.2804 | 0.6444 |
| 1.0303 | 2.0 | 5760 | 1.3236 | 0.6986 |
| 0.8925 | 3.0 | 8640 | 1.0502 | 0.7014 |
| 0.9221 | 4.0 | 11520 | 1.0111 | 0.7194 |
| 0.7799 | 5.0 | 14400 | 1.0462 | 0.7083 |
| 0.7661 | 6.0 | 17280 | 1.0564 | 0.7236 |
| 0.7346 | 7.0 | 20160 | 1.0643 | 0.7250 |
| 0.6651 | 8.0 | 23040 | 1.0693 | 0.7264 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1