76e5f50559a0a7058767e719950784aa
This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-german on the contemmcm/clickbait dataset. It achieves the following results on the evaluation set:
- Loss: 0.0164
- Data Size: 0.25
- Epoch Runtime: 36.0777
- Accuracy: 0.9983
- F1 Macro: 0.9982
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Data Size | Epoch Runtime | Accuracy | F1 Macro |
|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 0.6300 | 0 | 8.0126 | 0.6740 | 0.5514 |
| No log | 1 | 650 | 0.4274 | 0.0078 | 8.9236 | 0.7818 | 0.7818 |
| No log | 2 | 1300 | 0.0135 | 0.0156 | 10.3509 | 0.9967 | 0.9965 |
| No log | 3 | 1950 | 0.0281 | 0.0312 | 12.3868 | 0.9959 | 0.9957 |
| No log | 4 | 2600 | 0.0627 | 0.0625 | 16.1683 | 0.9938 | 0.9935 |
| 0.0042 | 5 | 3250 | 0.0324 | 0.125 | 23.1871 | 0.9969 | 0.9967 |
| 0.0004 | 6 | 3900 | 0.0164 | 0.25 | 36.0777 | 0.9983 | 0.9982 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1
- Downloads last month
- 1