141dca80922f5b74521b2e9d0ee115de
This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-dutch on the dair-ai/emotion [split] dataset. It achieves the following results on the evaluation set:
- Loss: 1.5750
- Data Size: 0.5
- Epoch Runtime: 47.5928
- Accuracy: 0.3488
- F1 Macro: 0.0862
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 | 1.6425 | 0 | 3.6305 | 0.3483 | 0.0861 |
| No log | 1 | 500 | 1.5901 | 0.0078 | 4.3656 | 0.3503 | 0.0886 |
| No log | 2 | 1000 | 1.6324 | 0.0156 | 5.7164 | 0.3488 | 0.0862 |
| No log | 3 | 1500 | 1.4146 | 0.0312 | 7.8872 | 0.5045 | 0.2001 |
| No log | 4 | 2000 | 1.5093 | 0.0625 | 11.1827 | 0.4753 | 0.2283 |
| 0.0804 | 5 | 2500 | 1.6279 | 0.125 | 16.7889 | 0.3488 | 0.0862 |
| 1.6153 | 6 | 3000 | 1.4557 | 0.25 | 27.0646 | 0.4798 | 0.2012 |
| 0.2618 | 7 | 3500 | 1.5750 | 0.5 | 47.5928 | 0.3488 | 0.0862 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu128
- Datasets 4.3.0
- Tokenizers 0.22.1
- Downloads last month
- 15