distilbert_sharetask-finetuned_on_codemixed
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4642
- F1: 0.7804
- Precision: 0.7858
- Recall: 0.7765
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| 0.7045 | 1.0 | 689 | 0.6764 | 0.5846 | 0.5903 | 0.5837 |
| 0.6184 | 2.0 | 1378 | 0.6711 | 0.5226 | 0.6352 | 0.6017 |
| 0.3388 | 3.0 | 2067 | 0.6906 | 0.7117 | 0.7403 | 0.7041 |
| 0.2945 | 4.0 | 2756 | 1.0159 | 0.7216 | 0.7223 | 0.7346 |
| 0.0386 | 5.0 | 3445 | 1.2326 | 0.7602 | 0.7627 | 0.7582 |
| 0.1029 | 6.0 | 4134 | 1.3244 | 0.7663 | 0.7663 | 0.7663 |
| 0.0162 | 7.0 | 4823 | 1.4642 | 0.7804 | 0.7858 | 0.7765 |
| 0.0003 | 8.0 | 5512 | 1.6629 | 0.7508 | 0.7502 | 0.7514 |
| 0.078 | 9.0 | 6201 | 1.7105 | 0.7677 | 0.7662 | 0.7694 |
| 0.0555 | 10.0 | 6890 | 1.7501 | 0.7624 | 0.7622 | 0.7626 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 2