<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
lilt-xfund-fr-iob
This model is a fine-tuned version of pierreguillou/lilt-xlm-roberta-base-finetuned-funsd-iob-original on the xfun dataset. It achieves the following results on the evaluation set:
- Loss: 1.4385
- Precision: 0.6709
- Recall: 0.7392
- F1: 0.7034
- Accuracy: 0.7833
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.96 | 100 | 0.7562 | 0.5429 | 0.6605 | 0.5959 | 0.7588 |
| No log | 3.92 | 200 | 0.8666 | 0.5334 | 0.7085 | 0.6086 | 0.7490 |
| No log | 5.88 | 300 | 0.9068 | 0.6037 | 0.6967 | 0.6469 | 0.7826 |
| No log | 7.84 | 400 | 1.0555 | 0.6568 | 0.6416 | 0.6491 | 0.7724 |
| 0.3799 | 9.8 | 500 | 1.1015 | 0.6258 | 0.7106 | 0.6655 | 0.7569 |
| 0.3799 | 11.76 | 600 | 1.2493 | 0.6828 | 0.7291 | 0.7052 | 0.7815 |
| 0.3799 | 13.73 | 700 | 1.3291 | 0.6506 | 0.7308 | 0.6883 | 0.7742 |
| 0.3799 | 15.69 | 800 | 1.4046 | 0.6397 | 0.7543 | 0.6923 | 0.7707 |
| 0.3799 | 17.65 | 900 | 1.4320 | 0.6754 | 0.7291 | 0.7012 | 0.7839 |
| 0.0245 | 19.61 | 1000 | 1.4385 | 0.6709 | 0.7392 | 0.7034 | 0.7833 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
