xlm-roberta-base-NER-ind
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1404
- F1: 0.8130
Model description
Model is trained specifically for indian context, we used sentence-piece tokenizer to train the model, so use the sentences with proper delimeter like(. , ?) and appropiate capitalization of words.
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 2509 | 0.1427 | 0.7972 |
| No log | 2.0 | 5019 | 0.1366 | 0.8101 |
| 0.1384 | 3.0 | 7529 | 0.1366 | 0.8139 |
| 0.1384 | 4.0 | 10036 | 0.1404 | 0.8130 |
Framework versions
- Transformers 4.27.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3