metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RoBERTa-Large-full-finetuned-ner-pablo
results: []
RoBERTa-Large-full-finetuned-ner-pablo
This model is a fine-tuned version of FacebookAI/roberta-large on the n2c2 2018 dataset for the paper https://arxiv.org/abs/2409.19467. It achieves the following results on the evaluation set:
- Loss: 0.0738
- Precision: 0.8113
- Recall: 0.8082
- F1: 0.8098
- Accuracy: 0.9782
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 231 | 0.0809 | 0.7947 | 0.7638 | 0.7789 | 0.9764 |
| No log | 2.0 | 462 | 0.0713 | 0.8097 | 0.7929 | 0.8012 | 0.9779 |
| 0.2213 | 3.0 | 693 | 0.0704 | 0.8092 | 0.8046 | 0.8069 | 0.9780 |
| 0.2213 | 4.0 | 924 | 0.0738 | 0.8113 | 0.8082 | 0.8098 | 0.9782 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1