metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: NER_EHR_Spanish_model_Mulitlingual_BERT
results: []
NER_EHR_Spanish_model_Mulitlingual_BERT
This model is a fine-tuned version of bert-base-multilingual-cased on the DisTEMIST shared task 2022 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2603
- Precision: 0.5637
- Recall: 0.5801
- F1: 0.5718
- Accuracy: 0.9534
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
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 71 | 0.2060 | 0.5017 | 0.5540 | 0.5266 | 0.9496 |
| No log | 2.0 | 142 | 0.2163 | 0.5363 | 0.5433 | 0.5398 | 0.9495 |
| No log | 3.0 | 213 | 0.2245 | 0.5521 | 0.5356 | 0.5438 | 0.9514 |
| No log | 4.0 | 284 | 0.2453 | 0.5668 | 0.5985 | 0.5822 | 0.9522 |
| No log | 5.0 | 355 | 0.2433 | 0.5657 | 0.5579 | 0.5617 | 0.9530 |
| No log | 6.0 | 426 | 0.2553 | 0.5762 | 0.5762 | 0.5762 | 0.9536 |
| No log | 7.0 | 497 | 0.2603 | 0.5637 | 0.5801 | 0.5718 | 0.9534 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.0
- Tokenizers 0.12.1