metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_ep5_lr5
results: []
BERT_ep5_lr5
This model is a fine-tuned version of ajtamayoh/NER_EHR_Spanish_model_Mulitlingual_BERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2959
- Precision: 0.6769
- Recall: 0.6346
- F1: 0.6551
- Accuracy: 0.9424
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-09
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 467 | 0.3013 | 0.6775 | 0.6310 | 0.6534 | 0.9421 |
| 0.2977 | 2.0 | 934 | 0.2985 | 0.6764 | 0.6326 | 0.6538 | 0.9423 |
| 0.2958 | 3.0 | 1401 | 0.2967 | 0.6774 | 0.6343 | 0.6551 | 0.9423 |
| 0.2906 | 4.0 | 1868 | 0.2960 | 0.6769 | 0.6346 | 0.6551 | 0.9423 |
| 0.2833 | 5.0 | 2335 | 0.2959 | 0.6769 | 0.6346 | 0.6551 | 0.9424 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3