metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_ep6_lr5
results: []
BERT_ep6_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: 0.2877
- Precision: 0.6804
- Recall: 0.6408
- F1: 0.6600
- Accuracy: 0.9429
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 467 | 0.2952 | 0.6845 | 0.6360 | 0.6593 | 0.9425 |
| 0.2949 | 2.0 | 934 | 0.2919 | 0.6823 | 0.6379 | 0.6594 | 0.9428 |
| 0.2961 | 3.0 | 1401 | 0.2897 | 0.6819 | 0.6395 | 0.6600 | 0.9428 |
| 0.2845 | 4.0 | 1868 | 0.2884 | 0.6809 | 0.6406 | 0.6601 | 0.9428 |
| 0.29 | 5.0 | 2335 | 0.2878 | 0.6799 | 0.6406 | 0.6597 | 0.9429 |
| 0.2835 | 6.0 | 2802 | 0.2877 | 0.6804 | 0.6408 | 0.6600 | 0.9429 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2