metadata
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_BIOMAT_NER1800
results: []
BERT_BIOMAT_NER1800
This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1528
- Precision: 0.8240
- Recall: 0.8614
- F1: 0.8422
- Accuracy: 0.9741
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.257 | 1.0 | 869 | 0.0952 | 0.7898 | 0.8157 | 0.8025 | 0.9694 |
| 0.0707 | 2.0 | 1738 | 0.1023 | 0.8197 | 0.8494 | 0.8343 | 0.9729 |
| 0.0412 | 3.0 | 2607 | 0.1078 | 0.8234 | 0.8569 | 0.8398 | 0.9739 |
| 0.0263 | 4.0 | 3476 | 0.1201 | 0.8178 | 0.8675 | 0.8419 | 0.9732 |
| 0.0143 | 5.0 | 4345 | 0.1208 | 0.8317 | 0.8572 | 0.8443 | 0.9748 |
| 0.0094 | 6.0 | 5214 | 0.1353 | 0.8212 | 0.8566 | 0.8385 | 0.9736 |
| 0.0059 | 7.0 | 6083 | 0.1476 | 0.8128 | 0.8644 | 0.8378 | 0.9732 |
| 0.0047 | 8.0 | 6952 | 0.1474 | 0.8208 | 0.8630 | 0.8414 | 0.9741 |
| 0.0032 | 9.0 | 7821 | 0.1572 | 0.8129 | 0.8550 | 0.8334 | 0.9728 |
| 0.0024 | 10.0 | 8690 | 0.1528 | 0.8240 | 0.8614 | 0.8422 | 0.9741 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1