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_NER3600_ST_DA
results: []
BERT_BIOMAT_NER3600_ST_DA
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: 0.3385
- Precision: 0.9673
- Recall: 0.9631
- F1: 0.9652
- Accuracy: 0.9636
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2217 | 1.0 | 601 | 0.2356 | 0.9543 | 0.9508 | 0.9525 | 0.9472 |
| 0.0692 | 2.0 | 1202 | 0.2555 | 0.9571 | 0.9529 | 0.9550 | 0.9525 |
| 0.0406 | 3.0 | 1803 | 0.2416 | 0.9626 | 0.9584 | 0.9605 | 0.9584 |
| 0.0257 | 4.0 | 2404 | 0.2984 | 0.9644 | 0.9594 | 0.9619 | 0.9598 |
| 0.011 | 5.0 | 3005 | 0.2851 | 0.9663 | 0.9622 | 0.9643 | 0.9627 |
| 0.0079 | 6.0 | 3606 | 0.3022 | 0.9665 | 0.9622 | 0.9644 | 0.9627 |
| 0.0056 | 7.0 | 4207 | 0.3214 | 0.9668 | 0.9619 | 0.9644 | 0.9625 |
| 0.0043 | 8.0 | 4808 | 0.3227 | 0.9673 | 0.9631 | 0.9652 | 0.9636 |
| 0.0036 | 9.0 | 5409 | 0.3405 | 0.9672 | 0.9629 | 0.9650 | 0.9634 |
| 0.0025 | 10.0 | 6010 | 0.3385 | 0.9673 | 0.9631 | 0.9652 | 0.9636 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1