metadata
base_model: allenai/scibert_scivocab_cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scibert_ner_drugname
results: []
scibert_ner_drugname
This model is a fine-tuned version of allenai/scibert_scivocab_cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1243
- Precision: 0.7631
- Recall: 0.8520
- F1: 0.8051
- Accuracy: 0.9722
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0733 | 1.0 | 120 | 0.1176 | 0.6466 | 0.7713 | 0.7035 | 0.9583 |
| 0.0069 | 2.0 | 240 | 0.1126 | 0.6757 | 0.7848 | 0.7261 | 0.9654 |
| 0.0521 | 3.0 | 360 | 0.0949 | 0.7461 | 0.8565 | 0.7975 | 0.9707 |
| 0.0217 | 4.0 | 480 | 0.0972 | 0.7171 | 0.8296 | 0.7692 | 0.9718 |
| 0.001 | 5.0 | 600 | 0.1111 | 0.7422 | 0.8520 | 0.7933 | 0.9707 |
| 0.0044 | 6.0 | 720 | 0.1138 | 0.7664 | 0.8386 | 0.8009 | 0.9715 |
| 0.0011 | 7.0 | 840 | 0.1155 | 0.7449 | 0.8251 | 0.7830 | 0.9699 |
| 0.0006 | 8.0 | 960 | 0.1213 | 0.7344 | 0.8430 | 0.7850 | 0.9716 |
| 0.0289 | 9.0 | 1080 | 0.1238 | 0.7661 | 0.8520 | 0.8068 | 0.9718 |
| 0.0096 | 10.0 | 1200 | 0.1243 | 0.7631 | 0.8520 | 0.8051 | 0.9722 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2