metadata
license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ddi_42
results: []
ddi_42
This model is a fine-tuned version of microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2085
- Accuracy: 0.9551
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-05
- train_batch_size: 32
- eval_batch_size: 256
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 791 | 0.1986 | 0.9383 |
| 0.1723 | 2.0 | 1582 | 0.2700 | 0.9455 |
| 0.0772 | 3.0 | 2373 | 0.2085 | 0.9551 |
| 0.0516 | 4.0 | 3164 | 0.2970 | 0.9427 |
| 0.0516 | 5.0 | 3955 | 0.2620 | 0.9539 |
| 0.0341 | 6.0 | 4746 | 0.3973 | 0.9423 |
| 0.0203 | 7.0 | 5537 | 0.3637 | 0.9423 |
| 0.0146 | 8.0 | 6328 | 0.4154 | 0.9451 |
| 0.007 | 9.0 | 7119 | 0.4219 | 0.9463 |
| 0.007 | 10.0 | 7910 | 0.4098 | 0.9447 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2