metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: >-
BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-ContaminationQAmodel_PubmedBERT
results: []
BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-ContaminationQAmodel_PubmedBERT
This model is a fine-tuned version of Sotireas/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-ContaminationQAmodel_PubmedBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8993
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 |
|---|---|---|---|
| No log | 1.0 | 22 | 3.7532 |
| No log | 2.0 | 44 | 3.3351 |
| No log | 3.0 | 66 | 2.9546 |
| No log | 4.0 | 88 | 2.7920 |
| No log | 5.0 | 110 | 2.7378 |
| No log | 6.0 | 132 | 2.8442 |
| No log | 7.0 | 154 | 2.8171 |
| No log | 8.0 | 176 | 2.8177 |
| No log | 9.0 | 198 | 2.8956 |
| No log | 10.0 | 220 | 2.8993 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.12.1