<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
biolinkbert-large-mnli-resampled
This model is a fine-tuned version of BioLinkBERT-large on the
resampled version of GLUE MNLI, i.e. cnut1648/mnli_resampled_as_mednli.
The performance is reported below:
| Model | Dataset | Acc |
|---|---|---|
| Roberta-large-mnli | MNLI dev mm | 90.12 |
| MNLI dev m | 90.59 | |
| SNLI test | 88.25 | |
| BioLinkBERT-large | MNLI dev mm | 33.56 |
| MNLI dev m | 33.18 | |
| SNLI test | 32.66 | |
| BioLinkBERT-large-mnli-snli | MNLI dev mm | 85.75 |
| MNLI dev m | 85.30 | |
| SNLI test | 89.82 | |
| BioLinkBERT-large-mnli-resampled | MNLI dev mm | 80.22 |
| MNLI dev m | 78.07 | |
| SNLI test | 71.33 |
Compared to cnut1648/biolinkbert-large-mnli-snli, this checkpoint is never trained on SNLI.
The labels are "0": "entailment", "1": "neutral", "2": "contradiction"
Training procedure
We follow the same training procedure as cnut1648/biolinkbert-large-mnli-snli.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-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: 3.0
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu117
- Datasets 2.4.0
- Tokenizers 0.12.1
