---
library_name: transformers
license: mit
base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: arxiv_model
  results: []
---

<!-- 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. -->

# arxiv_model

This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3191
- Accuracy: 0.4606

## 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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 2.2414        | 1.0    | 1468 | 2.5282          | 0.3647   |
| 1.8278        | 2.0    | 2936 | 2.1141          | 0.4429   |
| 1.45          | 3.0    | 4404 | 2.1294          | 0.4538   |
| 1.0671        | 4.0    | 5872 | 2.2140          | 0.4576   |
| 0.7401        | 4.9968 | 7335 | 2.3191          | 0.4606   |


### Framework versions

- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1