---
library_name: transformers
language:
- en
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
- matthews_correlation
model-index:
- name: DisamBertCrossEncoder-base
  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. -->

# DisamBertCrossEncoder-base

This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3160
- Precision: 0.6783
- Recall: 0.5978
- F1: 0.6355
- Accuracy: 0.9378
- Matthews Correlation: 0.6031

## 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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 320
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy | Matthews Correlation |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|:--------------------:|
| No log        | 0     | 0     | 1123.2456       | 0.0907    | 1.0    | 0.1663 | 0.0909   | 0.0045               |
| 0.1943        | 1.0   | 9050  | 0.1832          | 0.7346    | 0.2615 | 0.3857 | 0.9245   | 0.4096               |
| 0.1500        | 2.0   | 18100 | 0.1551          | 0.7019    | 0.4967 | 0.5817 | 0.9352   | 0.5574               |
| 0.1242        | 3.0   | 27150 | 0.1481          | 0.7381    | 0.5451 | 0.6271 | 0.9412   | 0.6040               |
| 0.1017        | 4.0   | 36200 | 0.1482          | 0.7413    | 0.5604 | 0.6383 | 0.9424   | 0.6147               |
| 0.0774        | 5.0   | 45250 | 0.1564          | 0.7179    | 0.6154 | 0.6627 | 0.9432   | 0.6342               |
| 0.0610        | 6.0   | 54300 | 0.1859          | 0.7579    | 0.5297 | 0.6235 | 0.9420   | 0.6044               |
| 0.0434        | 7.0   | 63350 | 0.2016          | 0.6754    | 0.6264 | 0.6499 | 0.9388   | 0.6170               |
| 0.0298        | 8.0   | 72400 | 0.2480          | 0.6520    | 0.6505 | 0.6513 | 0.9368   | 0.6165               |
| 0.0216        | 9.0   | 81450 | 0.2961          | 0.6819    | 0.5890 | 0.6321 | 0.9378   | 0.6002               |
| 0.0174        | 10.0  | 90500 | 0.3160          | 0.6783    | 0.5978 | 0.6355 | 0.9378   | 0.6031               |


### Framework versions

- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2