---
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ModernBert-distilled-Bayesian_Assign4
  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. -->

# ModernBert-distilled-Bayesian_Assign4

This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2843
- Accuracy: 0.9632

## 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: 32
- eval_batch_size: 32
- seed: 42
- 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: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.7039        | 1.0   | 477  | 0.7901          | 0.9223   |
| 0.3159        | 2.0   | 954  | 0.4548          | 0.9506   |
| 0.0871        | 3.0   | 1431 | 0.3953          | 0.9584   |
| 0.0512        | 4.0   | 1908 | 0.3407          | 0.9606   |
| 0.0382        | 5.0   | 2385 | 0.3271          | 0.9616   |
| 0.03          | 6.0   | 2862 | 0.3090          | 0.9610   |
| 0.0243        | 7.0   | 3339 | 0.2933          | 0.9642   |
| 0.0217        | 8.0   | 3816 | 0.2898          | 0.9645   |
| 0.0189        | 9.0   | 4293 | 0.2863          | 0.9635   |
| 0.018         | 10.0  | 4770 | 0.2843          | 0.9632   |


### Framework versions

- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1