---
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Assignment4-modernbert-optuna-tuned
  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. -->

# Assignment4-modernbert-optuna-tuned

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: 0.4052
- Accuracy: 0.9739

## 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: 6e-05
- train_batch_size: 32
- eval_batch_size: 8
- 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: cosine
- num_epochs: 8

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 12.0069       | 0.2096 | 100  | 5.0978          | 0.7661   |
| 3.4684        | 0.4193 | 200  | 2.0509          | 0.9206   |
| 1.8229        | 0.6289 | 300  | 1.5597          | 0.9452   |
| 1.4306        | 0.8386 | 400  | 1.2236          | 0.9535   |
| 1.1           | 1.0482 | 500  | 1.0535          | 0.9613   |
| 0.8086        | 1.2579 | 600  | 0.8738          | 0.9665   |
| 0.7382        | 1.4675 | 700  | 0.8479          | 0.9597   |
| 0.6412        | 1.6771 | 800  | 0.7502          | 0.9677   |
| 0.6152        | 1.8868 | 900  | 0.7203          | 0.9687   |
| 0.5391        | 2.0964 | 1000 | 0.6897          | 0.9652   |
| 0.4475        | 2.3061 | 1100 | 0.6466          | 0.9713   |
| 0.4256        | 2.5157 | 1200 | 0.6227          | 0.9674   |
| 0.3984        | 2.7254 | 1300 | 0.5820          | 0.9719   |
| 0.3809        | 2.9350 | 1400 | 0.5644          | 0.9710   |
| 0.3424        | 3.1447 | 1500 | 0.5406          | 0.9710   |
| 0.3176        | 3.3543 | 1600 | 0.5278          | 0.9723   |
| 0.2981        | 3.5639 | 1700 | 0.5222          | 0.9719   |
| 0.2939        | 3.7736 | 1800 | 0.4962          | 0.9729   |
| 0.2858        | 3.9832 | 1900 | 0.4803          | 0.9739   |
| 0.2494        | 4.1929 | 2000 | 0.4714          | 0.9742   |
| 0.235         | 4.4025 | 2100 | 0.4656          | 0.9729   |
| 0.2318        | 4.6122 | 2200 | 0.4559          | 0.9735   |
| 0.2298        | 4.8218 | 2300 | 0.4485          | 0.9723   |
| 0.2276        | 5.0314 | 2400 | 0.4356          | 0.9752   |
| 0.1969        | 5.2411 | 2500 | 0.4308          | 0.9729   |
| 0.1937        | 5.4507 | 2600 | 0.4225          | 0.9739   |
| 0.1883        | 5.6604 | 2700 | 0.4213          | 0.9739   |
| 0.1873        | 5.8700 | 2800 | 0.4149          | 0.9748   |
| 0.181         | 6.0797 | 2900 | 0.4126          | 0.9758   |
| 0.1725        | 6.2893 | 3000 | 0.4111          | 0.9739   |
| 0.1649        | 6.4990 | 3100 | 0.4092          | 0.9752   |
| 0.1638        | 6.7086 | 3200 | 0.4071          | 0.9742   |
| 0.1614        | 6.9182 | 3300 | 0.4064          | 0.9742   |
| 0.1591        | 7.1279 | 3400 | 0.4058          | 0.9735   |
| 0.1541        | 7.3375 | 3500 | 0.4061          | 0.9735   |
| 0.157         | 7.5472 | 3600 | 0.4053          | 0.9739   |
| 0.1564        | 7.7568 | 3700 | 0.4052          | 0.9739   |
| 0.1541        | 7.9665 | 3800 | 0.4052          | 0.9739   |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1