---
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Assignment4_Finetuned_ModernBERT_V2
  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_Finetuned_ModernBERT_V2

This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1926
- Accuracy: 0.9713
- F1: 0.9709

## 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: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
| 2.5497        | 0.2096 | 100  | 0.7948          | 0.7981   | 0.7867 |
| 0.514         | 0.4193 | 200  | 0.5135          | 0.8674   | 0.8618 |
| 0.3511        | 0.6289 | 300  | 0.4394          | 0.9      | 0.8968 |
| 0.2795        | 0.8386 | 400  | 0.3201          | 0.9258   | 0.9241 |
| 0.2055        | 1.0482 | 500  | 0.3262          | 0.9258   | 0.9248 |
| 0.1421        | 1.2579 | 600  | 0.3060          | 0.94     | 0.9391 |
| 0.1235        | 1.4675 | 700  | 0.3153          | 0.9352   | 0.9357 |
| 0.1166        | 1.6771 | 800  | 0.2892          | 0.9432   | 0.9427 |
| 0.0941        | 1.8868 | 900  | 0.2639          | 0.9513   | 0.9513 |
| 0.0832        | 2.0964 | 1000 | 0.2272          | 0.9587   | 0.9584 |
| 0.0331        | 2.3061 | 1100 | 0.2210          | 0.96     | 0.9596 |
| 0.0509        | 2.5157 | 1200 | 0.2112          | 0.9587   | 0.9582 |
| 0.023         | 2.7254 | 1300 | 0.2087          | 0.9597   | 0.9590 |
| 0.0206        | 2.9350 | 1400 | 0.2072          | 0.9645   | 0.9638 |
| 0.0194        | 3.1447 | 1500 | 0.1981          | 0.9639   | 0.9635 |
| 0.0101        | 3.3543 | 1600 | 0.1958          | 0.9697   | 0.9693 |
| 0.0052        | 3.5639 | 1700 | 0.2033          | 0.9687   | 0.9683 |
| 0.0056        | 3.7736 | 1800 | 0.1985          | 0.97     | 0.9696 |
| 0.0117        | 3.9832 | 1900 | 0.1914          | 0.9716   | 0.9713 |
| 0.0021        | 4.1929 | 2000 | 0.1910          | 0.9719   | 0.9716 |
| 0.0015        | 4.4025 | 2100 | 0.1916          | 0.9716   | 0.9712 |
| 0.0024        | 4.6122 | 2200 | 0.1926          | 0.9713   | 0.9709 |
| 0.0008        | 4.8218 | 2300 | 0.1926          | 0.9713   | 0.9709 |


### Framework versions

- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1