---
library_name: transformers
license: mit
base_model: jhu-clsp/mmBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: router-mmBERT-base-6e-5-batch64
  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. -->

# router-mmBERT-base-6e-5-batch64

This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6451
- Accuracy: 0.6251
- Precision: 0.6246
- Recall: 0.6251
- F1: 0.6229

## 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: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 1.379         | 0.0929 | 100  | 0.7915          | 0.5262   | 0.6719    | 0.5262 | 0.3662 |
| 1.3923        | 0.1859 | 200  | 0.6671          | 0.6013   | 0.6284    | 0.6013 | 0.5650 |
| 1.3808        | 0.2788 | 300  | 0.6831          | 0.5710   | 0.6836    | 0.5710 | 0.4720 |
| 1.358         | 0.3717 | 400  | 0.6631          | 0.5903   | 0.5927    | 0.5903 | 0.5904 |
| 1.308         | 0.4647 | 500  | 0.6580          | 0.6024   | 0.6031    | 0.6024 | 0.5955 |
| 1.3378        | 0.5576 | 600  | 0.6953          | 0.5295   | 0.5883    | 0.5295 | 0.4701 |
| 1.3219        | 0.6506 | 700  | 0.6657          | 0.5765   | 0.5888    | 0.5765 | 0.5710 |
| 1.3212        | 0.7435 | 800  | 0.6580          | 0.5958   | 0.5953    | 0.5958 | 0.5954 |
| 1.2893        | 0.8364 | 900  | 0.6612          | 0.5919   | 0.6025    | 0.5919 | 0.5883 |
| 1.2436        | 0.9294 | 1000 | 0.6543          | 0.6151   | 0.6225    | 0.6151 | 0.6011 |
| 1.3296        | 1.0223 | 1100 | 0.6509          | 0.6157   | 0.6311    | 0.6157 | 0.5941 |
| 1.2985        | 1.1152 | 1200 | 0.6564          | 0.6151   | 0.6157    | 0.6151 | 0.6101 |
| 1.1993        | 1.2082 | 1300 | 0.6562          | 0.6013   | 0.6085    | 0.6013 | 0.5997 |
| 1.2665        | 1.3011 | 1400 | 0.6832          | 0.5699   | 0.5980    | 0.5699 | 0.5520 |
| 1.2523        | 1.3941 | 1500 | 0.6548          | 0.6068   | 0.6062    | 0.6068 | 0.6062 |
| 1.1899        | 1.4870 | 1600 | 0.6545          | 0.6173   | 0.6166    | 0.6173 | 0.6162 |
| 1.2433        | 1.5799 | 1700 | 0.6487          | 0.6240   | 0.6264    | 0.6240 | 0.6169 |
| 1.2378        | 1.6729 | 1800 | 0.6507          | 0.6201   | 0.6196    | 0.6201 | 0.6197 |
| 1.2489        | 1.7658 | 1900 | 0.6441          | 0.6322   | 0.6340    | 0.6322 | 0.6268 |
| 1.2625        | 1.8587 | 2000 | 0.6448          | 0.6273   | 0.6271    | 0.6273 | 0.6245 |
| 1.3145        | 1.9517 | 2100 | 0.6451          | 0.6251   | 0.6246    | 0.6251 | 0.6229 |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1