metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: modernbert-disfluency
results: []
modernbert-disfluency
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1619
- Precision: 0.8263
- Recall: 0.7602
- F1: 0.7919
- Accuracy: 0.9556
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: 4e-05
- train_batch_size: 64
- eval_batch_size: 128
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 49 | 0.3026 | 0.8905 | 0.5 | 0.6404 | 0.9178 |
| No log | 2.0 | 98 | 0.2426 | 0.8512 | 0.5861 | 0.6942 | 0.9340 |
| 0.4156 | 3.0 | 147 | 0.1860 | 0.8020 | 0.6721 | 0.7313 | 0.9464 |
| 0.4156 | 4.0 | 196 | 0.1633 | 0.8263 | 0.7602 | 0.7919 | 0.9556 |
| 0.1117 | 5.0 | 245 | 0.1810 | 0.8025 | 0.7992 | 0.8008 | 0.9554 |
| 0.1117 | 6.0 | 294 | 0.1832 | 0.782 | 0.8012 | 0.7915 | 0.9561 |
| 0.0401 | 7.0 | 343 | 0.1956 | 0.8043 | 0.7746 | 0.7891 | 0.9554 |
| 0.0401 | 8.0 | 392 | 0.1973 | 0.7864 | 0.7848 | 0.7856 | 0.9563 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0