metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: modernbert-output
results: []
modernbert-output
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: 0.6180
- Accuracy: 0.8867
- Macro F1: 0.8872
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 3.0392 | 1.0 | 140 | 0.6617 | 0.8267 | 0.8251 |
| 1.4070 | 2.0 | 280 | 0.5377 | 0.8733 | 0.8759 |
| 0.5328 | 3.0 | 420 | 0.6954 | 0.86 | 0.8646 |
| 0.3036 | 4.0 | 560 | 0.6180 | 0.8867 | 0.8872 |
| 0.0971 | 5.0 | 700 | 0.6528 | 0.88 | 0.8813 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2