metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: modernbert_agree_classifier
results: []
modernbert_agree_classifier
This model is a fine-tuned version of answerdotai/ModernBERT-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4925
- Accuracy: 0.8698
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: 6.000000000000001e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 12
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3307 | 0.2757 | 50 | 0.8133 | 0.5547 |
| 2.4211 | 0.5515 | 100 | 0.6010 | 0.6615 |
| 1.9701 | 0.8272 | 150 | 0.5964 | 0.6901 |
| 0.2215 | 1.0993 | 200 | 0.6405 | 0.7109 |
| 0.1582 | 1.375 | 250 | 0.4628 | 0.7995 |
| 0.1519 | 1.6507 | 300 | 0.4207 | 0.7995 |
| 0.8939 | 1.9265 | 350 | 0.4925 | 0.8698 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1