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: 0.7424
- Accuracy: 0.5687
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: 6
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- 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
- training_steps: 550
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.327 | 0.1497 | 50 | 0.6950 | 0.5640 |
| 1.5088 | 0.2994 | 100 | 0.6833 | 0.5687 |
| 1.2018 | 0.4491 | 150 | 0.6867 | 0.5687 |
| 1.3053 | 0.5988 | 200 | 0.6923 | 0.5687 |
| 1.2024 | 0.7485 | 250 | 0.6879 | 0.5687 |
| 1.774 | 0.8982 | 300 | 0.7197 | 0.4313 |
| 1.4274 | 1.0479 | 350 | 0.6862 | 0.5687 |
| 1.199 | 1.1976 | 400 | 0.6995 | 0.5687 |
| 1.4548 | 1.3473 | 450 | 0.7085 | 0.4313 |
| 1.581 | 1.4970 | 500 | 0.6845 | 0.5687 |
| 1.8775 | 1.6467 | 550 | 0.7424 | 0.5687 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1