metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: modernbert-user-52979
results: []
modernbert-user-52979
This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3661
- Accuracy: 0.7069
- F1: 0.6878
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss |
|---|---|---|---|---|---|
| 0.6699 | 1.0 | 115 | 0.6983 | 0.5826 | 0.6130 |
| 0.5743 | 2.0 | 230 | 0.6724 | 0.5813 | 0.5881 |
| 0.4333 | 3.0 | 345 | 0.7155 | 0.6735 | 0.6304 |
| 0.5214 | 4.0 | 460 | 0.6983 | 0.6537 | 0.9174 |
| 0.5352 | 5.0 | 575 | 0.6638 | 0.6394 | 1.0110 |
| 0.2924 | 6.0 | 690 | 0.7069 | 0.6783 | 1.7635 |
| 0.3369 | 7.0 | 805 | 0.7069 | 0.6668 | 1.8718 |
| 0.1793 | 8.0 | 920 | 0.6983 | 0.6715 | 2.2900 |
| 0.016 | 9.0 | 1035 | 0.6897 | 0.6647 | 2.4075 |
| 0.0553 | 10.0 | 1150 | 0.7069 | 0.6878 | 2.3661 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.6.0
- Datasets 3.3.1
- Tokenizers 0.21.0