metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: fold_3
results: []
fold_3
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: 1.1954
- F1: 0.8447
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: 32
- eval_batch_size: 16
- 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 | Validation Loss | F1 |
|---|---|---|---|---|
| 0.425 | 1.0 | 300 | 0.4228 | 0.8290 |
| 0.265 | 2.0 | 600 | 0.4118 | 0.8407 |
| 0.1577 | 3.0 | 900 | 0.4843 | 0.8540 |
| 0.0773 | 4.0 | 1200 | 0.7007 | 0.8394 |
| 0.0406 | 5.0 | 1500 | 0.8548 | 0.8487 |
| 0.0192 | 6.0 | 1800 | 1.0277 | 0.8444 |
| 0.0184 | 7.0 | 2100 | 0.9923 | 0.8469 |
| 0.0068 | 8.0 | 2400 | 1.1065 | 0.8461 |
| 0.0049 | 9.0 | 2700 | 1.1675 | 0.8448 |
| 0.0014 | 10.0 | 3000 | 1.1954 | 0.8447 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0