metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: fold_4
results: []
fold_4
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: 1.1424
- F1: 0.8050
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 |
|---|---|---|---|---|
| No log | 1.0 | 20 | 1.1259 | 0.3473 |
| No log | 2.0 | 40 | 1.0386 | 0.6004 |
| No log | 3.0 | 60 | 1.0188 | 0.6095 |
| No log | 4.0 | 80 | 0.8320 | 0.7176 |
| 0.7917 | 5.0 | 100 | 1.3236 | 0.6829 |
| 0.7917 | 6.0 | 120 | 0.9291 | 0.7648 |
| 0.7917 | 7.0 | 140 | 1.1950 | 0.7217 |
| 0.7917 | 8.0 | 160 | 1.1574 | 0.7446 |
| 0.7917 | 9.0 | 180 | 1.1451 | 0.8035 |
| 0.0401 | 10.0 | 200 | 1.1424 | 0.8050 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1
- Datasets 3.2.0
- Tokenizers 0.21.0