metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: valueeval24-modern-bert-cos-initialfreeze-diff-lr
results: []
valueeval24-modern-bert-cos-initialfreeze-diff-lr
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: 0.7684
- F1: 0.2039
- Roc Auc: 0.5705
- Accuracy: 0.1033
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.0167 | 1.0 | 3115 | 0.2207 | 0.2035 | 0.5691 | 0.1071 |
| 0.0138 | 2.0 | 6230 | 0.2613 | 0.2091 | 0.5730 | 0.1083 |
| 0.0102 | 3.0 | 9345 | 0.3444 | 0.2249 | 0.5841 | 0.1147 |
| 0.0073 | 4.0 | 12460 | 0.6223 | 0.1944 | 0.5654 | 0.0991 |
| 0.0053 | 5.0 | 15575 | 0.6920 | 0.1973 | 0.5668 | 0.1004 |
| 0.0022 | 6.0 | 18690 | 0.7143 | 0.1983 | 0.5680 | 0.0996 |
| 0.0012 | 7.0 | 21805 | 0.7309 | 0.1968 | 0.5672 | 0.0993 |
| 0.0007 | 8.0 | 24920 | 0.7349 | 0.2035 | 0.5706 | 0.1031 |
| 0.0006 | 9.0 | 28035 | 0.7521 | 0.2064 | 0.5718 | 0.1070 |
| 0.0003 | 10.0 | 31150 | 0.7684 | 0.2039 | 0.5705 | 0.1033 |
Framework versions
- Transformers 4.53.1
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2