metadata

library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
model-index:
  - name: arq-modernbert-focal-lr-3e-5
    results: []

arq-modernbert-focal-lr-3e-5

This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 28.4821
F1-micro: 0.4796
F1-macro: 0.4528

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: 16
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: linear
lr_scheduler_warmup_steps: 18
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	F1-micro	F1-macro
78.0007	1.0	45	27.7867	0.3995	0.3173
75.4879	2.0	90	27.6958	0.4442	0.3902
72.5709	3.0	135	27.8264	0.4444	0.3989
69.4113	4.0	180	28.4821	0.4796	0.4528

Framework versions

Transformers 4.48.1
Pytorch 2.5.1+cu121
Tokenizers 0.21.0