modernbert-match-user-52164

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: 1.5489
  • Accuracy: 0.6304
  • F1: 0.5641
  • Precision: 0.5521
  • Recall: 0.6304
  • F1 Class 0: 0.3226
  • F1 Class 1: 0.1905
  • F1 Class 2: 0.0
  • F1 Class 3: 0.2778
  • F1 Class 4: 0.7879

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • 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_with_restarts
  • lr_scheduler_warmup_steps: 184
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall F1 Class 0 F1 Class 1 F1 Class 2 F1 Class 3 F1 Class 4
1.1594 1.0 184 1.2153 0.6087 0.4606 0.3705 0.6087 0.0 0.0 0.0 0.0 0.7568
1.1026 2.0 368 1.3772 0.6196 0.5074 0.4619 0.6196 0.1714 0.0 0.0 0.0909 0.7829
0.9719 3.0 552 1.2712 0.6304 0.5229 0.4938 0.6304 0.2941 0.1176 0.0 0.0 0.7829
0.839 4.0 736 1.5489 0.6304 0.5641 0.5521 0.6304 0.3226 0.1905 0.0 0.2778 0.7879

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0
  • Datasets 2.21.0
  • Tokenizers 0.21.0
Downloads last month
20
Safetensors
Model size
150M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for matiashoyl/modernbert-match-user-52164

Finetuned
(440)
this model