Hugging Face's logo

ElMad
/
victorious-moose-736

Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
Inference Endpoints
Model card Files Community
victorious-moose-736 / README.md
ElMad's picture
ElMad
stackoverflow_tag_classification/modernBERT_vs_Deberta/ModernBERT-base/victorious-moose-736
8bb7005 verified
preview code
|
raw
history blame contribute delete
3.18 kB
metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
  - generated_from_trainer
model-index:
  - name: victorious-moose-736
    results: []

victorious-moose-736

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: 0.1689
  • Hamming Loss: 0.0619
  • Zero One Loss: 0.4450
  • Jaccard Score: 0.3857
  • Hamming Loss Optimised: 0.0592
  • Hamming Loss Threshold: 0.7299
  • Zero One Loss Optimised: 0.4387
  • Zero One Loss Threshold: 0.4119
  • Jaccard Score Optimised: 0.3464
  • Jaccard Score Threshold: 0.2462

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: 2.115467719563917e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 2024
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.8101446041573426,0.9056914031952074) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Hamming Loss Zero One Loss Jaccard Score Hamming Loss Optimised Hamming Loss Threshold Zero One Loss Optimised Zero One Loss Threshold Jaccard Score Optimised Jaccard Score Threshold
No log 1.0 100 0.1830 0.0644 0.5162 0.4740 0.0643 0.4982 0.4975 0.3276 0.3889 0.2962
No log 2.0 200 0.1643 0.062 0.4625 0.3920 0.0597 0.6455 0.4587 0.4816 0.3518 0.2755
No log 3.0 300 0.1678 0.0636 0.4550 0.3934 0.0595 0.7017 0.4425 0.3683 0.3441 0.2888
No log 4.0 400 0.1689 0.0619 0.4450 0.3857 0.0592 0.7299 0.4387 0.4119 0.3464 0.2462

Framework versions

  • Transformers 4.48.0.dev0
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.21.0