Hugging Face's logo

g-assismoraes
/
mdeberta-semeval25_narratives09_maxf1_fold3

Text Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mdeberta-semeval25_narratives09_maxf1_fold3 / README.md
g-assismoraes's picture
g-assismoraes
End of training
42ba366 verified
preview code
|
raw
history blame contribute delete
4.5 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
  - generated_from_trainer
model-index:
  - name: mdeberta-semeval25_narratives09_maxf1_fold3
    results: []

mdeberta-semeval25_narratives09_maxf1_fold3

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 4.1972
  • Precision Samples: 0.3634
  • Recall Samples: 0.7451
  • F1 Samples: 0.4586
  • Precision Macro: 0.6979
  • Recall Macro: 0.4621
  • F1 Macro: 0.2857
  • Precision Micro: 0.3270
  • Recall Micro: 0.6974
  • F1 Micro: 0.4452
  • Precision Weighted: 0.4846
  • Recall Weighted: 0.6974
  • F1 Weighted: 0.3864

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: 32
  • eval_batch_size: 32
  • 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
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Samples Recall Samples F1 Samples Precision Macro Recall Macro F1 Macro Precision Micro Recall Micro F1 Micro Precision Weighted Recall Weighted F1 Weighted
5.6486 1.0 19 5.3335 1.0 0.0 0.0 1.0 0.0476 0.0476 1.0 0.0 0.0 1.0 0.0 0.0
5.1544 2.0 38 5.1485 0.3023 0.3614 0.2993 0.8755 0.1773 0.1289 0.2996 0.3063 0.3029 0.7138 0.3063 0.1870
4.8667 3.0 57 4.9432 0.2776 0.4614 0.3282 0.8665 0.2238 0.1327 0.2853 0.4022 0.3338 0.6952 0.4022 0.1947
4.5126 4.0 76 4.6697 0.3487 0.5930 0.4045 0.7826 0.2967 0.1944 0.3166 0.5129 0.3915 0.5781 0.5129 0.2876
4.6317 5.0 95 4.4823 0.3405 0.6624 0.4196 0.7583 0.3672 0.2290 0.3034 0.5978 0.4025 0.5513 0.5978 0.3219
4.4113 6.0 114 4.3402 0.3574 0.7394 0.4481 0.7165 0.4305 0.2537 0.3140 0.6790 0.4294 0.4928 0.6790 0.3587
3.9755 7.0 133 4.2814 0.3659 0.7354 0.4539 0.7175 0.4258 0.2523 0.3176 0.6716 0.4313 0.4960 0.6716 0.3581
4.0457 8.0 152 4.2820 0.3549 0.7009 0.4398 0.7116 0.4227 0.2646 0.32 0.6494 0.4287 0.4905 0.6494 0.3644
4.0695 9.0 171 4.1947 0.3767 0.7511 0.4662 0.7109 0.4572 0.2863 0.3259 0.7011 0.4450 0.4949 0.7011 0.3884
4.3445 10.0 190 4.1972 0.3634 0.7451 0.4586 0.6979 0.4621 0.2857 0.3270 0.6974 0.4452 0.4846 0.6974 0.3864

Framework versions

  • Transformers 4.46.0
  • Pytorch 2.3.1
  • Datasets 2.21.0
  • Tokenizers 0.20.1