mljn's picture
Model save
0971781 verified
metadata
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mdeberta-v3-base-finetuned-french-green-stance
    results: []

mdeberta-v3-base-finetuned-french-green-stance

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: 0.3085
  • Accuracy: 0.9533
  • F1 Macro: 0.9428
  • Accuracy Balanced: 0.9425
  • F1 Micro: 0.9533
  • Precision Macro: 0.9431
  • Recall Macro: 0.9425
  • Precision Micro: 0.9533
  • Recall Micro: 0.9533

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: linear
  • lr_scheduler_warmup_ratio: 0.06
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro Accuracy Balanced F1 Micro Precision Macro Recall Macro Precision Micro Recall Micro
0.3304 1.0 1393 0.4028 0.9160 0.8984 0.9035 0.9160 0.8937 0.9035 0.9160 0.9160
0.2085 2.0 2786 0.2895 0.9440 0.9298 0.9201 0.9440 0.9410 0.9201 0.9440 0.9440
0.1368 3.0 4179 0.3136 0.9519 0.9408 0.9384 0.9519 0.9432 0.9384 0.9519 0.9519
0.0374 4.0 5572 0.3085 0.9533 0.9428 0.9425 0.9533 0.9431 0.9425 0.9533 0.9533

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.3.2
  • Tokenizers 0.21.0