2026-08-27-crf-classweights-clean

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

2026-08-27-crf-classweights-clean

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 8.6272
• Precision: 0.7821
• Recall: 0.8211
• F1: 0.8011
• Accuracy: 0.9722
• Academicdiscipline F1: 0.3810
• Ambiguouslydefinedconcept F1: 0.7356
• Discoursephenomenon F1: 0.6549
• Graphemicphenomenon F1: 0.0
• Languagerelatedterm F1: 0.8691
• Languageresourceinformation F1: 0.7868
• Lexicalphenomenon F1: 0.6759
• Morphologicalphenomenon F1: 0.8191
• Morphosyntacticphenomenon F1: 0.8479
• New Tag F1: 0.8207
• Otherlinguisticterm F1: 0.7439
• Phonologicalphenomenon F1: 0.8649
• Semanticphenomenon F1: 0.7048
• Syntacticphenomenon F1: 0.7965
• Topnode Dummy F1: 0.6852
• Unclassifiedlinguisticconcept F1: 0.8787

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: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use 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: 0.1
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.57.6
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.22.2