mbert-argumentClassification-russian

<!-- 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. -->

mbert-argumentClassification-russian

This model is a fine-tuned version of fromdeath2morning/mbert-argumentClassification-russian on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1073
• eval_model_preparation_time: 0.003
• eval_accuracy: 0.9853
• eval_w_accuracy: 0.8859
• eval_classification_report: {'None': {'precision': 0.8626373626373627, 'recall': 0.8870056497175142, 'f1-score': 0.8746518105849582, 'support': 177.0}, 'S': {'precision': 0.9941788338581926, 'recall': 0.9938942949818736, 'f1-score': 0.9940365440580125, 'support': 10482.0}, 'A': {'precision': 0.883248730964467, 'recall': 0.9015544041450777, 'f1-score': 0.8923076923076924, 'support': 386.0}, 'P': {'precision': 0.8939393939393939, 'recall': 0.8676470588235294, 'f1-score': 0.8805970149253731, 'support': 340.0}, 'accuracy': 0.9853315766359244, 'macro avg': {'precision': 0.908501080349854, 'recall': 0.9125253519169988, 'f1-score': 0.910398265469009, 'support': 11385.0}, 'weighted avg': {'precision': 0.9853792493438794, 'recall': 0.9853315766359244, 'f1-score': 0.9853437136227509, 'support': 11385.0}}
• eval_hamming_loss: 0.0147
• eval_runtime: 5.6239
• eval_samples_per_second: 106.866
• eval_steps_per_second: 13.514
• step: 0

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2