xlm-r-argumentClassification-russian

• eval_loss: 0.6192
• eval_model_preparation_time: 0.0062
• eval_accuracy: 0.9347
• eval_w_accuracy: 0.4962
• eval_classification_report: {'None': {'precision': 0.24074074074074073, 'recall': 0.26, 'f1-score': 0.25, 'support': 50.0}, 'S': {'precision': 0.9809734513274336, 'recall': 0.9563100813408922, 'f1-score': 0.9684847728407389, 'support': 16228.0}, 'A': {'precision': 0.11043872919818457, 'recall': 0.4147727272727273, 'f1-score': 0.17443249701314217, 'support': 176.0}, 'P': {'precision': 0.6313645621181263, 'recall': 0.541958041958042, 'f1-score': 0.5832549388523048, 'support': 572.0}, 'accuracy': 0.9347468577469752, 'macro avg': {'precision': 0.4908793708461213, 'recall': 0.5432602126429154, 'f1-score': 0.4940430521765464, 'support': 17026.0}, 'weighted avg': {'precision': 0.9580554417390508, 'recall': 0.9347468577469752, 'f1-score': 0.9452245294348257, 'support': 17026.0}}
• eval_runtime: 9.163
• eval_samples_per_second: 104.005
• eval_steps_per_second: 13.096
• step: 0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• 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 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2