mbert-argumentClassification-hindi

• eval_loss: 0.1784
• eval_model_preparation_time: 0.0028
• eval_accuracy: 0.9747
• eval_w_accuracy: 0.8048
• eval_classification_report: {'None': {'precision': 0.8275229357798165, 'recall': 0.8082437275985663, 'f1-score': 0.8177697189483227, 'support': 558.0}, 'S': {'precision': 0.9897019138310742, 'recall': 0.9919171822053657, 'f1-score': 0.9908083097848026, 'support': 32167.0}, 'A': {'precision': 0.8537768537768538, 'recall': 0.7802406586447118, 'f1-score': 0.8153540701522171, 'support': 1579.0}, 'P': {'precision': 0.7838736492103076, 'recall': 0.8374777975133215, 'f1-score': 0.8097896092743667, 'support': 1126.0}, 'accuracy': 0.9746824724809483, 'macro avg': {'precision': 0.863718838149513, 'recall': 0.8544698414904913, 'f1-score': 0.8584304270399273, 'support': 35430.0}, 'weighted avg': {'precision': 0.9745485363108597, 'recall': 0.9746824724809483, 'f1-score': 0.9745106853184927, 'support': 35430.0}}
• eval_hamming_loss: 0.0253
• eval_runtime: 16.1311
• eval_samples_per_second: 104.395
• eval_steps_per_second: 13.08
• 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 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2