wav2vec2-final-learning-rate-1e-4

• Loss: inf
• Wer: 0.4193
• Cer: 0.1025

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.0001
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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_steps: 400
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.51.1
• Pytorch 2.1.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.1