finetune_teacher_noisy_mozilla_50_epochs_take-1

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

• Loss: inf
• Wer: 0.3771

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: 0.0005
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 256
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
156.5412	10.31	1000	inf	0.4495
116.825	20.61	2000	inf	0.4151
88.1673	30.92	3000	inf	0.3941
65.9659	41.24	4000	inf	0.3771

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1
• Datasets 2.8.0
• Tokenizers 0.13.2