galgame-kotoba-whisper-enc-epoch2-2

This model was trained from scratch on the webdataset dataset.

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• training_steps: 291826
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.0
• Datasets 3.0.2
• Tokenizers 0.20.1