git-base-pokemon

This model is a fine-tuned version of TeeA/git-base-pokemon on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2101
• eval_wer_score: 4.6548
• eval_runtime: 25.4225
• eval_samples_per_second: 28.793
• eval_steps_per_second: 1.809
• epoch: 22.0
• step: 3349

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0