git-base-pokemon

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

• Loss: 0.7051
• Wer Score: 1.6596

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: 32
• eval_batch_size: 32
• 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
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
0.7017	10.0	50	0.5906	1.7247
0.2858	20.0	100	0.6435	1.6259
0.1529	30.0	150	0.6878	1.7054
0.0987	40.0	200	0.7051	1.6596

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0