pokemon_captions

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: 6.8345
• Wer Score: 49.8505

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: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
9.5056	0.21	10	8.3847	75.6675
8.0875	0.43	20	7.6115	75.9652
7.4568	0.64	30	7.1151	69.8376
7.0645	0.85	40	6.8345	49.8505

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cpu
• Datasets 2.18.0
• Tokenizers 0.15.2