Image-Caption-University-model

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: 0.4060
• Wer Score: 2.0586

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
7.1651	6.6667	50	4.6332	2.9074
2.6998	13.3333	100	1.0675	2.1821
0.3956	20.0	150	0.3752	2.5494
0.0633	26.6667	200	0.3804	1.9321
0.0196	33.3333	250	0.3981	2.4105
0.0141	40.0	300	0.4050	2.0679
0.0115	46.6667	350	0.4060	2.0586

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1