blip-image-captioning-large-shyam-shyam

This model is a fine-tuned version of shyamgv/blip-image-captioning-large-shyam on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0044
• Wer Score: 0.1111

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: 2
• eval_batch_size: 2
• seed: 42
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
0.0104	2.9412	50	0.0041	0.1111
0.0025	5.8824	100	0.0049	0.1111
0.0003	8.8235	150	0.0056	0.1667
0.0002	11.7647	200	0.0045	0.1111
0.0001	14.7059	250	0.0044	0.1111

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0