BLIP_Captioning

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

• Loss: 0.0001

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 1
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0023	0.9634	1500	0.0006
0.0012	1.9268	3000	0.0014
0.0007	2.8902	4500	0.0005
0.0006	3.8536	6000	0.0001
0.0002	4.8170	7500	0.0001

Framework versions

• Transformers 4.55.4
• Pytorch 2.5.1+cu121
• Tokenizers 0.21.4