blip-finetuned-kag100

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: 0.8447

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: 1e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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
• lr_scheduler_warmup_steps: 50
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.379	1.1130	50	1.3287
1.0477	2.2260	100	1.0919
0.8732	3.3390	150	0.9758
0.796	4.4520	200	0.9150
0.732	5.5650	250	0.9030
0.7011	6.6780	300	0.8376
0.6761	7.7910	350	0.8530
0.663	8.9040	400	0.8447

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0