blip-image-captioning-base-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: 0.1444
• Wer Score: 0.7172

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: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Score
0.8613	0.9259	500	0.1123	0.7625
0.079	1.8519	1000	0.1131	0.7234
0.055	2.7778	1500	0.1228	0.7312
0.0389	3.7037	2000	0.1313	0.7531
0.0277	4.6296	2500	0.1360	0.7469
0.0205	5.5556	3000	0.1367	0.7188
0.0167	6.4815	3500	0.1410	0.7188
0.0154	7.4074	4000	0.1405	0.7188
0.0145	8.3333	4500	0.1435	0.7172
0.0137	9.2593	5000	0.1444	0.7172

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1