aoi_clip_high_resolution_crossAttenttionFusion_fusin_gpt_new_sampler

This model is a fine-tuned version of OFA-Sys/chinese-clip-vit-base-patch16 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 5.3131
• Accuracy: 0.0559

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-05
• train_batch_size: 25
• eval_batch_size: 20
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 200
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 200.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.152	19.9759	6220	3.0212	0.0537
1.9424	39.9518	12440	3.4495	0.0563
1.7646	59.9277	18660	3.9469	0.0561
1.6901	79.9037	24880	4.2354	0.0550
1.6562	99.8796	31100	4.6732	0.0548
1.6398	119.8555	37320	4.8612	0.0550
1.6289	139.8314	43540	4.8784	0.0550
1.6192	159.8073	49760	5.2516	0.0554
1.6163	179.7832	55980	5.2837	0.0558
1.6165	199.7591	62200	5.3131	0.0558

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1