aoi_clip_clean

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: 5.6248

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: 40
• eval_batch_size: 44
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 120.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.2626	12.0	17748	6.2362
0.057	24.0	35496	6.3541
0.0428	36.0	53244	6.0895
0.0359	48.0	70992	6.1071
0.0312	60.0	88740	5.9994
0.0287	72.0	106488	5.8543
0.0262	84.0	124236	5.7595
0.0246	96.0	141984	5.7167
0.0227	108.0	159732	5.6840
0.0215	120.0	177480	5.6248

Framework versions

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