aoi_clip

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: 5.5439

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: 150.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.2989	10.0	14790	6.2126
0.0626	20.0	29580	6.1552
0.0467	30.0	44370	6.0248
0.0383	40.0	59160	6.0260
0.0333	50.0	73950	5.9856
0.0301	60.0	88740	5.8489
0.0275	70.0	103530	5.8452
0.0255	80.0	118320	5.7286
0.0238	90.0	133110	5.6773
0.0225	100.0	147900	5.5744
0.0243	110.0	162690	5.6549
0.024	120.0	177480	5.5997
0.0227	130.0	192270	5.5604
0.0219	140.0	207060	5.5429
0.0217	150.0	221850	5.5439

Framework versions

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