sentance_split_by_aoi_gpt_add

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: 3.5837
• Accuracy: 0.1044

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: 60.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.168	5.9676	276	2.9707	0.1067
0.8242	11.9351	552	3.4872	0.0994
0.639	17.9027	828	3.5071	0.0965
0.5825	23.8703	1104	3.5619	0.0994
0.5449	29.8378	1380	3.5003	0.0994
0.5257	35.8054	1656	3.4785	0.1019
0.512	41.7730	1932	3.4630	0.1020
0.5039	47.7405	2208	3.5130	0.1036
0.492	53.7081	2484	3.5763	0.1038
0.4922	59.6757	2760	3.5837	0.1041

Framework versions

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