fusion_concate_sep_SEP_describe_gpt

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: 3.6264
• Accuracy: 0.0807

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: 20
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 320
• 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
2.4506	5.9807	1164	2.9871	0.0736
2.3229	11.9615	2328	3.1384	0.0733
2.2364	17.9422	3492	3.1920	0.0795
2.1589	23.9229	4656	3.2667	0.0825
2.1034	29.9037	5820	3.2883	0.0835
2.0555	35.8844	6984	3.3512	0.0837
2.0231	41.8651	8148	3.4304	0.0836
2.0056	47.8459	9312	3.5540	0.0831
1.9964	53.8266	10476	3.5894	0.0820
1.9848	59.8073	11640	3.6264	0.0813

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.20.0