sentance_split_by_aoi_ocr_None_2

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: 3.4765
• Accuracy: 0.1927

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
1.2383	5.9676	276	2.6388	0.2417
0.9769	11.9351	552	2.8174	0.2247
0.8157	17.9027	828	3.1486	0.2148
0.7322	23.8703	1104	3.3020	0.2080
0.6777	29.8378	1380	3.3933	0.2026
0.6466	35.8054	1656	3.4180	0.1995
0.6273	41.7730	1932	3.4385	0.1971
0.6188	47.7405	2208	3.4671	0.1953
0.6051	53.7081	2484	3.4631	0.1944
0.6049	59.6757	2760	3.4765	0.1935

Framework versions

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