aoi_clip_high_resolution_text_only_gpt_new_sampler

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: 3.2382
• Accuracy: 0.1291

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: 50
• eval_batch_size: 20
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 200
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5113	9.9839	3110	2.8518	0.1566
2.3003	19.9679	6220	3.0242	0.1476
2.2124	29.9518	9330	3.1246	0.1404
2.1682	39.9358	12440	3.1806	0.1371
2.1384	49.9197	15550	3.2024	0.1342
2.1246	59.9037	18660	3.2168	0.1323
2.1121	69.8876	21770	3.2209	0.1313
2.0987	79.8716	24880	3.2137	0.1307
2.0986	89.8555	27990	3.2374	0.1301
2.0962	99.8395	31100	3.2382	0.1295

Framework versions

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