clip-ROCOv2-radiology-5ep

This model is a fine-tuned version of openai/clip-vit-base-patch32 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4365

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: 5e-06
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.5698	0.6588	500	1.4979
1.0335	1.3175	1000	1.2915
0.9555	1.9763	1500	1.1798
0.644	2.6350	2000	1.2104
0.3687	3.2938	2500	1.3033
0.3659	3.9526	3000	1.3342
0.2289	4.6113	3500	1.4365

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 4.4.1
• Tokenizers 0.19.1