clip-vit-bert-coco

This model was trained from scratch on the ydshieh/coco_dataset_script 2017 dataset. It achieves the following results on the evaluation set:

• eval_loss: 4.1888
• eval_runtime: 5.7658
• eval_samples_per_second: 22.2
• eval_steps_per_second: 0.173
• step: 0

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-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.2