Edit model card

Rocketknight1/clip-roberta-coco

This model is a fine-tuned version of on the ydshieh/coco_dataset_script 2017 dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.1749
  • Validation Loss: 1.6969
  • Epoch: 2

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:

  • optimizer: {'name': 'AdamWeightDecay', 'global_clipnorm': 1.0, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 27738, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
0.6558 1.8089 0
0.3065 1.7544 1
0.1749 1.6969 2

Framework versions

  • Transformers 4.27.0.dev0
  • TensorFlow 2.11.0
  • Datasets 2.9.1.dev0
  • Tokenizers 0.13.2
Downloads last month
2

Dataset used to train Rocketknight1/clip-roberta-coco