Edit model card

sf_20240220_v1

This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0768
  • Validation Loss: 0.1343
  • Epoch: 8

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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.0006, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
0.1840 0.1748 0
0.1043 0.1361 1
0.0939 0.1137 2
0.0865 0.1056 3
0.0839 0.0860 4
0.0806 0.1238 5
0.0786 0.0906 6
0.0760 0.0895 7
0.0768 0.1343 8

Framework versions

  • Transformers 4.37.0
  • TensorFlow 2.15.0
  • Datasets 2.1.0
  • Tokenizers 0.15.1
Downloads last month
0
Unable to determine this model’s pipeline type. Check the docs .

Finetuned from