segformer_400train80val_subset_10epochs

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: 0.0838
• Validation Loss: 0.0902
• Epoch: 9

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': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.3830	0.2178	0
0.1680	0.2520	1
0.1641	0.1378	2
0.1141	0.1192	3
0.1130	0.0994	4
0.0945	0.0984	5
0.0863	0.0950	6
0.0874	0.0905	7
0.0858	0.0918	8
0.0838	0.0902	9

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Tokenizers 0.15.2