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
- Downloads last month
- 3
Model tree for rparasa/segformer_400train80val_subset_10epochs
Base model
nvidia/mit-b0
Finetuned
this model