sf_20240220_v2

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: 0.0514
• Validation Loss: 0.0698
• Epoch: 14

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
0.1435	0.1090	0
0.0923	0.0976	1
0.0815	0.0951	2
0.0760	0.0959	3
0.0735	0.0844	4
0.0710	0.0824	5
0.0669	0.0719	6
0.0628	0.0738	7
0.0664	0.0801	8
0.0665	0.0756	9
0.0612	0.0672	10
0.0571	0.0703	11
0.0546	0.0714	12
0.0553	0.0841	13
0.0514	0.0698	14

Framework versions

• Transformers 4.37.0
• TensorFlow 2.15.0
• Datasets 2.1.0
• Tokenizers 0.15.1