ASL_t5_movinet

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.5272
• Train Top 1: 0.8966
• Train Top 5: 0.9383
• Validation Loss: 0.7459
• Validation Top 1: 0.8710
• Validation Top 5: 0.9142
• Train Bleu: 0.0
• Train Gen Len: 2.0
• 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': 'Adafactor', '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': 1e-04, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
• training_precision: float32

Training results

Train Loss	Train Top 1	Train Top 5	Validation Loss	Validation Top 1	Validation Top 5	Train Bleu	Train Gen Len	Epoch
0.5971	0.8879	0.9305	0.7228	0.8744	0.9170	0.0	2.0	0
0.5567	0.8928	0.9353	0.7311	0.8736	0.9156	0.0	2.0	1
0.5272	0.8966	0.9383	0.7459	0.8710	0.9142	0.0	2.0	2

Framework versions

• Transformers 4.34.1
• TensorFlow 2.13.0
• Datasets 2.15.0
• Tokenizers 0.14.1