Sanyam52/bart-base-finetuned-amazon-polarity

This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.1288
• Validation Loss: 3.7985
• Epoch: 7

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': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 8540, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 100, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
3.5874	3.1401	0
2.9473	3.1637	1
2.4875	3.2704	2
2.1011	3.3707	3
1.7622	3.4952	4
1.4862	3.6390	5
1.2748	3.7576	6
1.1288	3.7985	7

Framework versions

• Transformers 4.42.4
• TensorFlow 2.17.0
• Datasets 2.21.0
• Tokenizers 0.19.1