You can deploy this model and start earning money today!

MarcoLYH/
distilbert-base-uncased-finetuned-v2

Name: distilbert-base-uncased-finetuned-v2
Rating: 2.5 (5 reviews)

generated_from_keras_callback

apache-2.0

endpoints_compatible

Views

No views yet

MarcoLYH/distilbert-base-uncased-finetuned-v2

This model is a fine-tuned version of distilbert-base-uncased-distilled-squad on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.8512
Train End Logits Accuracy: 0.7917
Train Start Logits Accuracy: 0.7708
Validation Loss: 0.9185
Validation End Logits Accuracy: 0.7000
Validation Start Logits Accuracy: 0.8000
Epoch: 4

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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 14, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1, 'power': 1.0, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
2.0417	0.4583	0.5833	1.2444	0.6000	0.7000	0
1.5102	0.5625	0.6875	1.0279	0.7000	0.75	1
1.1881	0.6458	0.6875	0.9774	0.7000	0.8000	2
1.1344	0.6875	0.6875	0.9360	0.7000	0.8000	3
0.8512	0.7917	0.7708	0.9185	0.7000	0.8000	4

Framework versions

Transformers 4.30.1
TensorFlow 2.12.0
Datasets 2.12.0
Tokenizers 0.13.3