metadata

license: apache-2.0
base_model: distilbert-base-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: LongRiver/distilbert-base-cased-finetuned
    results: []

LongRiver/distilbert-base-cased-finetuned

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

Train Loss: 0.4033
Train End Logits Accuracy: 0.8959
Train Start Logits Accuracy: 0.8678
Validation Loss: 2.9031
Validation End Logits Accuracy: 0.5200
Validation Start Logits Accuracy: 0.4756
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 22620, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
2.3101	0.5128	0.5040	2.0900	0.5237	0.4869	0
1.6815	0.5991	0.5717	1.9820	0.5390	0.5048	1
1.3961	0.6595	0.6236	2.0232	0.5424	0.5110	2
1.1489	0.7152	0.6761	2.1478	0.5322	0.4948	3
0.9422	0.7640	0.7229	2.2796	0.5336	0.4918	4
0.7732	0.8052	0.7643	2.4008	0.5180	0.4767	5
0.6369	0.8344	0.8008	2.6350	0.5010	0.4572	6
0.5378	0.8606	0.8272	2.6468	0.5339	0.4905	7
0.4549	0.8851	0.8520	2.8469	0.5146	0.4677	8
0.4033	0.8959	0.8678	2.9031	0.5200	0.4756	9

Framework versions

Transformers 4.39.3
TensorFlow 2.15.0
Datasets 2.18.0
Tokenizers 0.15.2