xtremedistil-l6-h256-uncased-future-time-references-D1

This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on the jonaskoenig/trump_administration_statement and jonaskoenig/future-time-refernces-static-filter datsets.

It achieves the following results on the evaluation set:

• Train Loss: 0.0099
• Train Sparse Categorical Accuracy: 0.9977
• Validation Loss: 0.0128
• Validation Sparse Categorical Accuracy: 0.9976
• Epoch: 3

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', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Sparse Categorical Accuracy	Validation Loss	Validation Sparse Categorical Accuracy	Epoch
0.0276	0.9932	0.0156	0.9968	0
0.0138	0.9969	0.0125	0.9972	1
0.0117	0.9974	0.0126	0.9974	2
0.0099	0.9977	0.0128	0.9976	3

The test accuracy is: 99.77%

Framework versions

• Transformers 4.20.1
• TensorFlow 2.9.1
• Datasets 2.3.2
• Tokenizers 0.12.1