jonaskoenig/topic_classification_04

1---2license: mit3tags:4- generated_from_keras_callback5base_model: microsoft/xtremedistil-l6-h256-uncased6model-index:7- name: topic_classification_048  results: []9---10 11<!-- This model card has been generated automatically according to the information Keras had access to. You should12probably proofread and complete it, then remove this comment. -->13 14# topic_classification_0415 16This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.17It achieves the following results on the evaluation set:18- Train Loss: 0.832519- Train Sparse Categorical Accuracy: 0.723720- Epoch: 921 22## Model description23 24More information needed25 26## Intended uses & limitations27 28More information needed29 30## Training and evaluation data31 32More information needed33 34## Training procedure35 36### Training hyperparameters37 38The following hyperparameters were used during training:39- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}40- training_precision: float3241 42### Training results43 44| Train Loss | Train Sparse Categorical Accuracy | Epoch |45|:----------:|:---------------------------------:|:-----:|46| 1.0735     | 0.6503                            | 0     |47| 0.9742     | 0.6799                            | 1     |48| 0.9424     | 0.6900                            | 2     |49| 0.9199     | 0.6970                            | 3     |50| 0.9016     | 0.7026                            | 4     |51| 0.8853     | 0.7073                            | 5     |52| 0.8707     | 0.7120                            | 6     |53| 0.8578     | 0.7160                            | 7     |54| 0.8448     | 0.7199                            | 8     |55| 0.8325     | 0.7237                            | 9     |56 57 58### Framework versions59 60- Transformers 4.20.161- TensorFlow 2.9.162- Datasets 2.3.263- Tokenizers 0.12.164