jonaskoenig/topic_classification_01

1---2license: mit3tags:4- generated_from_keras_callback5model-index:6- name: topic_classification_017  results: []8---9 10<!-- This model card has been generated automatically according to the information Keras had access to. You should11probably proofread and complete it, then remove this comment. -->12 13# topic_classification_0114 15This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on an unknown dataset.16It achieves the following results on the evaluation set:17- Train Loss: 0.030618- Train Binary Crossentropy: 0.557819- Epoch: 920 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- optimizer: {'name': 'Adam', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}39- training_precision: float3240 41### Training results42 43| Train Loss | Train Binary Crossentropy | Epoch |44|:----------:|:-------------------------:|:-----:|45| 0.0397     | 0.7274                    | 0     |46| 0.0352     | 0.6392                    | 1     |47| 0.0339     | 0.6142                    | 2     |48| 0.0330     | 0.5989                    | 3     |49| 0.0324     | 0.5882                    | 4     |50| 0.0319     | 0.5799                    | 5     |51| 0.0315     | 0.5730                    | 6     |52| 0.0312     | 0.5672                    | 7     |53| 0.0309     | 0.5623                    | 8     |54| 0.0306     | 0.5578                    | 9     |55 56 57### Framework versions58 59- Transformers 4.20.160- TensorFlow 2.9.161- Datasets 2.3.262- Tokenizers 0.12.163