SHS/tokenization-practice

1---2license: apache-2.03tags:4- generated_from_keras_callback5model-index:6- name: SHS/tokenization-practice7  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# SHS/tokenization-practice14 15This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.16It achieves the following results on the evaluation set:17- Train Loss: 0.120318- Validation Loss: 0.253719- Train Precision: 0.597120- Train Recall: 0.445021- Train F1: 0.509922- Train Accuracy: 0.947523- Epoch: 224 25## Model description26 27More information needed28 29## Intended uses & limitations30 31More information needed32 33## Training and evaluation data34 35More information needed36 37## Training procedure38 39### Training hyperparameters40 41The following hyperparameters were used during training:42- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 636, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}43- training_precision: float3244 45### Training results46 47| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |48|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|49| 0.3513     | 0.3180          | 0.3947          | 0.0718       | 0.1215   | 0.9260         | 0     |50| 0.1624     | 0.2624          | 0.5321          | 0.3971       | 0.4548   | 0.9438         | 1     |51| 0.1203     | 0.2537          | 0.5971          | 0.4450       | 0.5099   | 0.9475         | 2     |52 53 54### Framework versions55 56- Transformers 4.26.057- TensorFlow 2.11.058- Datasets 2.9.059- Tokenizers 0.13.260