ayshi/basic_distil

1---2license: apache-2.03base_model: ayshi/basic_distil4tags:5- generated_from_keras_callback6model-index:7- name: ayshi/basic_distil8  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# ayshi/basic_distil15 16This model is a fine-tuned version of [ayshi/basic_distil](https://huggingface.co/ayshi/basic_distil) on an unknown dataset.17It achieves the following results on the evaluation set:18- Train Loss: 0.011419- Validation Loss: 1.003520- Train Accuracy: 0.791121- Epoch: 1922 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- 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': 640, '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}41- training_precision: float3242 43### Training results44 45| Train Loss | Validation Loss | Train Accuracy | Epoch |46|:----------:|:---------------:|:--------------:|:-----:|47| 0.3282     | 0.7966          | 0.7644         | 0     |48| 0.2163     | 0.8219          | 0.7778         | 1     |49| 0.1323     | 0.8099          | 0.7778         | 2     |50| 0.0933     | 0.8337          | 0.7956         | 3     |51| 0.0619     | 0.9082          | 0.7689         | 4     |52| 0.0461     | 0.9380          | 0.7778         | 5     |53| 0.0495     | 0.9502          | 0.7556         | 6     |54| 0.0301     | 0.9445          | 0.7733         | 7     |55| 0.0249     | 0.9578          | 0.8            | 8     |56| 0.0209     | 0.9663          | 0.7911         | 9     |57| 0.0200     | 0.9828          | 0.7778         | 10    |58| 0.0159     | 0.9987          | 0.7689         | 11    |59| 0.0163     | 1.0120          | 0.7689         | 12    |60| 0.0142     | 1.0020          | 0.7956         | 13    |61| 0.0153     | 1.0270          | 0.7911         | 14    |62| 0.0142     | 1.0159          | 0.7822         | 15    |63| 0.0130     | 1.0049          | 0.7911         | 16    |64| 0.0129     | 1.0085          | 0.7956         | 17    |65| 0.0099     | 1.0033          | 0.7911         | 18    |66| 0.0114     | 1.0035          | 0.7911         | 19    |67 68 69### Framework versions70 71- Transformers 4.34.072- TensorFlow 2.13.073- Datasets 2.14.574- Tokenizers 0.14.175