MatFil99/bert-nlp-project-ft-google

1---2license: apache-2.03tags:4- generated_from_trainer5metrics:6- accuracy7- f18model-index:9- name: bert-nlp-project-ft-google10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# bert-nlp-project-ft-google17 18This model is a fine-tuned version of [jestemleon/bert-nlp-project-google](https://huggingface.co/jestemleon/bert-nlp-project-google) on the [steciuk/google](https://huggingface.co/datasets/steciuk/google) dataset.19It achieves the following results on the evaluation set:20- Loss: 0.325521- Accuracy: 0.910522- F1: 0.917423 24and flowing results on the testing set:25- Accuracy: 0.911526- F1: 0.918027 28## Model description29 30More information needed31 32## Intended uses & limitations33 34More information needed35 36## Training and evaluation data37 38More information needed39 40## Training procedure41 42### Training hyperparameters43 44The following hyperparameters were used during training:45- learning_rate: 2e-0546- train_batch_size: 1647- eval_batch_size: 1648- seed: 4249- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0850- lr_scheduler_type: linear51- num_epochs: 352- mixed_precision_training: Native AMP53 54### Training results55 56| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |57|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|58| 0.3506        | 0.37  | 196  | 0.2922          | 0.8876   | 0.9017 |59| 0.2724        | 0.75  | 392  | 0.2456          | 0.9038   | 0.9099 |60| 0.2299        | 1.12  | 588  | 0.2781          | 0.9124   | 0.9192 |61| 0.2009        | 1.49  | 784  | 0.2934          | 0.8981   | 0.9016 |62| 0.182         | 1.86  | 980  | 0.2854          | 0.9095   | 0.9164 |63| 0.1569        | 2.24  | 1176 | 0.2932          | 0.9086   | 0.9150 |64| 0.118         | 2.61  | 1372 | 0.3258          | 0.9067   | 0.9139 |65| 0.1188        | 2.98  | 1568 | 0.3255          | 0.9105   | 0.9174 |66 67 68### Framework versions69 70- Transformers 4.25.171- Pytorch 1.13.0+cu11672- Datasets 2.8.073- Tokenizers 0.13.274