pglee/github-issue-classifier

1---2license: mit3tags:4- generated_from_trainer5metrics:6- accuracy7- f18- precision9- recall10model-index:11- name: github-issue-classifier12  results: []13---14 15<!-- This model card has been generated automatically according to the information the Trainer had access to. You16should probably proofread and complete it, then remove this comment. -->17 18# github-issue-classifier19 20This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.21It achieves the following results on the evaluation set:22- Loss: 0.068423- Accuracy: 0.87524- F1: 0.045525- Precision: 1.026- Recall: 0.023327 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: 8e-0546- train_batch_size: 25647- eval_batch_size: 51248- seed: 4249- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0850- lr_scheduler_type: cosine51- lr_scheduler_warmup_ratio: 0.152- num_epochs: 453- mixed_precision_training: Native AMP54 55### Training results56 57| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |58|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|59| No log        | 1.0   | 6    | 0.0888          | 0.8720   | 0.0    | 0.0       | 0.0    |60| No log        | 2.0   | 12   | 0.0700          | 0.8720   | 0.0    | 0.0       | 0.0    |61| No log        | 3.0   | 18   | 0.0713          | 0.8720   | 0.0851 | 0.5       | 0.0465 |62| No log        | 4.0   | 24   | 0.0684          | 0.875    | 0.0455 | 1.0       | 0.0233 |63 64 65### Framework versions66 67- Transformers 4.20.168- Pytorch 1.11.069- Datasets 2.1.070- Tokenizers 0.12.171