autoevaluate/binary-classification

1---2license: apache-2.03tags:4- generated_from_trainer5datasets:6- glue7metrics:8- accuracy9model-index:10- name: autoevaluate-binary-classification11  results:12  - task:13      type: text-classification14      name: Text Classification15    dataset:16      name: glue17      type: glue18      args: sst219    metrics:20    - type: accuracy21      value: 0.896788990825688122      name: Accuracy23  - task:24      type: text-classification25      name: Text Classification26    dataset:27      name: glue28      type: glue29      config: sst230      split: validation31    metrics:32    - type: accuracy33      value: 0.896788990825688134      name: Accuracy35      verified: true36      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZmNGE1N2FjODM3OGJiM2Q2NTY5MzZjNGFhNGVjYzcwOTlkMzVhYjdmOTgwY2Y1NzMyZjY0NzAxMzZkMjM4NyIsInZlcnNpb24iOjF9.LabPe-QWLUUJdPyQ0Ki9rHq74opfAO1fxvu2FjUFiY9zhxAe0RKNjZRHPbrF10249Z3kDZSAq2yzQ1TjKvoLBQ37    - type: precision38      value: 0.889867841409691739      name: Precision40      verified: true41      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTczZjUwY2MzNTMzY2VlMjFmZGI2MzAwNTEwM2IzYWVkYmFiNjk0MDM3YmYzYjFmNGM3NWI5NDIzODJjMTA1ZCIsInZlcnNpb24iOjF9.3RC343Rtep7yxGH82c1WV2IAVqhJTRoOwiwFVp_w0K0JK_dTqnfEylLb1yMt367ztvkhhOgRn4i9GsL4ZNC5BQ42    - type: recall43      value: 0.909909909909909944      name: Recall45      verified: true46      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmM4M2Y3YTVjOTlhZjc2OGUxMzFhNGI3YzM4MDI0NDMwMmQyMmRmY2MyMTI5ZTdmYWVjMTlmYWE0N2Q0ZjJiNyIsInZlcnNpb24iOjF9.lMKosw258_E40HdqY8BFyWVJYAMx4cpVyYusGEqN429_cv3DzeIMaOr00trGsJX3BIqr-j5ScjLVV79f5nK2CA47    - type: auc48      value: 0.967218678959333149      name: AUC50      verified: true51      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzY1YmM4YjJhNTY2ZmIyYmI5ZTBjZjc3MDZiMzQ3ZTEyZWQ1M2I4ZTk4OGYwNzZiY2VlODRkODRjNTg2MDNmMSIsInZlcnNpb24iOjF9.tO3GQ5Rgl26zHz18-yR2wtcajmb_MEPNCZiA1Exz4255-m1iDFyMPM2Pw4s75xUSXWzsF--bo6eqmCLo4yjkBw52    - type: f153      value: 0.899777282850779554      name: F155      verified: true56      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmM0ZjhjZWY2ZGZiYWZhOTY2OWUwNzcxMTRlNjU4MDMyMWViMjg2YzE0YzBiMzVlYTU2ODkyZWY0MzcxOWJlOCIsInZlcnNpb24iOjF9.sySuyn4j72Gt3wstru118StL7pzGgZKzAPtE0FM7HVfdBrVXwZckKaUmoQR-nKaVynbo1h4mykNdM-_MwmLlCA57    - type: loss58      value: 0.3009203672409057659      name: loss60      verified: true61      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQ2ZjJiMjVhNTMxZGIxMTFlMjVhYTQyOGI2YjgyOTI3OTQ4NGU0ZWYxMDY2MmI1OGNiNDcwNTU3MmEzM2YzZSIsInZlcnNpb24iOjF9.MGCrOvwyOdMQ91z2pzgsIxS-PMCZy2YwNX7IuMNAVokRhTSGUYtFt-8px1Dv9w39IT6ZbySZ7kQQKz6kK8HWAQ62    - type: matthews_correlation63      value: 0.79363058479581464      name: matthews_correlation65      verified: true66      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGY5ODMyZjc4MTk0NWU1YTRmNGI5NDU0ZGRlMDEwY2ZhN2YzMjAxNDE2MTY4ZTI2OWZjMzkwMzc5NTY3NTlkMSIsInZlcnNpb24iOjF9.1WB_1AIkuk68pphfqpqB_T1VpM3wJPe7mNGOvaDANcek7TKUFuT6kA8J1h1SICS_80mdXDI4yJGGZy3CZwpXDQ67---68 69<!-- This model card has been generated automatically according to the information the Trainer had access to. You70should probably proofread and complete it, then remove this comment. -->71 72# binary-classification73 74This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.75It achieves the following results on the evaluation set:76- Loss: 0.300977- Accuracy: 0.896878 79## Model description80 81More information needed82 83## Intended uses & limitations84 85More information needed86 87## Training and evaluation data88 89More information needed90 91## Training procedure92 93### Training hyperparameters94 95The following hyperparameters were used during training:96- learning_rate: 2e-0597- train_batch_size: 1698- eval_batch_size: 1699- seed: 42100- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08101- lr_scheduler_type: linear102- num_epochs: 1103 104### Training results105 106| Training Loss | Epoch | Step | Validation Loss | Accuracy |107|:-------------:|:-----:|:----:|:---------------:|:--------:|108| 0.175         | 1.0   | 4210 | 0.3009          | 0.8968   |109 110 111### Framework versions112 113- Transformers 4.19.2114- Pytorch 1.11.0+cu113115- Datasets 2.2.2116- Tokenizers 0.12.1117