agi-css/distilroberta-base-etc

1---2license: apache-2.03tags:4- generated_from_trainer5metrics:6- accuracy7- f18model-index:9- name: distilroberta-base-etc10  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# distilroberta-base-etc17 18This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.19It achieves the following results on the evaluation set:20- Loss: 0.338221- Accuracy: 0.91922- F1: 0.919023 24## Model description25 26More information needed27 28## Intended uses & limitations29 30More information needed31 32## Training and evaluation data33 34More information needed35 36## Training procedure37 38### Training hyperparameters39 40The following hyperparameters were used during training:41- learning_rate: 4.969790133269121e-0542- train_batch_size: 40043- eval_batch_size: 40044- seed: 4245- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0846- lr_scheduler_type: linear47- num_epochs: 748 49### Training results50 51| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |52|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|53| No log        | 1.0   | 84   | 0.2372          | 0.907    | 0.9070 |54| No log        | 2.0   | 168  | 0.2358          | 0.9083   | 0.9083 |55| No log        | 3.0   | 252  | 0.2430          | 0.9137   | 0.9137 |56| No log        | 4.0   | 336  | 0.2449          | 0.919    | 0.9190 |57| No log        | 5.0   | 420  | 0.2884          | 0.9193   | 0.9193 |58| No log        | 6.0   | 504  | 0.3179          | 0.9167   | 0.9167 |59| No log        | 7.0   | 588  | 0.3382          | 0.919    | 0.9190 |60 61 62### Framework versions63 64- Transformers 4.18.065- Pytorch 1.11.0+cu11366- Datasets 2.1.067- Tokenizers 0.12.168