AnonymousCS/populism_classifier_bsample_399

1---2library_name: transformers3license: apache-2.04base_model: google/rembert5tags:6- generated_from_trainer7metrics:8- accuracy9model-index:10- name: populism_classifier_bsample_39911  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# populism_classifier_bsample_39918 19This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on the None dataset.20It achieves the following results on the evaluation set:21- Loss: 0.688322- Accuracy: 0.854823- 1-f1: 0.422824- 1-recall: 0.963025- 1-precision: 0.270826- Balanced Acc: 0.905727 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: 1e-0546- train_batch_size: 3247- eval_batch_size: 3248- seed: 4249- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments50- lr_scheduler_type: linear51- num_epochs: 2052- mixed_precision_training: Native AMP53 54### Training results55 56| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |57|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|58| 0.0644        | 1.0   | 7    | 0.2491          | 0.9223   | 0.5778 | 0.9630   | 0.4127      | 0.9414       |59| 0.0028        | 2.0   | 14   | 0.6544          | 0.8487   | 0.4127 | 0.9630   | 0.2626      | 0.9025       |60| 0.0009        | 3.0   | 21   | 0.6883          | 0.8548   | 0.4228 | 0.9630   | 0.2708      | 0.9057       |61 62 63### Framework versions64 65- Transformers 4.46.366- Pytorch 2.4.1+cu12167- Datasets 3.1.068- Tokenizers 0.20.369