ajrayman/Morality_binary

1---2library_name: transformers3license: mit4base_model: microsoft/deberta-v3-base5tags:6- generated_from_trainer7metrics:8- accuracy9- precision10- recall11- f112model-index:13- name: Morality_binary14  results: []15---16 17<!-- This model card has been generated automatically according to the information the Trainer had access to. You18should probably proofread and complete it, then remove this comment. -->19 20# Morality_binary21 22This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.23It achieves the following results on the evaluation set:24- Loss: 0.706125- Accuracy: 0.709826- Precision: 0.715427- Recall: 0.695828- F1: 0.705429- Auc: 0.776830 31## Model description32 33More information needed34 35## Intended uses & limitations36 37More information needed38 39## Training and evaluation data40 41More information needed42 43## Training procedure44 45### Training hyperparameters46 47The following hyperparameters were used during training:48- learning_rate: 2e-0549- train_batch_size: 3250- eval_batch_size: 3251- seed: 123452- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0853- lr_scheduler_type: linear54- lr_scheduler_warmup_ratio: 0.0655- num_epochs: 856 57### Training results58 59| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Auc    |60|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|61| No log        | 1.0   | 118  | 0.6111          | 0.6538   | 0.5994    | 0.9252 | 0.7275 | 0.7760 |62| No log        | 2.0   | 236  | 0.5807          | 0.7086   | 0.6590    | 0.8628 | 0.7473 | 0.7903 |63| No log        | 3.0   | 354  | 0.5870          | 0.7136   | 0.6727    | 0.8304 | 0.7433 | 0.7975 |64| No log        | 4.0   | 472  | 0.7061          | 0.7098   | 0.7154    | 0.6958 | 0.7054 | 0.7768 |65 66 67### Framework versions68 69- Transformers 4.44.170- Pytorch 1.11.071- Datasets 2.12.072- Tokenizers 0.19.173