autoevaluate/multi-class-classification-not-evaluated

1---2license: apache-2.03tags:4- generated_from_trainer5datasets:6- emotion7metrics:8- accuracy9duplicated_from: autoevaluate/multi-class-classification10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# multi-class-classification16 17This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.18It achieves the following results on the evaluation set:19- Loss: 0.200920- Accuracy: 0.92821 22## Model description23 24More information needed25 26## Intended uses & limitations27 28More information needed29 30## Training and evaluation data31 32More information needed33 34## Training procedure35 36### Training hyperparameters37 38The following hyperparameters were used during training:39- learning_rate: 2e-0540- train_batch_size: 1641- eval_batch_size: 1642- seed: 4243- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0844- lr_scheduler_type: linear45- num_epochs: 146 47### Training results48 49| Training Loss | Epoch | Step | Validation Loss | Accuracy |50|:-------------:|:-----:|:----:|:---------------:|:--------:|51| 0.2643        | 1.0   | 1000 | 0.2009          | 0.928    |52 53 54### Framework versions55 56- Transformers 4.19.257- Pytorch 1.11.0+cu11358- Datasets 2.2.259- Tokenizers 0.12.160