autoevaluate/multi-class-classification

1---2license: apache-2.03tags:4- generated_from_trainer5datasets:6- emotion7metrics:8- accuracy9---10 11<!-- This model card has been generated automatically according to the information the Trainer had access to. You12should probably proofread and complete it, then remove this comment. -->13 14# multi-class-classification15 16This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.17It achieves the following results on the evaluation set:18- Loss: 0.200919- Accuracy: 0.92820 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 2e-0539- train_batch_size: 1640- eval_batch_size: 1641- seed: 4242- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0843- lr_scheduler_type: linear44- num_epochs: 145 46### Training results47 48| Training Loss | Epoch | Step | Validation Loss | Accuracy |49|:-------------:|:-----:|:----:|:---------------:|:--------:|50| 0.2643        | 1.0   | 1000 | 0.2009          | 0.928    |51 52 53### Framework versions54 55- Transformers 4.19.256- Pytorch 1.11.0+cu11357- Datasets 2.2.258- Tokenizers 0.12.159