Edit model card

DistilBERT-finetuned-on-emotion

This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2180
  • Accuracy: 0.9235
  • F1: 0.9235

Model description

DiestilBERT is fine-tuned on emotions dataset. Click the following link to see how the model works: https://huggingface.co/spaces/Rahmat82/emotions_classifier

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.8046 1.0 250 0.3115 0.9085 0.9081
0.2405 2.0 500 0.2180 0.9235 0.9235

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
1,120
Safetensors
Model size
67M params
Tensor type
F32
·

Finetuned from

Dataset used to train Rahmat82/DistilBERT-finetuned-on-emotion

Space using Rahmat82/DistilBERT-finetuned-on-emotion 1

Evaluation results