Hugging Face's logo

bella05
/
mango-8-0.00002-fin

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
mango-8-0.00002-fin / README.md
bella05's picture
bella05
End of training
dcdd4cf verified
preview code
|
raw
history blame contribute delete
1.53 kB
metadata
base_model: klue/roberta-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: mango-8-0.00002-fin
    results: []

mango-8-0.00002-fin

This model is a fine-tuned version of klue/roberta-large on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8943
  • Accuracy: 0.6359
  • F1: 0.6341

Model description

More information needed

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.4634 1.0 932 1.3093 0.6319 0.6226
0.3085 2.0 1864 1.5492 0.6426 0.6304
0.1601 3.0 2796 1.8943 0.6359 0.6341

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0a0+b5021ba
  • Datasets 2.6.2
  • Tokenizers 0.14.1