kapliff89's picture
Upload tokenizer
d1f43e8 verified
metadata
tags:
  - generated_from_trainer
base_model: klue/roberta-base
model-index:
  - name: roberta-base-finetuned-nmrv
    results: []

roberta-base-finetuned-nmrv

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

  • Loss: 0.4680

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.3653 1.0 6250 0.3319
0.2665 2.0 12500 0.3970
0.1822 3.0 18750 0.4680

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1