Edit model card

distilbert-base-uncased-finetuned-sst2

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

  • Loss: 0.6600
  • Accuracy: 0.9037

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: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0367 1.0 4210 0.5104 0.8968
0.0287 2.0 8420 0.6466 0.9002
0.0372 3.0 12630 0.5988 0.9014
0.028 4.0 16840 0.6600 0.9037
0.0111 5.0 21050 0.8030 0.9014

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
8
Safetensors
Model size
67M params
Tensor type
F32
·

Finetuned from

Dataset used to train dinhlnd1610/distilbert-base-uncased-finetuned-sst2

Evaluation results