Edit model card

finetuned_sentence_itr0_2e-05_all_26_02_2022-03_57_45

This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4345
  • Accuracy: 0.8321
  • F1: 0.8904

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: 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: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.0 195 0.3922 0.8061 0.8747
No log 2.0 390 0.3764 0.8171 0.8837
0.4074 3.0 585 0.3873 0.8220 0.8843
0.4074 4.0 780 0.4361 0.8232 0.8854
0.4074 5.0 975 0.4555 0.8159 0.8793

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.1+cu113
  • Datasets 1.18.0
  • Tokenizers 0.10.3
Downloads last month
5
Inference API
This model can be loaded on Inference API (serverless).