doyoungkim's picture
add model
67be788
|
raw
history blame
1.77 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model_index:
  - name: bert-base-uncased-finetuned-sst2
    results:
      - dataset:
          name: glue
          type: glue
          args: sst2
        metric:
          name: Accuracy
          type: accuracy
          value: 0.9357798165137615

bert-base-uncased-finetuned-sst2

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

  • Loss: 0.4175
  • Accuracy: 0.9358

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
0.178 1.0 4210 0.3340 0.9037
0.1246 2.0 8420 0.3303 0.9186
0.0756 3.0 12630 0.3180 0.9289
0.0663 4.0 16840 0.3218 0.9323
0.0389 5.0 21050 0.4175 0.9358

Framework versions

  • Transformers 4.9.1
  • Pytorch 1.9.0+cu102
  • Datasets 1.11.0
  • Tokenizers 0.10.3