Hugging Face's logo

ywongnon
/
finetuned-bert-mrpc

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
finetuned-bert-mrpc / README.md
ywongnon's picture
ywongnon
End of training
559b871 verified
preview code
|
raw
history blame contribute delete
1.55 kB
metadata
license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: finetuned-bert-mrpc
    results: []

finetuned-bert-mrpc

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

  • Loss: 0.4169
  • Accuracy: 0.8456
  • F1: 0.8916

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: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.5961 1.0 230 0.4327 0.8211 0.8805
0.3717 2.0 460 0.3646 0.8456 0.8930
0.2154 3.0 690 0.4169 0.8456 0.8916

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.2.1+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.2