test_trainer / README.md
Newton Kimathi
End of training
4bac7b3
|
raw
history blame
1.52 kB
metadata
license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
model-index:
  - name: test_trainer
    results: []

test_trainer

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: 0.8618

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: 5e-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

Training results

Training Loss Epoch Step Validation Loss
0.7967 0.5 500 0.7875
0.7052 1.0 1000 0.6743
0.5908 1.5 1500 0.6750
0.57 2.0 2000 0.6167
0.3826 2.5 2500 0.7804
0.3326 3.0 3000 0.8618

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3