ryantaw's picture
End of training
44213ae
|
raw
history blame
2.09 kB
metadata
license: mit
base_model: prajjwal1/bert-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bert-small-finetuned
    results: []

bert-small-finetuned

This model is a fine-tuned version of prajjwal1/bert-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9943
  • Accuracy: 0.5822
  • F1 Score: 0.5820

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: 1.0136026165598675e-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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Score
No log 1.0 186 1.1631 0.4636 0.4346
No log 2.0 372 1.0563 0.5553 0.5558
1.1271 3.0 558 1.0238 0.5633 0.5629
1.1271 4.0 744 0.9990 0.5795 0.5786
1.1271 5.0 930 0.9943 0.5822 0.5820
0.8392 6.0 1116 1.0389 0.5741 0.5692
0.8392 7.0 1302 1.0114 0.5768 0.5759
0.8392 8.0 1488 1.0277 0.5741 0.5702
0.692 9.0 1674 1.0246 0.5822 0.5799
0.692 10.0 1860 1.0241 0.5822 0.5797

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1