omersubasi's picture
update model card README.md
65ccbaa
|
raw
history blame
2.06 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: fine-tune-vanilla-bert-base-uncased-ch9
    results: []

fine-tune-vanilla-bert-base-uncased-ch9

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

  • Loss: 0.1877
  • Micro f1: 0.7208
  • Macro f1: 0.6293

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: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Micro f1 Macro f1
0.4535 1.0 56 0.3607 0.0 0.0
0.3388 2.0 112 0.3270 0.0 0.0
0.3023 3.0 168 0.2794 0.4654 0.2139
0.2515 4.0 224 0.2420 0.4750 0.1855
0.2095 5.0 280 0.2263 0.5318 0.2599
0.1673 6.0 336 0.2135 0.6429 0.4327
0.1424 7.0 392 0.1885 0.6631 0.4890
0.1049 8.0 448 0.1801 0.7164 0.6139
0.08 9.0 504 0.1802 0.7136 0.6020
0.0637 10.0 560 0.1877 0.7208 0.6293

Framework versions

  • Transformers 4.16.2
  • Pytorch 2.1.0+cu118
  • Datasets 1.16.1
  • Tokenizers 0.15.0