xmod-base / README.md
Ghunghru's picture
End of training
b741281 verified
metadata
license: mit
base_model: facebook/xmod-base
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: xmod-base
    results: []

xmod-base

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

  • Loss: 0.5756
  • F1: 0.4000

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-06
  • 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 F1
0.6685 1.0 189 0.6350 0.0
0.6631 2.0 378 0.6223 0.0
0.6368 3.0 567 0.6064 0.0
0.6075 4.0 756 0.5928 0.0
0.6102 5.0 945 0.5549 0.3729
0.5635 6.0 1134 0.6121 0.2727
0.5783 7.0 1323 0.5595 0.4118
0.5206 8.0 1512 0.5852 0.4068
0.5619 9.0 1701 0.5778 0.4000
0.5518 10.0 1890 0.5756 0.4000

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.2
  • Datasets 2.12.0
  • Tokenizers 0.13.3