funnel-test-512 / README.md
lectura's picture
End of training
d57e53b verified
metadata
license: apache-2.0
base_model: funnel-transformer/xlarge-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: funnel-test-512
    results: []

funnel-test-512

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

  • Loss: 0.4556
  • Accuracy: 0.8041

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: 1e-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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6108 0.2 59 0.6724 0.6460
0.651 0.4 118 0.6463 0.6451
0.6052 0.61 177 0.6210 0.6424
0.4588 0.81 236 0.4556 0.8041

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1
  • Datasets 2.16.1
  • Tokenizers 0.15.0