HintsGenerator / README.md
vishnun's picture
update model card README.md
f23a7e0
|
raw
history blame
1.73 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: HintsGenerator
    results: []

HintsGenerator

This model is a fine-tuned version of patrickvonplaten/t5-tiny-random on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 5.7914

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-05
  • train_batch_size: 16
  • 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
4.8644 1.0 4212 7.3992
4.2267 2.0 8424 6.8927
3.8213 3.0 12636 6.5816
3.5707 4.0 16848 6.3507
3.3617 5.0 21060 6.1117
3.2614 6.0 25272 5.9754
3.1676 7.0 29484 5.8835
3.1363 8.0 33696 5.8340
3.1046 9.0 37908 5.7960
3.1239 10.0 42120 5.7914

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3