rafaeljosem's picture
update model card README.md
0fd4d65
|
raw
history blame
2.27 kB
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: DeepESP-gpt2-spanish-tripadvisor
    results: []

DeepESP-gpt2-spanish-tripadvisor

This model is a fine-tuned version of DeepESP/gpt2-spanish on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5865

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
0.8665 1.0 2089 0.7441
0.7336 2.0 4178 0.6916
0.6856 3.0 6267 0.6632
0.6559 4.0 8356 0.6446
0.6341 5.0 10445 0.6322
0.6169 6.0 12534 0.6213
0.6022 7.0 14623 0.6138
0.5896 8.0 16712 0.6096
0.5788 9.0 18801 0.6037
0.5692 10.0 20890 0.5989
0.5604 11.0 22979 0.5965
0.5528 12.0 25068 0.5941
0.5457 13.0 27157 0.5915
0.5392 14.0 29246 0.5900
0.5334 15.0 31335 0.5879
0.5285 16.0 33424 0.5875
0.524 17.0 35513 0.5870
0.5209 18.0 37602 0.5866
0.5179 19.0 39691 0.5867
0.5157 20.0 41780 0.5865

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1
  • Datasets 2.13.0
  • Tokenizers 0.13.3