Peppa-Pig / README.md
jenny1998's picture
End of training
40e683e verified
|
raw
history blame
1.47 kB
metadata
license: mit
base_model: DeepESP/gpt2-spanish
tags:
  - generated_from_trainer
model-index:
  - name: Peppa-Pig
    results: []

Peppa-Pig

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: 0.7720

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: 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: 5

Training results

Training Loss Epoch Step Validation Loss
0.8665 1.0 280 0.8239
0.7219 2.0 560 0.7911
0.5982 3.0 840 0.7747
0.5209 4.0 1120 0.7717
0.5325 5.0 1400 0.7720

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0