votaquangnhat's picture
End of training
6f16453 verified
metadata
library_name: transformers
license: mit
base_model: danghuy1999/gpt2-viwiki
tags:
  - generated_from_trainer
model-index:
  - name: vietnamese-poem-gpt2-sauchu
    results: []

vietnamese-poem-gpt2-sauchu

This model is a fine-tuned version of danghuy1999/gpt2-viwiki on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 5.2482

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 136 6.4141
No log 2.0 272 6.0165
No log 3.0 408 5.7615
6.3641 4.0 544 5.5938
6.3641 5.0 680 5.4852
6.3641 6.0 816 5.4277
6.3641 7.0 952 5.3807
5.418 8.0 1088 5.3497
5.418 9.0 1224 5.3235
5.418 10.0 1360 5.3024
5.418 11.0 1496 5.2961
5.1065 12.0 1632 5.2781
5.1065 13.0 1768 5.2753
5.1065 14.0 1904 5.2596
4.9363 15.0 2040 5.2568
4.9363 16.0 2176 5.2558
4.9363 17.0 2312 5.2497
4.9363 18.0 2448 5.2536
4.8312 19.0 2584 5.2485
4.8312 20.0 2720 5.2482

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0