Beit_PhoBart / README.md
Skyler215's picture
End of training
67b05dc verified
metadata
library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: Beit_PhoBart
    results: []

Beit_PhoBart

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

  • Loss: 1.5865
  • Bleu-4: 0.0954

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • 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: 300
  • num_epochs: 100
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu-4
No log 1.0 236 1.7574 0.0672
1.9578 2.0 472 1.6226 0.0748
1.5495 3.0 708 1.5523 0.0796
1.3763 4.0 944 1.4998 0.0821
1.3763 5.0 1180 1.4815 0.0881
1.2355 6.0 1416 1.4835 0.0875
1.1027 7.0 1652 1.4790 0.0926
0.9865 8.0 1888 1.5128 0.0925
0.884 9.0 2124 1.5453 0.0956
0.884 10.0 2360 1.5865 0.0954

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3