freeze-viet-tay-combine

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

• Loss: 0.1783
• Sacrebleu: 14.0257
• Meteor: 0.1498

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu	Meteor
0.2618	1.0	6418	0.1882	11.8172	0.1159
0.2001	2.0	12836	0.1788	13.6365	0.1440
0.18	3.0	19254	0.1783	14.0257	0.1498

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1