BARTBana_Before

This model is a fine-tuned version of vinai/bartpho-syllable on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4830

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 15.0

Training results

Training Loss Epoch Step Validation Loss
5.2274 1.0 677 3.7284
3.8195 2.0 1354 2.6138
2.5688 3.0 2031 2.2841
2.3493 4.0 2708 2.0703
2.187 5.0 3385 1.9266
1.9879 6.0 4062 1.8244
1.9203 7.0 4739 1.7417
1.8537 8.0 5416 1.6667
1.7535 9.0 6093 1.6369
1.7223 10.0 6770 1.6014
1.6815 11.0 7447 1.5564
1.6334 12.0 8124 1.5452
1.6219 13.0 8801 1.5036
1.589 14.0 9478 1.5131
1.5717 15.0 10155 1.5005

Framework versions

  • Transformers 4.48.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
10
Safetensors
Model size
396M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for IAmSkyDra/BARTBana_v0

Finetuned
(44)
this model
Finetunes
1 model