Edit model card

results

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

  • Loss: 1.0423

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.5971 0.0634 100 1.0645
1.0654 0.1268 200 1.0526
1.0594 0.1902 300 1.0474
1.0548 0.2536 400 1.0448
1.0489 0.3171 500 1.0423
1.0333 0.3805 600 1.0416
1.0436 0.4439 700 1.0468
1.0037 0.5073 800 1.0841
0.9715 0.5707 900 1.4914
0.9784 0.6341 1000 1.4177
0.9652 0.6975 1100 1.6000
0.9476 0.7609 1200 1.5676
0.9604 0.8244 1300 1.6288
0.9493 0.8878 1400 1.6467
0.9531 0.9512 1500 1.6205

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.1+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
420M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from