trhgquan's picture
End of training
75fef16 verified
metadata
library_name: transformers
license: mit
base_model: vinai/phobert-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: phobert-human-tl-seed-6969
    results: []

phobert-human-tl-seed-6969

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

  • Loss: 0.4535
  • Accuracy: 0.8387
  • Precision: 0.6438
  • Recall: 0.4677
  • F1: 0.4914

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: 0.0001
  • train_batch_size: 64
  • eval_batch_size: 64
  • 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
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
No log 1.0 346 0.5154 0.8241 0.5456 0.3492 0.3314
0.5778 2.0 692 0.4712 0.8305 0.6220 0.4062 0.4191
0.4667 3.0 1038 0.4650 0.8331 0.6490 0.4069 0.4227
0.4667 4.0 1384 0.4665 0.8365 0.6819 0.4147 0.4337
0.4617 5.0 1730 0.4639 0.8357 0.6591 0.4129 0.4337
0.4577 6.0 2076 0.4606 0.8368 0.6775 0.4282 0.4479
0.4577 7.0 2422 0.4626 0.8361 0.6851 0.4134 0.4359
0.4554 8.0 2768 0.4530 0.8394 0.6468 0.4436 0.4674
0.4545 9.0 3114 0.4599 0.8342 0.6459 0.4083 0.4288
0.4545 10.0 3460 0.4603 0.8350 0.6825 0.4375 0.4543
0.4587 11.0 3806 0.4594 0.8346 0.6499 0.4092 0.4321
0.4491 12.0 4152 0.4535 0.8387 0.6438 0.4677 0.4914
0.4491 13.0 4498 0.4555 0.8353 0.6372 0.4213 0.4475
0.4579 14.0 4844 0.4563 0.8357 0.6552 0.4129 0.4359
0.4488 15.0 5190 0.4595 0.8335 0.6553 0.4019 0.4217
0.4587 16.0 5536 0.4663 0.8327 0.6580 0.3987 0.4161
0.4587 17.0 5882 0.4515 0.8387 0.6235 0.4357 0.4612

Framework versions

  • Transformers 4.51.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.0