Model

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: 3.4924

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 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	347	3.4224
0.0766	2.0	694	3.0937
0.0569	3.0	1041	3.4725
0.0569	4.0	1388	3.3484
0.0365	5.0	1735	3.5406
0.0364	6.0	2082	3.3922
0.0364	7.0	2429	3.2977
0.0353	8.0	2776	3.3093
0.0136	9.0	3123	3.5960
0.0136	10.0	3470	3.5143
0.0249	11.0	3817	3.5032
0.0156	12.0	4164	3.5010
0.0154	13.0	4511	3.4902
0.0154	14.0	4858	3.5322
0.0116	15.0	5205	3.4929
0.0066	16.0	5552	3.5660
0.0066	17.0	5899	3.5789
0.0053	18.0	6246	3.5614
0.003	19.0	6593	3.5579
0.003	20.0	6940	3.5902

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 2.16.1
• Tokenizers 0.21.0