DACN2

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: 3.1474

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	347	1.1891
1.3935	2.0	694	1.1047
0.8907	3.0	1041	1.0154
0.8907	4.0	1388	1.0854
0.593	5.0	1735	1.3185
0.3795	6.0	2082	1.5470
0.3795	7.0	2429	1.4931
0.2399	8.0	2776	1.6889
0.1596	9.0	3123	1.8808
0.1596	10.0	3470	2.0850
0.1084	11.0	3817	2.3343
0.0806	12.0	4164	2.5696
0.0472	13.0	4511	2.6458
0.0472	14.0	4858	2.7680
0.0485	15.0	5205	2.8165
0.0417	16.0	5552	2.8918
0.0417	17.0	5899	3.0412
0.0233	18.0	6246	3.0186
0.0193	19.0	6593	3.0639
0.0193	20.0	6940	3.0657
0.0191	21.0	7287	2.9095
0.0146	22.0	7634	3.0045
0.0146	23.0	7981	3.2984
0.013	24.0	8328	3.3791
0.0131	25.0	8675	3.2946
0.0101	26.0	9022	3.2814
0.0101	27.0	9369	3.3177
0.0114	28.0	9716	3.2819
0.0046	29.0	10063	3.2945
0.0046	30.0	10410	3.3072

Framework versions

• Transformers 4.35.2
• Pytorch 2.5.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.2