DACN3_LVC

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: 3.6795

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	347	1.6767
0.233	2.0	694	1.7635
0.189	3.0	1041	1.9054
0.189	4.0	1388	2.2254
0.1566	5.0	1735	2.1978
0.1968	6.0	2082	2.1144
0.1968	7.0	2429	2.2885
0.1541	8.0	2776	2.3121
0.1055	9.0	3123	2.5475
0.1055	10.0	3470	2.7483
0.09	11.0	3817	2.7914
0.0716	12.0	4164	2.9014
0.0469	13.0	4511	3.1734
0.0469	14.0	4858	3.0398
0.0571	15.0	5205	3.3835
0.0646	16.0	5552	3.0768
0.0646	17.0	5899	3.2561
0.0263	18.0	6246	3.3902
0.0395	19.0	6593	3.3001
0.0395	20.0	6940	3.3090
0.0258	21.0	7287	3.3304
0.0284	22.0	7634	3.6674
0.0284	23.0	7981	3.4840
0.0227	24.0	8328	3.5787
0.0262	25.0	8675	3.4169
0.0263	26.0	9022	3.4694
0.0263	27.0	9369	3.5745
0.027	28.0	9716	3.5336
0.0175	29.0	10063	3.5374
0.0175	30.0	10410	3.5704
0.0185	31.0	10757	3.5223
0.012	32.0	11104	3.4871
0.012	33.0	11451	3.6621
0.0117	34.0	11798	3.4769
0.0106	35.0	12145	3.6008
0.0106	36.0	12492	3.8597
0.0104	37.0	12839	3.5269
0.0076	38.0	13186	3.6466
0.0051	39.0	13533	3.6385
0.0051	40.0	13880	3.6788
0.0069	41.0	14227	3.6508
0.0033	42.0	14574	3.6343
0.0033	43.0	14921	3.5916
0.0033	44.0	15268	3.5940
0.0033	45.0	15615	3.5818
0.0033	46.0	15962	3.6118
0.0024	47.0	16309	3.5790
0.0012	48.0	16656	3.5841
0.0028	49.0	17003	3.6151
0.0028	50.0	17350	3.6149

Framework versions

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