CS505-Classifier-T4_predictLabel_a1_v4

This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0046

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.98	48	1.0265
No log	1.96	96	0.5809
No log	2.94	144	0.3461
No log	3.92	192	0.2725
No log	4.9	240	0.2168
No log	5.88	288	0.1728
No log	6.86	336	0.1516
No log	7.84	384	0.1076
No log	8.82	432	0.0783
No log	9.8	480	0.0653
0.4162	10.78	528	0.0473
0.4162	11.76	576	0.0413
0.4162	12.73	624	0.0344
0.4162	13.71	672	0.0253
0.4162	14.69	720	0.0244
0.4162	15.67	768	0.0204
0.4162	16.65	816	0.0210
0.4162	17.63	864	0.0168
0.4162	18.61	912	0.0155
0.4162	19.59	960	0.0132
0.0375	20.57	1008	0.0130
0.0375	21.55	1056	0.0097
0.0375	22.53	1104	0.0088
0.0375	23.51	1152	0.0081
0.0375	24.49	1200	0.0080
0.0375	25.47	1248	0.0069
0.0375	26.45	1296	0.0065
0.0375	27.43	1344	0.0062
0.0375	28.41	1392	0.0060
0.0375	29.39	1440	0.0056
0.0375	30.37	1488	0.0055
0.0114	31.35	1536	0.0053
0.0114	32.33	1584	0.0052
0.0114	33.31	1632	0.0051
0.0114	34.29	1680	0.0049
0.0114	35.27	1728	0.0048
0.0114	36.24	1776	0.0048
0.0114	37.22	1824	0.0047
0.0114	38.2	1872	0.0047
0.0114	39.18	1920	0.0046

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2