CS505-Classifier-T4_predictLabel_a1_v6

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: 0.0014

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: 5e-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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.98	48	0.6632
No log	1.96	96	0.3136
No log	2.94	144	0.2453
No log	3.92	192	0.1673
No log	4.9	240	0.1249
No log	5.88	288	0.0850
No log	6.86	336	0.0718
No log	7.84	384	0.0576
No log	8.82	432	0.0567
No log	9.8	480	0.0530
0.2878	10.78	528	0.0307
0.2878	11.76	576	0.0376
0.2878	12.73	624	0.0170
0.2878	13.71	672	0.0195
0.2878	14.69	720	0.0111
0.2878	15.67	768	0.0131
0.2878	16.65	816	0.0109
0.2878	17.63	864	0.0073
0.2878	18.61	912	0.0043
0.2878	19.59	960	0.0032
0.0238	20.57	1008	0.0067
0.0238	21.55	1056	0.0027
0.0238	22.53	1104	0.0025
0.0238	23.51	1152	0.0025
0.0238	24.49	1200	0.0022
0.0238	25.47	1248	0.0022
0.0238	26.45	1296	0.0021
0.0238	27.43	1344	0.0020
0.0238	28.41	1392	0.0019
0.0238	29.39	1440	0.0019
0.0238	30.37	1488	0.0018
0.0036	31.35	1536	0.0018
0.0036	32.33	1584	0.0018
0.0036	33.31	1632	0.0017
0.0036	34.29	1680	0.0017
0.0036	35.27	1728	0.0016
0.0036	36.24	1776	0.0017
0.0036	37.22	1824	0.0016
0.0036	38.2	1872	0.0016
0.0036	39.18	1920	0.0015
0.0036	40.16	1968	0.0015
0.0022	41.14	2016	0.0015
0.0022	42.12	2064	0.0015
0.0022	43.1	2112	0.0015
0.0022	44.08	2160	0.0015
0.0022	45.06	2208	0.0015
0.0022	46.04	2256	0.0015
0.0022	47.02	2304	0.0015
0.0022	48.0	2352	0.0015
0.0022	48.98	2400	0.0014
0.0022	49.96	2448	0.0014

Framework versions

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