CS505-Classifier-T4_predictLabel_a1_v11

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: 0.0012

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: 70

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.98	48	0.6966
No log	1.96	96	0.3265
No log	2.94	144	0.2746
No log	3.92	192	0.1899
No log	4.9	240	0.1671
No log	5.88	288	0.1193
No log	6.86	336	0.1259
No log	7.84	384	0.0737
No log	8.82	432	0.0461
No log	9.8	480	0.0490
0.3023	10.78	528	0.0293
0.3023	11.76	576	0.0324
0.3023	12.73	624	0.0355
0.3023	13.71	672	0.0331
0.3023	14.69	720	0.0158
0.3023	15.67	768	0.0108
0.3023	16.65	816	0.0062
0.3023	17.63	864	0.0048
0.3023	18.61	912	0.0038
0.3023	19.59	960	0.0053
0.0241	20.57	1008	0.0077
0.0241	21.55	1056	0.0027
0.0241	22.53	1104	0.0025
0.0241	23.51	1152	0.0051
0.0241	24.49	1200	0.0088
0.0241	25.47	1248	0.0023
0.0241	26.45	1296	0.0023
0.0241	27.43	1344	0.0022
0.0241	28.41	1392	0.0018
0.0241	29.39	1440	0.0019
0.0241	30.37	1488	0.0018
0.0065	31.35	1536	0.0017
0.0065	32.33	1584	0.0033
0.0065	33.31	1632	0.0016
0.0065	34.29	1680	0.0017
0.0065	35.27	1728	0.0015
0.0065	36.24	1776	0.0017
0.0065	37.22	1824	0.0015
0.0065	38.2	1872	0.0015
0.0065	39.18	1920	0.0014
0.0065	40.16	1968	0.0014
0.0028	41.14	2016	0.0014
0.0028	42.12	2064	0.0026
0.0028	43.1	2112	0.0015
0.0028	44.08	2160	0.0014
0.0028	45.06	2208	0.0013
0.0028	46.04	2256	0.0013
0.0028	47.02	2304	0.0013
0.0028	48.0	2352	0.0013
0.0028	48.98	2400	0.0013
0.0028	49.96	2448	0.0013
0.0028	50.94	2496	0.0013
0.002	51.92	2544	0.0012
0.002	52.9	2592	0.0012
0.002	53.88	2640	0.0012
0.002	54.86	2688	0.0012
0.002	55.84	2736	0.0013
0.002	56.82	2784	0.0012
0.002	57.8	2832	0.0012
0.002	58.78	2880	0.0012
0.002	59.76	2928	0.0012
0.002	60.73	2976	0.0012
0.0016	61.71	3024	0.0012
0.0016	62.69	3072	0.0012
0.0016	63.67	3120	0.0012
0.0016	64.65	3168	0.0012
0.0016	65.63	3216	0.0012
0.0016	66.61	3264	0.0012
0.0016	67.59	3312	0.0012
0.0016	68.57	3360	0.0012
0.0016	69.55	3408	0.0012

Framework versions

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