CS505-Classifier-T4_predictLabel_a1_v5

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: 0.0018

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: 40

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.98	48	0.6517
No log	1.96	96	0.3227
No log	2.94	144	0.2342
No log	3.92	192	0.1815
No log	4.9	240	0.1703
No log	5.88	288	0.1231
No log	6.86	336	0.0730
No log	7.84	384	0.0803
No log	8.82	432	0.0476
No log	9.8	480	0.0384
0.2908	10.78	528	0.0281
0.2908	11.76	576	0.0329
0.2908	12.73	624	0.0234
0.2908	13.71	672	0.0119
0.2908	14.69	720	0.0101
0.2908	15.67	768	0.0081
0.2908	16.65	816	0.0137
0.2908	17.63	864	0.0075
0.2908	18.61	912	0.0053
0.2908	19.59	960	0.0035
0.0216	20.57	1008	0.0060
0.0216	21.55	1056	0.0028
0.0216	22.53	1104	0.0027
0.0216	23.51	1152	0.0026
0.0216	24.49	1200	0.0024
0.0216	25.47	1248	0.0023
0.0216	26.45	1296	0.0022
0.0216	27.43	1344	0.0022
0.0216	28.41	1392	0.0021
0.0216	29.39	1440	0.0020
0.0216	30.37	1488	0.0021
0.0043	31.35	1536	0.0020
0.0043	32.33	1584	0.0019
0.0043	33.31	1632	0.0019
0.0043	34.29	1680	0.0019
0.0043	35.27	1728	0.0019
0.0043	36.24	1776	0.0019
0.0043	37.22	1824	0.0019
0.0043	38.2	1872	0.0018
0.0043	39.18	1920	0.0018

Framework versions

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