CS505-Classifier-T4_predictLabel_a1

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

• Loss: 0.0155

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.98	48	1.0473
No log	1.96	96	0.5664
No log	2.94	144	0.3371
No log	3.92	192	0.2277
No log	4.9	240	0.1850
No log	5.88	288	0.1451
No log	6.86	336	0.1126
No log	7.84	384	0.0853
No log	8.82	432	0.0635
No log	9.8	480	0.0598
0.4029	10.78	528	0.0407
0.4029	11.76	576	0.0337
0.4029	12.73	624	0.0300
0.4029	13.71	672	0.0270
0.4029	14.69	720	0.0209
0.4029	15.67	768	0.0196
0.4029	16.65	816	0.0205
0.4029	17.63	864	0.0181
0.4029	18.61	912	0.0160
0.4029	19.59	960	0.0155

Framework versions

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