CS505-NerCOQE-PhoBERT-Aspect

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

• Loss: 0.0002
• F1: 1.0

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: 16
• eval_batch_size: 128
• 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	F1
No log	1.0	53	0.2631	0.1626
No log	2.0	106	0.1622	0.3338
No log	3.0	159	0.1359	0.5259
No log	4.0	212	0.0471	0.8120
No log	5.0	265	0.0417	0.7700
No log	6.0	318	0.0294	0.8356
No log	7.0	371	0.0101	0.9432
No log	8.0	424	0.0051	0.9685
No log	9.0	477	0.0077	0.9554
No log	10.0	530	0.0017	0.9900
No log	11.0	583	0.0036	0.9823
No log	12.0	636	0.0017	0.9871
No log	13.0	689	0.0008	0.9978
No log	14.0	742	0.0007	0.9964
No log	15.0	795	0.0004	0.9986
No log	16.0	848	0.0002	1.0
No log	17.0	901	0.0002	1.0
No log	18.0	954	0.0002	0.9993
No log	19.0	1007	0.0002	1.0
No log	20.0	1060	0.0002	1.0

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2