CS505-NerCOQE-PhoBERT-Object

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: 0.0001
• 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	0.1756	0.3581
No log	2.0	106	0.0932	0.6366
No log	3.0	159	0.0513	0.7744
No log	4.0	212	0.0179	0.9116
No log	5.0	265	0.0140	0.8816
No log	6.0	318	0.0071	0.9495
No log	7.0	371	0.0036	0.9686
No log	8.0	424	0.0029	0.9814
No log	9.0	477	0.0026	0.9784
No log	10.0	530	0.0011	0.9921
No log	11.0	583	0.0012	0.9902
No log	12.0	636	0.0008	0.9951
No log	13.0	689	0.0011	0.9931
No log	14.0	742	0.0003	0.9960
No log	15.0	795	0.0003	0.9990
No log	16.0	848	0.0001	1.0
No log	17.0	901	0.0002	0.9990
No log	18.0	954	0.0001	1.0
No log	19.0	1007	0.0001	1.0
No log	20.0	1060	0.0001	1.0

Framework versions

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