phobert-base-v2-finetuned-cola

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: 0.4604
• Accuracy: 0.9018
• F1: 0.9034
• Precision: 0.9080
• Recall: 0.9018

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	39	1.1866	0.8474	0.8536	0.8922	0.8474
No log	2.0	78	0.8260	0.8632	0.8683	0.8967	0.8632
No log	3.0	117	0.4604	0.9018	0.9034	0.9080	0.9018
No log	4.0	156	0.6405	0.8912	0.8927	0.8962	0.8912
No log	5.0	195	0.6415	0.8895	0.8909	0.8941	0.8895
No log	6.0	234	0.6742	0.9053	0.9074	0.9157	0.9053
No log	7.0	273	0.8472	0.8719	0.8762	0.8971	0.8719
No log	8.0	312	0.7390	0.8947	0.8975	0.9086	0.8947
No log	9.0	351	0.7700	0.8930	0.8958	0.9074	0.8930
No log	10.0	390	0.7635	0.8930	0.8958	0.9074	0.8930

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2