7k-PhoContent-10304

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: 0.2320
• Accuracy: 0.9419
• F1: 0.9150
• Precision: 0.9233
• Recall: 0.9074

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.7443	2.6144	100	0.2005	0.9360	0.9056	0.9183	0.8945
0.348	5.2288	200	0.2175	0.9360	0.9024	0.9329	0.8792
0.348	7.8431	300	0.1926	0.9419	0.9128	0.9342	0.8952
0.1555	10.4575	400	0.2010	0.9457	0.9197	0.9344	0.9069
0.0984	13.0719	500	0.2211	0.9302	0.8967	0.9106	0.8846
0.0984	15.6863	600	0.2338	0.9322	0.8999	0.9124	0.8889
0.065	18.3007	700	0.2320	0.9419	0.9150	0.9233	0.9074

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0