PhoLexiContent-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: 0.2676
• Accuracy: 0.9379
• F1: 0.9072
• Precision: 0.9100
• Recall: 0.9046

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: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.7189	2.7586	100	0.1735	0.9437	0.9157	0.9199	0.9116
0.178	5.5172	200	0.1864	0.9408	0.9099	0.9211	0.8998
0.0931	8.2759	300	0.2137	0.9418	0.9124	0.9182	0.9070
0.0931	11.0345	400	0.2234	0.9408	0.9129	0.9096	0.9163
0.0564	13.7931	500	0.2346	0.9370	0.9075	0.9030	0.9122
0.0334	16.5517	600	0.2652	0.9350	0.9037	0.9030	0.9044
0.0334	19.3103	700	0.2676	0.9379	0.9072	0.9100	0.9046

Framework versions

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