Revision_11_03_PhoBert_Lexical_Meta_Q1

This model is a fine-tuned version of phunganhsang/PhoBert_Lexical_Dataset45K on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2511
• Accuracy: 0.9401
• F1: 0.7425

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.4065	100	0.1935	0.9304	0.7305
No log	0.8130	200	0.1800	0.9417	0.7484
0.2067	1.2195	300	0.1854	0.9438	0.7418
0.2067	1.6260	400	0.1959	0.9407	0.7444
0.1358	2.0325	500	0.2029	0.9432	0.7439
0.1358	2.4390	600	0.2148	0.9429	0.7471
0.1358	2.8455	700	0.2343	0.9324	0.7347
0.0997	3.2520	800	0.2295	0.9426	0.7442
0.0997	3.6585	900	0.2468	0.9352	0.7356
0.0725	4.0650	1000	0.2442	0.9432	0.7495
0.0725	4.4715	1100	0.2491	0.9403	0.7423
0.0725	4.8780	1200	0.2511	0.9401	0.7425

Framework versions

• Transformers 5.3.0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2