test

This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6816
• Accuracy: 0.8543
• F1: 0.8351

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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.4545	150	0.6440	0.8190	0.6792
No log	0.9091	300	0.5366	0.8283	0.7146
0.8169	1.3636	450	0.4794	0.8418	0.7297
0.8169	1.8182	600	0.4390	0.8608	0.8331
0.4454	2.2727	750	0.4754	0.8471	0.8247
0.4454	2.7273	900	0.4398	0.8564	0.8243
0.3148	3.1818	1050	0.4512	0.8553	0.8265
0.3148	3.6364	1200	0.4722	0.8519	0.8332
0.2367	4.0909	1350	0.4722	0.8596	0.8287
0.2367	4.5455	1500	0.4794	0.8623	0.8415
0.1722	5.0	1650	0.4721	0.8568	0.8257
0.1722	5.4545	1800	0.5492	0.8581	0.8293
0.1722	5.9091	1950	0.5362	0.8598	0.8285
0.1339	6.3636	2100	0.5936	0.8530	0.8311
0.1339	6.8182	2250	0.5909	0.8598	0.8284
0.1051	7.2727	2400	0.5739	0.8583	0.8358
0.1051	7.7273	2550	0.6112	0.8589	0.8348
0.0882	8.1818	2700	0.6568	0.8541	0.8304
0.0882	8.6364	2850	0.6647	0.8564	0.8373
0.0715	9.0909	3000	0.6697	0.8560	0.8363
0.0715	9.5455	3150	0.6750	0.8549	0.8386
0.0586	10.0	3300	0.6816	0.8543	0.8351

Framework versions

• Transformers 4.57.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.1