phobert-base-v2-DACN1

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: 0.5520
• Accuracy: 0.8784
• F1: 0.8781

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: 32
• eval_batch_size: 32
• 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
No log	0.2782	200	0.4102	0.8061	0.8037
No log	0.5563	400	0.3549	0.8456	0.8461
No log	0.8345	600	0.3583	0.8466	0.8454
0.4175	1.1127	800	0.3401	0.8537	0.8523
0.4175	1.3908	1000	0.3179	0.8639	0.8646
0.4175	1.6690	1200	0.3148	0.8687	0.8691
0.4175	1.9471	1400	0.3240	0.8574	0.8582
0.3061	2.2253	1600	0.3148	0.8734	0.8740
0.3061	2.5035	1800	0.3224	0.8742	0.8743
0.3061	2.7816	2000	0.3288	0.8678	0.8671
0.2524	3.0598	2200	0.3512	0.8767	0.8769
0.2524	3.3380	2400	0.3421	0.8798	0.8796
0.2524	3.6161	2600	0.3089	0.8795	0.8799
0.2524	3.8943	2800	0.3569	0.8718	0.8725
0.2123	4.1725	3000	0.3840	0.8747	0.8744
0.2123	4.4506	3200	0.3681	0.8729	0.8736
0.2123	4.7288	3400	0.3575	0.8725	0.8732
0.1771	5.0070	3600	0.3575	0.8793	0.8794
0.1771	5.2851	3800	0.4285	0.8758	0.8752
0.1771	5.5633	4000	0.3843	0.8778	0.8782
0.1771	5.8414	4200	0.3951	0.8780	0.8779
0.1479	6.1196	4400	0.4364	0.8734	0.8726
0.1479	6.3978	4600	0.4273	0.8753	0.8752
0.1479	6.6759	4800	0.4596	0.8786	0.8783
0.1479	6.9541	5000	0.4498	0.8784	0.8785
0.1284	7.2323	5200	0.4592	0.8793	0.8795
0.1284	7.5104	5400	0.4796	0.8755	0.8747
0.1284	7.7886	5600	0.4830	0.8729	0.8722
0.1068	8.0668	5800	0.4879	0.8789	0.8787
0.1068	8.3449	6000	0.5213	0.8767	0.8761
0.1068	8.6231	6200	0.5114	0.8769	0.8764
0.1068	8.9013	6400	0.5090	0.8778	0.8777
0.0946	9.1794	6600	0.5192	0.8800	0.8800
0.0946	9.4576	6800	0.5517	0.8753	0.8748
0.0946	9.7357	7000	0.5520	0.8784	0.8781

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1