model_content_V2_test

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: 0.2218
• Accuracy: 0.9696
• F1: 0.9647

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	0.1419	150	0.1158	0.9649	0.9590
No log	0.2838	300	0.1143	0.9619	0.9551
No log	0.4257	450	0.1021	0.9589	0.9532
No log	0.5676	600	0.1081	0.9674	0.9621
No log	0.7096	750	0.0905	0.9659	0.9608
No log	0.8515	900	0.0891	0.9685	0.9635
No log	0.9934	1050	0.1108	0.9676	0.9623
0.111	1.1353	1200	0.0890	0.9690	0.9643
0.111	1.2772	1350	0.0882	0.9700	0.9654
0.111	1.4191	1500	0.0890	0.9708	0.9661
0.111	1.5610	1650	0.0946	0.9688	0.9639
0.111	1.7029	1800	0.0936	0.9703	0.9656
0.111	1.8448	1950	0.0982	0.9712	0.9667
0.111	1.9868	2100	0.1060	0.9614	0.9560
0.0717	2.1287	2250	0.1264	0.9658	0.9609
0.0717	2.2706	2400	0.0902	0.9691	0.9643
0.0717	2.4125	2550	0.0869	0.9699	0.9653
0.0717	2.5544	2700	0.1086	0.9689	0.9638
0.0717	2.6963	2850	0.1122	0.9683	0.9638
0.0717	2.8382	3000	0.0945	0.9698	0.9651
0.0717	2.9801	3150	0.1068	0.9692	0.9647
0.0555	3.1220	3300	0.1041	0.9713	0.9668
0.0555	3.2640	3450	0.1022	0.9710	0.9664
0.0555	3.4059	3600	0.1292	0.9684	0.9637
0.0555	3.5478	3750	0.1135	0.9718	0.9673
0.0555	3.6897	3900	0.1114	0.9711	0.9664
0.0555	3.8316	4050	0.1205	0.9704	0.9656
0.0555	3.9735	4200	0.1136	0.9692	0.9646
0.0429	4.1154	4350	0.1356	0.9688	0.9641
0.0429	4.2573	4500	0.1547	0.9668	0.9619
0.0429	4.3992	4650	0.1360	0.9687	0.9640
0.0429	4.5412	4800	0.1505	0.9686	0.9633
0.0429	4.6831	4950	0.1401	0.9677	0.9629
0.0429	4.8250	5100	0.1359	0.9710	0.9664
0.0429	4.9669	5250	0.1400	0.9711	0.9664
0.0311	5.1088	5400	0.1545	0.9690	0.9643
0.0311	5.2507	5550	0.1638	0.9689	0.9641
0.0311	5.3926	5700	0.1801	0.9692	0.9645
0.0311	5.5345	5850	0.1618	0.9698	0.9649
0.0311	5.6764	6000	0.1612	0.9640	0.9575
0.0311	5.8184	6150	0.1831	0.9681	0.9628
0.0311	5.9603	6300	0.1496	0.9700	0.9651
0.0229	6.1022	6450	0.1788	0.9697	0.9648
0.0229	6.2441	6600	0.1743	0.9700	0.9650
0.0229	6.3860	6750	0.1856	0.9701	0.9652
0.0229	6.5279	6900	0.1718	0.9702	0.9654
0.0229	6.6698	7050	0.1668	0.9695	0.9645
0.0229	6.8117	7200	0.1705	0.9697	0.9647
0.0229	6.9536	7350	0.1758	0.9701	0.9652
0.0178	7.0956	7500	0.1803	0.9679	0.9631
0.0178	7.2375	7650	0.1744	0.9701	0.9651
0.0178	7.3794	7800	0.1708	0.9693	0.9644
0.0178	7.5213	7950	0.1663	0.9692	0.9643
0.0178	7.6632	8100	0.1895	0.9692	0.9644
0.0178	7.8051	8250	0.1877	0.9701	0.9653
0.0178	7.9470	8400	0.1864	0.9692	0.9644
0.0125	8.0889	8550	0.1953	0.9702	0.9655
0.0125	8.2308	8700	0.2072	0.9692	0.9642
0.0125	8.3728	8850	0.1991	0.9686	0.9636
0.0125	8.5147	9000	0.2083	0.9697	0.9647
0.0125	8.6566	9150	0.2085	0.9697	0.9648
0.0125	8.7985	9300	0.2087	0.9699	0.9651
0.0125	8.9404	9450	0.2128	0.9688	0.9639
0.0076	9.0823	9600	0.2150	0.9692	0.9642
0.0076	9.2242	9750	0.2133	0.9692	0.9643
0.0076	9.3661	9900	0.2121	0.9692	0.9642
0.0076	9.5080	10050	0.2220	0.9694	0.9645
0.0076	9.6500	10200	0.2218	0.9692	0.9643
0.0076	9.7919	10350	0.2201	0.9696	0.9647
0.0076	9.9338	10500	0.2218	0.9696	0.9647

Framework versions

• Transformers 4.56.1
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.0