fabriceyhc/bert-base-uncased-yahoo_answers_topics

来源：🤗🏴‍☠️ 救援者：isilicontext-classificationapache-2.0439 MBother✓ 2 个校验和1,882 天前更新

bert-base-uncased-yahoo_answers_topics

This model is a fine-tuned version of bert-base-uncased on the yahoo_answers_topics dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.162	0.01	2000	1.7444	0.5681
1.3126	0.02	4000	1.0081	0.7054
0.9592	0.03	6000	0.9021	0.7234
0.8903	0.05	8000	0.8827	0.7276
0.8685	0.06	10000	0.8540	0.7341
0.8422	0.07	12000	0.8547	0.7365
0.8535	0.08	14000	0.8264	0.7372
0.8178	0.09	16000	0.8331	0.7389
0.8325	0.1	18000	0.8242	0.7411
0.8181	0.12	20000	0.8356	0.7437
0.8171	0.13	22000	0.8090	0.7451
0.8092	0.14	24000	0.8469	0.7392
0.8057	0.15	26000	0.8185	0.7478
0.8085	0.16	28000	0.8090	0.7467
0.8229	0.17	30000	0.8225	0.7417
0.8151	0.18	32000	0.8262	0.7419
0.81	0.2	34000	0.8149	0.7383
0.8073	0.21	36000	0.8225	0.7441
0.816	0.22	38000	0.8037	0.744
0.8217	0.23	40000	0.8409	0.743
0.82	0.24	42000	0.8286	0.7385
0.8101	0.25	44000	0.8282	0.7413
0.8254	0.27	46000	0.8170	0.7414