Narkantak/Intent-classification-12k

working

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

• Loss: 0.0013
• Accuracy: 0.9997
• F1: 0.9997
• Precision: 0.9997
• Recall: 0.9997

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: 5e-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
• lr_scheduler_warmup_steps: 10
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.7386	0.05	10	1.4921	0.5744	0.5473	0.6739	0.5638
1.2954	0.11	20	0.9534	0.9091	0.9066	0.9148	0.9082
0.7734	0.16	30	0.4544	0.9570	0.9567	0.9585	0.9578
0.3456	0.21	40	0.1662	0.9907	0.9908	0.9909	0.9907
0.1226	0.26	50	0.0743	0.9914	0.9914	0.9916	0.9914
0.0709	0.32	60	0.0446	0.9917	0.9917	0.9921	0.9914
0.0565	0.37	70	0.0408	0.9897	0.9898	0.9897	0.9900
0.0172	0.42	80	0.0214	0.9967	0.9967	0.9966	0.9968
0.0234	0.48	90	0.0217	0.9954	0.9954	0.9954	0.9954
0.027	0.53	100	0.0158	0.9977	0.9977	0.9976	0.9977
0.0346	0.58	110	0.0119	0.9980	0.9980	0.9980	0.9981
0.0621	0.63	120	0.0093	0.9990	0.9990	0.9990	0.9990
0.0065	0.69	130	0.0156	0.9960	0.9960	0.9960	0.9960
0.006	0.74	140	0.0081	0.9980	0.9980	0.9979	0.9980
0.0045	0.79	150	0.0091	0.9970	0.9970	0.9969	0.9971
0.0108	0.85	160	0.0045	0.9997	0.9997	0.9997	0.9996
0.0128	0.9	170	0.0033	0.9997	0.9997	0.9997	0.9996
0.0166	0.95	180	0.0112	0.9974	0.9974	0.9973	0.9974
0.0031	1.01	190	0.0117	0.9974	0.9974	0.9973	0.9974
0.0028	1.06	200	0.0143	0.9967	0.9967	0.9967	0.9967
0.0031	1.11	210	0.0076	0.9987	0.9987	0.9987	0.9987
0.0126	1.16	220	0.0051	0.9990	0.9990	0.9990	0.9990
0.0194	1.22	230	0.0048	0.9993	0.9993	0.9993	0.9993
0.0021	1.27	240	0.0093	0.9980	0.9980	0.9980	0.9980
0.002	1.32	250	0.0082	0.9983	0.9983	0.9983	0.9983
0.0187	1.38	260	0.0041	0.9993	0.9993	0.9993	0.9993
0.0018	1.43	270	0.0049	0.9990	0.9990	0.9990	0.9990
0.0016	1.48	280	0.0050	0.9987	0.9987	0.9987	0.9986
0.0016	1.53	290	0.0047	0.9993	0.9993	0.9993	0.9993
0.0014	1.59	300	0.0049	0.9993	0.9993	0.9993	0.9993
0.0014	1.64	310	0.0050	0.9990	0.9990	0.9990	0.9990
0.0013	1.69	320	0.0051	0.9990	0.9990	0.9990	0.9990
0.0089	1.75	330	0.0360	0.9911	0.9911	0.9913	0.9911
0.0211	1.8	340	0.0042	0.9987	0.9987	0.9987	0.9987
0.0014	1.85	350	0.0223	0.9957	0.9957	0.9957	0.9957
0.003	1.9	360	0.0027	0.9993	0.9993	0.9993	0.9993
0.0086	1.96	370	0.0026	0.9993	0.9994	0.9994	0.9993
0.0013	2.01	380	0.0023	0.9990	0.9990	0.9990	0.9990
0.0011	2.06	390	0.0037	0.9987	0.9987	0.9987	0.9986
0.0047	2.12	400	0.0066	0.9980	0.9980	0.9980	0.9980
0.0013	2.17	410	0.0037	0.9990	0.9990	0.9990	0.9990
0.001	2.22	420	0.0020	0.9997	0.9997	0.9997	0.9996
0.0009	2.28	430	0.0014	0.9997	0.9997	0.9997	0.9996
0.0009	2.33	440	0.0012	0.9997	0.9997	0.9997	0.9996
0.0008	2.38	450	0.0011	0.9997	0.9997	0.9997	0.9996
0.0008	2.43	460	0.0011	0.9997	0.9997	0.9997	0.9996
0.0009	2.49	470	0.0010	1.0	1.0	1.0	1.0
0.0008	2.54	480	0.0012	0.9997	0.9997	0.9997	0.9997
0.0007	2.59	490	0.0012	0.9997	0.9997	0.9997	0.9997
0.0007	2.65	500	0.0012	0.9997	0.9997	0.9997	0.9997
0.0007	2.7	510	0.0012	0.9997	0.9997	0.9997	0.9997
0.014	2.75	520	0.0019	0.9997	0.9997	0.9997	0.9997
0.0009	2.8	530	0.0036	0.9993	0.9993	0.9994	0.9993
0.0007	2.86	540	0.0036	0.9993	0.9993	0.9994	0.9993
0.0007	2.91	550	0.0032	0.9993	0.9993	0.9994	0.9993
0.0006	2.96	560	0.0028	0.9993	0.9993	0.9994	0.9993
0.0006	3.02	570	0.0026	0.9993	0.9993	0.9994	0.9993
0.0006	3.07	580	0.0024	0.9993	0.9993	0.9994	0.9993
0.0007	3.12	590	0.0023	0.9993	0.9993	0.9994	0.9993
0.0005	3.17	600	0.0021	0.9993	0.9993	0.9994	0.9993
0.0006	3.23	610	0.0021	0.9993	0.9993	0.9994	0.9993
0.0006	3.28	620	0.0018	0.9993	0.9993	0.9994	0.9993
0.0005	3.33	630	0.0017	0.9993	0.9993	0.9994	0.9993
0.0005	3.39	640	0.0016	0.9993	0.9993	0.9994	0.9993
0.0005	3.44	650	0.0014	0.9993	0.9993	0.9994	0.9993
0.0005	3.49	660	0.0013	0.9997	0.9997	0.9997	0.9997
0.0005	3.54	670	0.0012	0.9997	0.9997	0.9997	0.9997
0.0005	3.6	680	0.0011	0.9997	0.9997	0.9997	0.9997
0.0004	3.65	690	0.0011	0.9997	0.9997	0.9997	0.9997
0.0004	3.7	700	0.0011	0.9997	0.9997	0.9997	0.9997
0.0004	3.76	710	0.0010	0.9997	0.9997	0.9997	0.9997
0.0004	3.81	720	0.0010	0.9997	0.9997	0.9997	0.9997
0.0004	3.86	730	0.0010	0.9997	0.9997	0.9997	0.9997
0.0004	3.92	740	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	3.97	750	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	4.02	760	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	4.07	770	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	4.13	780	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	4.18	790	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	4.23	800	0.0009	0.9997	0.9997	0.9997	0.9997
0.0004	4.29	810	0.0008	0.9997	0.9997	0.9997	0.9997
0.0004	4.34	820	0.0008	0.9997	0.9997	0.9997	0.9997
0.0004	4.39	830	0.0008	0.9997	0.9997	0.9997	0.9997
0.0004	4.44	840	0.0008	0.9997	0.9997	0.9997	0.9997
0.0004	4.5	850	0.0008	0.9997	0.9997	0.9997	0.9997
0.0003	4.55	860	0.0008	0.9997	0.9997	0.9997	0.9997
0.0004	4.6	870	0.0008	0.9997	0.9997	0.9997	0.9997
0.0003	4.66	880	0.0008	0.9997	0.9997	0.9997	0.9997
0.0003	4.71	890	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	4.76	900	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	4.81	910	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	4.87	920	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	4.92	930	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	4.97	940	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	5.03	950	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	5.08	960	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	5.13	970	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	5.19	980	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	5.24	990	0.0007	0.9997	0.9997	0.9997	0.9997
0.0003	5.29	1000	0.0006	0.9997	0.9997	0.9997	0.9997
0.0003	5.34	1010	0.0006	0.9997	0.9997	0.9997	0.9997
0.0003	5.4	1020	0.0006	1.0	1.0	1.0	1.0
0.0003	5.45	1030	0.0006	1.0	1.0	1.0	1.0
0.0003	5.5	1040	0.0006	1.0	1.0	1.0	1.0
0.0003	5.56	1050	0.0006	1.0	1.0	1.0	1.0
0.0003	5.61	1060	0.0006	1.0	1.0	1.0	1.0
0.0003	5.66	1070	0.0006	1.0	1.0	1.0	1.0
0.0003	5.71	1080	0.0006	1.0	1.0	1.0	1.0
0.0003	5.77	1090	0.0006	1.0	1.0	1.0	1.0
0.0003	5.82	1100	0.0006	1.0	1.0	1.0	1.0
0.0003	5.87	1110	0.0006	1.0	1.0	1.0	1.0
0.0003	5.93	1120	0.0006	1.0	1.0	1.0	1.0
0.0003	5.98	1130	0.0006	1.0	1.0	1.0	1.0
0.0003	6.03	1140	0.0006	1.0	1.0	1.0	1.0
0.0003	6.08	1150	0.0006	1.0	1.0	1.0	1.0
0.0003	6.14	1160	0.0006	1.0	1.0	1.0	1.0
0.0003	6.19	1170	0.0006	1.0	1.0	1.0	1.0
0.0003	6.24	1180	0.0006	1.0	1.0	1.0	1.0
0.0003	6.3	1190	0.0006	1.0	1.0	1.0	1.0
0.0002	6.35	1200	0.0006	1.0	1.0	1.0	1.0
0.0003	6.4	1210	0.0006	1.0	1.0	1.0	1.0
0.0002	6.46	1220	0.0006	1.0	1.0	1.0	1.0
0.0002	6.51	1230	0.0006	1.0	1.0	1.0	1.0
0.0002	6.56	1240	0.0006	1.0	1.0	1.0	1.0
0.0002	6.61	1250	0.0006	1.0	1.0	1.0	1.0
0.0002	6.67	1260	0.0005	1.0	1.0	1.0	1.0
0.0002	6.72	1270	0.0005	1.0	1.0	1.0	1.0
0.0002	6.77	1280	0.0005	1.0	1.0	1.0	1.0
0.0002	6.83	1290	0.0005	1.0	1.0	1.0	1.0
0.0002	6.88	1300	0.0005	1.0	1.0	1.0	1.0
0.0002	6.93	1310	0.0005	1.0	1.0	1.0	1.0
0.0002	6.98	1320	0.0005	1.0	1.0	1.0	1.0
0.0002	7.04	1330	0.0005	1.0	1.0	1.0	1.0
0.0002	7.09	1340	0.0005	1.0	1.0	1.0	1.0
0.0002	7.14	1350	0.0005	1.0	1.0	1.0	1.0
0.0002	7.2	1360	0.0005	1.0	1.0	1.0	1.0
0.0002	7.25	1370	0.0005	1.0	1.0	1.0	1.0
0.0002	7.3	1380	0.0005	1.0	1.0	1.0	1.0
0.0002	7.35	1390	0.0005	1.0	1.0	1.0	1.0
0.0002	7.41	1400	0.0005	1.0	1.0	1.0	1.0
0.0002	7.46	1410	0.0005	1.0	1.0	1.0	1.0
0.0002	7.51	1420	0.0005	1.0	1.0	1.0	1.0
0.0002	7.57	1430	0.0005	1.0	1.0	1.0	1.0
0.0002	7.62	1440	0.0005	1.0	1.0	1.0	1.0
0.0002	7.67	1450	0.0005	1.0	1.0	1.0	1.0
0.0002	7.72	1460	0.0005	1.0	1.0	1.0	1.0
0.0002	7.78	1470	0.0005	1.0	1.0	1.0	1.0
0.0002	7.83	1480	0.0005	1.0	1.0	1.0	1.0
0.0002	7.88	1490	0.0005	1.0	1.0	1.0	1.0
0.0002	7.94	1500	0.0005	1.0	1.0	1.0	1.0
0.0002	7.99	1510	0.0005	1.0	1.0	1.0	1.0
0.0002	8.04	1520	0.0005	1.0	1.0	1.0	1.0
0.0002	8.1	1530	0.0005	1.0	1.0	1.0	1.0
0.0002	8.15	1540	0.0005	1.0	1.0	1.0	1.0
0.0002	8.2	1550	0.0005	1.0	1.0	1.0	1.0
0.0002	8.25	1560	0.0005	1.0	1.0	1.0	1.0
0.0002	8.31	1570	0.0005	1.0	1.0	1.0	1.0
0.0002	8.36	1580	0.0005	1.0	1.0	1.0	1.0
0.0002	8.41	1590	0.0005	1.0	1.0	1.0	1.0
0.0002	8.47	1600	0.0005	1.0	1.0	1.0	1.0
0.0002	8.52	1610	0.0005	1.0	1.0	1.0	1.0
0.0002	8.57	1620	0.0005	1.0	1.0	1.0	1.0
0.0002	8.62	1630	0.0005	1.0	1.0	1.0	1.0
0.0002	8.68	1640	0.0005	1.0	1.0	1.0	1.0
0.0002	8.73	1650	0.0005	1.0	1.0	1.0	1.0
0.0002	8.78	1660	0.0005	1.0	1.0	1.0	1.0
0.0002	8.84	1670	0.0005	1.0	1.0	1.0	1.0
0.0002	8.89	1680	0.0005	1.0	1.0	1.0	1.0
0.0002	8.94	1690	0.0005	1.0	1.0	1.0	1.0
0.0002	8.99	1700	0.0005	1.0	1.0	1.0	1.0
0.0002	9.05	1710	0.0005	1.0	1.0	1.0	1.0
0.0002	9.1	1720	0.0005	1.0	1.0	1.0	1.0
0.0002	9.15	1730	0.0005	1.0	1.0	1.0	1.0
0.0002	9.21	1740	0.0005	1.0	1.0	1.0	1.0
0.0002	9.26	1750	0.0005	1.0	1.0	1.0	1.0
0.0002	9.31	1760	0.0005	1.0	1.0	1.0	1.0
0.0002	9.37	1770	0.0005	1.0	1.0	1.0	1.0
0.0002	9.42	1780	0.0005	1.0	1.0	1.0	1.0
0.0002	9.47	1790	0.0005	1.0	1.0	1.0	1.0
0.0002	9.52	1800	0.0005	1.0	1.0	1.0	1.0
0.0002	9.58	1810	0.0005	1.0	1.0	1.0	1.0
0.0002	9.63	1820	0.0005	1.0	1.0	1.0	1.0
0.0002	9.68	1830	0.0005	1.0	1.0	1.0	1.0
0.0002	9.74	1840	0.0005	1.0	1.0	1.0	1.0
0.0002	9.79	1850	0.0005	1.0	1.0	1.0	1.0
0.0002	9.84	1860	0.0005	1.0	1.0	1.0	1.0
0.0002	9.89	1870	0.0005	1.0	1.0	1.0	1.0
0.0002	9.95	1880	0.0005	1.0	1.0	1.0	1.0
0.0002	10.0	1890	0.0005	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2