results

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0750
Accuracy: 0.6202
F1: 0.6107

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.02	20	2.2641	0.2781	0.1211
No log	0.04	40	2.0495	0.2786	0.1221
No log	0.05	60	1.8930	0.4343	0.3708
No log	0.07	80	1.8073	0.4046	0.3218
No log	0.09	100	1.7021	0.4710	0.4005
No log	0.11	120	1.6779	0.4715	0.4077
No log	0.12	140	1.6050	0.4804	0.4139
No log	0.14	160	1.5298	0.5032	0.4416
No log	0.16	180	1.4980	0.5037	0.4427
No log	0.18	200	1.4566	0.5112	0.4553
No log	0.19	220	1.4303	0.5295	0.4736
No log	0.21	240	1.4033	0.5340	0.4835
No log	0.23	260	1.4549	0.5052	0.4588
No log	0.25	280	1.3637	0.5404	0.5032
No log	0.26	300	1.3285	0.5473	0.5067
No log	0.28	320	1.3536	0.5454	0.5199
No log	0.3	340	1.3069	0.5528	0.5166
No log	0.32	360	1.2906	0.5464	0.5134
No log	0.33	380	1.2867	0.5612	0.5355
No log	0.35	400	1.2854	0.5493	0.5145
No log	0.37	420	1.2707	0.5702	0.5465
No log	0.39	440	1.2698	0.5667	0.5484
No log	0.41	460	1.2531	0.5766	0.5637
No log	0.42	480	1.2348	0.5801	0.5592
No log	0.44	500	1.2392	0.5756	0.5531
No log	0.46	520	1.2110	0.5821	0.5584
No log	0.48	540	1.2050	0.5771	0.5546
No log	0.49	560	1.2078	0.5756	0.5482
No log	0.51	580	1.2088	0.5776	0.5518
No log	0.53	600	1.1987	0.5905	0.5758
No log	0.55	620	1.1893	0.5761	0.5548
No log	0.56	640	1.1991	0.5801	0.5667
No log	0.58	660	1.1939	0.5865	0.5755
No log	0.6	680	1.1701	0.5875	0.5653
No log	0.62	700	1.1852	0.5870	0.5709
No log	0.63	720	1.1699	0.5845	0.5668
No log	0.65	740	1.1778	0.5910	0.5731
No log	0.67	760	1.1546	0.5984	0.5806
No log	0.69	780	1.1720	0.5890	0.5687
No log	0.7	800	1.1554	0.5940	0.5730
No log	0.72	820	1.1454	0.5910	0.5748
No log	0.74	840	1.1457	0.6034	0.5893
No log	0.76	860	1.1631	0.5935	0.5663
No log	0.78	880	1.1277	0.6059	0.5930
No log	0.79	900	1.1291	0.5984	0.5839
No log	0.81	920	1.1345	0.5954	0.5826
No log	0.83	940	1.1253	0.6034	0.5868
No log	0.85	960	1.1397	0.5989	0.5899
No log	0.86	980	1.1223	0.6009	0.5890
No log	0.88	1000	1.1363	0.6059	0.5917
No log	0.9	1020	1.1391	0.5944	0.5787
No log	0.92	1040	1.1480	0.5860	0.5732
No log	0.93	1060	1.1065	0.6063	0.5925
No log	0.95	1080	1.1250	0.5984	0.5844
No log	0.97	1100	1.1344	0.5935	0.5835
No log	0.99	1120	1.1452	0.5880	0.5700
1.3609	1.0	1140	1.1084	0.6093	0.5960
1.3609	1.02	1160	1.1079	0.6098	0.6006
1.3609	1.04	1180	1.1178	0.6073	0.5951
1.3609	1.06	1200	1.1267	0.6004	0.5878
1.3609	1.07	1220	1.1084	0.6098	0.5977
1.3609	1.09	1240	1.1109	0.6039	0.5910
1.3609	1.11	1260	1.1142	0.6078	0.5968
1.3609	1.13	1280	1.1218	0.6024	0.5915
1.3609	1.15	1300	1.0929	0.6197	0.6057
1.3609	1.16	1320	1.1001	0.6108	0.5995
1.3609	1.18	1340	1.1049	0.6068	0.5993
1.3609	1.2	1360	1.1019	0.6098	0.5971
1.3609	1.22	1380	1.1140	0.6029	0.5942
1.3609	1.23	1400	1.0981	0.6078	0.5991
1.3609	1.25	1420	1.1129	0.6078	0.5965
1.3609	1.27	1440	1.0896	0.6173	0.6076
1.3609	1.29	1460	1.1062	0.6059	0.5935
1.3609	1.3	1480	1.1038	0.6143	0.5996
1.3609	1.32	1500	1.0906	0.6182	0.6072
1.3609	1.34	1520	1.0883	0.6182	0.6099
1.3609	1.36	1540	1.1114	0.6024	0.5955
1.3609	1.37	1560	1.0884	0.6158	0.6044
1.3609	1.39	1580	1.0994	0.6088	0.6021
1.3609	1.41	1600	1.0857	0.6187	0.6055
1.3609	1.43	1620	1.1067	0.6098	0.6027
1.3609	1.44	1640	1.0845	0.6237	0.6167
1.3609	1.46	1660	1.0899	0.6177	0.6065
1.3609	1.48	1680	1.0925	0.6177	0.6067
1.3609	1.5	1700	1.0831	0.6148	0.6042
1.3609	1.52	1720	1.0988	0.6108	0.6017
1.3609	1.53	1740	1.0810	0.6173	0.6069
1.3609	1.55	1760	1.0857	0.6163	0.6049
1.3609	1.57	1780	1.1003	0.6103	0.5985
1.3609	1.59	1800	1.0861	0.6143	0.6045
1.3609	1.6	1820	1.1024	0.6073	0.5976
1.3609	1.62	1840	1.0786	0.6222	0.6094
1.3609	1.64	1860	1.0984	0.6088	0.5968
1.3609	1.66	1880	1.0750	0.6227	0.6146
1.3609	1.67	1900	1.0849	0.6108	0.6029
1.3609	1.69	1920	1.0787	0.6192	0.6102
1.3609	1.71	1940	1.0831	0.6133	0.6036
1.3609	1.73	1960	1.0739	0.6197	0.6136
1.3609	1.74	1980	1.0766	0.6187	0.6092
1.3609	1.76	2000	1.0778	0.6207	0.6119
1.3609	1.78	2020	1.0739	0.6168	0.6053
1.3609	1.8	2040	1.0736	0.6182	0.6066
1.3609	1.81	2060	1.0723	0.6212	0.6107
1.3609	1.83	2080	1.0792	0.6222	0.6126
1.3609	1.85	2100	1.0823	0.6177	0.6091
1.3609	1.87	2120	1.0706	0.6197	0.6094
1.3609	1.89	2140	1.0729	0.6217	0.6107
1.3609	1.9	2160	1.0728	0.6202	0.6094
1.3609	1.92	2180	1.0754	0.6187	0.6083
1.3609	1.94	2200	1.0775	0.6192	0.6094
1.3609	1.96	2220	1.0773	0.6187	0.6090
1.3609	1.97	2240	1.0767	0.6177	0.6082
1.3609	1.99	2260	1.0750	0.6202	0.6107

Framework versions

Transformers 4.36.0
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.15.0

Loading…

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.02	20	2.2641	0.2781	0.1211
No log	0.04	40	2.0495	0.2786	0.1221
No log	0.05	60	1.8930	0.4343	0.3708
No log	0.07	80	1.8073	0.4046	0.3218
No log	0.09	100	1.7021	0.4710	0.4005
No log	0.11	120	1.6779	0.4715	0.4077
No log	0.12	140	1.6050	0.4804	0.4139
No log	0.14	160	1.5298	0.5032	0.4416
No log	0.16	180	1.4980	0.5037	0.4427
No log	0.18	200	1.4566	0.5112	0.4553
No log	0.19	220	1.4303	0.5295	0.4736
No log	0.21	240	1.4033	0.5340	0.4835
No log	0.23	260	1.4549	0.5052	0.4588
No log	0.25	280	1.3637	0.5404	0.5032
No log	0.26	300	1.3285	0.5473	0.5067
No log	0.28	320	1.3536	0.5454	0.5199
No log	0.3	340	1.3069	0.5528	0.5166
No log	0.32	360	1.2906	0.5464	0.5134
No log	0.33	380	1.2867	0.5612	0.5355
No log	0.35	400	1.2854	0.5493	0.5145
No log	0.37	420	1.2707	0.5702	0.5465
No log	0.39	440	1.2698	0.5667	0.5484
No log	0.41	460	1.2531	0.5766	0.5637
No log	0.42	480	1.2348	0.5801	0.5592
No log	0.44	500	1.2392	0.5756	0.5531
No log	0.46	520	1.2110	0.5821	0.5584
No log	0.48	540	1.2050	0.5771	0.5546
No log	0.49	560	1.2078	0.5756	0.5482
No log	0.51	580	1.2088	0.5776	0.5518
No log	0.53	600	1.1987	0.5905	0.5758
No log	0.55	620	1.1893	0.5761	0.5548
No log	0.56	640	1.1991	0.5801	0.5667
No log	0.58	660	1.1939	0.5865	0.5755
No log	0.6	680	1.1701	0.5875	0.5653
No log	0.62	700	1.1852	0.5870	0.5709
No log	0.63	720	1.1699	0.5845	0.5668
No log	0.65	740	1.1778	0.5910	0.5731
No log	0.67	760	1.1546	0.5984	0.5806
No log	0.69	780	1.1720	0.5890	0.5687
No log	0.7	800	1.1554	0.5940	0.5730
No log	0.72	820	1.1454	0.5910	0.5748
No log	0.74	840	1.1457	0.6034	0.5893
No log	0.76	860	1.1631	0.5935	0.5663
No log	0.78	880	1.1277	0.6059	0.5930
No log	0.79	900	1.1291	0.5984	0.5839
No log	0.81	920	1.1345	0.5954	0.5826
No log	0.83	940	1.1253	0.6034	0.5868
No log	0.85	960	1.1397	0.5989	0.5899
No log	0.86	980	1.1223	0.6009	0.5890
No log	0.88	1000	1.1363	0.6059	0.5917
No log	0.9	1020	1.1391	0.5944	0.5787
No log	0.92	1040	1.1480	0.5860	0.5732
No log	0.93	1060	1.1065	0.6063	0.5925
No log	0.95	1080	1.1250	0.5984	0.5844
No log	0.97	1100	1.1344	0.5935	0.5835
No log	0.99	1120	1.1452	0.5880	0.5700
1.3609	1.0	1140	1.1084	0.6093	0.5960
1.3609	1.02	1160	1.1079	0.6098	0.6006
1.3609	1.04	1180	1.1178	0.6073	0.5951
1.3609	1.06	1200	1.1267	0.6004	0.5878
1.3609	1.07	1220	1.1084	0.6098	0.5977
1.3609	1.09	1240	1.1109	0.6039	0.5910
1.3609	1.11	1260	1.1142	0.6078	0.5968
1.3609	1.13	1280	1.1218	0.6024	0.5915
1.3609	1.15	1300	1.0929	0.6197	0.6057
1.3609	1.16	1320	1.1001	0.6108	0.5995
1.3609	1.18	1340	1.1049	0.6068	0.5993
1.3609	1.2	1360	1.1019	0.6098	0.5971
1.3609	1.22	1380	1.1140	0.6029	0.5942
1.3609	1.23	1400	1.0981	0.6078	0.5991
1.3609	1.25	1420	1.1129	0.6078	0.5965
1.3609	1.27	1440	1.0896	0.6173	0.6076
1.3609	1.29	1460	1.1062	0.6059	0.5935
1.3609	1.3	1480	1.1038	0.6143	0.5996
1.3609	1.32	1500	1.0906	0.6182	0.6072
1.3609	1.34	1520	1.0883	0.6182	0.6099
1.3609	1.36	1540	1.1114	0.6024	0.5955
1.3609	1.37	1560	1.0884	0.6158	0.6044
1.3609	1.39	1580	1.0994	0.6088	0.6021
1.3609	1.41	1600	1.0857	0.6187	0.6055
1.3609	1.43	1620	1.1067	0.6098	0.6027
1.3609	1.44	1640	1.0845	0.6237	0.6167
1.3609	1.46	1660	1.0899	0.6177	0.6065
1.3609	1.48	1680	1.0925	0.6177	0.6067
1.3609	1.5	1700	1.0831	0.6148	0.6042
1.3609	1.52	1720	1.0988	0.6108	0.6017
1.3609	1.53	1740	1.0810	0.6173	0.6069
1.3609	1.55	1760	1.0857	0.6163	0.6049
1.3609	1.57	1780	1.1003	0.6103	0.5985
1.3609	1.59	1800	1.0861	0.6143	0.6045
1.3609	1.6	1820	1.1024	0.6073	0.5976
1.3609	1.62	1840	1.0786	0.6222	0.6094
1.3609	1.64	1860	1.0984	0.6088	0.5968
1.3609	1.66	1880	1.0750	0.6227	0.6146
1.3609	1.67	1900	1.0849	0.6108	0.6029
1.3609	1.69	1920	1.0787	0.6192	0.6102
1.3609	1.71	1940	1.0831	0.6133	0.6036
1.3609	1.73	1960	1.0739	0.6197	0.6136
1.3609	1.74	1980	1.0766	0.6187	0.6092
1.3609	1.76	2000	1.0778	0.6207	0.6119
1.3609	1.78	2020	1.0739	0.6168	0.6053
1.3609	1.8	2040	1.0736	0.6182	0.6066
1.3609	1.81	2060	1.0723	0.6212	0.6107
1.3609	1.83	2080	1.0792	0.6222	0.6126
1.3609	1.85	2100	1.0823	0.6177	0.6091
1.3609	1.87	2120	1.0706	0.6197	0.6094
1.3609	1.89	2140	1.0729	0.6217	0.6107
1.3609	1.9	2160	1.0728	0.6202	0.6094
1.3609	1.92	2180	1.0754	0.6187	0.6083
1.3609	1.94	2200	1.0775	0.6192	0.6094
1.3609	1.96	2220	1.0773	0.6187	0.6090
1.3609	1.97	2240	1.0767	0.6177	0.6082
1.3609	1.99	2260	1.0750	0.6202	0.6107

Framework versions

Transformers 4.36.0

Pytorch 2.0.0

Datasets 2.1.0

Tokenizers 0.15.0

tuanHenry/distilbert_base_uncased_Movies_genre_predict

results

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

results

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions