amazon_kindle_sentiment_analysis_definitivo

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

• Loss: 0.9897
• Accuracy: 0.585

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: 8
• eval_batch_size: 8
• 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
1.6088	0.01	10	1.5857	0.265
1.6469	0.02	20	1.5750	0.2617
1.5407	0.03	30	1.5206	0.295
1.5096	0.03	40	1.5134	0.3792
1.5668	0.04	50	1.4435	0.33
1.386	0.05	60	1.3578	0.32
1.3041	0.06	70	1.2950	0.4167
1.2491	0.07	80	1.2376	0.4242
1.4186	0.07	90	1.3518	0.4175
1.3238	0.08	100	1.1709	0.4675
1.1596	0.09	110	1.1853	0.4417
1.1351	0.1	120	1.3158	0.4083
1.1573	0.11	130	1.1438	0.475
1.1858	0.12	140	1.2280	0.45
1.268	0.12	150	1.3686	0.3767
1.3871	0.13	160	1.2159	0.4525
1.1129	0.14	170	1.1402	0.4783
1.1144	0.15	180	1.2366	0.4558
1.1953	0.16	190	1.1209	0.4717
1.2515	0.17	200	1.1857	0.4408
1.0826	0.17	210	1.1044	0.48
1.0192	0.18	220	1.0932	0.4925
1.2467	0.19	230	1.0608	0.5058
0.9914	0.2	240	1.1134	0.4942
1.1065	0.21	250	1.1115	0.4833
1.1161	0.22	260	1.2943	0.485
1.4564	0.23	270	1.3899	0.3892
1.4043	0.23	280	1.1529	0.4742
1.0993	0.24	290	1.3811	0.4167
1.1307	0.25	300	1.0985	0.4892
1.1536	0.26	310	1.0903	0.5133
1.0491	0.27	320	1.1709	0.4875
1.1946	0.28	330	1.1875	0.4725
1.1956	0.28	340	1.0579	0.5292
0.8626	0.29	350	1.2314	0.48
1.2908	0.3	360	1.0875	0.5225
1.1227	0.31	370	1.1000	0.4975
1.0407	0.32	380	1.1035	0.5267
1.2242	0.33	390	1.1243	0.4833
1.2052	0.33	400	1.0719	0.5067
1.1526	0.34	410	1.0351	0.5442
0.9881	0.35	420	1.0394	0.5333
1.0651	0.36	430	1.0422	0.5317
1.0571	0.37	440	1.0310	0.5408
1.22	0.38	450	1.0176	0.5358
0.9914	0.38	460	1.2306	0.4733
1.0956	0.39	470	1.0239	0.5358
0.9464	0.4	480	1.0895	0.51
1.0855	0.41	490	1.0398	0.5292
1.2345	0.42	500	1.1024	0.5133
1.1624	0.42	510	1.1720	0.4733
1.1251	0.43	520	1.1044	0.4858
1.0896	0.44	530	1.0415	0.5225
0.9643	0.45	540	1.0211	0.5383
1.1421	0.46	550	1.1593	0.5017
1.0463	0.47	560	1.0246	0.52
1.0508	0.47	570	1.0377	0.515
1.0507	0.48	580	1.0565	0.5408
0.8932	0.49	590	1.0147	0.5483
0.8834	0.5	600	1.0191	0.5458
1.0548	0.51	610	1.0668	0.5392
1.1106	0.52	620	1.0086	0.53
1.0587	0.53	630	1.0144	0.5483
0.9468	0.53	640	1.1663	0.5042
1.0948	0.54	650	1.0263	0.5458
1.2202	0.55	660	0.9932	0.5358
0.898	0.56	670	1.0217	0.52
1.2074	0.57	680	1.0416	0.5333
1.1777	0.57	690	0.9986	0.5483
1.0448	0.58	700	0.9836	0.5558
0.9387	0.59	710	1.0127	0.5392
1.0905	0.6	720	1.0633	0.5183
0.9262	0.61	730	1.0046	0.5375
1.0691	0.62	740	1.0005	0.5458
0.8828	0.62	750	1.0031	0.55
1.1497	0.63	760	1.0785	0.4925
0.9907	0.64	770	1.0094	0.54
0.9741	0.65	780	0.9794	0.555
0.8731	0.66	790	1.0327	0.5217
1.1001	0.67	800	1.0335	0.5325
1.0796	0.68	810	1.0004	0.5492
1.1743	0.68	820	1.0022	0.5425
1.0616	0.69	830	1.0307	0.5375
0.9953	0.7	840	0.9799	0.555
1.0607	0.71	850	1.1107	0.5108
1.2028	0.72	860	0.9770	0.55
0.9749	0.72	870	0.9927	0.5483
0.9752	0.73	880	1.0249	0.5342
0.9905	0.74	890	0.9946	0.5408
0.9116	0.75	900	1.0538	0.5433
1.1579	0.76	910	0.9914	0.555
1.0955	0.77	920	1.0265	0.5383
1.1222	0.78	930	1.0443	0.5175
0.9873	0.78	940	0.9877	0.5408
0.8737	0.79	950	1.0376	0.5442
1.0869	0.8	960	0.9777	0.555
1.0751	0.81	970	0.9655	0.5675
1.092	0.82	980	0.9720	0.5533
1.0741	0.82	990	0.9939	0.5325
1.0502	0.83	1000	0.9864	0.5517
1.0623	0.84	1010	0.9637	0.5567
1.0641	0.85	1020	0.9590	0.565
0.9818	0.86	1030	1.0268	0.5317
1.01	0.87	1040	0.9562	0.5517
0.9202	0.88	1050	0.9766	0.5458
0.9179	0.88	1060	0.9771	0.55
1.0009	0.89	1070	1.0164	0.535
0.9891	0.9	1080	0.9699	0.5542
0.9137	0.91	1090	1.0187	0.5325
0.9941	0.92	1100	0.9797	0.5592
0.9203	0.93	1110	1.0172	0.5292
0.8416	0.93	1120	1.0945	0.505
1.0899	0.94	1130	0.9963	0.55
1.0149	0.95	1140	0.9716	0.5592
0.9339	0.96	1150	0.9762	0.5492
1.0562	0.97	1160	1.0362	0.5258
1.0929	0.97	1170	0.9954	0.5433
1.0686	0.98	1180	1.0128	0.5342
1.1207	0.99	1190	0.9771	0.5525
0.9934	1.0	1200	0.9731	0.5575
0.8436	1.01	1210	0.9501	0.5558
0.7829	1.02	1220	0.9517	0.5708
0.7667	1.02	1230	0.9789	0.565
0.8093	1.03	1240	1.0047	0.5683
0.9297	1.04	1250	0.9831	0.5642
0.7154	1.05	1260	1.0401	0.5425
0.78	1.06	1270	0.9859	0.5683
0.8144	1.07	1280	0.9833	0.565
0.9511	1.07	1290	0.9870	0.5675
0.781	1.08	1300	0.9851	0.5633
0.8336	1.09	1310	0.9990	0.5625
0.9651	1.1	1320	1.0068	0.5542
0.7268	1.11	1330	0.9673	0.5742
0.7733	1.12	1340	0.9806	0.5692
0.7022	1.12	1350	1.0552	0.5508
0.8362	1.13	1360	0.9981	0.5683
0.9729	1.14	1370	1.0001	0.5683
0.7756	1.15	1380	0.9706	0.5625
0.7695	1.16	1390	1.0897	0.5392
0.7771	1.17	1400	1.0611	0.5483
0.6836	1.18	1410	1.0292	0.5575
0.8588	1.18	1420	0.9883	0.5767
0.7796	1.19	1430	1.0347	0.5658
0.8175	1.2	1440	1.0069	0.5717
0.6805	1.21	1450	1.0415	0.5525
0.7783	1.22	1460	1.0041	0.5708
1.046	1.23	1470	1.0039	0.5592
0.8762	1.23	1480	0.9609	0.5667
0.8282	1.24	1490	0.9625	0.5567
0.7038	1.25	1500	0.9559	0.5675
0.6776	1.26	1510	0.9826	0.5625
0.6715	1.27	1520	1.0019	0.5625
0.6957	1.27	1530	1.0005	0.5667
0.8419	1.28	1540	0.9876	0.575
0.7598	1.29	1550	1.0067	0.57
0.8714	1.3	1560	1.0743	0.55
0.864	1.31	1570	1.0003	0.5767
0.7178	1.32	1580	1.0116	0.5642
0.7912	1.32	1590	1.0323	0.5642
0.7834	1.33	1600	1.0123	0.5675
0.6978	1.34	1610	1.0530	0.55
0.7452	1.35	1620	1.0123	0.5658
0.8377	1.36	1630	1.0238	0.5608
0.7119	1.37	1640	1.0407	0.5642
0.7891	1.38	1650	1.0125	0.5692
0.7185	1.38	1660	1.0460	0.5483
0.7011	1.39	1670	1.0203	0.5658
0.8356	1.4	1680	1.0003	0.5667
0.6473	1.41	1690	0.9958	0.5742
0.6722	1.42	1700	0.9979	0.5817
0.7462	1.43	1710	0.9990	0.5817
0.6933	1.43	1720	1.0167	0.5758
0.6566	1.44	1730	1.0205	0.5825
0.7495	1.45	1740	1.0854	0.5483
0.9585	1.46	1750	1.0658	0.5567
0.8849	1.47	1760	1.0129	0.5708
0.9289	1.48	1770	0.9918	0.5942
0.751	1.48	1780	0.9849	0.5875
0.9082	1.49	1790	0.9887	0.5692
0.8307	1.5	1800	0.9978	0.5758
0.7014	1.51	1810	1.0261	0.5567
0.6632	1.52	1820	1.0294	0.5567
0.6885	1.52	1830	1.0054	0.5683
0.8374	1.53	1840	0.9983	0.5717
0.73	1.54	1850	0.9974	0.5792
0.7691	1.55	1860	0.9933	0.5775
0.795	1.56	1870	0.9918	0.5742
0.8298	1.57	1880	0.9970	0.5733
0.7621	1.57	1890	0.9981	0.5708
0.6753	1.58	1900	1.0033	0.5733
0.5386	1.59	1910	1.0098	0.5758
1.1066	1.6	1920	0.9923	0.5842
0.9523	1.61	1930	0.9987	0.5692
0.7225	1.62	1940	0.9958	0.5675
0.7592	1.62	1950	0.9800	0.58
0.7368	1.63	1960	1.0065	0.5658
0.7683	1.64	1970	0.9865	0.5708
0.5852	1.65	1980	0.9991	0.5675
0.7919	1.66	1990	1.0034	0.5708
0.7784	1.67	2000	0.9961	0.5717
0.8155	1.68	2010	0.9812	0.575
0.6281	1.68	2020	0.9803	0.5825
0.6084	1.69	2030	0.9802	0.5733
0.6207	1.7	2040	0.9843	0.5767
0.8847	1.71	2050	0.9871	0.5817
0.7049	1.72	2060	0.9897	0.5783
0.7144	1.73	2070	0.9914	0.5808
0.5971	1.73	2080	0.9915	0.5883
0.7566	1.74	2090	0.9888	0.5833
0.8263	1.75	2100	1.0017	0.5775
0.6402	1.76	2110	0.9872	0.5833
0.9838	1.77	2120	0.9852	0.5833
0.5518	1.77	2130	0.9803	0.585
0.737	1.78	2140	0.9892	0.5883
0.8021	1.79	2150	0.9917	0.585
0.6804	1.8	2160	0.9928	0.5775
0.6661	1.81	2170	0.9921	0.5808
0.6192	1.82	2180	0.9941	0.5833
0.7101	1.82	2190	0.9980	0.5858
0.7373	1.83	2200	1.0018	0.5825
0.845	1.84	2210	1.0030	0.5808
0.6556	1.85	2220	1.0077	0.5758
0.7979	1.86	2230	1.0115	0.5708
0.5802	1.87	2240	1.0065	0.5767
0.6794	1.88	2250	0.9945	0.5842
0.8538	1.88	2260	0.9901	0.5817
0.884	1.89	2270	0.9877	0.58
0.8306	1.9	2280	0.9850	0.5825
0.7196	1.91	2290	0.9846	0.5775
0.6548	1.92	2300	0.9850	0.5825
0.7692	1.93	2310	0.9863	0.5833
0.6386	1.93	2320	0.9880	0.5842
0.9404	1.94	2330	0.9919	0.5842
0.6133	1.95	2340	0.9920	0.5825
0.7229	1.96	2350	0.9898	0.5825
0.6681	1.97	2360	0.9887	0.585
0.7672	1.98	2370	0.9884	0.585
0.6217	1.98	2380	0.9893	0.5858
0.7101	1.99	2390	0.9897	0.585
0.6067	2.0	2400	0.9897	0.585

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2