amazon_kindle_sentiment_analysis

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: 0.9971
• Accuracy: 0.5767

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
1.7685	0.01	10	1.6673	0.1667
1.6796	0.02	20	1.6135	0.2483
1.6381	0.03	30	1.5789	0.2783
1.6055	0.03	40	1.5616	0.2933
1.5592	0.04	50	1.4920	0.3267
1.4193	0.05	60	1.3834	0.3883
1.3265	0.06	70	1.3438	0.3983
1.251	0.07	80	1.2632	0.3992
1.3455	0.07	90	1.2927	0.43
1.2964	0.08	100	1.2623	0.4275
1.3695	0.09	110	1.2770	0.4267
1.194	0.1	120	1.2108	0.4517
1.2885	0.11	130	1.2087	0.4508
1.2418	0.12	140	1.2169	0.4367
1.3893	0.12	150	1.2551	0.4208
1.3133	0.13	160	1.1803	0.4458
1.2526	0.14	170	1.1464	0.4717
1.2132	0.15	180	1.1648	0.4683
1.287	0.16	190	1.1203	0.5017
1.0573	0.17	200	1.1034	0.4983
1.1957	0.17	210	1.1519	0.48
1.3078	0.18	220	1.1356	0.5058
1.141	0.19	230	1.1697	0.445
1.3239	0.2	240	1.1909	0.445
1.069	0.21	250	1.1622	0.4567
1.1035	0.22	260	1.1622	0.4817
1.1384	0.23	270	1.1441	0.4867
1.1704	0.23	280	1.1047	0.515
1.2567	0.24	290	1.0590	0.5175
1.0127	0.25	300	1.1075	0.5025
0.9903	0.26	310	1.1014	0.52
1.0588	0.27	320	1.0738	0.5233
1.2552	0.28	330	1.0917	0.5058
1.0464	0.28	340	1.0621	0.5408
1.0819	0.29	350	1.1541	0.4833
1.0828	0.3	360	1.0351	0.5242
1.1456	0.31	370	1.0940	0.4917
1.0856	0.32	380	1.0818	0.4825
1.0456	0.33	390	1.1336	0.4875
1.2629	0.33	400	1.1399	0.4692
1.1563	0.34	410	1.1484	0.46
1.214	0.35	420	1.0943	0.5117
1.1227	0.36	430	1.0438	0.5333
1.1006	0.37	440	1.1435	0.4842
1.4169	0.38	450	1.0695	0.495
1.0879	0.38	460	1.0750	0.5142
1.103	0.39	470	1.0469	0.5542
1.1574	0.4	480	1.0849	0.5233
1.0681	0.41	490	1.0680	0.5283
1.1664	0.42	500	1.0261	0.5517
0.9498	0.42	510	1.0322	0.5292
1.2028	0.43	520	1.0459	0.525
0.9554	0.44	530	1.0558	0.5242
1.1721	0.45	540	1.0990	0.5333
1.1527	0.46	550	1.0562	0.52
1.0249	0.47	560	1.0748	0.5183
1.1108	0.47	570	1.0515	0.5183
1.0518	0.48	580	1.0743	0.5017
1.1625	0.49	590	1.0369	0.5358
1.0914	0.5	600	1.0133	0.5383
1.0405	0.51	610	1.0769	0.495
1.0241	0.52	620	1.0320	0.5483
1.3388	0.53	630	1.0194	0.5367
1.112	0.53	640	1.0215	0.5533
1.1039	0.54	650	1.0652	0.5233
1.0739	0.55	660	1.0563	0.4975
0.8854	0.56	670	1.0234	0.5425
1.0837	0.57	680	1.0446	0.5375
0.9748	0.57	690	1.0236	0.5558
1.1436	0.58	700	1.0025	0.5558
1.0762	0.59	710	1.0263	0.5442
1.1594	0.6	720	1.0044	0.5417
1.0542	0.61	730	0.9851	0.5633
0.9711	0.62	740	1.0097	0.5325
1.0963	0.62	750	0.9819	0.5517
1.0313	0.63	760	1.0008	0.5575
1.0046	0.64	770	1.0398	0.5417
1.0007	0.65	780	1.0929	0.4992
1.0521	0.66	790	1.0413	0.5408
0.9918	0.67	800	1.0485	0.5433
1.1687	0.68	810	1.0181	0.5375
0.8415	0.68	820	1.0161	0.55
0.9516	0.69	830	1.0558	0.5342
0.9161	0.7	840	0.9982	0.5558
1.0259	0.71	850	1.0429	0.53
0.9952	0.72	860	1.0378	0.5333
0.9626	0.72	870	1.0100	0.5425
1.0424	0.73	880	1.0394	0.5117
1.1013	0.74	890	1.0234	0.5358
1.1225	0.75	900	1.0127	0.5392
0.8886	0.76	910	1.0138	0.5358
0.8954	0.77	920	0.9991	0.5425
0.8965	0.78	930	1.0029	0.54
1.021	0.78	940	0.9975	0.555
1.0586	0.79	950	1.0274	0.5592
1.1711	0.8	960	1.0118	0.5325
0.9104	0.81	970	1.0249	0.5175
0.9854	0.82	980	1.0195	0.5275
1.0797	0.82	990	0.9979	0.5517
1.0675	0.83	1000	0.9811	0.5492
1.0044	0.84	1010	1.0465	0.5217
0.9931	0.85	1020	1.0218	0.5425
1.086	0.86	1030	1.0056	0.5425
1.0026	0.87	1040	1.0012	0.5483
1.0327	0.88	1050	1.0388	0.5358
0.9409	0.88	1060	0.9844	0.5667
0.9433	0.89	1070	0.9801	0.5583
1.1275	0.9	1080	0.9905	0.5417
0.9402	0.91	1090	1.0152	0.555
1.0165	0.92	1100	0.9882	0.5442
0.8924	0.93	1110	1.0120	0.5458
1.0267	0.93	1120	1.0318	0.5367
1.0285	0.94	1130	1.0633	0.525
1.2551	0.95	1140	1.0032	0.5408
1.0909	0.96	1150	0.9681	0.56
1.0208	0.97	1160	0.9570	0.5725
0.9663	0.97	1170	0.9622	0.5617
0.9391	0.98	1180	0.9486	0.5775
1.1975	0.99	1190	0.9506	0.5617
0.9428	1.0	1200	0.9806	0.5492
0.7799	1.01	1210	0.9805	0.5675
0.7864	1.02	1220	0.9642	0.5833
0.711	1.02	1230	0.9985	0.5625
0.8444	1.03	1240	1.0404	0.5725
0.7398	1.04	1250	1.0310	0.5575
0.7063	1.05	1260	1.0468	0.5733
0.9286	1.06	1270	1.0341	0.5592
0.6747	1.07	1280	1.0461	0.5467
0.7503	1.07	1290	1.0218	0.5692
0.8217	1.08	1300	1.0439	0.5792
0.7533	1.09	1310	1.0069	0.5558
0.8461	1.1	1320	1.0202	0.5608
0.797	1.11	1330	1.0288	0.5617
0.8489	1.12	1340	1.0867	0.5367
0.7139	1.12	1350	1.0144	0.5567
0.779	1.13	1360	1.0101	0.5692
0.7901	1.14	1370	0.9999	0.5675
0.672	1.15	1380	1.0314	0.56
0.6909	1.16	1390	1.0347	0.5533
0.7485	1.17	1400	1.0149	0.5642
0.7932	1.18	1410	0.9997	0.5792
0.8111	1.18	1420	1.0173	0.5567
0.7201	1.19	1430	1.0044	0.5675
0.8785	1.2	1440	1.0240	0.5775
0.872	1.21	1450	1.0030	0.5825
0.698	1.22	1460	0.9872	0.5808
0.6795	1.23	1470	1.0854	0.5425
0.7207	1.23	1480	1.0158	0.585
0.8295	1.24	1490	1.0298	0.5683
0.7546	1.25	1500	1.0075	0.5817
0.833	1.26	1510	1.0133	0.5683
0.7183	1.27	1520	1.0075	0.5817
0.826	1.27	1530	1.1743	0.5242
0.8769	1.28	1540	1.1146	0.5292
0.9382	1.29	1550	1.0655	0.5708
0.8704	1.3	1560	1.0595	0.56
0.8551	1.31	1570	1.0004	0.5733
0.7856	1.32	1580	1.0010	0.5733
0.8383	1.32	1590	1.0158	0.565
0.664	1.33	1600	0.9840	0.5808
0.8265	1.34	1610	1.0043	0.5775
0.6619	1.35	1620	1.0370	0.5725
0.7648	1.36	1630	0.9861	0.5808
0.7817	1.37	1640	1.0044	0.5733
0.9077	1.38	1650	0.9890	0.5808
0.6679	1.38	1660	1.0057	0.5808
0.6428	1.39	1670	1.0133	0.585
1.0346	1.4	1680	1.0188	0.5842
0.7576	1.41	1690	1.0069	0.5717
0.7416	1.42	1700	1.0103	0.5658
0.6503	1.43	1710	0.9962	0.5733
0.8442	1.43	1720	1.0023	0.5775
0.7053	1.44	1730	1.0052	0.5758
0.7496	1.45	1740	1.0058	0.5775
0.8825	1.46	1750	1.0027	0.5767
0.824	1.47	1760	1.0013	0.5767
0.7946	1.48	1770	0.9987	0.5733
0.877	1.48	1780	1.0019	0.5683
0.6465	1.49	1790	0.9998	0.5842
0.7524	1.5	1800	1.0263	0.57
0.7318	1.51	1810	1.0141	0.5842
0.78	1.52	1820	1.0553	0.5633
0.7671	1.52	1830	1.0525	0.5558
0.6737	1.53	1840	1.0197	0.565
0.8028	1.54	1850	1.0087	0.5742
0.914	1.55	1860	1.0111	0.5767
0.6607	1.56	1870	0.9969	0.59
0.8758	1.57	1880	1.0142	0.5725
0.8346	1.57	1890	1.0196	0.5683
0.8353	1.58	1900	0.9847	0.5733
0.7901	1.59	1910	1.0127	0.5533
0.628	1.6	1920	0.9966	0.5575
0.7719	1.61	1930	0.9969	0.5758
0.6255	1.62	1940	1.0018	0.5817
0.7852	1.62	1950	1.0032	0.5758
0.805	1.63	1960	1.0020	0.5842
0.8991	1.64	1970	1.0026	0.5908
0.5871	1.65	1980	1.0016	0.59
0.6986	1.66	1990	1.0231	0.5758
0.8239	1.67	2000	1.0098	0.5867
0.6166	1.68	2010	1.0211	0.5858
0.743	1.68	2020	1.0158	0.585
0.8171	1.69	2030	1.0093	0.5867
0.5622	1.7	2040	1.0113	0.5875
0.7664	1.71	2050	1.0079	0.5817
0.6106	1.72	2060	1.0123	0.5808
0.6013	1.73	2070	1.0101	0.585
0.6778	1.73	2080	1.0037	0.5808
0.6183	1.74	2090	1.0040	0.5833
0.7904	1.75	2100	1.0092	0.585
0.8565	1.76	2110	1.0027	0.5833
0.5864	1.77	2120	1.0020	0.57
0.6965	1.77	2130	1.0012	0.5733
0.8319	1.78	2140	1.0028	0.5725
0.9115	1.79	2150	1.0004	0.575
0.709	1.8	2160	0.9981	0.58
0.7741	1.81	2170	0.9975	0.5775
0.8429	1.82	2180	1.0029	0.5792
0.7965	1.82	2190	1.0042	0.5783
0.6964	1.83	2200	1.0024	0.575
0.7082	1.84	2210	0.9980	0.5792
0.6589	1.85	2220	0.9955	0.5808
0.7475	1.86	2230	0.9977	0.5692
0.6762	1.87	2240	1.0053	0.5758
0.7361	1.88	2250	1.0028	0.5683
0.7648	1.88	2260	0.9996	0.5692
0.6421	1.89	2270	0.9980	0.5733
0.7902	1.9	2280	1.0011	0.5767
0.6654	1.91	2290	0.9972	0.5858
0.7229	1.92	2300	0.9930	0.5825
0.985	1.93	2310	0.9933	0.575
0.7008	1.93	2320	0.9911	0.5775
0.635	1.94	2330	0.9903	0.5725
0.7219	1.95	2340	0.9932	0.5758
0.9246	1.96	2350	0.9950	0.5767
0.6654	1.97	2360	0.9961	0.5775
0.6016	1.98	2370	0.9958	0.58
0.7429	1.98	2380	0.9963	0.58
0.7566	1.99	2390	0.9968	0.5775
0.7313	2.0	2400	0.9971	0.5767

Framework versions

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