Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6325	0.01	10	1.5991	0.2008
1.582	0.02	20	1.5884	0.2975
1.5363	0.03	30	1.5598	0.275
1.5358	0.03	40	1.4794	0.3367
1.5065	0.04	50	1.3755	0.3825
1.392	0.05	60	1.2745	0.4458
1.3156	0.06	70	1.2164	0.4058
1.2387	0.07	80	1.2414	0.4283
1.3621	0.07	90	1.1632	0.4808
1.242	0.08	100	1.4167	0.365
1.242	0.09	110	1.2389	0.4367
1.2249	0.1	120	1.3337	0.4083
1.3734	0.11	130	1.1265	0.49
1.3003	0.12	140	1.1609	0.4675
1.0861	0.12	150	1.4087	0.4017
1.1882	0.13	160	1.1827	0.4442
1.2343	0.14	170	1.2829	0.43
1.1028	0.15	180	1.1621	0.505
1.3076	0.16	190	1.2701	0.405
1.1405	0.17	200	1.2041	0.4458
1.2308	0.17	210	1.1216	0.4558
1.2857	0.18	220	1.1178	0.47
1.1742	0.19	230	1.1206	0.5225
1.1472	0.2	240	1.1125	0.4925
1.2596	0.21	250	1.1274	0.4867
1.1323	0.22	260	1.0597	0.5342
1.0149	0.23	270	1.0703	0.5225
1.1787	0.23	280	1.1797	0.485
1.1165	0.24	290	1.1038	0.51
1.0636	0.25	300	1.0767	0.5392
1.1375	0.26	310	1.0852	0.525
1.2661	0.27	320	1.1114	0.4967
1.168	0.28	330	1.0562	0.5258
1.2809	0.28	340	1.0941	0.5117
1.1089	0.29	350	1.0778	0.4975
1.0561	0.3	360	1.1326	0.4467
1.1941	0.31	370	1.0203	0.5417
1.0317	0.32	380	1.0387	0.525
1.1056	0.33	390	1.0369	0.5342
1.2667	0.33	400	1.0146	0.5492
1.1629	0.34	410	1.0507	0.5442
0.9479	0.35	420	1.0260	0.5408
1.049	0.36	430	1.0202	0.5292
1.0778	0.37	440	0.9926	0.5583
0.8634	0.38	450	1.0885	0.5275
1.1605	0.38	460	0.9796	0.5558
1.0557	0.39	470	1.0047	0.5475
1.0388	0.4	480	1.0342	0.5508
0.9782	0.41	490	1.0917	0.5008
1.0986	0.42	500	1.1414	0.5125
1.0982	0.42	510	1.0110	0.5433
1.0264	0.43	520	1.0003	0.5542
1.045	0.44	530	1.0478	0.5333
1.0532	0.45	540	1.0700	0.5133
1.1025	0.46	550	1.0191	0.5367
1.1531	0.47	560	1.0951	0.5325
1.0562	0.47	570	1.0527	0.5208
1.0935	0.48	580	1.0087	0.5525
0.9918	0.49	590	1.1201	0.49
1.0098	0.5	600	1.0244	0.5425
1.0064	0.51	610	1.0375	0.54
1.0049	0.52	620	1.0123	0.545
1.2486	0.53	630	1.1018	0.515
1.1461	0.53	640	1.0022	0.5433
1.0624	0.54	650	1.0048	0.5483
1.1099	0.55	660	0.9848	0.5575
1.0624	0.56	670	0.9804	0.5575
1.0554	0.57	680	1.0003	0.5458
1.009	0.57	690	1.0566	0.5183
1.0326	0.58	700	1.0969	0.5125
1.1079	0.59	710	1.0181	0.5383
0.9814	0.6	720	0.9950	0.5442
0.9225	0.61	730	1.0021	0.5533
1.0408	0.62	740	1.0248	0.555
1.033	0.62	750	1.0587	0.5142
0.9995	0.63	760	0.9895	0.5592
0.9837	0.64	770	0.9991	0.5458
1.0901	0.65	780	1.0011	0.5583
0.89	0.66	790	1.1504	0.5108
1.2833	0.67	800	1.0055	0.545
0.9868	0.68	810	1.0228	0.5333
1.0203	0.68	820	0.9798	0.5517
0.9778	0.69	830	0.9739	0.5583
1.0526	0.7	840	0.9525	0.5592
1.0748	0.71	850	0.9648	0.5625
1.0818	0.72	860	0.9868	0.5425
1.1718	0.72	870	1.0041	0.54
1.052	0.73	880	0.9926	0.5633
0.9856	0.74	890	1.0029	0.5367
1.0623	0.75	900	1.0920	0.5375
1.2347	0.76	910	0.9949	0.5558
1.0313	0.77	920	0.9606	0.5583
1.0903	0.78	930	0.9673	0.5542
1.0952	0.78	940	0.9778	0.55
0.9689	0.79	950	0.9669	0.555
1.1173	0.8	960	0.9415	0.57
0.9672	0.81	970	0.9393	0.575
0.8624	0.82	980	0.9409	0.5767
0.9683	0.82	990	0.9770	0.5467
0.9681	0.83	1000	1.0163	0.5383
1.1862	0.84	1010	0.9532	0.5692
0.9935	0.85	1020	0.9815	0.5425
1.1011	0.86	1030	1.0984	0.5167
0.9626	0.87	1040	0.9493	0.5675
1.0268	0.88	1050	1.0367	0.5583
1.15	0.88	1060	0.9533	0.5792
1.1613	0.89	1070	0.9860	0.5558
0.8876	0.9	1080	0.9948	0.5583
0.9916	0.91	1090	0.9418	0.5775
1.034	0.92	1100	0.9532	0.5617
1.2078	0.93	1110	0.9457	0.5658
0.9293	0.93	1120	0.9474	0.5642
0.9945	0.94	1130	0.9856	0.5467
1.1483	0.95	1140	0.9769	0.5683
1.0652	0.96	1150	0.9333	0.5808
0.943	0.97	1160	0.9613	0.5717
0.8959	0.97	1170	0.9292	0.5742
1.0558	0.98	1180	0.9216	0.5833
0.9603	0.99	1190	0.9352	0.5792
1.0854	1.0	1200	0.9403	0.5833
0.7435	1.01	1210	0.9177	0.5875
0.8798	1.02	1220	0.9625	0.5592
0.7921	1.02	1230	0.9349	0.5717
0.6194	1.03	1240	0.9355	0.5958
0.7193	1.04	1250	0.9540	0.5908
0.7902	1.05	1260	0.9912	0.5842
0.9728	1.06	1270	0.9568	0.5817
0.8948	1.07	1280	0.9572	0.5667
0.7172	1.07	1290	1.0331	0.5608
0.7905	1.08	1300	0.9523	0.5692
0.7699	1.09	1310	1.0065	0.5625
0.9043	1.1	1320	1.0960	0.5208
0.8665	1.11	1330	0.9775	0.565
0.7809	1.12	1340	0.9941	0.5542
0.6454	1.12	1350	1.0438	0.5675
0.8919	1.13	1360	0.9652	0.5742
0.6891	1.14	1370	1.0144	0.5733
0.7775	1.15	1380	0.9862	0.5733
0.7469	1.16	1390	0.9685	0.58
0.7795	1.17	1400	0.9845	0.5725
0.8594	1.18	1410	0.9833	0.5683
0.8161	1.18	1420	0.9933	0.57
0.8836	1.19	1430	1.0641	0.5383
0.8316	1.2	1440	0.9770	0.5642
0.7242	1.21	1450	0.9647	0.5592
0.7889	1.22	1460	1.0378	0.5525
0.8997	1.23	1470	1.0074	0.5717
0.8315	1.23	1480	0.9810	0.585
0.928	1.24	1490	0.9673	0.585
0.7716	1.25	1500	0.9758	0.5717
0.7998	1.26	1510	0.9980	0.58
0.6825	1.27	1520	0.9766	0.5867
0.8354	1.27	1530	0.9622	0.5783
0.7766	1.28	1540	0.9506	0.59
0.7776	1.29	1550	0.9469	0.5992
0.772	1.3	1560	0.9380	0.5908
0.6561	1.31	1570	0.9896	0.5783
0.9753	1.32	1580	0.9428	0.59
0.685	1.32	1590	0.9492	0.59
0.7375	1.33	1600	0.9792	0.5825
0.7753	1.34	1610	0.9611	0.5908
0.7627	1.35	1620	0.9787	0.5842
0.8135	1.36	1630	1.0000	0.5617
0.8031	1.37	1640	0.9770	0.5758
0.7973	1.38	1650	1.0509	0.58
0.7865	1.38	1660	0.9632	0.5925
0.8153	1.39	1670	0.9572	0.5875
0.7022	1.4	1680	0.9872	0.5767
0.7709	1.41	1690	0.9615	0.5833
0.8874	1.42	1700	0.9548	0.5817
0.7961	1.43	1710	0.9472	0.5967
0.7718	1.43	1720	0.9849	0.5725
0.7515	1.44	1730	0.9825	0.5742
0.9256	1.45	1740	0.9514	0.5817
0.8487	1.46	1750	0.9591	0.5908
0.7539	1.47	1760	0.9509	0.5975
0.7333	1.48	1770	0.9835	0.5883
0.6634	1.48	1780	1.0435	0.5675
0.7045	1.49	1790	0.9614	0.5908
0.8598	1.5	1800	0.9362	0.595
0.8418	1.51	1810	0.9409	0.5958
0.8074	1.52	1820	0.9379	0.5992
0.8183	1.52	1830	0.9296	0.6042
0.8257	1.53	1840	0.9324	0.6058
0.6653	1.54	1850	0.9261	0.605
0.7399	1.55	1860	0.9448	0.6033
0.762	1.56	1870	0.9568	0.5942
0.6583	1.57	1880	0.9650	0.5833
0.9037	1.57	1890	0.9301	0.5967
0.7022	1.58	1900	0.9499	0.6042
0.8169	1.59	1910	0.9537	0.6025
0.5907	1.6	1920	0.9700	0.595
0.7397	1.61	1930	0.9684	0.5942
0.7224	1.62	1940	0.9516	0.6
0.664	1.62	1950	0.9405	0.5933
0.6477	1.63	1960	0.9474	0.5967
0.8474	1.64	1970	0.9540	0.5883
0.6596	1.65	1980	0.9482	0.5992
0.7187	1.66	1990	0.9404	0.5933
0.7754	1.67	2000	0.9389	0.5892
0.7789	1.68	2010	0.9369	0.5942
0.8082	1.68	2020	0.9288	0.5983
0.7271	1.69	2030	0.9319	0.5992
0.7631	1.7	2040	0.9344	0.6
0.8105	1.71	2050	0.9538	0.5925
0.7941	1.72	2060	0.9625	0.5958
0.8801	1.73	2070	0.9412	0.5975
0.6754	1.73	2080	0.9262	0.6033
0.7901	1.74	2090	0.9301	0.5983
0.9318	1.75	2100	0.9361	0.5992
0.8394	1.76	2110	0.9198	0.6008
0.6138	1.77	2120	0.9234	0.6083
0.7199	1.77	2130	0.9233	0.6083
0.7092	1.78	2140	0.9219	0.6033
0.8862	1.79	2150	0.9199	0.6067
0.7834	1.8	2160	0.9199	0.6025
0.729	1.81	2170	0.9206	0.6058
0.6533	1.82	2180	0.9252	0.605
0.7499	1.82	2190	0.9284	0.6125
0.7665	1.83	2200	0.9295	0.6092
0.5497	1.84	2210	0.9369	0.6083
0.8775	1.85	2220	0.9402	0.61
0.6465	1.86	2230	0.9389	0.6092
0.573	1.87	2240	0.9369	0.6125
0.6852	1.88	2250	0.9368	0.6125
0.6715	1.88	2260	0.9346	0.6142
0.6263	1.89	2270	0.9339	0.6133
0.5795	1.9	2280	0.9313	0.6125
0.681	1.91	2290	0.9347	0.6083
0.7992	1.92	2300	0.9342	0.6125
0.6634	1.93	2310	0.9323	0.6117
0.7184	1.93	2320	0.9310	0.6092
0.6863	1.94	2330	0.9318	0.61
0.687	1.95	2340	0.9336	0.6117
0.7697	1.96	2350	0.9348	0.6133
0.7281	1.97	2360	0.9332	0.6117
0.7628	1.98	2370	0.9304	0.6108
0.7419	1.98	2380	0.9297	0.6075
0.7973	1.99	2390	0.9292	0.6075
0.5734	2.0	2400	0.9292	0.6083

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

denise227/amazon_kindle_sentiment_analysis_final

amazon_kindle_sentiment_analysis_final

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

denise227/
amazon_kindle_sentiment_analysis_final