GQA_BERT_German_legal_SQuAD_1000

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1558

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: 160
• eval_batch_size: 40
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	5.4106
No log	2.0	4	4.3760
No log	3.0	6	3.8386
No log	4.0	8	3.4019
No log	5.0	10	2.9920
No log	6.0	12	2.6213
No log	7.0	14	2.2878
No log	8.0	16	2.0208
No log	9.0	18	1.7822
No log	10.0	20	1.5722
No log	11.0	22	1.4058
No log	12.0	24	1.2577
No log	13.0	26	1.1312
No log	14.0	28	1.0551
No log	15.0	30	0.9930
No log	16.0	32	0.9489
No log	17.0	34	0.9143
No log	18.0	36	0.9072
No log	19.0	38	0.9140
No log	20.0	40	0.8989
No log	21.0	42	0.8953
No log	22.0	44	0.9172
No log	23.0	46	0.9546
No log	24.0	48	0.9681
No log	25.0	50	0.9606
No log	26.0	52	0.9408
No log	27.0	54	0.9250
No log	28.0	56	0.9220
No log	29.0	58	0.9373
No log	30.0	60	0.9668
No log	31.0	62	0.9668
No log	32.0	64	0.9594
No log	33.0	66	0.9573
No log	34.0	68	0.9488
No log	35.0	70	0.9749
No log	36.0	72	1.0145
No log	37.0	74	1.0467
No log	38.0	76	1.0828
No log	39.0	78	1.1090
No log	40.0	80	1.1043
No log	41.0	82	1.0685
No log	42.0	84	1.0280
No log	43.0	86	1.0371
No log	44.0	88	1.0636
No log	45.0	90	1.0904
No log	46.0	92	1.1224
No log	47.0	94	1.1243
No log	48.0	96	1.0905
No log	49.0	98	1.0289
No log	50.0	100	0.9908
No log	51.0	102	0.9714
No log	52.0	104	0.9660
No log	53.0	106	1.0100
No log	54.0	108	1.0633
No log	55.0	110	1.1044
No log	56.0	112	1.1235
No log	57.0	114	1.1014
No log	58.0	116	1.0543
No log	59.0	118	0.9955
No log	60.0	120	0.9773
No log	61.0	122	0.9870
No log	62.0	124	1.0294
No log	63.0	126	1.0576
No log	64.0	128	1.0765
No log	65.0	130	1.0864
No log	66.0	132	1.0997
No log	67.0	134	1.1052
No log	68.0	136	1.1019
No log	69.0	138	1.0971
No log	70.0	140	1.1070
No log	71.0	142	1.1038
No log	72.0	144	1.0788
No log	73.0	146	1.0475
No log	74.0	148	1.0148
No log	75.0	150	1.0116
No log	76.0	152	1.0157
No log	77.0	154	1.0376
No log	78.0	156	1.0504
No log	79.0	158	1.0475
No log	80.0	160	1.0556
No log	81.0	162	1.0530
No log	82.0	164	1.0458
No log	83.0	166	1.0454
No log	84.0	168	1.0656
No log	85.0	170	1.0833
No log	86.0	172	1.0923
No log	87.0	174	1.0911
No log	88.0	176	1.0803
No log	89.0	178	1.0575
No log	90.0	180	1.0371
No log	91.0	182	1.0352
No log	92.0	184	1.0508
No log	93.0	186	1.0546
No log	94.0	188	1.0625
No log	95.0	190	1.0561
No log	96.0	192	1.0366
No log	97.0	194	1.0265
No log	98.0	196	1.0286
No log	99.0	198	1.0448
No log	100.0	200	1.0689
No log	101.0	202	1.0835
No log	102.0	204	1.0967
No log	103.0	206	1.0810
No log	104.0	208	1.0710
No log	105.0	210	1.0538
No log	106.0	212	1.0512
No log	107.0	214	1.0539
No log	108.0	216	1.0535
No log	109.0	218	1.0397
No log	110.0	220	1.0360
No log	111.0	222	1.0479
No log	112.0	224	1.0558
No log	113.0	226	1.0525
No log	114.0	228	1.0513
No log	115.0	230	1.0679
No log	116.0	232	1.0945
No log	117.0	234	1.1037
No log	118.0	236	1.1158
No log	119.0	238	1.1081
No log	120.0	240	1.0973
No log	121.0	242	1.0947
No log	122.0	244	1.0866
No log	123.0	246	1.0766
No log	124.0	248	1.0589
No log	125.0	250	1.0458
No log	126.0	252	1.0648
No log	127.0	254	1.0869
No log	128.0	256	1.0910
No log	129.0	258	1.1066
No log	130.0	260	1.1145
No log	131.0	262	1.1107
No log	132.0	264	1.0802
No log	133.0	266	1.0570
No log	134.0	268	1.0308
No log	135.0	270	1.0149
No log	136.0	272	1.0135
No log	137.0	274	1.0241
No log	138.0	276	1.0311
No log	139.0	278	1.0378
No log	140.0	280	1.0421
No log	141.0	282	1.0554
No log	142.0	284	1.0694
No log	143.0	286	1.0856
No log	144.0	288	1.1031
No log	145.0	290	1.1157
No log	146.0	292	1.1055
No log	147.0	294	1.1045
No log	148.0	296	1.1188
No log	149.0	298	1.1268
No log	150.0	300	1.1195
No log	151.0	302	1.1045
No log	152.0	304	1.0963
No log	153.0	306	1.1043
No log	154.0	308	1.1261
No log	155.0	310	1.1431
No log	156.0	312	1.1466
No log	157.0	314	1.1403
No log	158.0	316	1.1290
No log	159.0	318	1.1105
No log	160.0	320	1.1132
No log	161.0	322	1.1144
No log	162.0	324	1.1061
No log	163.0	326	1.0910
No log	164.0	328	1.0748
No log	165.0	330	1.0729
No log	166.0	332	1.0814
No log	167.0	334	1.0908
No log	168.0	336	1.1036
No log	169.0	338	1.1271
No log	170.0	340	1.1464
No log	171.0	342	1.1583
No log	172.0	344	1.1672
No log	173.0	346	1.1624
No log	174.0	348	1.1390
No log	175.0	350	1.0843
No log	176.0	352	1.0204
No log	177.0	354	0.9874
No log	178.0	356	0.9719
No log	179.0	358	0.9721
No log	180.0	360	0.9863
No log	181.0	362	1.0094
No log	182.0	364	1.0308
No log	183.0	366	1.0536
No log	184.0	368	1.0748
No log	185.0	370	1.1033
No log	186.0	372	1.1211
No log	187.0	374	1.1360
No log	188.0	376	1.1434
No log	189.0	378	1.1329
No log	190.0	380	1.1048
No log	191.0	382	1.0957
No log	192.0	384	1.0780
No log	193.0	386	1.0572
No log	194.0	388	1.0435
No log	195.0	390	1.0419
No log	196.0	392	1.0610
No log	197.0	394	1.1001
No log	198.0	396	1.1431
No log	199.0	398	1.1635
No log	200.0	400	1.1661
No log	201.0	402	1.1578
No log	202.0	404	1.1336
No log	203.0	406	1.1108
No log	204.0	408	1.0950
No log	205.0	410	1.0849
No log	206.0	412	1.1056
No log	207.0	414	1.1499
No log	208.0	416	1.1823
No log	209.0	418	1.1833
No log	210.0	420	1.1882
No log	211.0	422	1.1736
No log	212.0	424	1.1444
No log	213.0	426	1.1162
No log	214.0	428	1.0816
No log	215.0	430	1.0608
No log	216.0	432	1.0649
No log	217.0	434	1.0604
No log	218.0	436	1.0702
No log	219.0	438	1.0816
No log	220.0	440	1.1474
No log	221.0	442	1.2056
No log	222.0	444	1.2090
No log	223.0	446	1.2152
No log	224.0	448	1.1864
No log	225.0	450	1.1459
No log	226.0	452	1.1150
No log	227.0	454	1.0951
No log	228.0	456	1.0857
No log	229.0	458	1.0874
No log	230.0	460	1.0987
No log	231.0	462	1.1011
No log	232.0	464	1.1062
No log	233.0	466	1.1090
No log	234.0	468	1.1189
No log	235.0	470	1.1138
No log	236.0	472	1.1205
No log	237.0	474	1.1330
No log	238.0	476	1.1338
No log	239.0	478	1.1135
No log	240.0	480	1.0886
No log	241.0	482	1.0845
No log	242.0	484	1.0747
No log	243.0	486	1.0677
No log	244.0	488	1.0824
No log	245.0	490	1.1008
No log	246.0	492	1.1007
No log	247.0	494	1.0848
No log	248.0	496	1.0728
No log	249.0	498	1.0585
0.5922	250.0	500	1.0618
0.5922	251.0	502	1.0591
0.5922	252.0	504	1.0551
0.5922	253.0	506	1.0478
0.5922	254.0	508	1.0385
0.5922	255.0	510	1.0311
0.5922	256.0	512	1.0257
0.5922	257.0	514	1.0259
0.5922	258.0	516	1.0344
0.5922	259.0	518	1.0510
0.5922	260.0	520	1.0796
0.5922	261.0	522	1.0888
0.5922	262.0	524	1.0821
0.5922	263.0	526	1.0778
0.5922	264.0	528	1.0721
0.5922	265.0	530	1.0781
0.5922	266.0	532	1.0865
0.5922	267.0	534	1.0884
0.5922	268.0	536	1.0968
0.5922	269.0	538	1.0962
0.5922	270.0	540	1.0944
0.5922	271.0	542	1.0910
0.5922	272.0	544	1.0936
0.5922	273.0	546	1.1021
0.5922	274.0	548	1.1126
0.5922	275.0	550	1.1259
0.5922	276.0	552	1.1481
0.5922	277.0	554	1.1635
0.5922	278.0	556	1.1696
0.5922	279.0	558	1.1611
0.5922	280.0	560	1.1398
0.5922	281.0	562	1.1147
0.5922	282.0	564	1.0867
0.5922	283.0	566	1.0676
0.5922	284.0	568	1.0555
0.5922	285.0	570	1.0568
0.5922	286.0	572	1.0963
0.5922	287.0	574	1.1409
0.5922	288.0	576	1.1714
0.5922	289.0	578	1.1963
0.5922	290.0	580	1.1997
0.5922	291.0	582	1.1952
0.5922	292.0	584	1.1851
0.5922	293.0	586	1.1829
0.5922	294.0	588	1.1392
0.5922	295.0	590	1.1129
0.5922	296.0	592	1.0964
0.5922	297.0	594	1.0828
0.5922	298.0	596	1.0712
0.5922	299.0	598	1.0590
0.5922	300.0	600	1.0614
0.5922	301.0	602	1.0745
0.5922	302.0	604	1.0848
0.5922	303.0	606	1.0982
0.5922	304.0	608	1.1136
0.5922	305.0	610	1.1167
0.5922	306.0	612	1.1300
0.5922	307.0	614	1.1521
0.5922	308.0	616	1.1617
0.5922	309.0	618	1.1735
0.5922	310.0	620	1.2090
0.5922	311.0	622	1.2318
0.5922	312.0	624	1.2372
0.5922	313.0	626	1.2384
0.5922	314.0	628	1.2275
0.5922	315.0	630	1.2059
0.5922	316.0	632	1.1896
0.5922	317.0	634	1.1617
0.5922	318.0	636	1.1334
0.5922	319.0	638	1.0988
0.5922	320.0	640	1.0666
0.5922	321.0	642	1.0406
0.5922	322.0	644	1.0344
0.5922	323.0	646	1.0627
0.5922	324.0	648	1.1087
0.5922	325.0	650	1.1714
0.5922	326.0	652	1.2168
0.5922	327.0	654	1.2482
0.5922	328.0	656	1.2589
0.5922	329.0	658	1.2538
0.5922	330.0	660	1.2394
0.5922	331.0	662	1.2193
0.5922	332.0	664	1.2064
0.5922	333.0	666	1.1908
0.5922	334.0	668	1.1798
0.5922	335.0	670	1.1761
0.5922	336.0	672	1.1555
0.5922	337.0	674	1.1190
0.5922	338.0	676	1.0968
0.5922	339.0	678	1.0821
0.5922	340.0	680	1.0757
0.5922	341.0	682	1.0722
0.5922	342.0	684	1.0680
0.5922	343.0	686	1.0767
0.5922	344.0	688	1.0917
0.5922	345.0	690	1.1010
0.5922	346.0	692	1.1058
0.5922	347.0	694	1.1119
0.5922	348.0	696	1.1101
0.5922	349.0	698	1.1025
0.5922	350.0	700	1.0941
0.5922	351.0	702	1.0888
0.5922	352.0	704	1.0893
0.5922	353.0	706	1.0921
0.5922	354.0	708	1.0910
0.5922	355.0	710	1.0918
0.5922	356.0	712	1.0813
0.5922	357.0	714	1.0736
0.5922	358.0	716	1.0665
0.5922	359.0	718	1.0583
0.5922	360.0	720	1.0495
0.5922	361.0	722	1.0510
0.5922	362.0	724	1.0829
0.5922	363.0	726	1.1163
0.5922	364.0	728	1.1434
0.5922	365.0	730	1.1611
0.5922	366.0	732	1.1853
0.5922	367.0	734	1.2239
0.5922	368.0	736	1.2532
0.5922	369.0	738	1.2657
0.5922	370.0	740	1.2696
0.5922	371.0	742	1.2609
0.5922	372.0	744	1.2430
0.5922	373.0	746	1.2168
0.5922	374.0	748	1.1824
0.5922	375.0	750	1.1458
0.5922	376.0	752	1.1188
0.5922	377.0	754	1.0995
0.5922	378.0	756	1.0811
0.5922	379.0	758	1.0728
0.5922	380.0	760	1.0652
0.5922	381.0	762	1.0623
0.5922	382.0	764	1.0716
0.5922	383.0	766	1.0931
0.5922	384.0	768	1.1229
0.5922	385.0	770	1.1486
0.5922	386.0	772	1.1675
0.5922	387.0	774	1.1771
0.5922	388.0	776	1.1787
0.5922	389.0	778	1.1776
0.5922	390.0	780	1.1756
0.5922	391.0	782	1.1694
0.5922	392.0	784	1.1624
0.5922	393.0	786	1.1542
0.5922	394.0	788	1.1457
0.5922	395.0	790	1.1370
0.5922	396.0	792	1.1303
0.5922	397.0	794	1.1235
0.5922	398.0	796	1.1197
0.5922	399.0	798	1.1135
0.5922	400.0	800	1.0979
0.5922	401.0	802	1.0835
0.5922	402.0	804	1.0683
0.5922	403.0	806	1.0581
0.5922	404.0	808	1.0560
0.5922	405.0	810	1.0543
0.5922	406.0	812	1.0415
0.5922	407.0	814	1.0341
0.5922	408.0	816	1.0388
0.5922	409.0	818	1.0562
0.5922	410.0	820	1.0838
0.5922	411.0	822	1.1071
0.5922	412.0	824	1.1360
0.5922	413.0	826	1.1538
0.5922	414.0	828	1.1883
0.5922	415.0	830	1.2152
0.5922	416.0	832	1.2398
0.5922	417.0	834	1.2545
0.5922	418.0	836	1.2657
0.5922	419.0	838	1.2691
0.5922	420.0	840	1.2659
0.5922	421.0	842	1.2646
0.5922	422.0	844	1.2581
0.5922	423.0	846	1.2550
0.5922	424.0	848	1.2507
0.5922	425.0	850	1.2459
0.5922	426.0	852	1.2417
0.5922	427.0	854	1.2365
0.5922	428.0	856	1.2300
0.5922	429.0	858	1.2322
0.5922	430.0	860	1.2267
0.5922	431.0	862	1.2199
0.5922	432.0	864	1.2107
0.5922	433.0	866	1.2014
0.5922	434.0	868	1.1949
0.5922	435.0	870	1.1892
0.5922	436.0	872	1.1835
0.5922	437.0	874	1.1756
0.5922	438.0	876	1.1870
0.5922	439.0	878	1.1962
0.5922	440.0	880	1.2069
0.5922	441.0	882	1.2179
0.5922	442.0	884	1.2263
0.5922	443.0	886	1.2368
0.5922	444.0	888	1.2488
0.5922	445.0	890	1.2584
0.5922	446.0	892	1.2676
0.5922	447.0	894	1.2755
0.5922	448.0	896	1.2822
0.5922	449.0	898	1.2887
0.5922	450.0	900	1.2911
0.5922	451.0	902	1.2927
0.5922	452.0	904	1.2964
0.5922	453.0	906	1.2987
0.5922	454.0	908	1.2957
0.5922	455.0	910	1.2944
0.5922	456.0	912	1.2967
0.5922	457.0	914	1.2969
0.5922	458.0	916	1.2902
0.5922	459.0	918	1.2865
0.5922	460.0	920	1.2887
0.5922	461.0	922	1.2904
0.5922	462.0	924	1.2899
0.5922	463.0	926	1.2855
0.5922	464.0	928	1.2820
0.5922	465.0	930	1.2825
0.5922	466.0	932	1.2809
0.5922	467.0	934	1.2778
0.5922	468.0	936	1.2769
0.5922	469.0	938	1.2735
0.5922	470.0	940	1.2757
0.5922	471.0	942	1.2715
0.5922	472.0	944	1.2676
0.5922	473.0	946	1.2573
0.5922	474.0	948	1.2405
0.5922	475.0	950	1.2193
0.5922	476.0	952	1.1999
0.5922	477.0	954	1.2051
0.5922	478.0	956	1.2076
0.5922	479.0	958	1.2045
0.5922	480.0	960	1.2081
0.5922	481.0	962	1.2212
0.5922	482.0	964	1.2311
0.5922	483.0	966	1.2418
0.5922	484.0	968	1.2523
0.5922	485.0	970	1.2580
0.5922	486.0	972	1.2665
0.5922	487.0	974	1.2711
0.5922	488.0	976	1.2739
0.5922	489.0	978	1.2733
0.5922	490.0	980	1.2758
0.5922	491.0	982	1.2794
0.5922	492.0	984	1.2824
0.5922	493.0	986	1.2838
0.5922	494.0	988	1.2825
0.5922	495.0	990	1.2806
0.5922	496.0	992	1.2769
0.5922	497.0	994	1.2743
0.5922	498.0	996	1.2710
0.5922	499.0	998	1.2669
0.4788	500.0	1000	1.2626
0.4788	501.0	1002	1.2605
0.4788	502.0	1004	1.2631
0.4788	503.0	1006	1.2684
0.4788	504.0	1008	1.2724
0.4788	505.0	1010	1.2762
0.4788	506.0	1012	1.2780
0.4788	507.0	1014	1.2761
0.4788	508.0	1016	1.2774
0.4788	509.0	1018	1.2779
0.4788	510.0	1020	1.2758
0.4788	511.0	1022	1.2711
0.4788	512.0	1024	1.2651
0.4788	513.0	1026	1.2606
0.4788	514.0	1028	1.2555
0.4788	515.0	1030	1.2541
0.4788	516.0	1032	1.2496
0.4788	517.0	1034	1.2424
0.4788	518.0	1036	1.2384
0.4788	519.0	1038	1.2381
0.4788	520.0	1040	1.2339
0.4788	521.0	1042	1.2251
0.4788	522.0	1044	1.2169
0.4788	523.0	1046	1.2087
0.4788	524.0	1048	1.1933
0.4788	525.0	1050	1.1792
0.4788	526.0	1052	1.1675
0.4788	527.0	1054	1.1603
0.4788	528.0	1056	1.1544
0.4788	529.0	1058	1.1581
0.4788	530.0	1060	1.1634
0.4788	531.0	1062	1.1674
0.4788	532.0	1064	1.1685
0.4788	533.0	1066	1.1679
0.4788	534.0	1068	1.1698
0.4788	535.0	1070	1.1711
0.4788	536.0	1072	1.1757
0.4788	537.0	1074	1.1768
0.4788	538.0	1076	1.1770
0.4788	539.0	1078	1.1808
0.4788	540.0	1080	1.1843
0.4788	541.0	1082	1.1852
0.4788	542.0	1084	1.1837
0.4788	543.0	1086	1.1842
0.4788	544.0	1088	1.1876
0.4788	545.0	1090	1.1924
0.4788	546.0	1092	1.1955
0.4788	547.0	1094	1.1933
0.4788	548.0	1096	1.1912
0.4788	549.0	1098	1.1906
0.4788	550.0	1100	1.1941
0.4788	551.0	1102	1.2004
0.4788	552.0	1104	1.2083
0.4788	553.0	1106	1.2145
0.4788	554.0	1108	1.2211
0.4788	555.0	1110	1.2300
0.4788	556.0	1112	1.2380
0.4788	557.0	1114	1.2442
0.4788	558.0	1116	1.2496
0.4788	559.0	1118	1.2519
0.4788	560.0	1120	1.2522
0.4788	561.0	1122	1.2500
0.4788	562.0	1124	1.2486
0.4788	563.0	1126	1.2467
0.4788	564.0	1128	1.2455
0.4788	565.0	1130	1.2481
0.4788	566.0	1132	1.2509
0.4788	567.0	1134	1.2543
0.4788	568.0	1136	1.2605
0.4788	569.0	1138	1.2652
0.4788	570.0	1140	1.2669
0.4788	571.0	1142	1.2690
0.4788	572.0	1144	1.2686
0.4788	573.0	1146	1.2666
0.4788	574.0	1148	1.2666
0.4788	575.0	1150	1.2679
0.4788	576.0	1152	1.2674
0.4788	577.0	1154	1.2673
0.4788	578.0	1156	1.2669
0.4788	579.0	1158	1.2662
0.4788	580.0	1160	1.2659
0.4788	581.0	1162	1.2648
0.4788	582.0	1164	1.2595
0.4788	583.0	1166	1.2542
0.4788	584.0	1168	1.2468
0.4788	585.0	1170	1.2374
0.4788	586.0	1172	1.2233
0.4788	587.0	1174	1.2091
0.4788	588.0	1176	1.1970
0.4788	589.0	1178	1.1898
0.4788	590.0	1180	1.1811
0.4788	591.0	1182	1.1713
0.4788	592.0	1184	1.1662
0.4788	593.0	1186	1.1572
0.4788	594.0	1188	1.1482
0.4788	595.0	1190	1.1402
0.4788	596.0	1192	1.1373
0.4788	597.0	1194	1.1384
0.4788	598.0	1196	1.1433
0.4788	599.0	1198	1.1529
0.4788	600.0	1200	1.1608
0.4788	601.0	1202	1.1694
0.4788	602.0	1204	1.1772
0.4788	603.0	1206	1.1821
0.4788	604.0	1208	1.1891
0.4788	605.0	1210	1.1967
0.4788	606.0	1212	1.2054
0.4788	607.0	1214	1.2110
0.4788	608.0	1216	1.2139
0.4788	609.0	1218	1.2173
0.4788	610.0	1220	1.2175
0.4788	611.0	1222	1.2194
0.4788	612.0	1224	1.2223
0.4788	613.0	1226	1.2258
0.4788	614.0	1228	1.2278
0.4788	615.0	1230	1.2299
0.4788	616.0	1232	1.2281
0.4788	617.0	1234	1.2226
0.4788	618.0	1236	1.2155
0.4788	619.0	1238	1.2067
0.4788	620.0	1240	1.1970
0.4788	621.0	1242	1.1899
0.4788	622.0	1244	1.1849
0.4788	623.0	1246	1.1825
0.4788	624.0	1248	1.1769
0.4788	625.0	1250	1.1720
0.4788	626.0	1252	1.1693
0.4788	627.0	1254	1.1598
0.4788	628.0	1256	1.1574
0.4788	629.0	1258	1.1609
0.4788	630.0	1260	1.1661
0.4788	631.0	1262	1.1655
0.4788	632.0	1264	1.1680
0.4788	633.0	1266	1.1715
0.4788	634.0	1268	1.1723
0.4788	635.0	1270	1.1682
0.4788	636.0	1272	1.1630
0.4788	637.0	1274	1.1621
0.4788	638.0	1276	1.1616
0.4788	639.0	1278	1.1670
0.4788	640.0	1280	1.1656
0.4788	641.0	1282	1.1656
0.4788	642.0	1284	1.1659
0.4788	643.0	1286	1.1700
0.4788	644.0	1288	1.1718
0.4788	645.0	1290	1.1695
0.4788	646.0	1292	1.1653
0.4788	647.0	1294	1.1608
0.4788	648.0	1296	1.1575
0.4788	649.0	1298	1.1549
0.4788	650.0	1300	1.1525
0.4788	651.0	1302	1.1477
0.4788	652.0	1304	1.1403
0.4788	653.0	1306	1.1329
0.4788	654.0	1308	1.1256
0.4788	655.0	1310	1.1203
0.4788	656.0	1312	1.1172
0.4788	657.0	1314	1.1209
0.4788	658.0	1316	1.1239
0.4788	659.0	1318	1.1253
0.4788	660.0	1320	1.1263
0.4788	661.0	1322	1.1313
0.4788	662.0	1324	1.1391
0.4788	663.0	1326	1.1440
0.4788	664.0	1328	1.1492
0.4788	665.0	1330	1.1512
0.4788	666.0	1332	1.1554
0.4788	667.0	1334	1.1543
0.4788	668.0	1336	1.1553
0.4788	669.0	1338	1.1574
0.4788	670.0	1340	1.1577
0.4788	671.0	1342	1.1612
0.4788	672.0	1344	1.1653
0.4788	673.0	1346	1.1692
0.4788	674.0	1348	1.1721
0.4788	675.0	1350	1.1742
0.4788	676.0	1352	1.1772
0.4788	677.0	1354	1.1785
0.4788	678.0	1356	1.1765
0.4788	679.0	1358	1.1755
0.4788	680.0	1360	1.1759
0.4788	681.0	1362	1.1781
0.4788	682.0	1364	1.1776
0.4788	683.0	1366	1.1837
0.4788	684.0	1368	1.1890
0.4788	685.0	1370	1.1940
0.4788	686.0	1372	1.1985
0.4788	687.0	1374	1.2009
0.4788	688.0	1376	1.2036
0.4788	689.0	1378	1.2051
0.4788	690.0	1380	1.2072
0.4788	691.0	1382	1.2115
0.4788	692.0	1384	1.2149
0.4788	693.0	1386	1.2175
0.4788	694.0	1388	1.2178
0.4788	695.0	1390	1.2175
0.4788	696.0	1392	1.2152
0.4788	697.0	1394	1.2118
0.4788	698.0	1396	1.2073
0.4788	699.0	1398	1.2020
0.4788	700.0	1400	1.1967
0.4788	701.0	1402	1.1917
0.4788	702.0	1404	1.1881
0.4788	703.0	1406	1.1940
0.4788	704.0	1408	1.1987
0.4788	705.0	1410	1.2009
0.4788	706.0	1412	1.2014
0.4788	707.0	1414	1.2013
0.4788	708.0	1416	1.2011
0.4788	709.0	1418	1.2073
0.4788	710.0	1420	1.2176
0.4788	711.0	1422	1.2239
0.4788	712.0	1424	1.2277
0.4788	713.0	1426	1.2282
0.4788	714.0	1428	1.2265
0.4788	715.0	1430	1.2251
0.4788	716.0	1432	1.2243
0.4788	717.0	1434	1.2225
0.4788	718.0	1436	1.2164
0.4788	719.0	1438	1.2120
0.4788	720.0	1440	1.2093
0.4788	721.0	1442	1.2011
0.4788	722.0	1444	1.1930
0.4788	723.0	1446	1.1880
0.4788	724.0	1448	1.1804
0.4788	725.0	1450	1.1704
0.4788	726.0	1452	1.1560
0.4788	727.0	1454	1.1434
0.4788	728.0	1456	1.1354
0.4788	729.0	1458	1.1279
0.4788	730.0	1460	1.1244
0.4788	731.0	1462	1.1235
0.4788	732.0	1464	1.1209
0.4788	733.0	1466	1.1207
0.4788	734.0	1468	1.1290
0.4788	735.0	1470	1.1395
0.4788	736.0	1472	1.1493
0.4788	737.0	1474	1.1620
0.4788	738.0	1476	1.1734
0.4788	739.0	1478	1.1823
0.4788	740.0	1480	1.1884
0.4788	741.0	1482	1.1909
0.4788	742.0	1484	1.1918
0.4788	743.0	1486	1.1916
0.4788	744.0	1488	1.1914
0.4788	745.0	1490	1.1919
0.4788	746.0	1492	1.1924
0.4788	747.0	1494	1.1933
0.4788	748.0	1496	1.1937
0.4788	749.0	1498	1.1938
0.4781	750.0	1500	1.1940
0.4781	751.0	1502	1.1931
0.4781	752.0	1504	1.1925
0.4781	753.0	1506	1.1913
0.4781	754.0	1508	1.1904
0.4781	755.0	1510	1.1890
0.4781	756.0	1512	1.1906
0.4781	757.0	1514	1.1942
0.4781	758.0	1516	1.1968
0.4781	759.0	1518	1.1991
0.4781	760.0	1520	1.2009
0.4781	761.0	1522	1.2050
0.4781	762.0	1524	1.2126
0.4781	763.0	1526	1.2183
0.4781	764.0	1528	1.2214
0.4781	765.0	1530	1.2217
0.4781	766.0	1532	1.2214
0.4781	767.0	1534	1.2188
0.4781	768.0	1536	1.2150
0.4781	769.0	1538	1.2096
0.4781	770.0	1540	1.2116
0.4781	771.0	1542	1.2168
0.4781	772.0	1544	1.2192
0.4781	773.0	1546	1.2201
0.4781	774.0	1548	1.2134
0.4781	775.0	1550	1.2045
0.4781	776.0	1552	1.1982
0.4781	777.0	1554	1.1896
0.4781	778.0	1556	1.1777
0.4781	779.0	1558	1.1661
0.4781	780.0	1560	1.1546
0.4781	781.0	1562	1.1440
0.4781	782.0	1564	1.1370
0.4781	783.0	1566	1.1323
0.4781	784.0	1568	1.1278
0.4781	785.0	1570	1.1233
0.4781	786.0	1572	1.1209
0.4781	787.0	1574	1.1154
0.4781	788.0	1576	1.1129
0.4781	789.0	1578	1.1108
0.4781	790.0	1580	1.1097
0.4781	791.0	1582	1.1102
0.4781	792.0	1584	1.1114
0.4781	793.0	1586	1.1132
0.4781	794.0	1588	1.1109
0.4781	795.0	1590	1.1116
0.4781	796.0	1592	1.1147
0.4781	797.0	1594	1.1203
0.4781	798.0	1596	1.1231
0.4781	799.0	1598	1.1248
0.4781	800.0	1600	1.1219
0.4781	801.0	1602	1.1208
0.4781	802.0	1604	1.1222
0.4781	803.0	1606	1.1257
0.4781	804.0	1608	1.1293
0.4781	805.0	1610	1.1304
0.4781	806.0	1612	1.1348
0.4781	807.0	1614	1.1406
0.4781	808.0	1616	1.1468
0.4781	809.0	1618	1.1503
0.4781	810.0	1620	1.1542
0.4781	811.0	1622	1.1570
0.4781	812.0	1624	1.1600
0.4781	813.0	1626	1.1637
0.4781	814.0	1628	1.1667
0.4781	815.0	1630	1.1679
0.4781	816.0	1632	1.1671
0.4781	817.0	1634	1.1673
0.4781	818.0	1636	1.1671
0.4781	819.0	1638	1.1676
0.4781	820.0	1640	1.1683
0.4781	821.0	1642	1.1690
0.4781	822.0	1644	1.1696
0.4781	823.0	1646	1.1690
0.4781	824.0	1648	1.1691
0.4781	825.0	1650	1.1693
0.4781	826.0	1652	1.1689
0.4781	827.0	1654	1.1667
0.4781	828.0	1656	1.1644
0.4781	829.0	1658	1.1625
0.4781	830.0	1660	1.1584
0.4781	831.0	1662	1.1538
0.4781	832.0	1664	1.1474
0.4781	833.0	1666	1.1418
0.4781	834.0	1668	1.1364
0.4781	835.0	1670	1.1332
0.4781	836.0	1672	1.1288
0.4781	837.0	1674	1.1255
0.4781	838.0	1676	1.1239
0.4781	839.0	1678	1.1216
0.4781	840.0	1680	1.1194
0.4781	841.0	1682	1.1178
0.4781	842.0	1684	1.1191
0.4781	843.0	1686	1.1218
0.4781	844.0	1688	1.1250
0.4781	845.0	1690	1.1249
0.4781	846.0	1692	1.1224
0.4781	847.0	1694	1.1217
0.4781	848.0	1696	1.1174
0.4781	849.0	1698	1.1146
0.4781	850.0	1700	1.1135
0.4781	851.0	1702	1.1125
0.4781	852.0	1704	1.1114
0.4781	853.0	1706	1.1102
0.4781	854.0	1708	1.1089
0.4781	855.0	1710	1.1085
0.4781	856.0	1712	1.1069
0.4781	857.0	1714	1.1047
0.4781	858.0	1716	1.1000
0.4781	859.0	1718	1.0988
0.4781	860.0	1720	1.0952
0.4781	861.0	1722	1.0934
0.4781	862.0	1724	1.0934
0.4781	863.0	1726	1.0914
0.4781	864.0	1728	1.0911
0.4781	865.0	1730	1.0955
0.4781	866.0	1732	1.0983
0.4781	867.0	1734	1.0984
0.4781	868.0	1736	1.0990
0.4781	869.0	1738	1.1023
0.4781	870.0	1740	1.1068
0.4781	871.0	1742	1.1113
0.4781	872.0	1744	1.1149
0.4781	873.0	1746	1.1186
0.4781	874.0	1748	1.1217
0.4781	875.0	1750	1.1238
0.4781	876.0	1752	1.1264
0.4781	877.0	1754	1.1295
0.4781	878.0	1756	1.1319
0.4781	879.0	1758	1.1341
0.4781	880.0	1760	1.1357
0.4781	881.0	1762	1.1347
0.4781	882.0	1764	1.1336
0.4781	883.0	1766	1.1342
0.4781	884.0	1768	1.1352
0.4781	885.0	1770	1.1366
0.4781	886.0	1772	1.1389
0.4781	887.0	1774	1.1427
0.4781	888.0	1776	1.1454
0.4781	889.0	1778	1.1472
0.4781	890.0	1780	1.1493
0.4781	891.0	1782	1.1507
0.4781	892.0	1784	1.1511
0.4781	893.0	1786	1.1515
0.4781	894.0	1788	1.1509
0.4781	895.0	1790	1.1505
0.4781	896.0	1792	1.1494
0.4781	897.0	1794	1.1476
0.4781	898.0	1796	1.1461
0.4781	899.0	1798	1.1453
0.4781	900.0	1800	1.1443
0.4781	901.0	1802	1.1446
0.4781	902.0	1804	1.1460
0.4781	903.0	1806	1.1472
0.4781	904.0	1808	1.1482
0.4781	905.0	1810	1.1491
0.4781	906.0	1812	1.1505
0.4781	907.0	1814	1.1515
0.4781	908.0	1816	1.1520
0.4781	909.0	1818	1.1525
0.4781	910.0	1820	1.1531
0.4781	911.0	1822	1.1551
0.4781	912.0	1824	1.1570
0.4781	913.0	1826	1.1585
0.4781	914.0	1828	1.1595
0.4781	915.0	1830	1.1608
0.4781	916.0	1832	1.1625
0.4781	917.0	1834	1.1632
0.4781	918.0	1836	1.1641
0.4781	919.0	1838	1.1649
0.4781	920.0	1840	1.1658
0.4781	921.0	1842	1.1664
0.4781	922.0	1844	1.1662
0.4781	923.0	1846	1.1660
0.4781	924.0	1848	1.1672
0.4781	925.0	1850	1.1674
0.4781	926.0	1852	1.1667
0.4781	927.0	1854	1.1652
0.4781	928.0	1856	1.1640
0.4781	929.0	1858	1.1632
0.4781	930.0	1860	1.1626
0.4781	931.0	1862	1.1617
0.4781	932.0	1864	1.1610
0.4781	933.0	1866	1.1611
0.4781	934.0	1868	1.1613
0.4781	935.0	1870	1.1613
0.4781	936.0	1872	1.1618
0.4781	937.0	1874	1.1624
0.4781	938.0	1876	1.1625
0.4781	939.0	1878	1.1623
0.4781	940.0	1880	1.1624
0.4781	941.0	1882	1.1619
0.4781	942.0	1884	1.1598
0.4781	943.0	1886	1.1571
0.4781	944.0	1888	1.1551
0.4781	945.0	1890	1.1531
0.4781	946.0	1892	1.1520
0.4781	947.0	1894	1.1511
0.4781	948.0	1896	1.1509
0.4781	949.0	1898	1.1511
0.4781	950.0	1900	1.1509
0.4781	951.0	1902	1.1508
0.4781	952.0	1904	1.1511
0.4781	953.0	1906	1.1515
0.4781	954.0	1908	1.1520
0.4781	955.0	1910	1.1527
0.4781	956.0	1912	1.1535
0.4781	957.0	1914	1.1546
0.4781	958.0	1916	1.1557
0.4781	959.0	1918	1.1564
0.4781	960.0	1920	1.1568
0.4781	961.0	1922	1.1572
0.4781	962.0	1924	1.1578
0.4781	963.0	1926	1.1583
0.4781	964.0	1928	1.1587
0.4781	965.0	1930	1.1589
0.4781	966.0	1932	1.1587
0.4781	967.0	1934	1.1587
0.4781	968.0	1936	1.1586
0.4781	969.0	1938	1.1587
0.4781	970.0	1940	1.1591
0.4781	971.0	1942	1.1594
0.4781	972.0	1944	1.1596
0.4781	973.0	1946	1.1597
0.4781	974.0	1948	1.1599
0.4781	975.0	1950	1.1600
0.4781	976.0	1952	1.1596
0.4781	977.0	1954	1.1591
0.4781	978.0	1956	1.1585
0.4781	979.0	1958	1.1580
0.4781	980.0	1960	1.1575
0.4781	981.0	1962	1.1571
0.4781	982.0	1964	1.1569
0.4781	983.0	1966	1.1568
0.4781	984.0	1968	1.1567
0.4781	985.0	1970	1.1565
0.4781	986.0	1972	1.1564
0.4781	987.0	1974	1.1562
0.4781	988.0	1976	1.1561
0.4781	989.0	1978	1.1560
0.4781	990.0	1980	1.1559
0.4781	991.0	1982	1.1559
0.4781	992.0	1984	1.1558
0.4781	993.0	1986	1.1558
0.4781	994.0	1988	1.1558
0.4781	995.0	1990	1.1557
0.4781	996.0	1992	1.1557
0.4781	997.0	1994	1.1557
0.4781	998.0	1996	1.1558
0.4781	999.0	1998	1.1558
0.4784	1000.0	2000	1.1558

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.7
• Tokenizers 0.15.0