README.md

metadata

tags:
  - generated_from_trainer
model-index:
  - name: GQA_RoBERTa_legal_SQuAD_complete_augmented_1000
    results: []

GQA_RoBERTa_legal_SQuAD_complete_augmented_1000

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

• Loss: 4.7861

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: 128
• eval_batch_size: 32
• 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	4	5.0223
No log	2.0	8	2.8523
No log	3.0	12	3.8159
No log	4.0	16	2.6311
No log	5.0	20	3.0900
No log	6.0	24	2.4416
No log	7.0	28	2.5390
No log	8.0	32	2.9257
No log	9.0	36	2.5334
No log	10.0	40	2.9268
No log	11.0	44	2.3971
No log	12.0	48	3.0426
No log	13.0	52	2.7291
No log	14.0	56	2.6897
No log	15.0	60	3.1254
No log	16.0	64	2.7555
No log	17.0	68	3.1737
No log	18.0	72	3.0224
No log	19.0	76	3.2564
No log	20.0	80	3.1519
No log	21.0	84	3.1495
No log	22.0	88	3.5671
No log	23.0	92	3.2413
No log	24.0	96	3.1965
No log	25.0	100	3.4133
No log	26.0	104	3.3503
No log	27.0	108	3.6105
No log	28.0	112	3.9621
No log	29.0	116	3.5849
No log	30.0	120	3.6768
No log	31.0	124	3.4918
No log	32.0	128	3.7783
No log	33.0	132	3.4769
No log	34.0	136	3.5188
No log	35.0	140	3.5691
No log	36.0	144	3.3389
No log	37.0	148	3.6734
No log	38.0	152	3.4745
No log	39.0	156	3.6131
No log	40.0	160	3.5911
No log	41.0	164	3.8296
No log	42.0	168	3.6103
No log	43.0	172	3.6957
No log	44.0	176	3.6936
No log	45.0	180	3.5780
No log	46.0	184	3.6764
No log	47.0	188	3.7031
No log	48.0	192	3.7834
No log	49.0	196	3.6589
No log	50.0	200	3.6860
No log	51.0	204	3.8114
No log	52.0	208	3.7939
No log	53.0	212	3.8300
No log	54.0	216	3.7047
No log	55.0	220	3.8573
No log	56.0	224	3.9302
No log	57.0	228	4.0313
No log	58.0	232	3.8129
No log	59.0	236	3.8477
No log	60.0	240	3.6475
No log	61.0	244	3.7684
No log	62.0	248	3.5979
No log	63.0	252	3.6298
No log	64.0	256	3.7154
No log	65.0	260	3.8287
No log	66.0	264	3.9307
No log	67.0	268	3.8536
No log	68.0	272	3.9610
No log	69.0	276	3.8192
No log	70.0	280	3.8299
No log	71.0	284	4.0224
No log	72.0	288	3.8624
No log	73.0	292	3.9964
No log	74.0	296	3.9232
No log	75.0	300	3.9818
No log	76.0	304	3.9013
No log	77.0	308	4.0030
No log	78.0	312	3.8596
No log	79.0	316	3.9778
No log	80.0	320	3.8843
No log	81.0	324	3.9264
No log	82.0	328	3.8552
No log	83.0	332	3.9048
No log	84.0	336	4.0706
No log	85.0	340	4.2214
No log	86.0	344	4.1661
No log	87.0	348	4.0337
No log	88.0	352	3.9430
No log	89.0	356	3.9684
No log	90.0	360	4.0809
No log	91.0	364	4.0568
No log	92.0	368	3.9827
No log	93.0	372	4.1511
No log	94.0	376	4.1450
No log	95.0	380	4.1175
No log	96.0	384	4.2006
No log	97.0	388	3.9752
No log	98.0	392	4.0454
No log	99.0	396	4.2443
No log	100.0	400	4.2779
No log	101.0	404	4.2538
No log	102.0	408	4.1353
No log	103.0	412	3.9408
No log	104.0	416	4.0144
No log	105.0	420	4.0951
No log	106.0	424	4.0865
No log	107.0	428	4.0719
No log	108.0	432	4.1023
No log	109.0	436	4.2087
No log	110.0	440	4.2839
No log	111.0	444	4.2652
No log	112.0	448	4.1606
No log	113.0	452	4.1005
No log	114.0	456	3.9858
No log	115.0	460	3.9611
No log	116.0	464	3.9378
No log	117.0	468	3.9768
No log	118.0	472	4.0587
No log	119.0	476	4.1282
No log	120.0	480	4.2870
No log	121.0	484	4.4031
No log	122.0	488	4.3375
No log	123.0	492	4.3448
No log	124.0	496	4.3315
0.9733	125.0	500	4.3195
0.9733	126.0	504	4.2897
0.9733	127.0	508	4.2792
0.9733	128.0	512	4.2421
0.9733	129.0	516	4.2482
0.9733	130.0	520	4.2262
0.9733	131.0	524	4.2123
0.9733	132.0	528	4.3406
0.9733	133.0	532	4.4297
0.9733	134.0	536	4.3609
0.9733	135.0	540	4.3984
0.9733	136.0	544	4.3983
0.9733	137.0	548	4.2838
0.9733	138.0	552	4.2928
0.9733	139.0	556	4.5066
0.9733	140.0	560	4.4615
0.9733	141.0	564	4.3652
0.9733	142.0	568	4.2916
0.9733	143.0	572	4.3113
0.9733	144.0	576	4.3665
0.9733	145.0	580	4.4276
0.9733	146.0	584	4.4424
0.9733	147.0	588	4.3451
0.9733	148.0	592	4.2873
0.9733	149.0	596	4.5468
0.9733	150.0	600	4.2870
0.9733	151.0	604	4.3809
0.9733	152.0	608	4.3749
0.9733	153.0	612	4.3765
0.9733	154.0	616	4.5222
0.9733	155.0	620	4.5564
0.9733	156.0	624	4.5331
0.9733	157.0	628	4.4896
0.9733	158.0	632	4.5695
0.9733	159.0	636	4.6037
0.9733	160.0	640	4.5562
0.9733	161.0	644	4.4604
0.9733	162.0	648	4.4429
0.9733	163.0	652	4.4885
0.9733	164.0	656	4.4393
0.9733	165.0	660	4.4089
0.9733	166.0	664	4.3417
0.9733	167.0	668	4.3700
0.9733	168.0	672	4.4799
0.9733	169.0	676	4.5491
0.9733	170.0	680	4.5392
0.9733	171.0	684	4.5612
0.9733	172.0	688	4.5585
0.9733	173.0	692	4.4628
0.9733	174.0	696	4.4139
0.9733	175.0	700	4.3983
0.9733	176.0	704	4.4730
0.9733	177.0	708	4.6430
0.9733	178.0	712	4.6935
0.9733	179.0	716	4.6830
0.9733	180.0	720	4.5862
0.9733	181.0	724	4.5714
0.9733	182.0	728	4.6126
0.9733	183.0	732	4.6645
0.9733	184.0	736	4.5883
0.9733	185.0	740	4.4737
0.9733	186.0	744	4.5620
0.9733	187.0	748	4.5745
0.9733	188.0	752	4.4853
0.9733	189.0	756	4.4044
0.9733	190.0	760	4.3280
0.9733	191.0	764	4.2970
0.9733	192.0	768	4.4379
0.9733	193.0	772	4.6276
0.9733	194.0	776	4.5577
0.9733	195.0	780	4.5110
0.9733	196.0	784	4.5292
0.9733	197.0	788	4.5340
0.9733	198.0	792	4.5680
0.9733	199.0	796	4.6000
0.9733	200.0	800	4.6681
0.9733	201.0	804	4.7434
0.9733	202.0	808	4.7533
0.9733	203.0	812	4.6744
0.9733	204.0	816	4.4846
0.9733	205.0	820	4.3907
0.9733	206.0	824	4.3803
0.9733	207.0	828	4.4896
0.9733	208.0	832	4.6414
0.9733	209.0	836	4.6912
0.9733	210.0	840	4.6613
0.9733	211.0	844	4.4985
0.9733	212.0	848	4.4101
0.9733	213.0	852	4.4544
0.9733	214.0	856	4.5422
0.9733	215.0	860	4.5933
0.9733	216.0	864	4.6756
0.9733	217.0	868	4.8066
0.9733	218.0	872	4.9017
0.9733	219.0	876	4.8989
0.9733	220.0	880	4.9589
0.9733	221.0	884	4.9592
0.9733	222.0	888	4.8638
0.9733	223.0	892	4.9024
0.9733	224.0	896	4.9606
0.9733	225.0	900	4.9516
0.9733	226.0	904	4.8659
0.9733	227.0	908	4.8707
0.9733	228.0	912	4.9110
0.9733	229.0	916	4.9822
0.9733	230.0	920	4.9834
0.9733	231.0	924	4.9321
0.9733	232.0	928	4.8442
0.9733	233.0	932	4.8059
0.9733	234.0	936	4.8435
0.9733	235.0	940	4.9005
0.9733	236.0	944	4.9396
0.9733	237.0	948	4.9574
0.9733	238.0	952	4.9253
0.9733	239.0	956	4.8477
0.9733	240.0	960	4.7434
0.9733	241.0	964	4.6672
0.9733	242.0	968	4.6263
0.9733	243.0	972	4.5984
0.9733	244.0	976	4.6784
0.9733	245.0	980	4.7184
0.9733	246.0	984	4.7109
0.9733	247.0	988	4.6908
0.9733	248.0	992	4.7122
0.9733	249.0	996	4.7699
0.577	250.0	1000	4.8105
0.577	251.0	1004	4.7321
0.577	252.0	1008	4.7788
0.577	253.0	1012	4.7664
0.577	254.0	1016	4.7186
0.577	255.0	1020	4.6839
0.577	256.0	1024	4.7281
0.577	257.0	1028	4.7537
0.577	258.0	1032	4.7255
0.577	259.0	1036	4.7441
0.577	260.0	1040	4.7061
0.577	261.0	1044	4.6083
0.577	262.0	1048	4.5721
0.577	263.0	1052	4.6302
0.577	264.0	1056	4.7050
0.577	265.0	1060	4.7201
0.577	266.0	1064	4.6846
0.577	267.0	1068	4.6985
0.577	268.0	1072	4.7163
0.577	269.0	1076	4.6915
0.577	270.0	1080	4.6710
0.577	271.0	1084	4.6492
0.577	272.0	1088	4.6230
0.577	273.0	1092	4.5921
0.577	274.0	1096	4.5964
0.577	275.0	1100	4.6562
0.577	276.0	1104	4.7072
0.577	277.0	1108	4.7008
0.577	278.0	1112	4.6853
0.577	279.0	1116	4.6899
0.577	280.0	1120	4.6795
0.577	281.0	1124	4.6765
0.577	282.0	1128	4.6797
0.577	283.0	1132	4.7535
0.577	284.0	1136	4.7824
0.577	285.0	1140	4.7858
0.577	286.0	1144	4.7832
0.577	287.0	1148	4.7422
0.577	288.0	1152	4.6813
0.577	289.0	1156	4.7354
0.577	290.0	1160	4.8014
0.577	291.0	1164	4.7987
0.577	292.0	1168	4.7584
0.577	293.0	1172	4.7471
0.577	294.0	1176	4.7681
0.577	295.0	1180	4.6920
0.577	296.0	1184	4.6703
0.577	297.0	1188	4.8136
0.577	298.0	1192	4.9141
0.577	299.0	1196	4.9406
0.577	300.0	1200	4.7864
0.577	301.0	1204	4.5520
0.577	302.0	1208	4.4293
0.577	303.0	1212	4.4539
0.577	304.0	1216	4.5314
0.577	305.0	1220	4.5890
0.577	306.0	1224	4.6227
0.577	307.0	1228	4.6875
0.577	308.0	1232	4.7249
0.577	309.0	1236	4.7322
0.577	310.0	1240	4.7397
0.577	311.0	1244	4.7549
0.577	312.0	1248	4.6466
0.577	313.0	1252	4.5435
0.577	314.0	1256	4.4918
0.577	315.0	1260	4.4255
0.577	316.0	1264	4.4386
0.577	317.0	1268	4.5044
0.577	318.0	1272	4.5757
0.577	319.0	1276	4.5812
0.577	320.0	1280	4.5851
0.577	321.0	1284	4.6033
0.577	322.0	1288	4.5993
0.577	323.0	1292	4.5768
0.577	324.0	1296	4.5621
0.577	325.0	1300	4.5805
0.577	326.0	1304	4.6187
0.577	327.0	1308	4.6577
0.577	328.0	1312	4.6563
0.577	329.0	1316	4.6162
0.577	330.0	1320	4.6589
0.577	331.0	1324	4.7063
0.577	332.0	1328	4.6797
0.577	333.0	1332	4.6802
0.577	334.0	1336	4.7031
0.577	335.0	1340	4.7186
0.577	336.0	1344	4.6746
0.577	337.0	1348	4.6097
0.577	338.0	1352	4.5605
0.577	339.0	1356	4.5580
0.577	340.0	1360	4.6469
0.577	341.0	1364	4.6779
0.577	342.0	1368	4.6689
0.577	343.0	1372	4.5809
0.577	344.0	1376	4.5291
0.577	345.0	1380	4.5975
0.577	346.0	1384	4.6472
0.577	347.0	1388	4.6942
0.577	348.0	1392	4.7050
0.577	349.0	1396	4.6820
0.577	350.0	1400	4.7134
0.577	351.0	1404	4.7799
0.577	352.0	1408	4.7937
0.577	353.0	1412	4.7322
0.577	354.0	1416	4.6855
0.577	355.0	1420	4.6440
0.577	356.0	1424	4.6886
0.577	357.0	1428	4.7013
0.577	358.0	1432	4.6361
0.577	359.0	1436	4.5411
0.577	360.0	1440	4.4232
0.577	361.0	1444	4.4198
0.577	362.0	1448	4.4475
0.577	363.0	1452	4.4347
0.577	364.0	1456	4.4378
0.577	365.0	1460	4.4281
0.577	366.0	1464	4.4215
0.577	367.0	1468	4.4247
0.577	368.0	1472	4.4440
0.577	369.0	1476	4.4928
0.577	370.0	1480	4.5404
0.577	371.0	1484	4.5708
0.577	372.0	1488	4.6013
0.577	373.0	1492	4.5348
0.577	374.0	1496	4.4869
0.5739	375.0	1500	4.4752
0.5739	376.0	1504	4.4353
0.5739	377.0	1508	4.4553
0.5739	378.0	1512	4.5842
0.5739	379.0	1516	4.5905
0.5739	380.0	1520	4.6228
0.5739	381.0	1524	4.6348
0.5739	382.0	1528	4.6295
0.5739	383.0	1532	4.6087
0.5739	384.0	1536	4.5743
0.5739	385.0	1540	4.5627
0.5739	386.0	1544	4.6751
0.5739	387.0	1548	4.7205
0.5739	388.0	1552	4.7259
0.5739	389.0	1556	4.6987
0.5739	390.0	1560	4.6607
0.5739	391.0	1564	4.6240
0.5739	392.0	1568	4.6189
0.5739	393.0	1572	4.6322
0.5739	394.0	1576	4.6959
0.5739	395.0	1580	4.8216
0.5739	396.0	1584	4.8674
0.5739	397.0	1588	4.8670
0.5739	398.0	1592	4.8802
0.5739	399.0	1596	4.8637
0.5739	400.0	1600	4.9058
0.5739	401.0	1604	4.9272
0.5739	402.0	1608	4.8673
0.5739	403.0	1612	4.8409
0.5739	404.0	1616	4.8568
0.5739	405.0	1620	4.8657
0.5739	406.0	1624	4.8959
0.5739	407.0	1628	4.9302
0.5739	408.0	1632	4.8637
0.5739	409.0	1636	4.8191
0.5739	410.0	1640	4.7846
0.5739	411.0	1644	4.7605
0.5739	412.0	1648	4.7158
0.5739	413.0	1652	4.6502
0.5739	414.0	1656	4.6192
0.5739	415.0	1660	4.6413
0.5739	416.0	1664	4.6479
0.5739	417.0	1668	4.6460
0.5739	418.0	1672	4.6255
0.5739	419.0	1676	4.6512
0.5739	420.0	1680	4.7034
0.5739	421.0	1684	4.7127
0.5739	422.0	1688	4.6560
0.5739	423.0	1692	4.6141
0.5739	424.0	1696	4.5415
0.5739	425.0	1700	4.4629
0.5739	426.0	1704	4.4071
0.5739	427.0	1708	4.5795
0.5739	428.0	1712	4.6696
0.5739	429.0	1716	4.6674
0.5739	430.0	1720	4.6385
0.5739	431.0	1724	4.5972
0.5739	432.0	1728	4.5892
0.5739	433.0	1732	4.6200
0.5739	434.0	1736	4.8678
0.5739	435.0	1740	4.8369
0.5739	436.0	1744	4.7758
0.5739	437.0	1748	4.6869
0.5739	438.0	1752	4.5748
0.5739	439.0	1756	4.5290
0.5739	440.0	1760	4.4868
0.5739	441.0	1764	4.5006
0.5739	442.0	1768	4.5280
0.5739	443.0	1772	4.5572
0.5739	444.0	1776	4.5311
0.5739	445.0	1780	4.5205
0.5739	446.0	1784	4.5789
0.5739	447.0	1788	4.6828
0.5739	448.0	1792	4.7170
0.5739	449.0	1796	4.7070
0.5739	450.0	1800	4.6626
0.5739	451.0	1804	4.6244
0.5739	452.0	1808	4.6144
0.5739	453.0	1812	4.5767
0.5739	454.0	1816	4.5577
0.5739	455.0	1820	4.5127
0.5739	456.0	1824	4.4690
0.5739	457.0	1828	4.5020
0.5739	458.0	1832	4.5846
0.5739	459.0	1836	4.6244
0.5739	460.0	1840	4.6500
0.5739	461.0	1844	4.7259
0.5739	462.0	1848	4.8255
0.5739	463.0	1852	4.8126
0.5739	464.0	1856	4.6967
0.5739	465.0	1860	4.6631
0.5739	466.0	1864	4.6783
0.5739	467.0	1868	4.6725
0.5739	468.0	1872	4.6868
0.5739	469.0	1876	4.7040
0.5739	470.0	1880	4.7162
0.5739	471.0	1884	4.7499
0.5739	472.0	1888	4.8164
0.5739	473.0	1892	4.9572
0.5739	474.0	1896	5.0608
0.5739	475.0	1900	4.9154
0.5739	476.0	1904	4.8342
0.5739	477.0	1908	4.7712
0.5739	478.0	1912	4.7491
0.5739	479.0	1916	4.7203
0.5739	480.0	1920	4.6996
0.5739	481.0	1924	4.7895
0.5739	482.0	1928	4.7967
0.5739	483.0	1932	4.7828
0.5739	484.0	1936	4.8152
0.5739	485.0	1940	4.8264
0.5739	486.0	1944	4.7713
0.5739	487.0	1948	4.7377
0.5739	488.0	1952	4.7615
0.5739	489.0	1956	4.7894
0.5739	490.0	1960	4.8035
0.5739	491.0	1964	4.7815
0.5739	492.0	1968	4.7387
0.5739	493.0	1972	4.6920
0.5739	494.0	1976	4.6554
0.5739	495.0	1980	4.6914
0.5739	496.0	1984	4.7082
0.5739	497.0	1988	4.7152
0.5739	498.0	1992	4.7713
0.5739	499.0	1996	4.8209
0.5709	500.0	2000	4.7627
0.5709	501.0	2004	4.7031
0.5709	502.0	2008	4.6865
0.5709	503.0	2012	4.7169
0.5709	504.0	2016	4.8232
0.5709	505.0	2020	4.8669
0.5709	506.0	2024	4.8781
0.5709	507.0	2028	4.8486
0.5709	508.0	2032	4.8299
0.5709	509.0	2036	4.8279
0.5709	510.0	2040	4.8429
0.5709	511.0	2044	4.8281
0.5709	512.0	2048	4.7986
0.5709	513.0	2052	4.7286
0.5709	514.0	2056	4.6322
0.5709	515.0	2060	4.5916
0.5709	516.0	2064	4.5476
0.5709	517.0	2068	4.5146
0.5709	518.0	2072	4.5321
0.5709	519.0	2076	4.5867
0.5709	520.0	2080	4.6954
0.5709	521.0	2084	4.8335
0.5709	522.0	2088	4.8957
0.5709	523.0	2092	4.8813
0.5709	524.0	2096	4.8347
0.5709	525.0	2100	4.7978
0.5709	526.0	2104	4.7563
0.5709	527.0	2108	4.6921
0.5709	528.0	2112	4.6450
0.5709	529.0	2116	4.6596
0.5709	530.0	2120	4.7358
0.5709	531.0	2124	4.9031
0.5709	532.0	2128	5.0239
0.5709	533.0	2132	4.9160
0.5709	534.0	2136	4.8329
0.5709	535.0	2140	4.7997
0.5709	536.0	2144	4.8154
0.5709	537.0	2148	4.8268
0.5709	538.0	2152	4.7946
0.5709	539.0	2156	4.7542
0.5709	540.0	2160	4.7001
0.5709	541.0	2164	4.6652
0.5709	542.0	2168	4.6335
0.5709	543.0	2172	4.6183
0.5709	544.0	2176	4.6223
0.5709	545.0	2180	4.6376
0.5709	546.0	2184	4.6704
0.5709	547.0	2188	4.7008
0.5709	548.0	2192	4.6985
0.5709	549.0	2196	4.7083
0.5709	550.0	2200	4.7104
0.5709	551.0	2204	4.7251
0.5709	552.0	2208	4.7268
0.5709	553.0	2212	4.7190
0.5709	554.0	2216	4.7111
0.5709	555.0	2220	4.6991
0.5709	556.0	2224	4.7086
0.5709	557.0	2228	4.7145
0.5709	558.0	2232	4.7019
0.5709	559.0	2236	4.6923
0.5709	560.0	2240	4.6930
0.5709	561.0	2244	4.6898
0.5709	562.0	2248	4.6807
0.5709	563.0	2252	4.6610
0.5709	564.0	2256	4.6576
0.5709	565.0	2260	4.6404
0.5709	566.0	2264	4.6293
0.5709	567.0	2268	4.6177
0.5709	568.0	2272	4.6257
0.5709	569.0	2276	4.6420
0.5709	570.0	2280	4.6645
0.5709	571.0	2284	4.7087
0.5709	572.0	2288	4.7545
0.5709	573.0	2292	4.7645
0.5709	574.0	2296	4.7646
0.5709	575.0	2300	4.7536
0.5709	576.0	2304	4.7343
0.5709	577.0	2308	4.7281
0.5709	578.0	2312	4.7296
0.5709	579.0	2316	4.7406
0.5709	580.0	2320	4.7361
0.5709	581.0	2324	4.7266
0.5709	582.0	2328	4.7185
0.5709	583.0	2332	4.7251
0.5709	584.0	2336	4.6865
0.5709	585.0	2340	4.6572
0.5709	586.0	2344	4.6305
0.5709	587.0	2348	4.6360
0.5709	588.0	2352	4.6530
0.5709	589.0	2356	4.6291
0.5709	590.0	2360	4.6116
0.5709	591.0	2364	4.5997
0.5709	592.0	2368	4.5756
0.5709	593.0	2372	4.6193
0.5709	594.0	2376	4.6599
0.5709	595.0	2380	4.6867
0.5709	596.0	2384	4.7336
0.5709	597.0	2388	4.8040
0.5709	598.0	2392	4.8246
0.5709	599.0	2396	4.8215
0.5709	600.0	2400	4.8174
0.5709	601.0	2404	4.7797
0.5709	602.0	2408	4.7372
0.5709	603.0	2412	4.6813
0.5709	604.0	2416	4.6542
0.5709	605.0	2420	4.6479
0.5709	606.0	2424	4.6485
0.5709	607.0	2428	4.6755
0.5709	608.0	2432	4.6901
0.5709	609.0	2436	4.6706
0.5709	610.0	2440	4.6922
0.5709	611.0	2444	4.7344
0.5709	612.0	2448	4.7258
0.5709	613.0	2452	4.7182
0.5709	614.0	2456	4.7303
0.5709	615.0	2460	4.7555
0.5709	616.0	2464	4.7707
0.5709	617.0	2468	4.7515
0.5709	618.0	2472	4.7458
0.5709	619.0	2476	4.7445
0.5709	620.0	2480	4.7724
0.5709	621.0	2484	4.8123
0.5709	622.0	2488	4.8101
0.5709	623.0	2492	4.7760
0.5709	624.0	2496	4.7299
0.5723	625.0	2500	4.6696
0.5723	626.0	2504	4.6250
0.5723	627.0	2508	4.6113
0.5723	628.0	2512	4.6396
0.5723	629.0	2516	4.6281
0.5723	630.0	2520	4.6477
0.5723	631.0	2524	4.6302
0.5723	632.0	2528	4.5830
0.5723	633.0	2532	4.5698
0.5723	634.0	2536	4.6090
0.5723	635.0	2540	4.6613
0.5723	636.0	2544	4.7351
0.5723	637.0	2548	4.7877
0.5723	638.0	2552	4.7797
0.5723	639.0	2556	4.7533
0.5723	640.0	2560	4.7175
0.5723	641.0	2564	4.6598
0.5723	642.0	2568	4.6409
0.5723	643.0	2572	4.6083
0.5723	644.0	2576	4.5548
0.5723	645.0	2580	4.5234
0.5723	646.0	2584	4.5563
0.5723	647.0	2588	4.5378
0.5723	648.0	2592	4.5461
0.5723	649.0	2596	4.5503
0.5723	650.0	2600	4.5824
0.5723	651.0	2604	4.6385
0.5723	652.0	2608	4.6744
0.5723	653.0	2612	4.7002
0.5723	654.0	2616	4.7274
0.5723	655.0	2620	4.7525
0.5723	656.0	2624	4.7690
0.5723	657.0	2628	4.7471
0.5723	658.0	2632	4.7010
0.5723	659.0	2636	4.6737
0.5723	660.0	2640	4.6386
0.5723	661.0	2644	4.5908
0.5723	662.0	2648	4.5525
0.5723	663.0	2652	4.5443
0.5723	664.0	2656	4.6356
0.5723	665.0	2660	4.7524
0.5723	666.0	2664	4.8199
0.5723	667.0	2668	4.8506
0.5723	668.0	2672	4.8559
0.5723	669.0	2676	4.8541
0.5723	670.0	2680	4.8621
0.5723	671.0	2684	4.8630
0.5723	672.0	2688	4.8667
0.5723	673.0	2692	4.8635
0.5723	674.0	2696	4.8612
0.5723	675.0	2700	4.8482
0.5723	676.0	2704	4.8434
0.5723	677.0	2708	4.8007
0.5723	678.0	2712	4.7399
0.5723	679.0	2716	4.6966
0.5723	680.0	2720	4.7343
0.5723	681.0	2724	4.8523
0.5723	682.0	2728	4.9574
0.5723	683.0	2732	4.9729
0.5723	684.0	2736	4.9252
0.5723	685.0	2740	4.8899
0.5723	686.0	2744	4.8817
0.5723	687.0	2748	4.8816
0.5723	688.0	2752	4.8659
0.5723	689.0	2756	4.8126
0.5723	690.0	2760	4.7937
0.5723	691.0	2764	4.7670
0.5723	692.0	2768	4.7575
0.5723	693.0	2772	4.7593
0.5723	694.0	2776	4.7674
0.5723	695.0	2780	4.7875
0.5723	696.0	2784	4.7985
0.5723	697.0	2788	4.8212
0.5723	698.0	2792	4.8438
0.5723	699.0	2796	4.8526
0.5723	700.0	2800	4.8531
0.5723	701.0	2804	4.8454
0.5723	702.0	2808	4.8194
0.5723	703.0	2812	4.7941
0.5723	704.0	2816	4.7778
0.5723	705.0	2820	4.7688
0.5723	706.0	2824	4.7689
0.5723	707.0	2828	4.7691
0.5723	708.0	2832	4.7539
0.5723	709.0	2836	4.7403
0.5723	710.0	2840	4.7198
0.5723	711.0	2844	4.6670
0.5723	712.0	2848	4.6419
0.5723	713.0	2852	4.6627
0.5723	714.0	2856	4.6959
0.5723	715.0	2860	4.7410
0.5723	716.0	2864	4.8099
0.5723	717.0	2868	4.8738
0.5723	718.0	2872	4.8950
0.5723	719.0	2876	4.9208
0.5723	720.0	2880	4.9222
0.5723	721.0	2884	4.8998
0.5723	722.0	2888	4.8853
0.5723	723.0	2892	4.8587
0.5723	724.0	2896	4.8301
0.5723	725.0	2900	4.8083
0.5723	726.0	2904	4.7945
0.5723	727.0	2908	4.7884
0.5723	728.0	2912	4.7797
0.5723	729.0	2916	4.7929
0.5723	730.0	2920	4.7991
0.5723	731.0	2924	4.8011
0.5723	732.0	2928	4.8297
0.5723	733.0	2932	4.8795
0.5723	734.0	2936	4.9405
0.5723	735.0	2940	4.9608
0.5723	736.0	2944	4.9680
0.5723	737.0	2948	4.9683
0.5723	738.0	2952	4.9721
0.5723	739.0	2956	4.9668
0.5723	740.0	2960	4.9544
0.5723	741.0	2964	4.9360
0.5723	742.0	2968	4.9315
0.5723	743.0	2972	4.9497
0.5723	744.0	2976	4.9599
0.5723	745.0	2980	4.9827
0.5723	746.0	2984	4.9896
0.5723	747.0	2988	5.0273
0.5723	748.0	2992	5.0524
0.5723	749.0	2996	5.0389
0.5708	750.0	3000	5.0163
0.5708	751.0	3004	4.9961
0.5708	752.0	3008	4.9750
0.5708	753.0	3012	4.9448
0.5708	754.0	3016	4.9077
0.5708	755.0	3020	4.8762
0.5708	756.0	3024	4.8722
0.5708	757.0	3028	4.9045
0.5708	758.0	3032	4.9472
0.5708	759.0	3036	4.9857
0.5708	760.0	3040	4.9990
0.5708	761.0	3044	4.9888
0.5708	762.0	3048	4.9819
0.5708	763.0	3052	4.9808
0.5708	764.0	3056	4.9878
0.5708	765.0	3060	4.9815
0.5708	766.0	3064	4.9671
0.5708	767.0	3068	4.9589
0.5708	768.0	3072	4.9450
0.5708	769.0	3076	4.9100
0.5708	770.0	3080	4.8922
0.5708	771.0	3084	4.8088
0.5708	772.0	3088	4.8033
0.5708	773.0	3092	4.8108
0.5708	774.0	3096	4.8358
0.5708	775.0	3100	4.8521
0.5708	776.0	3104	4.8607
0.5708	777.0	3108	4.8612
0.5708	778.0	3112	4.8359
0.5708	779.0	3116	4.8302
0.5708	780.0	3120	4.8525
0.5708	781.0	3124	4.8766
0.5708	782.0	3128	4.9085
0.5708	783.0	3132	4.9360
0.5708	784.0	3136	4.9493
0.5708	785.0	3140	4.9478
0.5708	786.0	3144	4.9385
0.5708	787.0	3148	4.9239
0.5708	788.0	3152	4.9173
0.5708	789.0	3156	4.9275
0.5708	790.0	3160	4.9301
0.5708	791.0	3164	4.9312
0.5708	792.0	3168	4.9268
0.5708	793.0	3172	4.9264
0.5708	794.0	3176	4.9217
0.5708	795.0	3180	4.9157
0.5708	796.0	3184	4.9116
0.5708	797.0	3188	4.9167
0.5708	798.0	3192	4.9230
0.5708	799.0	3196	4.9246
0.5708	800.0	3200	4.9094
0.5708	801.0	3204	4.8857
0.5708	802.0	3208	4.8734
0.5708	803.0	3212	4.8783
0.5708	804.0	3216	4.8859
0.5708	805.0	3220	4.9010
0.5708	806.0	3224	4.9133
0.5708	807.0	3228	4.9292
0.5708	808.0	3232	4.9447
0.5708	809.0	3236	4.9535
0.5708	810.0	3240	4.9429
0.5708	811.0	3244	4.9352
0.5708	812.0	3248	4.9297
0.5708	813.0	3252	4.9364
0.5708	814.0	3256	4.9323
0.5708	815.0	3260	4.9199
0.5708	816.0	3264	4.9071
0.5708	817.0	3268	4.9013
0.5708	818.0	3272	4.9071
0.5708	819.0	3276	4.9027
0.5708	820.0	3280	4.8757
0.5708	821.0	3284	4.8450
0.5708	822.0	3288	4.8284
0.5708	823.0	3292	4.8178
0.5708	824.0	3296	4.8131
0.5708	825.0	3300	4.8232
0.5708	826.0	3304	4.8311
0.5708	827.0	3308	4.8254
0.5708	828.0	3312	4.8179
0.5708	829.0	3316	4.8184
0.5708	830.0	3320	4.8077
0.5708	831.0	3324	4.7956
0.5708	832.0	3328	4.7927
0.5708	833.0	3332	4.8152
0.5708	834.0	3336	4.8295
0.5708	835.0	3340	4.8388
0.5708	836.0	3344	4.8508
0.5708	837.0	3348	4.8763
0.5708	838.0	3352	4.8998
0.5708	839.0	3356	4.9319
0.5708	840.0	3360	4.9529
0.5708	841.0	3364	4.9653
0.5708	842.0	3368	4.9652
0.5708	843.0	3372	4.9567
0.5708	844.0	3376	4.9494
0.5708	845.0	3380	4.9376
0.5708	846.0	3384	4.9251
0.5708	847.0	3388	4.9129
0.5708	848.0	3392	4.8795
0.5708	849.0	3396	4.8646
0.5708	850.0	3400	4.8512
0.5708	851.0	3404	4.8363
0.5708	852.0	3408	4.8233
0.5708	853.0	3412	4.8179
0.5708	854.0	3416	4.8112
0.5708	855.0	3420	4.8090
0.5708	856.0	3424	4.8047
0.5708	857.0	3428	4.7930
0.5708	858.0	3432	4.7918
0.5708	859.0	3436	4.7954
0.5708	860.0	3440	4.8041
0.5708	861.0	3444	4.8215
0.5708	862.0	3448	4.8425
0.5708	863.0	3452	4.8537
0.5708	864.0	3456	4.8598
0.5708	865.0	3460	4.8520
0.5708	866.0	3464	4.8468
0.5708	867.0	3468	4.8405
0.5708	868.0	3472	4.8434
0.5708	869.0	3476	4.8412
0.5708	870.0	3480	4.8376
0.5708	871.0	3484	4.8309
0.5708	872.0	3488	4.8215
0.5708	873.0	3492	4.8096
0.5708	874.0	3496	4.7947
0.5573	875.0	3500	4.7860
0.5573	876.0	3504	4.7804
0.5573	877.0	3508	4.7728
0.5573	878.0	3512	4.7677
0.5573	879.0	3516	4.7593
0.5573	880.0	3520	4.7471
0.5573	881.0	3524	4.7474
0.5573	882.0	3528	4.7445
0.5573	883.0	3532	4.7488
0.5573	884.0	3536	4.7621
0.5573	885.0	3540	4.7701
0.5573	886.0	3544	4.7762
0.5573	887.0	3548	4.7806
0.5573	888.0	3552	4.7846
0.5573	889.0	3556	4.7889
0.5573	890.0	3560	4.7875
0.5573	891.0	3564	4.7860
0.5573	892.0	3568	4.7842
0.5573	893.0	3572	4.7821
0.5573	894.0	3576	4.7733
0.5573	895.0	3580	4.7696
0.5573	896.0	3584	4.7682
0.5573	897.0	3588	4.7673
0.5573	898.0	3592	4.7664
0.5573	899.0	3596	4.7571
0.5573	900.0	3600	4.7597
0.5573	901.0	3604	4.7560
0.5573	902.0	3608	4.7505
0.5573	903.0	3612	4.7487
0.5573	904.0	3616	4.7304
0.5573	905.0	3620	4.7117
0.5573	906.0	3624	4.6966
0.5573	907.0	3628	4.6814
0.5573	908.0	3632	4.6728
0.5573	909.0	3636	4.6685
0.5573	910.0	3640	4.6684
0.5573	911.0	3644	4.6715
0.5573	912.0	3648	4.6853
0.5573	913.0	3652	4.7031
0.5573	914.0	3656	4.7193
0.5573	915.0	3660	4.7263
0.5573	916.0	3664	4.7296
0.5573	917.0	3668	4.7284
0.5573	918.0	3672	4.7326
0.5573	919.0	3676	4.7443
0.5573	920.0	3680	4.7547
0.5573	921.0	3684	4.7583
0.5573	922.0	3688	4.7589
0.5573	923.0	3692	4.7598
0.5573	924.0	3696	4.7568
0.5573	925.0	3700	4.7553
0.5573	926.0	3704	4.7539
0.5573	927.0	3708	4.7699
0.5573	928.0	3712	4.7815
0.5573	929.0	3716	4.7888
0.5573	930.0	3720	4.7942
0.5573	931.0	3724	4.7978
0.5573	932.0	3728	4.7984
0.5573	933.0	3732	4.7985
0.5573	934.0	3736	4.7992
0.5573	935.0	3740	4.8031
0.5573	936.0	3744	4.8053
0.5573	937.0	3748	4.8059
0.5573	938.0	3752	4.8094
0.5573	939.0	3756	4.8141
0.5573	940.0	3760	4.8167
0.5573	941.0	3764	4.8085
0.5573	942.0	3768	4.8007
0.5573	943.0	3772	4.7946
0.5573	944.0	3776	4.7903
0.5573	945.0	3780	4.7868
0.5573	946.0	3784	4.7839
0.5573	947.0	3788	4.7820
0.5573	948.0	3792	4.7829
0.5573	949.0	3796	4.7830
0.5573	950.0	3800	4.7845
0.5573	951.0	3804	4.7857
0.5573	952.0	3808	4.7889
0.5573	953.0	3812	4.7889
0.5573	954.0	3816	4.7846
0.5573	955.0	3820	4.7809
0.5573	956.0	3824	4.7779
0.5573	957.0	3828	4.7801
0.5573	958.0	3832	4.7831
0.5573	959.0	3836	4.7846
0.5573	960.0	3840	4.7860
0.5573	961.0	3844	4.7853
0.5573	962.0	3848	4.7854
0.5573	963.0	3852	4.7860
0.5573	964.0	3856	4.7884
0.5573	965.0	3860	4.7893
0.5573	966.0	3864	4.7894
0.5573	967.0	3868	4.7918
0.5573	968.0	3872	4.7939
0.5573	969.0	3876	4.7958
0.5573	970.0	3880	4.7985
0.5573	971.0	3884	4.7999
0.5573	972.0	3888	4.8019
0.5573	973.0	3892	4.8037
0.5573	974.0	3896	4.8059
0.5573	975.0	3900	4.8067
0.5573	976.0	3904	4.8079
0.5573	977.0	3908	4.8097
0.5573	978.0	3912	4.8107
0.5573	979.0	3916	4.8117
0.5573	980.0	3920	4.8122
0.5573	981.0	3924	4.8111
0.5573	982.0	3928	4.8096
0.5573	983.0	3932	4.8071
0.5573	984.0	3936	4.8056
0.5573	985.0	3940	4.8024
0.5573	986.0	3944	4.8000
0.5573	987.0	3948	4.7983
0.5573	988.0	3952	4.7963
0.5573	989.0	3956	4.7942
0.5573	990.0	3960	4.7912
0.5573	991.0	3964	4.7896
0.5573	992.0	3968	4.7892
0.5573	993.0	3972	4.7886
0.5573	994.0	3976	4.7878
0.5573	995.0	3980	4.7871
0.5573	996.0	3984	4.7869
0.5573	997.0	3988	4.7869
0.5573	998.0	3992	4.7866
0.5573	999.0	3996	4.7862
0.5545	1000.0	4000	4.7861

Framework versions

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