explcre commited on
Commit
74384b5
·
verified ·
1 Parent(s): 2dc65e2

Upload _reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t1_r128_alpha1_s2_20260506_203542/log.jsonl with huggingface_hub

Browse files
_reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t1_r128_alpha1_s2_20260506_203542/log.jsonl ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 1, "loss": -5.218864440917969, "mean_r": -0.8065592050552368, "max_r": -0.5677419304847717, "mean_grounded": 3.25, "mean_halluc": 46.0, "mean_cited": 49.5, "mean_tf_grounded_rate": 0.07545392691534603, "gnorm": 422.7616271972656, "elapsed_s": 50.92622399330139, "cell": "Oli", "id": "train:gen:Oli:INCENP:chr11_61898377_61898877:2758"}
2
+ {"step": 5, "loss": 35.575927734375, "mean_r": -0.33550700545310974, "max_r": -0.11818181723356247, "mean_grounded": 5.0, "mean_halluc": 12.0, "mean_cited": 17.5, "mean_tf_grounded_rate": 0.2841783216783217, "gnorm": 475.6947937011719, "elapsed_s": 197.1946940422058, "cell": "OPC", "id": "train:gen:OPC:TFDP1:chr13_113421828_113422328:2143"}
3
+ {"step": 10, "loss": 84.15061950683594, "mean_r": -0.6828333139419556, "max_r": -0.3700000047683716, "mean_grounded": 2.25, "mean_halluc": 18.0, "mean_cited": 20.25, "mean_tf_grounded_rate": 0.12666666666666668, "gnorm": 434.95928955078125, "elapsed_s": 381.2034614086151, "cell": "OPC", "id": "train:gen:OPC:SOX1-OT:chr13_112062696_112063196:1950"}
4
+ {"step": 15, "loss": 33.464683532714844, "mean_r": -0.523809552192688, "max_r": -0.06666667014360428, "mean_grounded": 2.75, "mean_halluc": 8.5, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.22718253968253968, "gnorm": 220.08421325683594, "elapsed_s": 564.2862162590027, "cell": "Mic", "id": "train:gen:Mic:MLLT10:chr10_21710666_21711166:3866"}
5
+ {"step": 20, "loss": -30.4185848236084, "mean_r": -0.2574625015258789, "max_r": 0.20000000298023224, "mean_grounded": 5.0, "mean_halluc": 10.25, "mean_cited": 15.25, "mean_tf_grounded_rate": 0.3551868802440885, "gnorm": 316.0599365234375, "elapsed_s": 746.3882215023041, "cell": "Ast", "id": "train:gen:Ast:RDX:chr11_110092883_110093383:1458"}
6
+ {"step": 25, "loss": 158.39466857910156, "mean_r": -0.44681820273399353, "max_r": -0.06363636255264282, "mean_grounded": 2.5, "mean_halluc": 6.25, "mean_cited": 9.75, "mean_tf_grounded_rate": 0.19772727272727275, "gnorm": 347.6630859375, "elapsed_s": 931.1540968418121, "cell": "Oli", "id": "train:gen:Oli:FAAP20:chr1_2226476_2226976:2582"}
7
+ {"step": 30, "loss": -106.62429809570312, "mean_r": -0.24360445141792297, "max_r": 0.11999999731779099, "mean_grounded": 5.0, "mean_halluc": 12.75, "mean_cited": 18.5, "mean_tf_grounded_rate": 0.3175039872408294, "gnorm": 411.363037109375, "elapsed_s": 1110.058364391327, "cell": "OPC", "id": "train:gen:OPC:MDP1:chr14_24408760_24409260:3171"}
8
+ {"step": 35, "loss": -29.934234619140625, "mean_r": -0.6397569179534912, "max_r": -0.3777777850627899, "mean_grounded": 3.0, "mean_halluc": 22.0, "mean_cited": 25.0, "mean_tf_grounded_rate": 0.1539614898989899, "gnorm": 286.0727233886719, "elapsed_s": 1291.7536396980286, "cell": "Mic", "id": "train:gen:Mic:MAP10:chr1_232624826_232625326:426"}
9
+ {"step": 40, "loss": -98.45370483398438, "mean_r": -0.4814246892929077, "max_r": -0.23749999701976776, "mean_grounded": 3.0, "mean_halluc": 13.0, "mean_cited": 17.25, "mean_tf_grounded_rate": 0.17071040372670807, "gnorm": 468.7721862792969, "elapsed_s": 1469.2674129009247, "cell": "In", "id": "train:gen:In:RER1:chr1_2319391_2319891:1074"}
10
+ {"step": 45, "loss": 180.8311004638672, "mean_r": -0.641883134841919, "max_r": -0.4000000059604645, "mean_grounded": 3.0, "mean_halluc": 12.0, "mean_cited": 15.5, "mean_tf_grounded_rate": 0.13344155844155844, "gnorm": 374.6826171875, "elapsed_s": 1652.2075836658478, "cell": "Ast", "id": "train:gen:Ast:BICD1:chr12_32307923_32308423:3044"}
11
+ {"step": 50, "loss": -70.22618865966797, "mean_r": -0.5386034250259399, "max_r": 0.20000000298023224, "mean_grounded": 1.75, "mean_halluc": 11.0, "mean_cited": 12.75, "mean_tf_grounded_rate": 0.22526350461133068, "gnorm": 205.33738708496094, "elapsed_s": 1834.103666305542, "cell": "In", "id": "train:gen:In:NKAPD1:chr11_112016414_112016914:3491"}
12
+ {"step": 55, "loss": -6.240154266357422, "mean_r": -0.19053445756435394, "max_r": 0.20000000298023224, "mean_grounded": 6.0, "mean_halluc": 8.25, "mean_cited": 14.25, "mean_tf_grounded_rate": 0.40280969030969027, "gnorm": 197.09228515625, "elapsed_s": 2007.087559223175, "cell": "OPC", "id": "train:gen:OPC:NXPE1:chr11_114440471_114440971:2359"}
13
+ {"step": 60, "loss": -102.85977172851562, "mean_r": -0.16276738047599792, "max_r": 0.0, "mean_grounded": 3.25, "mean_halluc": 5.75, "mean_cited": 9.0, "mean_tf_grounded_rate": 0.25635026737967914, "gnorm": 378.9931640625, "elapsed_s": 2180.7611997127533, "cell": "Ex", "id": "train:gen:Ex:FAM91A1:chr8_123674873_123675373:3633"}
14
+ {"step": 65, "loss": -13.142425537109375, "mean_r": -0.3529924154281616, "max_r": 0.06666667014360428, "mean_grounded": 2.5, "mean_halluc": 7.5, "mean_cited": 10.25, "mean_tf_grounded_rate": 0.23712121212121212, "gnorm": 442.8056335449219, "elapsed_s": 2354.6300885677338, "cell": "OPC", "id": "train:gen:OPC:FNDC10:chr1_1434245_1434745:1004"}
15
+ {"step": 70, "loss": -91.81523132324219, "mean_r": 0.3107143044471741, "max_r": 0.6000000238418579, "mean_grounded": 6.5, "mean_halluc": 3.75, "mean_cited": 10.25, "mean_tf_grounded_rate": 0.65, "gnorm": 345.3846740722656, "elapsed_s": 2539.7534017562866, "cell": "Ast", "id": "train:gen:Ast:VDR:chr12_47753216_47753716:3446"}
16
+ {"step": 75, "loss": -89.78193664550781, "mean_r": -0.33416664600372314, "max_r": -0.1599999964237213, "mean_grounded": 3.25, "mean_halluc": 9.0, "mean_cited": 12.25, "mean_tf_grounded_rate": 0.29583333333333334, "gnorm": 516.70458984375, "elapsed_s": 2730.1963741779327, "cell": "Oli", "id": "train:gen:Oli:PRDM16:chr1_2921972_2922472:3117"}
17
+ {"step": 80, "loss": -48.4810791015625, "mean_r": -0.32083332538604736, "max_r": 0.05999999865889549, "mean_grounded": 2.5, "mean_halluc": 9.75, "mean_cited": 12.25, "mean_tf_grounded_rate": 0.20208333333333334, "gnorm": 188.87411499023438, "elapsed_s": 3037.6961925029755, "cell": "In", "id": "train:gen:In:ANAPC15:chr11_72333594_72334094:1224"}
18
+ {"step": 85, "loss": -134.23179626464844, "mean_r": 0.118956059217453, "max_r": 0.5714285969734192, "mean_grounded": 7.5, "mean_halluc": 6.25, "mean_cited": 13.75, "mean_tf_grounded_rate": 0.5412087912087912, "gnorm": 370.0169372558594, "elapsed_s": 3457.6802003383636, "cell": "Ex", "id": "train:gen:Ex:RALYL:chr8_84183538_84184038:608"}
19
+ {"step": 90, "loss": -58.688053131103516, "mean_r": 0.14166665077209473, "max_r": 0.7857142686843872, "mean_grounded": 6.25, "mean_halluc": 6.0, "mean_cited": 12.25, "mean_tf_grounded_rate": 0.5619047619047619, "gnorm": 198.3438262939453, "elapsed_s": 3867.5240049362183, "cell": "Ast", "id": "train:gen:Ast:MSANTD4:chr11_106020847_106021347:1309"}
20
+ {"step": 95, "loss": -28.600069046020508, "mean_r": 0.4145604372024536, "max_r": 0.800000011920929, "mean_grounded": 11.5, "mean_halluc": 4.75, "mean_cited": 16.25, "mean_tf_grounded_rate": 0.6983516483516483, "gnorm": 200.20529174804688, "elapsed_s": 4183.9363667964935, "cell": "Ex", "id": "train:gen:Ex:PCAT6:chr1_202614316_202614816:2209"}
21
+ {"step": 100, "loss": -6.653812408447266, "mean_r": 0.34126535058021545, "max_r": 0.4571428596973419, "mean_grounded": 10.0, "mean_halluc": 5.0, "mean_cited": 15.0, "mean_tf_grounded_rate": 0.6651381706528766, "gnorm": 272.1414489746094, "elapsed_s": 4491.195063829422, "cell": "Ex", "id": "train:gen:Ex:EDEM3:chr1_184694970_184695470:457"}
22
+ {"step": 105, "loss": -4.416484832763672, "mean_r": 0.238571435213089, "max_r": 0.5400000214576721, "mean_grounded": 5.25, "mean_halluc": 3.75, "mean_cited": 9.0, "mean_tf_grounded_rate": 0.5928571428571427, "gnorm": 227.85971069335938, "elapsed_s": 4798.530719995499, "cell": "In", "id": "train:gen:In:AKIP1:chr11_9029297_9029797:1589"}
23
+ {"step": 110, "loss": -166.10800170898438, "mean_r": -0.19857142865657806, "max_r": 0.0, "mean_grounded": 2.75, "mean_halluc": 6.25, "mean_cited": 9.0, "mean_tf_grounded_rate": 0.22976190476190472, "gnorm": 359.359130859375, "elapsed_s": 5097.406448602676, "cell": "OPC", "id": "train:gen:OPC:MMP17:chr12_131621804_131622304:3008"}
24
+ {"step": 115, "loss": -59.862239837646484, "mean_r": 0.6931372284889221, "max_r": 0.9904761910438538, "mean_grounded": 14.75, "mean_halluc": 3.25, "mean_cited": 18.25, "mean_tf_grounded_rate": 0.8070728291316527, "gnorm": 206.9934539794922, "elapsed_s": 5400.197008132935, "cell": "Ex", "id": "train:gen:Ex:FER1L6-AS1:chr8_124166147_124166647:3697"}
25
+ {"step": 120, "loss": -29.57158660888672, "mean_r": 0.15710341930389404, "max_r": 0.6545454263687134, "mean_grounded": 7.25, "mean_halluc": 6.25, "mean_cited": 13.5, "mean_tf_grounded_rate": 0.576278984173721, "gnorm": 204.1288604736328, "elapsed_s": 5580.342207193375, "cell": "In", "id": "train:gen:In:LINC01219:chr11_2152509_2153009:722"}
26
+ {"step": 125, "loss": -59.83890151977539, "mean_r": 0.3603261113166809, "max_r": 0.8500000238418579, "mean_grounded": 12.25, "mean_halluc": 6.0, "mean_cited": 18.25, "mean_tf_grounded_rate": 0.6663043478260869, "gnorm": 135.166015625, "elapsed_s": 5765.421758413315, "cell": "Oli", "id": "train:gen:Oli:ARID5B:chr10_62056193_62056693:2706"}
27
+ {"step": 130, "loss": -45.70667266845703, "mean_r": 0.0694444477558136, "max_r": 0.5555555820465088, "mean_grounded": 4.75, "mean_halluc": 4.25, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.5168650793650794, "gnorm": 225.0059356689453, "elapsed_s": 5953.515341520309, "cell": "Ex", "id": "train:gen:Ex:PRXL2B:chr1_2563406_2563906:2367"}
28
+ {"step": 135, "loss": -26.257949829101562, "mean_r": 0.4800282120704651, "max_r": 0.7714285850524902, "mean_grounded": 10.0, "mean_halluc": 4.0, "mean_cited": 14.0, "mean_tf_grounded_rate": 0.7266212406015038, "gnorm": 207.65029907226562, "elapsed_s": 6143.662634849548, "cell": "In", "id": "train:gen:In:CSTF3-DT:chr11_33387606_33388106:3076"}
29
+ {"step": 140, "loss": -25.037628173828125, "mean_r": 0.62882399559021, "max_r": 0.7142857313156128, "mean_grounded": 7.25, "mean_halluc": 2.0, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.7905483405483406, "gnorm": 159.41317749023438, "elapsed_s": 6323.759788751602, "cell": "Ast", "id": "train:gen:Ast:CCND2-AS1:chr12_4046409_4046909:430"}
30
+ {"step": 145, "loss": -76.65938568115234, "mean_r": 0.1548701375722885, "max_r": 0.800000011920929, "mean_grounded": 6.5, "mean_halluc": 3.0, "mean_cited": 9.5, "mean_tf_grounded_rate": 0.5626623376623376, "gnorm": 248.88922119140625, "elapsed_s": 6511.503359794617, "cell": "Mic", "id": "train:gen:Mic:LSP1:chr11_1851829_1852329:1078"}
31
+ {"step": 150, "loss": -20.26806640625, "mean_r": 0.08025389909744263, "max_r": 0.5555555820465088, "mean_grounded": 7.5, "mean_halluc": 6.25, "mean_cited": 14.25, "mean_tf_grounded_rate": 0.5086726998491704, "gnorm": 216.60049438476562, "elapsed_s": 6699.107643604279, "cell": "OPC", "id": "train:gen:OPC:CDKL1:chr14_50336234_50336734:3860"}
32
+ {"step": 155, "loss": -123.94859313964844, "mean_r": 0.397549033164978, "max_r": 0.6666666865348816, "mean_grounded": 13.75, "mean_halluc": 7.0, "mean_cited": 20.75, "mean_tf_grounded_rate": 0.6973039215686274, "gnorm": 316.9662780761719, "elapsed_s": 6885.9748384952545, "cell": "OPC", "id": "train:gen:OPC:AIP:chr11_67445480_67445980:92"}
33
+ {"step": 160, "loss": -136.35328674316406, "mean_r": 0.3647451102733612, "max_r": 1.0, "mean_grounded": 5.0, "mean_halluc": 7.25, "mean_cited": 12.25, "mean_tf_grounded_rate": 0.6453921568627451, "gnorm": 351.3057556152344, "elapsed_s": 7076.034197092056, "cell": "OPC", "id": "train:gen:OPC:CCND2-AS1:chr12_4294615_4295115:729"}
34
+ {"step": 165, "loss": -133.87208557128906, "mean_r": -0.2690476179122925, "max_r": 0.3333333432674408, "mean_grounded": 1.75, "mean_halluc": 9.75, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.3647186147186147, "gnorm": 294.1203918457031, "elapsed_s": 7266.722614765167, "cell": "OPC", "id": "train:gen:OPC:HSD17B6:chr12_56633380_56633880:2246"}
35
+ {"step": 170, "loss": -41.015316009521484, "mean_r": 0.5951923131942749, "max_r": 1.0, "mean_grounded": 11.25, "mean_halluc": 3.0, "mean_cited": 14.25, "mean_tf_grounded_rate": 0.7975961538461538, "gnorm": 208.5245361328125, "elapsed_s": 7454.8700358867645, "cell": "Ex", "id": "train:gen:Ex:SSU72:chr1_1574944_1575444:1413"}
36
+ {"step": 175, "loss": -33.95487594604492, "mean_r": 0.46638888120651245, "max_r": 1.0099999904632568, "mean_grounded": 10.25, "mean_halluc": 2.25, "mean_cited": 12.5, "mean_tf_grounded_rate": 0.7301587301587301, "gnorm": 194.21267700195312, "elapsed_s": 7643.874708175659, "cell": "OPC", "id": "train:gen:OPC:TGM1:chr14_24162777_24163277:3232"}
37
+ {"step": 180, "loss": -63.506446838378906, "mean_r": 0.37113097310066223, "max_r": 1.009523868560791, "mean_grounded": 11.25, "mean_halluc": 4.0, "mean_cited": 15.25, "mean_tf_grounded_rate": 0.684375, "gnorm": 198.28932189941406, "elapsed_s": 7828.621751308441, "cell": "Ex", "id": "train:gen:Ex:RABIF:chr1_202834735_202835235:2257"}
38
+ {"step": 185, "loss": -92.64372253417969, "mean_r": 0.12037036567926407, "max_r": 0.9481481313705444, "mean_grounded": 9.75, "mean_halluc": 5.0, "mean_cited": 15.0, "mean_tf_grounded_rate": 0.525462962962963, "gnorm": 308.61029052734375, "elapsed_s": 8016.06320643425, "cell": "In", "id": "train:gen:In:FBLIM1:chr1_15849912_15850412:3705"}
39
+ {"step": 190, "loss": -99.30598449707031, "mean_r": 0.2456521838903427, "max_r": 1.0, "mean_grounded": 7.0, "mean_halluc": 5.5, "mean_cited": 12.5, "mean_tf_grounded_rate": 0.6156832298136646, "gnorm": 256.8082275390625, "elapsed_s": 8198.107093334198, "cell": "OPC", "id": "train:gen:OPC:TNFRSF19:chr13_23427972_23428472:3552"}
40
+ {"step": 195, "loss": -164.28952026367188, "mean_r": -0.26777949929237366, "max_r": 0.0, "mean_grounded": 2.25, "mean_halluc": 8.0, "mean_cited": 10.5, "mean_tf_grounded_rate": 0.19228778467908902, "gnorm": 412.50604248046875, "elapsed_s": 8383.31619977951, "cell": "Ast", "id": "train:gen:Ast:PRDM16:chr1_3117463_3117963:1329"}
41
+ {"step": 200, "loss": -23.019786834716797, "mean_r": 0.8148897290229797, "max_r": 1.0, "mean_grounded": 12.25, "mean_halluc": 2.0, "mean_cited": 14.25, "mean_tf_grounded_rate": 0.8837826797385621, "gnorm": 213.93299865722656, "elapsed_s": 8573.556691169739, "cell": "In", "id": "train:gen:In:LTBP3:chr11_65526027_65526527:3162"}
42
+ {"step": 205, "loss": -93.08203125, "mean_r": 0.1210317462682724, "max_r": 0.4285714328289032, "mean_grounded": 5.25, "mean_halluc": 5.25, "mean_cited": 10.5, "mean_tf_grounded_rate": 0.5563492063492064, "gnorm": 245.73997497558594, "elapsed_s": 8762.976057767868, "cell": "In", "id": "train:gen:In:CRACR2B:chr11_872871_873371:111"}
43
+ {"step": 210, "loss": -41.811676025390625, "mean_r": 0.8170163631439209, "max_r": 1.0, "mean_grounded": 19.0, "mean_halluc": 1.75, "mean_cited": 20.75, "mean_tf_grounded_rate": 0.9085081585081586, "gnorm": 248.06434631347656, "elapsed_s": 8952.211522579193, "cell": "Mic", "id": "train:gen:Mic:PCBD1:chr10_70834385_70834885:3135"}
44
+ {"step": 215, "loss": -200.57615661621094, "mean_r": 0.23348316550254822, "max_r": 0.8333333134651184, "mean_grounded": 6.75, "mean_halluc": 5.5, "mean_cited": 12.5, "mean_tf_grounded_rate": 0.5677031302031302, "gnorm": 416.8918762207031, "elapsed_s": 9141.421489715576, "cell": "Ast", "id": "train:gen:Ast:BARX2:chr11_129319843_129320343:3966"}
45
+ {"step": 220, "loss": -116.13182067871094, "mean_r": 0.09318183362483978, "max_r": 1.2000000476837158, "mean_grounded": 2.5, "mean_halluc": 6.5, "mean_cited": 9.75, "mean_tf_grounded_rate": 0.4371212121212122, "gnorm": 358.8985900878906, "elapsed_s": 9326.476865768433, "cell": "Oli", "id": "train:gen:Oli:FAM241B:chr10_69486131_69486631:3045"}
46
+ {"step": 225, "loss": 3.94183349609375, "mean_r": 0.5118860006332397, "max_r": 0.6842105388641357, "mean_grounded": 11.5, "mean_halluc": 3.75, "mean_cited": 15.25, "mean_tf_grounded_rate": 0.7396929824561402, "gnorm": 237.57742309570312, "elapsed_s": 9515.546446084976, "cell": "Ex", "id": "train:gen:Ex:DPY19L4:chr8_94720064_94720564:1359"}
47
+ {"step": 230, "loss": -100.10344696044922, "mean_r": 0.27388888597488403, "max_r": 0.6666666865348816, "mean_grounded": 13.75, "mean_halluc": 8.25, "mean_cited": 22.0, "mean_tf_grounded_rate": 0.6319444444444444, "gnorm": 313.3280944824219, "elapsed_s": 9704.634086370468, "cell": "Mic", "id": "train:gen:Mic:DCLRE1C:chr10_15035215_15035715:3391"}
48
+ {"step": 235, "loss": -7.705142021179199, "mean_r": 0.9004464149475098, "max_r": 1.1142857074737549, "mean_grounded": 13.0, "mean_halluc": 1.0, "mean_cited": 14.0, "mean_tf_grounded_rate": 0.928125, "gnorm": 83.50918579101562, "elapsed_s": 9893.31168437004, "cell": "In", "id": "train:gen:In:NPPA:chr1_11651079_11651579:3283"}
49
+ {"step": 240, "loss": -144.74234008789062, "mean_r": 0.24625641107559204, "max_r": 1.0, "mean_grounded": 5.0, "mean_halluc": 6.0, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.5935897435897436, "gnorm": 319.5679931640625, "elapsed_s": 10081.004237174988, "cell": "OPC", "id": "train:gen:OPC:GCH1:chr14_54724729_54725229:247"}
50
+ {"step": 245, "loss": -112.56712341308594, "mean_r": 0.09038460999727249, "max_r": 1.0, "mean_grounded": 5.5, "mean_halluc": 6.75, "mean_cited": 12.25, "mean_tf_grounded_rate": 0.5269230769230768, "gnorm": 254.27627563476562, "elapsed_s": 10272.158127069473, "cell": "Ex", "id": "train:gen:Ex:PLEKHA6:chr1_204345034_204345534:3713"}
51
+ {"step": 250, "loss": -18.053068161010742, "mean_r": 0.9244444370269775, "max_r": 1.0199999809265137, "mean_grounded": 14.0, "mean_halluc": 0.75, "mean_cited": 14.75, "mean_tf_grounded_rate": 0.9409722222222222, "gnorm": 201.33538818359375, "elapsed_s": 10462.04444026947, "cell": "In", "id": "train:gen:In:FAM181B:chr11_82815377_82815877:2282"}