explcre commited on
Commit
2047357
·
verified ·
1 Parent(s): 03e6995

Upload _reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t3_r128_alpha1_s3_par_20260507_005010/log.jsonl with huggingface_hub

Browse files
_reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t3_r128_alpha1_s3_par_20260507_005010/log.jsonl ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 1, "loss": -62.18814468383789, "mean_r": -0.6071428060531616, "max_r": -0.5, "mean_grounded": 2.25, "mean_halluc": 12.5, "mean_cited": 15.25, "mean_tf_grounded_rate": 0.1494047619047619, "gnorm": 410.549072265625, "elapsed_s": 48.56407928466797, "cell": "In", "id": "train:edit:In:SND1-IT1:chr7_127888347_127888847:1653"}
2
+ {"step": 5, "loss": -110.19990539550781, "mean_r": -0.6815476417541504, "max_r": -0.6166666746139526, "mean_grounded": 1.5, "mean_halluc": 16.25, "mean_cited": 18.25, "mean_tf_grounded_rate": 0.08630952380952381, "gnorm": 541.4973754882812, "elapsed_s": 191.61814737319946, "cell": "Ex", "id": "train:edit:Ex:MIR29B2CHG:chr1_207919721_207920221:1250"}
3
+ {"step": 10, "loss": 189.69204711914062, "mean_r": -0.8232972025871277, "max_r": -0.6352941393852234, "mean_grounded": 1.0, "mean_halluc": 8.25, "mean_cited": 9.5, "mean_tf_grounded_rate": 0.05572755417956656, "gnorm": 402.7617492675781, "elapsed_s": 367.0337257385254, "cell": "OPC", "id": "train:edit:OPC:GLCCI1:chr7_7870523_7871023:333"}
4
+ {"step": 15, "loss": -132.26309204101562, "mean_r": -0.3499999940395355, "max_r": 1.0, "mean_grounded": 0.5, "mean_halluc": 6.5, "mean_cited": 7.5, "mean_tf_grounded_rate": 0.26785714285714285, "gnorm": 273.3899841308594, "elapsed_s": 538.600282907486, "cell": "Mic", "id": "train:edit:Mic:EVA1B:chr1_36400002_36400502:3540"}
5
+ {"step": 20, "loss": -140.89944458007812, "mean_r": -0.25833332538604736, "max_r": 0.5, "mean_grounded": 2.0, "mean_halluc": 7.5, "mean_cited": 10.0, "mean_tf_grounded_rate": 0.2916666666666667, "gnorm": 347.7494812011719, "elapsed_s": 694.2420992851257, "cell": "Ast", "id": "train:edit:Ast:MAGOH:chr1_53305605_53306105:228"}
6
+ {"step": 25, "loss": -72.94137573242188, "mean_r": -0.7169949412345886, "max_r": -0.5600000023841858, "mean_grounded": 0.25, "mean_halluc": 13.0, "mean_cited": 14.75, "mean_tf_grounded_rate": 0.025, "gnorm": 502.339111328125, "elapsed_s": 874.3455336093903, "cell": "Oli", "id": "train:edit:Oli:ZFP36:chr19_39349210_39349710:653"}
7
+ {"step": 30, "loss": -26.32823944091797, "mean_r": -0.5035101175308228, "max_r": -0.1818181872367859, "mean_grounded": 1.75, "mean_halluc": 8.75, "mean_cited": 11.75, "mean_tf_grounded_rate": 0.15012626262626264, "gnorm": 437.66583251953125, "elapsed_s": 1052.7420649528503, "cell": "Mic", "id": "train:edit:Mic:CDH15:chr16_88977794_88978294:2991"}
8
+ {"step": 35, "loss": 93.8807601928711, "mean_r": -0.7846736907958984, "max_r": -0.6666666865348816, "mean_grounded": 1.0, "mean_halluc": 10.75, "mean_cited": 12.25, "mean_tf_grounded_rate": 0.06973581973581974, "gnorm": 400.18951416015625, "elapsed_s": 1229.797791481018, "cell": "In", "id": "train:edit:In:LRRC56:chr11_640216_640716:3357"}
9
+ {"step": 40, "loss": -175.54000854492188, "mean_r": -0.442307710647583, "max_r": 0.0, "mean_grounded": 1.75, "mean_halluc": 11.0, "mean_cited": 12.75, "mean_tf_grounded_rate": 0.11615384615384616, "gnorm": 377.7589416503906, "elapsed_s": 1414.281956911087, "cell": "Mic", "id": "train:edit:Mic:SIPA1:chr11_65652352_65652852:3382"}
10
+ {"step": 45, "loss": -76.31844329833984, "mean_r": -0.1133333295583725, "max_r": 0.06666667014360428, "mean_grounded": 0.5, "mean_halluc": 2.25, "mean_cited": 3.25, "mean_tf_grounded_rate": 0.10833333333333334, "gnorm": 432.98297119140625, "elapsed_s": 1591.3449778556824, "cell": "Ast", "id": "train:edit:Ast:SYN3:chr22_32843166_32843666:1656"}
11
+ {"step": 50, "loss": -85.02119445800781, "mean_r": -0.45192307233810425, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 3.25, "mean_cited": 3.5, "mean_tf_grounded_rate": 0.0, "gnorm": 240.878173828125, "elapsed_s": 1773.7889394760132, "cell": "Ex", "id": "train:edit:Ex:PSMD1:chr2_230924334_230924834:3881"}
12
+ {"step": 55, "loss": -95.26789855957031, "mean_r": -0.5940476059913635, "max_r": -0.2857142984867096, "mean_grounded": 1.0, "mean_halluc": 8.0, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.15178571428571427, "gnorm": 421.9581298828125, "elapsed_s": 1944.9084331989288, "cell": "Oli", "id": "train:edit:Oli:INPP5K:chr17_1648718_1649218:2894"}
13
+ {"step": 60, "loss": 87.06375122070312, "mean_r": -0.7466386556625366, "max_r": -0.5571428537368774, "mean_grounded": 0.5, "mean_halluc": 8.0, "mean_cited": 8.5, "mean_tf_grounded_rate": 0.06696428571428571, "gnorm": 389.80181884765625, "elapsed_s": 2113.1579599380493, "cell": "OPC", "id": "train:edit:OPC:AGPS:chr2_177628765_177629265:3135"}
14
+ {"step": 65, "loss": -187.80018615722656, "mean_r": -0.42097902297973633, "max_r": 0.0, "mean_grounded": 0.25, "mean_halluc": 6.25, "mean_cited": 6.5, "mean_tf_grounded_rate": 0.125, "gnorm": 367.68402099609375, "elapsed_s": 2292.572273492813, "cell": "In", "id": "train:edit:In:PLXNA4:chr7_132869181_132869681:2731"}
15
+ {"step": 70, "loss": -86.65145874023438, "mean_r": -0.6621212363243103, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 3.5, "mean_cited": 3.75, "mean_tf_grounded_rate": 0.0, "gnorm": 172.92315673828125, "elapsed_s": 2474.1830286979675, "cell": "Ex", "id": "train:edit:Ex:LRRN4CL:chr11_62936740_62937240:643"}
16
+ {"step": 75, "loss": -72.8033218383789, "mean_r": 0.18611112236976624, "max_r": 1.2000000476837158, "mean_grounded": 1.5, "mean_halluc": 2.5, "mean_cited": 4.25, "mean_tf_grounded_rate": 0.3888888888888889, "gnorm": 278.49725341796875, "elapsed_s": 2648.636190891266, "cell": "Ex", "id": "train:edit:Ex:CKAP4:chr12_106125394_106125894:3365"}
17
+ {"step": 80, "loss": -191.45631408691406, "mean_r": -0.1815476268529892, "max_r": 0.10000000149011612, "mean_grounded": 0.75, "mean_halluc": 4.0, "mean_cited": 5.25, "mean_tf_grounded_rate": 0.19642857142857142, "gnorm": 511.4512634277344, "elapsed_s": 2828.817238330841, "cell": "OPC", "id": "train:edit:OPC:IL17RB:chr3_53796142_53796642:3987"}
18
+ {"step": 85, "loss": -157.27638244628906, "mean_r": -0.4334615468978882, "max_r": 0.0, "mean_grounded": 1.0, "mean_halluc": 9.0, "mean_cited": 10.75, "mean_tf_grounded_rate": 0.07596153846153847, "gnorm": 334.5196533203125, "elapsed_s": 3008.4655957221985, "cell": "Ex", "id": "train:edit:Ex:SV2C:chr5_76025055_76025555:612"}
19
+ {"step": 90, "loss": -147.7225341796875, "mean_r": -0.5180357098579407, "max_r": 0.0, "mean_grounded": 1.0, "mean_halluc": 8.5, "mean_cited": 10.0, "mean_tf_grounded_rate": 0.07410714285714286, "gnorm": 270.45025634765625, "elapsed_s": 3189.0442271232605, "cell": "Mic", "id": "train:edit:Mic:ATP6V1A:chr3_113670476_113670976:86"}
20
+ {"step": 95, "loss": -115.96092224121094, "mean_r": -0.4084848463535309, "max_r": 0.0, "mean_grounded": 1.5, "mean_halluc": 7.5, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.23257575757575757, "gnorm": 385.920166015625, "elapsed_s": 3374.4554331302643, "cell": "Oli", "id": "train:edit:Oli:CCSAP:chr1_229299177_229299677:1845"}
21
+ {"step": 100, "loss": -109.0660400390625, "mean_r": -0.4513157904148102, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 4.75, "mean_cited": 5.0, "mean_tf_grounded_rate": 0.0, "gnorm": 226.89288330078125, "elapsed_s": 3560.6195211410522, "cell": "Mic", "id": "train:edit:Mic:STRIP1:chr1_109784397_109784897:2541"}
22
+ {"step": 105, "loss": 5.509817123413086, "mean_r": 0.3125, "max_r": 1.0, "mean_grounded": 1.75, "mean_halluc": 0.75, "mean_cited": 2.5, "mean_tf_grounded_rate": 0.40625, "gnorm": 229.69290161132812, "elapsed_s": 3745.8083510398865, "cell": "Mic", "id": "train:edit:Mic:DDX41:chr5_177405804_177406304:2125"}
23
+ {"step": 110, "loss": -80.55997467041016, "mean_r": -0.1568181812763214, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 2.25, "mean_cited": 3.0, "mean_tf_grounded_rate": 0.0, "gnorm": 377.13580322265625, "elapsed_s": 3929.3624584674835, "cell": "Mic", "id": "train:edit:Mic:LRPAP1:chr4_3392377_3392877:2860"}
24
+ {"step": 115, "loss": 36.671470642089844, "mean_r": -0.6603858470916748, "max_r": -0.5, "mean_grounded": 1.75, "mean_halluc": 17.0, "mean_cited": 19.0, "mean_tf_grounded_rate": 0.10758928571428572, "gnorm": 464.3946838378906, "elapsed_s": 4112.552114009857, "cell": "Ast", "id": "train:edit:Ast:PIK3CA:chr3_179345867_179346367:1010"}
25
+ {"step": 120, "loss": -126.66165161132812, "mean_r": -0.30119049549102783, "max_r": 0.0, "mean_grounded": 0.25, "mean_halluc": 4.0, "mean_cited": 4.75, "mean_tf_grounded_rate": 0.020833333333333332, "gnorm": 384.6724548339844, "elapsed_s": 4298.016083478928, "cell": "Ast", "id": "train:edit:Ast:EPCAM-DT:chr2_47391631_47392131:1985"}
26
+ {"step": 125, "loss": 81.58678436279297, "mean_r": -0.44826841354370117, "max_r": -0.2454545497894287, "mean_grounded": 2.25, "mean_halluc": 7.75, "mean_cited": 10.5, "mean_tf_grounded_rate": 0.22005772005772006, "gnorm": 382.5301513671875, "elapsed_s": 4489.5602169036865, "cell": "Ex", "id": "train:edit:Ex:CNTN4-AS2:chr3_2327545_2328045:504"}
27
+ {"step": 130, "loss": -97.35746765136719, "mean_r": -0.23000000417232513, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 3.75, "mean_cited": 3.75, "mean_tf_grounded_rate": 0.0, "gnorm": 294.1395263671875, "elapsed_s": 4680.179282903671, "cell": "OPC", "id": "train:edit:OPC:ZNF502:chr3_44476289_44476789:1834"}
28
+ {"step": 135, "loss": -110.84915924072266, "mean_r": -0.04444444179534912, "max_r": 0.5, "mean_grounded": 0.75, "mean_halluc": 2.25, "mean_cited": 3.25, "mean_tf_grounded_rate": 0.1875, "gnorm": 398.39111328125, "elapsed_s": 4871.525849580765, "cell": "In", "id": "train:edit:In:NOP14:chr4_2834473_2834973:99"}
29
+ {"step": 140, "loss": -101.678955078125, "mean_r": -0.17023809254169464, "max_r": 0.0833333358168602, "mean_grounded": 2.0, "mean_halluc": 5.75, "mean_cited": 8.5, "mean_tf_grounded_rate": 0.19791666666666669, "gnorm": 475.77886962890625, "elapsed_s": 5063.330948114395, "cell": "OPC", "id": "train:edit:OPC:DEDD2:chr19_42244624_42245124:4082"}
30
+ {"step": 145, "loss": 0.0, "mean_r": 0.0, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.0, "mean_cited": 0.0, "mean_tf_grounded_rate": 0.0, "gnorm": 0.0, "elapsed_s": 5254.912788152695, "cell": "Oli", "id": "train:edit:Oli:KIF2C:chr1_44660824_44661324:2156"}
31
+ {"step": 150, "loss": -171.71832275390625, "mean_r": -0.5221154093742371, "max_r": 0.0, "mean_grounded": 1.25, "mean_halluc": 9.5, "mean_cited": 10.75, "mean_tf_grounded_rate": 0.06944444444444445, "gnorm": 360.0874938964844, "elapsed_s": 5441.150552749634, "cell": "Ex", "id": "train:edit:Ex:CEP85:chr1_26016496_26016996:503"}
32
+ {"step": 155, "loss": 84.17100524902344, "mean_r": -0.7821428775787354, "max_r": -0.12857143580913544, "mean_grounded": 1.5, "mean_halluc": 4.0, "mean_cited": 5.5, "mean_tf_grounded_rate": 0.10714285714285714, "gnorm": 330.9013366699219, "elapsed_s": 5630.904017925262, "cell": "Mic", "id": "train:edit:Mic:MYO7B:chr2_127390933_127391433:1686"}
33
+ {"step": 160, "loss": 25.723966598510742, "mean_r": 0.1785714328289032, "max_r": 0.7142857313156128, "mean_grounded": 1.5, "mean_halluc": 0.25, "mean_cited": 1.75, "mean_tf_grounded_rate": 0.21428571428571427, "gnorm": 212.44644165039062, "elapsed_s": 5820.547861814499, "cell": "Oli", "id": "train:edit:Oli:ZNF839:chr14_102191452_102191952:1198"}
34
+ {"step": 165, "loss": -28.028940200805664, "mean_r": -0.25, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.25, "mean_cited": 0.25, "mean_tf_grounded_rate": 0.0, "gnorm": 167.03233337402344, "elapsed_s": 6009.097616434097, "cell": "Oli", "id": "train:edit:Oli:RAB36:chr22_23282738_23283238:73"}
35
+ {"step": 170, "loss": -107.42401885986328, "mean_r": -0.11818181723356247, "max_r": 0.4000000059604645, "mean_grounded": 0.5, "mean_halluc": 2.75, "mean_cited": 3.5, "mean_tf_grounded_rate": 0.16666666666666666, "gnorm": 400.05987548828125, "elapsed_s": 6198.614594936371, "cell": "Oli", "id": "train:edit:Oli:PURB:chr7_44749709_44750209:2026"}
36
+ {"step": 175, "loss": -38.00294876098633, "mean_r": -0.0833333358168602, "max_r": 0.0, "mean_grounded": 0.5, "mean_halluc": 0.75, "mean_cited": 1.25, "mean_tf_grounded_rate": 0.20833333333333331, "gnorm": 237.77078247070312, "elapsed_s": 6389.940973997116, "cell": "OPC", "id": "train:edit:OPC:FSCN1:chr7_5686247_5686747:71"}
37
+ {"step": 180, "loss": -28.001291275024414, "mean_r": -0.05000000074505806, "max_r": 0.0, "mean_grounded": 0.5, "mean_halluc": 0.75, "mean_cited": 1.25, "mean_tf_grounded_rate": 0.1, "gnorm": 269.5014343261719, "elapsed_s": 6581.041960954666, "cell": "End", "id": "train:edit:End:CST3:chr20_23868939_23869439:1158"}
38
+ {"step": 185, "loss": -3.159186363220215, "mean_r": -0.2750000059604645, "max_r": 0.0, "mean_grounded": 0.5, "mean_halluc": 1.25, "mean_cited": 1.75, "mean_tf_grounded_rate": 0.1, "gnorm": 151.06671142578125, "elapsed_s": 6772.244442224503, "cell": "Mic", "id": "train:edit:Mic:RIOK1:chr6_7328290_7328790:488"}
39
+ {"step": 190, "loss": 30.844457626342773, "mean_r": 0.25, "max_r": 1.0, "mean_grounded": 1.0, "mean_halluc": 0.0, "mean_cited": 1.0, "mean_tf_grounded_rate": 0.25, "gnorm": 270.4340515136719, "elapsed_s": 6964.012972354889, "cell": "In", "id": "train:edit:In:MYL7:chr7_44067436_44067936:1241"}
40
+ {"step": 195, "loss": -139.40658569335938, "mean_r": -0.1607142835855484, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 1.5, "mean_cited": 1.75, "mean_tf_grounded_rate": 0.0, "gnorm": 427.5216979980469, "elapsed_s": 7155.078929185867, "cell": "In", "id": "train:edit:In:DLX6-AS1:chr7_97023543_97024043:3241"}
41
+ {"step": 200, "loss": -14.42874813079834, "mean_r": -0.5321428775787354, "max_r": 0.6000000238418579, "mean_grounded": 1.0, "mean_halluc": 2.25, "mean_cited": 3.5, "mean_tf_grounded_rate": 0.2, "gnorm": 172.74411010742188, "elapsed_s": 7346.427536725998, "cell": "Ast", "id": "train:edit:Ast:VCAN:chr5_83672574_83673074:2367"}
42
+ {"step": 205, "loss": 3.377377510070801, "mean_r": 0.25, "max_r": 1.0, "mean_grounded": 0.5, "mean_halluc": 0.25, "mean_cited": 0.75, "mean_tf_grounded_rate": 0.375, "gnorm": 143.4545440673828, "elapsed_s": 7537.494421005249, "cell": "Ast", "id": "train:edit:Ast:ZNF623:chr8_143800951_143801451:555"}
43
+ {"step": 210, "loss": 15.940664291381836, "mean_r": 0.25, "max_r": 1.0, "mean_grounded": 0.25, "mean_halluc": 0.0, "mean_cited": 0.25, "mean_tf_grounded_rate": 0.25, "gnorm": 208.8988494873047, "elapsed_s": 7728.778774738312, "cell": "Mic", "id": "train:edit:Mic:SPNS2:chr17_4540193_4540693:2519"}
44
+ {"step": 215, "loss": 16.685592651367188, "mean_r": 0.25, "max_r": 1.0, "mean_grounded": 0.5, "mean_halluc": 0.0, "mean_cited": 0.5, "mean_tf_grounded_rate": 0.25, "gnorm": 172.12362670898438, "elapsed_s": 7919.717823982239, "cell": "OPC", "id": "train:edit:OPC:CACNG4:chr17_67037162_67037662:194"}
45
+ {"step": 220, "loss": 0.0, "mean_r": 0.0, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.0, "mean_cited": 0.0, "mean_tf_grounded_rate": 0.0, "gnorm": 0.0, "elapsed_s": 8110.8125994205475, "cell": "Ex", "id": "train:edit:Ex:MTMR14:chr3_9695466_9695966:1251"}
46
+ {"step": 225, "loss": -34.14190673828125, "mean_r": -0.253104567527771, "max_r": 0.644444465637207, "mean_grounded": 2.5, "mean_halluc": 5.75, "mean_cited": 9.75, "mean_tf_grounded_rate": 0.23161764705882354, "gnorm": 279.35235595703125, "elapsed_s": 8301.501113891602, "cell": "OPC", "id": "train:edit:OPC:BEST3:chr12_69738518_69739018:3436"}
47
+ {"step": 230, "loss": 24.967952728271484, "mean_r": 0.1071428582072258, "max_r": 0.4285714328289032, "mean_grounded": 1.75, "mean_halluc": 1.0, "mean_cited": 3.0, "mean_tf_grounded_rate": 0.2785714285714286, "gnorm": 253.17576599121094, "elapsed_s": 8492.115145921707, "cell": "OPC", "id": "train:edit:OPC:PARD6B:chr20_50638318_50638818:3787"}
48
+ {"step": 235, "loss": 0.0, "mean_r": 0.0, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.0, "mean_cited": 0.0, "mean_tf_grounded_rate": 0.0, "gnorm": 0.0, "elapsed_s": 8683.170018196106, "cell": "Ex", "id": "train:edit:Ex:TRPC3:chr4_121785286_121785786:52"}
49
+ {"step": 240, "loss": -135.12905883789062, "mean_r": -0.19423076510429382, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 3.0, "mean_cited": 3.25, "mean_tf_grounded_rate": 0.0, "gnorm": 396.4239501953125, "elapsed_s": 8873.615556955338, "cell": "Oli", "id": "train:edit:Oli:HAT1:chr2_171724201_171724701:2033"}
50
+ {"step": 245, "loss": -53.132720947265625, "mean_r": 0.23157894611358643, "max_r": 1.0, "mean_grounded": 2.25, "mean_halluc": 2.5, "mean_cited": 5.25, "mean_tf_grounded_rate": 0.34210526315789475, "gnorm": 266.11883544921875, "elapsed_s": 9064.515143871307, "cell": "OPC", "id": "train:edit:OPC:HIST1H3D:chr6_26156896_26157396:3548"}
51
+ {"step": 250, "loss": -3.550837516784668, "mean_r": -0.5, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 0.5, "mean_cited": 0.5, "mean_tf_grounded_rate": 0.0, "gnorm": 106.78069305419922, "elapsed_s": 9255.234219312668, "cell": "In", "id": "train:edit:In:MSRB1:chr16_2175258_2175758:2619"}