Upload _reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t2_r128_alpha1_s3_20260507_044835/log.jsonl with huggingface_hub
Browse files
_reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t2_r128_alpha1_s3_20260507_044835/log.jsonl
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"step": 1, "loss": 80.77110290527344, "mean_r": -0.8216667175292969, "max_r": -0.6000000238418579, "mean_grounded": 0.75, "mean_halluc": 12.5, "mean_cited": 13.25, "mean_tf_grounded_rate": 0.05512820512820513, "gnorm": 514.6940307617188, "elapsed_s": 50.28360629081726, "cell": "Oli", "id": "train:pair_pos:Oli:TIAL1:chr10_119693231_119693731:1131"}
|
| 2 |
+
{"step": 5, "loss": 83.90618133544922, "mean_r": -0.7913933992385864, "max_r": -0.21250000596046448, "mean_grounded": 1.5, "mean_halluc": 38.75, "mean_cited": 40.25, "mean_tf_grounded_rate": 0.09375, "gnorm": 438.9825134277344, "elapsed_s": 193.1581757068634, "cell": "Oli", "id": "train:pair_neg:Oli:WEE2:chr7_141688659_141689159:1151"}
|
| 3 |
+
{"step": 10, "loss": -33.547271728515625, "mean_r": -0.7238043546676636, "max_r": -0.6000000238418579, "mean_grounded": 1.0, "mean_halluc": 17.25, "mean_cited": 19.5, "mean_tf_grounded_rate": 0.04777777777777778, "gnorm": 572.7837524414062, "elapsed_s": 350.1274325847626, "cell": "Mic", "id": "train:pair_neg:Mic:TCIRG1:chr11_67789814_67790314:2378"}
|
| 4 |
+
{"step": 15, "loss": 24.332138061523438, "mean_r": -0.24336066842079163, "max_r": 0.23157894611358643, "mean_grounded": 6.0, "mean_halluc": 12.5, "mean_cited": 19.25, "mean_tf_grounded_rate": 0.3039815447710184, "gnorm": 508.61639404296875, "elapsed_s": 518.4939813613892, "cell": "Ast", "id": "train:pair_pos:Ast:ART1:chr11_3453735_3454235:1427"}
|
| 5 |
+
{"step": 20, "loss": 11.739974975585938, "mean_r": -0.7245604395866394, "max_r": -0.5153846144676208, "mean_grounded": 0.5, "mean_halluc": 22.25, "mean_cited": 23.25, "mean_tf_grounded_rate": 0.054945054945054944, "gnorm": 470.56658935546875, "elapsed_s": 692.2053468227386, "cell": "OPC", "id": "train:pair_pos:OPC:AGAP5:chr10_73624206_73624706:3961"}
|
| 6 |
+
{"step": 25, "loss": -141.90965270996094, "mean_r": 0.267800509929657, "max_r": 1.0, "mean_grounded": 4.5, "mean_halluc": 7.0, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.6219948849104859, "gnorm": 324.447509765625, "elapsed_s": 869.0430390834808, "cell": "Ast", "id": "train:pair_pos:Ast:ASRGL1:chr11_62569614_62570114:3624"}
|
| 7 |
+
{"step": 30, "loss": 110.59297943115234, "mean_r": -0.4477972090244293, "max_r": 0.11999999731779099, "mean_grounded": 2.0, "mean_halluc": 8.75, "mean_cited": 11.25, "mean_tf_grounded_rate": 0.19090909090909092, "gnorm": 475.6636657714844, "elapsed_s": 1041.3282611370087, "cell": "Ast", "id": "train:pair_pos:Ast:MRTFB:chr16_14301368_14301868:3533"}
|
| 8 |
+
{"step": 35, "loss": -40.079402923583984, "mean_r": -0.29847222566604614, "max_r": 0.23999999463558197, "mean_grounded": 3.25, "mean_halluc": 8.0, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.3173611111111111, "gnorm": 348.9560852050781, "elapsed_s": 1213.1267440319061, "cell": "Ast", "id": "train:pair_pos:Ast:TP73:chr1_3504030_3504530:1617"}
|
| 9 |
+
{"step": 40, "loss": -125.9754638671875, "mean_r": -0.47579625248908997, "max_r": -0.18000000715255737, "mean_grounded": 3.5, "mean_halluc": 13.5, "mean_cited": 17.5, "mean_tf_grounded_rate": 0.2349865047233468, "gnorm": 429.9833984375, "elapsed_s": 1385.5108399391174, "cell": "Ast", "id": "train:pair_pos:Ast:LGR4:chr11_27469948_27470448:3524"}
|
| 10 |
+
{"step": 45, "loss": -10.807151794433594, "mean_r": -0.5432597994804382, "max_r": -0.3499999940395355, "mean_grounded": 3.0, "mean_halluc": 13.5, "mean_cited": 16.75, "mean_tf_grounded_rate": 0.17790032679738563, "gnorm": 578.2479248046875, "elapsed_s": 1556.8942821025848, "cell": "Ast", "id": "train:pair_neg:Ast:ARHGAP4:chrX_154097524_154098024:787"}
|
| 11 |
+
{"step": 50, "loss": -40.11273193359375, "mean_r": -0.3615546226501465, "max_r": -0.24705882370471954, "mean_grounded": 3.75, "mean_halluc": 11.25, "mean_cited": 15.25, "mean_tf_grounded_rate": 0.26330532212885155, "gnorm": 440.54449462890625, "elapsed_s": 1725.7594501972198, "cell": "Mic", "id": "train:pair_pos:Mic:SLC47A1:chr17_19646986_19647486:1271"}
|
| 12 |
+
{"step": 55, "loss": -103.248779296875, "mean_r": -0.5373015999794006, "max_r": -0.2666666805744171, "mean_grounded": 2.0, "mean_halluc": 11.0, "mean_cited": 13.75, "mean_tf_grounded_rate": 0.16865079365079366, "gnorm": 485.51129150390625, "elapsed_s": 1897.3484437465668, "cell": "In", "id": "train:pair_neg:In:DUS4L:chr7_107371596_107372096:1203"}
|
| 13 |
+
{"step": 60, "loss": 93.50972747802734, "mean_r": -0.5134809613227844, "max_r": -0.19230769574642181, "mean_grounded": 2.75, "mean_halluc": 10.75, "mean_cited": 13.75, "mean_tf_grounded_rate": 0.1892968142968143, "gnorm": 358.890869140625, "elapsed_s": 2062.1149344444275, "cell": "Ast", "id": "train:pair_pos:Ast:KLF17:chr1_44355047_44355547:3462"}
|
| 14 |
+
{"step": 65, "loss": 21.4892578125, "mean_r": -0.5664335489273071, "max_r": -0.3384615480899811, "mean_grounded": 2.75, "mean_halluc": 11.75, "mean_cited": 14.75, "mean_tf_grounded_rate": 0.1654195804195804, "gnorm": 379.0263977050781, "elapsed_s": 2235.889911174774, "cell": "Ast", "id": "train:pair_pos:Ast:CINP:chr14_102492168_102492668:2983"}
|
| 15 |
+
{"step": 70, "loss": -46.47312927246094, "mean_r": -0.38989901542663574, "max_r": 0.13333334028720856, "mean_grounded": 3.0, "mean_halluc": 9.0, "mean_cited": 12.5, "mean_tf_grounded_rate": 0.2537878787878788, "gnorm": 557.3974609375, "elapsed_s": 2410.0868854522705, "cell": "Ex", "id": "train:pair_neg:Ex:CGGBP1:chr3_88151371_88151871:2198"}
|
| 16 |
+
{"step": 75, "loss": -44.34358215332031, "mean_r": -0.1041666641831398, "max_r": 0.30000001192092896, "mean_grounded": 3.5, "mean_halluc": 6.0, "mean_cited": 10.0, "mean_tf_grounded_rate": 0.2503205128205128, "gnorm": 500.87811279296875, "elapsed_s": 2578.6072397232056, "cell": "Ast", "id": "train:pair_pos:Ast:SLC6A13:chr12_271133_271633:72"}
|
| 17 |
+
{"step": 80, "loss": -74.841796875, "mean_r": -0.17307692766189575, "max_r": 0.6000000238418579, "mean_grounded": 3.0, "mean_halluc": 6.0, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.35645604395604397, "gnorm": 305.185302734375, "elapsed_s": 2751.0548832416534, "cell": "Ast", "id": "train:pair_pos:Ast:CFAP74:chr1_1920748_1921248:766"}
|
| 18 |
+
{"step": 85, "loss": -26.32306671142578, "mean_r": -0.4054762125015259, "max_r": -0.20000000298023224, "mean_grounded": 2.25, "mean_halluc": 6.75, "mean_cited": 9.5, "mean_tf_grounded_rate": 0.2089285714285714, "gnorm": 432.56768798828125, "elapsed_s": 2919.7268517017365, "cell": "In", "id": "train:pair_pos:In:PPRC1:chr10_101884994_101885494:3892"}
|
| 19 |
+
{"step": 90, "loss": 59.57316589355469, "mean_r": -0.029230769723653793, "max_r": 0.023076923564076424, "mean_grounded": 4.75, "mean_halluc": 6.75, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.4115384615384615, "gnorm": 399.2134704589844, "elapsed_s": 3084.458697080612, "cell": "Ast", "id": "train:pair_pos:Ast:COPS7A:chr12_6527155_6527655:959"}
|
| 20 |
+
{"step": 95, "loss": -68.27378845214844, "mean_r": -0.4207359254360199, "max_r": -0.18000000715255737, "mean_grounded": 4.0, "mean_halluc": 15.5, "mean_cited": 20.0, "mean_tf_grounded_rate": 0.23564213564213565, "gnorm": 456.6268615722656, "elapsed_s": 3245.223747253418, "cell": "Ast", "id": "train:pair_pos:Ast:LRP4:chr11_47118852_47119352:1335"}
|
| 21 |
+
{"step": 100, "loss": -225.0859375, "mean_r": -0.4487878680229187, "max_r": 0.0, "mean_grounded": 1.5, "mean_halluc": 9.25, "mean_cited": 10.75, "mean_tf_grounded_rate": 0.1140151515151515, "gnorm": 478.38421630859375, "elapsed_s": 3415.2856843471527, "cell": "Ast", "id": "train:pair_pos:Ast:LRRC55:chr11_57211308_57211808:2019"}
|
| 22 |
+
{"step": 105, "loss": 17.90606689453125, "mean_r": -0.27145832777023315, "max_r": 0.21250000596046448, "mean_grounded": 4.5, "mean_halluc": 9.0, "mean_cited": 14.0, "mean_tf_grounded_rate": 0.28541666666666665, "gnorm": 433.63720703125, "elapsed_s": 3582.237601995468, "cell": "Ast", "id": "train:pair_pos:Ast:FAM41C:chr1_941520_942020:24"}
|
| 23 |
+
{"step": 110, "loss": -40.341552734375, "mean_r": -0.32681816816329956, "max_r": -0.25999999046325684, "mean_grounded": 2.75, "mean_halluc": 7.5, "mean_cited": 10.5, "mean_tf_grounded_rate": 0.26136363636363635, "gnorm": 447.862548828125, "elapsed_s": 3734.9819555282593, "cell": "End", "id": "train:pair_pos:End:TMEM121:chr14_105498656_105499156:902"}
|
| 24 |
+
{"step": 115, "loss": -1.363128662109375, "mean_r": -0.2780681848526001, "max_r": -0.027272727340459824, "mean_grounded": 5.25, "mean_halluc": 10.75, "mean_cited": 17.0, "mean_tf_grounded_rate": 0.29384469696969695, "gnorm": 419.2023620605469, "elapsed_s": 3889.340273141861, "cell": "Ast", "id": "train:pair_pos:Ast:ZDHHC5:chr11_57427617_57428117:2307"}
|
| 25 |
+
{"step": 120, "loss": -149.09262084960938, "mean_r": -0.21353384852409363, "max_r": 1.0, "mean_grounded": 3.0, "mean_halluc": 7.5, "mean_cited": 11.5, "mean_tf_grounded_rate": 0.3488721804511278, "gnorm": 328.8318176269531, "elapsed_s": 4057.9865713119507, "cell": "Ex", "id": "train:pair_neg:Ex:PHETA1:chr12_111185910_111186410:479"}
|
| 26 |
+
{"step": 125, "loss": 99.04361724853516, "mean_r": -0.15386904776096344, "max_r": -0.03333333507180214, "mean_grounded": 3.5, "mean_halluc": 6.0, "mean_cited": 10.0, "mean_tf_grounded_rate": 0.3392857142857143, "gnorm": 437.196044921875, "elapsed_s": 4230.925471782684, "cell": "OPC", "id": "train:pair_neg:OPC:ALDOA:chr16_30030479_30030979:296"}
|
| 27 |
+
{"step": 130, "loss": -45.3918571472168, "mean_r": 0.004186604171991348, "max_r": 0.22727273404598236, "mean_grounded": 5.25, "mean_halluc": 7.25, "mean_cited": 13.0, "mean_tf_grounded_rate": 0.4162038619275461, "gnorm": 412.8166198730469, "elapsed_s": 4410.347144365311, "cell": "Oli", "id": "train:pair_neg:Oli:UBN1:chr16_4967030_4967530:837"}
|
| 28 |
+
{"step": 135, "loss": -100.61750793457031, "mean_r": -0.24108392000198364, "max_r": 0.0, "mean_grounded": 2.25, "mean_halluc": 6.75, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.18356643356643357, "gnorm": 369.89801025390625, "elapsed_s": 4584.195008277893, "cell": "Ast", "id": "train:pair_pos:Ast:LNX2:chr13_27638435_27638935:3808"}
|
| 29 |
+
{"step": 140, "loss": -88.15803527832031, "mean_r": 0.18339230120182037, "max_r": 0.699999988079071, "mean_grounded": 6.25, "mean_halluc": 7.5, "mean_cited": 14.0, "mean_tf_grounded_rate": 0.5183731387291759, "gnorm": 381.1214599609375, "elapsed_s": 4738.309872150421, "cell": "Ast", "id": "train:pair_pos:Ast:DZIP1:chr13_95496385_95496885:1925"}
|
| 30 |
+
{"step": 145, "loss": 79.7239990234375, "mean_r": -0.4128749966621399, "max_r": -0.05000000074505806, "mean_grounded": 3.75, "mean_halluc": 16.0, "mean_cited": 19.75, "mean_tf_grounded_rate": 0.26197916666666665, "gnorm": 376.2814025878906, "elapsed_s": 4915.069397211075, "cell": "Ast", "id": "train:pair_pos:Ast:NEK3:chr13_52390267_52390767:917"}
|
| 31 |
+
{"step": 150, "loss": -126.88933563232422, "mean_r": 0.23273809254169464, "max_r": 1.0333333015441895, "mean_grounded": 4.25, "mean_halluc": 4.25, "mean_cited": 9.0, "mean_tf_grounded_rate": 0.529491341991342, "gnorm": 315.1418151855469, "elapsed_s": 5090.648319244385, "cell": "Mic", "id": "train:pair_pos:Mic:GNB4:chr3_179453060_179453560:1907"}
|
| 32 |
+
{"step": 155, "loss": -13.678577423095703, "mean_r": -0.0867857113480568, "max_r": 0.01666666753590107, "mean_grounded": 4.5, "mean_halluc": 7.5, "mean_cited": 12.75, "mean_tf_grounded_rate": 0.3601190476190476, "gnorm": 436.85906982421875, "elapsed_s": 5260.500825643539, "cell": "Ast", "id": "train:pair_pos:Ast:ARFIP2:chr11_6567164_6567664:1736"}
|
| 33 |
+
{"step": 160, "loss": -11.192184448242188, "mean_r": -0.17413420975208282, "max_r": 0.20000000298023224, "mean_grounded": 3.0, "mean_halluc": 4.75, "mean_cited": 8.25, "mean_tf_grounded_rate": 0.3301948051948052, "gnorm": 428.4222717285156, "elapsed_s": 5444.281126260757, "cell": "Ast", "id": "train:pair_neg:Ast:SNAPIN:chr1_153554127_153554627:3034"}
|
| 34 |
+
{"step": 165, "loss": 24.492019653320312, "mean_r": -0.13952019810676575, "max_r": -0.05000000074505806, "mean_grounded": 3.75, "mean_halluc": 6.5, "mean_cited": 10.5, "mean_tf_grounded_rate": 0.3391729797979798, "gnorm": 427.9548034667969, "elapsed_s": 5616.279240608215, "cell": "Ast", "id": "train:pair_pos:Ast:PTPRJ:chr11_47973285_47973785:2005"}
|
| 35 |
+
{"step": 170, "loss": -130.26937866210938, "mean_r": 0.21805554628372192, "max_r": 1.0, "mean_grounded": 3.75, "mean_halluc": 6.25, "mean_cited": 11.0, "mean_tf_grounded_rate": 0.5458333333333333, "gnorm": 377.8606872558594, "elapsed_s": 5796.411918878555, "cell": "Mic", "id": "train:pair_neg:Mic:DEGS2:chr14_100312570_100313070:2112"}
|
| 36 |
+
{"step": 175, "loss": -114.32825469970703, "mean_r": 0.1251068413257599, "max_r": 0.550000011920929, "mean_grounded": 4.25, "mean_halluc": 4.75, "mean_cited": 9.75, "mean_tf_grounded_rate": 0.4738247863247863, "gnorm": 398.3206481933594, "elapsed_s": 5976.548135995865, "cell": "Ast", "id": "train:pair_pos:Ast:SPNS1:chr16_29130376_29130876:437"}
|
| 37 |
+
{"step": 180, "loss": 52.26029968261719, "mean_r": -0.4208333194255829, "max_r": 0.2199999988079071, "mean_grounded": 3.25, "mean_halluc": 8.0, "mean_cited": 11.25, "mean_tf_grounded_rate": 0.2635416666666667, "gnorm": 372.72747802734375, "elapsed_s": 6159.331789255142, "cell": "Mic", "id": "train:pair_pos:Mic:ZNF362:chr1_33237519_33238019:2872"}
|
| 38 |
+
{"step": 185, "loss": -63.27106475830078, "mean_r": 0.14499999582767487, "max_r": 1.0, "mean_grounded": 2.0, "mean_halluc": 3.25, "mean_cited": 5.75, "mean_tf_grounded_rate": 0.39999999999999997, "gnorm": 284.2621765136719, "elapsed_s": 6336.236979961395, "cell": "Ex", "id": "train:pair_pos:Ex:SF3A1:chr22_30424449_30424949:1143"}
|
| 39 |
+
{"step": 190, "loss": -19.42317008972168, "mean_r": 0.16845238208770752, "max_r": 0.6000000238418579, "mean_grounded": 3.0, "mean_halluc": 2.75, "mean_cited": 5.75, "mean_tf_grounded_rate": 0.40476190476190477, "gnorm": 430.9595031738281, "elapsed_s": 6518.158425569534, "cell": "Ast", "id": "train:pair_pos:Ast:TMX1:chr14_51088727_51089227:2086"}
|
| 40 |
+
{"step": 195, "loss": 39.62022399902344, "mean_r": -0.425555557012558, "max_r": -0.3799999952316284, "mean_grounded": 2.75, "mean_halluc": 12.25, "mean_cited": 16.0, "mean_tf_grounded_rate": 0.1717948717948718, "gnorm": 463.9270324707031, "elapsed_s": 6698.379506826401, "cell": "Ast", "id": "train:pair_pos:Ast:SEMA4B:chr15_90158391_90158891:2529"}
|