explcre commited on
Commit
a1c8a9e
·
verified ·
1 Parent(s): 9227d6e

Upload _reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t3_r128_alpha1_s2_par_20260506_221253/log.jsonl with huggingface_hub

Browse files
_reasoning_rl_multiseed/exp_phase8_reasoning_grounded_rl_t3_r128_alpha1_s2_par_20260506_221253/log.jsonl ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 1, "loss": 99.54866027832031, "mean_r": -0.8137362599372864, "max_r": -0.6333333253860474, "mean_grounded": 0.25, "mean_halluc": 9.5, "mean_cited": 10.25, "mean_tf_grounded_rate": 0.019230769230769232, "gnorm": 417.38580322265625, "elapsed_s": 49.00086331367493, "cell": "Oli", "id": "train:edit:Oli:ARL6IP4:chr12_122839369_122839869:3262"}
2
+ {"step": 5, "loss": 45.6891975402832, "mean_r": -0.8527777791023254, "max_r": -0.6666666865348816, "mean_grounded": 0.0, "mean_halluc": 8.75, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.0, "gnorm": 334.50396728515625, "elapsed_s": 184.91056060791016, "cell": "Ex", "id": "train:edit:Ex:DNAAF1:chr16_84178560_84179060:1583"}
3
+ {"step": 10, "loss": -151.15805053710938, "mean_r": -0.6806226968765259, "max_r": -0.47999998927116394, "mean_grounded": 1.0, "mean_halluc": 11.0, "mean_cited": 12.0, "mean_tf_grounded_rate": 0.08846153846153847, "gnorm": 564.0594482421875, "elapsed_s": 359.7687704563141, "cell": "Ex", "id": "train:edit:Ex:MLLT6:chr17_38868079_38868579:1284"}
4
+ {"step": 15, "loss": -66.16642761230469, "mean_r": -0.3159523904323578, "max_r": 0.3333333432674408, "mean_grounded": 1.5, "mean_halluc": 6.25, "mean_cited": 8.25, "mean_tf_grounded_rate": 0.2669642857142857, "gnorm": 283.5673522949219, "elapsed_s": 530.5415060520172, "cell": "Ast", "id": "train:edit:Ast:DNAJC24:chr11_31243512_31244012:3637"}
5
+ {"step": 20, "loss": 65.90116882324219, "mean_r": -0.596795916557312, "max_r": -0.30000001192092896, "mean_grounded": 2.0, "mean_halluc": 25.5, "mean_cited": 27.75, "mean_tf_grounded_rate": 0.1682213751438435, "gnorm": 531.0924682617188, "elapsed_s": 700.5572099685669, "cell": "Ast", "id": "train:edit:Ast:IFITM10:chr11_1855490_1855990:1025"}
6
+ {"step": 25, "loss": -130.81112670898438, "mean_r": -0.14208334684371948, "max_r": 1.0, "mean_grounded": 2.75, "mean_halluc": 6.5, "mean_cited": 9.25, "mean_tf_grounded_rate": 0.40208333333333335, "gnorm": 300.39093017578125, "elapsed_s": 873.0645732879639, "cell": "Ast", "id": "train:edit:Ast:SPARCL1:chr4_87483231_87483731:281"}
7
+ {"step": 30, "loss": -46.04944610595703, "mean_r": -0.47860753536224365, "max_r": 0.0, "mean_grounded": 1.5, "mean_halluc": 10.25, "mean_cited": 11.75, "mean_tf_grounded_rate": 0.09505772005772006, "gnorm": 236.1367645263672, "elapsed_s": 1055.0520577430725, "cell": "Mic", "id": "train:edit:Mic:BRD7:chr16_50312442_50312942:2718"}
8
+ {"step": 35, "loss": -91.60397338867188, "mean_r": -0.7679486870765686, "max_r": -0.5, "mean_grounded": 0.5, "mean_halluc": 10.25, "mean_cited": 11.0, "mean_tf_grounded_rate": 0.03571428571428571, "gnorm": 478.71514892578125, "elapsed_s": 1211.2856006622314, "cell": "Ast", "id": "train:edit:Ast:LINC01136:chr1_203146515_203147015:2070"}
9
+ {"step": 40, "loss": 28.521331787109375, "mean_r": -0.5103527903556824, "max_r": -0.17894737422466278, "mean_grounded": 2.75, "mean_halluc": 12.0, "mean_cited": 16.0, "mean_tf_grounded_rate": 0.14325896262395119, "gnorm": 528.1494140625, "elapsed_s": 1381.4892029762268, "cell": "Mic", "id": "train:edit:Mic:MYO1C:chr17_1589953_1590453:367"}
10
+ {"step": 45, "loss": 92.89891815185547, "mean_r": -0.6608928442001343, "max_r": -0.375, "mean_grounded": 1.75, "mean_halluc": 9.0, "mean_cited": 10.75, "mean_tf_grounded_rate": 0.14107142857142857, "gnorm": 368.6761474609375, "elapsed_s": 1560.6473388671875, "cell": "Oli", "id": "train:edit:Oli:RRP9:chr3_52014575_52015075:2797"}
11
+ {"step": 50, "loss": -126.95048522949219, "mean_r": -0.3968142867088318, "max_r": 0.027272727340459824, "mean_grounded": 1.5, "mean_halluc": 8.25, "mean_cited": 11.0, "mean_tf_grounded_rate": 0.2297979797979798, "gnorm": 494.4970397949219, "elapsed_s": 1729.027425289154, "cell": "Mic", "id": "train:edit:Mic:LINC00461:chr5_88824152_88824652:1592"}
12
+ {"step": 55, "loss": -174.87115478515625, "mean_r": -0.1547618955373764, "max_r": 0.6666666865348816, "mean_grounded": 2.0, "mean_halluc": 5.25, "mean_cited": 7.5, "mean_tf_grounded_rate": 0.36904761904761907, "gnorm": 398.80517578125, "elapsed_s": 1897.2932534217834, "cell": "OPC", "id": "train:edit:OPC:NECAP2:chr1_16618781_16619281:89"}
13
+ {"step": 60, "loss": 102.36299133300781, "mean_r": -0.6600000262260437, "max_r": -0.32499998807907104, "mean_grounded": 1.0, "mean_halluc": 5.75, "mean_cited": 6.75, "mean_tf_grounded_rate": 0.11875, "gnorm": 431.9703674316406, "elapsed_s": 2073.872147321701, "cell": "OPC", "id": "train:edit:OPC:ST6GALNAC4:chr9_127974038_127974538:3061"}
14
+ {"step": 65, "loss": -119.45207977294922, "mean_r": -0.4563811123371124, "max_r": 0.0, "mean_grounded": 1.25, "mean_halluc": 8.25, "mean_cited": 10.5, "mean_tf_grounded_rate": 0.2089160839160839, "gnorm": 401.8527526855469, "elapsed_s": 2249.6015202999115, "cell": "In", "id": "train:edit:In:ARHGAP23:chr17_38382206_38382706:2017"}
15
+ {"step": 70, "loss": -6.098522186279297, "mean_r": -0.546491265296936, "max_r": 0.46666666865348816, "mean_grounded": 1.0, "mean_halluc": 5.0, "mean_cited": 6.25, "mean_tf_grounded_rate": 0.19298245614035087, "gnorm": 184.36102294921875, "elapsed_s": 2427.759548664093, "cell": "Ex", "id": "train:edit:Ex:LRRC8C-DT:chr1_89615585_89616085:3270"}
16
+ {"step": 75, "loss": 161.15802001953125, "mean_r": -0.4642156958580017, "max_r": -0.25555557012557983, "mean_grounded": 2.0, "mean_halluc": 6.25, "mean_cited": 9.0, "mean_tf_grounded_rate": 0.16993464052287582, "gnorm": 313.43768310546875, "elapsed_s": 2595.079828262329, "cell": "Ast", "id": "train:edit:Ast:ADGRA2:chr8_37660454_37660954:3960"}
17
+ {"step": 80, "loss": -77.44438171386719, "mean_r": -0.3812820613384247, "max_r": -0.3199999928474426, "mean_grounded": 3.0, "mean_halluc": 10.25, "mean_cited": 14.0, "mean_tf_grounded_rate": 0.21620879120879122, "gnorm": 486.1454772949219, "elapsed_s": 2774.0563082695007, "cell": "OPC", "id": "train:edit:OPC:SUPT6H:chr17_28756280_28756780:1873"}
18
+ {"step": 85, "loss": -83.1576156616211, "mean_r": -0.1111111119389534, "max_r": 0.0, "mean_grounded": 1.25, "mean_halluc": 3.5, "mean_cited": 5.25, "mean_tf_grounded_rate": 0.125, "gnorm": 402.34173583984375, "elapsed_s": 2934.4273993968964, "cell": "Ex", "id": "train:edit:Ex:AP5M1:chr14_57502639_57503139:36"}
19
+ {"step": 90, "loss": -81.19766998291016, "mean_r": 0.012500002980232239, "max_r": 1.0, "mean_grounded": 1.0, "mean_halluc": 5.0, "mean_cited": 6.5, "mean_tf_grounded_rate": 0.3272058823529412, "gnorm": 199.83834838867188, "elapsed_s": 3111.9773845672607, "cell": "Mic", "id": "train:edit:Mic:PRAM1:chr19_8501142_8501642:1210"}
20
+ {"step": 95, "loss": -106.01592254638672, "mean_r": 0.04500000178813934, "max_r": 1.0, "mean_grounded": 0.75, "mean_halluc": 3.75, "mean_cited": 4.5, "mean_tf_grounded_rate": 0.25, "gnorm": 365.8923645019531, "elapsed_s": 3277.311765432358, "cell": "Ex", "id": "train:edit:Ex:HIST1H3D:chr6_26305260_26305760:2885"}
21
+ {"step": 100, "loss": -113.65707397460938, "mean_r": -0.4049144983291626, "max_r": 0.0, "mean_grounded": 1.5, "mean_halluc": 8.75, "mean_cited": 11.0, "mean_tf_grounded_rate": 0.09401709401709402, "gnorm": 317.07476806640625, "elapsed_s": 3450.287213087082, "cell": "Ex", "id": "train:edit:Ex:KCNC4:chr1_110188842_110189342:2173"}
22
+ {"step": 105, "loss": 143.9363250732422, "mean_r": -0.6272222399711609, "max_r": -0.1599999964237213, "mean_grounded": 1.0, "mean_halluc": 5.25, "mean_cited": 6.75, "mean_tf_grounded_rate": 0.10555555555555556, "gnorm": 407.5021667480469, "elapsed_s": 3622.530579805374, "cell": "Ex", "id": "train:edit:Ex:PAFAH1B3:chr19_42284641_42285141:455"}
23
+ {"step": 110, "loss": -147.84027099609375, "mean_r": -0.20642857253551483, "max_r": 0.0, "mean_grounded": 2.5, "mean_halluc": 6.75, "mean_cited": 9.5, "mean_tf_grounded_rate": 0.2193609022556391, "gnorm": 375.79522705078125, "elapsed_s": 3788.209677696228, "cell": "Mic", "id": "train:edit:Mic:MRTFA-AS1:chr22_40637712_40638212:1892"}
24
+ {"step": 115, "loss": -123.27445983886719, "mean_r": -0.300595223903656, "max_r": 0.0, "mean_grounded": 2.0, "mean_halluc": 6.5, "mean_cited": 8.5, "mean_tf_grounded_rate": 0.1919642857142857, "gnorm": 376.16351318359375, "elapsed_s": 3960.0108025074005, "cell": "OPC", "id": "train:edit:OPC:CISH:chr3_50392030_50392530:3309"}
25
+ {"step": 120, "loss": -98.86676025390625, "mean_r": -0.20357142388820648, "max_r": 0.0, "mean_grounded": 0.75, "mean_halluc": 3.25, "mean_cited": 4.75, "mean_tf_grounded_rate": 0.0625, "gnorm": 352.8898620605469, "elapsed_s": 4132.925541162491, "cell": "Ex", "id": "train:edit:Ex:CRABP2:chr1_156677962_156678462:2854"}
26
+ {"step": 125, "loss": -178.89976501464844, "mean_r": -0.08500000089406967, "max_r": 0.0, "mean_grounded": 0.5, "mean_halluc": 1.75, "mean_cited": 2.5, "mean_tf_grounded_rate": 0.05, "gnorm": 423.4192199707031, "elapsed_s": 4313.804117679596, "cell": "Ex", "id": "train:edit:Ex:LINC01798:chr2_66435427_66435927:3222"}
27
+ {"step": 130, "loss": -121.78821563720703, "mean_r": -0.07479755580425262, "max_r": 1.0, "mean_grounded": 3.25, "mean_halluc": 8.5, "mean_cited": 11.75, "mean_tf_grounded_rate": 0.42491718807508283, "gnorm": 324.3727722167969, "elapsed_s": 4488.8092658519745, "cell": "Ast", "id": "train:edit:Ast:TRIM44:chr11_35412993_35413493:530"}
28
+ {"step": 135, "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": 4677.28106546402, "cell": "Mic", "id": "train:edit:Mic:C2orf81:chr2_74559886_74560386:406"}
29
+ {"step": 140, "loss": -5.5561065673828125, "mean_r": -0.5, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 1.5, "mean_cited": 1.5, "mean_tf_grounded_rate": 0.0, "gnorm": 235.037841796875, "elapsed_s": 4856.181046009064, "cell": "In", "id": "train:edit:In:ZNF502:chr3_44478195_44478695:1390"}
30
+ {"step": 145, "loss": 10.118714332580566, "mean_r": -0.5090259909629822, "max_r": -0.11428571492433548, "mean_grounded": 1.25, "mean_halluc": 5.75, "mean_cited": 7.5, "mean_tf_grounded_rate": 0.15487012987012988, "gnorm": 230.9693145751953, "elapsed_s": 5018.613379955292, "cell": "Ast", "id": "train:edit:Ast:APOE:chr19_45103922_45104422:2484"}
31
+ {"step": 150, "loss": -57.12116622924805, "mean_r": -0.4138888716697693, "max_r": 0.0, "mean_grounded": 0.0, "mean_halluc": 2.25, "mean_cited": 2.5, "mean_tf_grounded_rate": 0.0, "gnorm": 219.06956481933594, "elapsed_s": 5194.495962381363, "cell": "OPC", "id": "train:edit:OPC:SMOX:chr20_4014810_4015310:263"}
32
+ {"step": 155, "loss": -55.922637939453125, "mean_r": -0.49047619104385376, "max_r": 0.0, "mean_grounded": 0.75, "mean_halluc": 4.25, "mean_cited": 5.5, "mean_tf_grounded_rate": 0.05357142857142857, "gnorm": 246.07179260253906, "elapsed_s": 5376.263090848923, "cell": "Mic", "id": "train:edit:Mic:CABP1:chr12_120745462_120745962:2979"}
33
+ {"step": 160, "loss": 21.328842163085938, "mean_r": 0.2666666805744171, "max_r": 1.0666667222976685, "mean_grounded": 0.75, "mean_halluc": 0.0, "mean_cited": 0.75, "mean_tf_grounded_rate": 0.25, "gnorm": 221.0929412841797, "elapsed_s": 5551.170246601105, "cell": "Oli", "id": "train:edit:Oli:ASB1:chr2_238231457_238231957:2921"}
34
+ {"step": 165, "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": 5731.143841743469, "cell": "In", "id": "train:edit:In:MICAL2:chr11_12154186_12154686:2175"}
35
+ {"step": 170, "loss": 75.49429321289062, "mean_r": -0.7152777910232544, "max_r": -0.25, "mean_grounded": 1.25, "mean_halluc": 7.5, "mean_cited": 8.75, "mean_tf_grounded_rate": 0.1111111111111111, "gnorm": 343.5888977050781, "elapsed_s": 5914.154980897903, "cell": "Ex", "id": "train:edit:Ex:ZBTB22:chr6_33453498_33453998:3240"}
36
+ {"step": 175, "loss": -88.32212829589844, "mean_r": -0.38083332777023315, "max_r": 0.0, "mean_grounded": 1.0, "mean_halluc": 5.5, "mean_cited": 7.25, "mean_tf_grounded_rate": 0.0875, "gnorm": 345.3414306640625, "elapsed_s": 6097.774803638458, "cell": "OPC", "id": "train:edit:OPC:OXTR:chr3_8964009_8964509:3279"}
37
+ {"step": 180, "loss": -188.7674102783203, "mean_r": -0.276583731174469, "max_r": 0.0, "mean_grounded": 1.0, "mean_halluc": 6.0, "mean_cited": 7.5, "mean_tf_grounded_rate": 0.06334841628959276, "gnorm": 445.44818115234375, "elapsed_s": 6272.146455287933, "cell": "In", "id": "train:edit:In:CLEC4F:chr2_70726946_70727446:846"}
38
+ {"step": 185, "loss": 25.024864196777344, "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": 200.82376098632812, "elapsed_s": 6460.8062653541565, "cell": "Ex", "id": "train:edit:Ex:ROPN1L:chr5_10564805_10565305:956"}
39
+ {"step": 190, "loss": -196.58143615722656, "mean_r": -0.1607142835855484, "max_r": 0.0, "mean_grounded": 0.25, "mean_halluc": 3.0, "mean_cited": 3.5, "mean_tf_grounded_rate": 0.017857142857142856, "gnorm": 501.4290466308594, "elapsed_s": 6644.912449121475, "cell": "Oli", "id": "train:edit:Oli:LINC01545:chrX_46953593_46954093:2594"}
40
+ {"step": 195, "loss": 8.879433631896973, "mean_r": 0.05000000074505806, "max_r": 0.20000000298023224, "mean_grounded": 0.0, "mean_halluc": 0.0, "mean_cited": 0.5, "mean_tf_grounded_rate": 0.0, "gnorm": 146.4046173095703, "elapsed_s": 6834.870848655701, "cell": "Mic", "id": "train:edit:Mic:ST6GALNAC2:chr17_76734243_76734743:4077"}
41
+ {"step": 200, "loss": -113.83219909667969, "mean_r": -0.10851648449897766, "max_r": 0.0, "mean_grounded": 2.75, "mean_halluc": 5.0, "mean_cited": 7.75, "mean_tf_grounded_rate": 0.29395604395604397, "gnorm": 420.6631164550781, "elapsed_s": 7018.053369998932, "cell": "Oli", "id": "train:edit:Oli:PAF1:chr19_39358336_39358836:591"}
42
+ {"step": 205, "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": 7208.4198496341705, "cell": "Mic", "id": "train:edit:Mic:PRMT5:chr14_22783766_22784266:1155"}
43
+ {"step": 210, "loss": -0.3379502296447754, "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": 173.0336456298828, "elapsed_s": 7399.590926408768, "cell": "Ast", "id": "train:edit:Ast:GPR162:chr12_6928186_6928686:1120"}
44
+ {"step": 215, "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": 7590.284432649612, "cell": "OPC", "id": "train:edit:OPC:ALOX12-AS1:chr17_7246962_7247462:1396"}
45
+ {"step": 220, "loss": -96.42239379882812, "mean_r": -0.31736111640930176, "max_r": 0.0, "mean_grounded": 0.5, "mean_halluc": 3.75, "mean_cited": 4.75, "mean_tf_grounded_rate": 0.15625, "gnorm": 355.60626220703125, "elapsed_s": 7778.894175767899, "cell": "Oli", "id": "train:edit:Oli:PSG1:chr19_42823165_42823665:2139"}
46
+ {"step": 225, "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": 7970.128037929535, "cell": "Mic", "id": "train:edit:Mic:HMCN2:chr9_130045595_130046095:1544"}
47
+ {"step": 230, "loss": -198.59262084960938, "mean_r": -0.2068965584039688, "max_r": 0.0, "mean_grounded": 0.25, "mean_halluc": 6.75, "mean_cited": 7.25, "mean_tf_grounded_rate": 0.008620689655172414, "gnorm": 479.5699768066406, "elapsed_s": 8161.052763462067, "cell": "Ex", "id": "train:edit:Ex:PRC1:chr15_91127197_91127697:83"}
48
+ {"step": 235, "loss": 16.50429916381836, "mean_r": 0.5, "max_r": 1.0, "mean_grounded": 1.0, "mean_halluc": 0.0, "mean_cited": 1.0, "mean_tf_grounded_rate": 0.5, "gnorm": 204.99131774902344, "elapsed_s": 8351.86955332756, "cell": "Ex", "id": "train:edit:Ex:C9orf50:chr9_129480475_129480975:1699"}
49
+ {"step": 240, "loss": 21.67795181274414, "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": 202.8062286376953, "elapsed_s": 8541.5930621624, "cell": "In", "id": "train:edit:In:PSMD8:chr19_38362304_38362804:3086"}
50
+ {"step": 245, "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": 8732.48773932457, "cell": "Ex", "id": "train:edit:Ex:PKDCC:chr2_41987361_41987861:1099"}
51
+ {"step": 250, "loss": 13.414009094238281, "mean_r": 0.30000001192092896, "max_r": 1.2000000476837158, "mean_grounded": 0.5, "mean_halluc": 0.0, "mean_cited": 0.5, "mean_tf_grounded_rate": 0.25, "gnorm": 212.565185546875, "elapsed_s": 8923.54199719429, "cell": "Ex", "id": "train:edit:Ex:FSTL4:chr5_133415728_133416228:567"}