Solshine commited on
Commit
e0215ae
·
verified ·
1 Parent(s): 6ef481e

add checkpoints/grpo_dense_arm_priordev/trainloss.csv (T1-dose-response)

Browse files
checkpoints/grpo_dense_arm_priordev/trainloss.csv ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,mean_reward,frac_std_pos,rvp,rho_bar,pg_loss,wall_s
2
+ 1,0.1341748982667923,1.0,0.014,0.25,0.2348256465047598,29.6
3
+ 2,0.057455018162727356,1.0,0.0001,0.125,-0.06414104253053665,26.3
4
+ 3,0.08695521950721741,1.0,0.0099,0.0833,0.13279707729816437,32.2
5
+ 4,0.045260004699230194,1.0,0.0003,0.0625,0.16566495597362518,30.1
6
+ 5,0.09987104684114456,1.0,0.015,0.1,0.11638461239635944,31.9
7
+ 6,0.11920560896396637,1.0,0.0022,0.0833,-0.05380058288574219,31.9
8
+ 7,-0.046929363161325455,1.0,0.0022,0.0714,0.026599518954753876,31.8
9
+ 8,-0.026013724505901337,1.0,0.0038,0.0625,0.1636540899053216,29.9
10
+ 9,0.08339753746986389,1.0,0.0032,0.0556,0.10061368346214294,31.0
11
+ 10,0.10721440613269806,1.0,0.0005,0.05,0.048415251076221466,27.8
12
+ 11,0.0017562122084200382,1.0,0.0034,0.0455,-0.01980537176132202,31.8
13
+ 12,0.1635836511850357,0.0,0.0,0.0417,0.0,22.8
14
+ 13,0.031418509781360626,1.0,0.0061,0.0385,-0.07698769122362137,28.8
15
+ 14,0.02648991346359253,1.0,0.0038,0.0357,-0.003788769245147705,29.3
16
+ 15,0.15576940774917603,1.0,0.0071,0.05,-0.00994434580206871,31.8
17
+ 16,0.17006130516529083,1.0,0.0134,0.0781,0.10310828685760498,28.9
18
+ 17,0.049867089837789536,1.0,0.0018,0.0735,-0.1879311427474022,30.7
19
+ 18,0.02340550534427166,1.0,0.0015,0.0694,-0.12939582765102386,30.0
20
+ 19,0.20943795144557953,1.0,0.0055,0.0921,-0.004395276308059692,29.4
21
+ 20,0.04114586114883423,1.0,0.0026,0.0875,0.08073481917381287,29.8
22
+ 21,0.26712191104888916,1.0,0.0017,0.131,0.019746631383895874,29.4
23
+ 22,-0.010343567468225956,1.0,0.0042,0.125,0.11516215652227402,30.3
24
+ 23,0.11140191555023193,1.0,0.0225,0.1304,0.03297156095504761,27.7
25
+ 24,0.1640576273202896,1.0,0.007,0.1458,-0.003820478916168213,31.1
26
+ 25,0.05150310695171356,1.0,0.0022,0.14,-0.02318245731294155,30.9
27
+ 26,0.08275085687637329,1.0,0.0015,0.1346,-0.1863756738603115,29.5
28
+ 27,0.1617453694343567,1.0,0.0075,0.1481,-0.20524151623249054,29.4
29
+ 28,0.13121429085731506,1.0,0.0149,0.1518,0.20991159975528717,28.7
30
+ 29,0.20079997181892395,1.0,0.0145,0.1638,-0.20060268510133028,28.9
31
+ 30,0.05386141315102577,1.0,0.0318,0.1667,0.11443503573536873,30.6
32
+ 31,-0.06429538875818253,1.0,0.0002,0.1613,-0.0971866250038147,30.2
33
+ 32,0.09457550197839737,1.0,0.0051,0.1562,0.09623582288622856,30.9
34
+ 33,0.07227514684200287,1.0,0.0036,0.1515,0.14611409790813923,29.9
35
+ 34,0.029739148914813995,1.0,0.0054,0.1471,0.06327973306179047,30.3
36
+ 35,-0.042256757616996765,1.0,0.0012,0.1429,-0.21914631128311157,30.1
37
+ 36,0.020775355398654938,1.0,0.0049,0.1389,0.039898745715618134,30.8
38
+ 37,0.07358317077159882,1.0,0.0025,0.1351,-0.09340912103652954,31.2
39
+ 38,0.037175025790929794,1.0,0.0101,0.1316,-0.03483669459819794,30.4
40
+ 39,0.20050154626369476,1.0,0.0028,0.141,-0.03886377811431885,27.9
41
+ 40,0.025165444239974022,1.0,0.0011,0.1375,0.19380832789465785,30.6
42
+ 41,0.16284705698490143,1.0,0.0061,0.1402,0.10362820327281952,26.1
43
+ 42,0.05414630100131035,1.0,0.0,0.1369,-0.02923709899187088,23.0
44
+ 43,-0.02781594730913639,1.0,0.0009,0.1337,0.13632901012897491,29.2
45
+ 44,0.04573794826865196,1.0,0.0046,0.1307,-0.18365109339356422,29.4
46
+ 45,0.004086003638803959,1.0,0.0016,0.1278,0.16107490099966526,29.3
47
+ 46,0.14321264624595642,1.0,0.0018,0.125,0.16899818694218993,29.2
48
+ 47,-0.05455701798200607,1.0,0.0064,0.1223,-0.09515520557761192,28.8
49
+ 48,-0.028772059828042984,1.0,0.0025,0.1198,0.15731218922883272,27.7
50
+ 49,0.2070212960243225,1.0,0.0004,0.1224,0.0016609951853752136,26.3
51
+ 50,0.02143212780356407,1.0,0.0002,0.12,0.0021066665649414062,30.4
52
+ 51,0.006852094084024429,1.0,0.0001,0.1176,-0.03676681965589523,30.3
53
+ 52,0.149496927857399,1.0,0.002,0.1202,-0.08277001464739442,31.0
54
+ 53,-0.0027384664863348007,1.0,0.0,0.1179,-0.2164907306432724,29.0
55
+ 54,0.027924921363592148,1.0,0.001,0.1157,-0.13028913736343384,31.7
56
+ 55,0.09002865105867386,1.0,0.0053,0.1182,0.46494995802640915,30.0
57
+ 56,-0.043229587376117706,1.0,0.0002,0.1161,-0.058171290904283524,30.2
58
+ 57,0.009222692809998989,1.0,0.001,0.114,-0.01848844438791275,30.7
59
+ 58,-0.05024299770593643,1.0,0.0033,0.1121,0.07210696139372885,29.9
60
+ 59,0.0640450268983841,1.0,0.001,0.1102,-0.1320682093501091,31.4
61
+ 60,0.012038275599479675,1.0,0.0054,0.1083,-0.2619587108492851,29.7
62
+ 61,0.18671274185180664,1.0,0.0004,0.1148,0.052940621972084045,30.3
63
+ 62,0.03734297305345535,1.0,0.0058,0.1129,0.1277923658490181,31.0
64
+ 63,-0.008154969662427902,1.0,0.0012,0.1111,-0.022002294659614563,29.9
65
+ 64,0.004193880129605532,1.0,0.0012,0.1094,0.16958382166922092,31.3
66
+ 65,0.09408266097307205,1.0,0.0001,0.1077,0.202454574406147,29.9
67
+ 66,0.11620618402957916,1.0,0.0071,0.1098,0.047028351575136185,29.8
68
+ 67,0.11986561119556427,1.0,0.0018,0.1082,0.003132067620754242,31.7
69
+ 68,-0.02248132787644863,1.0,0.0033,0.1066,-0.07680901512503624,28.6
70
+ 69,0.1419398933649063,1.0,0.0006,0.1051,-0.054691895842552185,30.4
71
+ 70,0.10689936578273773,1.0,0.0099,0.1071,-0.190109483897686,30.9
72
+ 71,-0.004557466134428978,1.0,0.0024,0.1056,-0.06809887290000916,30.2
73
+ 72,0.07630844414234161,1.0,0.0049,0.1042,-0.1458759382367134,30.2
74
+ 73,0.03953910619020462,1.0,0.0015,0.1027,0.04241156578063965,31.2
75
+ 74,0.027735130861401558,1.0,0.0032,0.1014,0.22515888512134552,28.6
76
+ 75,0.04606063663959503,1.0,0.0017,0.1,0.34009732003323734,30.8
77
+ 76,0.07129239290952682,1.0,0.0021,0.0987,0.00677422434091568,28.3
78
+ 77,0.0971464067697525,1.0,0.0012,0.0974,0.03149466589093208,32.0
79
+ 78,-0.004067123867571354,1.0,0.0037,0.0962,0.4230440706014633,31.1
80
+ 79,0.19224867224693298,1.0,0.0048,0.1013,0.11079849302768707,27.1
81
+ 80,0.09596655517816544,1.0,0.0027,0.1,0.04155772551894188,28.2
82
+ 81,0.09453360736370087,1.0,0.0028,0.0988,0.16083300858736038,28.8
83
+ 82,0.05476279556751251,1.0,0.0007,0.0976,0.3378244563937187,31.5
84
+ 83,0.07004973292350769,1.0,0.0007,0.0964,0.07027055695652962,30.2
85
+ 84,0.09876693785190582,1.0,0.0032,0.0952,-0.03310418128967285,31.3
86
+ 85,0.0038329781964421272,1.0,0.0007,0.0941,0.16628096252679825,29.8
87
+ 86,-0.03322524577379227,1.0,0.0018,0.093,-0.10988493263721466,31.5
88
+ 87,0.03571943938732147,1.0,0.0037,0.092,-0.0053243860602378845,30.4
89
+ 88,0.0823914110660553,1.0,0.0045,0.0909,0.1474541500210762,31.2
90
+ 89,0.0401618517935276,1.0,0.0055,0.0899,-0.08121748827397823,31.3
91
+ 90,0.021383212879300117,1.0,0.0074,0.0889,-0.06659992784261703,29.7
92
+ 91,0.009306039661169052,1.0,0.003,0.0879,-0.004429332911968231,28.9
93
+ 92,0.06930389255285263,1.0,0.0013,0.087,-0.03802322596311569,30.6
94
+ 93,0.10750488191843033,1.0,0.0056,0.0887,0.0008076978847384453,28.5
95
+ 94,0.029809189960360527,1.0,0.0001,0.0878,0.15810205042362213,28.0
96
+ 95,0.10995741188526154,1.0,0.005,0.0868,0.09920914098620415,30.5
97
+ 96,0.12511178851127625,1.0,0.0015,0.0859,-0.034762488678097725,28.7
98
+ 97,-0.0021977522410452366,1.0,0.001,0.0851,-0.2053147479891777,27.3
99
+ 98,0.05622880533337593,1.0,0.0018,0.0842,0.1608796939253807,28.6
100
+ 99,0.06600053608417511,1.0,0.0013,0.0833,-0.05121326167136431,26.7
101
+ 100,-0.027124928310513496,1.0,0.0002,0.0825,0.193537138402462,29.1
102
+ 101,0.029689708724617958,1.0,0.0017,0.0817,-0.01751013845205307,30.7
103
+ 102,0.10949239879846573,1.0,0.0067,0.0833,0.03262527473270893,31.3
104
+ 103,0.06521551311016083,1.0,0.0062,0.0825,-0.0030950456857681274,31.3
105
+ 104,0.08499926328659058,1.0,0.0153,0.0865,0.07407888770103455,28.4
106
+ 105,0.02349892631173134,1.0,0.0021,0.0857,-0.18719713389873505,31.1
107
+ 106,-0.032058678567409515,1.0,0.0023,0.0849,0.3678546417504549,28.0
108
+ 107,0.08349071443080902,1.0,0.0044,0.0841,-0.04273555427789688,29.3
109
+ 108,0.0424666553735733,1.0,0.006,0.0833,-0.2173658236861229,32.0
110
+ 109,0.07301123440265656,1.0,0.0015,0.0826,0.09633883088827133,30.4
111
+ 110,0.06939182430505753,1.0,0.0031,0.0818,0.05820424109697342,31.1
112
+ 111,-0.04054964333772659,1.0,0.0006,0.0811,-0.0654483251273632,31.3
113
+ 112,0.08613677322864532,1.0,0.0066,0.0804,-0.13728907704353333,26.8
114
+ 113,0.15867343544960022,1.0,0.0249,0.0841,-0.19507178664207458,28.7
115
+ 114,0.03450194001197815,1.0,0.0065,0.0833,0.10180722922086716,29.7
116
+ 115,0.05898337811231613,1.0,0.0087,0.0826,-0.03634234517812729,29.4
117
+ 116,0.0347687229514122,1.0,0.0008,0.0819,0.14255217462778091,28.8
118
+ 117,0.002235383726656437,1.0,0.0009,0.0812,0.02334950491786003,28.5
119
+ 118,0.1486402451992035,1.0,0.0118,0.0847,0.18189652264118195,27.9
120
+ 119,0.05021163076162338,1.0,0.0037,0.084,-0.04669173061847687,27.3
121
+ 120,0.06387124210596085,1.0,0.0023,0.0833,-0.20947583205997944,31.8
122
+ 121,0.029098786413669586,1.0,0.0049,0.0826,0.021518245339393616,30.1
123
+ 122,0.08022043108940125,1.0,0.0237,0.084,0.09956962801516056,30.5
124
+ 123,0.04777082800865173,1.0,0.0003,0.0833,-0.18743959441781044,28.4
125
+ 124,-0.034843843430280685,1.0,0.0001,0.0827,0.10106763988733292,27.5
126
+ 125,0.01206153817474842,1.0,0.0006,0.082,-0.0743512948974967,27.9
127
+ 126,0.07289667427539825,1.0,0.0066,0.0813,0.1406468227505684,29.2
128
+ 127,0.02920103818178177,1.0,0.0022,0.0807,-0.010131608694791794,30.7
129
+ 128,-0.001773717813193798,1.0,0.0021,0.0801,0.2382524535059929,29.2
130
+ 129,0.10422204434871674,1.0,0.0132,0.0814,0.1271612048149109,29.3
131
+ 130,0.046917758882045746,1.0,0.0036,0.0808,-0.1104724183678627,27.9
132
+ 131,0.018979394808411598,1.0,0.0011,0.0802,0.036950744688510895,29.1
133
+ 132,-0.021654505282640457,1.0,0.0013,0.0795,0.017574032302945852,28.6
134
+ 133,0.021633004769682884,1.0,0.0023,0.0789,0.3148087039589882,27.3
135
+ 134,0.044070739299058914,1.0,0.0002,0.0784,-0.11766268964856863,29.8
136
+ 135,-0.04469586908817291,1.0,0.001,0.0778,0.04971832409501076,31.8
137
+ 136,0.23697412014007568,1.0,0.0106,0.0827,0.21286903508007526,26.8
138
+ 137,0.03183958679437637,1.0,0.003,0.0821,-0.03481748793274164,27.9
139
+ 138,0.09262553602457047,1.0,0.0082,0.0815,-0.18164940178394318,28.7
140
+ 139,0.10779477655887604,1.0,0.002,0.0809,-0.11328021436929703,29.0
141
+ 140,0.2643651068210602,1.0,0.007,0.0857,-0.09663691744208336,31.8
142
+ 141,-0.01766451820731163,1.0,0.0008,0.0851,0.16636500391177833,30.4
143
+ 142,0.1600855141878128,1.0,0.0137,0.0863,0.2734976205974817,28.5
144
+ 143,0.10021286457777023,1.0,0.051,0.0874,-0.0031379833817481995,28.9
145
+ 144,0.06451719999313354,1.0,0.0077,0.0868,-0.3093295618891716,27.8
146
+ 145,0.22984717786312103,1.0,0.0275,0.0897,-0.04464511573314667,29.9
147
+ 146,0.004651719704270363,1.0,0.0011,0.089,0.10363511554896832,28.0
148
+ 147,0.048186659812927246,1.0,0.0105,0.0901,0.011150576174259186,27.6
149
+ 148,0.019115786999464035,1.0,0.0056,0.0895,-0.2745651602745056,31.2
150
+ 149,0.1262677013874054,1.0,0.0123,0.0906,-0.14554782211780548,30.7
151
+ 150,0.04168200492858887,1.0,0.0013,0.09,0.10216568782925606,27.0
152
+ 151,0.10111045837402344,1.0,0.0003,0.0894,-0.1470082774758339,28.8
153
+ 152,0.14460763335227966,1.0,0.0108,0.0905,-0.03763730823993683,30.7
154
+ 153,0.06842949986457825,1.0,0.0029,0.0899,0.13703658245503902,30.3
155
+ 154,0.034365031868219376,1.0,0.004,0.0893,0.03408375009894371,29.8
156
+ 155,0.07681750506162643,1.0,0.0022,0.0887,-0.028924904763698578,29.3
157
+ 156,0.11601808667182922,1.0,0.0019,0.0881,0.06366980448365211,29.4
158
+ 157,0.05461009591817856,1.0,0.0101,0.0876,-0.005144175142049789,30.4
159
+ 158,0.15992049872875214,1.0,0.0021,0.0886,-0.0956850852817297,29.6
160
+ 159,0.13969242572784424,1.0,0.0044,0.0896,-0.2825683350674808,31.5
161
+ 160,0.007558177225291729,1.0,0.0012,0.0891,-0.12243044376373291,29.4
162
+ 161,-0.05202917009592056,1.0,0.0007,0.0885,0.1796530056744814,31.0
163
+ 162,0.05516324192285538,1.0,0.0007,0.088,0.002548225224018097,27.6
164
+ 163,0.22338207066059113,1.0,0.0245,0.0905,0.1587180271744728,30.7
165
+ 164,0.052716806530952454,1.0,0.0059,0.0899,-0.1821192428469658,27.6
166
+ 165,0.09336598217487335,1.0,0.0063,0.0909,-0.2122674062848091,27.0
167
+ 166,0.10427968204021454,1.0,0.0064,0.0904,0.24855110980570316,29.3
168
+ 167,-0.012051794677972794,1.0,0.0006,0.0898,0.08917568461038172,29.8
169
+ 168,-0.010607377626001835,1.0,0.0011,0.0893,-0.37468278408050537,30.0
170
+ 169,0.1312733292579651,1.0,0.0052,0.0888,-0.147146824747324,30.6
171
+ 170,0.05013740807771683,1.0,0.0005,0.0882,0.09978066757321358,29.8
172
+ 171,0.03839642181992531,1.0,0.0128,0.0892,0.027538621798157692,29.6
173
+ 172,0.12706083059310913,1.0,0.0048,0.0887,0.1828925460577011,30.5
174
+ 173,0.11121407896280289,1.0,0.0096,0.0896,-0.01812296360731125,29.1
175
+ 174,-0.032041165977716446,1.0,0.0013,0.0891,-0.051999762654304504,29.4
176
+ 175,0.1011592298746109,1.0,0.0036,0.0886,-0.08441723044961691,29.2
177
+ 176,0.09289081394672394,1.0,0.0024,0.0881,-0.14167992770671844,27.7
178
+ 177,0.007201455533504486,1.0,0.0022,0.0876,0.05578947812318802,30.2
179
+ 178,0.19000063836574554,1.0,0.0027,0.0899,-0.03360991179943085,27.9
180
+ 179,0.09907535463571548,1.0,0.0039,0.0894,0.030920155346393585,31.2
181
+ 180,-0.015596438199281693,1.0,0.0006,0.0889,-0.23624131828546524,30.3
182
+ 181,0.13292057812213898,1.0,0.0047,0.0898,0.15156656503677368,29.3
183
+ 182,0.07430467009544373,1.0,0.0066,0.0893,-0.2921307012438774,31.5
184
+ 183,0.024118131026625633,1.0,0.0016,0.0888,-0.08930314611643553,28.0
185
+ 184,-0.010693450458347797,1.0,0.0074,0.0883,0.04902390390634537,30.6
186
+ 185,0.0363956093788147,1.0,0.0082,0.0878,0.027908634394407272,29.1
187
+ 186,0.07793447375297546,1.0,0.0129,0.0887,-0.101932592689991,30.5
188
+ 187,0.12121456116437912,1.0,0.0019,0.0882,-0.08650180604308844,31.0
189
+ 188,0.08846070617437363,1.0,0.0025,0.0878,0.33702361583709717,31.1
190
+ 189,0.0013635288923978806,1.0,0.0046,0.0873,-0.031744107604026794,30.0
191
+ 190,0.1602027714252472,1.0,0.0262,0.0895,-0.006251424551010132,29.1
192
+ 191,0.0041908035054802895,1.0,0.001,0.089,0.165599025785923,31.0
193
+ 192,0.08142875134944916,1.0,0.0044,0.0885,-0.019350767135620117,28.6
194
+ 193,-0.00036260485649108887,1.0,0.0019,0.0881,-0.04388320446014404,29.4
195
+ 194,-0.08030523359775543,1.0,0.0019,0.0876,-0.0949811115860939,29.5
196
+ 195,0.03584199398756027,1.0,0.0013,0.0872,0.05959251523017883,29.5
197
+ 196,0.06353393197059631,1.0,0.0012,0.0867,0.1219354160130024,30.0
198
+ 197,0.01498439908027649,1.0,0.0012,0.0863,0.0731434989720583,30.9
199
+ 198,0.01898116245865822,1.0,0.0017,0.0859,-0.3102857545018196,30.9
200
+ 199,0.07446327805519104,1.0,0.0061,0.0854,0.21809040009975433,29.1
201
+ 200,0.139372318983078,1.0,0.006,0.0862,0.2642488032579422,30.2