Upload folder using huggingface_hub
Browse files
seq_code_math_gt_sft_seed1/run_info.json
CHANGED
|
@@ -32,9 +32,32 @@
|
|
| 32 |
"math_hard_ce": 0.7975115962293889
|
| 33 |
},
|
| 34 |
"peak_gb_student": 33.696606159210205,
|
| 35 |
-
"peak_gb_teachers": 29.222092628479004
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
}
|
| 39 |
}
|
| 40 |
}
|
|
|
|
| 32 |
"math_hard_ce": 0.7975115962293889
|
| 33 |
},
|
| 34 |
"peak_gb_student": 33.696606159210205,
|
| 35 |
+
"peak_gb_teachers": 29.222092628479004
|
| 36 |
+
},
|
| 37 |
+
"stage2_math": {
|
| 38 |
+
"domain": "math",
|
| 39 |
+
"steps": 896,
|
| 40 |
+
"train_h": 2.9764579196108714,
|
| 41 |
+
"val_start": {
|
| 42 |
+
"step": 0,
|
| 43 |
+
"math_kl": 0.18707215095927757,
|
| 44 |
+
"math_ce": 0.8169582523867784,
|
| 45 |
+
"code_kl": 0.34373369645959484,
|
| 46 |
+
"code_ce": 0.248868452603892,
|
| 47 |
+
"math_hard_kl": 0.281878406746077,
|
| 48 |
+
"math_hard_ce": 0.7980098331233478
|
| 49 |
+
},
|
| 50 |
+
"val_end": {
|
| 51 |
+
"step": 896,
|
| 52 |
+
"math_kl": 0.2757146853520857,
|
| 53 |
+
"math_ce": 0.48866650442357035,
|
| 54 |
+
"code_kl": 0.23322471331621716,
|
| 55 |
+
"code_ce": 0.2632293531111412,
|
| 56 |
+
"math_hard_kl": 0.3334636116516183,
|
| 57 |
+
"math_hard_ce": 0.6151642707250928
|
| 58 |
+
},
|
| 59 |
+
"peak_gb_student": 36.51224708557129,
|
| 60 |
+
"peak_gb_teachers": 29.517569541931152
|
| 61 |
}
|
| 62 |
}
|
| 63 |
}
|
seq_code_math_gt_sft_seed1/stage2_math/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 32768,
|
| 44 |
+
"max_window_layers": 21,
|
| 45 |
+
"model_type": "qwen2",
|
| 46 |
+
"num_attention_heads": 12,
|
| 47 |
+
"num_hidden_layers": 28,
|
| 48 |
+
"num_key_value_heads": 2,
|
| 49 |
+
"pad_token_id": null,
|
| 50 |
+
"rms_norm_eps": 1e-06,
|
| 51 |
+
"rope_parameters": {
|
| 52 |
+
"rope_theta": 1000000.0,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
},
|
| 55 |
+
"sliding_window": null,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.20.2",
|
| 58 |
+
"use_cache": false,
|
| 59 |
+
"use_sliding_window": false,
|
| 60 |
+
"vocab_size": 151936
|
| 61 |
+
}
|
seq_code_math_gt_sft_seed1/stage2_math/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.20.2"
|
| 14 |
+
}
|
seq_code_math_gt_sft_seed1/stage2_math/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.19034193901484575, "ce": 0.7487423771507937}, {"step": 2, "kl": 0.18002051771538394, "ce": 0.7283463316807618}, {"step": 3, "kl": 0.20349442267035658, "ce": 0.7598819363606425}, {"step": 4, "kl": 0.16837978005563603, "ce": 0.7973208865522752}, {"step": 5, "kl": 0.11192863597258328, "ce": 0.8329260149627665}, {"step": 6, "kl": 0.17328261774135603, "ce": 0.9201528219922536}, {"step": 7, "kl": 0.1289489442068006, "ce": 0.8523378638311547}, {"step": 8, "kl": 0.17570031821628088, "ce": 0.6833031877198753}, {"step": 9, "kl": 0.15544665149138243, "ce": 0.5309977143101173}, {"step": 10, "kl": 0.26823721086796865, "ce": 0.5259409272351028}, {"step": 11, "kl": 0.1277483565797422, "ce": 0.5186385356675173}, {"step": 12, "kl": 0.1630801121863718, "ce": 0.4930573847464824}, {"step": 13, "kl": 0.2774930304808051, "ce": 0.6424681787062863}, {"step": 14, "kl": 0.20182031889929192, "ce": 0.5433895958120633}, {"step": 15, "kl": 0.1651035596552693, "ce": 0.610453126771693}, {"step": 16, "kl": 0.14476628543421693, "ce": 0.6320729249252777}, {"step": 17, "kl": 0.21162921965518866, "ce": 0.6217719129014871}, {"step": 18, "kl": 0.1955275751118149, "ce": 0.547517577852584}, {"step": 19, "kl": 1.0837894561442925, "ce": 0.5141055272767794}, {"step": 20, "kl": 0.23464159115563707, "ce": 0.6703809406113584}, {"step": 21, "kl": 0.32900962980839404, "ce": 0.5397921397324611}, {"step": 22, "kl": 0.14361908426686723, "ce": 0.44107582073076335}, {"step": 23, "kl": 0.17228154490651218, "ce": 0.49544605065786457}, {"step": 24, "kl": 0.20923319321889877, "ce": 0.606172506887624}, {"step": 25, "kl": 0.19714562924202347, "ce": 0.6256426706742705}, {"step": 26, "kl": 0.21007586665139177, "ce": 0.529354983542797}, {"step": 27, "kl": 0.18157092703624714, "ce": 0.613475443253731}, {"step": 28, "kl": 0.23638185617672608, "ce": 0.5389046642618557}, {"step": 29, "kl": 0.22959106628261927, "ce": 0.5612275984784194}, {"step": 30, "kl": 0.22048349627249952, "ce": 0.6161932119506351}, {"step": 31, "kl": 0.2318048986671847, "ce": 0.5879846335003432}, {"step": 32, "kl": 0.22066447748352475, "ce": 0.5170258995487855}, {"step": 33, "kl": 0.2263808561744859, "ce": 0.4161856204799616}, {"step": 34, "kl": 0.21342195172790684, "ce": 0.5668582330169962}, {"step": 35, "kl": 1.1402578152668952, "ce": 0.6158282219694196}, {"step": 36, "kl": 0.26571665518773036, "ce": 0.777640900437288}, {"step": 37, "kl": 0.23300371679204196, "ce": 0.5979129862452702}, {"step": 38, "kl": 0.2311459402004934, "ce": 0.5350179307848356}, {"step": 39, "kl": 0.2510432409407884, "ce": 0.6452828284770342}, {"step": 40, "kl": 0.19168923421136297, "ce": 0.4991160458787842}, {"step": 41, "kl": 0.21691348220147338, "ce": 0.6313395134818406}, {"step": 42, "kl": 0.21845429749386858, "ce": 0.6236078448857922}, {"step": 43, "kl": 0.20251914169653754, "ce": 0.511410921912402}, {"step": 44, "kl": 0.2636614745701785, "ce": 0.5773290301370697}, {"step": 45, "kl": 0.31240416327344095, "ce": 0.5735849537723888}, {"step": 46, "kl": 0.2066708003510572, "ce": 0.44442928645990815}, {"step": 47, "kl": 0.24762458531679615, "ce": 0.5620758052303277}, {"step": 48, "kl": 0.21728740924000822, "ce": 0.4813222391598551}, {"step": 49, "kl": 0.18909041996228557, "ce": 0.5705880082769821}, {"step": 50, "kl": 0.2355337615993732, "ce": 0.5444156901804715}, {"step": 51, "kl": 0.2130735077569068, "ce": 0.4962352860117789}, {"step": 52, "kl": 0.6806992906468736, "ce": 0.6647985761051515}, {"step": 53, "kl": 0.28665263061382684, "ce": 0.6483956755024113}, {"step": 54, "kl": 0.22685888261218254, "ce": 0.6059689239370976}, {"step": 55, "kl": 0.30513399101613914, "ce": 0.614134348502233}, {"step": 56, "kl": 0.19661059195960312, "ce": 0.5380585114705004}, {"step": 57, "kl": 0.21763461246808682, "ce": 0.5698695312342082}, {"step": 58, "kl": 0.25685991601731933, "ce": 0.43749086430278455}, {"step": 59, "kl": 0.36585115816096936, "ce": 0.5932377567083374}, {"step": 60, "kl": 0.35194781203477365, "ce": 0.5467411725354413}, {"step": 61, "kl": 0.29873298043074126, "ce": 0.610677478149647}, {"step": 62, "kl": 0.2201143342940534, "ce": 0.47934467536358794}, {"step": 63, "kl": 0.5351081435257846, "ce": 0.5921344850807284}, {"step": 64, "kl": 0.2906864833179623, "ce": 0.5379821217795606}, {"step": 65, "kl": 0.203656362913795, "ce": 0.5620346995233332}, {"step": 66, "kl": 0.23645926808876594, "ce": 0.5637621165051008}, {"step": 67, "kl": 0.20827693365281186, "ce": 0.6698295811549718}, {"step": 68, "kl": 0.2143763861249217, "ce": 0.4305598718963089}, {"step": 69, "kl": 0.21355942498710168, "ce": 0.574456132307777}, {"step": 70, "kl": 0.21568972572632703, "ce": 0.5738464764307286}, {"step": 71, "kl": 0.31023720616443473, "ce": 0.5577843548783503}, {"step": 72, "kl": 0.21318867927542312, "ce": 0.6772221453296113}, {"step": 73, "kl": 0.20266646424260065, "ce": 0.7129852503456332}, {"step": 74, "kl": 0.20798336913322182, "ce": 0.7174987561774977}, {"step": 75, "kl": 0.211305540884248, "ce": 0.707617032317608}, {"step": 76, "kl": 0.25819876611726106, "ce": 0.5338914754736515}, {"step": 77, "kl": 0.19627074528177943, "ce": 0.5935315733974419}, {"step": 78, "kl": 0.20885109062653026, "ce": 0.5280510072684889}, {"step": 79, "kl": 0.23105183821562472, "ce": 0.48126368096183364}, {"step": 80, "kl": 0.21617053818218676, "ce": 0.6401186361392831}, {"step": 81, "kl": 0.28260307132336193, "ce": 0.4911012317502521}, {"step": 82, "kl": 0.22105731918847754, "ce": 0.5075421727316365}, {"step": 83, "kl": 0.42039623817503813, "ce": 0.562533180935541}, {"step": 84, "kl": 0.26676216189683044, "ce": 0.5959918621408328}, {"step": 85, "kl": 0.20435124330471544, "ce": 0.4747504339872466}, {"step": 86, "kl": 0.2007182509315508, "ce": 0.5325996931523485}, {"step": 87, "kl": 0.2121371964347151, "ce": 0.5717676887540032}, {"step": 88, "kl": 0.2812355650636294, "ce": 0.5795155972887468}, {"step": 89, "kl": 0.21793467584254606, "ce": 0.856679015036135}, {"step": 90, "kl": 0.2339008339607521, "ce": 0.6667556737908455}, {"step": 91, "kl": 0.20280238869375486, "ce": 0.5292878321356727}, {"step": 92, "kl": 0.22678771613672585, "ce": 0.5373165098637332}, {"step": 93, "kl": 0.20428979635862238, "ce": 0.5495194537162014}, {"step": 94, "kl": 0.24136181451045832, "ce": 0.5315418893895585}, {"step": 95, "kl": 0.2806414240701582, "ce": 0.6046645219485381}, {"step": 96, "kl": 0.21592208349026554, "ce": 0.46218453761767253}, {"step": 97, "kl": 0.18896851989893879, "ce": 0.6335024933060871}, {"step": 98, "kl": 0.1858756922578114, "ce": 0.548601839169132}, {"step": 99, "kl": 0.6462080611299015, "ce": 0.5261950515992846}, {"step": 100, "kl": 0.21776746493553897, "ce": 0.5531232256153178}, {"step": 101, "kl": 0.19247524046288958, "ce": 0.535273327952232}, {"step": 102, "kl": 0.20796259076465437, "ce": 0.5458814061974729}, {"step": 103, "kl": 0.2096501356510536, "ce": 0.4572887607028015}, {"step": 104, "kl": 0.2142657990886805, "ce": 0.5211916187883683}, {"step": 105, "kl": 0.19107541701563663, "ce": 0.6149799810588689}, {"step": 106, "kl": 0.3916111943731101, "ce": 0.562289824288978}, {"step": 107, "kl": 0.3889670497360791, "ce": 0.5574885597896365}, {"step": 108, "kl": 0.3234841213935026, "ce": 0.6564458792907182}, {"step": 109, "kl": 0.42318610087066044, "ce": 0.5781082828875647}, {"step": 110, "kl": 0.19658551625236864, "ce": 0.4544079025531026}, {"step": 111, "kl": 0.17525836339836517, "ce": 0.6194727590987085}, {"step": 112, "kl": 0.2301603891610457, "ce": 0.5429774593027831}, {"step": 113, "kl": 0.47796182193084136, "ce": 0.701164253087935}, {"step": 114, "kl": 0.2011279513786401, "ce": 0.5966193490439078}, {"step": 115, "kl": 0.2094279126400711, "ce": 0.6333754982624495}, {"step": 116, "kl": 0.264736744142063, "ce": 0.5577451812979438}, {"step": 117, "kl": 0.20989044419797964, "ce": 0.5225682846325673}, {"step": 118, "kl": 0.20171931636032953, "ce": 0.5674195879756815}, {"step": 119, "kl": 0.20731660716400735, "ce": 0.4619778431597901}, {"step": 120, "kl": 0.5029433130836826, "ce": 0.47693857791225636}, {"step": 121, "kl": 0.19790631515692778, "ce": 0.5376325700666521}, {"step": 122, "kl": 1.8143135781582174, "ce": 0.5811777277323726}, {"step": 123, "kl": 0.25969259018745927, "ce": 0.6664688657346033}, {"step": 124, "kl": 0.27580397818436775, "ce": 0.46094770542242985}, {"step": 125, "kl": 0.2033323037563988, "ce": 0.4631835353596637}, {"step": 126, "kl": 0.1913490767624732, "ce": 0.6033388400002766}, {"step": 127, "kl": 0.26680096289745964, "ce": 0.48061409422256407}, {"step": 128, "kl": 0.19551949508695957, "ce": 0.573539238598519}, {"step": 129, "kl": 0.21692580906211903, "ce": 0.5021388282436204}, {"step": 130, "kl": 0.31355278735250547, "ce": 0.4640032099540306}, {"step": 131, "kl": 0.24665928812251242, "ce": 0.5306873599322253}, {"step": 132, "kl": 0.28969241736834456, "ce": 0.6935744336284326}, {"step": 133, "kl": 0.2444227470446156, "ce": 0.6056013221749046}, {"step": 134, "kl": 0.5000394815327628, "ce": 0.6003225747080606}, {"step": 135, "kl": 0.4328429774544724, "ce": 0.6101715337073539}, {"step": 136, "kl": 0.18901798319476362, "ce": 0.4375087950368715}, {"step": 137, "kl": 0.2388994805501361, "ce": 0.5172608176092213}, {"step": 138, "kl": 0.8500738476453245, "ce": 0.46568598422202545}, {"step": 139, "kl": 0.24771732113141032, "ce": 0.5594615513075843}, {"step": 140, "kl": 0.8175294444298404, "ce": 0.5227899872214011}, {"step": 141, "kl": 0.2535529018246781, "ce": 0.5447316508401524}, {"step": 142, "kl": 0.2201145168524891, "ce": 0.5362267849937318}, {"step": 143, "kl": 0.19405133159187055, "ce": 0.4505525477912382}, {"step": 144, "kl": 0.6707748663761414, "ce": 0.5361857914285613}, {"step": 145, "kl": 0.18816286948436445, "ce": 0.5897511905439116}, {"step": 146, "kl": 0.20291166195290627, "ce": 0.5885601537433791}, {"step": 147, "kl": 0.3152284575245033, "ce": 0.516788872725644}, {"step": 148, "kl": 0.29737764696433444, "ce": 0.5501116989590303}, {"step": 149, "kl": 0.18801425173123193, "ce": 0.7264414550532676}, {"step": 150, "kl": 0.20211270030798348, "ce": 0.487164599041237}, {"step": 151, "kl": 0.28468907281359757, "ce": 0.5507885639403762}, {"step": 152, "kl": 0.22509422658071826, "ce": 0.49964431555672634}, {"step": 153, "kl": 0.2032029988709027, "ce": 0.6092927144587136}, {"step": 154, "kl": 0.41609061617037024, "ce": 0.6803309862448674}, {"step": 155, "kl": 0.24385865340054716, "ce": 0.6196210505957085}, {"step": 156, "kl": 0.3848169077603065, "ce": 0.5529655492333718}, {"step": 157, "kl": 0.6894679504801526, "ce": 0.7286852595354243}, {"step": 158, "kl": 0.20056190663475515, "ce": 0.5298492656334974}, {"step": 159, "kl": 0.20394521084928177, "ce": 0.48879014764913514}, {"step": 160, "kl": 0.5181425605312642, "ce": 0.5566482936875502}, {"step": 161, "kl": 0.6797300833650446, "ce": 0.46745757265118426}, {"step": 162, "kl": 0.4473419325354669, "ce": 0.5758584987617539}, {"step": 163, "kl": 0.24256148345339612, "ce": 0.542456708602072}, {"step": 164, "kl": 0.23128309097883043, "ce": 0.5368812518504814}, {"step": 165, "kl": 0.34435157673264316, "ce": 0.6093409982787868}, {"step": 166, "kl": 0.28752982326854903, "ce": 0.5996711379714432}, {"step": 167, "kl": 0.2315466207468453, "ce": 0.5991656619432735}, {"step": 168, "kl": 0.23870846798437842, "ce": 0.4846824478236941}, {"step": 169, "kl": 0.3936130752563477, "ce": 0.5787103364419808}, {"step": 170, "kl": 0.24271583185567486, "ce": 0.6070419790926207}, {"step": 171, "kl": 0.30243547630839246, "ce": 0.6340716185653111}, {"step": 172, "kl": 0.19689588523286183, "ce": 0.40610551368141795}, {"step": 173, "kl": 0.2337920499991504, "ce": 0.49990042236419174}, {"step": 174, "kl": 0.24517722115755786, "ce": 0.6030932884226408}, {"step": 175, "kl": 0.23085446706673154, "ce": 0.6058258648813847}, {"step": 176, "kl": 0.19490715159968958, "ce": 0.43287460095904245}, {"step": 177, "kl": 0.22238560149737635, "ce": 0.6459135413826156}, {"step": 178, "kl": 0.20048344123195985, "ce": 0.4666101077113469}, {"step": 179, "kl": 0.29499169542649395, "ce": 0.5698365393937435}, {"step": 180, "kl": 0.29294501489009384, "ce": 0.5563151941732657}, {"step": 181, "kl": 0.1949063370956746, "ce": 0.5229342494437055}, {"step": 182, "kl": 0.211389386996424, "ce": 0.6192917791364363}, {"step": 183, "kl": 0.2807456584164863, "ce": 0.5370715171255888}, {"step": 184, "kl": 0.22965451515840937, "ce": 0.5454298756313152}, {"step": 185, "kl": 0.3945839362425046, "ce": 0.5252566610538526}, {"step": 186, "kl": 0.3430600978505102, "ce": 0.5233167355741709}, {"step": 187, "kl": 0.2725504759850187, "ce": 0.5571657978866527}, {"step": 188, "kl": 0.2601869703555851, "ce": 0.5812643838095499}, {"step": 189, "kl": 0.2615332858958038, "ce": 0.5381743452092163}, {"step": 190, "kl": 0.2167631594991567, "ce": 0.5265082482164442}, {"step": 191, "kl": 0.22373333777255477, "ce": 0.49647614421676034}, {"step": 192, "kl": 0.2616116197025105, "ce": 0.6437448641324692}, {"step": 193, "kl": 0.23903818168367438, "ce": 0.5586823086718429}, {"step": 194, "kl": 0.21893230180420942, "ce": 0.6106612504312283}, {"step": 195, "kl": 0.25928095046279886, "ce": 0.5867245382588269}, {"step": 196, "kl": 0.21057471616146436, "ce": 0.468037136936687}, {"step": 197, "kl": 0.19163374605419098, "ce": 0.5540104747444861}, {"step": 198, "kl": 0.2412905808528017, "ce": 0.5500987767466583}, {"step": 199, "kl": 0.28567219500090757, "ce": 0.6180155507676465}, {"step": 200, "kl": 0.29097701255427416, "ce": 0.5224439972865864}, {"step": 201, "kl": 0.22459001073097049, "ce": 0.5321884091482514}, {"step": 202, "kl": 0.23068828279630677, "ce": 0.6233059815303839}, {"step": 203, "kl": 0.2292530768669128, "ce": 0.5186977448821937}, {"step": 204, "kl": 0.23532623833583383, "ce": 0.4983962623784329}, {"step": 205, "kl": 0.43893244515028185, "ce": 0.5539906856600798}, {"step": 206, "kl": 0.245144930836049, "ce": 0.4836702220468687}, {"step": 207, "kl": 0.6978732135838317, "ce": 0.5930700778418175}, {"step": 208, "kl": 0.2176043601488585, "ce": 0.5146220705270967}, {"step": 209, "kl": 0.2465485226669808, "ce": 0.6366562088987588}, {"step": 210, "kl": 0.23029074799211707, "ce": 0.5034728071054517}, {"step": 211, "kl": 0.2164007104905532, "ce": 0.48407951813032885}, {"step": 212, "kl": 0.20913196328079917, "ce": 0.5562789510905715}, {"step": 213, "kl": 0.2831978998686138, "ce": 0.5364780065777537}, {"step": 214, "kl": 0.28738595764802377, "ce": 0.45389127130772666}, {"step": 215, "kl": 0.22133388838898244, "ce": 0.6103676602820255}, {"step": 216, "kl": 0.35387923281989253, "ce": 0.6285825840309986}, {"step": 217, "kl": 0.22240159969576034, "ce": 0.6418952737900026}, {"step": 218, "kl": 0.2914312679089254, "ce": 0.6715829378685687}, {"step": 219, "kl": 0.20673451059767955, "ce": 0.5479989475047095}, {"step": 220, "kl": 0.29009812274335933, "ce": 0.6836988612656156}, {"step": 221, "kl": 0.22957341929972147, "ce": 0.6395219093343172}, {"step": 222, "kl": 0.19590571056152384, "ce": 0.5258011088219827}, {"step": 223, "kl": 0.19988725260234202, "ce": 0.4918702262306033}, {"step": 224, "kl": 0.2272211764807643, "ce": 0.5710521567451591}, {"step": 225, "kl": 0.35015606006402616, "ce": 0.5188735470406239}, {"step": 226, "kl": 0.19643988747253244, "ce": 0.49858419773238777}, {"step": 227, "kl": 0.2543947467863006, "ce": 0.6251240339308279}, {"step": 228, "kl": 0.23734818547807407, "ce": 0.6204472332216573}, {"step": 229, "kl": 0.22191427965976357, "ce": 0.49455984397520225}, {"step": 230, "kl": 0.23920513143500044, "ce": 0.37767033774839176}, {"step": 231, "kl": 0.21972623316052703, "ce": 0.5476911893486406}, {"step": 232, "kl": 0.22499104966884004, "ce": 0.613051566460942}, {"step": 233, "kl": 0.22941574150459465, "ce": 0.5349023421731776}, {"step": 234, "kl": 0.2252964461340472, "ce": 0.5890850396169164}, {"step": 235, "kl": 0.22563248783648648, "ce": 0.5353225179256459}, {"step": 236, "kl": 0.6024078616687495, "ce": 0.5347150775858527}, {"step": 237, "kl": 0.24702949409339026, "ce": 0.606220972271329}, {"step": 238, "kl": 0.44373936806955644, "ce": 0.6177571444274074}, {"step": 239, "kl": 0.20176026370380779, "ce": 0.5823541433657906}, {"step": 240, "kl": 0.24844561550750752, "ce": 0.45811241106553513}, {"step": 241, "kl": 0.23975159879996583, "ce": 0.5383044401535921}, {"step": 242, "kl": 0.20409644695959817, "ce": 0.5324906055210695}, {"step": 243, "kl": 0.32858241032869884, "ce": 0.5753457180655334}, {"step": 244, "kl": 0.2180624732418337, "ce": 0.5415775248558864}, {"step": 245, "kl": 0.27108455128295517, "ce": 0.5822706887888354}, {"step": 246, "kl": 0.18866145199194795, "ce": 0.4926380487044806}, {"step": 247, "kl": 0.1978630084710832, "ce": 0.49813411342212766}, {"step": 248, "kl": 0.25212634584438876, "ce": 0.5686331896582751}, {"step": 249, "kl": 0.22241106100691233, "ce": 0.49490406741956827}, {"step": 250, "kl": 0.265585128379004, "ce": 0.655095009319113}, {"step": 251, "kl": 0.21888664369543498, "ce": 0.41303359957393687}, {"step": 252, "kl": 0.23757736327875692, "ce": 0.5920870586951599}, {"step": 253, "kl": 0.36843250790143534, "ce": 0.6111537952026218}, {"step": 254, "kl": 0.24552360299074288, "ce": 0.6956613152325002}, {"step": 255, "kl": 0.24481089543170875, "ce": 0.6019308518524539}, {"step": 256, "kl": 0.24432977747409226, "ce": 0.5742177496121714}, {"step": 257, "kl": 0.3596428919329434, "ce": 0.5752736859443859}, {"step": 258, "kl": 0.2271831887129019, "ce": 0.49345759531897954}, {"step": 259, "kl": 0.21722927651575405, "ce": 0.4909831524189668}, {"step": 260, "kl": 0.20597829667535103, "ce": 0.4371301054514642}, {"step": 261, "kl": 0.27390691693623864, "ce": 0.5136548056798672}, {"step": 262, "kl": 0.29800084993070286, "ce": 0.560805598532323}, {"step": 263, "kl": 0.22868539390330792, "ce": 0.4865601285611419}, {"step": 264, "kl": 0.21484608573862202, "ce": 0.5063843719578843}, {"step": 265, "kl": 0.21293111132093853, "ce": 0.552067357298786}, {"step": 266, "kl": 0.22868536700873662, "ce": 0.42873388142685626}, {"step": 267, "kl": 0.21213030138995578, "ce": 0.43597496333389296}, {"step": 268, "kl": 0.23110524159413318, "ce": 0.5764305392783049}, {"step": 269, "kl": 0.3188075638184711, "ce": 0.5467764821817017}, {"step": 270, "kl": 0.23441810646492559, "ce": 0.6538184064097531}, {"step": 271, "kl": 0.2421007451503191, "ce": 0.608056103222514}, {"step": 272, "kl": 0.2584586199624552, "ce": 0.5242680896314057}, {"step": 273, "kl": 0.23337189944856881, "ce": 0.6149604864163122}, {"step": 274, "kl": 0.20391650857383076, "ce": 0.5481980994972023}, {"step": 275, "kl": 0.22977557710367583, "ce": 0.41612386418969594}, {"step": 276, "kl": 0.24796287270271317, "ce": 0.569554372052728}, {"step": 277, "kl": 0.21760957976744955, "ce": 0.5309327694487277}, {"step": 278, "kl": 0.28076524034890427, "ce": 0.5088546487536593}, {"step": 279, "kl": 0.195407850240229, "ce": 0.5108440697734171}, {"step": 280, "kl": 0.41357014664964264, "ce": 0.6524492982196324}, {"step": 281, "kl": 0.338014362785933, "ce": 0.6399922116646627}, {"step": 282, "kl": 0.2055853328713681, "ce": 0.5493174989118454}, {"step": 283, "kl": 0.22613373466457048, "ce": 0.6107623032928123}, {"step": 284, "kl": 0.20498396784211564, "ce": 0.43190256277694217}, {"step": 285, "kl": 0.23466265805562336, "ce": 0.5766634687086248}, {"step": 286, "kl": 0.20158627128614073, "ce": 0.5450823297049741}, {"step": 287, "kl": 0.2367279283521957, "ce": 0.49708955524334497}, {"step": 288, "kl": 0.2387634150016647, "ce": 0.6132583989725484}, {"step": 289, "kl": 0.25127412058250387, "ce": 0.5541227392932687}, {"step": 290, "kl": 0.24118186396038907, "ce": 0.5286291946589147}, {"step": 291, "kl": 0.2102598088560823, "ce": 0.48003032057739276}, {"step": 292, "kl": 0.25042364231530057, "ce": 0.5762436030681042}, {"step": 293, "kl": 0.2243670091905801, "ce": 0.5939288749553449}, {"step": 294, "kl": 0.23158408103302672, "ce": 0.5212080891375428}, {"step": 295, "kl": 0.22352440106077068, "ce": 0.4982515598336856}, {"step": 296, "kl": 0.24923437172570972, "ce": 0.6191149003453955}, {"step": 297, "kl": 0.5371592400692764, "ce": 0.5807544169043689}, {"step": 298, "kl": 0.24522163316813694, "ce": 0.49155060205040874}, {"step": 299, "kl": 0.20828605978919845, "ce": 0.5379950567926571}, {"step": 300, "kl": 0.2562316920704131, "ce": 0.6029620595680651}, {"step": 301, "kl": 0.23816822312314068, "ce": 0.5025438972773169}, {"step": 302, "kl": 0.23140495507567177, "ce": 0.6149523396560561}, {"step": 303, "kl": 0.2574407589670172, "ce": 0.5459256386635682}, {"step": 304, "kl": 0.22912035301817416, "ce": 0.5219314021890731}, {"step": 305, "kl": 0.23841027646809704, "ce": 0.4146835187632957}, {"step": 306, "kl": 0.23786717704452792, "ce": 0.5948166391777486}, {"step": 307, "kl": 0.2525563021890478, "ce": 0.5011499449229231}, {"step": 308, "kl": 0.22302853368856376, "ce": 0.4776782089268464}, {"step": 309, "kl": 0.25960774655805796, "ce": 0.4726002360223054}, {"step": 310, "kl": 0.30483403123907665, "ce": 0.4974829255283591}, {"step": 311, "kl": 0.2250570840584446, "ce": 0.5552733967831963}, {"step": 312, "kl": 0.21640630682245682, "ce": 0.4987732112607477}, {"step": 313, "kl": 0.25121136660075316, "ce": 0.5069911541289567}, {"step": 314, "kl": 0.22271338960333212, "ce": 0.54936154650557}, {"step": 315, "kl": 0.20722026957825368, "ce": 0.4159388951295932}, {"step": 316, "kl": 0.2612020505548516, "ce": 0.5957691901817248}, {"step": 317, "kl": 0.18794513073151115, "ce": 0.46903337073366314}, {"step": 318, "kl": 0.32827652078887215, "ce": 0.4849385859124541}, {"step": 319, "kl": 0.24389180099647148, "ce": 0.475953425735424}, {"step": 320, "kl": 0.25931765851184113, "ce": 0.5174994521221143}, {"step": 321, "kl": 0.22739643556041578, "ce": 0.480527748073711}, {"step": 322, "kl": 0.23254988467085927, "ce": 0.44419037642332826}, {"step": 323, "kl": 0.22155669744334708, "ce": 0.5662406344594005}, {"step": 324, "kl": 0.19440866836310347, "ce": 0.5270658676489226}, {"step": 325, "kl": 0.20725257017880144, "ce": 0.5618051443086562}, {"step": 326, "kl": 0.23117879918299272, "ce": 0.5360772624684644}, {"step": 327, "kl": 0.2530225710429903, "ce": 0.6296864153257011}, {"step": 328, "kl": 0.3220211104263228, "ce": 0.49034791768983355}, {"step": 329, "kl": 0.2482384027601251, "ce": 0.7020343600867507}, {"step": 330, "kl": 0.27252080906217024, "ce": 0.5180571773018512}, {"step": 331, "kl": 0.23201756881455246, "ce": 0.7080922271708496}, {"step": 332, "kl": 0.27095278134614365, "ce": 0.4988382899394671}, {"step": 333, "kl": 0.19658070158534438, "ce": 0.47601161605809833}, {"step": 334, "kl": 0.25067172830131557, "ce": 0.5091808637836407}, {"step": 335, "kl": 0.23039491794891326, "ce": 0.6509070771730134}, {"step": 336, "kl": 0.2286734179391191, "ce": 0.5192720741518723}, {"step": 337, "kl": 0.2504012740442973, "ce": 0.5790344954715333}, {"step": 338, "kl": 0.2169341642628071, "ce": 0.5785263487570288}, {"step": 339, "kl": 0.19404382821775723, "ce": 0.5672061649086816}, {"step": 340, "kl": 0.29803666097748743, "ce": 0.5182177702585855}, {"step": 341, "kl": 0.23415492351590622, "ce": 0.5810519327132643}, {"step": 342, "kl": 0.22940866715098981, "ce": 0.5340348103181204}, {"step": 343, "kl": 0.22292843709233073, "ce": 0.5588976883782142}, {"step": 344, "kl": 0.18899059872435928, "ce": 0.4775099144794652}, {"step": 345, "kl": 0.23379289982749624, "ce": 0.406466438241948}, {"step": 346, "kl": 0.24631662330495815, "ce": 0.5650931367407891}, {"step": 347, "kl": 0.21287068963121042, "ce": 0.4499453030623399}, {"step": 348, "kl": 0.35125910018711903, "ce": 0.6752248649004781}, {"step": 349, "kl": 0.27918553359201165, "ce": 0.5134856602492408}, {"step": 350, "kl": 0.21608782352538872, "ce": 0.5678290140345558}, {"step": 351, "kl": 0.21468506308093455, "ce": 0.6030567496832162}, {"step": 352, "kl": 0.2682092745694247, "ce": 0.6363284783397647}, {"step": 353, "kl": 0.25883702939618947, "ce": 0.42317745459340783}, {"step": 354, "kl": 0.20224609936982327, "ce": 0.559235698955475}, {"step": 355, "kl": 0.20106881031844012, "ce": 0.538010576747146}, {"step": 356, "kl": 0.22161666543559133, "ce": 0.583128968398034}, {"step": 357, "kl": 0.21398223234004324, "ce": 0.44353389472854576}, {"step": 358, "kl": 0.21444794962827088, "ce": 0.476684403520377}, {"step": 359, "kl": 0.18722664978356715, "ce": 0.5559886329571724}, {"step": 360, "kl": 0.2066889120537192, "ce": 0.48503829539066023}, {"step": 361, "kl": 0.19040226400715032, "ce": 0.49824747228667726}, {"step": 362, "kl": 0.2691519735730684, "ce": 0.6250050294168804}, {"step": 363, "kl": 0.5320019846906231, "ce": 0.5868981125927294}, {"step": 364, "kl": 0.2539158964860003, "ce": 0.6078604664179181}, {"step": 365, "kl": 0.22208822881736212, "ce": 0.5376954840388491}, {"step": 366, "kl": 0.2523116213704317, "ce": 0.5601079078334299}, {"step": 367, "kl": 0.22378400069181556, "ce": 0.5144483234976621}, {"step": 368, "kl": 0.2591538531672207, "ce": 0.7593990264962253}, {"step": 369, "kl": 0.2796925946505956, "ce": 0.6564348402229547}, {"step": 370, "kl": 0.24500952562580386, "ce": 0.6375650210910373}, {"step": 371, "kl": 0.23150038503019157, "ce": 0.5387308122151997}, {"step": 372, "kl": 0.21267798581654115, "ce": 0.4821498136115585}, {"step": 373, "kl": 0.2478898750281499, "ce": 0.6250617141926968}, {"step": 374, "kl": 0.30928904029852655, "ce": 0.4756815302338251}, {"step": 375, "kl": 0.24311033577839228, "ce": 0.6035221528747166}, {"step": 376, "kl": 0.20056260016865726, "ce": 0.619870913152993}, {"step": 377, "kl": 0.26154135573093873, "ce": 0.5586315440150198}, {"step": 378, "kl": 0.21132060533707206, "ce": 0.44383788073223096}, {"step": 379, "kl": 0.36081114743368775, "ce": 0.5343672228311824}, {"step": 380, "kl": 0.3805773647678872, "ce": 0.4284809114014892}, {"step": 381, "kl": 0.3136153959420625, "ce": 0.5444843008163127}, {"step": 382, "kl": 0.23380089988676134, "ce": 0.4575199411359177}, {"step": 383, "kl": 0.2536294811387453, "ce": 0.4594885024108658}, {"step": 384, "kl": 0.1896139512090464, "ce": 0.3791133740458626}, {"step": 385, "kl": 0.32749981145226764, "ce": 0.6296925798942585}, {"step": 386, "kl": 0.28932384090291385, "ce": 0.635332782249319}, {"step": 387, "kl": 0.24670092905530766, "ce": 0.45430129715334694}, {"step": 388, "kl": 0.22045462985437908, "ce": 0.5399433445855271}, {"step": 389, "kl": 0.3056105277749734, "ce": 0.5449735921983574}, {"step": 390, "kl": 0.21566682211908159, "ce": 0.4797761365644078}, {"step": 391, "kl": 0.25436313847430075, "ce": 0.6309090176251357}, {"step": 392, "kl": 0.2119873342538141, "ce": 0.5338064240118188}, {"step": 393, "kl": 0.2184163673823915, "ce": 0.5139164775364481}, {"step": 394, "kl": 0.4692136482886224, "ce": 0.6211413464065063}, {"step": 395, "kl": 0.36066410879855637, "ce": 0.5244243670102758}, {"step": 396, "kl": 0.34636058937781794, "ce": 0.5969816551612881}, {"step": 397, "kl": 0.22192911556184278, "ce": 0.4995175698275939}, {"step": 398, "kl": 0.2779677955826234, "ce": 0.506249169790298}, {"step": 399, "kl": 0.21461301188742968, "ce": 0.5400473175311071}, {"step": 400, "kl": 0.5565789738455372, "ce": 0.6535393257132592}, {"step": 401, "kl": 0.2091832106897195, "ce": 0.4417350068886171}, {"step": 402, "kl": 0.21205818101960303, "ce": 0.5387231460018763}, {"step": 403, "kl": 0.2230076001295801, "ce": 0.4297923853335478}, {"step": 404, "kl": 0.2173731583776586, "ce": 0.6462747152173641}, {"step": 405, "kl": 0.3283777455874058, "ce": 0.5951191728765315}, {"step": 406, "kl": 0.28117136909516816, "ce": 0.6528495212898044}, {"step": 407, "kl": 0.38297300482380825, "ce": 0.5517644245905092}, {"step": 408, "kl": 0.24288166802900146, "ce": 0.46602666632981127}, {"step": 409, "kl": 0.21527513126575445, "ce": 0.7363312778188221}, {"step": 410, "kl": 0.23539834421674594, "ce": 0.5042083674839565}, {"step": 411, "kl": 0.3811194733847152, "ce": 0.5572678704671846}, {"step": 412, "kl": 0.2362238681646255, "ce": 0.5704509793083643}, {"step": 413, "kl": 0.20218669879363926, "ce": 0.4397420560970098}, {"step": 414, "kl": 0.2779515751682354, "ce": 0.435934812696459}, {"step": 415, "kl": 0.276109530835388, "ce": 0.5604947500099424}, {"step": 416, "kl": 0.24606235508015334, "ce": 0.5054209160520218}, {"step": 417, "kl": 0.2271993303615535, "ce": 0.574910468517687}, {"step": 418, "kl": 0.2777429295241801, "ce": 0.5959325939695411}, {"step": 419, "kl": 0.234441054572366, "ce": 0.4311820701611048}, {"step": 420, "kl": 0.23509862174004537, "ce": 0.6069202285593742}, {"step": 421, "kl": 0.21392739299827873, "ce": 0.49041181634068853}, {"step": 422, "kl": 0.2076356402074235, "ce": 0.4006147832938211}, {"step": 423, "kl": 0.2928265838870239, "ce": 0.6204568837255641}, {"step": 424, "kl": 0.25852942085277986, "ce": 0.5193125757507977}, {"step": 425, "kl": 0.2094228171161186, "ce": 0.5694522610713032}, {"step": 426, "kl": 0.22494557071325405, "ce": 0.6553293194770813}, {"step": 427, "kl": 0.2494592605411566, "ce": 0.6068314331944743}, {"step": 428, "kl": 1.0142748028104822, "ce": 0.5622812734264694}, {"step": 429, "kl": 0.23638592156838245, "ce": 0.3736455447507524}, {"step": 430, "kl": 0.2369094707622105, "ce": 0.6330306774017108}, {"step": 431, "kl": 0.22852420083138936, "ce": 0.7138021971890118}, {"step": 432, "kl": 0.24231872460947915, "ce": 0.5804967769884051}, {"step": 433, "kl": 0.3720783836271134, "ce": 0.4044902434755705}, {"step": 434, "kl": 0.27720109643758123, "ce": 0.5154346091582664}, {"step": 435, "kl": 0.2292232543334642, "ce": 0.4099014862101003}, {"step": 436, "kl": 0.33886003272290255, "ce": 0.4319776476341485}, {"step": 437, "kl": 0.21921772132742723, "ce": 0.5539281491428844}, {"step": 438, "kl": 0.43004890162743536, "ce": 0.6101915066092555}, {"step": 439, "kl": 0.23872651306948225, "ce": 0.5205985619802774}, {"step": 440, "kl": 0.20119814819918305, "ce": 0.5556019166141939}, {"step": 441, "kl": 0.22460764080112977, "ce": 0.5922802444256027}, {"step": 442, "kl": 0.32921855909782544, "ce": 0.6211184290529208}, {"step": 443, "kl": 0.3938099275152367, "ce": 0.5833879783714759}, {"step": 444, "kl": 0.2344265220298828, "ce": 0.5402540481046986}, {"step": 445, "kl": 0.31607616221045864, "ce": 0.5512876460973086}, {"step": 446, "kl": 0.21178354109302683, "ce": 0.5034433133134218}, {"step": 447, "kl": 0.24225928439750327, "ce": 0.6312264342579347}, {"step": 448, "kl": 0.2251375606416375, "ce": 0.4755679068130567}, {"step": 449, "kl": 0.270851374538493, "ce": 0.35912898837503726}, {"step": 450, "kl": 0.2264729782103512, "ce": 0.510526146356046}, {"step": 451, "kl": 0.21719605919159857, "ce": 0.32193858020368027}, {"step": 452, "kl": 0.22643129518643187, "ce": 0.4054668147649414}, {"step": 453, "kl": 0.22282982845765587, "ce": 0.35881426937919914}, {"step": 454, "kl": 0.25331889051334766, "ce": 0.31647551350477265}, {"step": 455, "kl": 0.29392132094102413, "ce": 0.3639178868064132}, {"step": 456, "kl": 0.2612193144214858, "ce": 0.40635466838305967}, {"step": 457, "kl": 0.422220485316954, "ce": 0.3843720459574692}, {"step": 458, "kl": 0.2645851397445566, "ce": 0.3967926596748062}, {"step": 459, "kl": 0.2647105479180414, "ce": 0.3983158832663278}, {"step": 460, "kl": 0.21628303372168034, "ce": 0.4001986706843142}, {"step": 461, "kl": 0.22592138289628771, "ce": 0.3886873837406424}, {"step": 462, "kl": 0.2259686987645547, "ce": 0.43528743430133504}, {"step": 463, "kl": 0.2944621869326821, "ce": 0.3853882413193967}, {"step": 464, "kl": 0.3440172415737533, "ce": 0.4038865711648635}, {"step": 465, "kl": 0.253077890131748, "ce": 0.33169503389038985}, {"step": 466, "kl": 0.22957103582801128, "ce": 0.3382117664289701}, {"step": 467, "kl": 0.31377568358351104, "ce": 0.39321774519165203}, {"step": 468, "kl": 0.32626656911045565, "ce": 0.43277010389168347}, {"step": 469, "kl": 0.23309079074563754, "ce": 0.37213824672769874}, {"step": 470, "kl": 0.2734345276618059, "ce": 0.2971017411414613}, {"step": 471, "kl": 0.38802525851839764, "ce": 0.5018243701850936}, {"step": 472, "kl": 0.20689467004233508, "ce": 0.24749560503269427}, {"step": 473, "kl": 0.3042721827695265, "ce": 0.3301847572657961}, {"step": 474, "kl": 0.2542815604682717, "ce": 0.31064952814667157}, {"step": 475, "kl": 0.2231427168111843, "ce": 0.34661413529241236}, {"step": 476, "kl": 0.19988837993341202, "ce": 0.360905284947024}, {"step": 477, "kl": 0.21370622046859974, "ce": 0.3406088337602056}, {"step": 478, "kl": 0.274886659622071, "ce": 0.4311921072754472}, {"step": 479, "kl": 0.379293805899406, "ce": 0.429805147098396}, {"step": 480, "kl": 0.2276339211578679, "ce": 0.3533776435070615}, {"step": 481, "kl": 0.2422926370311837, "ce": 0.3339213128504769}, {"step": 482, "kl": 0.7211053510861583, "ce": 0.3839274160261077}, {"step": 483, "kl": 0.22134728227162853, "ce": 0.36737344925662124}, {"step": 484, "kl": 0.2299704905814378, "ce": 0.5048291670867388}, {"step": 485, "kl": 0.23712242494916635, "ce": 0.3614124975969919}, {"step": 486, "kl": 0.3861513278916958, "ce": 0.3112187068814231}, {"step": 487, "kl": 0.4869997089570869, "ce": 0.3611783045756666}, {"step": 488, "kl": 0.2953716966818889, "ce": 0.38504173993900015}, {"step": 489, "kl": 0.24078488371297382, "ce": 0.3456253503398569}, {"step": 490, "kl": 0.22577337714377832, "ce": 0.33423748277403564}, {"step": 491, "kl": 0.40125413107754127, "ce": 0.3774806239783004}, {"step": 492, "kl": 0.32366310270659293, "ce": 0.37599822760041496}, {"step": 493, "kl": 0.22955967252723344, "ce": 0.42831832389800356}, {"step": 494, "kl": 0.28150355922339404, "ce": 0.34625536655110234}, {"step": 495, "kl": 0.2006317844802336, "ce": 0.3431492648816755}, {"step": 496, "kl": 0.24033273786506396, "ce": 0.4540323311427854}, {"step": 497, "kl": 0.2570690332457076, "ce": 0.3410381252864076}, {"step": 498, "kl": 0.30260537492296413, "ce": 0.39074953130638024}, {"step": 499, "kl": 0.20731463336543693, "ce": 0.3751768548284943}, {"step": 500, "kl": 0.23106919440127344, "ce": 0.4133573552742261}, {"step": 501, "kl": 0.22049211047314177, "ce": 0.38475861453353644}, {"step": 502, "kl": 0.24085026222555472, "ce": 0.45362357930614744}, {"step": 503, "kl": 0.34661747751275374, "ce": 0.29591427690600003}, {"step": 504, "kl": 0.3348753720844331, "ce": 0.42531985344393547}, {"step": 505, "kl": 0.20443600452374128, "ce": 0.3233611488342285}, {"step": 506, "kl": 0.3343116336637581, "ce": 0.3277569985929071}, {"step": 507, "kl": 0.4169050179470345, "ce": 0.4631222021083709}, {"step": 508, "kl": 0.2593883267289388, "ce": 0.49208830160440803}, {"step": 509, "kl": 0.35942407811590804, "ce": 0.30655251029238784}, {"step": 510, "kl": 0.42726023348980724, "ce": 0.3374678200978777}, {"step": 511, "kl": 0.21335079709746363, "ce": 0.3539023638206765}, {"step": 512, "kl": 0.4218423824490294, "ce": 0.3401703050710859}, {"step": 513, "kl": 0.21442582336717173, "ce": 0.38710756080415054}, {"step": 514, "kl": 0.2084203901674953, "ce": 0.3901705755797805}, {"step": 515, "kl": 0.3505269006301568, "ce": 0.2119211474700788}, {"step": 516, "kl": 0.3157833103028683, "ce": 0.4441640886686359}, {"step": 517, "kl": 0.20517662197432165, "ce": 0.37111809225939096}, {"step": 518, "kl": 0.32830099537403234, "ce": 0.45210908158168095}, {"step": 519, "kl": 0.25446070004269944, "ce": 0.37403996530078903}, {"step": 520, "kl": 0.25463525071751114, "ce": 0.35982476688157533}, {"step": 521, "kl": 0.23095079757142692, "ce": 0.44170460375506326}, {"step": 522, "kl": 0.2157833517318971, "ce": 0.4828236997003512}, {"step": 523, "kl": 0.23981377978314786, "ce": 0.3838137877287882}, {"step": 524, "kl": 0.25021764630434523, "ce": 0.4068331181230478}, {"step": 525, "kl": 0.21932529278390273, "ce": 0.30180029492001154}, {"step": 526, "kl": 0.23640199706791945, "ce": 0.395747219551353}, {"step": 527, "kl": 0.18880602877159228, "ce": 0.3399488592428446}, {"step": 528, "kl": 0.3053847400297371, "ce": 0.2951080434684678}, {"step": 529, "kl": 0.21203116862131519, "ce": 0.4053124877273059}, {"step": 530, "kl": 0.23298471212830052, "ce": 0.4740594744994106}, {"step": 531, "kl": 0.3282504875084994, "ce": 0.38389273952766556}, {"step": 532, "kl": 0.28424353318167467, "ce": 0.312141501349899}, {"step": 533, "kl": 0.25338531255072405, "ce": 0.30010431712528446}, {"step": 534, "kl": 0.2092536247153966, "ce": 0.4172678360572228}, {"step": 535, "kl": 0.30226022890298676, "ce": 0.27041662906203107}, {"step": 536, "kl": 0.2230545856334545, "ce": 0.38557956683237915}, {"step": 537, "kl": 0.2576654273459604, "ce": 0.3457049812792029}, {"step": 538, "kl": 0.20801714178069755, "ce": 0.3761644742886964}, {"step": 539, "kl": 0.24769473901356803, "ce": 0.35695203214167615}, {"step": 540, "kl": 0.22530904474866803, "ce": 0.38605555334355346}, {"step": 541, "kl": 0.21828413768938396, "ce": 0.4291966773790758}, {"step": 542, "kl": 0.21181827157423505, "ce": 0.2872725311249174}, {"step": 543, "kl": 0.37487160131342606, "ce": 0.4173361910597744}, {"step": 544, "kl": 0.23308105828955955, "ce": 0.3268093621068198}, {"step": 545, "kl": 0.2557062772157316, "ce": 0.3440171501508527}, {"step": 546, "kl": 0.35363312937541774, "ce": 0.3239939969521249}, {"step": 547, "kl": 0.2661629397829454, "ce": 0.3656597791773173}, {"step": 548, "kl": 0.23097960587889785, "ce": 0.41927995445459176}, {"step": 549, "kl": 0.21763853859001034, "ce": 0.3075400794476317}, {"step": 550, "kl": 0.25287308345354775, "ce": 0.2559234060557825}, {"step": 551, "kl": 0.23491063514468072, "ce": 0.3729689125702759}, {"step": 552, "kl": 0.22003932080535976, "ce": 0.4183045521883873}, {"step": 553, "kl": 0.22628834021037522, "ce": 0.33291169877562427}, {"step": 554, "kl": 0.23303598102397377, "ce": 0.41886547112486217}, {"step": 555, "kl": 0.224391101106, "ce": 0.43437456224785476}, {"step": 556, "kl": 0.21422469232851177, "ce": 0.37415278190411}, {"step": 557, "kl": 0.25958637655695044, "ce": 0.43150544134793956}, {"step": 558, "kl": 0.2406181028637106, "ce": 0.32831435160447403}, {"step": 559, "kl": 0.21119874764002877, "ce": 0.40777063297228217}, {"step": 560, "kl": 0.4760740677307608, "ce": 0.327985804571422}, {"step": 561, "kl": 0.28116393665989226, "ce": 0.3747610188610858}, {"step": 562, "kl": 0.20991511341382055, "ce": 0.31347000028458105}, {"step": 563, "kl": 0.3593356022671147, "ce": 0.36699086778027534}, {"step": 564, "kl": 0.2607155411827321, "ce": 0.41561052151449257}, {"step": 565, "kl": 0.22314128123570218, "ce": 0.23765707847789058}, {"step": 566, "kl": 0.21514428386912413, "ce": 0.31382516921834747}, {"step": 567, "kl": 0.2257658890340666, "ce": 0.41489377611980927}, {"step": 568, "kl": 0.19518191561252246, "ce": 0.4179353804204403}, {"step": 569, "kl": 0.26474503224109, "ce": 0.37419368614851445}, {"step": 570, "kl": 1.0333625845421421, "ce": 0.45767276841491644}, {"step": 571, "kl": 0.2195915327098071, "ce": 0.29071138529435236}, {"step": 572, "kl": 0.2385381779579161, "ce": 0.3825777936680868}, {"step": 573, "kl": 0.25041106198928986, "ce": 0.40070750328030474}, {"step": 574, "kl": 0.21949912958927648, "ce": 0.3778955274989202}, {"step": 575, "kl": 0.2699646958424426, "ce": 0.4279150307386691}, {"step": 576, "kl": 0.22060491643019575, "ce": 0.3899697597671605}, {"step": 577, "kl": 0.25312726149862774, "ce": 0.38870949344174455}, {"step": 578, "kl": 0.24019250079805785, "ce": 0.32692951685198485}, {"step": 579, "kl": 0.3447339295867404, "ce": 0.36448383818143343}, {"step": 580, "kl": 0.5866639303403444, "ce": 0.3608767214090393}, {"step": 581, "kl": 0.2591132502008323, "ce": 0.46335324089308294}, {"step": 582, "kl": 0.2308428931495873, "ce": 0.3408542751992948}, {"step": 583, "kl": 0.5402898631004414, "ce": 0.3713041286457279}, {"step": 584, "kl": 0.25192215319554095, "ce": 0.30593039481985224}, {"step": 585, "kl": 0.24700930618323083, "ce": 0.3830830230232848}, {"step": 586, "kl": 0.21652110258984075, "ce": 0.5107041433604596}, {"step": 587, "kl": 0.21918206650555822, "ce": 0.32764554394861206}, {"step": 588, "kl": 0.3646194534054305, "ce": 0.2811705175484389}, {"step": 589, "kl": 0.24076569586437485, "ce": 0.30083776659392053}, {"step": 590, "kl": 0.19504401272601155, "ce": 0.3661525161481211}, {"step": 591, "kl": 0.23138010696924627, "ce": 0.33802834819222}, {"step": 592, "kl": 0.26335404077279667, "ce": 0.34021167050152096}, {"step": 593, "kl": 0.24030204112086656, "ce": 0.2860756855119358}, {"step": 594, "kl": 0.22542166671325645, "ce": 0.3925296978626497}, {"step": 595, "kl": 0.37301739625811514, "ce": 0.4092249533026506}, {"step": 596, "kl": 0.27399160076680823, "ce": 0.3981029508308209}, {"step": 597, "kl": 0.37437261975034664, "ce": 0.4019047764034641}, {"step": 598, "kl": 0.2721939372369622, "ce": 0.3418917636667222}, {"step": 599, "kl": 0.2645820904819647, "ce": 0.44488140898857365}, {"step": 600, "kl": 0.21987071875665176, "ce": 0.3496986267832086}, {"step": 601, "kl": 0.2600898392648189, "ce": 0.3960190395206973}, {"step": 602, "kl": 0.221001055109268, "ce": 0.2949700649214485}, {"step": 603, "kl": 0.23972880173552216, "ce": 0.3921821290629513}, {"step": 604, "kl": 0.20325932107114522, "ce": 0.302971647334014}, {"step": 605, "kl": 0.23344035970662308, "ce": 0.3957723350133052}, {"step": 606, "kl": 0.4448635168861113, "ce": 0.38063162157439473}, {"step": 607, "kl": 0.21894305700253233, "ce": 0.39385136821239297}, {"step": 608, "kl": 0.2537366960839106, "ce": 0.36397639372593776}, {"step": 609, "kl": 0.21268143162280917, "ce": 0.3487966722189149}, {"step": 610, "kl": 0.2121935388205363, "ce": 0.3488278346979968}, {"step": 611, "kl": 0.3913564215557006, "ce": 0.38434701329512566}, {"step": 612, "kl": 0.2746184469645525, "ce": 0.5063403965999644}, {"step": 613, "kl": 0.21855917202394637, "ce": 0.394059644799726}, {"step": 614, "kl": 0.21904711264197543, "ce": 0.30559626003223606}, {"step": 615, "kl": 0.24091789878239397, "ce": 0.3676992839803698}, {"step": 616, "kl": 0.21718427033182766, "ce": 0.33992780663894306}, {"step": 617, "kl": 0.27792231261472805, "ce": 0.41270106146841035}, {"step": 618, "kl": 0.3151432403276135, "ce": 0.48193211271517605}, {"step": 619, "kl": 0.2204276522047745, "ce": 0.3450787932552213}, {"step": 620, "kl": 0.5346912198991918, "ce": 0.3505463722125004}, {"step": 621, "kl": 0.2429312383714725, "ce": 0.33458451260911665}, {"step": 622, "kl": 0.22996015910340883, "ce": 0.4090982874457606}, {"step": 623, "kl": 0.23366412960946326, "ce": 0.4433348912890906}, {"step": 624, "kl": 0.36677546074616413, "ce": 0.4359086489229061}, {"step": 625, "kl": 0.22519632487271213, "ce": 0.37896804273515083}, {"step": 626, "kl": 0.8566707774380503, "ce": 0.3036709936542167}, {"step": 627, "kl": 0.22582987167853413, "ce": 0.3319409588771447}, {"step": 628, "kl": 0.558798713066992, "ce": 0.39894337103952254}, {"step": 629, "kl": 0.23814365675591992, "ce": 0.36633929104427027}, {"step": 630, "kl": 0.24982078259356816, "ce": 0.3063539602394385}, {"step": 631, "kl": 0.3372150462252285, "ce": 0.4134911417410385}, {"step": 632, "kl": 0.21190763451783073, "ce": 0.32865847264796305}, {"step": 633, "kl": 0.24882379740030167, "ce": 0.4804445437675162}, {"step": 634, "kl": 0.35762071159178666, "ce": 0.3902157702292516}, {"step": 635, "kl": 0.2766473342549591, "ce": 0.48220273717487594}, {"step": 636, "kl": 0.5241081753249778, "ce": 0.3497940540524431}, {"step": 637, "kl": 0.316062431448645, "ce": 0.4381894173626377}, {"step": 638, "kl": 0.24685090884551547, "ce": 0.38327228826083776}, {"step": 639, "kl": 0.2229987332422835, "ce": 0.3343204159090196}, {"step": 640, "kl": 0.32588487114519243, "ce": 0.40889901804758505}, {"step": 641, "kl": 0.2907060414994944, "ce": 0.3878744104089562}, {"step": 642, "kl": 0.3351295609985919, "ce": 0.4603759763745376}, {"step": 643, "kl": 1.9787010862169683, "ce": 0.32908181024191646}, {"step": 644, "kl": 0.2371276391603155, "ce": 0.37370643868351605}, {"step": 645, "kl": 0.2206719065088275, "ce": 0.29911987580774857}, {"step": 646, "kl": 0.20828876397029028, "ce": 0.3502161518986214}, {"step": 647, "kl": 0.2138104126418846, "ce": 0.3711908063486054}, {"step": 648, "kl": 0.22654541835675088, "ce": 0.37855418950426106}, {"step": 649, "kl": 0.39802788530411687, "ce": 0.35727032891635235}, {"step": 650, "kl": 0.3129331702650012, "ce": 0.3542821356900938}, {"step": 651, "kl": 0.240321496529578, "ce": 0.33600549104841854}, {"step": 652, "kl": 0.22030216456570167, "ce": 0.36730277297365027}, {"step": 653, "kl": 0.21069706040428993, "ce": 0.32282519340515137}, {"step": 654, "kl": 0.22083340516092892, "ce": 0.3701610043382398}, {"step": 655, "kl": 0.19918689252176064, "ce": 0.3386547966586875}, {"step": 656, "kl": 0.21348769019708339, "ce": 0.3203476625664642}, {"step": 657, "kl": 0.21233324734669812, "ce": 0.33855058248050673}, {"step": 658, "kl": 0.33672699378021453, "ce": 0.34147661880104263}, {"step": 659, "kl": 0.22809744631764178, "ce": 0.27065193521397446}, {"step": 660, "kl": 0.2291303175081465, "ce": 0.35732173733912104}, {"step": 661, "kl": 0.6416088527334226, "ce": 0.5659649877259135}, {"step": 662, "kl": 0.21889611024762548, "ce": 0.37561420308804816}, {"step": 663, "kl": 0.34382242447471884, "ce": 0.3458307743562243}, {"step": 664, "kl": 0.2591228757208189, "ce": 0.3741398217755433}, {"step": 665, "kl": 0.9002229116462603, "ce": 0.38822584376232716}, {"step": 666, "kl": 0.22799384706502152, "ce": 0.4636759238743335}, {"step": 667, "kl": 0.20465548224386204, "ce": 0.4299030884290104}, {"step": 668, "kl": 0.24929351967502866, "ce": 0.3726425651125433}, {"step": 669, "kl": 0.34932345864422587, "ce": 0.3989662256330186}, {"step": 670, "kl": 0.25579223720305555, "ce": 0.3594961530449582}, {"step": 671, "kl": 0.34890159303015406, "ce": 0.33427783066525113}, {"step": 672, "kl": 0.21196343369580703, "ce": 0.3279501565969965}, {"step": 673, "kl": 0.27194257620549767, "ce": 0.3642530825956609}, {"step": 674, "kl": 0.2206474360406045, "ce": 0.30453478375668125}, {"step": 675, "kl": 0.2149354488114038, "ce": 0.34137394479758904}, {"step": 676, "kl": 0.26961515959318694, "ce": 0.28047911900809486}, {"step": 677, "kl": 0.2379206907218541, "ce": 0.35776465759430853}, {"step": 678, "kl": 0.22594368292801975, "ce": 0.32608352214822905}, {"step": 679, "kl": 0.2241578598423521, "ce": 0.385370863405323}, {"step": 680, "kl": 0.2990502100711892, "ce": 0.5021146639640238}, {"step": 681, "kl": 0.24969597222747836, "ce": 0.3526581819215069}, {"step": 682, "kl": 0.24844894390764544, "ce": 0.38178937852511474}, {"step": 683, "kl": 0.24953650177832093, "ce": 0.32802141571401766}, {"step": 684, "kl": 0.524789364641925, "ce": 0.4055698360307649}, {"step": 685, "kl": 0.2115696180386942, "ce": 0.4091577765357522}, {"step": 686, "kl": 0.22991749639766257, "ce": 0.3230770924886068}, {"step": 687, "kl": 0.34800705606240406, "ce": 0.38664028085598995}, {"step": 688, "kl": 0.31463327547587067, "ce": 0.3424260232739679}, {"step": 689, "kl": 0.2651126037903519, "ce": 0.4650757085242536}, {"step": 690, "kl": 0.2814844522100621, "ce": 0.4144638008340079}, {"step": 691, "kl": 0.23436959859494663, "ce": 0.4025794137578724}, {"step": 692, "kl": 0.239679426323064, "ce": 0.3314110553880477}, {"step": 693, "kl": 0.5118697714492269, "ce": 0.29402209545025926}, {"step": 694, "kl": 0.3004835604810628, "ce": 0.36491507495552056}, {"step": 695, "kl": 0.2514098693988439, "ce": 0.32432942181026425}, {"step": 696, "kl": 0.30530254800128537, "ce": 0.34835481372288124}, {"step": 697, "kl": 0.2576491951061277, "ce": 0.40000633506393973}, {"step": 698, "kl": 0.39112615935464246, "ce": 0.44437361829061556}, {"step": 699, "kl": 0.5183310544154265, "ce": 0.42650267074069204}, {"step": 700, "kl": 0.2188789972725952, "ce": 0.3698925405027549}, {"step": 701, "kl": 0.2598251873948183, "ce": 0.47018947232243957}, {"step": 702, "kl": 0.21305989958188487, "ce": 0.41870243740022045}, {"step": 703, "kl": 0.20464064419269565, "ce": 0.38290894472556564}, {"step": 704, "kl": 0.33487449417920245, "ce": 0.3655379262877719}, {"step": 705, "kl": 0.2259287139899233, "ce": 0.32195673784589207}, {"step": 706, "kl": 0.23606939050433012, "ce": 0.3922817351891344}, {"step": 707, "kl": 0.2297812144330372, "ce": 0.44339421637307946}, {"step": 708, "kl": 0.22715417039608526, "ce": 0.31875050643670966}, {"step": 709, "kl": 0.292582662097711, "ce": 0.32208355493391627}, {"step": 710, "kl": 0.27588901425214507, "ce": 0.35254672590637925}, {"step": 711, "kl": 1.3665075975391905, "ce": 0.35948033753042014}, {"step": 712, "kl": 1.0682312772816838, "ce": 0.31370661736946476}, {"step": 713, "kl": 0.3048927851876836, "ce": 0.4625525487447451}, {"step": 714, "kl": 0.25009942954583964, "ce": 0.4624231186322797}, {"step": 715, "kl": 0.25745014845466285, "ce": 0.4725632786514736}, {"step": 716, "kl": 0.4298140955065153, "ce": 0.46328333748254935}, {"step": 717, "kl": 0.2137916900915827, "ce": 0.3021536815524268}, {"step": 718, "kl": 0.2878104739471605, "ce": 0.4243531680844781}, {"step": 719, "kl": 0.26013502721396364, "ce": 0.43216105506239855}, {"step": 720, "kl": 0.22727641109967123, "ce": 0.4348959546479617}, {"step": 721, "kl": 0.19900866678785464, "ce": 0.3173071026531201}, {"step": 722, "kl": 0.2130262751345638, "ce": 0.25883824542688993}, {"step": 723, "kl": 0.31687877750584614, "ce": 0.44776450788798383}, {"step": 724, "kl": 0.2836402305326504, "ce": 0.43384882956192183}, {"step": 725, "kl": 0.3555025717973315, "ce": 0.3275195586423743}, {"step": 726, "kl": 0.30719903124530995, "ce": 0.33775475239418173}, {"step": 727, "kl": 0.3010911513567168, "ce": 0.34561085199378194}, {"step": 728, "kl": 0.23538386509808717, "ce": 0.2964651936848958}, {"step": 729, "kl": 0.19230855735048452, "ce": 0.3701029941499028}, {"step": 730, "kl": 0.28749721388183463, "ce": 0.27595612120392093}, {"step": 731, "kl": 0.24401962733289154, "ce": 0.3064507772222185}, {"step": 732, "kl": 0.23163802963506805, "ce": 0.3860474781635957}, {"step": 733, "kl": 0.23817620447307075, "ce": 0.42033514068560474}, {"step": 734, "kl": 0.20919814690501157, "ce": 0.28661365858568144}, {"step": 735, "kl": 0.30954219290931223, "ce": 0.41757848238569883}, {"step": 736, "kl": 0.26300221248289085, "ce": 0.33371048332998177}, {"step": 737, "kl": 0.22681292422668675, "ce": 0.3262488512504666}, {"step": 738, "kl": 0.232698209313964, "ce": 0.38276569738022}, {"step": 739, "kl": 0.238386442980274, "ce": 0.3844370757655402}, {"step": 740, "kl": 0.2698297519610371, "ce": 0.41487748985128464}, {"step": 741, "kl": 0.2737004722174653, "ce": 0.47034653621788997}, {"step": 742, "kl": 0.21987150885410134, "ce": 0.37830847853194494}, {"step": 743, "kl": 0.3545442822021949, "ce": 0.3553248112595926}, {"step": 744, "kl": 0.24096573125657275, "ce": 0.37493783389466906}, {"step": 745, "kl": 0.25105327526442833, "ce": 0.31506378419207415}, {"step": 746, "kl": 0.3823071895092294, "ce": 0.344777861339634}, {"step": 747, "kl": 0.22302516588412577, "ce": 0.3592523120015571}, {"step": 748, "kl": 0.248282628756198, "ce": 0.37452004471616523}, {"step": 749, "kl": 0.24409896879971688, "ce": 0.4882618624366956}, {"step": 750, "kl": 0.22171442044195097, "ce": 0.38634128148592545}, {"step": 751, "kl": 0.32169605036042787, "ce": 0.3767664447762611}, {"step": 752, "kl": 0.25553896017374955, "ce": 0.4567989744879496}, {"step": 753, "kl": 0.20268912661348532, "ce": 0.4563510190835238}, {"step": 754, "kl": 0.2843149850907031, "ce": 0.4290223770200562}, {"step": 755, "kl": 0.2397185780451848, "ce": 0.4109719317892323}, {"step": 756, "kl": 0.4080396670594285, "ce": 0.33172735522817054}, {"step": 757, "kl": 0.3175989296874598, "ce": 0.2549769953836369}, {"step": 758, "kl": 0.23515567955258668, "ce": 0.41584635077536614}, {"step": 759, "kl": 0.2214622986735007, "ce": 0.32530496607189774}, {"step": 760, "kl": 0.21876563583662625, "ce": 0.3926377898073071}, {"step": 761, "kl": 0.18570445899580632, "ce": 0.39188061015285225}, {"step": 762, "kl": 0.19647269674917042, "ce": 0.3493873644460743}, {"step": 763, "kl": 0.2437713138568665, "ce": 0.3628337449567937}, {"step": 764, "kl": 0.19913958094205275, "ce": 0.275724489837197}, {"step": 765, "kl": 0.21023807426014304, "ce": 0.4369303873743877}, {"step": 766, "kl": 0.22907964512561174, "ce": 0.3881372827884248}, {"step": 767, "kl": 0.3292376339694013, "ce": 0.38836999054480636}, {"step": 768, "kl": 0.27798934445322326, "ce": 0.3871516922553583}, {"step": 769, "kl": 0.2270260009288415, "ce": 0.28573567055342874}, {"step": 770, "kl": 0.2605503747856901, "ce": 0.3925772237199225}, {"step": 771, "kl": 0.30655914839171133, "ce": 0.37585994173127074}, {"step": 772, "kl": 0.23456250971244166, "ce": 0.38023609953250237}, {"step": 773, "kl": 0.25016908607533705, "ce": 0.3931607354098072}, {"step": 774, "kl": 0.2424087722175448, "ce": 0.26330404959029907}, {"step": 775, "kl": 0.2341176476264604, "ce": 0.256546085712622}, {"step": 776, "kl": 0.2724458977821912, "ce": 0.44056269786125113}, {"step": 777, "kl": 0.33095547572501616, "ce": 0.31637737081462464}, {"step": 778, "kl": 0.29432698805837765, "ce": 0.4179214258732505}, {"step": 779, "kl": 0.19395837207570762, "ce": 0.3609058532082947}, {"step": 780, "kl": 0.24562468603336157, "ce": 0.3886180336443881}, {"step": 781, "kl": 0.19310337435047945, "ce": 0.3619937613597107}, {"step": 782, "kl": 0.7429086710162507, "ce": 0.48220800855152096}, {"step": 783, "kl": 0.22585136075150525, "ce": 0.34810815939742523}, {"step": 784, "kl": 0.2575488434071801, "ce": 0.3948383399395799}, {"step": 785, "kl": 0.3983416375644267, "ce": 0.3986584532770036}, {"step": 786, "kl": 0.2434865449662481, "ce": 0.41616470664870664}, {"step": 787, "kl": 0.515115479160188, "ce": 0.4897952465604247}, {"step": 788, "kl": 0.3192092268162606, "ce": 0.3774487085102508}, {"step": 789, "kl": 0.2666978719658788, "ce": 0.4018458675126545}, {"step": 790, "kl": 0.3265691916158559, "ce": 0.3525601796329742}, {"step": 791, "kl": 0.25149356582764154, "ce": 0.47392947366399263}, {"step": 792, "kl": 0.2054270065577332, "ce": 0.3170979716951295}, {"step": 793, "kl": 0.2575999128420023, "ce": 0.3519916416873515}, {"step": 794, "kl": 0.19106253678589008, "ce": 0.2858659828851834}, {"step": 795, "kl": 0.2378322628607967, "ce": 0.396931047361224}, {"step": 796, "kl": 0.37746425587533294, "ce": 0.39720732410604714}, {"step": 797, "kl": 0.20559079871930497, "ce": 0.2853682054398989}, {"step": 798, "kl": 0.2431098287732845, "ce": 0.33398071139496455}, {"step": 799, "kl": 0.21854908220970795, "ce": 0.382762713006379}, {"step": 800, "kl": 0.20762227368395567, "ce": 0.38316938925169464}, {"step": 801, "kl": 0.4223351700978749, "ce": 0.45658429360018565}, {"step": 802, "kl": 0.224183814814209, "ce": 0.3935516451828531}, {"step": 803, "kl": 0.31822704149045866, "ce": 0.38527003209329563}, {"step": 804, "kl": 0.4228292016157521, "ce": 0.41784550434606454}, {"step": 805, "kl": 0.25345677787775167, "ce": 0.2729947718239205}, {"step": 806, "kl": 0.4727570584790935, "ce": 0.4610729162886172}, {"step": 807, "kl": 0.2415203531700598, "ce": 0.4368219343074079}, {"step": 808, "kl": 0.2380543561360017, "ce": 0.3658042804894963}, {"step": 809, "kl": 0.37963787083741796, "ce": 0.4347003038170972}, {"step": 810, "kl": 0.2809761392945612, "ce": 0.4327821405665563}, {"step": 811, "kl": 0.31814303140118305, "ce": 0.3493448706782575}, {"step": 812, "kl": 0.2667603526246347, "ce": 0.42930599523798363}, {"step": 813, "kl": 0.21180319187303656, "ce": 0.27980518239573754}, {"step": 814, "kl": 0.3689402608714132, "ce": 0.30994848572111056}, {"step": 815, "kl": 0.21936589974513476, "ce": 0.3103520323532299}, {"step": 816, "kl": 0.23453172260677166, "ce": 0.25613379202719916}, {"step": 817, "kl": 0.2800479440446942, "ce": 0.2563956707652298}, {"step": 818, "kl": 0.22242960244953133, "ce": 0.36072055117951496}, {"step": 819, "kl": 0.37137564687784286, "ce": 0.3562435178499381}, {"step": 820, "kl": 0.2396168783483881, "ce": 0.3181221679204985}, {"step": 821, "kl": 0.24135793568904806, "ce": 0.3411594906835086}, {"step": 822, "kl": 0.234614760644074, "ce": 0.39367158203544866}, {"step": 823, "kl": 0.2270321570531094, "ce": 0.35277188285794814}, {"step": 824, "kl": 0.2293230164512335, "ce": 0.3705381580885085}, {"step": 825, "kl": 0.4724606799579346, "ce": 0.4384322497370867}, {"step": 826, "kl": 0.21226688058230225, "ce": 0.38387554008259706}, {"step": 827, "kl": 0.24727663573194816, "ce": 0.3952616863626225}, {"step": 828, "kl": 0.5081688661417342, "ce": 0.40661538573322553}, {"step": 829, "kl": 0.22175070629027732, "ce": 0.36851424070882755}, {"step": 830, "kl": 0.2432034448709695, "ce": 0.44845074960773457}, {"step": 831, "kl": 0.35744742043644206, "ce": 0.39586237296462057}, {"step": 832, "kl": 0.2177035872409557, "ce": 0.4050920251629673}, {"step": 833, "kl": 0.2127581481893513, "ce": 0.3543087597976564}, {"step": 834, "kl": 0.2509712937724278, "ce": 0.4309651814080369}, {"step": 835, "kl": 0.22880137377239868, "ce": 0.3254832069968992}, {"step": 836, "kl": 0.22737106778989383, "ce": 0.43290565772060363}, {"step": 837, "kl": 0.2762941905412124, "ce": 0.24253279198506833}, {"step": 838, "kl": 0.24670814468988742, "ce": 0.42105633283065536}, {"step": 839, "kl": 0.9191081526584397, "ce": 0.4360131619987112}, {"step": 840, "kl": 0.23351144639230736, "ce": 0.5183249402858451}, {"step": 841, "kl": 0.20614238302383642, "ce": 0.347779653993221}, {"step": 842, "kl": 0.8131237973481618, "ce": 0.4842659138952166}, {"step": 843, "kl": 0.4454210035984102, "ce": 0.4578428340780324}, {"step": 844, "kl": 0.2204328205540162, "ce": 0.3981739325051779}, {"step": 845, "kl": 0.24900676820661638, "ce": 0.39124371839922806}, {"step": 846, "kl": 0.233743137888953, "ce": 0.3397754663693761}, {"step": 847, "kl": 0.24803223167118799, "ce": 0.36810347913304187}, {"step": 848, "kl": 0.24396574883376299, "ce": 0.4721255055340854}, {"step": 849, "kl": 0.6043276661643648, "ce": 0.3539959008992342}, {"step": 850, "kl": 0.25672411263204065, "ce": 0.3440066861514154}, {"step": 851, "kl": 0.26880570180914054, "ce": 0.3765086349265653}, {"step": 852, "kl": 0.2109683267082613, "ce": 0.3806497930048334}, {"step": 853, "kl": 0.2403874408315729, "ce": 0.27787015400235615}, {"step": 854, "kl": 0.2265208856804546, "ce": 0.4666511142729317}, {"step": 855, "kl": 0.46195089952966495, "ce": 0.34336697544431705}, {"step": 856, "kl": 0.4203653281591802, "ce": 0.4012356531516946}, {"step": 857, "kl": 0.28308060788869216, "ce": 0.3556953575506179}, {"step": 858, "kl": 0.21266796524657736, "ce": 0.34784210356114087}, {"step": 859, "kl": 0.21734206497606234, "ce": 0.3084839818131284}, {"step": 860, "kl": 0.23180929476952947, "ce": 0.38644392829784063}, {"step": 861, "kl": 0.21771810096755395, "ce": 0.27403206037754085}, {"step": 862, "kl": 0.29650328666774256, "ce": 0.37065245377904055}, {"step": 863, "kl": 0.22265388527625207, "ce": 0.344389137906716}, {"step": 864, "kl": 0.20569111341604124, "ce": 0.309157652724497}, {"step": 865, "kl": 0.2239179177331031, "ce": 0.40179206480245494}, {"step": 866, "kl": 0.3034771732398268, "ce": 0.35224618986593836}, {"step": 867, "kl": 0.20486081208303883, "ce": 0.41897564783267016}, {"step": 868, "kl": 0.2481033885465574, "ce": 0.37437652732150767}, {"step": 869, "kl": 0.20265900654282018, "ce": 0.3456512102873429}, {"step": 870, "kl": 0.5004370971446571, "ce": 0.3133237661739161}, {"step": 871, "kl": 0.2977437248845158, "ce": 0.3710476274375456}, {"step": 872, "kl": 0.24812354783437057, "ce": 0.43853193267469115}, {"step": 873, "kl": 0.24867814321942255, "ce": 0.31700440140457836}, {"step": 874, "kl": 0.28572640525258663, "ce": 0.41068554905008636}, {"step": 875, "kl": 0.24332641012497602, "ce": 0.2937393520461711}, {"step": 876, "kl": 0.2141026592170856, "ce": 0.3205305608363844}, {"step": 877, "kl": 0.23434423332369697, "ce": 0.38436478677953645}, {"step": 878, "kl": 0.5332177938748321, "ce": 0.3651319080716061}, {"step": 879, "kl": 0.24125334950972097, "ce": 0.4180650298510333}, {"step": 880, "kl": 0.22687749463043905, "ce": 0.36921843480226274}, {"step": 881, "kl": 0.2793527979876127, "ce": 0.33701520940647295}, {"step": 882, "kl": 0.22565916378109294, "ce": 0.32989967289726585}, {"step": 883, "kl": 0.29701721233899975, "ce": 0.332890945111633}, {"step": 884, "kl": 0.33880119074694504, "ce": 0.46188453654884654}, {"step": 885, "kl": 0.23433506131624937, "ce": 0.4341702118963872}, {"step": 886, "kl": 0.25533127751290213, "ce": 0.4235196857783147}, {"step": 887, "kl": 0.2489318986171038, "ce": 0.5533065314702622}, {"step": 888, "kl": 0.24690966159247912, "ce": 0.3262332972183114}, {"step": 889, "kl": 0.23216575509016096, "ce": 0.3610711441214262}, {"step": 890, "kl": 0.33715944445457285, "ce": 0.3185053490973138}, {"step": 891, "kl": 0.3938914515030668, "ce": 0.34374523258664386}, {"step": 892, "kl": 0.24041844922409564, "ce": 0.37952999084714856}, {"step": 893, "kl": 0.24879177110674858, "ce": 0.3443634652706563}, {"step": 894, "kl": 0.2333810587656852, "ce": 0.43672323489345743}, {"step": 895, "kl": 0.23028939114661923, "ce": 0.3482175566336632}, {"step": 896, "kl": 0.3002029100798128, "ce": 0.27308549822576195}], "val": [{"step": 0, "math_kl": 0.18707215095927757, "math_ce": 0.8169582523867784, "code_kl": 0.34373369645959484, "code_ce": 0.248868452603892, "math_hard_kl": 0.281878406746077, "math_hard_ce": 0.7980098331233478}, {"step": 448, "math_kl": 0.27229734652808457, "math_ce": 0.44931093337809225, "code_kl": 0.21869504607937518, "code_ce": 0.25811268284515243, "math_hard_kl": 0.3127551198787737, "math_hard_ce": 0.5981767777283613}, {"step": 896, "math_kl": 0.2757146853520857, "math_ce": 0.48866650442357035, "code_kl": 0.23322471331621716, "code_ce": 0.2632293531111412, "math_hard_kl": 0.3334636116516183, "math_hard_ce": 0.6151642707250928}]}
|
seq_code_math_gt_sft_seed1/stage2_math/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30c29869db088cbcd0e5488c24734b243ff79d810410894418e19617dca67487
|
| 3 |
+
size 3087467144
|