pmangesh commited on
Commit
c26c8ce
·
verified ·
1 Parent(s): df95a3d

Upload folder using huggingface_hub

Browse files
seq_code_math_gt_sft/run_info.json CHANGED
@@ -32,9 +32,32 @@
32
  "math_hard_ce": 0.7910297951570997
33
  },
34
  "peak_gb_student": 33.80862855911255,
35
- "peak_gb_teachers": 30.005428314208984,
36
- "bench_h": 0.4040532970428467,
37
- "gpu_bench": "NVIDIA RTX A6000"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
39
  }
40
  }
 
32
  "math_hard_ce": 0.7910297951570997
33
  },
34
  "peak_gb_student": 33.80862855911255,
35
+ "peak_gb_teachers": 30.005428314208984
36
+ },
37
+ "stage2_math": {
38
+ "domain": "math",
39
+ "steps": 896,
40
+ "train_h": 2.688884120848444,
41
+ "val_start": {
42
+ "step": 0,
43
+ "math_kl": 0.18375438443199724,
44
+ "math_ce": 0.796609162952875,
45
+ "code_kl": 0.34498801428341486,
46
+ "code_ce": 0.24669437762251217,
47
+ "math_hard_kl": 0.27730645571818935,
48
+ "math_hard_ce": 0.7908673360534969
49
+ },
50
+ "val_end": {
51
+ "step": 896,
52
+ "math_kl": 0.2711174080266869,
53
+ "math_ce": 0.48686714429648636,
54
+ "code_kl": 0.23916414351690382,
55
+ "code_ce": 0.26016022039706727,
56
+ "math_hard_kl": 0.3349221330783336,
57
+ "math_hard_ce": 0.6155070331563108
58
+ },
59
+ "peak_gb_student": 36.68444871902466,
60
+ "peak_gb_teachers": 30.639182090759277
61
  }
62
  }
63
  }
seq_code_math_gt_sft/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/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/stage2_math/log.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [{"step": 1, "kl": 0.20949168127879889, "ce": 0.731041568368454}, {"step": 2, "kl": 0.15744822500924444, "ce": 0.9120210649255631}, {"step": 3, "kl": 0.11934768544957788, "ce": 0.7219536390276434}, {"step": 4, "kl": 0.19452231371886475, "ce": 0.7213080313844036}, {"step": 5, "kl": 0.14991287588332955, "ce": 0.7874266346270855}, {"step": 6, "kl": 0.2329978552572041, "ce": 0.578472802822501}, {"step": 7, "kl": 1.077140774607877, "ce": 0.7315818645626123}, {"step": 8, "kl": 0.14532283756252287, "ce": 0.7438927837489044}, {"step": 9, "kl": 0.5739249318545211, "ce": 0.6559890845326618}, {"step": 10, "kl": 0.20426848320657093, "ce": 0.5987980028613051}, {"step": 11, "kl": 0.14087337168890868, "ce": 0.5499793178320833}, {"step": 12, "kl": 0.09881381273356445, "ce": 0.5846159392107124}, {"step": 13, "kl": 0.16903192239508436, "ce": 0.6393135773145764}, {"step": 14, "kl": 0.13957995074501614, "ce": 0.5912410089513069}, {"step": 15, "kl": 0.1485377386924541, "ce": 0.6394760824607757}, {"step": 16, "kl": 0.1366858491977262, "ce": 0.542817182409192}, {"step": 17, "kl": 0.28311784501706133, "ce": 0.5423595935951518}, {"step": 18, "kl": 0.32102033448415007, "ce": 0.6322948793946895}, {"step": 19, "kl": 0.18949589768703257, "ce": 0.4628901448462719}, {"step": 20, "kl": 0.14057332346977452, "ce": 0.5920785888033011}, {"step": 21, "kl": 0.16569222756273055, "ce": 0.6519600206346654}, {"step": 22, "kl": 0.1676472327850742, "ce": 0.6452466818715648}, {"step": 23, "kl": 0.4696800629842543, "ce": 0.592418546819522}, {"step": 24, "kl": 0.1774596045147152, "ce": 0.5733404309555408}, {"step": 25, "kl": 0.16430215480581856, "ce": 0.5215389069020335}, {"step": 26, "kl": 0.16315037363478047, "ce": 0.5152220754433123}, {"step": 27, "kl": 0.20033975303823875, "ce": 0.5246549497059867}, {"step": 28, "kl": 0.2122094423764431, "ce": 0.4973765349350016}, {"step": 29, "kl": 0.18771163126015206, "ce": 0.5188483992205887}, {"step": 30, "kl": 0.17806557514602256, "ce": 0.5751203553024139}, {"step": 31, "kl": 0.24610396161324216, "ce": 0.505751479648183}, {"step": 32, "kl": 0.317016707131006, "ce": 0.5364070721751953}, {"step": 33, "kl": 0.21547929681931202, "ce": 0.552304761125091}, {"step": 34, "kl": 0.19445143592377326, "ce": 0.5882943010595975}, {"step": 35, "kl": 0.20509206759334792, "ce": 0.5500087637409604}, {"step": 36, "kl": 0.2195349114607548, "ce": 0.627349804395778}, {"step": 37, "kl": 0.36322439795893996, "ce": 0.6835380295986727}, {"step": 38, "kl": 0.2342077195830063, "ce": 0.486969233677171}, {"step": 39, "kl": 0.2553560784165288, "ce": 0.5145337916302604}, {"step": 40, "kl": 0.21031728386264528, "ce": 0.6352292041326804}, {"step": 41, "kl": 0.19524097997374545, "ce": 0.5406914698344663}, {"step": 42, "kl": 0.251242276081235, "ce": 0.5246151837164281}, {"step": 43, "kl": 0.1877291226807908, "ce": 0.6754593183851434}, {"step": 44, "kl": 0.23409496254408246, "ce": 0.6033476560197873}, {"step": 45, "kl": 0.23525393496818767, "ce": 0.5637190717331906}, {"step": 46, "kl": 0.19514132127577485, "ce": 0.6095923118966173}, {"step": 47, "kl": 0.23904020849536675, "ce": 0.5886748890751756}, {"step": 48, "kl": 0.23490304900549108, "ce": 0.5994444024858194}, {"step": 49, "kl": 0.21634142532031878, "ce": 0.5129797560898857}, {"step": 50, "kl": 0.23034294848624587, "ce": 0.5548316129704112}, {"step": 51, "kl": 0.20033221394929673, "ce": 0.4109786309371154}, {"step": 52, "kl": 0.18486747108891083, "ce": 0.573245923071449}, {"step": 53, "kl": 0.25554501995146656, "ce": 0.5968818979757129}, {"step": 54, "kl": 0.20607140103956043, "ce": 0.6620378791712135}, {"step": 55, "kl": 0.20527636399563415, "ce": 0.6189535295618327}, {"step": 56, "kl": 0.18745344118813123, "ce": 0.45462615960758573}, {"step": 57, "kl": 0.19987916429932567, "ce": 0.740721085264876}, {"step": 58, "kl": 0.20773370839372465, "ce": 0.6092202797626901}, {"step": 59, "kl": 0.256592502293418, "ce": 0.6577604564991868}, {"step": 60, "kl": 0.21557739475484242, "ce": 0.5532485710832653}, {"step": 61, "kl": 0.1701684383800329, "ce": 0.46531789841678384}, {"step": 62, "kl": 0.22441042321258414, "ce": 0.48013132330197006}, {"step": 63, "kl": 0.20192391142978772, "ce": 0.6204347364239184}, {"step": 64, "kl": 0.24014175816586145, "ce": 0.4637960177918984}, {"step": 65, "kl": 0.20679065257332294, "ce": 0.580783056083828}, {"step": 66, "kl": 0.22050153915233486, "ce": 0.49553636908320053}, {"step": 67, "kl": 0.2715206701491927, "ce": 0.5491824998051287}, {"step": 68, "kl": 0.21173305793402206, "ce": 0.5218570257301391}, {"step": 69, "kl": 0.23869480794017567, "ce": 0.5542877807402476}, {"step": 70, "kl": 0.29457732669035036, "ce": 0.5791726374862217}, {"step": 71, "kl": 0.198193938120486, "ce": 0.4789204411366832}, {"step": 72, "kl": 0.2807802765037727, "ce": 0.5802905221759596}, {"step": 73, "kl": 0.19393414977391796, "ce": 0.4687432640868916}, {"step": 74, "kl": 0.2011063433010255, "ce": 0.6796247553528592}, {"step": 75, "kl": 0.20560633523084296, "ce": 0.4795757021518261}, {"step": 76, "kl": 0.19584949779314967, "ce": 0.556697268537673}, {"step": 77, "kl": 0.2589689175447147, "ce": 0.5678779822302352}, {"step": 78, "kl": 0.17673408847281794, "ce": 0.47570816605179395}, {"step": 79, "kl": 0.3343579328017266, "ce": 0.5412610106495345}, {"step": 80, "kl": 0.32221749563452, "ce": 0.5291669793501517}, {"step": 81, "kl": 0.2678260913566153, "ce": 0.5370310095823687}, {"step": 82, "kl": 0.22279690045561457, "ce": 0.6500148638556985}, {"step": 83, "kl": 0.24982362748804682, "ce": 0.4318283345328485}, {"step": 84, "kl": 0.2914618399782679, "ce": 0.628358303783643}, {"step": 85, "kl": 0.19754561878489868, "ce": 0.38575566084260127}, {"step": 86, "kl": 0.18716315552818008, "ce": 0.533459712367255}, {"step": 87, "kl": 0.43347433877322916, "ce": 0.553362304039059}, {"step": 88, "kl": 0.26667600639361816, "ce": 0.7310432503382889}, {"step": 89, "kl": 0.25263981539796126, "ce": 0.6265187115103783}, {"step": 90, "kl": 0.20749353860141134, "ce": 0.4468881253410984}, {"step": 91, "kl": 0.32857826312026633, "ce": 0.5780330407427441}, {"step": 92, "kl": 0.1969926689555935, "ce": 0.4792527732335386}, {"step": 93, "kl": 0.28650477024797494, "ce": 0.4959314037849917}, {"step": 94, "kl": 0.19461475512627477, "ce": 0.6467144788151687}, {"step": 95, "kl": 0.22184942023594426, "ce": 0.6581357869234952}, {"step": 96, "kl": 0.2315375843632615, "ce": 0.5826039304318369}, {"step": 97, "kl": 0.19772026823928868, "ce": 0.41160598678748217}, {"step": 98, "kl": 0.1898129087078178, "ce": 0.627298818853651}, {"step": 99, "kl": 0.1939492631615932, "ce": 0.5095197306892086}, {"step": 100, "kl": 0.192438813208028, "ce": 0.5026182802305413}, {"step": 101, "kl": 0.2565518106337338, "ce": 0.6345713375815095}, {"step": 102, "kl": 0.2106905054896774, "ce": 0.5438863538108987}, {"step": 103, "kl": 0.20145486788330486, "ce": 0.49639386983872413}, {"step": 104, "kl": 0.8558643173434983, "ce": 0.7696157097023703}, {"step": 105, "kl": 0.43779771909892073, "ce": 0.6277194022403549}, {"step": 106, "kl": 0.26837843998014216, "ce": 0.6709158423528887}, {"step": 107, "kl": 0.34577680725763055, "ce": 0.5214947058198098}, {"step": 108, "kl": 0.17243676474737454, "ce": 0.5425031003174776}, {"step": 109, "kl": 0.2134446875001882, "ce": 0.6626766850884852}, {"step": 110, "kl": 0.28255515009316945, "ce": 0.6015238621617072}, {"step": 111, "kl": 0.260069758473771, "ce": 0.6280441561837906}, {"step": 112, "kl": 0.199237153016932, "ce": 0.4768020603330395}, {"step": 113, "kl": 0.2591624858028498, "ce": 0.5281993354406818}, {"step": 114, "kl": 0.19361431614677221, "ce": 0.4547071712545625}, {"step": 115, "kl": 0.17699300037550322, "ce": 0.5143597140361277}, {"step": 116, "kl": 0.18006556568985208, "ce": 0.560563191764631}, {"step": 117, "kl": 0.21357289090742593, "ce": 0.6402474010430148}, {"step": 118, "kl": 0.2216687209012584, "ce": 0.48940259677660713}, {"step": 119, "kl": 0.2442830917210255, "ce": 0.5721350584657533}, {"step": 120, "kl": 0.3647472628822669, "ce": 0.506583243564192}, {"step": 121, "kl": 0.18558675242523287, "ce": 0.5728513682310657}, {"step": 122, "kl": 0.1867548624674479, "ce": 0.5286405747074587}, {"step": 123, "kl": 0.17810169743345008, "ce": 0.48371110813251667}, {"step": 124, "kl": 0.20656045847460117, "ce": 0.631960786749362}, {"step": 125, "kl": 0.21253120959644586, "ce": 0.5463697575847768}, {"step": 126, "kl": 0.188809241166095, "ce": 0.6293376440923599}, {"step": 127, "kl": 0.30769206423087303, "ce": 0.6239850588688345}, {"step": 128, "kl": 0.1769368504178062, "ce": 0.5521043650582114}, {"step": 129, "kl": 0.23342906117589976, "ce": 0.6583014401522549}, {"step": 130, "kl": 0.18350028505166152, "ce": 0.5727391534676591}, {"step": 131, "kl": 0.19450564491119765, "ce": 0.6162586690704455}, {"step": 132, "kl": 0.2089897526305164, "ce": 0.6790451797002001}, {"step": 133, "kl": 0.2390641430714247, "ce": 0.48810066023339577}, {"step": 134, "kl": 0.20281440970797923, "ce": 0.5225117844828935}, {"step": 135, "kl": 0.18544824837450946, "ce": 0.5051988349231362}, {"step": 136, "kl": 0.2719258464168341, "ce": 0.5137388215617742}, {"step": 137, "kl": 0.20819261035458225, "ce": 0.5589717487859184}, {"step": 138, "kl": 0.395696425492437, "ce": 0.5918086156989276}, {"step": 139, "kl": 0.2752441506049309, "ce": 0.5911922855066617}, {"step": 140, "kl": 0.26405195531507536, "ce": 0.6171104011528178}, {"step": 141, "kl": 0.18835408821970417, "ce": 0.6019173987769327}, {"step": 142, "kl": 0.2281842990024591, "ce": 0.5003141293118187}, {"step": 143, "kl": 0.2786609661176641, "ce": 0.6181403924860261}, {"step": 144, "kl": 0.21923347130600288, "ce": 0.5825171838393451}, {"step": 145, "kl": 0.21516961589024214, "ce": 0.5820260367685051}, {"step": 146, "kl": 0.19592741510178935, "ce": 0.6943244858205407}, {"step": 147, "kl": 0.17960563746703995, "ce": 0.4391051828646677}, {"step": 148, "kl": 0.3513751807161922, "ce": 0.6346964310917265}, {"step": 149, "kl": 0.5315137731755204, "ce": 0.46587486134940975}, {"step": 150, "kl": 0.19689815785491024, "ce": 0.5665671328703562}, {"step": 151, "kl": 0.19689816176569985, "ce": 0.6126067229179998}, {"step": 152, "kl": 0.570757332526648, "ce": 0.556422992646835}, {"step": 153, "kl": 0.22443419649469515, "ce": 0.5777435700845132}, {"step": 154, "kl": 0.26014054713929935, "ce": 0.6266660355072968}, {"step": 155, "kl": 0.5844902614107068, "ce": 0.5894820872514849}, {"step": 156, "kl": 0.22357018696554223, "ce": 0.4837707894906326}, {"step": 157, "kl": 0.22801449621508935, "ce": 0.5893755069468387}, {"step": 158, "kl": 0.21019544868089843, "ce": 0.512563382862883}, {"step": 159, "kl": 1.0438795842361845, "ce": 0.5889045179853758}, {"step": 160, "kl": 0.20178953040447187, "ce": 0.5453480627977568}, {"step": 161, "kl": 0.24786135745565657, "ce": 0.5102589467609899}, {"step": 162, "kl": 0.18245635739522964, "ce": 0.5766565170271454}, {"step": 163, "kl": 0.2178363103086764, "ce": 0.5458065416311244}, {"step": 164, "kl": 0.1988253638147093, "ce": 0.5000810026607034}, {"step": 165, "kl": 0.5627160139048277, "ce": 0.5519863388873382}, {"step": 166, "kl": 0.3314023545282311, "ce": 0.43403968756977096}, {"step": 167, "kl": 0.374528988737703, "ce": 0.5894152508494577}, {"step": 168, "kl": 0.34059499254935477, "ce": 0.5026227253586499}, {"step": 169, "kl": 0.2750829681148374, "ce": 0.5303619730467216}, {"step": 170, "kl": 0.20261289460888468, "ce": 0.44921440360472376}, {"step": 171, "kl": 0.4199261890484925, "ce": 0.5541437799331228}, {"step": 172, "kl": 0.21444093018062566, "ce": 0.5080713357231958}, {"step": 173, "kl": 0.23474264972438924, "ce": 0.6935703467134464}, {"step": 174, "kl": 0.42144540003261277, "ce": 0.5774088809483615}, {"step": 175, "kl": 0.7196058739756611, "ce": 0.6011456873592914}, {"step": 176, "kl": 0.18750654603963707, "ce": 0.6432022426905256}, {"step": 177, "kl": 0.18265723947026946, "ce": 0.5675622061896997}, {"step": 178, "kl": 0.1948141341443061, "ce": 0.47119004224582134}, {"step": 179, "kl": 0.30545638333463815, "ce": 0.5829272775340321}, {"step": 180, "kl": 0.2075186573216459, "ce": 0.5968474888623412}, {"step": 181, "kl": 0.7743877876295876, "ce": 0.6008553009784867}, {"step": 182, "kl": 0.25051158410290403, "ce": 0.47807238024120036}, {"step": 183, "kl": 0.19335528376432554, "ce": 0.6242602848043672}, {"step": 184, "kl": 0.20835077766415044, "ce": 0.4864141502144206}, {"step": 185, "kl": 0.21715892075612034, "ce": 0.5426538020782892}, {"step": 186, "kl": 0.21570219094299103, "ce": 0.5384598638703121}, {"step": 187, "kl": 0.3831291623789591, "ce": 0.5367875296638925}, {"step": 188, "kl": 0.1944042892812939, "ce": 0.565931717361436}, {"step": 189, "kl": 0.9356790162792535, "ce": 0.5001561251779802}, {"step": 190, "kl": 0.200115346031231, "ce": 0.48166281268110755}, {"step": 191, "kl": 0.2818090391962509, "ce": 0.5873593408560311}, {"step": 192, "kl": 0.2190828428789862, "ce": 0.6585887592040633}, {"step": 193, "kl": 0.18933631896972658, "ce": 0.4969088467490813}, {"step": 194, "kl": 0.6872504668823494, "ce": 0.6058611780455816}, {"step": 195, "kl": 0.21711503184201603, "ce": 0.5557602667039441}, {"step": 196, "kl": 0.2515696291987028, "ce": 0.6438937493263065}, {"step": 197, "kl": 0.23823367656016764, "ce": 0.5344557962254776}, {"step": 198, "kl": 0.2092154615047748, "ce": 0.6466427547129714}, {"step": 199, "kl": 0.2023086163305467, "ce": 0.545363349806297}, {"step": 200, "kl": 0.1740222200089993, "ce": 0.43805666098376167}, {"step": 201, "kl": 0.21636328109501787, "ce": 0.6085087870472417}, {"step": 202, "kl": 0.2631818399072331, "ce": 0.4559730214580124}, {"step": 203, "kl": 0.31774124360420336, "ce": 0.6421101991788236}, {"step": 204, "kl": 0.23226768136716097, "ce": 0.4795083542339137}, {"step": 205, "kl": 0.24944678013913926, "ce": 0.5222229227130505}, {"step": 206, "kl": 0.27374565208645657, "ce": 0.5501977061981436}, {"step": 207, "kl": 0.2190833827178877, "ce": 0.4400443525077579}, {"step": 208, "kl": 0.2097308443164599, "ce": 0.542510967473683}, {"step": 209, "kl": 0.24187009488864336, "ce": 0.581364402770996}, {"step": 210, "kl": 0.25224786052833886, "ce": 0.5130406967842178}, {"step": 211, "kl": 0.20255146264966517, "ce": 0.5678892377455942}, {"step": 212, "kl": 0.2449093618984959, "ce": 0.5637964448340554}, {"step": 213, "kl": 0.21716203490355285, "ce": 0.41020929742172774}, {"step": 214, "kl": 0.27171109010335154, "ce": 0.5764330346663996}, {"step": 215, "kl": 0.21550001017672432, "ce": 0.569927215159265}, {"step": 216, "kl": 0.20321805931156517, "ce": 0.6829431501703229}, {"step": 217, "kl": 0.20316065912661344, "ce": 0.524058326613158}, {"step": 218, "kl": 0.22502090775487485, "ce": 0.5251441059112548}, {"step": 219, "kl": 0.31047728129060337, "ce": 0.5346857512938535}, {"step": 220, "kl": 0.2799026096536224, "ce": 0.5105194530922834}, {"step": 221, "kl": 0.2113497395836239, "ce": 0.4781509135169575}, {"step": 222, "kl": 0.24867110562014888, "ce": 0.5365656579716754}, {"step": 223, "kl": 0.5187671214205498, "ce": 0.6682408429951359}, {"step": 224, "kl": 0.2610993994021751, "ce": 0.6164294373270011}, {"step": 225, "kl": 0.30790762083002876, "ce": 0.6732709458222037}, {"step": 226, "kl": 0.22464547496400472, "ce": 0.506508089019031}, {"step": 227, "kl": 0.2298369114952428, "ce": 0.5813680219996081}, {"step": 228, "kl": 0.30567248315522166, "ce": 0.5330743200985002}, {"step": 229, "kl": 0.2187947960958776, "ce": 0.5957178116602513}, {"step": 230, "kl": 0.2331671326118294, "ce": 0.47989842593916393}, {"step": 231, "kl": 0.2291684096532007, "ce": 0.6015281427727611}, {"step": 232, "kl": 0.2599113089193771, "ce": 0.5121588429502227}, {"step": 233, "kl": 0.23401055217293185, "ce": 0.5369594716650294}, {"step": 234, "kl": 0.20435268629231026, "ce": 0.49452784472063926}, {"step": 235, "kl": 0.236049275305866, "ce": 0.46660238198673026}, {"step": 236, "kl": 0.20812570765911154, "ce": 0.6092923894933179}, {"step": 237, "kl": 0.21993431623920048, "ce": 0.5911901471698242}, {"step": 238, "kl": 0.2054438882786126, "ce": 0.49511199658907123}, {"step": 239, "kl": 0.19815869897853572, "ce": 0.5150315326036932}, {"step": 240, "kl": 0.21330857849451204, "ce": 0.5921134397607303}, {"step": 241, "kl": 0.20333105156692605, "ce": 0.44396231947862597}, {"step": 242, "kl": 0.6442837093932502, "ce": 0.5184508411575897}, {"step": 243, "kl": 0.19299609682227803, "ce": 0.4479911190839688}, {"step": 244, "kl": 0.40742347638925364, "ce": 0.5578892379422611}, {"step": 245, "kl": 0.19835136749806398, "ce": 0.5080018531325047}, {"step": 246, "kl": 0.2526127263558734, "ce": 0.45487660260740037}, {"step": 247, "kl": 0.22289428264610947, "ce": 0.5869475827196637}, {"step": 248, "kl": 0.38641647033390236, "ce": 0.5548558181741325}, {"step": 249, "kl": 0.2052152561862346, "ce": 0.5803418238687352}, {"step": 250, "kl": 0.21204920669542393, "ce": 0.544423163409625}, {"step": 251, "kl": 0.26493561988417946, "ce": 0.6194753333639316}, {"step": 252, "kl": 0.2959290272455727, "ce": 0.46791073417744633}, {"step": 253, "kl": 0.23251972026067805, "ce": 0.5167528499468197}, {"step": 254, "kl": 0.2156068065351967, "ce": 0.5826795513061678}, {"step": 255, "kl": 0.22378581806019104, "ce": 0.6388791647013397}, {"step": 256, "kl": 0.203430958328142, "ce": 0.6781303349745607}, {"step": 257, "kl": 0.28421415393528116, "ce": 0.5331838765911634}, {"step": 258, "kl": 0.22250375257186022, "ce": 0.582166152149658}, {"step": 259, "kl": 0.2383115908584883, "ce": 0.5412941233291175}, {"step": 260, "kl": 0.27565926783993094, "ce": 0.5237690162988113}, {"step": 261, "kl": 0.2736947657844258, "ce": 0.6181023692917698}, {"step": 262, "kl": 0.2103619207479811, "ce": 0.6057992545129819}, {"step": 263, "kl": 0.1954763042699994, "ce": 0.5452751752816194}, {"step": 264, "kl": 0.21576863690825016, "ce": 0.5923579428919937}, {"step": 265, "kl": 0.20727010981134378, "ce": 0.4620921819037606}, {"step": 266, "kl": 0.1874015265584525, "ce": 0.4650921497612654}, {"step": 267, "kl": 0.23004691444938027, "ce": 0.4838024398825217}, {"step": 268, "kl": 0.2743655972468352, "ce": 0.5718153566164472}, {"step": 269, "kl": 0.1767604436516254, "ce": 0.5272419027951489}, {"step": 270, "kl": 0.3573521656034747, "ce": 0.517266494020707}, {"step": 271, "kl": 0.2539803999124825, "ce": 0.6310381256569207}, {"step": 272, "kl": 0.22428039463400928, "ce": 0.5067368854733815}, {"step": 273, "kl": 0.21006792165702623, "ce": 0.5546651817246624}, {"step": 274, "kl": 0.19616892181768322, "ce": 0.535866472206803}, {"step": 275, "kl": 0.18996078152078272, "ce": 0.5773443815325939}, {"step": 276, "kl": 0.2037646595898978, "ce": 0.6749981983632601}, {"step": 277, "kl": 0.20815626799376816, "ce": 0.5534376289457652}, {"step": 278, "kl": 0.2666714729336338, "ce": 0.4397646360135426}, {"step": 279, "kl": 0.1983187452292607, "ce": 0.5047433325165339}, {"step": 280, "kl": 0.27167174385581205, "ce": 0.5977286080866167}, {"step": 281, "kl": 0.312214952236886, "ce": 0.5731782996680596}, {"step": 282, "kl": 0.23174867450665673, "ce": 0.4589353543773376}, {"step": 283, "kl": 0.1978105153192634, "ce": 0.5151600981690321}, {"step": 284, "kl": 0.2658732932830865, "ce": 0.5217011921382284}, {"step": 285, "kl": 0.1899442327874992, "ce": 0.5450461334816402}, {"step": 286, "kl": 0.22176145429904143, "ce": 0.5887681528286889}, {"step": 287, "kl": 0.1945239654057193, "ce": 0.6585675910810428}, {"step": 288, "kl": 0.2385256163205459, "ce": 0.7260475444855912}, {"step": 289, "kl": 0.2761126920128696, "ce": 0.5246893869687433}, {"step": 290, "kl": 0.3031082389187444, "ce": 0.4476501021412028}, {"step": 291, "kl": 0.2475792514777453, "ce": 0.4541044177498334}, {"step": 292, "kl": 0.577599465025264, "ce": 0.4784039642612238}, {"step": 293, "kl": 0.30922247245422274, "ce": 0.5102207839952632}, {"step": 294, "kl": 0.19875817760586648, "ce": 0.5775667729585068}, {"step": 295, "kl": 0.2462409308695053, "ce": 0.4893181064522678}, {"step": 296, "kl": 0.2939351761314612, "ce": 0.6911764737077063}, {"step": 297, "kl": 0.20256077499289596, "ce": 0.5729455057555438}, {"step": 298, "kl": 0.3196820937206972, "ce": 0.6648284110012433}, {"step": 299, "kl": 0.2768043404007773, "ce": 0.5539095145891809}, {"step": 300, "kl": 0.21178095069410913, "ce": 0.6483651528787606}, {"step": 301, "kl": 0.21349631457371945, "ce": 0.5490805499524954}, {"step": 302, "kl": 0.20655479261106402, "ce": 0.5017481474541622}, {"step": 303, "kl": 0.21022066624044516, "ce": 0.5489771037058787}, {"step": 304, "kl": 0.43585136662358825, "ce": 0.6275779149347684}, {"step": 305, "kl": 0.2432406627019997, "ce": 0.6636173416861926}, {"step": 306, "kl": 0.3051930765195186, "ce": 0.5625133037750467}, {"step": 307, "kl": 0.22314923549129995, "ce": 0.5370750964527399}, {"step": 308, "kl": 0.33894346775766937, "ce": 0.37927217838805455}, {"step": 309, "kl": 0.26930454246412666, "ce": 0.5077770824188288}, {"step": 310, "kl": 0.20189493894998764, "ce": 0.4837886643882663}, {"step": 311, "kl": 0.22442087622991214, "ce": 0.5584315603818284}, {"step": 312, "kl": 0.256901125272905, "ce": 0.47231576915601253}, {"step": 313, "kl": 0.20183991820872982, "ce": 0.47340463931017585}, {"step": 314, "kl": 0.2318992081336422, "ce": 0.5337205252223447}, {"step": 315, "kl": 0.2238168293902725, "ce": 0.5133101030346482}, {"step": 316, "kl": 0.22003090426657573, "ce": 0.5260234977288594}, {"step": 317, "kl": 0.3198353389074654, "ce": 0.6211581910529966}, {"step": 318, "kl": 0.24385332086747122, "ce": 0.5787898846100691}, {"step": 319, "kl": 0.23689097771277795, "ce": 0.5047940401433537}, {"step": 320, "kl": 0.24092170478954306, "ce": 0.5506612449151025}, {"step": 321, "kl": 0.27782825482728885, "ce": 0.49799574515837314}, {"step": 322, "kl": 0.22529141367021005, "ce": 0.5283802258892927}, {"step": 323, "kl": 0.2436202047676239, "ce": 0.6586517987896129}, {"step": 324, "kl": 0.20292375584800065, "ce": 0.4638387050769466}, {"step": 325, "kl": 0.2926364625348028, "ce": 0.5664050683947253}, {"step": 326, "kl": 0.2312348583439091, "ce": 0.484339804325289}, {"step": 327, "kl": 0.24322111727241486, "ce": 0.5593780922154404}, {"step": 328, "kl": 0.19846459281471912, "ce": 0.47145821642969904}, {"step": 329, "kl": 0.22948109100459235, "ce": 0.5351271958415185}, {"step": 330, "kl": 0.22253416864051812, "ce": 0.5175024429148459}, {"step": 331, "kl": 0.23787444147125442, "ce": 0.46194538782154376}, {"step": 332, "kl": 0.21971854572409089, "ce": 0.6158342759428657}, {"step": 333, "kl": 0.23122202879304338, "ce": 0.5022678597028866}, {"step": 334, "kl": 0.2116907394610179, "ce": 0.4527690181993458}, {"step": 335, "kl": 0.21694044754204475, "ce": 0.5488593131216185}, {"step": 336, "kl": 0.23159487888810146, "ce": 0.6710063180440314}, {"step": 337, "kl": 0.28416301175553066, "ce": 0.5447025565437345}, {"step": 338, "kl": 0.2349859177239319, "ce": 0.461714881081735}, {"step": 339, "kl": 0.1936420359555776, "ce": 0.5768349760650373}, {"step": 340, "kl": 0.1774047715175707, "ce": 0.44933157403144985}, {"step": 341, "kl": 0.22077318904237647, "ce": 0.5564142593939934}, {"step": 342, "kl": 0.2003832035155093, "ce": 0.5836490294972404}, {"step": 343, "kl": 0.1864860588225873, "ce": 0.46234795412384766}, {"step": 344, "kl": 0.22774728808239186, "ce": 0.5917523727911949}, {"step": 345, "kl": 0.20598148951112671, "ce": 0.46072533386440473}, {"step": 346, "kl": 0.19459728397581935, "ce": 0.5886007729894556}, {"step": 347, "kl": 0.29883653882263495, "ce": 0.5252319121843114}, {"step": 348, "kl": 0.31223311845646345, "ce": 0.6086625061825511}, {"step": 349, "kl": 0.34196800348453704, "ce": 0.49257194159542705}, {"step": 350, "kl": 0.22269571310066738, "ce": 0.5591289000497526}, {"step": 351, "kl": 0.23240918385265366, "ce": 0.5891740577130965}, {"step": 352, "kl": 0.18700255606027455, "ce": 0.46486863999826467}, {"step": 353, "kl": 0.18398852189151227, "ce": 0.45980218001082995}, {"step": 354, "kl": 0.5840595423320022, "ce": 0.5348566405196507}, {"step": 355, "kl": 0.23499124804226326, "ce": 0.5393477491228689}, {"step": 356, "kl": 0.3305679345266117, "ce": 0.4948192811684922}, {"step": 357, "kl": 0.19763598452288283, "ce": 0.5252919719884114}, {"step": 358, "kl": 0.2340752730258676, "ce": 0.562624436816866}, {"step": 359, "kl": 0.18022975378747993, "ce": 0.5208629387535634}, {"step": 360, "kl": 0.20743096927031787, "ce": 0.4966897114331086}, {"step": 361, "kl": 0.23731563261173338, "ce": 0.4866162102679402}, {"step": 362, "kl": 0.2490604674606638, "ce": 0.6464587763736123}, {"step": 363, "kl": 1.7307884277606318, "ce": 0.5936175330771324}, {"step": 364, "kl": 0.3384690474058535, "ce": 0.5953111763557318}, {"step": 365, "kl": 0.24910407357136824, "ce": 0.5432047632199909}, {"step": 366, "kl": 0.1955043020061074, "ce": 0.4925072938261951}, {"step": 367, "kl": 0.19911777778656758, "ce": 0.471106907015177}, {"step": 368, "kl": 0.21150484118695367, "ce": 0.47303465237661174}, {"step": 369, "kl": 0.20414093798500657, "ce": 0.5374046516353159}, {"step": 370, "kl": 0.20926486157213314, "ce": 0.587216568822774}, {"step": 371, "kl": 0.21246075556433758, "ce": 0.5398266991360213}, {"step": 372, "kl": 0.23336353867432574, "ce": 0.5914719409301502}, {"step": 373, "kl": 0.245009330433232, "ce": 0.44883829160617583}, {"step": 374, "kl": 0.22317081450297005, "ce": 0.5073343707944455}, {"step": 375, "kl": 0.35090087855394025, "ce": 0.5995504591200087}, {"step": 376, "kl": 0.3657772960914393, "ce": 0.5293157547483429}, {"step": 377, "kl": 0.6868186075959408, "ce": 0.5803536719618365}, {"step": 378, "kl": 0.21314007066580176, "ce": 0.43751540881418965}, {"step": 379, "kl": 0.23110224281520136, "ce": 0.4623962257988402}, {"step": 380, "kl": 0.24662512683285281, "ce": 0.5033784875305247}, {"step": 381, "kl": 0.2342207936382798, "ce": 0.5228256594529207}, {"step": 382, "kl": 0.26296790690280036, "ce": 0.4614012253185935}, {"step": 383, "kl": 0.3003677462461031, "ce": 0.5187832885015577}, {"step": 384, "kl": 0.30774240967788496, "ce": 0.5909971268492245}, {"step": 385, "kl": 0.22962393820111932, "ce": 0.5719872715884518}, {"step": 386, "kl": 0.22034917853548608, "ce": 0.5489543616147707}, {"step": 387, "kl": 0.22213727874735023, "ce": 0.5093241231495855}, {"step": 388, "kl": 0.2124626369586975, "ce": 0.6206877424310727}, {"step": 389, "kl": 0.22378465470306164, "ce": 0.7285589855568033}, {"step": 390, "kl": 0.23161266193068633, "ce": 0.5381360251538316}, {"step": 391, "kl": 0.22818412266904448, "ce": 0.5565473068995341}, {"step": 392, "kl": 0.30748178522592745, "ce": 0.5931251391157899}, {"step": 393, "kl": 0.5726325609046174, "ce": 0.5415134556563436}, {"step": 394, "kl": 0.24560566235466696, "ce": 0.5913945507473416}, {"step": 395, "kl": 0.23452524234046293, "ce": 0.5254296857126701}, {"step": 396, "kl": 0.21580438863152301, "ce": 0.6273259733423229}, {"step": 397, "kl": 0.20360281045309042, "ce": 0.6402996942922063}, {"step": 398, "kl": 0.21208624429885592, "ce": 0.555988034634265}, {"step": 399, "kl": 0.20273389627941202, "ce": 0.47778595419857994}, {"step": 400, "kl": 0.2105674125537014, "ce": 0.47133726636973056}, {"step": 401, "kl": 0.20686940699626888, "ce": 0.48572046025987753}, {"step": 402, "kl": 0.2915083684604546, "ce": 0.517116823922033}, {"step": 403, "kl": 0.31653556354386553, "ce": 0.4990417738694411}, {"step": 404, "kl": 0.2333750285008028, "ce": 0.5322678622635395}, {"step": 405, "kl": 0.2749137357253507, "ce": 0.5728282992701708}, {"step": 406, "kl": 0.25043945094250053, "ce": 0.4269125458656061}, {"step": 407, "kl": 0.22052475018238038, "ce": 0.5849211026836374}, {"step": 408, "kl": 0.19244741670611173, "ce": 0.5819140952207347}, {"step": 409, "kl": 0.35550717285448663, "ce": 0.6742730578613281}, {"step": 410, "kl": 0.2385680263705763, "ce": 0.6034564050241782}, {"step": 411, "kl": 0.29528872843968823, "ce": 0.5253635658146144}, {"step": 412, "kl": 0.19895190418042746, "ce": 0.4865193485555069}, {"step": 413, "kl": 0.2004945008148336, "ce": 0.45545922240878145}, {"step": 414, "kl": 0.25785526066478387, "ce": 0.5122570995896392}, {"step": 415, "kl": 0.22248580159130185, "ce": 0.5293552833037973}, {"step": 416, "kl": 0.2201741214521276, "ce": 0.5812428577680011}, {"step": 417, "kl": 0.19514007009667336, "ce": 0.5296705048453358}, {"step": 418, "kl": 0.23231016785142347, "ce": 0.5288308186322892}, {"step": 419, "kl": 0.43215527243783414, "ce": 0.5829805035129528}, {"step": 420, "kl": 0.3003883936141167, "ce": 0.6320272551642524}, {"step": 421, "kl": 0.22846207950994188, "ce": 0.632274564878078}, {"step": 422, "kl": 0.373784523138603, "ce": 0.49159734510894126}, {"step": 423, "kl": 0.24591706444220782, "ce": 0.5780805949826728}, {"step": 424, "kl": 0.2029762394050031, "ce": 0.5625550109491391}, {"step": 425, "kl": 0.21702572871003123, "ce": 0.5864336830036783}, {"step": 426, "kl": 0.22720196959844532, "ce": 0.5896344669860394}, {"step": 427, "kl": 0.21248977964510068, "ce": 0.5305333417090997}, {"step": 428, "kl": 0.21544196164623425, "ce": 0.510237118900346}, {"step": 429, "kl": 0.23625857516215687, "ce": 0.5987277058037845}, {"step": 430, "kl": 0.2557711178029077, "ce": 0.42675603485263214}, {"step": 431, "kl": 0.22827949295064753, "ce": 0.43210715022622553}, {"step": 432, "kl": 0.22736608315489207, "ce": 0.5057994054538658}, {"step": 433, "kl": 0.21135989364383584, "ce": 0.5472888566511179}, {"step": 434, "kl": 0.25059787140070733, "ce": 0.5801007175886146}, {"step": 435, "kl": 0.24017990536284567, "ce": 0.5563526691759685}, {"step": 436, "kl": 0.23896950774086834, "ce": 0.47126315528687457}, {"step": 437, "kl": 1.0691920521779874, "ce": 0.5160434689307165}, {"step": 438, "kl": 0.3450250237275028, "ce": 0.5376098476044119}, {"step": 439, "kl": 0.26853382080990407, "ce": 0.6525334803089398}, {"step": 440, "kl": 0.3925622639732923, "ce": 0.5745785687633396}, {"step": 441, "kl": 0.2376589841825804, "ce": 0.43866532113516477}, {"step": 442, "kl": 0.5236900074680965, "ce": 0.6544305072932977}, {"step": 443, "kl": 0.2978911499910801, "ce": 0.4798955285077767}, {"step": 444, "kl": 0.20796965761248673, "ce": 0.4841477792771136}, {"step": 445, "kl": 0.25983402113820026, "ce": 0.6030167984829762}, {"step": 446, "kl": 0.3030495302596325, "ce": 0.5817777424147634}, {"step": 447, "kl": 0.25423463508893174, "ce": 0.5587288477552679}, {"step": 448, "kl": 0.20803618058773277, "ce": 0.5299905975442074}, {"step": 449, "kl": 0.33016206681439697, "ce": 0.3357453164467014}, {"step": 450, "kl": 0.21321135604937458, "ce": 0.32339156923499535}, {"step": 451, "kl": 0.2472941247300004, "ce": 0.4064700149893078}, {"step": 452, "kl": 0.20538932598366688, "ce": 0.34307208845663867}, {"step": 453, "kl": 0.3358872564150951, "ce": 0.49854691944063667}, {"step": 454, "kl": 0.22937362109623632, "ce": 0.3590831688323204}, {"step": 455, "kl": 0.3352799341091325, "ce": 0.42170754128459537}, {"step": 456, "kl": 0.22063231024033664, "ce": 0.3057763943768511}, {"step": 457, "kl": 0.2593411767144993, "ce": 0.3321564662035381}, {"step": 458, "kl": 0.25669357221994793, "ce": 0.5041860448164737}, {"step": 459, "kl": 0.28301258071788754, "ce": 0.4611079797350154}, {"step": 460, "kl": 0.23091686601868208, "ce": 0.4673982382332606}, {"step": 461, "kl": 0.22505179244546275, "ce": 0.44271615128608266}, {"step": 462, "kl": 0.26366440215865106, "ce": 0.2787234791324599}, {"step": 463, "kl": 0.2879483402920834, "ce": 0.4214233207427519}, {"step": 464, "kl": 0.30922186084833997, "ce": 0.3125028087078044}, {"step": 465, "kl": 0.9436148286060888, "ce": 0.4835024185826078}, {"step": 466, "kl": 0.3236533881830591, "ce": 0.35135140518433017}, {"step": 467, "kl": 0.24026724920084916, "ce": 0.3624731568597798}, {"step": 468, "kl": 0.3282511799163093, "ce": 0.46131361722196895}, {"step": 469, "kl": 0.40061801406042136, "ce": 0.3781049514633279}, {"step": 470, "kl": 0.5676137105190019, "ce": 0.470696412508337}, {"step": 471, "kl": 0.23294441655843073, "ce": 0.3511518468911247}, {"step": 472, "kl": 0.32324344495506335, "ce": 0.4513820236362942}, {"step": 473, "kl": 0.281799017501822, "ce": 0.3676140032707034}, {"step": 474, "kl": 0.28485263814350126, "ce": 0.30023792606185784}, {"step": 475, "kl": 0.21275929947088926, "ce": 0.38323283083182347}, {"step": 476, "kl": 0.22822788767390106, "ce": 0.362066298974788}, {"step": 477, "kl": 0.19291243856895282, "ce": 0.32801990350182036}, {"step": 478, "kl": 0.2793467014029442, "ce": 0.4546286112236778}, {"step": 479, "kl": 0.24787679791389955, "ce": 0.37529022286050084}, {"step": 480, "kl": 0.23411159765779727, "ce": 0.29343501140124545}, {"step": 481, "kl": 0.22871863580440607, "ce": 0.26164892262582695}, {"step": 482, "kl": 0.22429990536434824, "ce": 0.34370752112172287}, {"step": 483, "kl": 0.9808353914291855, "ce": 0.41504761833203263}, {"step": 484, "kl": 0.2207373353939624, "ce": 0.47728289385428135}, {"step": 485, "kl": 0.2346504837678723, "ce": 0.29933293520820103}, {"step": 486, "kl": 0.20120388968783035, "ce": 0.3227373548257269}, {"step": 487, "kl": 0.24258271909861884, "ce": 0.3234682863096401}, {"step": 488, "kl": 0.2807123643996752, "ce": 0.3187178779259252}, {"step": 489, "kl": 0.21530813926881948, "ce": 0.29907441812028884}, {"step": 490, "kl": 0.21326078874976095, "ce": 0.31431491590849936}, {"step": 491, "kl": 0.2535597531279294, "ce": 0.4182390195747754}, {"step": 492, "kl": 0.20903262667484743, "ce": 0.477369260395182}, {"step": 493, "kl": 0.22203858381276081, "ce": 0.3857498920494823}, {"step": 494, "kl": 0.24962322364984127, "ce": 0.2929013895035241}, {"step": 495, "kl": 1.981754052821218, "ce": 0.26595125629206134}, {"step": 496, "kl": 0.3011873533206845, "ce": 0.3662062724380314}, {"step": 497, "kl": 0.40791985096121175, "ce": 0.3240029713474573}, {"step": 498, "kl": 0.2225965041597886, "ce": 0.30239082264502554}, {"step": 499, "kl": 0.272882373259016, "ce": 0.38047212065573577}, {"step": 500, "kl": 0.25982382174211993, "ce": 0.38394796636910417}, {"step": 501, "kl": 0.22150227631028563, "ce": 0.34397378871777873}, {"step": 502, "kl": 0.22073543056774103, "ce": 0.31834325837477057}, {"step": 503, "kl": 0.24227668714794423, "ce": 0.4153372045984134}, {"step": 504, "kl": 0.21946150903278094, "ce": 0.40113095795031456}, {"step": 505, "kl": 0.2548777663724836, "ce": 0.43007269416171934}, {"step": 506, "kl": 0.2246330051713459, "ce": 0.27170013931562315}, {"step": 507, "kl": 0.2103538329320234, "ce": 0.330607249282489}, {"step": 508, "kl": 0.24878831144089464, "ce": 0.3895809658352566}, {"step": 509, "kl": 0.2202252656410848, "ce": 0.31521436963480776}, {"step": 510, "kl": 0.4112018137433573, "ce": 0.34144444160858706}, {"step": 511, "kl": 0.2392160831883811, "ce": 0.4254890069588377}, {"step": 512, "kl": 0.2618293816067917, "ce": 0.42130160185137244}, {"step": 513, "kl": 0.2253454595040644, "ce": 0.3771903657298775}, {"step": 514, "kl": 0.28948345704732203, "ce": 0.3634537853919414}, {"step": 515, "kl": 0.8360612032171778, "ce": 0.38380810776653684}, {"step": 516, "kl": 0.2356932520095772, "ce": 0.3747522203286718}, {"step": 517, "kl": 0.21298075353939422, "ce": 0.30586632453457385}, {"step": 518, "kl": 0.20589356984495788, "ce": 0.36797719613968766}, {"step": 519, "kl": 0.3368629290982815, "ce": 0.34680806205331527}, {"step": 520, "kl": 0.2879912185477814, "ce": 0.33137571768914625}, {"step": 521, "kl": 0.3585374812227547, "ce": 0.29633768231740487}, {"step": 522, "kl": 0.263881268011208, "ce": 0.28072999190490006}, {"step": 523, "kl": 0.2833319495610754, "ce": 0.37347575315495135}, {"step": 524, "kl": 0.23355966232934405, "ce": 0.28678752157744736}, {"step": 525, "kl": 0.5129301749378252, "ce": 0.34742139555493884}, {"step": 526, "kl": 0.2633339078163244, "ce": 0.39854397116226775}, {"step": 527, "kl": 0.23801081686657985, "ce": 0.3421461513923258}, {"step": 528, "kl": 0.4082106231371424, "ce": 0.398167972922932}, {"step": 529, "kl": 0.2486622110316835, "ce": 0.36477855821229577}, {"step": 530, "kl": 0.24569452730945168, "ce": 0.3179578661286142}, {"step": 531, "kl": 0.36010661162638224, "ce": 0.4473167619539619}, {"step": 532, "kl": 0.23549319940194025, "ce": 0.4285028666561149}, {"step": 533, "kl": 0.2435286563349873, "ce": 0.310286693892895}, {"step": 534, "kl": 0.28334178524746406, "ce": 0.4420619636268722}, {"step": 535, "kl": 0.2366409716738664, "ce": 0.3453351152744218}, {"step": 536, "kl": 0.21792417214215706, "ce": 0.3579938148662129}, {"step": 537, "kl": 0.23170238834184398, "ce": 0.4213447021885626}, {"step": 538, "kl": 0.7149201916719123, "ce": 0.42160623146812254}, {"step": 539, "kl": 0.25041852158243527, "ce": 0.4050265952100808}, {"step": 540, "kl": 0.26588505100435633, "ce": 0.39046990067096876}, {"step": 541, "kl": 0.2725330297842059, "ce": 0.33938175792689407}, {"step": 542, "kl": 0.21249289513276828, "ce": 0.39291514544638073}, {"step": 543, "kl": 0.23566039891363944, "ce": 0.48497775421182016}, {"step": 544, "kl": 0.21300109122101757, "ce": 0.3296408325802554}, {"step": 545, "kl": 0.3122108991010717, "ce": 0.4213610772822083}, {"step": 546, "kl": 0.2638857857539103, "ce": 0.397056877853825}, {"step": 547, "kl": 0.22234678281344536, "ce": 0.45610641497027665}, {"step": 548, "kl": 0.24688954922616002, "ce": 0.3754836816120234}, {"step": 549, "kl": 0.250321488180869, "ce": 0.31946175616996464}, {"step": 550, "kl": 0.456847910565987, "ce": 0.32939938266133384}, {"step": 551, "kl": 0.24235613629124597, "ce": 0.4244335808180272}, {"step": 552, "kl": 0.3190288069851328, "ce": 0.5034142006656137}, {"step": 553, "kl": 0.33371108502604396, "ce": 0.47887180037691357}, {"step": 554, "kl": 0.3326030334294943, "ce": 0.35390470240554955}, {"step": 555, "kl": 0.25568854921345896, "ce": 0.34092407287597654}, {"step": 556, "kl": 0.2378171670693474, "ce": 0.3301520451111826}, {"step": 557, "kl": 0.2222144128720399, "ce": 0.4075586105956791}, {"step": 558, "kl": 0.5729230965641224, "ce": 0.34897108085887796}, {"step": 559, "kl": 0.40321673230921967, "ce": 0.5169705119106904}, {"step": 560, "kl": 0.21200717538242925, "ce": 0.3583042866194329}, {"step": 561, "kl": 0.24321723881465956, "ce": 0.4381801783164877}, {"step": 562, "kl": 0.31311191176952424, "ce": 0.33182212991331633}, {"step": 563, "kl": 0.22315626960616924, "ce": 0.383760543783751}, {"step": 564, "kl": 0.24578547520526223, "ce": 0.46971135236997774}, {"step": 565, "kl": 0.2261033276725945, "ce": 0.3258990975205724}, {"step": 566, "kl": 0.21886201726740054, "ce": 0.40925204786946556}, {"step": 567, "kl": 0.24784989535264632, "ce": 0.4680105907929998}, {"step": 568, "kl": 0.31821418755343417, "ce": 0.3783560339009987}, {"step": 569, "kl": 0.24714381391209977, "ce": 0.388109482864582}, {"step": 570, "kl": 0.22797278081213465, "ce": 0.3795150445731563}, {"step": 571, "kl": 0.28088524143225824, "ce": 0.34148746880509906}, {"step": 572, "kl": 0.4678993554393611, "ce": 0.33171241733302853}, {"step": 573, "kl": 0.23469372440066052, "ce": 0.3123078987203261}, {"step": 574, "kl": 0.2930926889656028, "ce": 0.37228711201946607}, {"step": 575, "kl": 0.2078446804617673, "ce": 0.26099315886162633}, {"step": 576, "kl": 0.26527980420080577, "ce": 0.37100456422900974}, {"step": 577, "kl": 0.22918289840555636, "ce": 0.33150857675799594}, {"step": 578, "kl": 0.25198132658859607, "ce": 0.39145606261254795}, {"step": 579, "kl": 0.22732056006475718, "ce": 0.3434202507340813}, {"step": 580, "kl": 0.29884831228704883, "ce": 0.3931501548739652}, {"step": 581, "kl": 0.21722179231977626, "ce": 0.3445979314822226}, {"step": 582, "kl": 0.24206526808636286, "ce": 0.35779715376438886}, {"step": 583, "kl": 0.22890432863288854, "ce": 0.395795501103412}, {"step": 584, "kl": 0.2870627472174481, "ce": 0.33852870926280326}, {"step": 585, "kl": 0.2241927490854441, "ce": 0.4276586823439375}, {"step": 586, "kl": 0.33928487122825135, "ce": 0.38645198074878406}, {"step": 587, "kl": 0.22288554405926453, "ce": 0.3280315054757254}, {"step": 588, "kl": 0.22612396410333782, "ce": 0.37407418460738406}, {"step": 589, "kl": 0.21327351832255825, "ce": 0.38839673010482356}, {"step": 590, "kl": 0.215391828124517, "ce": 0.43146666711124604}, {"step": 591, "kl": 0.23661548781425643, "ce": 0.3780118459329819}, {"step": 592, "kl": 0.6436213552880532, "ce": 0.40336538930572574}, {"step": 593, "kl": 0.35495719824109234, "ce": 0.39271533622398036}, {"step": 594, "kl": 0.2326135774938072, "ce": 0.37042763060452377}, {"step": 595, "kl": 0.32291741870240337, "ce": 0.3657424156948671}, {"step": 596, "kl": 0.23397688060718003, "ce": 0.24736138250319534}, {"step": 597, "kl": 0.24172292109000826, "ce": 0.3394673481666842}, {"step": 598, "kl": 0.23616120951580508, "ce": 0.42472299981272404}, {"step": 599, "kl": 0.2421586620562569, "ce": 0.3646528159115313}, {"step": 600, "kl": 0.33415445813077066, "ce": 0.5130607711152814}, {"step": 601, "kl": 0.2058253030397241, "ce": 0.31569511649774157}, {"step": 602, "kl": 0.24236081759804803, "ce": 0.347271766807238}, {"step": 603, "kl": 0.24675594176759796, "ce": 0.4790627262434286}, {"step": 604, "kl": 0.33804786138724746, "ce": 0.3580589841374713}, {"step": 605, "kl": 0.5487912612605255, "ce": 0.3902909957589516}, {"step": 606, "kl": 0.19760503847736957, "ce": 0.32552825556879234}, {"step": 607, "kl": 0.2529069279236849, "ce": 0.3636936505836395}, {"step": 608, "kl": 0.8655662678777303, "ce": 0.37927240624971315}, {"step": 609, "kl": 0.24514951964345616, "ce": 0.2842939907185831}, {"step": 610, "kl": 0.23375596551157812, "ce": 0.2991697989413366}, {"step": 611, "kl": 1.1102288772480748, "ce": 0.36805949158238477}, {"step": 612, "kl": 0.2573222303698597, "ce": 0.39591670427749404}, {"step": 613, "kl": 0.212652495554432, "ce": 0.34275822975215164}, {"step": 614, "kl": 0.22499103815133625, "ce": 0.35311996142441127}, {"step": 615, "kl": 0.4278120088019937, "ce": 0.3804345756623203}, {"step": 616, "kl": 0.2225857816946011, "ce": 0.3452179527990013}, {"step": 617, "kl": 0.24964700750260954, "ce": 0.26821576261587265}, {"step": 618, "kl": 0.6900813226457396, "ce": 0.397317014087064}, {"step": 619, "kl": 0.21934757373824357, "ce": 0.2786408145556459}, {"step": 620, "kl": 0.2769228191004328, "ce": 0.2918037454604748}, {"step": 621, "kl": 0.19987345299903458, "ce": 0.44588095416032836}, {"step": 622, "kl": 0.23815443490126853, "ce": 0.4183200043069441}, {"step": 623, "kl": 0.2776336195824794, "ce": 0.3967585054769555}, {"step": 624, "kl": 0.753571947961915, "ce": 0.4106636297823203}, {"step": 625, "kl": 0.2738706476995317, "ce": 0.4295152648396894}, {"step": 626, "kl": 0.21106608702057436, "ce": 0.4667802973050641}, {"step": 627, "kl": 0.21184714395918872, "ce": 0.3770456432689712}, {"step": 628, "kl": 0.21638292231950138, "ce": 0.42273620289034924}, {"step": 629, "kl": 0.24582226143374464, "ce": 0.39734693245252956}, {"step": 630, "kl": 0.27008271431230935, "ce": 0.39675869460139385}, {"step": 631, "kl": 0.2527001684827423, "ce": 0.40716249167119944}, {"step": 632, "kl": 0.250445820709689, "ce": 0.3787934458770111}, {"step": 633, "kl": 0.2422694124600963, "ce": 0.38893515305712045}, {"step": 634, "kl": 0.31748589280445194, "ce": 0.35048479353261663}, {"step": 635, "kl": 0.9327779262809908, "ce": 0.2736079330500531}, {"step": 636, "kl": 0.49057246139574096, "ce": 0.3575329879047241}, {"step": 637, "kl": 0.37547296317848, "ce": 0.3346387199454849}, {"step": 638, "kl": 0.3808761789112487, "ce": 0.33030087764041766}, {"step": 639, "kl": 0.20721469192134123, "ce": 0.28935495191223154}, {"step": 640, "kl": 0.24498801897527303, "ce": 0.28268983347304427}, {"step": 641, "kl": 0.2354395270578704, "ce": 0.31759030763763174}, {"step": 642, "kl": 0.22059868039823216, "ce": 0.39227579166362814}, {"step": 643, "kl": 0.20707474571530246, "ce": 0.33867439414526807}, {"step": 644, "kl": 0.27206707496876037, "ce": 0.40092215772139317}, {"step": 645, "kl": 0.259502520868606, "ce": 0.40334800110519187}, {"step": 646, "kl": 0.25573934503077084, "ce": 0.4230591975883444}, {"step": 647, "kl": 0.24401866989647783, "ce": 0.4742414284656398}, {"step": 648, "kl": 0.29567887569168105, "ce": 0.4062025836127203}, {"step": 649, "kl": 0.23839756890355351, "ce": 0.46073326112717616}, {"step": 650, "kl": 0.23561889999850572, "ce": 0.39292249955247854}, {"step": 651, "kl": 0.2598890865634749, "ce": 0.3173540943652171}, {"step": 652, "kl": 0.3126602547570402, "ce": 0.4000938949711959}, {"step": 653, "kl": 0.30444042703304125, "ce": 0.4003414381799849}, {"step": 654, "kl": 0.32228438108245283, "ce": 0.4500431756087601}, {"step": 655, "kl": 0.24751682636222783, "ce": 0.4716671140885543}, {"step": 656, "kl": 0.35367275732692427, "ce": 0.38593128447837016}, {"step": 657, "kl": 0.2540768736038292, "ce": 0.406951402662407}, {"step": 658, "kl": 0.35517937788448295, "ce": 0.4363088961628172}, {"step": 659, "kl": 0.3234377409282484, "ce": 0.3357245022612384}, {"step": 660, "kl": 0.35620156645897716, "ce": 0.4037322909361433}, {"step": 661, "kl": 0.41537712297232776, "ce": 0.4098054879931602}, {"step": 662, "kl": 0.23110349926949597, "ce": 0.2872390236564051}, {"step": 663, "kl": 0.2216767228752451, "ce": 0.4754300299829016}, {"step": 664, "kl": 0.41189020196322734, "ce": 0.2854299390417898}, {"step": 665, "kl": 0.3688118951300415, "ce": 0.33980078458414187}, {"step": 666, "kl": 0.2236716641741729, "ce": 0.48282595820024304}, {"step": 667, "kl": 0.22381395978959934, "ce": 0.35757171432851403}, {"step": 668, "kl": 0.20160190295211283, "ce": 0.4458566775670034}, {"step": 669, "kl": 0.2720627256708222, "ce": 0.3909459265858947}, {"step": 670, "kl": 0.2148172047512591, "ce": 0.3447326534680687}, {"step": 671, "kl": 0.7270453649416939, "ce": 0.3902468756629612}, {"step": 672, "kl": 0.23187582662539932, "ce": 0.2657869184280643}, {"step": 673, "kl": 0.24307801883376495, "ce": 0.4386692133608676}, {"step": 674, "kl": 0.3134574485769382, "ce": 0.46651158591871045}, {"step": 675, "kl": 0.402852243173379, "ce": 0.309349443657149}, {"step": 676, "kl": 0.2867233439500073, "ce": 0.43357986042614977}, {"step": 677, "kl": 0.20557723370960998, "ce": 0.3492912448874577}, {"step": 678, "kl": 0.27059288928818814, "ce": 0.41704372548159385}, {"step": 679, "kl": 0.265288274294183, "ce": 0.4223732993085806}, {"step": 680, "kl": 0.24852526631415098, "ce": 0.36374502619093224}, {"step": 681, "kl": 0.23681536425441913, "ce": 0.34642605273215266}, {"step": 682, "kl": 0.24989511783486526, "ce": 0.2840448963416987}, {"step": 683, "kl": 0.21508645273834687, "ce": 0.45131207023277964}, {"step": 684, "kl": 0.21121879010104042, "ce": 0.330763435879734}, {"step": 685, "kl": 0.22456734283126464, "ce": 0.28453074174018106}, {"step": 686, "kl": 0.2779371595019104, "ce": 0.3697895757361117}, {"step": 687, "kl": 0.22062796728326292, "ce": 0.3339630175994229}, {"step": 688, "kl": 0.3606660165214146, "ce": 0.292305648469686}, {"step": 689, "kl": 0.2410765690507004, "ce": 0.4350128462945501}, {"step": 690, "kl": 0.2244011759275367, "ce": 0.3260701330284444}, {"step": 691, "kl": 0.47044007687569595, "ce": 0.39750423092560094}, {"step": 692, "kl": 0.2932400548423386, "ce": 0.4731431494928906}, {"step": 693, "kl": 0.36293546981822145, "ce": 0.31421409938859673}, {"step": 694, "kl": 0.25407226440066605, "ce": 0.27011613642915766}, {"step": 695, "kl": 0.2088722531407262, "ce": 0.3318667844052215}, {"step": 696, "kl": 0.3231798180253991, "ce": 0.3531821016849417}, {"step": 697, "kl": 0.22620347005832664, "ce": 0.4090100255184371}, {"step": 698, "kl": 0.21983498453644568, "ce": 0.3782145048978445}, {"step": 699, "kl": 0.2398837383390689, "ce": 0.37000499713284507}, {"step": 700, "kl": 0.21447973991520686, "ce": 0.27948873341419517}, {"step": 701, "kl": 0.24738431421441476, "ce": 0.4101153049306854}, {"step": 702, "kl": 0.25845896615364855, "ce": 0.36753449559422835}, {"step": 703, "kl": 0.4247282591047571, "ce": 0.47865180243720284}, {"step": 704, "kl": 0.23919285253727396, "ce": 0.3354338021800435}, {"step": 705, "kl": 0.24199364504051596, "ce": 0.29963965794082065}, {"step": 706, "kl": 0.3648809333925979, "ce": 0.3329198384134211}, {"step": 707, "kl": 0.22199367582403878, "ce": 0.33313373588903383}, {"step": 708, "kl": 0.3057329179073643, "ce": 0.4143045532341519}, {"step": 709, "kl": 0.3017061727510082, "ce": 0.4444015941863725}, {"step": 710, "kl": 0.24594512507886312, "ce": 0.3387639831950646}, {"step": 711, "kl": 0.18735884919696744, "ce": 0.31350432068641004}, {"step": 712, "kl": 0.29497464227655423, "ce": 0.36746942733834553}, {"step": 713, "kl": 0.23972484505310665, "ce": 0.35350210513614916}, {"step": 714, "kl": 0.2302973914622554, "ce": 0.39221276236794766}, {"step": 715, "kl": 0.4473057471716357, "ce": 0.3857399480163201}, {"step": 716, "kl": 0.22900360822677615, "ce": 0.28936319691794254}, {"step": 717, "kl": 0.2129421690800711, "ce": 0.3677006867587898}, {"step": 718, "kl": 0.2536616824259143, "ce": 0.33132779600621703}, {"step": 719, "kl": 0.23525435186438398, "ce": 0.5439594675945766}, {"step": 720, "kl": 0.23079934283261588, "ce": 0.34239783531258616}, {"step": 721, "kl": 0.2869340484657953, "ce": 0.3030646044905014}, {"step": 722, "kl": 0.23401670089478566, "ce": 0.27775618554606896}, {"step": 723, "kl": 0.22167327469172918, "ce": 0.4073262114745344}, {"step": 724, "kl": 0.2658893468299668, "ce": 0.3875648315285706}, {"step": 725, "kl": 0.3131086965160831, "ce": 0.4274445165833778}, {"step": 726, "kl": 0.2283068158515394, "ce": 0.38898674677097705}, {"step": 727, "kl": 0.26691910432571225, "ce": 0.35311567241595004}, {"step": 728, "kl": 0.3056631575485944, "ce": 0.47940459402885227}, {"step": 729, "kl": 0.8053646904531572, "ce": 0.3438417743344243}, {"step": 730, "kl": 0.2304363842465572, "ce": 0.3264293214540567}, {"step": 731, "kl": 0.24538182482626406, "ce": 0.32828793658597544}, {"step": 732, "kl": 0.2635929928362774, "ce": 0.3969911814321757}, {"step": 733, "kl": 0.2058870291501528, "ce": 0.3179881436819153}, {"step": 734, "kl": 0.23983788470515602, "ce": 0.4197700260077047}, {"step": 735, "kl": 0.5151322400643326, "ce": 0.4829233986990792}, {"step": 736, "kl": 0.22233893092929624, "ce": 0.3526048749059432}, {"step": 737, "kl": 0.2754916451566334, "ce": 0.3249977741307771}, {"step": 738, "kl": 0.3471641981986807, "ce": 0.36680536786282036}, {"step": 739, "kl": 0.23148588030254794, "ce": 0.36773350051380754}, {"step": 740, "kl": 0.23249824036201933, "ce": 0.33491175953661134}, {"step": 741, "kl": 0.22157844615988412, "ce": 0.32303779671740773}, {"step": 742, "kl": 0.23531475170422145, "ce": 0.39891365850522476}, {"step": 743, "kl": 0.23012417621494077, "ce": 0.4076058227032455}, {"step": 744, "kl": 0.251931013041378, "ce": 0.30071410579384916}, {"step": 745, "kl": 0.24966986456075485, "ce": 0.32715282775461674}, {"step": 746, "kl": 0.3986069727962822, "ce": 0.32531025343225994}, {"step": 747, "kl": 0.228537127770211, "ce": 0.34245227981214904}, {"step": 748, "kl": 0.2099452712061851, "ce": 0.3670597220825755}, {"step": 749, "kl": 0.23813180564123804, "ce": 0.34731843258832334}, {"step": 750, "kl": 0.41101288681215586, "ce": 0.4084167293535389}, {"step": 751, "kl": 0.24022608921642735, "ce": 0.3287371694139467}, {"step": 752, "kl": 0.428122023068544, "ce": 0.31318947254615187}, {"step": 753, "kl": 0.22373484228710713, "ce": 0.4134708137932994}, {"step": 754, "kl": 0.2539711325217082, "ce": 0.34350820573315227}, {"step": 755, "kl": 0.3527450036083043, "ce": 0.3141941422982247}, {"step": 756, "kl": 0.27491148988530983, "ce": 0.3610904637455583}, {"step": 757, "kl": 0.2740498205996378, "ce": 0.4003647689487098}, {"step": 758, "kl": 0.2845323585146594, "ce": 0.38973844719521256}, {"step": 759, "kl": 0.24495463217458419, "ce": 0.3788176385952896}, {"step": 760, "kl": 0.2935555175992292, "ce": 0.30420806856870214}, {"step": 761, "kl": 0.23113416216277405, "ce": 0.5085989622919218}, {"step": 762, "kl": 0.2955102731022763, "ce": 0.4142972072241765}, {"step": 763, "kl": 0.4969893233422186, "ce": 0.36593548771061}, {"step": 764, "kl": 0.22332711562080085, "ce": 0.25941206885781287}, {"step": 765, "kl": 0.2348901843244087, "ce": 0.4234542738456674}, {"step": 766, "kl": 0.24404231957924663, "ce": 0.4089228220986756}, {"step": 767, "kl": 0.24809847471122032, "ce": 0.31623419100516553}, {"step": 768, "kl": 0.22724111416935466, "ce": 0.45978613283318526}, {"step": 769, "kl": 0.27879372886706627, "ce": 0.3213748768041559}, {"step": 770, "kl": 0.32485600044493157, "ce": 0.3614536177771174}, {"step": 771, "kl": 0.24280911834001034, "ce": 0.3585941675797249}, {"step": 772, "kl": 0.24583984065076986, "ce": 0.4315454067485431}, {"step": 773, "kl": 0.2283647667050986, "ce": 0.44867526538788327}, {"step": 774, "kl": 0.3528547911790537, "ce": 0.3677614346255946}, {"step": 775, "kl": 0.28778011740309245, "ce": 0.39254174711824086}, {"step": 776, "kl": 0.22721503140244864, "ce": 0.3836473835848024}, {"step": 777, "kl": 0.26910384267405063, "ce": 0.3111059231801076}, {"step": 778, "kl": 0.23388637042712743, "ce": 0.4841089855523588}, {"step": 779, "kl": 0.3711508999351695, "ce": 0.5124834431995681}, {"step": 780, "kl": 0.30008685622066333, "ce": 0.4624707332894772}, {"step": 781, "kl": 0.30347521292239465, "ce": 0.3503322861368371}, {"step": 782, "kl": 0.2710108761507626, "ce": 0.37330037719582215}, {"step": 783, "kl": 0.194278685696379, "ce": 0.3069898266866417}, {"step": 784, "kl": 0.24548188991221248, "ce": 0.3665923350001071}, {"step": 785, "kl": 0.27737608756727844, "ce": 0.35093368576015105}, {"step": 786, "kl": 0.26093441973823617, "ce": 0.3775316860099428}, {"step": 787, "kl": 0.25166728165665536, "ce": 0.3717232675282505}, {"step": 788, "kl": 0.279358165722754, "ce": 0.39702198482254175}, {"step": 789, "kl": 0.22057513657436578, "ce": 0.3986544604105873}, {"step": 790, "kl": 0.2192731697388437, "ce": 0.288424119442943}, {"step": 791, "kl": 0.24670313326151427, "ce": 0.2791443091064761}, {"step": 792, "kl": 0.30775437130492145, "ce": 0.41622905827196255}, {"step": 793, "kl": 0.2246130596751898, "ce": 0.3304833213807403}, {"step": 794, "kl": 0.3142563377043933, "ce": 0.4256757689623943}, {"step": 795, "kl": 0.2268725683789454, "ce": 0.35915249417597805}, {"step": 796, "kl": 0.2698446708007662, "ce": 0.3968603792876634}, {"step": 797, "kl": 0.26896227371983233, "ce": 0.3551420651688071}, {"step": 798, "kl": 0.3240424308575414, "ce": 0.4599718007952936}, {"step": 799, "kl": 0.21486667363970113, "ce": 0.3731698384118265}, {"step": 800, "kl": 0.23650601961234488, "ce": 0.3088061853915503}, {"step": 801, "kl": 0.19746260016981407, "ce": 0.40978784702220666}, {"step": 802, "kl": 0.251077259941645, "ce": 0.3048575728177575}, {"step": 803, "kl": 0.2101242517781849, "ce": 0.45483156570757666}, {"step": 804, "kl": 0.23174060636377536, "ce": 0.3625368316552392}, {"step": 805, "kl": 0.36521179179916036, "ce": 0.33890481217172497}, {"step": 806, "kl": 0.2911619649381468, "ce": 0.28697631203116547}, {"step": 807, "kl": 0.24487681668119218, "ce": 0.28536671914567124}, {"step": 808, "kl": 0.25937342344386805, "ce": 0.3120092269064344}, {"step": 809, "kl": 0.3637418095937032, "ce": 0.4403229765482496}, {"step": 810, "kl": 0.2694364654480555, "ce": 0.5152736810210132}, {"step": 811, "kl": 0.2986738428738114, "ce": 0.3434659605211963}, {"step": 812, "kl": 0.2042059952315297, "ce": 0.3837071318886844}, {"step": 813, "kl": 0.3607039960246737, "ce": 0.3541018954843343}, {"step": 814, "kl": 0.23855508250685103, "ce": 0.3126801294137693}, {"step": 815, "kl": 0.21962348652062558, "ce": 0.37682621787820625}, {"step": 816, "kl": 0.25859112363453896, "ce": 0.3948303089776047}, {"step": 817, "kl": 0.20485092709879327, "ce": 0.3885408496130047}, {"step": 818, "kl": 0.34547398447962346, "ce": 0.32646224966567744}, {"step": 819, "kl": 0.24342473048507968, "ce": 0.3809093565119308}, {"step": 820, "kl": 0.2602658420085494, "ce": 0.3294022562574038}, {"step": 821, "kl": 0.2722744017760747, "ce": 0.4657903095803225}, {"step": 822, "kl": 0.27557228351461477, "ce": 0.27959474054049516}, {"step": 823, "kl": 0.25182534683108826, "ce": 0.3820299246297288}, {"step": 824, "kl": 0.21984965565956316, "ce": 0.3474805875463119}, {"step": 825, "kl": 0.22185299132710765, "ce": 0.35876716746893744}, {"step": 826, "kl": 0.24802872860971092, "ce": 0.33504328601421396}, {"step": 827, "kl": 0.4358950116314593, "ce": 0.3514359146653774}, {"step": 828, "kl": 0.2760703898030997, "ce": 0.26808951772758016}, {"step": 829, "kl": 0.22928742661469687, "ce": 0.40015815534257326}, {"step": 830, "kl": 0.24741818452677644, "ce": 0.3744996783535403}, {"step": 831, "kl": 0.22728193826702026, "ce": 0.40872705987539304}, {"step": 832, "kl": 0.22125645078554024, "ce": 0.39188886510015775}, {"step": 833, "kl": 0.21268540038036263, "ce": 0.3126188088208437}, {"step": 834, "kl": 0.24199054763030628, "ce": 0.29441539102827285}, {"step": 835, "kl": 0.29763460782832796, "ce": 0.31223785370272794}, {"step": 836, "kl": 0.36695604445344054, "ce": 0.3801337918832545}, {"step": 837, "kl": 0.2611739600142538, "ce": 0.5031688585160882}, {"step": 838, "kl": 0.2529729902318295, "ce": 0.3118500990942138}, {"step": 839, "kl": 0.3979845022900343, "ce": 0.37161522733345437}, {"step": 840, "kl": 0.3223696096145442, "ce": 0.4625556392281862}, {"step": 841, "kl": 0.27935093168624564, "ce": 0.43267125493223596}, {"step": 842, "kl": 0.2721652665084494, "ce": 0.3549953527572745}, {"step": 843, "kl": 0.22850135835555677, "ce": 0.2681558519487267}, {"step": 844, "kl": 0.24485794811928185, "ce": 0.3722927657216184}, {"step": 845, "kl": 0.3854634311060096, "ce": 0.2936029459534097}, {"step": 846, "kl": 0.316244193770746, "ce": 0.4198475134692302}, {"step": 847, "kl": 0.30381666579172195, "ce": 0.31936148001864795}, {"step": 848, "kl": 0.23053814779548285, "ce": 0.34898229425742466}, {"step": 849, "kl": 0.2238979065182652, "ce": 0.27715371617819534}, {"step": 850, "kl": 0.32743226710272944, "ce": 0.39650090662192317}, {"step": 851, "kl": 0.21513787971247356, "ce": 0.28211260640311664}, {"step": 852, "kl": 0.19746038167855412, "ce": 0.26292738084002015}, {"step": 853, "kl": 0.23657005730025266, "ce": 0.4048616098250565}, {"step": 854, "kl": 0.29869510454684883, "ce": 0.3671987463260316}, {"step": 855, "kl": 0.46517607374217457, "ce": 0.4138491889752162}, {"step": 856, "kl": 0.23690153637275518, "ce": 0.33909198295643417}, {"step": 857, "kl": 0.25746532289743496, "ce": 0.4185306254506195}, {"step": 858, "kl": 0.21222995755044535, "ce": 0.3216461273863227}, {"step": 859, "kl": 0.2349977287635397, "ce": 0.4159658972102637}, {"step": 860, "kl": 0.22217575359121144, "ce": 0.33847339289962863}, {"step": 861, "kl": 0.20182527231983693, "ce": 0.27648593169826285}, {"step": 862, "kl": 0.23699663238815094, "ce": 0.4645859044522325}, {"step": 863, "kl": 0.2512973065142865, "ce": 0.2925486930540505}, {"step": 864, "kl": 0.20699806125042747, "ce": 0.28051144881089046}, {"step": 865, "kl": 0.22518251704760733, "ce": 0.36839984199015086}, {"step": 866, "kl": 0.2546844511457476, "ce": 0.39129379364917694}, {"step": 867, "kl": 0.3282850629881293, "ce": 0.36358446082660617}, {"step": 868, "kl": 0.2654017546537191, "ce": 0.3043064273653232}, {"step": 869, "kl": 0.21694781347525924, "ce": 0.2984969701546492}, {"step": 870, "kl": 0.27540894033578045, "ce": 0.32179011812769825}, {"step": 871, "kl": 0.24963666068470292, "ce": 0.37284328762039665}, {"step": 872, "kl": 0.21426371251099088, "ce": 0.38222437874963905}, {"step": 873, "kl": 0.2666776994676027, "ce": 0.41755045383693923}, {"step": 874, "kl": 0.28234299656349815, "ce": 0.39316577815240433}, {"step": 875, "kl": 0.272679142989327, "ce": 0.37441099119471166}, {"step": 876, "kl": 0.28993282711279067, "ce": 0.4376412819015834}, {"step": 877, "kl": 0.4341568638474156, "ce": 0.3731203729289369}, {"step": 878, "kl": 0.2915298268148372, "ce": 0.41893026094335345}, {"step": 879, "kl": 0.26135350320682116, "ce": 0.4245059905656939}, {"step": 880, "kl": 0.21526092163559246, "ce": 0.3886120923400762}, {"step": 881, "kl": 0.2182893651014965, "ce": 0.35239916553130146}, {"step": 882, "kl": 0.4254495270215949, "ce": 0.375627873134028}, {"step": 883, "kl": 0.2541005818803333, "ce": 0.46098122576796635}, {"step": 884, "kl": 0.20740776997959745, "ce": 0.37497333981259123}, {"step": 885, "kl": 0.2440211036385333, "ce": 0.3176460731115913}, {"step": 886, "kl": 0.26649710591085435, "ce": 0.42921970077374016}, {"step": 887, "kl": 0.27527534703808376, "ce": 0.3339059178872822}, {"step": 888, "kl": 0.27366622429062093, "ce": 0.450367459951271}, {"step": 889, "kl": 0.22750781640219697, "ce": 0.4596875832051427}, {"step": 890, "kl": 0.2636459068286531, "ce": 0.33562079706246867}, {"step": 891, "kl": 0.20466746018554172, "ce": 0.4130209315867019}, {"step": 892, "kl": 0.2385512780646623, "ce": 0.4207729847066276}, {"step": 893, "kl": 0.22482824963578535, "ce": 0.3155529450312445}, {"step": 894, "kl": 0.5334366456645778, "ce": 0.3741703243623423}, {"step": 895, "kl": 0.8759081251065618, "ce": 0.3953870934575251}, {"step": 896, "kl": 0.2518812137385727, "ce": 0.3354720069186265}], "val": [{"step": 0, "math_kl": 0.18375438443199724, "math_ce": 0.796609162952875, "code_kl": 0.34498801428341486, "code_ce": 0.24669437762251217, "math_hard_kl": 0.27730645571818935, "math_hard_ce": 0.7908673360534969}, {"step": 448, "math_kl": 0.2620013395384466, "math_ce": 0.45030905953311884, "code_kl": 0.22559929004439364, "code_ce": 0.2549985100735697, "math_hard_kl": 0.31547180185778473, "math_hard_ce": 0.5997092280034104}, {"step": 896, "math_kl": 0.2711174080266869, "math_ce": 0.48686714429648636, "code_kl": 0.23916414351690382, "code_ce": 0.26016022039706727, "math_hard_kl": 0.3349221330783336, "math_hard_ce": 0.6155070331563108}]}
seq_code_math_gt_sft/stage2_math/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292e6ba9d45951d312df2953e8d14131aabe8c063d520831d199f3c9b2b4538c
3
+ size 3087467144