pmangesh commited on
Commit
912b30c
·
verified ·
1 Parent(s): a45fce7

Upload folder using huggingface_hub

Browse files
seq_math_code_gt_sft/run_info.json CHANGED
@@ -32,9 +32,32 @@
32
  "math_hard_ce": 0.6152356422562573
33
  },
34
  "peak_gb_student": 36.754438400268555,
35
- "peak_gb_teachers": 29.564642429351807,
36
- "bench_h": 0.36716745177904764,
37
- "gpu_bench": "NVIDIA RTX 6000 Ada Generation"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
39
  }
40
  }
 
32
  "math_hard_ce": 0.6152356422562573
33
  },
34
  "peak_gb_student": 36.754438400268555,
35
+ "peak_gb_teachers": 29.564642429351807
36
+ },
37
+ "stage2_code": {
38
+ "domain": "code",
39
+ "steps": 922,
40
+ "train_h": 3.3934424249331157,
41
+ "val_start": {
42
+ "step": 0,
43
+ "math_kl": 0.2558450283886451,
44
+ "math_ce": 0.4875823904101404,
45
+ "code_kl": 0.16784317317180839,
46
+ "code_ce": 0.3320483730687428,
47
+ "math_hard_kl": 0.3206654156163548,
48
+ "math_hard_ce": 0.6148898550851406
49
+ },
50
+ "val_end": {
51
+ "step": 922,
52
+ "math_kl": 0.22842272387506696,
53
+ "math_ce": 0.5158765047799361,
54
+ "code_kl": 0.375653243372234,
55
+ "code_ce": 0.2474786401165565,
56
+ "math_hard_kl": 0.31006984450732655,
57
+ "math_hard_ce": 0.6471800292055488
58
+ },
59
+ "peak_gb_student": 33.701783180236816,
60
+ "peak_gb_teachers": 29.222092628479004
61
  }
62
  }
63
  }
seq_math_code_gt_sft/stage2_code/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_math_code_gt_sft/stage2_code/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_math_code_gt_sft/stage2_code/log.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [{"step": 1, "kl": 0.17517338531845014, "ce": 0.3809681081379539}, {"step": 2, "kl": 0.15942084881073348, "ce": 0.31563242165187866}, {"step": 3, "kl": 0.13811139851068224, "ce": 0.31065556032982866}, {"step": 4, "kl": 0.15346003850399115, "ce": 0.35072562220434594}, {"step": 5, "kl": 0.1941845653109562, "ce": 0.3845279038582586}, {"step": 6, "kl": 0.19880987859103796, "ce": 0.3784063389779685}, {"step": 7, "kl": 0.17216932894282166, "ce": 0.32448291928959916}, {"step": 8, "kl": 0.1756969739259896, "ce": 0.33399450113001233}, {"step": 9, "kl": 0.17608251584400283, "ce": 0.33085078051966477}, {"step": 10, "kl": 0.14103111484783862, "ce": 0.3187606014631915}, {"step": 11, "kl": 0.1718487158946314, "ce": 0.3097964131840656}, {"step": 12, "kl": 0.18019216250871153, "ce": 0.3221057370097041}, {"step": 13, "kl": 0.18644600098574204, "ce": 0.2994043824821571}, {"step": 14, "kl": 0.20933602621937655, "ce": 0.23837804257830272}, {"step": 15, "kl": 0.22209001714533025, "ce": 0.34650047473314155}, {"step": 16, "kl": 0.23261092030336142, "ce": 0.31236759848269513}, {"step": 17, "kl": 0.25572650204126607, "ce": 0.2787534128655891}, {"step": 18, "kl": 0.23145445580936885, "ce": 0.3087738101072627}, {"step": 19, "kl": 0.24936017935576416, "ce": 0.272326062375469}, {"step": 20, "kl": 0.23246373334202472, "ce": 0.2596079802931401}, {"step": 21, "kl": 0.25767237471119586, "ce": 0.3480968893009381}, {"step": 22, "kl": 0.24896457893339208, "ce": 0.276910121953376}, {"step": 23, "kl": 0.26449429248106704, "ce": 0.30774589806629793}, {"step": 24, "kl": 0.26440993601721746, "ce": 0.2844623468371623}, {"step": 25, "kl": 0.27653386047686884, "ce": 0.29106016792913464}, {"step": 26, "kl": 0.2687186613443622, "ce": 0.2525359825204039}, {"step": 27, "kl": 0.25433019879967833, "ce": 0.304111741718493}, {"step": 28, "kl": 0.3211742798310709, "ce": 0.29928581096984874}, {"step": 29, "kl": 0.23979665049439164, "ce": 0.2553947630543048}, {"step": 30, "kl": 0.29008541500421503, "ce": 0.3153681691211503}, {"step": 31, "kl": 0.3031301680476476, "ce": 0.2972253050271093}, {"step": 32, "kl": 0.27606629929297594, "ce": 0.2879799997447934}, {"step": 33, "kl": 0.27563922681088426, "ce": 0.3093345091913392}, {"step": 34, "kl": 0.3134934752022428, "ce": 0.2786555068833487}, {"step": 35, "kl": 0.2875062671422043, "ce": 0.25952082267065596}, {"step": 36, "kl": 0.2534950938714907, "ce": 0.289758763648018}, {"step": 37, "kl": 0.2903501785298857, "ce": 0.32002090406869865}, {"step": 38, "kl": 0.26881650205765595, "ce": 0.23034590440372268}, {"step": 39, "kl": 0.2739646380036198, "ce": 0.24286044761263575}, {"step": 40, "kl": 0.3330417255653023, "ce": 0.3089248355763622}, {"step": 41, "kl": 0.3298704185004218, "ce": 0.2443799904110775}, {"step": 42, "kl": 0.2933725779026876, "ce": 0.28390936995997573}, {"step": 43, "kl": 0.2836183888618941, "ce": 0.291797645588429}, {"step": 44, "kl": 0.34509349295273134, "ce": 0.31517705122110706}, {"step": 45, "kl": 0.3237158800474486, "ce": 0.272395304271153}, {"step": 46, "kl": 0.28964340982358316, "ce": 0.3329064008605837}, {"step": 47, "kl": 0.3019573428973303, "ce": 0.2820993425398308}, {"step": 48, "kl": 0.3173355720528825, "ce": 0.2707526760688882}, {"step": 49, "kl": 0.30514823538034075, "ce": 0.31968802995579215}, {"step": 50, "kl": 0.31051292126809515, "ce": 0.30970989519104897}, {"step": 51, "kl": 0.2814073237140346, "ce": 0.23615032485004467}, {"step": 52, "kl": 0.29180959501271836, "ce": 0.2942770163275541}, {"step": 53, "kl": 0.2885073188093489, "ce": 0.2809459747249606}, {"step": 54, "kl": 0.3116304120136323, "ce": 0.2674429815025604}, {"step": 55, "kl": 0.298097288274179, "ce": 0.3212938195554793}, {"step": 56, "kl": 0.29017053481272115, "ce": 0.2625337079879575}, {"step": 57, "kl": 0.34067259008534967, "ce": 0.2171285919932442}, {"step": 58, "kl": 0.32452201951757087, "ce": 0.2845907260070039}, {"step": 59, "kl": 0.312831539550703, "ce": 0.30150133456060857}, {"step": 60, "kl": 0.32177627853868745, "ce": 0.3058053826118683}, {"step": 61, "kl": 0.2606721400262829, "ce": 0.30718019737892244}, {"step": 62, "kl": 0.3499827361793802, "ce": 0.3148542584315143}, {"step": 63, "kl": 0.29145092960518443, "ce": 0.2782618263249016}, {"step": 64, "kl": 0.3424982857201977, "ce": 0.23177452300513923}, {"step": 65, "kl": 0.3261781995278091, "ce": 0.29632803698646504}, {"step": 66, "kl": 0.2826132693619367, "ce": 0.2995161475836747}, {"step": 67, "kl": 0.29712025288297267, "ce": 0.24769447416154522}, {"step": 68, "kl": 0.27803653686593033, "ce": 0.3157432578816274}, {"step": 69, "kl": 0.29663090242753626, "ce": 0.26374999952259837}, {"step": 70, "kl": 0.29324406818535087, "ce": 0.25975217958243707}, {"step": 71, "kl": 0.2670171774912289, "ce": 0.3004544687280711}, {"step": 72, "kl": 0.2933703773445651, "ce": 0.25879122181572156}, {"step": 73, "kl": 0.3519600190926547, "ce": 0.2938106509816457}, {"step": 74, "kl": 0.29541225720607944, "ce": 0.2953689518634727}, {"step": 75, "kl": 0.32755643170864424, "ce": 0.2561744654062882}, {"step": 76, "kl": 0.29789980920115994, "ce": 0.25119592275747943}, {"step": 77, "kl": 0.34740956752725105, "ce": 0.25571177677745127}, {"step": 78, "kl": 0.26338202618134127, "ce": 0.23536033960647915}, {"step": 79, "kl": 0.330550281916867, "ce": 0.28720587358671473}, {"step": 80, "kl": 0.31071279024412635, "ce": 0.30120031253030793}, {"step": 81, "kl": 0.32404282328012435, "ce": 0.28373054583408375}, {"step": 82, "kl": 0.34926494034853856, "ce": 0.24944275970004662}, {"step": 83, "kl": 0.2685285960995901, "ce": 0.24875963183416835}, {"step": 84, "kl": 0.2834657515146799, "ce": 0.31390666063315337}, {"step": 85, "kl": 0.3269015160550498, "ce": 0.2606888083241841}, {"step": 86, "kl": 0.3289320711266628, "ce": 0.2964465904199572}, {"step": 87, "kl": 0.3065672467221694, "ce": 0.26064928305282564}, {"step": 88, "kl": 0.29787885648128243, "ce": 0.23118052445282652}, {"step": 89, "kl": 0.31495636812714156, "ce": 0.3040460013049657}, {"step": 90, "kl": 0.31696162250755866, "ce": 0.2948278988713867}, {"step": 91, "kl": 0.2862936994016245, "ce": 0.26009975262292945}, {"step": 92, "kl": 0.2986079366146294, "ce": 0.28670248670154375}, {"step": 93, "kl": 0.29231569405518587, "ce": 0.2969304475643521}, {"step": 94, "kl": 0.2875578616667165, "ce": 0.26628877699404424}, {"step": 95, "kl": 0.32727406929329844, "ce": 0.2613260378950016}, {"step": 96, "kl": 0.33208081580952165, "ce": 0.3207713152992826}, {"step": 97, "kl": 0.29041317541360584, "ce": 0.2400892431982632}, {"step": 98, "kl": 0.2983379851459956, "ce": 0.30514848209788537}, {"step": 99, "kl": 0.25309338130848524, "ce": 0.27000087664893946}, {"step": 100, "kl": 0.30364359224502957, "ce": 0.2970912749986441}, {"step": 101, "kl": 0.31453386262284055, "ce": 0.3138396380787897}, {"step": 102, "kl": 0.350461128706718, "ce": 0.297679346793712}, {"step": 103, "kl": 0.32155437008529447, "ce": 0.3241441345802512}, {"step": 104, "kl": 0.33539260178232777, "ce": 0.2778866519140453}, {"step": 105, "kl": 0.33783639504091584, "ce": 0.2510737733003803}, {"step": 106, "kl": 0.3367724930267989, "ce": 0.3411306565569372}, {"step": 107, "kl": 0.29918590087178426, "ce": 0.30459689080870495}, {"step": 108, "kl": 0.3034344652215217, "ce": 0.28099336908824407}, {"step": 109, "kl": 0.3312858565593015, "ce": 0.25984942238936043}, {"step": 110, "kl": 0.3137476761292291, "ce": 0.2445016405803713}, {"step": 111, "kl": 0.2917589171082287, "ce": 0.26023641315842944}, {"step": 112, "kl": 0.29881059562859513, "ce": 0.24415135333083818}, {"step": 113, "kl": 0.29627525375719493, "ce": 0.26516607160191674}, {"step": 114, "kl": 0.32752036830854253, "ce": 0.3251588231599218}, {"step": 115, "kl": 0.33188289647444097, "ce": 0.21061509652755317}, {"step": 116, "kl": 0.2831735429076975, "ce": 0.23576281057007012}, {"step": 117, "kl": 0.32161865729522293, "ce": 0.2750137435276039}, {"step": 118, "kl": 0.320296700106918, "ce": 0.29652192849147174}, {"step": 119, "kl": 0.3356558526541221, "ce": 0.29208834813658907}, {"step": 120, "kl": 0.3272309156376223, "ce": 0.3067154333875587}, {"step": 121, "kl": 0.2826109119762074, "ce": 0.250878179940388}, {"step": 122, "kl": 0.349119981848247, "ce": 0.3065104455913502}, {"step": 123, "kl": 0.33456235510007626, "ce": 0.27430123969995535}, {"step": 124, "kl": 0.32664655347649735, "ce": 0.2924128186220829}, {"step": 125, "kl": 0.3464523878613224, "ce": 0.2852903140573163}, {"step": 126, "kl": 0.35194005887861524, "ce": 0.3441277448472614}, {"step": 127, "kl": 0.2883383512823401, "ce": 0.26464441779435544}, {"step": 128, "kl": 0.3453469348361417, "ce": 0.22532540627020053}, {"step": 129, "kl": 0.29586459217496286, "ce": 0.2647331354883838}, {"step": 130, "kl": 0.30076849827431146, "ce": 0.2641192209318187}, {"step": 131, "kl": 0.32407119465881395, "ce": 0.2629621728979342}, {"step": 132, "kl": 0.29200394862267415, "ce": 0.26597978105554737}, {"step": 133, "kl": 0.31022486179378794, "ce": 0.29518799504623033}, {"step": 134, "kl": 0.3020281202227559, "ce": 0.2965518596580283}, {"step": 135, "kl": 0.3356405993664308, "ce": 0.2589102705177777}, {"step": 136, "kl": 0.3229499518897272, "ce": 0.24106476623434814}, {"step": 137, "kl": 0.31979588732659747, "ce": 0.27136188790492227}, {"step": 138, "kl": 0.3136355395704097, "ce": 0.2623315138184367}, {"step": 139, "kl": 0.2708335296618673, "ce": 0.2860782900943032}, {"step": 140, "kl": 0.33983939072290614, "ce": 0.33372634673497314}, {"step": 141, "kl": 0.29549669456237715, "ce": 0.24842652621994946}, {"step": 142, "kl": 0.33661567493249167, "ce": 0.26396287191319334}, {"step": 143, "kl": 0.29309258533777527, "ce": 0.28246379821073436}, {"step": 144, "kl": 0.29713432790456556, "ce": 0.24986855256213028}, {"step": 145, "kl": 0.3126321559036514, "ce": 0.2906942920608214}, {"step": 146, "kl": 0.3392098569761939, "ce": 0.2862583186956433}, {"step": 147, "kl": 0.3386355408426624, "ce": 0.2807034082791436}, {"step": 148, "kl": 0.3049027653094532, "ce": 0.3311385162419323}, {"step": 149, "kl": 0.3014893945273753, "ce": 0.26674074974746914}, {"step": 150, "kl": 0.2957823922253754, "ce": 0.28775441724782586}, {"step": 151, "kl": 0.33069168767205404, "ce": 0.2914288658728966}, {"step": 152, "kl": 0.3265732176707911, "ce": 0.2653348504611341}, {"step": 153, "kl": 0.2897868073910497, "ce": 0.2724214782062758}, {"step": 154, "kl": 0.33865876458213395, "ce": 0.2642570721126598}, {"step": 155, "kl": 0.32757243431264316, "ce": 0.28847507111486276}, {"step": 156, "kl": 0.33714565045128997, "ce": 0.29330957738073404}, {"step": 157, "kl": 0.3495562381779772, "ce": 0.28987042988944905}, {"step": 158, "kl": 0.3349975899912853, "ce": 0.2719196893963363}, {"step": 159, "kl": 0.30131906771523953, "ce": 0.2991484401803481}, {"step": 160, "kl": 0.33510677690245677, "ce": 0.29311906450594477}, {"step": 161, "kl": 0.31831803083034627, "ce": 0.2927080053846446}, {"step": 162, "kl": 0.3396275501823089, "ce": 0.291917548824907}, {"step": 163, "kl": 0.2657495558768765, "ce": 0.24633918245475134}, {"step": 164, "kl": 0.33125317852856395, "ce": 0.261966040251885}, {"step": 165, "kl": 0.2705919937645803, "ce": 0.31827381330774773}, {"step": 166, "kl": 0.3092312924080917, "ce": 0.3247959151853476}, {"step": 167, "kl": 0.33462698478629377, "ce": 0.26433010164735}, {"step": 168, "kl": 0.2786963828167512, "ce": 0.26989546295456046}, {"step": 169, "kl": 0.3319405956544738, "ce": 0.2749993568750066}, {"step": 170, "kl": 0.3144479191987364, "ce": 0.29071393333253237}, {"step": 171, "kl": 0.2910352816770818, "ce": 0.2534965678218572}, {"step": 172, "kl": 0.29911971898212025, "ce": 0.28246795368868105}, {"step": 173, "kl": 0.3188467846426129, "ce": 0.28011290502066566}, {"step": 174, "kl": 0.2921295801798503, "ce": 0.29512318411312066}, {"step": 175, "kl": 0.2951295724343994, "ce": 0.2677875463172723}, {"step": 176, "kl": 0.3169216995165968, "ce": 0.25682797342332486}, {"step": 177, "kl": 0.32649208146211034, "ce": 0.29779341683876914}, {"step": 178, "kl": 0.2820210796560525, "ce": 0.2886331244418705}, {"step": 179, "kl": 0.2657905184275697, "ce": 0.2386132679439593}, {"step": 180, "kl": 0.2873608437234529, "ce": 0.27393274302223697}, {"step": 181, "kl": 0.3018195515838117, "ce": 0.2712038231273191}, {"step": 182, "kl": 0.2927554637756881, "ce": 0.2687163585793372}, {"step": 183, "kl": 0.30116921487031395, "ce": 0.26122386141721504}, {"step": 184, "kl": 0.30282302201228023, "ce": 0.26630674311531954}, {"step": 185, "kl": 0.3193109912508515, "ce": 0.2849421970934847}, {"step": 186, "kl": 0.29738025029500326, "ce": 0.2603583429656844}, {"step": 187, "kl": 0.32023847988203624, "ce": 0.2475024000203087}, {"step": 188, "kl": 0.3033072596153443, "ce": 0.22128522800147796}, {"step": 189, "kl": 0.30344478159390087, "ce": 0.27769154228458337}, {"step": 190, "kl": 0.3175854776060585, "ce": 0.2972220901471898}, {"step": 191, "kl": 0.34753186829430915, "ce": 0.2755166409541973}, {"step": 192, "kl": 0.2830043669131949, "ce": 0.2691689606343419}, {"step": 193, "kl": 0.30865069466275896, "ce": 0.3066725714121499}, {"step": 194, "kl": 0.3131493031264304, "ce": 0.3412766153871996}, {"step": 195, "kl": 0.3443244250956077, "ce": 0.2913675824303533}, {"step": 196, "kl": 0.36721523257649286, "ce": 0.24686869939439882}, {"step": 197, "kl": 0.3011919912794551, "ce": 0.29257089065365055}, {"step": 198, "kl": 0.2818981315976098, "ce": 0.2966180044047128}, {"step": 199, "kl": 0.31477984640906725, "ce": 0.2600316005727946}, {"step": 200, "kl": 0.30118754582284474, "ce": 0.2695196330286595}, {"step": 201, "kl": 0.31328253155549035, "ce": 0.2937486632290164}, {"step": 202, "kl": 0.30168695454312755, "ce": 0.26578938448977096}, {"step": 203, "kl": 0.3131989629104519, "ce": 0.27885826307736583}, {"step": 204, "kl": 0.34101440174022274, "ce": 0.31291388874593007}, {"step": 205, "kl": 0.33792564337202113, "ce": 0.23717105101947175}, {"step": 206, "kl": 0.32498719065387616, "ce": 0.2763175678666671}, {"step": 207, "kl": 0.2866252264561375, "ce": 0.2915400556362273}, {"step": 208, "kl": 0.30009286652519096, "ce": 0.26918200736851294}, {"step": 209, "kl": 0.3075041153106183, "ce": 0.3415473802932906}, {"step": 210, "kl": 0.286428584808877, "ce": 0.2498991394145496}, {"step": 211, "kl": 0.32227900250706054, "ce": 0.23869330138177897}, {"step": 212, "kl": 0.3059074010711162, "ce": 0.28319639828115856}, {"step": 213, "kl": 0.2902143829679413, "ce": 0.3004135545164983}, {"step": 214, "kl": 0.32521263916518905, "ce": 0.2854270823321708}, {"step": 215, "kl": 0.3057799689839374, "ce": 0.253909464772667}, {"step": 216, "kl": 0.3095102363973736, "ce": 0.28183846458604067}, {"step": 217, "kl": 0.2591995003946339, "ce": 0.24100823250856895}, {"step": 218, "kl": 0.31184967005411046, "ce": 0.27383498064110806}, {"step": 219, "kl": 0.31825150992916124, "ce": 0.3066418060046705}, {"step": 220, "kl": 0.3048332785563765, "ce": 0.29413938762204916}, {"step": 221, "kl": 0.3028080393377632, "ce": 0.2620394377268822}, {"step": 222, "kl": 0.33591196562055126, "ce": 0.3076885211589879}, {"step": 223, "kl": 0.2900545828948401, "ce": 0.2854565547687621}, {"step": 224, "kl": 0.3475887961952932, "ce": 0.29462890858356794}, {"step": 225, "kl": 0.2972496250477582, "ce": 0.2311605526636719}, {"step": 226, "kl": 0.32629619159764944, "ce": 0.26184101015625993}, {"step": 227, "kl": 0.3402297870489329, "ce": 0.28508468455747316}, {"step": 228, "kl": 0.3539014938000409, "ce": 0.2566972541163981}, {"step": 229, "kl": 0.2862172081618233, "ce": 0.2566122677521764}, {"step": 230, "kl": 0.27862291307282433, "ce": 0.2238588969490745}, {"step": 231, "kl": 0.3208342741176345, "ce": 0.24443240838089184}, {"step": 232, "kl": 0.29270622531681134, "ce": 0.2772552134621484}, {"step": 233, "kl": 0.32367348623896985, "ce": 0.311637125997377}, {"step": 234, "kl": 0.3160635682820395, "ce": 0.3242915808269802}, {"step": 235, "kl": 0.35802868983154895, "ce": 0.2489038208506605}, {"step": 236, "kl": 0.2869669303642577, "ce": 0.36767825742210414}, {"step": 237, "kl": 0.3009775408111602, "ce": 0.24638948920601852}, {"step": 238, "kl": 0.30482563111338656, "ce": 0.2532398789233453}, {"step": 239, "kl": 0.31899781184052317, "ce": 0.2760258849398548}, {"step": 240, "kl": 0.3415251850645739, "ce": 0.28966620491662054}, {"step": 241, "kl": 0.3501769436678387, "ce": 0.2655704537932154}, {"step": 242, "kl": 0.30204988166217833, "ce": 0.27280158956300116}, {"step": 243, "kl": 0.2933035505716322, "ce": 0.23797839833588275}, {"step": 244, "kl": 0.3005427463613109, "ce": 0.2476669202629314}, {"step": 245, "kl": 0.2881520168654204, "ce": 0.2637706152266926}, {"step": 246, "kl": 0.362660346117601, "ce": 0.2373534915918281}, {"step": 247, "kl": 0.33487587767844385, "ce": 0.2632906508607615}, {"step": 248, "kl": 0.31002362163126973, "ce": 0.2684381661426267}, {"step": 249, "kl": 0.34115254089583064, "ce": 0.22040954602704085}, {"step": 250, "kl": 0.33724531240147254, "ce": 0.2554518932967741}, {"step": 251, "kl": 0.3437929888003904, "ce": 0.2563994499189513}, {"step": 252, "kl": 0.3225603486985042, "ce": 0.2921106611210904}, {"step": 253, "kl": 0.26992886038416497, "ce": 0.22371385373549088}, {"step": 254, "kl": 0.3192788359336522, "ce": 0.2271716772432422}, {"step": 255, "kl": 0.2622548970297264, "ce": 0.22434953825215093}, {"step": 256, "kl": 0.3320465869019215, "ce": 0.33792726498966835}, {"step": 257, "kl": 0.302218939209882, "ce": 0.2603516098858994}, {"step": 258, "kl": 0.35753318290263336, "ce": 0.2610930360978791}, {"step": 259, "kl": 0.2857452512804959, "ce": 0.25948601875718513}, {"step": 260, "kl": 0.31815380143270966, "ce": 0.2516596903338387}, {"step": 261, "kl": 0.29540997345788916, "ce": 0.2716741447482882}, {"step": 262, "kl": 0.31765172137261727, "ce": 0.244538039000312}, {"step": 263, "kl": 0.33758167350774454, "ce": 0.32307017819871303}, {"step": 264, "kl": 0.31398667430270044, "ce": 0.27404360317481624}, {"step": 265, "kl": 0.2988706010173471, "ce": 0.24332410998951795}, {"step": 266, "kl": 0.30026318532903057, "ce": 0.2688327482633488}, {"step": 267, "kl": 0.29938438654261146, "ce": 0.23098742486972293}, {"step": 268, "kl": 0.3144132400241742, "ce": 0.24924896442853633}, {"step": 269, "kl": 0.33831143109594297, "ce": 0.3071590494146524}, {"step": 270, "kl": 0.32065262234313446, "ce": 0.2794520936926456}, {"step": 271, "kl": 0.2972684654853467, "ce": 0.29554378971888984}, {"step": 272, "kl": 0.3187735276490298, "ce": 0.2739313010436144}, {"step": 273, "kl": 0.291421106905105, "ce": 0.25104953920297024}, {"step": 274, "kl": 0.3477494577952039, "ce": 0.2780503493088942}, {"step": 275, "kl": 0.3111444889172883, "ce": 0.31359473351665823}, {"step": 276, "kl": 0.30503225494464203, "ce": 0.2787765835320344}, {"step": 277, "kl": 0.3308333775234897, "ce": 0.24819075851291128}, {"step": 278, "kl": 0.30525842551996685, "ce": 0.2701571778130551}, {"step": 279, "kl": 0.30154654683921034, "ce": 0.2495963116472604}, {"step": 280, "kl": 0.30379221868711387, "ce": 0.29915636318681077}, {"step": 281, "kl": 0.33013372069221325, "ce": 0.28206655778983103}, {"step": 282, "kl": 0.35276670955709033, "ce": 0.2746992024234081}, {"step": 283, "kl": 0.28270289079748023, "ce": 0.20068988879126295}, {"step": 284, "kl": 0.33985875339070226, "ce": 0.3027452090250904}, {"step": 285, "kl": 0.3515937705702171, "ce": 0.27441208071632867}, {"step": 286, "kl": 0.29456776892345093, "ce": 0.24211628938542032}, {"step": 287, "kl": 0.33333157345507614, "ce": 0.23537084924657026}, {"step": 288, "kl": 0.29189723296365433, "ce": 0.2319579886438753}, {"step": 289, "kl": 0.2785139892623662, "ce": 0.23575544487228187}, {"step": 290, "kl": 0.3185591446412922, "ce": 0.2890693780680864}, {"step": 291, "kl": 0.2816194665661857, "ce": 0.23506530867958567}, {"step": 292, "kl": 0.33767978523411063, "ce": 0.25261624152728057}, {"step": 293, "kl": 0.33783029605671083, "ce": 0.26827950707009673}, {"step": 294, "kl": 0.29624298032086965, "ce": 0.27324779507822006}, {"step": 295, "kl": 0.3207266353640359, "ce": 0.22409039242932852}, {"step": 296, "kl": 0.28698434648135795, "ce": 0.3069591519139932}, {"step": 297, "kl": 0.3038482555833486, "ce": 0.2267445289866085}, {"step": 298, "kl": 0.3581005562981256, "ce": 0.3015094830070257}, {"step": 299, "kl": 0.28439718490105487, "ce": 0.2395782901420129}, {"step": 300, "kl": 0.33365829718925827, "ce": 0.25483875689299207}, {"step": 301, "kl": 0.3122550568351556, "ce": 0.25479505780773315}, {"step": 302, "kl": 0.3069285144512105, "ce": 0.2744701456112766}, {"step": 303, "kl": 0.32287590994841403, "ce": 0.24521645222000116}, {"step": 304, "kl": 0.30060845362759014, "ce": 0.2718077819349773}, {"step": 305, "kl": 0.2884611127047586, "ce": 0.21498968036958557}, {"step": 306, "kl": 0.29691411197720946, "ce": 0.2636521983502516}, {"step": 307, "kl": 0.32347002520209966, "ce": 0.24870436227024745}, {"step": 308, "kl": 0.3094589261781602, "ce": 0.2744360482029256}, {"step": 309, "kl": 0.31847652604555515, "ce": 0.2399175414286414}, {"step": 310, "kl": 0.3238164267956145, "ce": 0.3017173661592245}, {"step": 311, "kl": 0.31937747195717153, "ce": 0.281587554831814}, {"step": 312, "kl": 0.36069034945058376, "ce": 0.28245115827790435}, {"step": 313, "kl": 0.2849777671670786, "ce": 0.23740514136658764}, {"step": 314, "kl": 0.30124212779498794, "ce": 0.24487939102032533}, {"step": 315, "kl": 0.26227245711065256, "ce": 0.2698736045471121}, {"step": 316, "kl": 0.28227491431078744, "ce": 0.2696102641751175}, {"step": 317, "kl": 0.30615898137361786, "ce": 0.25816044396333315}, {"step": 318, "kl": 0.3118905615330701, "ce": 0.26668910672946006}, {"step": 319, "kl": 0.3321970144973558, "ce": 0.30871004547793524}, {"step": 320, "kl": 0.3065274428746498, "ce": 0.2514800680998056}, {"step": 321, "kl": 0.2956649703324855, "ce": 0.23553765541925398}, {"step": 322, "kl": 0.3192818118490238, "ce": 0.260982362652122}, {"step": 323, "kl": 0.28937447072868866, "ce": 0.25244236922129537}, {"step": 324, "kl": 0.2919829479252344, "ce": 0.23959102323749698}, {"step": 325, "kl": 0.3057937955647838, "ce": 0.2825053348336169}, {"step": 326, "kl": 0.2795317099497448, "ce": 0.21663965379357875}, {"step": 327, "kl": 0.2895892631067567, "ce": 0.22997641450420944}, {"step": 328, "kl": 0.3251481223493986, "ce": 0.29807701603142434}, {"step": 329, "kl": 0.3237866188903148, "ce": 0.2872362772623697}, {"step": 330, "kl": 0.2837335422365876, "ce": 0.2327036645540476}, {"step": 331, "kl": 0.3353956738995454, "ce": 0.31118677531793437}, {"step": 332, "kl": 0.33003723601319757, "ce": 0.22955804834309823}, {"step": 333, "kl": 0.30576346111857494, "ce": 0.27059504009393404}, {"step": 334, "kl": 0.3240903424627987, "ce": 0.2699580597817771}, {"step": 335, "kl": 0.3153937713923903, "ce": 0.2583254739059599}, {"step": 336, "kl": 0.3219122808223317, "ce": 0.26940233494269183}, {"step": 337, "kl": 0.31354539512339463, "ce": 0.2456567628200322}, {"step": 338, "kl": 0.26992320035664696, "ce": 0.21828990845654972}, {"step": 339, "kl": 0.32838570435276243, "ce": 0.258973238960145}, {"step": 340, "kl": 0.2725873294642489, "ce": 0.23736889843230552}, {"step": 341, "kl": 0.34262349498927713, "ce": 0.29272960688936356}, {"step": 342, "kl": 0.27184917890688937, "ce": 0.2302783918635891}, {"step": 343, "kl": 0.31643564596631396, "ce": 0.27558649079002323}, {"step": 344, "kl": 0.28038314778508316, "ce": 0.31855315110932425}, {"step": 345, "kl": 0.30176104247903224, "ce": 0.2668436193047749}, {"step": 346, "kl": 0.2911359554131928, "ce": 0.19302503348324546}, {"step": 347, "kl": 0.2782843909002576, "ce": 0.233075767546516}, {"step": 348, "kl": 0.3503448255571391, "ce": 0.3213511535165569}, {"step": 349, "kl": 0.2788193476584475, "ce": 0.2594120969690955}, {"step": 350, "kl": 0.32948148666141946, "ce": 0.24823863453072292}, {"step": 351, "kl": 0.29672018266890826, "ce": 0.2665632790499753}, {"step": 352, "kl": 0.3139220466886502, "ce": 0.30748942010145286}, {"step": 353, "kl": 0.32904848062144865, "ce": 0.25504063922091924}, {"step": 354, "kl": 0.33933843199189734, "ce": 0.2581430568992895}, {"step": 355, "kl": 0.3147410780967404, "ce": 0.28768388986208476}, {"step": 356, "kl": 0.2868791163213546, "ce": 0.229968421277802}, {"step": 357, "kl": 0.292275932676137, "ce": 0.2813200733798915}, {"step": 358, "kl": 0.34054035532394517, "ce": 0.23676801021937763}, {"step": 359, "kl": 0.2957321309028788, "ce": 0.3038791970769933}, {"step": 360, "kl": 0.2639661110931274, "ce": 0.2520921061034224}, {"step": 361, "kl": 0.2651712741727143, "ce": 0.31171319107124706}, {"step": 362, "kl": 0.3456150510156558, "ce": 0.3545433283755958}, {"step": 363, "kl": 0.29925513406155574, "ce": 0.3185061535062458}, {"step": 364, "kl": 0.3229427319646969, "ce": 0.3194054750550802}, {"step": 365, "kl": 0.3409455731861224, "ce": 0.2683566377072515}, {"step": 366, "kl": 0.28084512714193055, "ce": 0.28740069805726326}, {"step": 367, "kl": 0.3342492712734927, "ce": 0.2493885490358096}, {"step": 368, "kl": 0.32313719543649183, "ce": 0.2735787414742011}, {"step": 369, "kl": 0.2547300024088781, "ce": 0.2505931938659567}, {"step": 370, "kl": 0.28973951239487455, "ce": 0.2427267447620306}, {"step": 371, "kl": 0.31837799262624783, "ce": 0.25085563424968954}, {"step": 372, "kl": 0.29784022528108894, "ce": 0.23268153962024604}, {"step": 373, "kl": 0.2838127425360089, "ce": 0.23815680001684061}, {"step": 374, "kl": 0.3383530261846117, "ce": 0.35417231158119344}, {"step": 375, "kl": 0.2854263504257974, "ce": 0.28847033704575376}, {"step": 376, "kl": 0.266439076598364, "ce": 0.26323433356588083}, {"step": 377, "kl": 0.2917232301882748, "ce": 0.20098643216277623}, {"step": 378, "kl": 0.30664646267782525, "ce": 0.2685160607885395}, {"step": 379, "kl": 0.3161116453282689, "ce": 0.2497745201034894}, {"step": 380, "kl": 0.31229309311967945, "ce": 0.2584559484798476}, {"step": 381, "kl": 0.3621106101992272, "ce": 0.27755779519897245}, {"step": 382, "kl": 0.2703136398990282, "ce": 0.233434882233205}, {"step": 383, "kl": 0.3173077272985097, "ce": 0.255353648462804}, {"step": 384, "kl": 0.2907571148193028, "ce": 0.2589312070895405}, {"step": 385, "kl": 0.31427609108603377, "ce": 0.26475480282172204}, {"step": 386, "kl": 0.30885483844557593, "ce": 0.3094319344706679}, {"step": 387, "kl": 0.32453506481527633, "ce": 0.28329112308566723}, {"step": 388, "kl": 0.34485175285078556, "ce": 0.2332523602634402}, {"step": 389, "kl": 0.33269190326813736, "ce": 0.29164112041622997}, {"step": 390, "kl": 0.32488569679673396, "ce": 0.2750097977890898}, {"step": 391, "kl": 0.33671932384434444, "ce": 0.2244720566721641}, {"step": 392, "kl": 0.33624056931978213, "ce": 0.24492501858099996}, {"step": 393, "kl": 0.33869759576556724, "ce": 0.25482184889964404}, {"step": 394, "kl": 0.327716500690665, "ce": 0.2712586648383383}, {"step": 395, "kl": 0.3302834527685889, "ce": 0.30158345459775615}, {"step": 396, "kl": 0.33138723562302974, "ce": 0.2759880078301177}, {"step": 397, "kl": 0.31054356794196014, "ce": 0.24657014185128942}, {"step": 398, "kl": 0.33432874075974095, "ce": 0.18646222179075642}, {"step": 399, "kl": 0.3269026714872712, "ce": 0.24300411908455144}, {"step": 400, "kl": 0.3159511497234774, "ce": 0.27564935866203016}, {"step": 401, "kl": 0.27990269285385405, "ce": 0.27600659757113893}, {"step": 402, "kl": 0.2960144961592792, "ce": 0.2774163713027673}, {"step": 403, "kl": 0.3262208789534628, "ce": 0.2626519085922919}, {"step": 404, "kl": 0.29322895459862497, "ce": 0.30334336111666443}, {"step": 405, "kl": 0.3194949541514233, "ce": 0.3057770837621141}, {"step": 406, "kl": 0.279417981606431, "ce": 0.19450667363011812}, {"step": 407, "kl": 0.3316085378515265, "ce": 0.2722523474534325}, {"step": 408, "kl": 0.2864971341770249, "ce": 0.3046861395042807}, {"step": 409, "kl": 0.2873930927865513, "ce": 0.2476231588555902}, {"step": 410, "kl": 0.32705737577716343, "ce": 0.2920019440583999}, {"step": 411, "kl": 0.3447646855086133, "ce": 0.25645575690362243}, {"step": 412, "kl": 0.3021269042816827, "ce": 0.29796349177570464}, {"step": 413, "kl": 0.3042981110740966, "ce": 0.2144782782112946}, {"step": 414, "kl": 0.300004536101333, "ce": 0.2821249078425052}, {"step": 415, "kl": 0.2942713329624822, "ce": 0.28075635696265305}, {"step": 416, "kl": 0.3432517122364246, "ce": 0.2503211640085055}, {"step": 417, "kl": 0.3157134901033161, "ce": 0.2244301237197077}, {"step": 418, "kl": 0.2881940782272334, "ce": 0.2370215521084042}, {"step": 419, "kl": 0.295087224604597, "ce": 0.2188562522044249}, {"step": 420, "kl": 0.29030284715626475, "ce": 0.23800891479315786}, {"step": 421, "kl": 0.37309204557011183, "ce": 0.25096390068123714}, {"step": 422, "kl": 0.27158293107031156, "ce": 0.2139567849021288}, {"step": 423, "kl": 0.29398405503777447, "ce": 0.2710717635043832}, {"step": 424, "kl": 0.3169610300167144, "ce": 0.2722361833296694}, {"step": 425, "kl": 0.3327381404500444, "ce": 0.29002293143673935}, {"step": 426, "kl": 0.2987326788531147, "ce": 0.2656676711501135}, {"step": 427, "kl": 0.30276280366690195, "ce": 0.25919181357844356}, {"step": 428, "kl": 0.28806636560312976, "ce": 0.25237705174690156}, {"step": 429, "kl": 0.29188714161710216, "ce": 0.3037218998964645}, {"step": 430, "kl": 0.30130154804543613, "ce": 0.304429471248577}, {"step": 431, "kl": 0.2687324776416833, "ce": 0.2644397239991564}, {"step": 432, "kl": 0.2951412169356582, "ce": 0.23424894943719374}, {"step": 433, "kl": 0.3162788772645967, "ce": 0.25994315737156287}, {"step": 434, "kl": 0.28864502623769916, "ce": 0.2156360641885413}, {"step": 435, "kl": 0.28820741565070146, "ce": 0.27746565568120257}, {"step": 436, "kl": 0.3177812224109784, "ce": 0.2818901618598986}, {"step": 437, "kl": 0.32479899375987936, "ce": 0.19346489556913204}, {"step": 438, "kl": 0.3081812597471235, "ce": 0.2660525248402349}, {"step": 439, "kl": 0.28149961330567386, "ce": 0.2217393166792739}, {"step": 440, "kl": 0.3113202487721163, "ce": 0.28419109064479703}, {"step": 441, "kl": 0.2464387914061207, "ce": 0.29218951010505456}, {"step": 442, "kl": 0.30583722954800574, "ce": 0.27502332452862405}, {"step": 443, "kl": 0.32104415583596696, "ce": 0.3181485620255293}, {"step": 444, "kl": 0.3205940967893556, "ce": 0.2542944447747592}, {"step": 445, "kl": 0.34316745989271585, "ce": 0.22151478719793377}, {"step": 446, "kl": 0.34363999279092355, "ce": 0.307541220044724}, {"step": 447, "kl": 0.312424010120967, "ce": 0.2792134362709345}, {"step": 448, "kl": 0.3219687142892507, "ce": 0.2603959778080816}, {"step": 449, "kl": 0.2996007048772463, "ce": 0.25500580013705104}, {"step": 450, "kl": 0.282035112269484, "ce": 0.2482990751757494}, {"step": 451, "kl": 0.30089406010788755, "ce": 0.2720347361131148}, {"step": 452, "kl": 0.2931193740947185, "ce": 0.28499017262127246}, {"step": 453, "kl": 0.29017715166633795, "ce": 0.2859937858348818}, {"step": 454, "kl": 0.2885143131404728, "ce": 0.25338290174437234}, {"step": 455, "kl": 0.3235080637073723, "ce": 0.23087344863111062}, {"step": 456, "kl": 0.32654663695514996, "ce": 0.299317659469905}, {"step": 457, "kl": 0.3436057277958507, "ce": 0.2620629088779093}, {"step": 458, "kl": 0.2762967352802189, "ce": 0.20961086678589252}, {"step": 459, "kl": 0.3450454187496109, "ce": 0.23712476303702906}, {"step": 460, "kl": 0.2937707239228488, "ce": 0.26117948959668186}, {"step": 461, "kl": 0.30932687642622975, "ce": 0.21692690238350856}, {"step": 462, "kl": 0.30914040259551534, "ce": 0.21229980749189573}, {"step": 463, "kl": 0.3525974867944951, "ce": 0.19669234996595783}, {"step": 464, "kl": 0.2817031207070073, "ce": 0.18079103818903838}, {"step": 465, "kl": 0.2844112776859694, "ce": 0.1685262779467806}, {"step": 466, "kl": 0.24501938842281987, "ce": 0.17744520383166215}, {"step": 467, "kl": 0.3306825727519423, "ce": 0.16786422043687343}, {"step": 468, "kl": 0.30886070361606016, "ce": 0.14701523469304528}, {"step": 469, "kl": 0.3089280711085495, "ce": 0.16600768801606733}, {"step": 470, "kl": 0.33776367673801916, "ce": 0.1578623395872319}, {"step": 471, "kl": 0.3446225533514964, "ce": 0.1747556176906608}, {"step": 472, "kl": 0.2889634013436817, "ce": 0.16544184820288527}, {"step": 473, "kl": 0.30865883992589993, "ce": 0.2088643762936629}, {"step": 474, "kl": 0.34883385940701245, "ce": 0.14676870313349932}, {"step": 475, "kl": 0.3486955179894734, "ce": 0.15205801752426687}, {"step": 476, "kl": 0.34784378315479203, "ce": 0.18324465772858667}, {"step": 477, "kl": 0.3844819216748069, "ce": 0.1875099451838193}, {"step": 478, "kl": 0.36242880444870207, "ce": 0.19785974652853888}, {"step": 479, "kl": 0.32285517939814823, "ce": 0.18364610838611112}, {"step": 480, "kl": 0.31522561656780257, "ce": 0.14559765455923673}, {"step": 481, "kl": 0.3171698033065008, "ce": 0.1703760321629829}, {"step": 482, "kl": 0.37604524731636046, "ce": 0.2012654735691012}, {"step": 483, "kl": 0.37238498653321106, "ce": 0.15913255757097347}, {"step": 484, "kl": 0.33772562530754224, "ce": 0.12099609035412706}, {"step": 485, "kl": 0.3746542273162063, "ce": 0.17026038156141726}, {"step": 486, "kl": 0.35129886109345915, "ce": 0.22033358159403843}, {"step": 487, "kl": 0.3584590545270134, "ce": 0.16928958333687452}, {"step": 488, "kl": 0.3648403638114873, "ce": 0.21161158699906005}, {"step": 489, "kl": 0.2793871902730424, "ce": 0.12349414286146318}, {"step": 490, "kl": 0.3801482748220536, "ce": 0.18125323742484123}, {"step": 491, "kl": 0.36710410631574697, "ce": 0.1821510312290733}, {"step": 492, "kl": 0.3271611829126556, "ce": 0.20722109268309402}, {"step": 493, "kl": 0.34859225506423624, "ce": 0.19075367789753875}, {"step": 494, "kl": 0.33632084393011635, "ce": 0.1825630668884012}, {"step": 495, "kl": 0.361530013738894, "ce": 0.1438286474060314}, {"step": 496, "kl": 0.31470086162292993, "ce": 0.17779162426240758}, {"step": 497, "kl": 0.323838240126116, "ce": 0.17549872605227743}, {"step": 498, "kl": 0.285802613861896, "ce": 0.1465717368311696}, {"step": 499, "kl": 0.34617308836000565, "ce": 0.13995724611721355}, {"step": 500, "kl": 0.34857259904666493, "ce": 0.14453855462616672}, {"step": 501, "kl": 0.4043259516195139, "ce": 0.15892076225920093}, {"step": 502, "kl": 0.32964353620528314, "ce": 0.17750797233525972}, {"step": 503, "kl": 0.4077754750253268, "ce": 0.1703202661635062}, {"step": 504, "kl": 0.3727613127292022, "ce": 0.17211571696054312}, {"step": 505, "kl": 0.35565305541603015, "ce": 0.18764163821688987}, {"step": 506, "kl": 0.3963596747652813, "ce": 0.16122512976139533}, {"step": 507, "kl": 0.2926544290444992, "ce": 0.15068091253261234}, {"step": 508, "kl": 0.31415775951440783, "ce": 0.1643043563299971}, {"step": 509, "kl": 0.3802618990315676, "ce": 0.2110980409782242}, {"step": 510, "kl": 0.35490059229600524, "ce": 0.18166147855107384}, {"step": 511, "kl": 0.35164457155805423, "ce": 0.17286852380388118}, {"step": 512, "kl": 0.30558589190161073, "ce": 0.14881462740520926}, {"step": 513, "kl": 0.36755236352273357, "ce": 0.1820247940504019}, {"step": 514, "kl": 0.40777729933443807, "ce": 0.17389854920802122}, {"step": 515, "kl": 0.32078250534758124, "ce": 0.1522517084354278}, {"step": 516, "kl": 0.33528764141560374, "ce": 0.17170367091733402}, {"step": 517, "kl": 0.3232809783081594, "ce": 0.1603321196084999}, {"step": 518, "kl": 0.34039250913239366, "ce": 0.15844149698108775}, {"step": 519, "kl": 0.4371648034423183, "ce": 0.1780884721860135}, {"step": 520, "kl": 0.3616095125070399, "ce": 0.17384461217303265}, {"step": 521, "kl": 0.3859255785443685, "ce": 0.16577777293325882}, {"step": 522, "kl": 0.32578343003879684, "ce": 0.17342143773201868}, {"step": 523, "kl": 0.31949810743088375, "ce": 0.18293355791248098}, {"step": 524, "kl": 0.29365154737892923, "ce": 0.14504782708534159}, {"step": 525, "kl": 0.29620391099267235, "ce": 0.16870547090284027}, {"step": 526, "kl": 0.38493104192732724, "ce": 0.1374500628665542}, {"step": 527, "kl": 0.3639783524374926, "ce": 0.14404353531856745}, {"step": 528, "kl": 0.35257901463654695, "ce": 0.1754545510605263}, {"step": 529, "kl": 0.3387556585341849, "ce": 0.1423251215275635}, {"step": 530, "kl": 0.36753295334683705, "ce": 0.158851259590132}, {"step": 531, "kl": 0.32470745165313464, "ce": 0.15940474224470658}, {"step": 532, "kl": 0.36364331724548593, "ce": 0.160577261893192}, {"step": 533, "kl": 0.34704036515741943, "ce": 0.1807807281451054}, {"step": 534, "kl": 0.29459891822241197, "ce": 0.11835863910823713}, {"step": 535, "kl": 0.39909429637333066, "ce": 0.1841539355997745}, {"step": 536, "kl": 0.37615168652251163, "ce": 0.15801474710088878}, {"step": 537, "kl": 0.37969060957254475, "ce": 0.16273239533895673}, {"step": 538, "kl": 0.3217287330286081, "ce": 0.14559944711935027}, {"step": 539, "kl": 0.38122397956967513, "ce": 0.19919408325332083}, {"step": 540, "kl": 0.3308384299704827, "ce": 0.17561365066365128}, {"step": 541, "kl": 0.41528054394768277, "ce": 0.1494143103374745}, {"step": 542, "kl": 0.3493398588767842, "ce": 0.18631465596963367}, {"step": 543, "kl": 0.34468859895793497, "ce": 0.1834253989223552}, {"step": 544, "kl": 0.3264858079840449, "ce": 0.19554030739703}, {"step": 545, "kl": 0.40351329682261866, "ce": 0.17658166560567318}, {"step": 546, "kl": 0.32957831698054013, "ce": 0.1289744230632302}, {"step": 547, "kl": 0.36192022117846606, "ce": 0.166123294683941}, {"step": 548, "kl": 0.33580765403923274, "ce": 0.1485613107035154}, {"step": 549, "kl": 0.37923885797804197, "ce": 0.15801510311476713}, {"step": 550, "kl": 0.39887364894906746, "ce": 0.18708451645952412}, {"step": 551, "kl": 0.35045998686465285, "ce": 0.15752082542364196}, {"step": 552, "kl": 0.35595772861920405, "ce": 0.17435148133512102}, {"step": 553, "kl": 0.32959684686537544, "ce": 0.18332686335018153}, {"step": 554, "kl": 0.31710998607533325, "ce": 0.12370291501509761}, {"step": 555, "kl": 0.35222129248635886, "ce": 0.17076972899098286}, {"step": 556, "kl": 0.32045484676373337, "ce": 0.17266308282443324}, {"step": 557, "kl": 0.3071383587915929, "ce": 0.18161303982202082}, {"step": 558, "kl": 0.3374197043862638, "ce": 0.13902751886203632}, {"step": 559, "kl": 0.34360918608442986, "ce": 0.17895833524526972}, {"step": 560, "kl": 0.37304536029885826, "ce": 0.1930505457058759}, {"step": 561, "kl": 0.34469471715708244, "ce": 0.16870950054000006}, {"step": 562, "kl": 0.3149148723775834, "ce": 0.18426930777480027}, {"step": 563, "kl": 0.37620563329926954, "ce": 0.15566636414531965}, {"step": 564, "kl": 0.3581844019372844, "ce": 0.20001039038583843}, {"step": 565, "kl": 0.38858595981750266, "ce": 0.17315850639078403}, {"step": 566, "kl": 0.3378269654215256, "ce": 0.19487747378420078}, {"step": 567, "kl": 0.3433050925793778, "ce": 0.1740462908220774}, {"step": 568, "kl": 0.3210001455336934, "ce": 0.16776983226270983}, {"step": 569, "kl": 0.3513268314208416, "ce": 0.16303716668901627}, {"step": 570, "kl": 0.27910023087864766, "ce": 0.1466279888471929}, {"step": 571, "kl": 0.3361530295627257, "ce": 0.16836061995103113}, {"step": 572, "kl": 0.37057844342902657, "ce": 0.16206711856455253}, {"step": 573, "kl": 0.29338434514965067, "ce": 0.16271096327058152}, {"step": 574, "kl": 0.3504529459723111, "ce": 0.17276513606796678}, {"step": 575, "kl": 0.37490286157349756, "ce": 0.20732620262364834}, {"step": 576, "kl": 0.3437648064197798, "ce": 0.15915205731288384}, {"step": 577, "kl": 0.3579057862967332, "ce": 0.1793337267291362}, {"step": 578, "kl": 0.38287751278394666, "ce": 0.16705766467148989}, {"step": 579, "kl": 0.31309645323491386, "ce": 0.1341349401136888}, {"step": 580, "kl": 0.33904387084257054, "ce": 0.20512394503967982}, {"step": 581, "kl": 0.336492013626143, "ce": 0.16888517212757867}, {"step": 582, "kl": 0.348365990485837, "ce": 0.1898911777879826}, {"step": 583, "kl": 0.3619145924698481, "ce": 0.18581451820837788}, {"step": 584, "kl": 0.36174143490858873, "ce": 0.15254297267863687}, {"step": 585, "kl": 0.3254180743734544, "ce": 0.16920810886450985}, {"step": 586, "kl": 0.3054984197155829, "ce": 0.13645100616937994}, {"step": 587, "kl": 0.383765461301289, "ce": 0.2050208898184383}, {"step": 588, "kl": 0.3475536991893589, "ce": 0.15171388566920752}, {"step": 589, "kl": 0.39346517239053125, "ce": 0.14783054894417813}, {"step": 590, "kl": 0.3762118366011592, "ce": 0.19378782477103204}, {"step": 591, "kl": 0.3191536234583039, "ce": 0.12985112090104148}, {"step": 592, "kl": 0.3408476628096221, "ce": 0.1474669270812406}, {"step": 593, "kl": 0.3361534041153905, "ce": 0.151369174978293}, {"step": 594, "kl": 0.336816743863576, "ce": 0.1924391515997072}, {"step": 595, "kl": 0.3490434124458969, "ce": 0.1647782959056569}, {"step": 596, "kl": 0.33342265553364764, "ce": 0.15463919073404642}, {"step": 597, "kl": 0.3525416943587992, "ce": 0.18145812508291143}, {"step": 598, "kl": 0.36039395711338235, "ce": 0.14973099972750686}, {"step": 599, "kl": 0.31847417436583647, "ce": 0.2004515203845106}, {"step": 600, "kl": 0.3671355269831852, "ce": 0.13815722924581966}, {"step": 601, "kl": 0.3900892459706723, "ce": 0.16377914834814464}, {"step": 602, "kl": 0.3188346926830001, "ce": 0.15492846761990414}, {"step": 603, "kl": 0.3395094096927102, "ce": 0.16822787180789925}, {"step": 604, "kl": 0.3744683448136654, "ce": 0.18581331449489655}, {"step": 605, "kl": 0.356304345498344, "ce": 0.17969544098209586}, {"step": 606, "kl": 0.3510948981487363, "ce": 0.18337131215861616}, {"step": 607, "kl": 0.3331876405783559, "ce": 0.1458339745081321}, {"step": 608, "kl": 0.3374995683171661, "ce": 0.18500200367129055}, {"step": 609, "kl": 0.30384284140512097, "ce": 0.15389597193975335}, {"step": 610, "kl": 0.37277082446563903, "ce": 0.14671967838179098}, {"step": 611, "kl": 0.32824739384808616, "ce": 0.1811164432524367}, {"step": 612, "kl": 0.34596538373300767, "ce": 0.175252258825264}, {"step": 613, "kl": 0.3415747715509804, "ce": 0.16397556107619712}, {"step": 614, "kl": 0.35285669328350333, "ce": 0.13719843040213808}, {"step": 615, "kl": 0.3493924068068811, "ce": 0.2195555322285338}, {"step": 616, "kl": 0.3356513509787699, "ce": 0.1838984055388888}, {"step": 617, "kl": 0.3282611287664557, "ce": 0.16810504860536185}, {"step": 618, "kl": 0.28082647512365805, "ce": 0.13771155919784156}, {"step": 619, "kl": 0.2990089393945082, "ce": 0.1561844028703224}, {"step": 620, "kl": 0.3099194992377136, "ce": 0.15469592432371107}, {"step": 621, "kl": 0.330235568210806, "ce": 0.1765002896034554}, {"step": 622, "kl": 0.34702089699666394, "ce": 0.1838404547851256}, {"step": 623, "kl": 0.4301954852695347, "ce": 0.21069277947449822}, {"step": 624, "kl": 0.4042990740463879, "ce": 0.16815758881028334}, {"step": 625, "kl": 0.3109831536245919, "ce": 0.13682887236671668}, {"step": 626, "kl": 0.32303038496166514, "ce": 0.1552737660173365}, {"step": 627, "kl": 0.36769141804568495, "ce": 0.16980462042760808}, {"step": 628, "kl": 0.4244630391974199, "ce": 0.17996640949662357}, {"step": 629, "kl": 0.3527636747810349, "ce": 0.185193983353517}, {"step": 630, "kl": 0.36050600174588754, "ce": 0.14660072994425477}, {"step": 631, "kl": 0.34359177463172536, "ce": 0.17277556241715758}, {"step": 632, "kl": 0.38881558933300997, "ce": 0.16461673024023032}, {"step": 633, "kl": 0.3943896231411281, "ce": 0.19255806062984418}, {"step": 634, "kl": 0.36817426312694235, "ce": 0.12498991821739755}, {"step": 635, "kl": 0.3276051270785665, "ce": 0.14549253142193475}, {"step": 636, "kl": 0.3661452837033286, "ce": 0.17825936877966211}, {"step": 637, "kl": 0.39330069648149113, "ce": 0.18262104742249047}, {"step": 638, "kl": 0.33265220216442265, "ce": 0.1438677579169547}, {"step": 639, "kl": 0.31783510812785076, "ce": 0.17877849487657868}, {"step": 640, "kl": 0.3153967888862194, "ce": 0.18166226479077432}, {"step": 641, "kl": 0.35161198865647286, "ce": 0.15309639835664313}, {"step": 642, "kl": 0.33321937723974493, "ce": 0.1709841054680141}, {"step": 643, "kl": 0.35046871153425035, "ce": 0.15234416704240294}, {"step": 644, "kl": 0.3996505937347079, "ce": 0.1616956691057471}, {"step": 645, "kl": 0.353040366904947, "ce": 0.17214750926826144}, {"step": 646, "kl": 0.3537100519543061, "ce": 0.14799806483096137}, {"step": 647, "kl": 0.36263505895287906, "ce": 0.15719132130039123}, {"step": 648, "kl": 0.3660180516079048, "ce": 0.15075833265340194}, {"step": 649, "kl": 0.35466058176820425, "ce": 0.1711522160913391}, {"step": 650, "kl": 0.3416868118764922, "ce": 0.15568399265873586}, {"step": 651, "kl": 0.35201598559820935, "ce": 0.17601466243406222}, {"step": 652, "kl": 0.3473320190589628, "ce": 0.14798329706061378}, {"step": 653, "kl": 0.3826540756285032, "ce": 0.15796138182183225}, {"step": 654, "kl": 0.34229042935097814, "ce": 0.156487570136551}, {"step": 655, "kl": 0.36953388515858393, "ce": 0.14331113757547434}, {"step": 656, "kl": 0.33466426733578686, "ce": 0.18607010216087672}, {"step": 657, "kl": 0.34125274067334266, "ce": 0.15231271497687401}, {"step": 658, "kl": 0.3376515403225459, "ce": 0.15058122639788965}, {"step": 659, "kl": 0.3330094679052887, "ce": 0.1355697563067814}, {"step": 660, "kl": 0.3857499847216107, "ce": 0.14053791498326113}, {"step": 661, "kl": 0.3603339811240652, "ce": 0.16636651020050047}, {"step": 662, "kl": 0.3742166990537416, "ce": 0.17978693993999673}, {"step": 663, "kl": 0.33815344878892856, "ce": 0.17444597709746587}, {"step": 664, "kl": 0.3493105216144081, "ce": 0.17795199167635944}, {"step": 665, "kl": 0.35467472080705087, "ce": 0.173511472271136}, {"step": 666, "kl": 0.3713999487875454, "ce": 0.15500153582676962}, {"step": 667, "kl": 0.3025222858959832, "ce": 0.1343593670715285}, {"step": 668, "kl": 0.34711262074147026, "ce": 0.17150583714361287}, {"step": 669, "kl": 0.3945604262001138, "ce": 0.16988518120995372}, {"step": 670, "kl": 0.3415247905973168, "ce": 0.15564021693155974}, {"step": 671, "kl": 0.3339193438840453, "ce": 0.16652386100694816}, {"step": 672, "kl": 0.3427616485847852, "ce": 0.16567092876609807}, {"step": 673, "kl": 0.383313251712011, "ce": 0.21135181150808202}, {"step": 674, "kl": 0.2926430014008528, "ce": 0.115758444301879}, {"step": 675, "kl": 0.33700868715798804, "ce": 0.12416252621789171}, {"step": 676, "kl": 0.33917487314233496, "ce": 0.15312106284596788}, {"step": 677, "kl": 0.3764176331048516, "ce": 0.15757733006631172}, {"step": 678, "kl": 0.31479487852965254, "ce": 0.13062867402157066}, {"step": 679, "kl": 0.3255286395021351, "ce": 0.1597509664308434}, {"step": 680, "kl": 0.37568426642348896, "ce": 0.14857593885166023}, {"step": 681, "kl": 0.3352839165061601, "ce": 0.1679746390327166}, {"step": 682, "kl": 0.3339794356734665, "ce": 0.2031513576638209}, {"step": 683, "kl": 0.37141608350374516, "ce": 0.17723559171291975}, {"step": 684, "kl": 0.34496825172564394, "ce": 0.17892074694215887}, {"step": 685, "kl": 0.3702848717221991, "ce": 0.1623791034798623}, {"step": 686, "kl": 0.39693107116050086, "ce": 0.17960805021707357}, {"step": 687, "kl": 0.3382488970469498, "ce": 0.1883379848637832}, {"step": 688, "kl": 0.3773207821582576, "ce": 0.18477778421168314}, {"step": 689, "kl": 0.3699929695815844, "ce": 0.1920161861954854}, {"step": 690, "kl": 0.3364182365471561, "ce": 0.15793465790631164}, {"step": 691, "kl": 0.3664481816561464, "ce": 0.17375205327384058}, {"step": 692, "kl": 0.35389834472537457, "ce": 0.17041369957384928}, {"step": 693, "kl": 0.3583091595226746, "ce": 0.13905886950843627}, {"step": 694, "kl": 0.29756206018784465, "ce": 0.1466640626257966}, {"step": 695, "kl": 0.315658416964177, "ce": 0.14773557400559345}, {"step": 696, "kl": 0.34809765183782004, "ce": 0.17510227160536107}, {"step": 697, "kl": 0.3536961757617662, "ce": 0.14549072257038173}, {"step": 698, "kl": 0.3796310202407485, "ce": 0.1806335317165188}, {"step": 699, "kl": 0.35136602090648517, "ce": 0.16534307116293948}, {"step": 700, "kl": 0.42955085031609785, "ce": 0.20122768179173559}, {"step": 701, "kl": 0.31941239247243475, "ce": 0.18482168814416566}, {"step": 702, "kl": 0.3478081040186897, "ce": 0.18402208260761735}, {"step": 703, "kl": 0.43633239081963865, "ce": 0.16123961424723224}, {"step": 704, "kl": 0.3410932228531047, "ce": 0.17057003844602112}, {"step": 705, "kl": 0.3521724164796192, "ce": 0.17558943688785644}, {"step": 706, "kl": 0.32243246681946147, "ce": 0.18376198155539375}, {"step": 707, "kl": 0.37661537465017486, "ce": 0.1635016685149964}, {"step": 708, "kl": 0.33147332115341177, "ce": 0.1454415693084301}, {"step": 709, "kl": 0.3738877132660703, "ce": 0.16104670192498294}, {"step": 710, "kl": 0.3544539160166211, "ce": 0.19649797058366794}, {"step": 711, "kl": 0.3776972275976429, "ce": 0.1242001489071863}, {"step": 712, "kl": 0.36481813995125684, "ce": 0.15784539547434617}, {"step": 713, "kl": 0.36262859870093245, "ce": 0.1899955001977531}, {"step": 714, "kl": 0.3804170989874057, "ce": 0.22084593794495813}, {"step": 715, "kl": 0.3476732490096662, "ce": 0.15420459986289387}, {"step": 716, "kl": 0.34071778188202584, "ce": 0.1617294454026496}, {"step": 717, "kl": 0.37780088316032573, "ce": 0.148381491473967}, {"step": 718, "kl": 0.3422798128052628, "ce": 0.15933957854572794}, {"step": 719, "kl": 0.37164233898501964, "ce": 0.180077734046402}, {"step": 720, "kl": 0.4250013584327044, "ce": 0.19064592482047946}, {"step": 721, "kl": 0.35668568279074814, "ce": 0.18070910268412804}, {"step": 722, "kl": 0.32435750639156014, "ce": 0.17639132822275916}, {"step": 723, "kl": 0.3664222306032545, "ce": 0.14825763159889083}, {"step": 724, "kl": 0.33444392654346594, "ce": 0.15944135798383044}, {"step": 725, "kl": 0.3102037620330365, "ce": 0.1725811351597107}, {"step": 726, "kl": 0.36758805013269114, "ce": 0.1661139613475229}, {"step": 727, "kl": 0.261473659989446, "ce": 0.14609503009335797}, {"step": 728, "kl": 0.4039804303396204, "ce": 0.1674554487524445}, {"step": 729, "kl": 0.37630628011659334, "ce": 0.1383736056919837}, {"step": 730, "kl": 0.40673858019251186, "ce": 0.1527257008555511}, {"step": 731, "kl": 0.3397376949263658, "ce": 0.17855932005818878}, {"step": 732, "kl": 0.3444884696839348, "ce": 0.13474251905117884}, {"step": 733, "kl": 0.3416902054232776, "ce": 0.16842261400377928}, {"step": 734, "kl": 0.34554432058448575, "ce": 0.16875806177584696}, {"step": 735, "kl": 0.3320864855482374, "ce": 0.16463398297627768}, {"step": 736, "kl": 0.3506333095029449, "ce": 0.17711885377309208}, {"step": 737, "kl": 0.2898906742139038, "ce": 0.13256449164391032}, {"step": 738, "kl": 0.3798324397265461, "ce": 0.19238094507976045}, {"step": 739, "kl": 0.39525175680536634, "ce": 0.177687767132297}, {"step": 740, "kl": 0.38652361499435683, "ce": 0.17922435544039075}, {"step": 741, "kl": 0.3289614328333693, "ce": 0.18424836593338206}, {"step": 742, "kl": 0.37645710563570556, "ce": 0.1791032339861124}, {"step": 743, "kl": 0.36455453260934945, "ce": 0.14887982750208742}, {"step": 744, "kl": 0.333287602555393, "ce": 0.15308913086595605}, {"step": 745, "kl": 0.38023488770669966, "ce": 0.13528582067242276}, {"step": 746, "kl": 0.31483881841088823, "ce": 0.16609055693420105}, {"step": 747, "kl": 0.39245923573148966, "ce": 0.16821264023837362}, {"step": 748, "kl": 0.3919486562529003, "ce": 0.18967831831771353}, {"step": 749, "kl": 0.3436396450066866, "ce": 0.18838711905966}, {"step": 750, "kl": 0.398553711539101, "ce": 0.17337541326832948}, {"step": 751, "kl": 0.36926766145414386, "ce": 0.16383641562820558}, {"step": 752, "kl": 0.4168780684283614, "ce": 0.1683614834694912}, {"step": 753, "kl": 0.35757160336012384, "ce": 0.17928397557506823}, {"step": 754, "kl": 0.41596866041171154, "ce": 0.1747646000769094}, {"step": 755, "kl": 0.3024108057846258, "ce": 0.16687007445703042}, {"step": 756, "kl": 0.3550709188862555, "ce": 0.14016547011037597}, {"step": 757, "kl": 0.32626866343805566, "ce": 0.17035488395436565}, {"step": 758, "kl": 0.349124430496869, "ce": 0.17340126347106563}, {"step": 759, "kl": 0.38101323647357416, "ce": 0.17180184508963542}, {"step": 760, "kl": 0.3919285253358705, "ce": 0.17345194701328806}, {"step": 761, "kl": 0.39188069772761513, "ce": 0.19114061609691926}, {"step": 762, "kl": 0.40411621250518387, "ce": 0.16105977156583}, {"step": 763, "kl": 0.34286132494997656, "ce": 0.14810111793751954}, {"step": 764, "kl": 0.3084407426067249, "ce": 0.15415700559734613}, {"step": 765, "kl": 0.3640849400322588, "ce": 0.12737725374583203}, {"step": 766, "kl": 0.38910726281416413, "ce": 0.19390926207883288}, {"step": 767, "kl": 0.3734961920723881, "ce": 0.17612188147779456}, {"step": 768, "kl": 0.38523909274321233, "ce": 0.19179317593789832}, {"step": 769, "kl": 0.3373412793537356, "ce": 0.16587661205027018}, {"step": 770, "kl": 0.36700455864729187, "ce": 0.1687174241566475}, {"step": 771, "kl": 0.35259746475903325, "ce": 0.17130416177192045}, {"step": 772, "kl": 0.39182082857685635, "ce": 0.15101642487518457}, {"step": 773, "kl": 0.3377438337271466, "ce": 0.17626766175393102}, {"step": 774, "kl": 0.3225657326333663, "ce": 0.15161039542829124}, {"step": 775, "kl": 0.4047319678095233, "ce": 0.19380211708621026}, {"step": 776, "kl": 0.3657053416957382, "ce": 0.16852540756418308}, {"step": 777, "kl": 0.32287797253166983, "ce": 0.14988452979030925}, {"step": 778, "kl": 0.3724785737970465, "ce": 0.18178472656556385}, {"step": 779, "kl": 0.399706280607582, "ce": 0.18393220097185617}, {"step": 780, "kl": 0.31733677654966064, "ce": 0.13883096932330688}, {"step": 781, "kl": 0.34285184838897526, "ce": 0.1666412819216459}, {"step": 782, "kl": 0.3271555706126152, "ce": 0.16363908867254068}, {"step": 783, "kl": 0.31462078140429606, "ce": 0.1519260507888929}, {"step": 784, "kl": 0.36596869144602323, "ce": 0.15155730369626352}, {"step": 785, "kl": 0.3431051353587009, "ce": 0.17128927771583366}, {"step": 786, "kl": 0.3634942269092274, "ce": 0.16225696401219153}, {"step": 787, "kl": 0.37251394375172137, "ce": 0.15941950021993748}, {"step": 788, "kl": 0.35501603755374267, "ce": 0.1747839371492336}, {"step": 789, "kl": 0.33740888331033936, "ce": 0.1348808052053941}, {"step": 790, "kl": 0.3677167432790318, "ce": 0.15642275693501909}, {"step": 791, "kl": 0.3696579417224833, "ce": 0.17999228463521819}, {"step": 792, "kl": 0.3330570561439186, "ce": 0.20666506199897086}, {"step": 793, "kl": 0.33790565546227513, "ce": 0.13629957173306548}, {"step": 794, "kl": 0.32665826048110735, "ce": 0.17229275534773947}, {"step": 795, "kl": 0.36251529842105246, "ce": 0.15653987194745594}, {"step": 796, "kl": 0.40159345020096615, "ce": 0.13259240180107654}, {"step": 797, "kl": 0.32715664998065797, "ce": 0.17915310237471044}, {"step": 798, "kl": 0.35106807601837875, "ce": 0.1527994041923803}, {"step": 799, "kl": 0.3525693791179344, "ce": 0.1433368160694895}, {"step": 800, "kl": 0.3707822453242156, "ce": 0.15361854879046127}, {"step": 801, "kl": 0.34402963852024127, "ce": 0.15996446105721934}, {"step": 802, "kl": 0.3347775426811479, "ce": 0.1768953593437164}, {"step": 803, "kl": 0.329144800229296, "ce": 0.17746950140263823}, {"step": 804, "kl": 0.37287001316170554, "ce": 0.1575282645472408}, {"step": 805, "kl": 0.4041418473716874, "ce": 0.20158505076929892}, {"step": 806, "kl": 0.34286414305236934, "ce": 0.16918146880084373}, {"step": 807, "kl": 0.40427821530604824, "ce": 0.16608282875370334}, {"step": 808, "kl": 0.35837796912002784, "ce": 0.2042514243997117}, {"step": 809, "kl": 0.38763533342705003, "ce": 0.1616472852153656}, {"step": 810, "kl": 0.39739909488494657, "ce": 0.20651007204020796}, {"step": 811, "kl": 0.3673462081615388, "ce": 0.15536528656283755}, {"step": 812, "kl": 0.34936862521701384, "ce": 0.17892375197126623}, {"step": 813, "kl": 0.34265645595289934, "ce": 0.1552691611514729}, {"step": 814, "kl": 0.32509517762357454, "ce": 0.13568109565733671}, {"step": 815, "kl": 0.33327836399311417, "ce": 0.14303791966145224}, {"step": 816, "kl": 0.37238240089497837, "ce": 0.17943829401090228}, {"step": 817, "kl": 0.33876891637372375, "ce": 0.1598281846540204}, {"step": 818, "kl": 0.35539525939354866, "ce": 0.19636455950103782}, {"step": 819, "kl": 0.3747237654554459, "ce": 0.15322128916643876}, {"step": 820, "kl": 0.3688918708591411, "ce": 0.20025223343771675}, {"step": 821, "kl": 0.3525540492281905, "ce": 0.1528634318236428}, {"step": 822, "kl": 0.3185966518098508, "ce": 0.1525464654487383}, {"step": 823, "kl": 0.326904215624792, "ce": 0.14315998326315052}, {"step": 824, "kl": 0.3653252447589487, "ce": 0.14403411148176726}, {"step": 825, "kl": 0.3332567325858183, "ce": 0.1491324789960122}, {"step": 826, "kl": 0.3307707340877621, "ce": 0.1848284815235902}, {"step": 827, "kl": 0.30279064039244274, "ce": 0.15447165227664816}, {"step": 828, "kl": 0.4095586028575573, "ce": 0.1640093259853537}, {"step": 829, "kl": 0.3631532699946004, "ce": 0.169768339389884}, {"step": 830, "kl": 0.3921923535446631, "ce": 0.1574708871530628}, {"step": 831, "kl": 0.38995661937348164, "ce": 0.183338382353157}, {"step": 832, "kl": 0.40926253144737457, "ce": 0.18161478418014482}, {"step": 833, "kl": 0.3332994115436016, "ce": 0.15820252457768288}, {"step": 834, "kl": 0.33681999422469233, "ce": 0.16796877230485088}, {"step": 835, "kl": 0.3629612972069445, "ce": 0.1689979489010171}, {"step": 836, "kl": 0.4026218144049958, "ce": 0.18052642841408723}, {"step": 837, "kl": 0.37978926085543263, "ce": 0.17177679075216784}, {"step": 838, "kl": 0.3185884580759464, "ce": 0.1545202183354868}, {"step": 839, "kl": 0.3518352890390234, "ce": 0.1590057602734404}, {"step": 840, "kl": 0.35158341239655444, "ce": 0.1697067825058485}, {"step": 841, "kl": 0.3322587580228076, "ce": 0.16981456609969903}, {"step": 842, "kl": 0.3389619477378756, "ce": 0.20634327252311835}, {"step": 843, "kl": 0.3542599711241924, "ce": 0.18143300205698681}, {"step": 844, "kl": 0.3365930049072752, "ce": 0.13402413688320292}, {"step": 845, "kl": 0.3284489993582513, "ce": 0.15385044270359316}, {"step": 846, "kl": 0.36825693396871545, "ce": 0.1980025646571713}, {"step": 847, "kl": 0.32797998855296523, "ce": 0.15819632087359964}, {"step": 848, "kl": 0.3311248793842908, "ce": 0.14916844494430503}, {"step": 849, "kl": 0.39082270055203827, "ce": 0.16285136609393863}, {"step": 850, "kl": 0.32196874046046425, "ce": 0.17816381361821815}, {"step": 851, "kl": 0.37323643941381646, "ce": 0.18279011646163798}, {"step": 852, "kl": 0.34747490516075713, "ce": 0.17537112629904844}, {"step": 853, "kl": 0.379309189273431, "ce": 0.1505302196015546}, {"step": 854, "kl": 0.3397408226272652, "ce": 0.1458606001722264}, {"step": 855, "kl": 0.34809815156262436, "ce": 0.17207922965049313}, {"step": 856, "kl": 0.3352687812136564, "ce": 0.15876167905014174}, {"step": 857, "kl": 0.3636991169760467, "ce": 0.16051894729351354}, {"step": 858, "kl": 0.3095018364377123, "ce": 0.16043567657470703}, {"step": 859, "kl": 0.33206648240655157, "ce": 0.13599710280676972}, {"step": 860, "kl": 0.39470441765489483, "ce": 0.16809761540753998}, {"step": 861, "kl": 0.3702294623388349, "ce": 0.17636582263150558}, {"step": 862, "kl": 0.3810893737364514, "ce": 0.18667858872709978}, {"step": 863, "kl": 0.3443665049377759, "ce": 0.1512379170260832}, {"step": 864, "kl": 0.3919306051004659, "ce": 0.15715876998218042}, {"step": 865, "kl": 0.3892812831246526, "ce": 0.19741896972684803}, {"step": 866, "kl": 0.33788944754430433, "ce": 0.17354693925341877}, {"step": 867, "kl": 0.352163588035536, "ce": 0.17769893728502714}, {"step": 868, "kl": 0.3540271974226362, "ce": 0.16013438120726758}, {"step": 869, "kl": 0.3454996564526074, "ce": 0.16514954787034256}, {"step": 870, "kl": 0.34389712183447363, "ce": 0.15693777352346358}, {"step": 871, "kl": 0.33500732018454454, "ce": 0.16647289034797438}, {"step": 872, "kl": 0.36181232224087045, "ce": 0.15682491468114343}, {"step": 873, "kl": 0.32526122618914166, "ce": 0.15947318875312988}, {"step": 874, "kl": 0.3697509345966335, "ce": 0.1890838484585188}, {"step": 875, "kl": 0.32034433061383494, "ce": 0.1785261405674757}, {"step": 876, "kl": 0.3731427102000778, "ce": 0.16780144970407598}, {"step": 877, "kl": 0.3662770510191165, "ce": 0.16337450691690972}, {"step": 878, "kl": 0.3103574360220376, "ce": 0.13544258680499968}, {"step": 879, "kl": 0.3474407045393972, "ce": 0.1379254390141316}, {"step": 880, "kl": 0.3405648765614685, "ce": 0.17982686402132994}, {"step": 881, "kl": 0.3344939135256983, "ce": 0.16898828820825468}, {"step": 882, "kl": 0.3082635707806669, "ce": 0.15428305755765018}, {"step": 883, "kl": 0.36127402663798047, "ce": 0.15258174160670807}, {"step": 884, "kl": 0.30388141733355223, "ce": 0.1253232006855904}, {"step": 885, "kl": 0.34367480937636746, "ce": 0.17549909900928198}, {"step": 886, "kl": 0.27328962185596667, "ce": 0.13405386126831245}, {"step": 887, "kl": 0.39350201683723307, "ce": 0.20815455823833304}, {"step": 888, "kl": 0.3355854499603571, "ce": 0.13884174163308735}, {"step": 889, "kl": 0.35759153527277426, "ce": 0.1361724233378411}, {"step": 890, "kl": 0.3904576807562823, "ce": 0.15913133387847028}, {"step": 891, "kl": 0.30531082539707693, "ce": 0.1444243786674922}, {"step": 892, "kl": 0.3389674787098019, "ce": 0.16638853582490024}, {"step": 893, "kl": 0.38356325574741246, "ce": 0.17468142550241111}, {"step": 894, "kl": 0.3984027858598503, "ce": 0.14773966599933858}, {"step": 895, "kl": 0.32793464569009867, "ce": 0.16772747617779354}, {"step": 896, "kl": 0.3947467483454917, "ce": 0.14873827917376484}, {"step": 897, "kl": 0.36418224276511324, "ce": 0.16949713437603903}, {"step": 898, "kl": 0.3214838885036583, "ce": 0.13206092206538947}, {"step": 899, "kl": 0.33952949675216887, "ce": 0.13522020498624115}, {"step": 900, "kl": 0.39207031122900166, "ce": 0.1769595439010381}, {"step": 901, "kl": 0.36750913602261503, "ce": 0.1882727541954689}, {"step": 902, "kl": 0.3556574145701601, "ce": 0.17708461061192018}, {"step": 903, "kl": 0.36707046088775397, "ce": 0.14845406725185806}, {"step": 904, "kl": 0.3469757417633413, "ce": 0.17976649051780388}, {"step": 905, "kl": 0.317431403618911, "ce": 0.15975919900204189}, {"step": 906, "kl": 0.3594135536102328, "ce": 0.19840904156890324}, {"step": 907, "kl": 0.3109172799996291, "ce": 0.18715832577689848}, {"step": 908, "kl": 0.3821187985889253, "ce": 0.1690919279563145}, {"step": 909, "kl": 0.370928512138352, "ce": 0.16423177820551307}, {"step": 910, "kl": 0.40368996857445766, "ce": 0.14418104445771066}, {"step": 911, "kl": 0.3548377630406619, "ce": 0.16815613879615254}, {"step": 912, "kl": 0.3804702558542487, "ce": 0.15665815518179385}, {"step": 913, "kl": 0.40880969001798173, "ce": 0.1466572951026377}, {"step": 914, "kl": 0.40050803709748567, "ce": 0.16688203187609196}, {"step": 915, "kl": 0.4166569434128172, "ce": 0.18582901466194043}, {"step": 916, "kl": 0.3549995570795081, "ce": 0.1624503383047885}, {"step": 917, "kl": 0.3330262529527819, "ce": 0.1646221380449052}, {"step": 918, "kl": 0.3093533089216104, "ce": 0.1556305522065353}, {"step": 919, "kl": 0.32558943536018087, "ce": 0.156448708260678}, {"step": 920, "kl": 0.3272071125066691, "ce": 0.13465960582856162}, {"step": 921, "kl": 0.3252557035838287, "ce": 0.15002728693828737}, {"step": 922, "kl": 0.3454057954208195, "ce": 0.14189667422625968}], "val": [{"step": 0, "math_kl": 0.2558450283886451, "math_ce": 0.4875823904101404, "code_kl": 0.16784317317180839, "code_ce": 0.3320483730687428, "math_hard_kl": 0.3206654156163548, "math_hard_ce": 0.6148898550851406}, {"step": 461, "math_kl": 0.20684506848608297, "math_ce": 0.474814856929452, "code_kl": 0.3148119765123359, "code_ce": 0.2394056971111512, "math_hard_kl": 0.26837776630076604, "math_hard_ce": 0.6158035761335884}, {"step": 922, "math_kl": 0.22842272387506696, "math_ce": 0.5158765047799361, "code_kl": 0.375653243372234, "code_ce": 0.2474786401165565, "math_hard_kl": 0.31006984450732655, "math_hard_ce": 0.6471800292055488}]}
seq_math_code_gt_sft/stage2_code/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0de87f0b92acbf04c56a02260a52f283c8ae597ccc78871fb6e7bbde7014353
3
+ size 3087467144