Upload folder using huggingface_hub
Browse files
seq_code_math_kd_only_seed1/run_info.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"setting": "KD only",
|
| 3 |
+
"alpha": 1.0,
|
| 4 |
+
"order": "code_math",
|
| 5 |
+
"seed": 1,
|
| 6 |
+
"exp": 2,
|
| 7 |
+
"student": "Qwen/Qwen2.5-1.5B-Instruct",
|
| 8 |
+
"gpu_student": "NVIDIA RTX A6000",
|
| 9 |
+
"gpu_teachers": "NVIDIA RTX 6000 Ada Generation",
|
| 10 |
+
"load_h": 0.0038557967212465073,
|
| 11 |
+
"stages": {
|
| 12 |
+
"stage1_code": {
|
| 13 |
+
"domain": "code",
|
| 14 |
+
"steps": 922,
|
| 15 |
+
"train_h": 3.483110751774576,
|
| 16 |
+
"val_start": {
|
| 17 |
+
"step": 0,
|
| 18 |
+
"math_kl": 0.15874307828215575,
|
| 19 |
+
"math_ce": 0.6515277156879916,
|
| 20 |
+
"code_kl": 0.14786912634071003,
|
| 21 |
+
"code_ce": 0.30340147782401555,
|
| 22 |
+
"math_hard_kl": 0.24940142917923272,
|
| 23 |
+
"math_hard_ce": 0.6765219455834559
|
| 24 |
+
},
|
| 25 |
+
"val_end": {
|
| 26 |
+
"step": 922,
|
| 27 |
+
"math_kl": 0.16037220667035662,
|
| 28 |
+
"math_ce": 0.6134552778130008,
|
| 29 |
+
"code_kl": 0.07813229218058698,
|
| 30 |
+
"code_ce": 0.3095525097758208,
|
| 31 |
+
"math_hard_kl": 0.24713406450048658,
|
| 32 |
+
"math_hard_ce": 0.6740036130352745
|
| 33 |
+
},
|
| 34 |
+
"peak_gb_student": 33.696606159210205,
|
| 35 |
+
"peak_gb_teachers": 30.005428314208984
|
| 36 |
+
}
|
| 37 |
+
}
|
| 38 |
+
}
|
seq_code_math_kd_only_seed1/stage1_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_code_math_kd_only_seed1/stage1_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_code_math_kd_only_seed1/stage1_code/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.13704440663161788, "ce": 0.29685733172593876}, {"step": 2, "kl": 0.14806935676745422, "ce": 0.3069120305653913}, {"step": 3, "kl": 0.13526995022546368, "ce": 0.34384542822837827}, {"step": 4, "kl": 0.14658927197789426, "ce": 0.34684019325643767}, {"step": 5, "kl": 0.14965146134208826, "ce": 0.3549354665127997}, {"step": 6, "kl": 0.15748170701743433, "ce": 0.32284757614558757}, {"step": 7, "kl": 0.13137309129343525, "ce": 0.246220184182349}, {"step": 8, "kl": 0.1339907637568922, "ce": 0.3658319265946098}, {"step": 9, "kl": 0.13883599798558124, "ce": 0.3153630710800474}, {"step": 10, "kl": 0.1350762702239269, "ce": 0.3182865191719284}, {"step": 11, "kl": 0.1393932541861741, "ce": 0.2972515975400415}, {"step": 12, "kl": 0.13680263821696684, "ce": 0.3164134147515417}, {"step": 13, "kl": 0.13834523406908797, "ce": 0.39332901391895664}, {"step": 14, "kl": 0.13005127832324961, "ce": 0.31041958223993976}, {"step": 15, "kl": 0.13963568648482666, "ce": 0.35507424365954654}, {"step": 16, "kl": 0.11827190723337846, "ce": 0.33500862121582037}, {"step": 17, "kl": 0.1394030716697479, "ce": 0.3908363938892526}, {"step": 18, "kl": 0.12775877864840499, "ce": 0.2840459418832456}, {"step": 19, "kl": 0.12271336624166641, "ce": 0.3387764016787211}, {"step": 20, "kl": 0.11687929415662862, "ce": 0.3145019165293641}, {"step": 21, "kl": 0.09885681459534545, "ce": 0.34476667306660735}, {"step": 22, "kl": 0.1473414086870838, "ce": 0.37685547280487036}, {"step": 23, "kl": 0.12210798489042803, "ce": 0.3405072408125225}, {"step": 24, "kl": 0.12185155813136966, "ce": 0.36283559210601474}, {"step": 25, "kl": 0.11244103166249436, "ce": 0.34680547084201424}, {"step": 26, "kl": 0.11871337588535183, "ce": 0.37483116069106936}, {"step": 27, "kl": 0.12972729493646476, "ce": 0.3956318193295861}, {"step": 28, "kl": 0.1319561867100482, "ce": 0.38645595402580885}, {"step": 29, "kl": 0.12108262467674161, "ce": 0.28278767636103086}, {"step": 30, "kl": 0.10992200988479076, "ce": 0.3370563722949964}, {"step": 31, "kl": 0.11920558882151454, "ce": 0.33784390224772654}, {"step": 32, "kl": 0.1179767993739254, "ce": 0.35488554831264785}, {"step": 33, "kl": 0.11798584275598711, "ce": 0.3206815281852347}, {"step": 34, "kl": 0.0996024269425408, "ce": 0.3264151282546016}, {"step": 35, "kl": 0.1278265623817944, "ce": 0.2951014072409751}, {"step": 36, "kl": 0.12334869438683607, "ce": 0.32042869534554963}, {"step": 37, "kl": 0.09596426265938174, "ce": 0.28126035548807476}, {"step": 38, "kl": 0.12737978970782357, "ce": 0.3239394208500359}, {"step": 39, "kl": 0.11148597101672705, "ce": 0.2840446807350574}, {"step": 40, "kl": 0.11305670532566223, "ce": 0.31814039449247244}, {"step": 41, "kl": 0.09984175774185883, "ce": 0.3209506746733181}, {"step": 42, "kl": 0.11618078306047236, "ce": 0.31628018804095454}, {"step": 43, "kl": 0.11557885259199954, "ce": 0.37559924937206934}, {"step": 44, "kl": 0.1251017744596444, "ce": 0.37676247975053606}, {"step": 45, "kl": 0.10926947551668065, "ce": 0.33094926304046}, {"step": 46, "kl": 0.12491639620277872, "ce": 0.29693105507577017}, {"step": 47, "kl": 0.13052838602862976, "ce": 0.3615430872696059}, {"step": 48, "kl": 0.1447564561802837, "ce": 0.3225563869725444}, {"step": 49, "kl": 0.12129087620009753, "ce": 0.4005296645716029}, {"step": 50, "kl": 0.12506926685760136, "ce": 0.3329974794240494}, {"step": 51, "kl": 0.1416879879836022, "ce": 0.31116578941859724}, {"step": 52, "kl": 0.12691741293221226, "ce": 0.35278677921310414}, {"step": 53, "kl": 0.1162268810794669, "ce": 0.31451679769801005}, {"step": 54, "kl": 0.10745702139722946, "ce": 0.32574387615824374}, {"step": 55, "kl": 0.11754305901628563, "ce": 0.3755159465822482}, {"step": 56, "kl": 0.1324540139513777, "ce": 0.36929477080675094}, {"step": 57, "kl": 0.13915828118428847, "ce": 0.3832023544298018}, {"step": 58, "kl": 0.1095521290864288, "ce": 0.2889981143725098}, {"step": 59, "kl": 0.09878477924648929, "ce": 0.3064758506385722}, {"step": 60, "kl": 0.1388992545667889, "ce": 0.36728376619690756}, {"step": 61, "kl": 0.10467395402839814, "ce": 0.3086734036581216}, {"step": 62, "kl": 0.10961398929806182, "ce": 0.3480198509558092}, {"step": 63, "kl": 0.10425342269129706, "ce": 0.3086046561311827}, {"step": 64, "kl": 0.12492903042216547, "ce": 0.3734765527309771}, {"step": 65, "kl": 0.13398809731632286, "ce": 0.3730282063954558}, {"step": 66, "kl": 0.12701469480267855, "ce": 0.3071281692086298}, {"step": 67, "kl": 0.08996527284340046, "ce": 0.2549928532561319}, {"step": 68, "kl": 0.10942148828148796, "ce": 0.4266736448090133}, {"step": 69, "kl": 0.12096396492000584, "ce": 0.35845914433662646}, {"step": 70, "kl": 0.1193455579969395, "ce": 0.3862673441569011}, {"step": 71, "kl": 0.12238442311521437, "ce": 0.31270511098956233}, {"step": 72, "kl": 0.11993161087930061, "ce": 0.3321626605267204}, {"step": 73, "kl": 0.11421788530163698, "ce": 0.2836191999898077}, {"step": 74, "kl": 0.09351684369709251, "ce": 0.30300658797763097}, {"step": 75, "kl": 0.08899040489736526, "ce": 0.3250602982901587}, {"step": 76, "kl": 0.11838123121427273, "ce": 0.3347885149600962}, {"step": 77, "kl": 0.09965604740745843, "ce": 0.3327748444501092}, {"step": 78, "kl": 0.10782011094417054, "ce": 0.30382411832420314}, {"step": 79, "kl": 0.11984247890972656, "ce": 0.3216278823288633}, {"step": 80, "kl": 0.11322266379005001, "ce": 0.3109728934452933}, {"step": 81, "kl": 0.10930029879782373, "ce": 0.33476761427763135}, {"step": 82, "kl": 0.09968400769704522, "ce": 0.3026782294465312}, {"step": 83, "kl": 0.1196314580985848, "ce": 0.3685463573563536}, {"step": 84, "kl": 0.14206273089044594, "ce": 0.4372729907710881}, {"step": 85, "kl": 0.10591999461921597, "ce": 0.28715227161819895}, {"step": 86, "kl": 0.12632093628128538, "ce": 0.35099654093540406}, {"step": 87, "kl": 0.10336536309673336, "ce": 0.3346773262989141}, {"step": 88, "kl": 0.10975103625707423, "ce": 0.37089590646787024}, {"step": 89, "kl": 0.1208127622743284, "ce": 0.4179257881810737}, {"step": 90, "kl": 0.1078416589842725, "ce": 0.3496137288793949}, {"step": 91, "kl": 0.09484171123196362, "ce": 0.33792257951331267}, {"step": 92, "kl": 0.12339016338794166, "ce": 0.327697070894581}, {"step": 93, "kl": 0.10527032855336635, "ce": 0.31271153587568784}, {"step": 94, "kl": 0.12783501424683566, "ce": 0.35259213379918153}, {"step": 95, "kl": 0.12204786437692809, "ce": 0.3735239891311472}, {"step": 96, "kl": 0.08712566423773697, "ce": 0.3033480782184182}, {"step": 97, "kl": 0.09693019444468744, "ce": 0.3039891357673255}, {"step": 98, "kl": 0.12647379960805355, "ce": 0.30084002350237316}, {"step": 99, "kl": 0.12379308432112728, "ce": 0.37055429689651126}, {"step": 100, "kl": 0.1267353404919277, "ce": 0.32270642182328774}, {"step": 101, "kl": 0.10903264412983021, "ce": 0.3719214301716916}, {"step": 102, "kl": 0.12216406758999926, "ce": 0.3356432903670379}, {"step": 103, "kl": 0.11222956593496253, "ce": 0.3570131192840603}, {"step": 104, "kl": 0.12183782068838353, "ce": 0.3719194270727991}, {"step": 105, "kl": 0.10277672482458926, "ce": 0.31273352778518837}, {"step": 106, "kl": 0.09957929992236476, "ce": 0.2625331979752565}, {"step": 107, "kl": 0.12344006552028602, "ce": 0.32253004134458246}, {"step": 108, "kl": 0.12247778278362698, "ce": 0.3830716716897205}, {"step": 109, "kl": 0.12788105508305675, "ce": 0.3595209791809448}, {"step": 110, "kl": 0.12028293183517025, "ce": 0.33149258051889086}, {"step": 111, "kl": 0.0991997419658198, "ce": 0.30066785274459357}, {"step": 112, "kl": 0.11025746068692509, "ce": 0.31055208200697626}, {"step": 113, "kl": 0.08593549603498755, "ce": 0.30734472729227974}, {"step": 114, "kl": 0.1140049825322247, "ce": 0.29839782959768135}, {"step": 115, "kl": 0.11861125092849906, "ce": 0.34307603849146656}, {"step": 116, "kl": 0.10882589713932128, "ce": 0.3258180183290484}, {"step": 117, "kl": 0.09659786918939818, "ce": 0.2760513137968156}, {"step": 118, "kl": 0.12898523012995464, "ce": 0.3528163337243965}, {"step": 119, "kl": 0.11618527321073639, "ce": 0.32685369904508293}, {"step": 120, "kl": 0.10643653173938207, "ce": 0.3251190948797859}, {"step": 121, "kl": 0.10273505177622566, "ce": 0.32285449964227253}, {"step": 122, "kl": 0.09915201258079259, "ce": 0.29944456121894747}, {"step": 123, "kl": 0.11259062984667786, "ce": 0.3496565357024182}, {"step": 124, "kl": 0.09459516445963713, "ce": 0.29265412150994363}, {"step": 125, "kl": 0.09529427204933942, "ce": 0.29926405153939173}, {"step": 126, "kl": 0.08078074419280667, "ce": 0.30327662645384323}, {"step": 127, "kl": 0.09108746089783322, "ce": 0.3120585770572111}, {"step": 128, "kl": 0.11612532062411907, "ce": 0.31100758751612895}, {"step": 129, "kl": 0.0999998191282294, "ce": 0.31950238376756834}, {"step": 130, "kl": 0.11625112758900498, "ce": 0.34016251754615534}, {"step": 131, "kl": 0.12446351761390739, "ce": 0.3429687274091264}, {"step": 132, "kl": 0.10596089405405863, "ce": 0.3090486395471094}, {"step": 133, "kl": 0.10317733215083172, "ce": 0.31422603214563294}, {"step": 134, "kl": 0.10036916423009477, "ce": 0.33834625384787853}, {"step": 135, "kl": 0.13692502174359078, "ce": 0.3643701028390268}, {"step": 136, "kl": 0.14480469312126698, "ce": 0.356607864940624}, {"step": 137, "kl": 0.1193660461837908, "ce": 0.3459369414687323}, {"step": 138, "kl": 0.12078127627600943, "ce": 0.3760184733637429}, {"step": 139, "kl": 0.10389560989346272, "ce": 0.3478221746534969}, {"step": 140, "kl": 0.08578149295554678, "ce": 0.30926676101758566}, {"step": 141, "kl": 0.10838749724197952, "ce": 0.3197515674502386}, {"step": 142, "kl": 0.12219497927389253, "ce": 0.35157446417824956}, {"step": 143, "kl": 0.10325405877743396, "ce": 0.3058908944592864}, {"step": 144, "kl": 0.09548380760104251, "ce": 0.2942171456062631}, {"step": 145, "kl": 0.09680210342557413, "ce": 0.29944448028435683}, {"step": 146, "kl": 0.11948201747332572, "ce": 0.38414455162650585}, {"step": 147, "kl": 0.09587245305527849, "ce": 0.3043474750677892}, {"step": 148, "kl": 0.11088318889665727, "ce": 0.3804266823844877}, {"step": 149, "kl": 0.11185969256578691, "ce": 0.3428857268846984}, {"step": 150, "kl": 0.11115737841673515, "ce": 0.30933520105006457}, {"step": 151, "kl": 0.12478183776866039, "ce": 0.3546464427666962}, {"step": 152, "kl": 0.10680896649315333, "ce": 0.30501816686200556}, {"step": 153, "kl": 0.10556547069631, "ce": 0.31145707662513766}, {"step": 154, "kl": 0.10785051148464772, "ce": 0.3650313692212219}, {"step": 155, "kl": 0.11385117641195046, "ce": 0.3814447725997752}, {"step": 156, "kl": 0.10458442209055255, "ce": 0.29068655720207687}, {"step": 157, "kl": 0.09968177098234025, "ce": 0.34206232722347746}, {"step": 158, "kl": 0.12123331860126554, "ce": 0.3477182910572919}, {"step": 159, "kl": 0.1039724445248084, "ce": 0.3701015160800997}, {"step": 160, "kl": 0.09357383458365871, "ce": 0.34298350680986117}, {"step": 161, "kl": 0.12555734826392811, "ce": 0.3817078768986406}, {"step": 162, "kl": 0.11602424639657545, "ce": 0.293942094788526}, {"step": 163, "kl": 0.12707543722700126, "ce": 0.32435427210768875}, {"step": 164, "kl": 0.1179250894249871, "ce": 0.31352631012717824}, {"step": 165, "kl": 0.09738741661626746, "ce": 0.33447445094621714}, {"step": 166, "kl": 0.10922506980984886, "ce": 0.3574659386175482}, {"step": 167, "kl": 0.11367560468835894, "ce": 0.33050945649258606}, {"step": 168, "kl": 0.12028769057326168, "ce": 0.31416640158292175}, {"step": 169, "kl": 0.11483090514610762, "ce": 0.3217690507256366}, {"step": 170, "kl": 0.10972946974310543, "ce": 0.30785347392043155}, {"step": 171, "kl": 0.11509332104961899, "ce": 0.297282487291691}, {"step": 172, "kl": 0.11940021415925073, "ce": 0.34727812902665617}, {"step": 173, "kl": 0.10598317168482793, "ce": 0.30801356765959}, {"step": 174, "kl": 0.11515757423127262, "ce": 0.33773506909292916}, {"step": 175, "kl": 0.10991752661925931, "ce": 0.2853326290457974}, {"step": 176, "kl": 0.12335090792655326, "ce": 0.33255555656045743}, {"step": 177, "kl": 0.11534882076882452, "ce": 0.32875509161090705}, {"step": 178, "kl": 0.1021364094070734, "ce": 0.3135989121844702}, {"step": 179, "kl": 0.10969517805189365, "ce": 0.3126946379443665}, {"step": 180, "kl": 0.0937389770758385, "ce": 0.31478308799392063}, {"step": 181, "kl": 0.10752378825022087, "ce": 0.2708309114626151}, {"step": 182, "kl": 0.09821348000991555, "ce": 0.3247868357695305}, {"step": 183, "kl": 0.12110498190040553, "ce": 0.2960828200683987}, {"step": 184, "kl": 0.11281086341099424, "ce": 0.328803069429962}, {"step": 185, "kl": 0.09312117304538656, "ce": 0.34138903855082153}, {"step": 186, "kl": 0.13137557381778353, "ce": 0.4108150141688989}, {"step": 187, "kl": 0.09917525818330471, "ce": 0.284170878224983}, {"step": 188, "kl": 0.11270592634977875, "ce": 0.34052073186366405}, {"step": 189, "kl": 0.1166523998553015, "ce": 0.3888445405513352}, {"step": 190, "kl": 0.1014199783327519, "ce": 0.30812447341447025}, {"step": 191, "kl": 0.09682516385803293, "ce": 0.3050120373998962}, {"step": 192, "kl": 0.12437202568658817, "ce": 0.36342820830448697}, {"step": 193, "kl": 0.10610031494366125, "ce": 0.3245383999871869}, {"step": 194, "kl": 0.09054183794540704, "ce": 0.32996551144241615}, {"step": 195, "kl": 0.12096378462655204, "ce": 0.33918008890682494}, {"step": 196, "kl": 0.10541334931372497, "ce": 0.3473413838369023}, {"step": 197, "kl": 0.11889690888384505, "ce": 0.3519026700527096}, {"step": 198, "kl": 0.1165833179925323, "ce": 0.279723940391388}, {"step": 199, "kl": 0.0893456339010114, "ce": 0.2899602113669313}, {"step": 200, "kl": 0.10481382144450474, "ce": 0.33150208325558495}, {"step": 201, "kl": 0.09222512272214646, "ce": 0.2747563139218786}, {"step": 202, "kl": 0.11048148612105801, "ce": 0.3596078740692272}, {"step": 203, "kl": 0.09588293007062974, "ce": 0.2871252213846504}, {"step": 204, "kl": 0.10866162297456866, "ce": 0.3352934071932796}, {"step": 205, "kl": 0.11918161462407607, "ce": 0.3699545965146946}, {"step": 206, "kl": 0.11676491918891853, "ce": 0.3046280885696968}, {"step": 207, "kl": 0.09617767288571313, "ce": 0.31267933674234366}, {"step": 208, "kl": 0.11424922131247202, "ce": 0.35736553777447716}, {"step": 209, "kl": 0.1061083424722252, "ce": 0.3757516748764936}, {"step": 210, "kl": 0.10002244913603392, "ce": 0.3185177784179268}, {"step": 211, "kl": 0.14210419501996657, "ce": 0.35853503690389216}, {"step": 212, "kl": 0.09951157311369685, "ce": 0.3587561894366161}, {"step": 213, "kl": 0.10468400047946301, "ce": 0.3895762193279152}, {"step": 214, "kl": 0.09241736601882658, "ce": 0.28767217160892344}, {"step": 215, "kl": 0.10777408951528553, "ce": 0.35347781328408967}, {"step": 216, "kl": 0.08702563826768606, "ce": 0.31899523004620267}, {"step": 217, "kl": 0.12442309433160499, "ce": 0.3757322629592421}, {"step": 218, "kl": 0.1190361896371674, "ce": 0.3442586545532328}, {"step": 219, "kl": 0.12012353184967667, "ce": 0.34170093469764085}, {"step": 220, "kl": 0.09096785536740959, "ce": 0.36047111670303655}, {"step": 221, "kl": 0.09572285321944367, "ce": 0.30043842958443334}, {"step": 222, "kl": 0.09226697972677286, "ce": 0.2632146583193331}, {"step": 223, "kl": 0.09355552136877338, "ce": 0.3856836083712181}, {"step": 224, "kl": 0.11039205351765217, "ce": 0.34076027976650447}, {"step": 225, "kl": 0.09953098283866652, "ce": 0.3068369138650244}, {"step": 226, "kl": 0.09603336755080744, "ce": 0.3096890061400657}, {"step": 227, "kl": 0.10135488192915326, "ce": 0.3366558910719581}, {"step": 228, "kl": 0.09529665994661965, "ce": 0.335482498757779}, {"step": 229, "kl": 0.09770773905316124, "ce": 0.3550112531749925}, {"step": 230, "kl": 0.10736307360576755, "ce": 0.3316476377722335}, {"step": 231, "kl": 0.09665740001574784, "ce": 0.3004488493869883}, {"step": 232, "kl": 0.11690903770450865, "ce": 0.37187095362810835}, {"step": 233, "kl": 0.08402207820936608, "ce": 0.32201020445000855}, {"step": 234, "kl": 0.10099430808960017, "ce": 0.28794613132229097}, {"step": 235, "kl": 0.10064388434603284, "ce": 0.2784624540098085}, {"step": 236, "kl": 0.10673104954453613, "ce": 0.2670672289460339}, {"step": 237, "kl": 0.12384229975743297, "ce": 0.39826244130595273}, {"step": 238, "kl": 0.10122493537352048, "ce": 0.36112457004001286}, {"step": 239, "kl": 0.09208745798523549, "ce": 0.3608864753317923}, {"step": 240, "kl": 0.09956840591374454, "ce": 0.3429507016875961}, {"step": 241, "kl": 0.08064368452329607, "ce": 0.29324235310925273}, {"step": 242, "kl": 0.09116105604430463, "ce": 0.33762244306793665}, {"step": 243, "kl": 0.13609994107523987, "ce": 0.34239959597138864}, {"step": 244, "kl": 0.10386848124635092, "ce": 0.31545622557626096}, {"step": 245, "kl": 0.10310444507090631, "ce": 0.3377326670256353}, {"step": 246, "kl": 0.10375657889150805, "ce": 0.30020960674799224}, {"step": 247, "kl": 0.08894327269549294, "ce": 0.30804657002435276}, {"step": 248, "kl": 0.08617692630463025, "ce": 0.3072836051493187}, {"step": 249, "kl": 0.08312834793587728, "ce": 0.32329469199359734}, {"step": 250, "kl": 0.09789668336434353, "ce": 0.32230672888335826}, {"step": 251, "kl": 0.09332516745323963, "ce": 0.33610855752040286}, {"step": 252, "kl": 0.1138182509385587, "ce": 0.3513019002333425}, {"step": 253, "kl": 0.09875022325593705, "ce": 0.3382067031978913}, {"step": 254, "kl": 0.1042199344800364, "ce": 0.36202818127898784}, {"step": 255, "kl": 0.10486986682580944, "ce": 0.3213204004277339}, {"step": 256, "kl": 0.1214393447523891, "ce": 0.30153096976089117}, {"step": 257, "kl": 0.11014563114275784, "ce": 0.3342133487273277}, {"step": 258, "kl": 0.09420004924605124, "ce": 0.30184969423722086}, {"step": 259, "kl": 0.10185112865911347, "ce": 0.3230115889727899}, {"step": 260, "kl": 0.11922834261901695, "ce": 0.3883871649123556}, {"step": 261, "kl": 0.09349396513594059, "ce": 0.3008431595641297}, {"step": 262, "kl": 0.10695056243808714, "ce": 0.2909259881233629}, {"step": 263, "kl": 0.12368561695614315, "ce": 0.3860909845876139}, {"step": 264, "kl": 0.11247346294503646, "ce": 0.2878910997722659}, {"step": 265, "kl": 0.09847941383689976, "ce": 0.3385997740500757}, {"step": 266, "kl": 0.11389963384206155, "ce": 0.35990141819818394}, {"step": 267, "kl": 0.0956692432845611, "ce": 0.33896250630002034}, {"step": 268, "kl": 0.10437304276277759, "ce": 0.35965775073259726}, {"step": 269, "kl": 0.09386183430151482, "ce": 0.2790905920481115}, {"step": 270, "kl": 0.09330005747259343, "ce": 0.3015726145526074}, {"step": 271, "kl": 0.11753041748519688, "ce": 0.256682353313628}, {"step": 272, "kl": 0.08534156968087384, "ce": 0.285075226688612}, {"step": 273, "kl": 0.09098314912351844, "ce": 0.3352026228713324}, {"step": 274, "kl": 0.12495778001324445, "ce": 0.3863497365223109}, {"step": 275, "kl": 0.09345351483632425, "ce": 0.29008367100622495}, {"step": 276, "kl": 0.10346814021011072, "ce": 0.3537595051561476}, {"step": 277, "kl": 0.08227177611331657, "ce": 0.29451519776731466}, {"step": 278, "kl": 0.10852659193852815, "ce": 0.33113008125826227}, {"step": 279, "kl": 0.10812139591774442, "ce": 0.3137256243498135}, {"step": 280, "kl": 0.09945139109446306, "ce": 0.29358518854264287}, {"step": 281, "kl": 0.10308788001500689, "ce": 0.37443353586751205}, {"step": 282, "kl": 0.10735142565816745, "ce": 0.2967457643460558}, {"step": 283, "kl": 0.10116373429004795, "ce": 0.2786345767570836}, {"step": 284, "kl": 0.09247536000574609, "ce": 0.3185159275956478}, {"step": 285, "kl": 0.10083568615537461, "ce": 0.3353528469166857}, {"step": 286, "kl": 0.10186490101266688, "ce": 0.31906789061824803}, {"step": 287, "kl": 0.09431153963788955, "ce": 0.3538897092287595}, {"step": 288, "kl": 0.09723688037638328, "ce": 0.33898945099072425}, {"step": 289, "kl": 0.12662781308035176, "ce": 0.4366818362292282}, {"step": 290, "kl": 0.08009064014605885, "ce": 0.282025721252516}, {"step": 291, "kl": 0.09572698069694346, "ce": 0.3203093951432549}, {"step": 292, "kl": 0.09698265609675502, "ce": 0.3704099757557166}, {"step": 293, "kl": 0.1263682242679473, "ce": 0.37644444552201206}, {"step": 294, "kl": 0.09290926840506862, "ce": 0.33142537185826254}, {"step": 295, "kl": 0.09422077567286768, "ce": 0.2924032750694047}, {"step": 296, "kl": 0.12761101390454818, "ce": 0.39505826713692427}, {"step": 297, "kl": 0.10008695026282464, "ce": 0.3504301724368579}, {"step": 298, "kl": 0.0936893944089549, "ce": 0.3296896751890791}, {"step": 299, "kl": 0.11124381406292555, "ce": 0.33747194213028464}, {"step": 300, "kl": 0.10490175333993423, "ce": 0.3063529444425659}, {"step": 301, "kl": 0.10971688930614709, "ce": 0.3507948184101998}, {"step": 302, "kl": 0.1065187074953082, "ce": 0.30894249824578895}, {"step": 303, "kl": 0.09188726792408908, "ce": 0.32533523726359836}, {"step": 304, "kl": 0.1031455405809777, "ce": 0.33541623288535355}, {"step": 305, "kl": 0.10772059615771808, "ce": 0.3550694489487232}, {"step": 306, "kl": 0.09495364036303792, "ce": 0.33452432133306687}, {"step": 307, "kl": 0.09038657580167242, "ce": 0.26710382407840166}, {"step": 308, "kl": 0.08127651994132921, "ce": 0.33150334906120776}, {"step": 309, "kl": 0.09388059126900634, "ce": 0.36253714104020773}, {"step": 310, "kl": 0.12916531927270988, "ce": 0.3643717428404149}, {"step": 311, "kl": 0.10549219423757078, "ce": 0.2987802922430897}, {"step": 312, "kl": 0.11871736610294649, "ce": 0.3990749416749565}, {"step": 313, "kl": 0.08295140844063219, "ce": 0.2398473702155722}, {"step": 314, "kl": 0.09197565486797037, "ce": 0.3351293304370525}, {"step": 315, "kl": 0.10172058953101654, "ce": 0.33732404668343113}, {"step": 316, "kl": 0.10585675358050611, "ce": 0.3150485242088743}, {"step": 317, "kl": 0.1043379699189752, "ce": 0.3741466394695876}, {"step": 318, "kl": 0.0967181303961812, "ce": 0.3181379614574694}, {"step": 319, "kl": 0.09142108675626531, "ce": 0.3189848898467138}, {"step": 320, "kl": 0.10715279807253456, "ce": 0.3274351739101723}, {"step": 321, "kl": 0.1012165529174604, "ce": 0.3654819962039329}, {"step": 322, "kl": 0.10061579466220354, "ce": 0.34332367003930153}, {"step": 323, "kl": 0.11465738450993554, "ce": 0.356472945371211}, {"step": 324, "kl": 0.11083272435100085, "ce": 0.29767390554395545}, {"step": 325, "kl": 0.10038752805194734, "ce": 0.26399786994950003}, {"step": 326, "kl": 0.10015444675446607, "ce": 0.3341187034428803}, {"step": 327, "kl": 0.09390839213432742, "ce": 0.30506419962668335}, {"step": 328, "kl": 0.0785236713376311, "ce": 0.2991664343981698}, {"step": 329, "kl": 0.10091920869001486, "ce": 0.35735714526089135}, {"step": 330, "kl": 0.12267461443281757, "ce": 0.3172694680671884}, {"step": 331, "kl": 0.09097977909959955, "ce": 0.32377244619865775}, {"step": 332, "kl": 0.09912750242209867, "ce": 0.2853033766877293}, {"step": 333, "kl": 0.10785714559470704, "ce": 0.338339832045014}, {"step": 334, "kl": 0.08184998948921095, "ce": 0.29805408789449894}, {"step": 335, "kl": 0.09004791422557806, "ce": 0.2702672808101706}, {"step": 336, "kl": 0.10146206907344446, "ce": 0.3779872441105059}, {"step": 337, "kl": 0.08990641809447106, "ce": 0.29995135855008975}, {"step": 338, "kl": 0.11169776829312805, "ce": 0.31335851874148896}, {"step": 339, "kl": 0.07726599781261889, "ce": 0.29971452012465705}, {"step": 340, "kl": 0.09463637446672407, "ce": 0.3433812817074811}, {"step": 341, "kl": 0.12241918244559341, "ce": 0.3558217077108241}, {"step": 342, "kl": 0.08952895124275397, "ce": 0.3336834592041056}, {"step": 343, "kl": 0.09713774441981451, "ce": 0.3077381548264201}, {"step": 344, "kl": 0.10966912816079816, "ce": 0.30805176427198017}, {"step": 345, "kl": 0.10704893148167227, "ce": 0.36649907756685307}, {"step": 346, "kl": 0.09695829672179032, "ce": 0.32961179661162443}, {"step": 347, "kl": 0.10543531355461691, "ce": 0.3423329311183062}, {"step": 348, "kl": 0.1192368448964588, "ce": 0.39040364982236425}, {"step": 349, "kl": 0.10940425082130509, "ce": 0.3355841113222013}, {"step": 350, "kl": 0.09434514148515115, "ce": 0.29968209572654353}, {"step": 351, "kl": 0.0849133387537536, "ce": 0.32624616667518797}, {"step": 352, "kl": 0.09632474627263443, "ce": 0.33809435608132243}, {"step": 353, "kl": 0.10967341069223804, "ce": 0.3152170056701572}, {"step": 354, "kl": 0.08592711619251624, "ce": 0.310993308852272}, {"step": 355, "kl": 0.10777136972873361, "ce": 0.3881439467658313}, {"step": 356, "kl": 0.0946326148054549, "ce": 0.38737335932071776}, {"step": 357, "kl": 0.10395926296953592, "ce": 0.32447833963389017}, {"step": 358, "kl": 0.11034583060773157, "ce": 0.2946427948772907}, {"step": 359, "kl": 0.09162208041477908, "ce": 0.35151064108701974}, {"step": 360, "kl": 0.10137680409328406, "ce": 0.29195707473570154}, {"step": 361, "kl": 0.106888780601826, "ce": 0.3629591063207047}, {"step": 362, "kl": 0.07715996136314618, "ce": 0.29479873307437315}, {"step": 363, "kl": 0.1124582917205608, "ce": 0.34408919072192934}, {"step": 364, "kl": 0.10845553783158518, "ce": 0.3456477470301862}, {"step": 365, "kl": 0.09699333214455598, "ce": 0.3606714629219052}, {"step": 366, "kl": 0.10528697900419824, "ce": 0.30827050717023374}, {"step": 367, "kl": 0.1076330786306489, "ce": 0.3601539348978792}, {"step": 368, "kl": 0.08671434138031087, "ce": 0.2960548778238113}, {"step": 369, "kl": 0.10004528556823167, "ce": 0.33375385605732116}, {"step": 370, "kl": 0.09021733607142791, "ce": 0.35349906664833813}, {"step": 371, "kl": 0.09445752996059437, "ce": 0.3680857057539875}, {"step": 372, "kl": 0.08701764982466473, "ce": 0.30662873974121635}, {"step": 373, "kl": 0.08274049071912147, "ce": 0.3935593117735687}, {"step": 374, "kl": 0.0921594059618796, "ce": 0.28820808246410984}, {"step": 375, "kl": 0.09900693947004159, "ce": 0.30660052761459977}, {"step": 376, "kl": 0.09750224707049254, "ce": 0.26453767639277104}, {"step": 377, "kl": 0.09375459124403876, "ce": 0.3071585263331459}, {"step": 378, "kl": 0.11058046174489455, "ce": 0.3290346351730854}, {"step": 379, "kl": 0.08420956405956012, "ce": 0.3172645097270398}, {"step": 380, "kl": 0.09452923802667762, "ce": 0.2627816631184199}, {"step": 381, "kl": 0.10008794420475592, "ce": 0.33249679481705197}, {"step": 382, "kl": 0.08491501786578573, "ce": 0.2724241704802008}, {"step": 383, "kl": 0.09587167038423598, "ce": 0.3341687474381586}, {"step": 384, "kl": 0.08725024950655635, "ce": 0.3172690947330496}, {"step": 385, "kl": 0.1116841823883516, "ce": 0.3251168024511212}, {"step": 386, "kl": 0.09785502867734133, "ce": 0.31168729462805206}, {"step": 387, "kl": 0.12034302063465835, "ce": 0.3221674452104936}, {"step": 388, "kl": 0.10193334216274107, "ce": 0.2881672465868589}, {"step": 389, "kl": 0.07103101727692053, "ce": 0.273335901675017}, {"step": 390, "kl": 0.10922424399286244, "ce": 0.34528265069685055}, {"step": 391, "kl": 0.09797845935873299, "ce": 0.3267188069563808}, {"step": 392, "kl": 0.08788218705120776, "ce": 0.3281413153872464}, {"step": 393, "kl": 0.1084180171063005, "ce": 0.3467259466252697}, {"step": 394, "kl": 0.11775678879769136, "ce": 0.3152834983598119}, {"step": 395, "kl": 0.10323700946512192, "ce": 0.3201786071510642}, {"step": 396, "kl": 0.10894073233171436, "ce": 0.31540012101170817}, {"step": 397, "kl": 0.10234672534722175, "ce": 0.2897033062218631}, {"step": 398, "kl": 0.09655259367367348, "ce": 0.28979282641368076}, {"step": 399, "kl": 0.098782470876261, "ce": 0.33410155895875}, {"step": 400, "kl": 0.10517934005150521, "ce": 0.3480148264053293}, {"step": 401, "kl": 0.10148244349451434, "ce": 0.3446045456102951}, {"step": 402, "kl": 0.08233494243060034, "ce": 0.2889150027001258}, {"step": 403, "kl": 0.09305244856374464, "ce": 0.2906991102419691}, {"step": 404, "kl": 0.1202199096648047, "ce": 0.3475822233030309}, {"step": 405, "kl": 0.08810990669138276, "ce": 0.2929100339543981}, {"step": 406, "kl": 0.07886015771660762, "ce": 0.3478842255491647}, {"step": 407, "kl": 0.08383163584996459, "ce": 0.3035775104166205}, {"step": 408, "kl": 0.08770946013474487, "ce": 0.3324114932430317}, {"step": 409, "kl": 0.08759578705692377, "ce": 0.31509185763069125}, {"step": 410, "kl": 0.13119195731583555, "ce": 0.37019978663540504}, {"step": 411, "kl": 0.08012796497261247, "ce": 0.33648156755105807}, {"step": 412, "kl": 0.09442456268338376, "ce": 0.33607113074903794}, {"step": 413, "kl": 0.08770894186716414, "ce": 0.31303477803391777}, {"step": 414, "kl": 0.10188821675175402, "ce": 0.344921163057675}, {"step": 415, "kl": 0.09264005852219943, "ce": 0.30873803627449087}, {"step": 416, "kl": 0.11913652855140165, "ce": 0.31811688047074094}, {"step": 417, "kl": 0.09558679627562365, "ce": 0.3361470414580201}, {"step": 418, "kl": 0.10570845107158089, "ce": 0.3380856178754371}, {"step": 419, "kl": 0.09910385488930923, "ce": 0.3507248203911333}, {"step": 420, "kl": 0.09707248983731837, "ce": 0.3616951767560481}, {"step": 421, "kl": 0.08114407898117322, "ce": 0.31887314641019954}, {"step": 422, "kl": 0.08669563505865764, "ce": 0.3397613344105121}, {"step": 423, "kl": 0.08190962757012457, "ce": 0.3098711713628218}, {"step": 424, "kl": 0.08460962659869888, "ce": 0.2694936383893964}, {"step": 425, "kl": 0.08577144611128068, "ce": 0.32886106410088917}, {"step": 426, "kl": 0.09080075138099943, "ce": 0.3368584386737119}, {"step": 427, "kl": 0.12236324163218634, "ce": 0.32403420834979746}, {"step": 428, "kl": 0.0836882422894593, "ce": 0.2889698182423669}, {"step": 429, "kl": 0.1004065925442192, "ce": 0.39014110062621926}, {"step": 430, "kl": 0.09943895839793795, "ce": 0.37412250073947656}, {"step": 431, "kl": 0.09412488420724664, "ce": 0.3025398335214389}, {"step": 432, "kl": 0.08397251601312676, "ce": 0.41539499435690636}, {"step": 433, "kl": 0.09252174028951636, "ce": 0.2812687567281922}, {"step": 434, "kl": 0.08443013849400313, "ce": 0.33581957443380805}, {"step": 435, "kl": 0.10632995043815853, "ce": 0.3292202310682137}, {"step": 436, "kl": 0.11674866165167101, "ce": 0.39914549728685556}, {"step": 437, "kl": 0.10175276694791113, "ce": 0.32377611177396715}, {"step": 438, "kl": 0.10023571724255839, "ce": 0.3688508562405467}, {"step": 439, "kl": 0.10409627839154924, "ce": 0.3345383569289461}, {"step": 440, "kl": 0.08126031844748047, "ce": 0.3351580145473658}, {"step": 441, "kl": 0.082929628163545, "ce": 0.313975667624638}, {"step": 442, "kl": 0.08634969703417464, "ce": 0.3330702232773078}, {"step": 443, "kl": 0.0871830817845592, "ce": 0.3316130689832899}, {"step": 444, "kl": 0.07199744825338994, "ce": 0.2783227145576781}, {"step": 445, "kl": 0.08591523424989204, "ce": 0.2945910659708917}, {"step": 446, "kl": 0.07620742727438441, "ce": 0.3803950790650685}, {"step": 447, "kl": 0.09597993503859278, "ce": 0.32931097599366815}, {"step": 448, "kl": 0.0928373722841177, "ce": 0.32155251940821167}, {"step": 449, "kl": 0.09129322357817528, "ce": 0.35798371213486885}, {"step": 450, "kl": 0.10350949583596139, "ce": 0.2833557968999904}, {"step": 451, "kl": 0.10478269737739662, "ce": 0.35862182850128504}, {"step": 452, "kl": 0.08468335149001008, "ce": 0.2875798706202626}, {"step": 453, "kl": 0.0816858725541724, "ce": 0.3200149949501427}, {"step": 454, "kl": 0.08616782247021212, "ce": 0.26576529948093675}, {"step": 455, "kl": 0.09436497396209735, "ce": 0.3071331584800632}, {"step": 456, "kl": 0.11122278869596482, "ce": 0.33473105644051226}, {"step": 457, "kl": 0.10331399004463804, "ce": 0.35301805059426383}, {"step": 458, "kl": 0.09917168114338608, "ce": 0.3183940122656265}, {"step": 459, "kl": 0.11300363471588074, "ce": 0.40719843559046437}, {"step": 460, "kl": 0.10654482230529173, "ce": 0.36983154021410075}, {"step": 461, "kl": 0.10682094509887999, "ce": 0.3019593420545069}, {"step": 462, "kl": 0.056045186719414906, "ce": 0.3151056975453983}, {"step": 463, "kl": 0.056395559004119786, "ce": 0.30574378753319764}, {"step": 464, "kl": 0.0644549634219346, "ce": 0.373885872667667}, {"step": 465, "kl": 0.06467719860282076, "ce": 0.3071261830596797}, {"step": 466, "kl": 0.059704134996352014, "ce": 0.3403576698604322}, {"step": 467, "kl": 0.055356800962044136, "ce": 0.3408681605499757}, {"step": 468, "kl": 0.07006563516655541, "ce": 0.3373229771307803}, {"step": 469, "kl": 0.04609579011563423, "ce": 0.27238661440689793}, {"step": 470, "kl": 0.048412765318533446, "ce": 0.28938791962430693}, {"step": 471, "kl": 0.05521197999853239, "ce": 0.3457162676542624}, {"step": 472, "kl": 0.047625051628071846, "ce": 0.32784904261766845}, {"step": 473, "kl": 0.0510730480826311, "ce": 0.3008060414239761}, {"step": 474, "kl": 0.05196189589126094, "ce": 0.30138841446638814}, {"step": 475, "kl": 0.05690150905971879, "ce": 0.3379199874647377}, {"step": 476, "kl": 0.05542240620353327, "ce": 0.2926566811714793}, {"step": 477, "kl": 0.05712163930144428, "ce": 0.33934072964661194}, {"step": 478, "kl": 0.057558104288421286, "ce": 0.3004207422308116}, {"step": 479, "kl": 0.058279141930856794, "ce": 0.3382802121873117}, {"step": 480, "kl": 0.049936859190612845, "ce": 0.2886750440763551}, {"step": 481, "kl": 0.053404295447757225, "ce": 0.2839889502567829}, {"step": 482, "kl": 0.04751715929903222, "ce": 0.27905678491714075}, {"step": 483, "kl": 0.05140062162540103, "ce": 0.33660081216505355}, {"step": 484, "kl": 0.06046617739136596, "ce": 0.34111347492688027}, {"step": 485, "kl": 0.0586139651256449, "ce": 0.31032395904812954}, {"step": 486, "kl": 0.048847752600616565, "ce": 0.30064714403445336}, {"step": 487, "kl": 0.05760829661801355, "ce": 0.31536862541305}, {"step": 488, "kl": 0.04996436768977338, "ce": 0.3228484965123268}, {"step": 489, "kl": 0.05922603763569063, "ce": 0.26417579118530404}, {"step": 490, "kl": 0.06401676861575147, "ce": 0.33985996106400357}, {"step": 491, "kl": 0.061138778256020515, "ce": 0.3609388044768688}, {"step": 492, "kl": 0.058953193771440045, "ce": 0.3193949179399806}, {"step": 493, "kl": 0.05883288203397604, "ce": 0.34355691164092605}, {"step": 494, "kl": 0.04422878195714055, "ce": 0.320351083669903}, {"step": 495, "kl": 0.062103626404251086, "ce": 0.3094797971538122}, {"step": 496, "kl": 0.04337742488762549, "ce": 0.3152322951753641}, {"step": 497, "kl": 0.05037876689322169, "ce": 0.30604539638075035}, {"step": 498, "kl": 0.04897883869725122, "ce": 0.3142480715991621}, {"step": 499, "kl": 0.046841765365839116, "ce": 0.32349026879267906}, {"step": 500, "kl": 0.04606614246418168, "ce": 0.3153131270229667}, {"step": 501, "kl": 0.06464719982225703, "ce": 0.2978942418153597}, {"step": 502, "kl": 0.06457367683564566, "ce": 0.3259228896384354}, {"step": 503, "kl": 0.0520830274312927, "ce": 0.3066060541082382}, {"step": 504, "kl": 0.052474132001333565, "ce": 0.31441459579922804}, {"step": 505, "kl": 0.05554698890577521, "ce": 0.37269550671696516}, {"step": 506, "kl": 0.055886102371572544, "ce": 0.3284855570201083}, {"step": 507, "kl": 0.044565776117463464, "ce": 0.2784914220942155}, {"step": 508, "kl": 0.048261377962289825, "ce": 0.2970024706573418}, {"step": 509, "kl": 0.0667054397868842, "ce": 0.34874801222064716}, {"step": 510, "kl": 0.05457412197548208, "ce": 0.30120104187404534}, {"step": 511, "kl": 0.05733861428935354, "ce": 0.299742081962412}, {"step": 512, "kl": 0.05425028199619318, "ce": 0.31940427227378715}, {"step": 513, "kl": 0.05056821633326379, "ce": 0.247879342611799}, {"step": 514, "kl": 0.05041926241221323, "ce": 0.31934737239236616}, {"step": 515, "kl": 0.059529357867820994, "ce": 0.3674477577769031}, {"step": 516, "kl": 0.06083777519268806, "ce": 0.3397366110123271}, {"step": 517, "kl": 0.05587658348153674, "ce": 0.32470856861385056}, {"step": 518, "kl": 0.04357446151406758, "ce": 0.29847190902376713}, {"step": 519, "kl": 0.05809645611456875, "ce": 0.333192351942643}, {"step": 520, "kl": 0.04840535774539467, "ce": 0.26854951381683345}, {"step": 521, "kl": 0.06240338356962696, "ce": 0.32957320950111946}, {"step": 522, "kl": 0.05478419994805206, "ce": 0.34287091570212314}, {"step": 523, "kl": 0.058593284877227626, "ce": 0.3352771720204904}, {"step": 524, "kl": 0.04946697998794588, "ce": 0.3467391287160362}, {"step": 525, "kl": 0.05698229269850799, "ce": 0.35076654028627835}, {"step": 526, "kl": 0.051823983517341424, "ce": 0.29285347527283206}, {"step": 527, "kl": 0.060483598209996076, "ce": 0.33626704644719396}, {"step": 528, "kl": 0.06881469588159402, "ce": 0.35953784701391756}, {"step": 529, "kl": 0.05575277218569538, "ce": 0.3083502061271375}, {"step": 530, "kl": 0.0548648400902826, "ce": 0.3219685041404139}, {"step": 531, "kl": 0.06570942105982415, "ce": 0.32824165698290547}, {"step": 532, "kl": 0.05221931928328406, "ce": 0.26141734928099114}, {"step": 533, "kl": 0.06668631426525799, "ce": 0.30874727303604355}, {"step": 534, "kl": 0.05015952855782031, "ce": 0.3164993319981058}, {"step": 535, "kl": 0.06319979567133235, "ce": 0.39082378046977273}, {"step": 536, "kl": 0.0528208974516148, "ce": 0.31286869192711725}, {"step": 537, "kl": 0.05212966158246517, "ce": 0.35160204709231196}, {"step": 538, "kl": 0.053126468505089584, "ce": 0.32019029691951856}, {"step": 539, "kl": 0.05459431321493531, "ce": 0.37755254005899236}, {"step": 540, "kl": 0.0441930969835321, "ce": 0.3045332609001996}, {"step": 541, "kl": 0.057380807413547126, "ce": 0.3283572142753167}, {"step": 542, "kl": 0.05267978857641351, "ce": 0.3208210249487617}, {"step": 543, "kl": 0.06149843177733247, "ce": 0.36247782083992536}, {"step": 544, "kl": 0.058147135568817454, "ce": 0.323143876075553}, {"step": 545, "kl": 0.046961240656032945, "ce": 0.32429138924958334}, {"step": 546, "kl": 0.07232147641781057, "ce": 0.3401345767674967}, {"step": 547, "kl": 0.054308529447957964, "ce": 0.27248407594489515}, {"step": 548, "kl": 0.05388831487600354, "ce": 0.3051491719257982}, {"step": 549, "kl": 0.05275493856881057, "ce": 0.33575153075643516}, {"step": 550, "kl": 0.06012188008989821, "ce": 0.3143578929580944}, {"step": 551, "kl": 0.04587339500246299, "ce": 0.2781134581426239}, {"step": 552, "kl": 0.04478453349294501, "ce": 0.3486247337375117}, {"step": 553, "kl": 0.05340266699493219, "ce": 0.3728499902892565}, {"step": 554, "kl": 0.07413014964542776, "ce": 0.3600607125049917}, {"step": 555, "kl": 0.04936145716199806, "ce": 0.32144267065786924}, {"step": 556, "kl": 0.05865487852784032, "ce": 0.318961154528519}, {"step": 557, "kl": 0.059459185240813756, "ce": 0.2924611356940025}, {"step": 558, "kl": 0.05439259130803365, "ce": 0.30912070299910327}, {"step": 559, "kl": 0.054167622596073134, "ce": 0.3023834960035692}, {"step": 560, "kl": 0.06399220161454416, "ce": 0.3795269069899551}, {"step": 561, "kl": 0.04400997648411747, "ce": 0.3315479929297984}, {"step": 562, "kl": 0.054522418159520886, "ce": 0.3438423720400643}, {"step": 563, "kl": 0.05497477564286664, "ce": 0.3600872404103027}, {"step": 564, "kl": 0.05070807855185446, "ce": 0.2859020685365239}, {"step": 565, "kl": 0.053571904013173674, "ce": 0.3238037192055285}, {"step": 566, "kl": 0.06176841525153931, "ce": 0.33506132056317295}, {"step": 567, "kl": 0.04264676828300319, "ce": 0.2767905335337248}, {"step": 568, "kl": 0.0537750742426797, "ce": 0.40904082444221274}, {"step": 569, "kl": 0.056099845767095556, "ce": 0.27128655202548674}, {"step": 570, "kl": 0.05625536813057415, "ce": 0.3198193839036251}, {"step": 571, "kl": 0.07890195657912277, "ce": 0.33670777396744805}, {"step": 572, "kl": 0.06614015842396626, "ce": 0.32244785169988754}, {"step": 573, "kl": 0.04865160226462414, "ce": 0.3148856177074318}, {"step": 574, "kl": 0.044945659974695, "ce": 0.3139583122273799}, {"step": 575, "kl": 0.0581788324475906, "ce": 0.36834317143130757}, {"step": 576, "kl": 0.04563554078137733, "ce": 0.3657157339155674}, {"step": 577, "kl": 0.051919978799171825, "ce": 0.3266124766701001}, {"step": 578, "kl": 0.053432718773639434, "ce": 0.3188589392724451}, {"step": 579, "kl": 0.048151195185502836, "ce": 0.3338196936098722}, {"step": 580, "kl": 0.04472567847735072, "ce": 0.296406375378318}, {"step": 581, "kl": 0.05133640065212185, "ce": 0.3608365984105352}, {"step": 582, "kl": 0.04511005940162338, "ce": 0.2962299551677888}, {"step": 583, "kl": 0.053953311556795135, "ce": 0.3832145214677603}, {"step": 584, "kl": 0.06530739834974603, "ce": 0.3838050466446883}, {"step": 585, "kl": 0.050303068587194744, "ce": 0.30999962436696876}, {"step": 586, "kl": 0.057632748270777245, "ce": 0.3407623805635492}, {"step": 587, "kl": 0.05093634558584026, "ce": 0.3235898441653714}, {"step": 588, "kl": 0.05521235992296233, "ce": 0.3109181951654072}, {"step": 589, "kl": 0.049598516157381416, "ce": 0.3160426132387149}, {"step": 590, "kl": 0.050408697889925635, "ce": 0.2812263989130287}, {"step": 591, "kl": 0.06937152099678633, "ce": 0.3704694704166469}, {"step": 592, "kl": 0.05378412654668964, "ce": 0.33635775765707326}, {"step": 593, "kl": 0.050377174953963565, "ce": 0.3103217196376706}, {"step": 594, "kl": 0.06205356487570712, "ce": 0.3921217920457549}, {"step": 595, "kl": 0.06341793503865456, "ce": 0.31381813835176786}, {"step": 596, "kl": 0.05224708414359974, "ce": 0.3367623343361705}, {"step": 597, "kl": 0.054692882274449205, "ce": 0.30407772407007916}, {"step": 598, "kl": 0.04621910002375623, "ce": 0.26868703538690053}, {"step": 599, "kl": 0.06011831304783818, "ce": 0.3143825605831791}, {"step": 600, "kl": 0.04859948469006495, "ce": 0.2925469721224825}, {"step": 601, "kl": 0.04798256891109487, "ce": 0.3374276866465864}, {"step": 602, "kl": 0.05026837077501992, "ce": 0.29619219396021457}, {"step": 603, "kl": 0.05415970799441286, "ce": 0.3155207439861466}, {"step": 604, "kl": 0.046382558864387496, "ce": 0.33398347332825723}, {"step": 605, "kl": 0.05759074490451249, "ce": 0.3857994087663278}, {"step": 606, "kl": 0.04532488497075307, "ce": 0.29795704492774305}, {"step": 607, "kl": 0.06167258770656543, "ce": 0.30157756612758446}, {"step": 608, "kl": 0.04749748778006956, "ce": 0.37729005098299173}, {"step": 609, "kl": 0.05985986940576171, "ce": 0.277093146576443}, {"step": 610, "kl": 0.05312805736364546, "ce": 0.3353129219002931}, {"step": 611, "kl": 0.05256824713891072, "ce": 0.35443893676338245}, {"step": 612, "kl": 0.04806670821290293, "ce": 0.2970476008242866}, {"step": 613, "kl": 0.04697261466150698, "ce": 0.3084857397187944}, {"step": 614, "kl": 0.0521284124016507, "ce": 0.36192566425996364}, {"step": 615, "kl": 0.05437620080800053, "ce": 0.33900238118073195}, {"step": 616, "kl": 0.046162508774685466, "ce": 0.3020824910604013}, {"step": 617, "kl": 0.042039755926808704, "ce": 0.3012168857575205}, {"step": 618, "kl": 0.05654611159453757, "ce": 0.3632588836049417}, {"step": 619, "kl": 0.04849953001333175, "ce": 0.26105758285107367}, {"step": 620, "kl": 0.05615628423909477, "ce": 0.3542010591492404}, {"step": 621, "kl": 0.05700243737008475, "ce": 0.3266127011533293}, {"step": 622, "kl": 0.048998627075151596, "ce": 0.3171919016414585}, {"step": 623, "kl": 0.050720545493639434, "ce": 0.312925078684508}, {"step": 624, "kl": 0.05328788450844553, "ce": 0.2966452918575451}, {"step": 625, "kl": 0.066610285973726, "ce": 0.355584316554178}, {"step": 626, "kl": 0.04612916133893761, "ce": 0.36632529819902515}, {"step": 627, "kl": 0.05433166810934555, "ce": 0.34344847580104093}, {"step": 628, "kl": 0.05239729665978351, "ce": 0.3007977042559976}, {"step": 629, "kl": 0.05367302414299435, "ce": 0.4054239193416068}, {"step": 630, "kl": 0.05238971651671633, "ce": 0.3360627598896439}, {"step": 631, "kl": 0.05133775343532794, "ce": 0.3243138664161441}, {"step": 632, "kl": 0.04167772343509086, "ce": 0.30531092564252216}, {"step": 633, "kl": 0.05320055011891456, "ce": 0.3582687950467148}, {"step": 634, "kl": 0.044546778602441446, "ce": 0.2640985612287539}, {"step": 635, "kl": 0.05565756226933054, "ce": 0.3099057852918146}, {"step": 636, "kl": 0.05492435610685968, "ce": 0.28182445886109697}, {"step": 637, "kl": 0.05561741497309817, "ce": 0.2904348403664451}, {"step": 638, "kl": 0.0522476954378489, "ce": 0.37083570994021436}, {"step": 639, "kl": 0.060306738411702435, "ce": 0.34643394687808987}, {"step": 640, "kl": 0.05074715011432938, "ce": 0.3800479683824765}, {"step": 641, "kl": 0.05385578260509413, "ce": 0.3174948533145368}, {"step": 642, "kl": 0.04745670970467067, "ce": 0.3039253571331826}, {"step": 643, "kl": 0.046746062169867486, "ce": 0.30172572041756374}, {"step": 644, "kl": 0.05363140251555929, "ce": 0.34129714149842283}, {"step": 645, "kl": 0.049386581185050876, "ce": 0.3206879749849572}, {"step": 646, "kl": 0.04779842503440437, "ce": 0.37212756313855133}, {"step": 647, "kl": 0.056448923182816246, "ce": 0.3239199643517571}, {"step": 648, "kl": 0.04708637152416695, "ce": 0.3331177646661474}, {"step": 649, "kl": 0.046328919711070254, "ce": 0.2766759993581727}, {"step": 650, "kl": 0.052847487091900916, "ce": 0.3190126916493365}, {"step": 651, "kl": 0.04481343932101793, "ce": 0.3051639707404905}, {"step": 652, "kl": 0.05281227845360877, "ce": 0.3012923885692847}, {"step": 653, "kl": 0.07038840325343394, "ce": 0.3708534093362836}, {"step": 654, "kl": 0.058301059736687824, "ce": 0.3257606199535543}, {"step": 655, "kl": 0.05999904553465197, "ce": 0.33267454185398493}, {"step": 656, "kl": 0.04594685045397428, "ce": 0.339638167605401}, {"step": 657, "kl": 0.05108538578925685, "ce": 0.34159551930223775}, {"step": 658, "kl": 0.05168780194029959, "ce": 0.3481216681493472}, {"step": 659, "kl": 0.04806309413477951, "ce": 0.2841179307251934}, {"step": 660, "kl": 0.05020869558539072, "ce": 0.30453262905936007}, {"step": 661, "kl": 0.059841137311333885, "ce": 0.3109471438613157}, {"step": 662, "kl": 0.06006565762624012, "ce": 0.36138548926182856}, {"step": 663, "kl": 0.05600696542024579, "ce": 0.3635095983302228}, {"step": 664, "kl": 0.05286987711122763, "ce": 0.3073604224126351}, {"step": 665, "kl": 0.060109711881289704, "ce": 0.34456109082072345}, {"step": 666, "kl": 0.04819908004011647, "ce": 0.2913196995265965}, {"step": 667, "kl": 0.05328503691252927, "ce": 0.36597614878761014}, {"step": 668, "kl": 0.05052735026525998, "ce": 0.3244550964030885}, {"step": 669, "kl": 0.05527541529873702, "ce": 0.3573198986999013}, {"step": 670, "kl": 0.043262173213884, "ce": 0.2982358695483263}, {"step": 671, "kl": 0.042122979902937834, "ce": 0.33162115621987104}, {"step": 672, "kl": 0.05409758918371984, "ce": 0.32671586185896484}, {"step": 673, "kl": 0.055076877450960474, "ce": 0.3102612380869882}, {"step": 674, "kl": 0.055072696296133934, "ce": 0.37612571299259356}, {"step": 675, "kl": 0.06402785593118217, "ce": 0.31720904641023573}, {"step": 676, "kl": 0.06357569195560238, "ce": 0.3302519956526466}, {"step": 677, "kl": 0.04951221191563623, "ce": 0.28997042686669644}, {"step": 678, "kl": 0.051941074446178896, "ce": 0.32262881007097616}, {"step": 679, "kl": 0.047815721597986804, "ce": 0.32632061640421545}, {"step": 680, "kl": 0.05842780531487039, "ce": 0.31938575792164076}, {"step": 681, "kl": 0.05355448217512811, "ce": 0.32618665423113274}, {"step": 682, "kl": 0.05552642076314021, "ce": 0.31294529880615196}, {"step": 683, "kl": 0.054036618019483104, "ce": 0.39200059400623427}, {"step": 684, "kl": 0.05869729262824415, "ce": 0.31344937390350225}, {"step": 685, "kl": 0.05064526114822084, "ce": 0.2760710051174599}, {"step": 686, "kl": 0.05546018199352368, "ce": 0.2972024359086354}, {"step": 687, "kl": 0.061744848130056394, "ce": 0.337372838696347}, {"step": 688, "kl": 0.06158412105682024, "ce": 0.31516139971963786}, {"step": 689, "kl": 0.0647452512273082, "ce": 0.3738146173713584}, {"step": 690, "kl": 0.04600421939801832, "ce": 0.36263301838659817}, {"step": 691, "kl": 0.05744577056462432, "ce": 0.30057878984812064}, {"step": 692, "kl": 0.050579796812915606, "ce": 0.2870610414215215}, {"step": 693, "kl": 0.05496853961928921, "ce": 0.3230809165262799}, {"step": 694, "kl": 0.04792100989588683, "ce": 0.25429936387993674}, {"step": 695, "kl": 0.04008565924256768, "ce": 0.29054677970969034}, {"step": 696, "kl": 0.06809130964830379, "ce": 0.33610513533464975}, {"step": 697, "kl": 0.04849580485817085, "ce": 0.28255880871479255}, {"step": 698, "kl": 0.059129474001636456, "ce": 0.36236352361387386}, {"step": 699, "kl": 0.06433687427127953, "ce": 0.35403959814254227}, {"step": 700, "kl": 0.05884839884183926, "ce": 0.3514931799678263}, {"step": 701, "kl": 0.06008149340044256, "ce": 0.3450743329697761}, {"step": 702, "kl": 0.04401004414199867, "ce": 0.26935640897787394}, {"step": 703, "kl": 0.05062701412888548, "ce": 0.2996940223273166}, {"step": 704, "kl": 0.05171249411967192, "ce": 0.3304621238481669}, {"step": 705, "kl": 0.0582553839025087, "ce": 0.3628457130455389}, {"step": 706, "kl": 0.052484163657923716, "ce": 0.3055116636850032}, {"step": 707, "kl": 0.05474728823891042, "ce": 0.3565616261783014}, {"step": 708, "kl": 0.05922662094053963, "ce": 0.32263703971776836}, {"step": 709, "kl": 0.05963586128529805, "ce": 0.32990568176773954}, {"step": 710, "kl": 0.04631813950984206, "ce": 0.2918947014171407}, {"step": 711, "kl": 0.05804541744055505, "ce": 0.33256747445906243}, {"step": 712, "kl": 0.06172053143088048, "ce": 0.3187400666240868}, {"step": 713, "kl": 0.04506236003653011, "ce": 0.32660413006697625}, {"step": 714, "kl": 0.04599955326908034, "ce": 0.32559752453758917}, {"step": 715, "kl": 0.051967927201830605, "ce": 0.3030559254577426}, {"step": 716, "kl": 0.049366304832806726, "ce": 0.3326452267271614}, {"step": 717, "kl": 0.054440413709023625, "ce": 0.3105120455341349}, {"step": 718, "kl": 0.046573128651759346, "ce": 0.2792996556590737}, {"step": 719, "kl": 0.05255331361944525, "ce": 0.3587871016259414}, {"step": 720, "kl": 0.06758550180313579, "ce": 0.4019799189333909}, {"step": 721, "kl": 0.056343430192104416, "ce": 0.3361677700405451}, {"step": 722, "kl": 0.044299505553876004, "ce": 0.30423667534453763}, {"step": 723, "kl": 0.05199862383151632, "ce": 0.3508791580002267}, {"step": 724, "kl": 0.05451300330318465, "ce": 0.35473686086720435}, {"step": 725, "kl": 0.0534293052354857, "ce": 0.34282826808440503}, {"step": 726, "kl": 0.053079909441371025, "ce": 0.3098291380092711}, {"step": 727, "kl": 0.05189694630887596, "ce": 0.3083398350070107}, {"step": 728, "kl": 0.05453845909578306, "ce": 0.31611566262051627}, {"step": 729, "kl": 0.052266669263539366, "ce": 0.3461821048734619}, {"step": 730, "kl": 0.05173604291019172, "ce": 0.2775477026523063}, {"step": 731, "kl": 0.05586542256072426, "ce": 0.3548073882683004}, {"step": 732, "kl": 0.05320618807306724, "ce": 0.339176375528073}, {"step": 733, "kl": 0.052171884828988234, "ce": 0.3521109399675755}, {"step": 734, "kl": 0.060393390890629894, "ce": 0.35289062833287893}, {"step": 735, "kl": 0.05572711079989494, "ce": 0.3551055847808434}, {"step": 736, "kl": 0.04331072414233552, "ce": 0.3053794696566876}, {"step": 737, "kl": 0.05303583983169441, "ce": 0.3313141836839563}, {"step": 738, "kl": 0.04958303650407987, "ce": 0.31399151330045666}, {"step": 739, "kl": 0.05101375893592835, "ce": 0.2858883600511986}, {"step": 740, "kl": 0.05953175276517868, "ce": 0.3960787414388794}, {"step": 741, "kl": 0.04046573906151356, "ce": 0.30271153993151034}, {"step": 742, "kl": 0.05915564271429054, "ce": 0.3456278093351434}, {"step": 743, "kl": 0.04689920316768598, "ce": 0.3272243069834701}, {"step": 744, "kl": 0.05434623561446887, "ce": 0.2991853683805142}, {"step": 745, "kl": 0.04747948292956881, "ce": 0.32947362855423323}, {"step": 746, "kl": 0.05551514455666846, "ce": 0.32012873138421327}, {"step": 747, "kl": 0.05809824233202591, "ce": 0.2666562306398601}, {"step": 748, "kl": 0.05056175257958748, "ce": 0.31209729740709113}, {"step": 749, "kl": 0.05344289397366058, "ce": 0.3521949291463796}, {"step": 750, "kl": 0.05362266626741206, "ce": 0.31427813605839255}, {"step": 751, "kl": 0.05780015962872499, "ce": 0.33115018387915385}, {"step": 752, "kl": 0.045740341664479926, "ce": 0.3229622370206723}, {"step": 753, "kl": 0.05414123397371816, "ce": 0.33261896199635405}, {"step": 754, "kl": 0.049244029653478856, "ce": 0.294243559111539}, {"step": 755, "kl": 0.05030004001492105, "ce": 0.33170484313913184}, {"step": 756, "kl": 0.04488263094653894, "ce": 0.3317900268655074}, {"step": 757, "kl": 0.046973689129210836, "ce": 0.3118905556371964}, {"step": 758, "kl": 0.04209173360905373, "ce": 0.3325722950800706}, {"step": 759, "kl": 0.04907361439520813, "ce": 0.3160186376251108}, {"step": 760, "kl": 0.06716435138533369, "ce": 0.30591607987985164}, {"step": 761, "kl": 0.055796702450133406, "ce": 0.29550238308376736}, {"step": 762, "kl": 0.05581214875314535, "ce": 0.29345270175487903}, {"step": 763, "kl": 0.05000502532245694, "ce": 0.3024442995722077}, {"step": 764, "kl": 0.05543068573499146, "ce": 0.33525377718743726}, {"step": 765, "kl": 0.056884865023468775, "ce": 0.33683198162732664}, {"step": 766, "kl": 0.050775220865837495, "ce": 0.33561068211998746}, {"step": 767, "kl": 0.05314908578314219, "ce": 0.33210905848131084}, {"step": 768, "kl": 0.04268437433384229, "ce": 0.33609069556967225}, {"step": 769, "kl": 0.04931241907455624, "ce": 0.3030261976338679}, {"step": 770, "kl": 0.04452548102174007, "ce": 0.3008706120744323}, {"step": 771, "kl": 0.06224841190702271, "ce": 0.36755790888507994}, {"step": 772, "kl": 0.04494906478943449, "ce": 0.32010012256855863}, {"step": 773, "kl": 0.04058649775458944, "ce": 0.2947806601702776}, {"step": 774, "kl": 0.057202220199069426, "ce": 0.3331547760290295}, {"step": 775, "kl": 0.039623615243113953, "ce": 0.3096713779634489}, {"step": 776, "kl": 0.0643243784035267, "ce": 0.32284791034431115}, {"step": 777, "kl": 0.04425219380195743, "ce": 0.3079643577657721}, {"step": 778, "kl": 0.05157909595515973, "ce": 0.32515295758058066}, {"step": 779, "kl": 0.050685815524259804, "ce": 0.36104705866696973}, {"step": 780, "kl": 0.05553454462515142, "ce": 0.3208393571956413}, {"step": 781, "kl": 0.05000448200902548, "ce": 0.33108178721178294}, {"step": 782, "kl": 0.046492123786409885, "ce": 0.2680351077501956}, {"step": 783, "kl": 0.05061451799020281, "ce": 0.34497361022270534}, {"step": 784, "kl": 0.03749280018934859, "ce": 0.273992255000837}, {"step": 785, "kl": 0.05378193921586787, "ce": 0.35044227633220937}, {"step": 786, "kl": 0.05442306318318138, "ce": 0.2924611183449074}, {"step": 787, "kl": 0.0415603051595447, "ce": 0.28512936378574383}, {"step": 788, "kl": 0.055153720665560436, "ce": 0.28138836256065436}, {"step": 789, "kl": 0.04570914920727294, "ce": 0.26760054132671307}, {"step": 790, "kl": 0.05240326798176623, "ce": 0.3084378156545099}, {"step": 791, "kl": 0.05727022878896942, "ce": 0.3392641218975129}, {"step": 792, "kl": 0.04219447563674143, "ce": 0.27436240476863916}, {"step": 793, "kl": 0.05982341772334966, "ce": 0.37765645971642037}, {"step": 794, "kl": 0.047392705962313736, "ce": 0.3546582785639148}, {"step": 795, "kl": 0.054330832457027176, "ce": 0.30941928715634553}, {"step": 796, "kl": 0.059992322382258184, "ce": 0.3107234073844919}, {"step": 797, "kl": 0.05034260252417575, "ce": 0.29981983473779705}, {"step": 798, "kl": 0.05114300736183202, "ce": 0.30414447157554475}, {"step": 799, "kl": 0.04541770113433828, "ce": 0.32750045044177195}, {"step": 800, "kl": 0.053930554837519726, "ce": 0.3246061102118235}, {"step": 801, "kl": 0.04976753780512467, "ce": 0.30308593975831427}, {"step": 802, "kl": 0.046956963675521046, "ce": 0.31992462852368764}, {"step": 803, "kl": 0.04576652369302265, "ce": 0.34019945969471604}, {"step": 804, "kl": 0.06313872297956952, "ce": 0.3596031674201693}, {"step": 805, "kl": 0.04803996420766257, "ce": 0.2964731385824289}, {"step": 806, "kl": 0.05480515664061083, "ce": 0.31120234298706057}, {"step": 807, "kl": 0.0473151204038989, "ce": 0.3128266466580904}, {"step": 808, "kl": 0.07384604276195773, "ce": 0.33813683242314213}, {"step": 809, "kl": 0.05157324199018806, "ce": 0.27601664955912264}, {"step": 810, "kl": 0.06313369359421322, "ce": 0.4122480477191577}, {"step": 811, "kl": 0.05387611050296863, "ce": 0.33112150313380667}, {"step": 812, "kl": 0.0585888851806674, "ce": 0.3429013197811408}, {"step": 813, "kl": 0.04950161328374064, "ce": 0.24866342377478876}, {"step": 814, "kl": 0.045588566839845066, "ce": 0.3201413893664114}, {"step": 815, "kl": 0.06329911955628865, "ce": 0.33942008814817803}, {"step": 816, "kl": 0.05862276887845657, "ce": 0.30069411197668394}, {"step": 817, "kl": 0.04859612756375396, "ce": 0.31252129683643876}, {"step": 818, "kl": 0.05056229833667227, "ce": 0.2881310376328286}, {"step": 819, "kl": 0.06167883410060839, "ce": 0.35761099550973513}, {"step": 820, "kl": 0.06658513862400252, "ce": 0.3210420374804746}, {"step": 821, "kl": 0.04664540234666166, "ce": 0.3326604879439181}, {"step": 822, "kl": 0.05194089912265711, "ce": 0.37689663394846745}, {"step": 823, "kl": 0.047640389135390086, "ce": 0.3287055135394694}, {"step": 824, "kl": 0.049795175763528265, "ce": 0.2787925342943591}, {"step": 825, "kl": 0.062247376717688964, "ce": 0.3254733469294406}, {"step": 826, "kl": 0.043457281707102904, "ce": 0.27977099039008985}, {"step": 827, "kl": 0.045330464356942025, "ce": 0.3221840960493101}, {"step": 828, "kl": 0.05551492705310084, "ce": 0.3361930649948778}, {"step": 829, "kl": 0.052160328655828966, "ce": 0.2845979089468298}, {"step": 830, "kl": 0.048480808828208315, "ce": 0.3160913198991099}, {"step": 831, "kl": 0.05216508274550695, "ce": 0.3580946230285865}, {"step": 832, "kl": 0.04924209629440249, "ce": 0.3521802670722901}, {"step": 833, "kl": 0.05623367752006327, "ce": 0.3169176185270932}, {"step": 834, "kl": 0.06557345437554, "ce": 0.3158794028650104}, {"step": 835, "kl": 0.04918089809864665, "ce": 0.29579288119828484}, {"step": 836, "kl": 0.04328318946353117, "ce": 0.2819887500011783}, {"step": 837, "kl": 0.05246805694845544, "ce": 0.3378620230423487}, {"step": 838, "kl": 0.04526770697757037, "ce": 0.31086450414454686}, {"step": 839, "kl": 0.04579083660845633, "ce": 0.22871107680035885}, {"step": 840, "kl": 0.049223866490769465, "ce": 0.3521861650333848}, {"step": 841, "kl": 0.04628885869841297, "ce": 0.35375324765285115}, {"step": 842, "kl": 0.05080235554594985, "ce": 0.365936560951984}, {"step": 843, "kl": 0.045824848751694264, "ce": 0.315877571113102}, {"step": 844, "kl": 0.07165869395867165, "ce": 0.32768856820016273}, {"step": 845, "kl": 0.05950447062898221, "ce": 0.3572349346572884}, {"step": 846, "kl": 0.047526072705631424, "ce": 0.3340889875465464}, {"step": 847, "kl": 0.050886308046811685, "ce": 0.3200706752888042}, {"step": 848, "kl": 0.06260123075230267, "ce": 0.3100018976132827}, {"step": 849, "kl": 0.05765324149172749, "ce": 0.2974886000813323}, {"step": 850, "kl": 0.05379567072816091, "ce": 0.3249477955547935}, {"step": 851, "kl": 0.05383058621609375, "ce": 0.3971654027749814}, {"step": 852, "kl": 0.052381827977943184, "ce": 0.35920410430935673}, {"step": 853, "kl": 0.05331720572960035, "ce": 0.3192294874584661}, {"step": 854, "kl": 0.05757689571897947, "ce": 0.2968836268440622}, {"step": 855, "kl": 0.05445802379041234, "ce": 0.3242510447816654}, {"step": 856, "kl": 0.04591209581680713, "ce": 0.3711102821055967}, {"step": 857, "kl": 0.06091125417807368, "ce": 0.3475564683560755}, {"step": 858, "kl": 0.051188349765823885, "ce": 0.3225980714178668}, {"step": 859, "kl": 0.06198404932955821, "ce": 0.32355676660979354}, {"step": 860, "kl": 0.05513851182147354, "ce": 0.33650910247433796}, {"step": 861, "kl": 0.04471372975912782, "ce": 0.2303746006843354}, {"step": 862, "kl": 0.04985748510250371, "ce": 0.3031108401715755}, {"step": 863, "kl": 0.06218580656475956, "ce": 0.34010733442696917}, {"step": 864, "kl": 0.05220575543799073, "ce": 0.32235220563670064}, {"step": 865, "kl": 0.057346255609975055, "ce": 0.33297776067461526}, {"step": 866, "kl": 0.04572588397954172, "ce": 0.3574419680997138}, {"step": 867, "kl": 0.058437372179946656, "ce": 0.35320409620809795}, {"step": 868, "kl": 0.05250272645744835, "ce": 0.33868784568025534}, {"step": 869, "kl": 0.05048986354363872, "ce": 0.30312956756965714}, {"step": 870, "kl": 0.05771449678584549, "ce": 0.37633310936799197}, {"step": 871, "kl": 0.056186981776244385, "ce": 0.2943197722933185}, {"step": 872, "kl": 0.05277806580445035, "ce": 0.2991883400275073}, {"step": 873, "kl": 0.056832716321956175, "ce": 0.2643267389327761}, {"step": 874, "kl": 0.0471592213305252, "ce": 0.308557090398265}, {"step": 875, "kl": 0.0627457184285735, "ce": 0.36875827606662076}, {"step": 876, "kl": 0.06641689971128523, "ce": 0.35756409952600343}, {"step": 877, "kl": 0.05576600985387108, "ce": 0.32062937073233805}, {"step": 878, "kl": 0.0564749580856338, "ce": 0.3260050734262618}, {"step": 879, "kl": 0.05309306805877787, "ce": 0.29304768213349236}, {"step": 880, "kl": 0.039644743971127064, "ce": 0.2680575170470383}, {"step": 881, "kl": 0.04087490680682698, "ce": 0.3369858441011847}, {"step": 882, "kl": 0.05804759443138597, "ce": 0.3551886795085892}, {"step": 883, "kl": 0.03880350255424033, "ce": 0.30910447287789494}, {"step": 884, "kl": 0.05125792161604218, "ce": 0.30693443670372}, {"step": 885, "kl": 0.04514735393874282, "ce": 0.26233156775432126}, {"step": 886, "kl": 0.05563506163927406, "ce": 0.3558517477448589}, {"step": 887, "kl": 0.048215626930486505, "ce": 0.3169003434934693}, {"step": 888, "kl": 0.05145041463478654, "ce": 0.2758602089047334}, {"step": 889, "kl": 0.04997353254001251, "ce": 0.285693734366661}, {"step": 890, "kl": 0.03790239727125272, "ce": 0.29744267441280525}, {"step": 891, "kl": 0.05282650835999749, "ce": 0.3323846963481404}, {"step": 892, "kl": 0.05786177624904443, "ce": 0.35885812331708017}, {"step": 893, "kl": 0.03983523979934497, "ce": 0.31000685309192216}, {"step": 894, "kl": 0.039968586416406805, "ce": 0.327041232581067}, {"step": 895, "kl": 0.05258372973047369, "ce": 0.3011597503275527}, {"step": 896, "kl": 0.07009476612953014, "ce": 0.35174427168571015}, {"step": 897, "kl": 0.04764514096065693, "ce": 0.3221469721529956}, {"step": 898, "kl": 0.04720520993594841, "ce": 0.3356054856640104}, {"step": 899, "kl": 0.052659803178322126, "ce": 0.35998848902171016}, {"step": 900, "kl": 0.06086621904408542, "ce": 0.29950640977233245}, {"step": 901, "kl": 0.05566587423284848, "ce": 0.3030852222703194}, {"step": 902, "kl": 0.04168200608158673, "ce": 0.2927420603868096}, {"step": 903, "kl": 0.046647063629629046, "ce": 0.30926070893240787}, {"step": 904, "kl": 0.041206183849784535, "ce": 0.3527466220379071}, {"step": 905, "kl": 0.05835602752144114, "ce": 0.34483346669613124}, {"step": 906, "kl": 0.055057648804175796, "ce": 0.3495932582500047}, {"step": 907, "kl": 0.046241257841637136, "ce": 0.3252012466400686}, {"step": 908, "kl": 0.051306236321181, "ce": 0.3533120449822861}, {"step": 909, "kl": 0.050411875975334045, "ce": 0.28753719195513655}, {"step": 910, "kl": 0.04261185730137644, "ce": 0.32025033150419735}, {"step": 911, "kl": 0.06371122097737977, "ce": 0.3090568549909285}, {"step": 912, "kl": 0.05266954944163152, "ce": 0.3558773281661886}, {"step": 913, "kl": 0.05600774636865502, "ce": 0.3355857568992137}, {"step": 914, "kl": 0.04925353033980318, "ce": 0.3160415625351316}, {"step": 915, "kl": 0.053951135329498814, "ce": 0.3528653148227603}, {"step": 916, "kl": 0.05464271868667612, "ce": 0.3851577757534022}, {"step": 917, "kl": 0.04695978237056783, "ce": 0.30536255572770354}, {"step": 918, "kl": 0.05611481644302336, "ce": 0.3482390182721684}, {"step": 919, "kl": 0.0534930474951343, "ce": 0.31080634235296795}, {"step": 920, "kl": 0.0492849034317101, "ce": 0.3049609176019144}, {"step": 921, "kl": 0.04885681353363336, "ce": 0.3313969829353567}, {"step": 922, "kl": 0.04491233083351357, "ce": 0.27336391476173877}], "val": [{"step": 0, "math_kl": 0.15874307828215575, "math_ce": 0.6515277156879916, "code_kl": 0.14786912634071003, "code_ce": 0.30340147782401555, "math_hard_kl": 0.24940142917923272, "math_hard_ce": 0.6765219455834559}, {"step": 461, "math_kl": 0.15301356140529504, "math_ce": 0.6182141406390151, "code_kl": 0.08415913636105464, "code_ce": 0.3109867262228607, "math_hard_kl": 0.23259892678797045, "math_hard_ce": 0.6734322228526027}, {"step": 922, "math_kl": 0.16037220667035662, "math_ce": 0.6134552778130008, "code_kl": 0.07813229218058698, "code_ce": 0.3095525097758208, "math_hard_kl": 0.24713406450048658, "math_hard_ce": 0.6740036130352745}]}
|
seq_code_math_kd_only_seed1/stage1_code/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f8db3fd60297cf742eb760e9acf23c740380edb122cb5cea8827eaa6b45604
|
| 3 |
+
size 3087467144
|