Upload folder using huggingface_hub
Browse files
seq_math_code_gt_sft/run_info.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"setting": "ground truth SFT",
|
| 3 |
+
"alpha": 0.0,
|
| 4 |
+
"order": "math_code",
|
| 5 |
+
"seed": 0,
|
| 6 |
+
"exp": 2,
|
| 7 |
+
"student": "Qwen/Qwen2.5-1.5B-Instruct",
|
| 8 |
+
"gpu_student": "NVIDIA RTX A6000",
|
| 9 |
+
"gpu_teachers": "NVIDIA RTX A6000",
|
| 10 |
+
"load_h": 0.004249601562817892,
|
| 11 |
+
"stages": {
|
| 12 |
+
"stage1_math": {
|
| 13 |
+
"domain": "math",
|
| 14 |
+
"steps": 896,
|
| 15 |
+
"train_h": 3.3275934724675285,
|
| 16 |
+
"val_start": {
|
| 17 |
+
"step": 0,
|
| 18 |
+
"math_kl": 0.15910778235068246,
|
| 19 |
+
"math_ce": 0.6515277156879916,
|
| 20 |
+
"code_kl": 0.14790875576132695,
|
| 21 |
+
"code_ce": 0.30340147782401555,
|
| 22 |
+
"math_hard_kl": 0.24894053959908363,
|
| 23 |
+
"math_hard_ce": 0.6765219455834559
|
| 24 |
+
},
|
| 25 |
+
"val_end": {
|
| 26 |
+
"step": 896,
|
| 27 |
+
"math_kl": 0.25596919708371585,
|
| 28 |
+
"math_ce": 0.4875917011939159,
|
| 29 |
+
"code_kl": 0.16789859193652845,
|
| 30 |
+
"code_ce": 0.33237521285888244,
|
| 31 |
+
"math_hard_kl": 0.3207115241939215,
|
| 32 |
+
"math_hard_ce": 0.6152356422562573
|
| 33 |
+
},
|
| 34 |
+
"peak_gb_student": 36.754438400268555,
|
| 35 |
+
"peak_gb_teachers": 29.564642429351807
|
| 36 |
+
}
|
| 37 |
+
}
|
| 38 |
+
}
|
seq_math_code_gt_sft/stage1_math/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 32768,
|
| 44 |
+
"max_window_layers": 21,
|
| 45 |
+
"model_type": "qwen2",
|
| 46 |
+
"num_attention_heads": 12,
|
| 47 |
+
"num_hidden_layers": 28,
|
| 48 |
+
"num_key_value_heads": 2,
|
| 49 |
+
"pad_token_id": null,
|
| 50 |
+
"rms_norm_eps": 1e-06,
|
| 51 |
+
"rope_parameters": {
|
| 52 |
+
"rope_theta": 1000000.0,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
},
|
| 55 |
+
"sliding_window": null,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.20.2",
|
| 58 |
+
"use_cache": false,
|
| 59 |
+
"use_sliding_window": false,
|
| 60 |
+
"vocab_size": 151936
|
| 61 |
+
}
|
seq_math_code_gt_sft/stage1_math/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.20.2"
|
| 14 |
+
}
|
seq_math_code_gt_sft/stage1_math/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.09804779970805773, "ce": 0.6862866131946294}, {"step": 2, "kl": 0.12091082490251354, "ce": 0.5893331765462193}, {"step": 3, "kl": 0.15676302660761476, "ce": 0.6546971053022393}, {"step": 4, "kl": 0.2974170804991579, "ce": 0.7660050769415038}, {"step": 5, "kl": 0.3196050499094307, "ce": 0.5201391673161107}, {"step": 6, "kl": 0.15676785860610526, "ce": 0.6035062692461223}, {"step": 7, "kl": 0.10453729907217561, "ce": 0.5200720742784974}, {"step": 8, "kl": 0.26556642573657896, "ce": 0.5348809124776573}, {"step": 9, "kl": 0.1906652581286111, "ce": 0.5700116198952182}, {"step": 10, "kl": 0.09532746743372279, "ce": 0.4780790002192373}, {"step": 11, "kl": 0.1312939177290629, "ce": 0.6739146989886767}, {"step": 12, "kl": 0.8282023477631355, "ce": 0.5873922066824777}, {"step": 13, "kl": 0.2675572930592919, "ce": 0.7319670462872395}, {"step": 14, "kl": 0.9219448144826601, "ce": 0.43806911261660103}, {"step": 15, "kl": 0.10287508388430713, "ce": 0.5894921942908136}, {"step": 16, "kl": 0.32469146335195875, "ce": 0.65483653288856}, {"step": 17, "kl": 0.3100215571410523, "ce": 0.5566350900875291}, {"step": 18, "kl": 0.1126166263486461, "ce": 0.5665069121598078}, {"step": 19, "kl": 0.8598298450123774, "ce": 0.6791510359886375}, {"step": 20, "kl": 0.15713174616464584, "ce": 0.5483645753762157}, {"step": 21, "kl": 0.9278094730041601, "ce": 0.5007908304458646}, {"step": 22, "kl": 0.1529673819816897, "ce": 0.6356296439377213}, {"step": 23, "kl": 0.13562967320810007, "ce": 0.6464104223775105}, {"step": 24, "kl": 0.2964768134256557, "ce": 0.5872854681554202}, {"step": 25, "kl": 0.1530313794249015, "ce": 0.4304981254708384}, {"step": 26, "kl": 0.14567822639509498, "ce": 0.5190165949463168}, {"step": 27, "kl": 0.2197361056959928, "ce": 0.4982683537309381}, {"step": 28, "kl": 0.203567563904548, "ce": 0.4837303452873585}, {"step": 29, "kl": 0.13693488810620605, "ce": 0.5392820410739007}, {"step": 30, "kl": 0.31400441984807004, "ce": 0.6531522328148939}, {"step": 31, "kl": 0.22088888877622095, "ce": 0.6642746152124479}, {"step": 32, "kl": 0.14835822601842874, "ce": 0.5430328501217719}, {"step": 33, "kl": 0.1604149573785703, "ce": 0.5510144664139972}, {"step": 34, "kl": 0.14642375608465813, "ce": 0.4656473292948105}, {"step": 35, "kl": 0.15677808858772865, "ce": 0.4495819111386824}, {"step": 36, "kl": 0.19543088350832158, "ce": 0.5748832573894185}, {"step": 37, "kl": 0.26429683508684443, "ce": 0.6940961616606268}, {"step": 38, "kl": 0.1680706299067027, "ce": 0.6445647172140874}, {"step": 39, "kl": 0.16410724767628626, "ce": 0.4807736047552136}, {"step": 40, "kl": 0.17124877264671348, "ce": 0.5158730902193652}, {"step": 41, "kl": 0.15012094376487345, "ce": 0.4743128460983471}, {"step": 42, "kl": 0.18175390755257953, "ce": 0.52504703856584}, {"step": 43, "kl": 0.20250909874954232, "ce": 0.5980552351159348}, {"step": 44, "kl": 0.18486144369407406, "ce": 0.5252630998842043}, {"step": 45, "kl": 0.33505909512347043, "ce": 0.6105044839938658}, {"step": 46, "kl": 0.13709403782080024, "ce": 0.5015040916132639}, {"step": 47, "kl": 0.15822644940019445, "ce": 0.47718889560047856}, {"step": 48, "kl": 0.3207022974648585, "ce": 0.5198664296200273}, {"step": 49, "kl": 0.18886875476024934, "ce": 0.6511239690028378}, {"step": 50, "kl": 0.14543976107156756, "ce": 0.5608343842062271}, {"step": 51, "kl": 0.19742898091806865, "ce": 0.5459652604283514}, {"step": 52, "kl": 0.3188947930558181, "ce": 0.5588931118330873}, {"step": 53, "kl": 0.16948114730976366, "ce": 0.5209273906409579}, {"step": 54, "kl": 0.14427763585631276, "ce": 0.5826496369186576}, {"step": 55, "kl": 0.154390832697143, "ce": 0.552020074510361}, {"step": 56, "kl": 0.2820654379021309, "ce": 0.5135087425166543}, {"step": 57, "kl": 0.2536312091087492, "ce": 0.6655566063424648}, {"step": 58, "kl": 0.3029879317641895, "ce": 0.48284810055805655}, {"step": 59, "kl": 0.14428026439236272, "ce": 0.46099022047927274}, {"step": 60, "kl": 0.22309219817817696, "ce": 0.6005300536317875}, {"step": 61, "kl": 0.3595002579567431, "ce": 0.659147013844889}, {"step": 62, "kl": 0.158220670021614, "ce": 0.4913684834285277}, {"step": 63, "kl": 0.19357827799387511, "ce": 0.4306362447887345}, {"step": 64, "kl": 0.27933085903965754, "ce": 0.5632859447928082}, {"step": 65, "kl": 0.5654142321467025, "ce": 0.7213114238863235}, {"step": 66, "kl": 0.15182791270361462, "ce": 0.5610011789689886}, {"step": 67, "kl": 0.18459169951135443, "ce": 0.6959641659664731}, {"step": 68, "kl": 0.1794787466102973, "ce": 0.7004311037714818}, {"step": 69, "kl": 0.25865702187394357, "ce": 0.6526889516240227}, {"step": 70, "kl": 0.37883234981754615, "ce": 0.603496437653219}, {"step": 71, "kl": 0.24253330931727082, "ce": 0.477278533156404}, {"step": 72, "kl": 0.18587920643671763, "ce": 0.6040652531025751}, {"step": 73, "kl": 0.16079393880651954, "ce": 0.571752285901761}, {"step": 74, "kl": 0.17068553965260516, "ce": 0.6105446335365032}, {"step": 75, "kl": 0.2179484316617537, "ce": 0.4524904104257063}, {"step": 76, "kl": 0.18091655360650763, "ce": 0.591210254782001}, {"step": 77, "kl": 0.1824079606481878, "ce": 0.48091195861905767}, {"step": 78, "kl": 0.23586542382829756, "ce": 0.5126256083990159}, {"step": 79, "kl": 0.19668117989721354, "ce": 0.45704933034530587}, {"step": 80, "kl": 0.20060672453571088, "ce": 0.6300422406311198}, {"step": 81, "kl": 0.17683302180258828, "ce": 0.6530635573042654}, {"step": 82, "kl": 0.17584542805436829, "ce": 0.4973579318010061}, {"step": 83, "kl": 0.1797308846416245, "ce": 0.5989677689484277}, {"step": 84, "kl": 0.209016326911491, "ce": 0.6260018773439552}, {"step": 85, "kl": 0.33688395597459486, "ce": 0.6170231990904604}, {"step": 86, "kl": 0.18529715526620347, "ce": 0.528961564841158}, {"step": 87, "kl": 0.17153096919955757, "ce": 0.647727362810058}, {"step": 88, "kl": 0.19029895896330037, "ce": 0.6168671797025571}, {"step": 89, "kl": 0.2091274550388657, "ce": 0.4994283965637404}, {"step": 90, "kl": 0.2653575104242149, "ce": 0.5637348458968967}, {"step": 91, "kl": 0.27738150944594137, "ce": 0.6307195054083184}, {"step": 92, "kl": 0.32984221198536845, "ce": 0.5989123843214447}, {"step": 93, "kl": 0.4955522661779166, "ce": 0.5636402740417334}, {"step": 94, "kl": 0.23267890232665295, "ce": 0.696477184826019}, {"step": 95, "kl": 0.2644745549103351, "ce": 0.6389376749593203}, {"step": 96, "kl": 0.17076944562213375, "ce": 0.5584221200974469}, {"step": 97, "kl": 0.20884965162847127, "ce": 0.4947866469882624}, {"step": 98, "kl": 0.15956093108667274, "ce": 0.4938183106961872}, {"step": 99, "kl": 0.21763285309986719, "ce": 0.5544262503075787}, {"step": 100, "kl": 0.15700622111971868, "ce": 0.5477422223891049}, {"step": 101, "kl": 0.46368767413514383, "ce": 0.577603243787919}, {"step": 102, "kl": 0.1999732203217004, "ce": 0.5291949737412107}, {"step": 103, "kl": 0.16259894693903257, "ce": 0.6398633477819556}, {"step": 104, "kl": 0.17931822929989583, "ce": 0.5102966809608762}, {"step": 105, "kl": 0.17805371017929933, "ce": 0.5284666509453646}, {"step": 106, "kl": 0.17065712065573896, "ce": 0.5145847747144409}, {"step": 107, "kl": 0.16554460962794235, "ce": 0.45522868633270264}, {"step": 108, "kl": 0.18313634347074553, "ce": 0.5004309264977101}, {"step": 109, "kl": 0.16397761192980748, "ce": 0.5822535406701606}, {"step": 110, "kl": 0.2596670464857755, "ce": 0.5859012275487053}, {"step": 111, "kl": 0.37965466602739084, "ce": 0.5333761674595485}, {"step": 112, "kl": 0.32563898078166376, "ce": 0.5731747823261226}, {"step": 113, "kl": 0.1982846025995135, "ce": 0.57938069121353}, {"step": 114, "kl": 0.17068379698261377, "ce": 0.5161942646045671}, {"step": 115, "kl": 0.15108619298739817, "ce": 0.5887934925932675}, {"step": 116, "kl": 1.0473445269373742, "ce": 0.3698720535424443}, {"step": 117, "kl": 0.15146439613572166, "ce": 0.5132632244152068}, {"step": 118, "kl": 0.1906667544221744, "ce": 0.5228564180400037}, {"step": 119, "kl": 0.19235888345439975, "ce": 0.6670336037224829}, {"step": 120, "kl": 0.1921657489275013, "ce": 0.5881824078998195}, {"step": 121, "kl": 0.209622204366758, "ce": 0.4951110496423885}, {"step": 122, "kl": 0.16454286502120055, "ce": 0.5135819655772467}, {"step": 123, "kl": 0.17957131332463813, "ce": 0.47200504464139137}, {"step": 124, "kl": 0.21824614217437874, "ce": 0.5508625403090052}, {"step": 125, "kl": 0.18020320321068375, "ce": 0.5486078103173967}, {"step": 126, "kl": 0.5635442728708051, "ce": 0.4960523535529402}, {"step": 127, "kl": 0.17014158758692302, "ce": 0.5223870804643143}, {"step": 128, "kl": 0.19784378131896507, "ce": 0.5685119370760018}, {"step": 129, "kl": 0.17888422695285772, "ce": 0.47511641511293207}, {"step": 130, "kl": 0.23882017663818944, "ce": 0.5183559513840484}, {"step": 131, "kl": 0.2671508105409586, "ce": 0.6433870233014151}, {"step": 132, "kl": 0.17263360926937854, "ce": 0.5437668787701377}, {"step": 133, "kl": 0.2147601012355953, "ce": 0.5769611840109223}, {"step": 134, "kl": 0.1629301180370388, "ce": 0.5367556098267999}, {"step": 135, "kl": 0.16308576337808053, "ce": 0.44554359436035157}, {"step": 136, "kl": 0.30588075865128433, "ce": 0.41088848724365234}, {"step": 137, "kl": 0.17787878410947836, "ce": 0.529287448440652}, {"step": 138, "kl": 0.16372094321529534, "ce": 0.45719892942811224}, {"step": 139, "kl": 0.14933874023117724, "ce": 0.36511462309480003}, {"step": 140, "kl": 0.18546020691273424, "ce": 0.654886924303495}, {"step": 141, "kl": 0.2132032403027337, "ce": 0.5448980500093927}, {"step": 142, "kl": 0.21101531507238408, "ce": 0.649653483496772}, {"step": 143, "kl": 0.1878149231188393, "ce": 0.4658998635153305}, {"step": 144, "kl": 0.21773170382589074, "ce": 0.4813259978815303}, {"step": 145, "kl": 0.25930640139520145, "ce": 0.552224766095212}, {"step": 146, "kl": 0.24568163840620932, "ce": 0.5697555863390954}, {"step": 147, "kl": 0.16757220863863428, "ce": 0.4743875317868933}, {"step": 148, "kl": 0.1669805806362941, "ce": 0.5489470713013556}, {"step": 149, "kl": 0.15850141634043668, "ce": 0.5481915985112957}, {"step": 150, "kl": 0.36606024074898075, "ce": 0.508862688706022}, {"step": 151, "kl": 0.17911299792557278, "ce": 0.4977326728538641}, {"step": 152, "kl": 0.16832925043879327, "ce": 0.4950751601500287}, {"step": 153, "kl": 0.16229274400968677, "ce": 0.5698042437820934}, {"step": 154, "kl": 0.19170264179150276, "ce": 0.7523064061124753}, {"step": 155, "kl": 0.19660588967065834, "ce": 0.46386989730338785}, {"step": 156, "kl": 0.16953184384117992, "ce": 0.5386644763150246}, {"step": 157, "kl": 0.5995001358551545, "ce": 0.6023058095496934}, {"step": 158, "kl": 0.18034150191793105, "ce": 0.6121219990224491}, {"step": 159, "kl": 0.16525631109717778, "ce": 0.5393316464904652}, {"step": 160, "kl": 0.16425005405409127, "ce": 0.47173722507545623}, {"step": 161, "kl": 0.35094392218392023, "ce": 0.6439920745229762}, {"step": 162, "kl": 0.1754331755171624, "ce": 0.5727663147913036}, {"step": 163, "kl": 0.199545087032527, "ce": 0.4660403314024101}, {"step": 164, "kl": 0.18366641792332505, "ce": 0.5338591900766274}, {"step": 165, "kl": 0.28667551102806144, "ce": 0.6003518451377605}, {"step": 166, "kl": 0.21074020522407033, "ce": 0.6755429444732892}, {"step": 167, "kl": 0.20566024001825367, "ce": 0.5749981610072141}, {"step": 168, "kl": 0.17064721416211606, "ce": 0.5186014924312662}, {"step": 169, "kl": 0.1795193812037061, "ce": 0.5298653516779052}, {"step": 170, "kl": 0.19210865575942634, "ce": 0.5168460009198536}, {"step": 171, "kl": 0.16125002795250323, "ce": 0.5385079463912565}, {"step": 172, "kl": 0.18689804207104055, "ce": 0.6766855950321342}, {"step": 173, "kl": 0.15705431983847695, "ce": 0.4499156209842425}, {"step": 174, "kl": 0.20527188669349694, "ce": 0.5017502947342976}, {"step": 175, "kl": 0.28721366659340003, "ce": 0.43962346163430954}, {"step": 176, "kl": 0.23307713338231226, "ce": 0.6054054604948521}, {"step": 177, "kl": 0.6725769679831852, "ce": 0.6444583785868137}, {"step": 178, "kl": 0.26955472968436034, "ce": 0.6209582652736123}, {"step": 179, "kl": 0.237993923201952, "ce": 0.5401507319172878}, {"step": 180, "kl": 0.19548072336562303, "ce": 0.5671843736404284}, {"step": 181, "kl": 0.16259438774736823, "ce": 0.5033779265123037}, {"step": 182, "kl": 0.19007532872481475, "ce": 0.6134949462408406}, {"step": 183, "kl": 0.18967135642725932, "ce": 0.5921443339056898}, {"step": 184, "kl": 0.3210640914539874, "ce": 0.6737922824610821}, {"step": 185, "kl": 0.18422101899269175, "ce": 0.5192238179250159}, {"step": 186, "kl": 0.21401809702075036, "ce": 0.5684823025383137}, {"step": 187, "kl": 0.2096641112864206, "ce": 0.6389623805583534}, {"step": 188, "kl": 0.17373197967908027, "ce": 0.42924246720299475}, {"step": 189, "kl": 0.24826448882302607, "ce": 0.5812607971141857}, {"step": 190, "kl": 0.3236317111275717, "ce": 0.5241365763597382}, {"step": 191, "kl": 0.232123538037805, "ce": 0.49695954240283063}, {"step": 192, "kl": 0.4646493380659308, "ce": 0.7207272758931359}, {"step": 193, "kl": 0.22249880657228205, "ce": 0.5178091094249815}, {"step": 194, "kl": 0.23166007771509173, "ce": 0.43797436577130244}, {"step": 195, "kl": 0.20543385962496413, "ce": 0.5306746510650304}, {"step": 196, "kl": 0.26026618848528177, "ce": 0.5178171786407282}, {"step": 197, "kl": 0.28813219307528215, "ce": 0.5748416649834767}, {"step": 198, "kl": 0.19226877902295325, "ce": 0.5299529613408828}, {"step": 199, "kl": 0.15123204209937963, "ce": 0.42053021841726224}, {"step": 200, "kl": 1.3162699175769292, "ce": 0.5070173759445927}, {"step": 201, "kl": 0.4904721833698027, "ce": 0.48908619488190047}, {"step": 202, "kl": 0.2678127000571791, "ce": 0.4200696790894372}, {"step": 203, "kl": 0.19667994144728826, "ce": 0.5189043742984367}, {"step": 204, "kl": 0.199114250771893, "ce": 0.5504770544821533}, {"step": 205, "kl": 0.1848527439989505, "ce": 0.5593947293112599}, {"step": 206, "kl": 0.2042168096380938, "ce": 0.3734566463855068}, {"step": 207, "kl": 0.3517821594031637, "ce": 0.6013462179815195}, {"step": 208, "kl": 0.6346677026908771, "ce": 0.5713932440433218}, {"step": 209, "kl": 0.16667346744203598, "ce": 0.5817017031878959}, {"step": 210, "kl": 0.19316010684177845, "ce": 0.6053618315396647}, {"step": 211, "kl": 0.2424445355061403, "ce": 0.5542127277675218}, {"step": 212, "kl": 0.2185264492524231, "ce": 0.6854458134286924}, {"step": 213, "kl": 0.45212632905442585, "ce": 0.6446399466239481}, {"step": 214, "kl": 0.46917354718665216, "ce": 0.5491867986759449}, {"step": 215, "kl": 0.20689778609283033, "ce": 0.5621412673200556}, {"step": 216, "kl": 0.1657618048784055, "ce": 0.5572207368309818}, {"step": 217, "kl": 0.2414570696038424, "ce": 0.6068943904160387}, {"step": 218, "kl": 0.19993046253908445, "ce": 0.4955150981336661}, {"step": 219, "kl": 0.2380618964433206, "ce": 0.4994119954129692}, {"step": 220, "kl": 0.23407151656436254, "ce": 0.6278822008056832}, {"step": 221, "kl": 0.32542560821644406, "ce": 0.49439784809084747}, {"step": 222, "kl": 0.1675924746215362, "ce": 0.5606072797685822}, {"step": 223, "kl": 0.2045919838305082, "ce": 0.6271962567210599}, {"step": 224, "kl": 0.19020264033503861, "ce": 0.4488725535262972}, {"step": 225, "kl": 0.26024913042783737, "ce": 0.568067626547515}, {"step": 226, "kl": 0.21123155105249605, "ce": 0.4708631493253086}, {"step": 227, "kl": 0.17966474255202242, "ce": 0.5620021513861143}, {"step": 228, "kl": 0.18561853399333458, "ce": 0.5412885967952684}, {"step": 229, "kl": 0.1805159764607375, "ce": 0.5478526239341261}, {"step": 230, "kl": 0.21440590173965443, "ce": 0.46548325539664026}, {"step": 231, "kl": 0.214388122184702, "ce": 0.5551411443902541}, {"step": 232, "kl": 0.30431294276365695, "ce": 0.6018674451661284}, {"step": 233, "kl": 0.2427008912542315, "ce": 0.7781806665508344}, {"step": 234, "kl": 0.1800350543039847, "ce": 0.4092042505180431}, {"step": 235, "kl": 0.1875110461881429, "ce": 0.575403613737788}, {"step": 236, "kl": 0.22155950901302365, "ce": 0.6630063015117981}, {"step": 237, "kl": 0.2908299040659769, "ce": 0.49797577214387295}, {"step": 238, "kl": 0.19023694152415818, "ce": 0.5733886942273838}, {"step": 239, "kl": 0.2016229221219585, "ce": 0.5834006751830073}, {"step": 240, "kl": 0.19380179240321357, "ce": 0.5589241877128523}, {"step": 241, "kl": 0.1813957862286029, "ce": 0.5399846527739797}, {"step": 242, "kl": 0.21556542675330748, "ce": 0.6541424598419536}, {"step": 243, "kl": 0.185927673977703, "ce": 0.5029284738527181}, {"step": 244, "kl": 0.34162995897072546, "ce": 0.598367124086817}, {"step": 245, "kl": 0.18524270945117643, "ce": 0.5610663562025665}, {"step": 246, "kl": 0.14738676137134582, "ce": 0.5579898278121753}, {"step": 247, "kl": 0.21557197838567582, "ce": 0.44638710736095916}, {"step": 248, "kl": 0.28026107432648606, "ce": 0.6395214028351994}, {"step": 249, "kl": 0.17648985225640862, "ce": 0.4724994404936221}, {"step": 250, "kl": 0.3079812975215988, "ce": 0.6273056359762413}, {"step": 251, "kl": 0.16763901507381845, "ce": 0.5713777639641214}, {"step": 252, "kl": 0.22787350200999276, "ce": 0.5700087398952908}, {"step": 253, "kl": 0.2258261911736869, "ce": 0.5098803110941204}, {"step": 254, "kl": 0.1864622003860377, "ce": 0.5989532763490737}, {"step": 255, "kl": 0.20368481103235497, "ce": 0.42239086733875986}, {"step": 256, "kl": 0.25424568370258993, "ce": 0.5623017446900024}, {"step": 257, "kl": 0.3303824496233675, "ce": 0.63422397992449}, {"step": 258, "kl": 0.18584613894101928, "ce": 0.5584318062354778}, {"step": 259, "kl": 0.18333985847339299, "ce": 0.5845170122440534}, {"step": 260, "kl": 0.22232794197060335, "ce": 0.5494698158362087}, {"step": 261, "kl": 0.17995914068992402, "ce": 0.5628092835899982}, {"step": 262, "kl": 0.4676183229721471, "ce": 0.5198718524056809}, {"step": 263, "kl": 0.1825297353544076, "ce": 0.4791008442294674}, {"step": 264, "kl": 0.19222418582800666, "ce": 0.63921448787735}, {"step": 265, "kl": 0.2675344583336712, "ce": 0.638905563145181}, {"step": 266, "kl": 0.210632983250017, "ce": 0.6614637369320386}, {"step": 267, "kl": 0.18999385617422151, "ce": 0.6360031985591108}, {"step": 268, "kl": 0.24095461734358328, "ce": 0.5323856338463585}, {"step": 269, "kl": 0.24316745295586348, "ce": 0.48786120101091945}, {"step": 270, "kl": 0.20843221296571326, "ce": 0.5379582960032514}, {"step": 271, "kl": 0.25594795607069865, "ce": 0.5528230442866867}, {"step": 272, "kl": 0.22797569453487346, "ce": 0.5113442775181362}, {"step": 273, "kl": 0.2772025724308349, "ce": 0.4755159403461562}, {"step": 274, "kl": 0.624033289461656, "ce": 0.582967999922716}, {"step": 275, "kl": 0.21669676928734166, "ce": 0.49234135500390414}, {"step": 276, "kl": 0.1916522981220993, "ce": 0.6105858939034597}, {"step": 277, "kl": 0.19797434038269524, "ce": 0.5958577463600587}, {"step": 278, "kl": 0.28821081154759276, "ce": 0.492278759140371}, {"step": 279, "kl": 0.21747810555091351, "ce": 0.4155469518119729}, {"step": 280, "kl": 0.18832401798011197, "ce": 0.539555400422534}, {"step": 281, "kl": 0.20191964017219863, "ce": 0.5460542342834587}, {"step": 282, "kl": 0.29951754822704557, "ce": 0.7041567975013007}, {"step": 283, "kl": 0.19954979902128128, "ce": 0.5229656145563204}, {"step": 284, "kl": 0.3377957834523533, "ce": 0.5766667776993473}, {"step": 285, "kl": 0.22465806792945311, "ce": 0.4758193774008981}, {"step": 286, "kl": 0.19051124919954482, "ce": 0.5807018325168787}, {"step": 287, "kl": 0.17637660042863784, "ce": 0.5050386080117159}, {"step": 288, "kl": 0.33011110505905106, "ce": 0.5295419981873866}, {"step": 289, "kl": 0.24413257427391605, "ce": 0.4947189693807892}, {"step": 290, "kl": 0.2514772699358231, "ce": 0.5436949216532506}, {"step": 291, "kl": 0.18757666332728995, "ce": 0.3906855344113464}, {"step": 292, "kl": 0.2911410592233946, "ce": 0.6553782374630892}, {"step": 293, "kl": 0.21603171869127993, "ce": 0.4883090190763021}, {"step": 294, "kl": 0.19756545043694904, "ce": 0.5144664892303358}, {"step": 295, "kl": 0.17538176357380098, "ce": 0.5222045573097809}, {"step": 296, "kl": 0.17544539980293902, "ce": 0.5198023558166547}, {"step": 297, "kl": 0.23695976543751998, "ce": 0.6151358115859746}, {"step": 298, "kl": 0.18727557284425778, "ce": 0.4603770146705248}, {"step": 299, "kl": 0.16904297515865008, "ce": 0.45498585389005425}, {"step": 300, "kl": 0.4255271721816415, "ce": 0.4898800675736818}, {"step": 301, "kl": 0.17607858216679526, "ce": 0.5258184527808301}, {"step": 302, "kl": 0.18644124411245794, "ce": 0.530981884828789}, {"step": 303, "kl": 0.23560730480047326, "ce": 0.5298403616544602}, {"step": 304, "kl": 0.22008600254313976, "ce": 0.5716177859534779}, {"step": 305, "kl": 0.2931073793807689, "ce": 0.6410393224043005}, {"step": 306, "kl": 0.3060578245283511, "ce": 0.5479683781070943}, {"step": 307, "kl": 0.1882237762476028, "ce": 0.505949923510622}, {"step": 308, "kl": 0.25452010275769343, "ce": 0.6214404904361348}, {"step": 309, "kl": 0.21066544958140265, "ce": 0.551746988708544}, {"step": 310, "kl": 0.4601619288539335, "ce": 0.5636292448215516}, {"step": 311, "kl": 0.24423773448332392, "ce": 0.63053052164403}, {"step": 312, "kl": 0.21103798917775418, "ce": 0.49037456141108965}, {"step": 313, "kl": 0.1903634201852899, "ce": 0.576810133473315}, {"step": 314, "kl": 0.3786521271086337, "ce": 0.6354514272077799}, {"step": 315, "kl": 0.20196695758932298, "ce": 0.5746773129311022}, {"step": 316, "kl": 0.19756563242169237, "ce": 0.5158068860231266}, {"step": 317, "kl": 0.22560912330027644, "ce": 0.5895803859577843}, {"step": 318, "kl": 0.2174432863748021, "ce": 0.5136039230659553}, {"step": 319, "kl": 0.251059090789122, "ce": 0.5985373026434521}, {"step": 320, "kl": 0.22746356732294887, "ce": 0.48714129502332226}, {"step": 321, "kl": 0.22151210533749197, "ce": 0.5422500672741472}, {"step": 322, "kl": 0.1773259422115137, "ce": 0.4840703594004932}, {"step": 323, "kl": 0.2147361211785647, "ce": 0.7656958553592864}, {"step": 324, "kl": 0.18571821967909918, "ce": 0.5410738362412508}, {"step": 325, "kl": 0.3068790041053392, "ce": 0.5819314244441982}, {"step": 326, "kl": 0.1916295337327771, "ce": 0.5954692296161396}, {"step": 327, "kl": 0.20791428815357488, "ce": 0.5647893914138337}, {"step": 328, "kl": 1.9428875832436923, "ce": 0.5794771570178998}, {"step": 329, "kl": 0.18492862372099597, "ce": 0.6157457539111892}, {"step": 330, "kl": 0.22166273792936986, "ce": 0.5672613204751153}, {"step": 331, "kl": 0.21242293120889652, "ce": 0.5557925845337466}, {"step": 332, "kl": 0.20624371917461543, "ce": 0.6813082635470336}, {"step": 333, "kl": 0.19183966106944034, "ce": 0.4678167540098761}, {"step": 334, "kl": 0.18796782653516161, "ce": 0.6092636167596656}, {"step": 335, "kl": 0.19349326694013524, "ce": 0.4007305762360036}, {"step": 336, "kl": 0.17255467290734328, "ce": 0.6014818830048692}, {"step": 337, "kl": 0.2564453719691103, "ce": 0.4290049861044812}, {"step": 338, "kl": 0.1908637182324306, "ce": 0.47524819844422805}, {"step": 339, "kl": 0.19794071333493346, "ce": 0.6002407353062973}, {"step": 340, "kl": 0.19868103446172303, "ce": 0.5850939623367793}, {"step": 341, "kl": 0.20815407789535792, "ce": 0.5777800225086219}, {"step": 342, "kl": 0.2352026144919903, "ce": 0.41582802930891377}, {"step": 343, "kl": 0.2289709506388014, "ce": 0.559155332318343}, {"step": 344, "kl": 0.1805650314430731, "ce": 0.5172646831924989}, {"step": 345, "kl": 0.18987833150787597, "ce": 0.4520499529516482}, {"step": 346, "kl": 0.2221279314630828, "ce": 0.6108810910904418}, {"step": 347, "kl": 0.22798187054944208, "ce": 0.5051251708553126}, {"step": 348, "kl": 0.29668069233446454, "ce": 0.6334547944647498}, {"step": 349, "kl": 0.25248767002663064, "ce": 0.5581871325467225}, {"step": 350, "kl": 0.20970679783654855, "ce": 0.49163520235975255}, {"step": 351, "kl": 0.18364320084258548, "ce": 0.49957337699936755}, {"step": 352, "kl": 0.25014875800746267, "ce": 0.608980211088058}, {"step": 353, "kl": 0.23789639541225666, "ce": 0.5771605447113437}, {"step": 354, "kl": 0.39340259369756314, "ce": 0.5543786240620028}, {"step": 355, "kl": 0.18350641427995606, "ce": 0.47352594841375256}, {"step": 356, "kl": 0.18765721040969327, "ce": 0.4510273186297041}, {"step": 357, "kl": 0.19323687045991522, "ce": 0.5163011822484649}, {"step": 358, "kl": 0.23043462723002547, "ce": 0.48528873806238704}, {"step": 359, "kl": 0.20339924766848136, "ce": 0.5379303264700632}, {"step": 360, "kl": 0.32164059937563855, "ce": 0.499522590637207}, {"step": 361, "kl": 0.18718249202710302, "ce": 0.46674042355910433}, {"step": 362, "kl": 0.31853696053121255, "ce": 0.4737546348831584}, {"step": 363, "kl": 0.1869360506749033, "ce": 0.47163983017711325}, {"step": 364, "kl": 0.24441521436928015, "ce": 0.42943580987271024}, {"step": 365, "kl": 0.19313250603358106, "ce": 0.6272002709836375}, {"step": 366, "kl": 0.1780298431207349, "ce": 0.565184411340895}, {"step": 367, "kl": 0.18084002276473768, "ce": 0.617531861514407}, {"step": 368, "kl": 0.18267630267264612, "ce": 0.536851422670283}, {"step": 369, "kl": 0.2082793924533594, "ce": 0.41835911606537424}, {"step": 370, "kl": 0.1936466090617331, "ce": 0.5475205665519758}, {"step": 371, "kl": 0.2951810816521393, "ce": 0.5779173527474707}, {"step": 372, "kl": 0.18446938999775703, "ce": 0.3856985532644704}, {"step": 373, "kl": 0.19425295869382428, "ce": 0.4822875823347823}, {"step": 374, "kl": 0.2843123658199171, "ce": 0.6146533401065317}, {"step": 375, "kl": 0.1681290268942362, "ce": 0.45505402500468084}, {"step": 376, "kl": 0.18781440921278392, "ce": 0.5130394338776157}, {"step": 377, "kl": 0.2553908646680266, "ce": 0.44476892730234246}, {"step": 378, "kl": 0.19754016841373925, "ce": 0.6016598367700726}, {"step": 379, "kl": 0.21696213615989224, "ce": 0.41341116357519925}, {"step": 380, "kl": 0.20915567644054034, "ce": 0.571541385517434}, {"step": 381, "kl": 0.2074057189020981, "ce": 0.5797337936639086}, {"step": 382, "kl": 0.21100133416298983, "ce": 0.444538446707201}, {"step": 383, "kl": 0.18546838689299855, "ce": 0.5167989934644392}, {"step": 384, "kl": 0.20366770104173157, "ce": 0.6364645003881851}, {"step": 385, "kl": 0.18424571421819608, "ce": 0.6277161510077247}, {"step": 386, "kl": 0.26511028807237874, "ce": 0.6030283904714296}, {"step": 387, "kl": 0.18849141746871217, "ce": 0.5275798548161508}, {"step": 388, "kl": 0.25485617595928806, "ce": 0.5566201083468761}, {"step": 389, "kl": 0.19223380757117584, "ce": 0.43937982964923733}, {"step": 390, "kl": 0.2660344990129739, "ce": 0.565865005170301}, {"step": 391, "kl": 0.20536499002654623, "ce": 0.650070382687384}, {"step": 392, "kl": 0.19156357871026838, "ce": 0.5234507111717852}, {"step": 393, "kl": 0.18674527257571188, "ce": 0.5428565020477895}, {"step": 394, "kl": 0.32531776379008226, "ce": 0.622686268266573}, {"step": 395, "kl": 0.2343227284142939, "ce": 0.6041368547631296}, {"step": 396, "kl": 0.25492459317760086, "ce": 0.6440083502664683}, {"step": 397, "kl": 0.21072430695688216, "ce": 0.6342984671904661}, {"step": 398, "kl": 0.26093687582507696, "ce": 0.6395052953379776}, {"step": 399, "kl": 0.4798813586311299, "ce": 0.5066679694543983}, {"step": 400, "kl": 0.32919762715465545, "ce": 0.5729411081300724}, {"step": 401, "kl": 0.3823206567797327, "ce": 0.459317261450345}, {"step": 402, "kl": 0.22910399585888752, "ce": 0.6241557459243023}, {"step": 403, "kl": 0.1765440235711468, "ce": 0.40159290373192597}, {"step": 404, "kl": 0.2629060005159228, "ce": 0.5623528870716075}, {"step": 405, "kl": 0.2009265970774027, "ce": 0.6420699599451339}, {"step": 406, "kl": 0.2810870027871257, "ce": 0.5581132635895345}, {"step": 407, "kl": 0.24451370734546918, "ce": 0.5424084658245018}, {"step": 408, "kl": 0.19367059271431825, "ce": 0.45004770250151244}, {"step": 409, "kl": 0.4675081569531486, "ce": 0.5727534143923441}, {"step": 410, "kl": 0.21064182569359852, "ce": 0.5717315081342289}, {"step": 411, "kl": 0.3402166405516157, "ce": 0.5549068865836656}, {"step": 412, "kl": 0.7522078915254192, "ce": 0.5982900853773039}, {"step": 413, "kl": 0.2856829288878727, "ce": 0.5654056236954178}, {"step": 414, "kl": 0.21287998675228814, "ce": 0.5549789528318417}, {"step": 415, "kl": 0.22682281117177078, "ce": 0.48110135021823314}, {"step": 416, "kl": 0.18442174072265624, "ce": 0.5634226720619085}, {"step": 417, "kl": 0.27404155157357024, "ce": 0.42450584489178944}, {"step": 418, "kl": 0.22248814273763, "ce": 0.6359947522156969}, {"step": 419, "kl": 0.2164525556543085, "ce": 0.5906195178778355}, {"step": 420, "kl": 0.22582583012151727, "ce": 0.4844261582900676}, {"step": 421, "kl": 0.302694563508625, "ce": 0.5055115086911697}, {"step": 422, "kl": 0.23881454619179387, "ce": 0.516560489346522}, {"step": 423, "kl": 0.22775241182050632, "ce": 0.46506931288387104}, {"step": 424, "kl": 0.23342028247050844, "ce": 0.5027673744604257}, {"step": 425, "kl": 0.3298670740082036, "ce": 0.36613215713949104}, {"step": 426, "kl": 0.19145265201429035, "ce": 0.46358487745129523}, {"step": 427, "kl": 0.17931173799348638, "ce": 0.5106686795398309}, {"step": 428, "kl": 0.3826673498441433, "ce": 0.5610570134343329}, {"step": 429, "kl": 0.24059798680019015, "ce": 0.5318672664518247}, {"step": 430, "kl": 0.18827466303153484, "ce": 0.4670382923480317}, {"step": 431, "kl": 0.1870691063957862, "ce": 0.46815855704136067}, {"step": 432, "kl": 0.19417690710260138, "ce": 0.6424300768364923}, {"step": 433, "kl": 0.38453026258390177, "ce": 0.7465433644693952}, {"step": 434, "kl": 0.6744216675281187, "ce": 0.4908134816530211}, {"step": 435, "kl": 0.2608002262544109, "ce": 0.6146689021052759}, {"step": 436, "kl": 0.18505298083341576, "ce": 0.5837774084218288}, {"step": 437, "kl": 0.245971320059582, "ce": 0.5153469335470533}, {"step": 438, "kl": 0.6142308536039496, "ce": 0.5859980228690991}, {"step": 439, "kl": 0.2020664787010366, "ce": 0.5030304959890198}, {"step": 440, "kl": 0.25766545964519255, "ce": 0.7929520578309377}, {"step": 441, "kl": 0.2524601714361439, "ce": 0.5351525837278963}, {"step": 442, "kl": 0.2261364793304946, "ce": 0.5151960169547573}, {"step": 443, "kl": 0.2063876177535596, "ce": 0.4374683733579129}, {"step": 444, "kl": 0.19836599188003626, "ce": 0.48635625130558224}, {"step": 445, "kl": 0.3607570715909879, "ce": 0.5564120034635187}, {"step": 446, "kl": 0.23694463998450632, "ce": 0.47854936954587}, {"step": 447, "kl": 0.19684964104742236, "ce": 0.5894546558901295}, {"step": 448, "kl": 0.35077883448007485, "ce": 0.4652915590817166}, {"step": 449, "kl": 0.3170918130160293, "ce": 0.44718050084155436}, {"step": 450, "kl": 0.32734932682883333, "ce": 0.3371438350015365}, {"step": 451, "kl": 0.2090551230587893, "ce": 0.32481332659658735}, {"step": 452, "kl": 0.36360846221327836, "ce": 0.31169163322869775}, {"step": 453, "kl": 0.5997415739823365, "ce": 0.3934591981930473}, {"step": 454, "kl": 0.2224465591854884, "ce": 0.46021054114824456}, {"step": 455, "kl": 0.1848862590220884, "ce": 0.39468558054798997}, {"step": 456, "kl": 0.8411701994471901, "ce": 0.38250595314361335}, {"step": 457, "kl": 0.19908921331197937, "ce": 0.3741137641874747}, {"step": 458, "kl": 0.49300732419091825, "ce": 0.4583226888563491}, {"step": 459, "kl": 0.23287646942518347, "ce": 0.3824623076914103}, {"step": 460, "kl": 0.2026956066076012, "ce": 0.4649840005393761}, {"step": 461, "kl": 0.2227338974225378, "ce": 0.5058972616727831}, {"step": 462, "kl": 0.4410897279957807, "ce": 0.3302160911051227}, {"step": 463, "kl": 0.20472800316092124, "ce": 0.3338854036637615}, {"step": 464, "kl": 0.21956817278106971, "ce": 0.401513092387084}, {"step": 465, "kl": 0.3247664183938198, "ce": 0.41174469589100504}, {"step": 466, "kl": 0.20550305687605616, "ce": 0.34613939058541504}, {"step": 467, "kl": 0.17942155413130584, "ce": 0.420463666876322}, {"step": 468, "kl": 0.3552247691795983, "ce": 0.4416818089375507}, {"step": 469, "kl": 0.19509162729254625, "ce": 0.3056607624943535}, {"step": 470, "kl": 0.37996968288605565, "ce": 0.41394341715732974}, {"step": 471, "kl": 0.19144014852103053, "ce": 0.29077523697398683}, {"step": 472, "kl": 0.2140031763228813, "ce": 0.4290258922444524}, {"step": 473, "kl": 0.3467224536940109, "ce": 0.3635609991756486}, {"step": 474, "kl": 0.27034296503244737, "ce": 0.42479964245806684}, {"step": 475, "kl": 0.25341616502382264, "ce": 0.5105138775484932}, {"step": 476, "kl": 0.2373972543020555, "ce": 0.3861004935579347}, {"step": 477, "kl": 0.223363578067628, "ce": 0.48463082152504405}, {"step": 478, "kl": 0.23554134453229292, "ce": 0.2584430125259017}, {"step": 479, "kl": 0.2630447227141482, "ce": 0.39142098730867425}, {"step": 480, "kl": 0.22081553670374862, "ce": 0.3183806402387832}, {"step": 481, "kl": 0.20130643930985292, "ce": 0.32574958997850084}, {"step": 482, "kl": 0.7639049146541211, "ce": 0.3591510334873622}, {"step": 483, "kl": 0.213004335555101, "ce": 0.38623860550768857}, {"step": 484, "kl": 0.17474477061724872, "ce": 0.45262414066731427}, {"step": 485, "kl": 0.27435583183281426, "ce": 0.3563395480828092}, {"step": 486, "kl": 0.17686936107677054, "ce": 0.29386252931409623}, {"step": 487, "kl": 0.20380271171101055, "ce": 0.4088126755417317}, {"step": 488, "kl": 0.3542116035957934, "ce": 0.4251504167961279}, {"step": 489, "kl": 0.27937967518750845, "ce": 0.38378120802047366}, {"step": 490, "kl": 0.34979110894021265, "ce": 0.35991624460786653}, {"step": 491, "kl": 0.3084763867762439, "ce": 0.356375264395312}, {"step": 492, "kl": 0.22067043025470542, "ce": 0.30424474123730244}, {"step": 493, "kl": 0.2981321948838338, "ce": 0.6450564966603596}, {"step": 494, "kl": 0.21311272076058874, "ce": 0.40038664988256495}, {"step": 495, "kl": 0.20468576214466072, "ce": 0.33373869116685734}, {"step": 496, "kl": 0.1998129419940418, "ce": 0.3998425611544842}, {"step": 497, "kl": 0.19778325685086007, "ce": 0.35570023159728886}, {"step": 498, "kl": 0.27365176549317993, "ce": 0.42516437093974974}, {"step": 499, "kl": 0.2430637628328527, "ce": 0.41248398286859117}, {"step": 500, "kl": 0.21487812940595197, "ce": 0.3839082244235339}, {"step": 501, "kl": 0.22528423452678614, "ce": 0.3592774830233883}, {"step": 502, "kl": 0.2296553764849123, "ce": 0.42285173727113146}, {"step": 503, "kl": 0.19863209484214386, "ce": 0.4085197525423933}, {"step": 504, "kl": 0.2008457983772281, "ce": 0.3297511199750068}, {"step": 505, "kl": 0.195036347711827, "ce": 0.3223266161840492}, {"step": 506, "kl": 0.1984591128603575, "ce": 0.46130900495921134}, {"step": 507, "kl": 0.21717252695123035, "ce": 0.35257605409331727}, {"step": 508, "kl": 0.24467128909747204, "ce": 0.32018421270577635}, {"step": 509, "kl": 0.23488053548610205, "ce": 0.35236018530523006}, {"step": 510, "kl": 0.19175167446397132, "ce": 0.33336005208151165}, {"step": 511, "kl": 0.22315946188566382, "ce": 0.44384446934961846}, {"step": 512, "kl": 0.18461970095631736, "ce": 0.3520252959852274}, {"step": 513, "kl": 0.19612832990396686, "ce": 0.3535546744896087}, {"step": 514, "kl": 0.22744728050795684, "ce": 0.42153650946583077}, {"step": 515, "kl": 0.178304081686971, "ce": 0.34501097906959005}, {"step": 516, "kl": 0.24683151767167644, "ce": 0.31307267330912286}, {"step": 517, "kl": 0.6207037527535748, "ce": 0.4312695330069908}, {"step": 518, "kl": 0.19714702040944743, "ce": 0.3285552266490491}, {"step": 519, "kl": 0.21484950271149955, "ce": 0.4636970377390911}, {"step": 520, "kl": 0.20458689253121115, "ce": 0.4777551266712142}, {"step": 521, "kl": 0.18400435446025024, "ce": 0.3302236149887746}, {"step": 522, "kl": 0.7288477238379113, "ce": 0.39623751712683297}, {"step": 523, "kl": 0.42800284533896055, "ce": 0.48709871221313983}, {"step": 524, "kl": 0.19541476960467266, "ce": 0.4515344054859244}, {"step": 525, "kl": 0.38383249750968185, "ce": 0.3378936970128422}, {"step": 526, "kl": 0.23617753905237096, "ce": 0.3608522950013188}, {"step": 527, "kl": 0.19721143634930788, "ce": 0.30694620053792737}, {"step": 528, "kl": 0.20239824255338612, "ce": 0.44097690520607596}, {"step": 529, "kl": 0.18651717429002854, "ce": 0.4073597256001384}, {"step": 530, "kl": 0.25866030601128537, "ce": 0.38990326640022244}, {"step": 531, "kl": 0.18478220426753664, "ce": 0.3178101649527396}, {"step": 532, "kl": 0.6561728391312871, "ce": 0.3685413067532134}, {"step": 533, "kl": 0.23143390264829364, "ce": 0.40681290417737487}, {"step": 534, "kl": 0.19917824499901948, "ce": 0.3725423662845759}, {"step": 535, "kl": 0.19620641640254427, "ce": 0.39502478558966453}, {"step": 536, "kl": 0.21834108704845295, "ce": 0.4366146114843956}, {"step": 537, "kl": 0.4779422771135148, "ce": 0.4553993966333853}, {"step": 538, "kl": 0.625956549556592, "ce": 0.35778910436338035}, {"step": 539, "kl": 0.22199737491892343, "ce": 0.3520378686685478}, {"step": 540, "kl": 0.3404432153450331, "ce": 0.40208631395858424}, {"step": 541, "kl": 0.2642862325901606, "ce": 0.37294701153470067}, {"step": 542, "kl": 0.4963907797757601, "ce": 0.3527482971169179}, {"step": 543, "kl": 0.28267369451989965, "ce": 0.3660358111992938}, {"step": 544, "kl": 0.7285983705961487, "ce": 0.39203134842302834}, {"step": 545, "kl": 0.19449576199011556, "ce": 0.38874612180211027}, {"step": 546, "kl": 0.8145066826020876, "ce": 0.4264791360469763}, {"step": 547, "kl": 0.2680452230438313, "ce": 0.41639834529114483}, {"step": 548, "kl": 0.24776328185532936, "ce": 0.3954480962550387}, {"step": 549, "kl": 0.2120809740671542, "ce": 0.2893224067454911}, {"step": 550, "kl": 0.21532931414399914, "ce": 0.3529472717731712}, {"step": 551, "kl": 0.19055445183574576, "ce": 0.39227264264779554}, {"step": 552, "kl": 0.2339228230907338, "ce": 0.38082347861345406}, {"step": 553, "kl": 0.200928481260444, "ce": 0.35511888365127264}, {"step": 554, "kl": 0.2968855927886025, "ce": 0.3728255062841167}, {"step": 555, "kl": 0.20475178306172861, "ce": 0.4705899090500353}, {"step": 556, "kl": 0.19812583003282988, "ce": 0.42453930497469633}, {"step": 557, "kl": 0.2701050197530483, "ce": 0.4370579846780819}, {"step": 558, "kl": 0.2543267677833262, "ce": 0.33822002079416064}, {"step": 559, "kl": 0.2281867229372453, "ce": 0.3826069018695583}, {"step": 560, "kl": 0.5044361202049025, "ce": 0.3275395549731201}, {"step": 561, "kl": 0.22249138994379633, "ce": 0.34420714879849407}, {"step": 562, "kl": 0.22029890398719212, "ce": 0.4139196880177916}, {"step": 563, "kl": 0.22155504581742938, "ce": 0.35862789956228125}, {"step": 564, "kl": 0.19685272476630516, "ce": 0.3978089137469378}, {"step": 565, "kl": 0.2919247527047106, "ce": 0.43465960602893533}, {"step": 566, "kl": 0.17861778547507515, "ce": 0.3433874772358099}, {"step": 567, "kl": 0.3268740383780386, "ce": 0.3107055356833567}, {"step": 568, "kl": 0.25398771264122505, "ce": 0.36269316655642236}, {"step": 569, "kl": 0.2616681948539064, "ce": 0.38489777241146816}, {"step": 570, "kl": 0.21122946157894207, "ce": 0.3672942755872242}, {"step": 571, "kl": 0.5758108163748011, "ce": 0.41092108870362426}, {"step": 572, "kl": 0.2157472307225039, "ce": 0.3405165547567423}, {"step": 573, "kl": 0.19591938070201226, "ce": 0.39196980409586624}, {"step": 574, "kl": 0.19854488600986592, "ce": 0.3026648037244648}, {"step": 575, "kl": 0.28909801056576134, "ce": 0.3048169508008314}, {"step": 576, "kl": 0.24755759431561958, "ce": 0.4111293338832371}, {"step": 577, "kl": 0.18243363216677325, "ce": 0.3974555505761054}, {"step": 578, "kl": 0.26978662469289644, "ce": 0.4138613895063994}, {"step": 579, "kl": 0.22694414322566012, "ce": 0.29353005718746894}, {"step": 580, "kl": 0.21021702253607016, "ce": 0.31559181307646544}, {"step": 581, "kl": 0.2812589174247833, "ce": 0.43040598337299174}, {"step": 582, "kl": 0.19125372207023258, "ce": 0.3023045733452494}, {"step": 583, "kl": 0.210262219570044, "ce": 0.3704593228298489}, {"step": 584, "kl": 0.21926000477351362, "ce": 0.3306216013909019}, {"step": 585, "kl": 0.21487858249727887, "ce": 0.3493000717780851}, {"step": 586, "kl": 0.22643408976075685, "ce": 0.2762505239159794}, {"step": 587, "kl": 0.24981968939814117, "ce": 0.3488077104060057}, {"step": 588, "kl": 0.24636734498343554, "ce": 0.3512146785842676}, {"step": 589, "kl": 0.5849978553057844, "ce": 0.45701678695491255}, {"step": 590, "kl": 0.24625399936594367, "ce": 0.4166393527006091}, {"step": 591, "kl": 0.4077853376582262, "ce": 0.46933565796882065}, {"step": 592, "kl": 0.34483470006588646, "ce": 0.3795575195888303}, {"step": 593, "kl": 0.2423764168654907, "ce": 0.36040713044850914}, {"step": 594, "kl": 0.3245881834857305, "ce": 0.34453020026398207}, {"step": 595, "kl": 0.2875769437623027, "ce": 0.34674826331498454}, {"step": 596, "kl": 0.1943059410863366, "ce": 0.29017670429804376}, {"step": 597, "kl": 0.2404331649250677, "ce": 0.374248380107316}, {"step": 598, "kl": 0.20740384806502615, "ce": 0.38114901702842463}, {"step": 599, "kl": 0.21488928701363355, "ce": 0.34904249364039797}, {"step": 600, "kl": 0.22933902632861763, "ce": 0.3761520524246388}, {"step": 601, "kl": 0.22366008175955035, "ce": 0.374472018618303}, {"step": 602, "kl": 0.18674275129339424, "ce": 0.4876926754892458}, {"step": 603, "kl": 1.7629552476143724, "ce": 0.3919917603613625}, {"step": 604, "kl": 0.20530510190133053, "ce": 0.25570846203989633}, {"step": 605, "kl": 0.3398783181521938, "ce": 0.3815160499064985}, {"step": 606, "kl": 0.20309411931842747, "ce": 0.41804116331500774}, {"step": 607, "kl": 0.24484180392620053, "ce": 0.4166811359684404}, {"step": 608, "kl": 0.3384566615956057, "ce": 0.27365827808312704}, {"step": 609, "kl": 0.2108938577046395, "ce": 0.2763471537800627}, {"step": 610, "kl": 0.22721273410964432, "ce": 0.28591360492479845}, {"step": 611, "kl": 0.4431364118966664, "ce": 0.4242879856207199}, {"step": 612, "kl": 0.17687546674207746, "ce": 0.28631828094087824}, {"step": 613, "kl": 0.25145814630683533, "ce": 0.39107763069626844}, {"step": 614, "kl": 0.22579683194223893, "ce": 0.29110946074890726}, {"step": 615, "kl": 0.2079630247200615, "ce": 0.3322037734515254}, {"step": 616, "kl": 0.20902597500090217, "ce": 0.29615015710696113}, {"step": 617, "kl": 0.22399354907795374, "ce": 0.4829729721515714}, {"step": 618, "kl": 0.22417264249039937, "ce": 0.27166047006283167}, {"step": 619, "kl": 0.20487184559522903, "ce": 0.4009192123378359}, {"step": 620, "kl": 0.20874687691653657, "ce": 0.33205098217070417}, {"step": 621, "kl": 0.1904066321010816, "ce": 0.3309228923102491}, {"step": 622, "kl": 0.20253188331973976, "ce": 0.3486790163539726}, {"step": 623, "kl": 0.3482500786545042, "ce": 0.4718873696959969}, {"step": 624, "kl": 0.2533857123158848, "ce": 0.3789164094843416}, {"step": 625, "kl": 0.29017790493899825, "ce": 0.37456605223036304}, {"step": 626, "kl": 0.25545223266169315, "ce": 0.32422290420716865}, {"step": 627, "kl": 0.2261629565715424, "ce": 0.36965892998931027}, {"step": 628, "kl": 0.22548499555097834, "ce": 0.3808578284285824}, {"step": 629, "kl": 0.20566357937361202, "ce": 0.3483826107219952}, {"step": 630, "kl": 0.20627401732792888, "ce": 0.4085169665203308}, {"step": 631, "kl": 0.255338744460339, "ce": 0.5126427880458178}, {"step": 632, "kl": 0.2991081018016172, "ce": 0.28901769773637426}, {"step": 633, "kl": 0.18551065851062432, "ce": 0.3374131094281409}, {"step": 634, "kl": 0.22526064351001984, "ce": 0.33210544710438883}, {"step": 635, "kl": 0.2216450048003728, "ce": 0.3661612985875178}, {"step": 636, "kl": 0.44300982806826794, "ce": 0.3830496427777049}, {"step": 637, "kl": 0.21900636768352394, "ce": 0.43259838315040455}, {"step": 638, "kl": 0.197849793650328, "ce": 0.2995605376846619}, {"step": 639, "kl": 0.22989365872780837, "ce": 0.2833310832607449}, {"step": 640, "kl": 0.197323492980232, "ce": 0.44138688558100636}, {"step": 641, "kl": 0.18207764756849892, "ce": 0.30744017177157934}, {"step": 642, "kl": 0.17310870820160865, "ce": 0.34948597098340595}, {"step": 643, "kl": 0.2443914400394707, "ce": 0.38830770775392487}, {"step": 644, "kl": 0.22319509399391094, "ce": 0.4555948361450312}, {"step": 645, "kl": 0.19873179691763054, "ce": 0.38517317573501164}, {"step": 646, "kl": 0.5323084409440779, "ce": 0.4401195035148756}, {"step": 647, "kl": 0.24778445732379134, "ce": 0.37338003601094316}, {"step": 648, "kl": 0.1784539677468538, "ce": 0.3870052327317882}, {"step": 649, "kl": 0.2107389794583205, "ce": 0.34148024066222765}, {"step": 650, "kl": 0.32365612274724376, "ce": 0.36600663066687167}, {"step": 651, "kl": 0.41112100003945706, "ce": 0.3360538860500875}, {"step": 652, "kl": 0.1978238746338689, "ce": 0.4124284193892465}, {"step": 653, "kl": 0.2765502593906067, "ce": 0.373923330569486}, {"step": 654, "kl": 0.21145133624492313, "ce": 0.293130470236004}, {"step": 655, "kl": 0.323041643175795, "ce": 0.4046598032218258}, {"step": 656, "kl": 0.19995008802604644, "ce": 0.27254711892096684}, {"step": 657, "kl": 0.3058220597166104, "ce": 0.3866337716567902}, {"step": 658, "kl": 0.21905915675118987, "ce": 0.3666911719731196}, {"step": 659, "kl": 0.301378756796122, "ce": 0.3416710944149081}, {"step": 660, "kl": 0.21149812036631058, "ce": 0.34457064430732764}, {"step": 661, "kl": 0.1867271107669033, "ce": 0.36680152709201236}, {"step": 662, "kl": 0.19141883452898859, "ce": 0.3535290369012085}, {"step": 663, "kl": 0.29757350110027786, "ce": 0.42075937541687763}, {"step": 664, "kl": 0.21298258811501955, "ce": 0.3316171568413786}, {"step": 665, "kl": 0.19466222261430266, "ce": 0.40487161672780847}, {"step": 666, "kl": 0.18223227173713197, "ce": 0.31546477794559546}, {"step": 667, "kl": 0.4412553326068262, "ce": 0.39952545801798506}, {"step": 668, "kl": 0.25518875318041273, "ce": 0.36168065652384157}, {"step": 669, "kl": 0.2617696056869354, "ce": 0.34010574315303943}, {"step": 670, "kl": 0.35584659869740976, "ce": 0.4388341917246792}, {"step": 671, "kl": 0.21850727064444495, "ce": 0.32492201985130237}, {"step": 672, "kl": 0.1734370731475063, "ce": 0.25881241789318266}, {"step": 673, "kl": 0.1984378198570038, "ce": 0.34294709582405924}, {"step": 674, "kl": 0.1982261610727361, "ce": 0.46978090865745664}, {"step": 675, "kl": 0.2601278593528107, "ce": 0.2711826952468608}, {"step": 676, "kl": 0.3187129561458581, "ce": 0.3384179675606772}, {"step": 677, "kl": 0.1677845123427677, "ce": 0.3202329290308218}, {"step": 678, "kl": 0.22532892341116828, "ce": 0.42828231068921574}, {"step": 679, "kl": 0.39749586230429995, "ce": 0.4171705397712114}, {"step": 680, "kl": 0.1764465950188743, "ce": 0.435322696362917}, {"step": 681, "kl": 0.35463313904485966, "ce": 0.3449089625689935}, {"step": 682, "kl": 0.22185619619850933, "ce": 0.3751153197490821}, {"step": 683, "kl": 0.1997884207313744, "ce": 0.3687337582918349}, {"step": 684, "kl": 0.181768275072956, "ce": 0.36408789769267635}, {"step": 685, "kl": 0.22060209792912927, "ce": 0.3709125309114736}, {"step": 686, "kl": 0.2525833559345221, "ce": 0.3518486798123861}, {"step": 687, "kl": 0.28554017382835034, "ce": 0.3714811403012953}, {"step": 688, "kl": 0.22093103561627758, "ce": 0.42470326120033475}, {"step": 689, "kl": 0.21649877569962994, "ce": 0.3560156865773467}, {"step": 690, "kl": 0.26039734590970554, "ce": 0.5345836074023271}, {"step": 691, "kl": 0.3200490204868795, "ce": 0.3970729297944966}, {"step": 692, "kl": 0.20614659794957646, "ce": 0.3463099330623642}, {"step": 693, "kl": 0.1937734919004784, "ce": 0.29855595187536643}, {"step": 694, "kl": 0.22129721456391402, "ce": 0.3475111346393092}, {"step": 695, "kl": 0.23483100956789565, "ce": 0.338655366874666}, {"step": 696, "kl": 0.2273293754926496, "ce": 0.32873799129998016}, {"step": 697, "kl": 0.18137110326551426, "ce": 0.36610975467001383}, {"step": 698, "kl": 0.3297614078683826, "ce": 0.38970039293363495}, {"step": 699, "kl": 0.2258169211681282, "ce": 0.4283712694252575}, {"step": 700, "kl": 0.19022075794605062, "ce": 0.28473432923894004}, {"step": 701, "kl": 0.22509819929840796, "ce": 0.35330368727294215}, {"step": 702, "kl": 0.2500558300505751, "ce": 0.448001490330064}, {"step": 703, "kl": 0.20002867129882132, "ce": 0.40308796643057976}, {"step": 704, "kl": 0.23618626951923907, "ce": 0.3437974680868387}, {"step": 705, "kl": 0.21508668139857104, "ce": 0.43562014463592724}, {"step": 706, "kl": 0.27266061471233005, "ce": 0.36292576456006953}, {"step": 707, "kl": 0.20840100276409682, "ce": 0.3062053334063836}, {"step": 708, "kl": 0.1862308990545489, "ce": 0.3035830108498715}, {"step": 709, "kl": 0.30178059403506147, "ce": 0.414868647562591}, {"step": 710, "kl": 0.19218766814587163, "ce": 0.4333517989774211}, {"step": 711, "kl": 0.2100006153057148, "ce": 0.35162139549210697}, {"step": 712, "kl": 0.2277448415701261, "ce": 0.3882466773169688}, {"step": 713, "kl": 0.1980163388265541, "ce": 0.3175408769585707}, {"step": 714, "kl": 0.1994402477502787, "ce": 0.29597749895142705}, {"step": 715, "kl": 0.20230363809343863, "ce": 0.38040382929286803}, {"step": 716, "kl": 0.21826168154831604, "ce": 0.3808075107413951}, {"step": 717, "kl": 0.19082908437484808, "ce": 0.3485576760336951}, {"step": 718, "kl": 0.23918165438960498, "ce": 0.3978847303175696}, {"step": 719, "kl": 0.2605259800486349, "ce": 0.3776546074137486}, {"step": 720, "kl": 0.22744730136230934, "ce": 0.4069003825652728}, {"step": 721, "kl": 0.5038792128254409, "ce": 0.3753283147066867}, {"step": 722, "kl": 0.2846377736826082, "ce": 0.4179014054346133}, {"step": 723, "kl": 0.23473504671520007, "ce": 0.3563911664924946}, {"step": 724, "kl": 0.21799168197512406, "ce": 0.26260183487346467}, {"step": 725, "kl": 0.18906966107884188, "ce": 0.3347600087561376}, {"step": 726, "kl": 0.2180581226256714, "ce": 0.3858527257728705}, {"step": 727, "kl": 0.24590442956138917, "ce": 0.3825244405995244}, {"step": 728, "kl": 0.191267362536988, "ce": 0.3560268803007284}, {"step": 729, "kl": 0.19821010754678975, "ce": 0.4431065683700605}, {"step": 730, "kl": 0.22496332134460342, "ce": 0.3623866505894586}, {"step": 731, "kl": 0.2614796589393649, "ce": 0.3479570108596409}, {"step": 732, "kl": 0.19443264278197717, "ce": 0.37369117905805094}, {"step": 733, "kl": 0.9483541403341731, "ce": 0.3579477754923014}, {"step": 734, "kl": 0.20210929999527816, "ce": 0.3158627346819942}, {"step": 735, "kl": 0.2406918573964386, "ce": 0.3745445750505063}, {"step": 736, "kl": 0.6063312071766553, "ce": 0.3360053168890192}, {"step": 737, "kl": 0.24365907387673083, "ce": 0.5096271068729155}, {"step": 738, "kl": 0.42211020112305575, "ce": 0.3141753710827941}, {"step": 739, "kl": 0.19382231194528327, "ce": 0.36463732066510396}, {"step": 740, "kl": 0.3426011033961924, "ce": 0.41156036709502386}, {"step": 741, "kl": 0.21262679490131225, "ce": 0.3485662552068975}, {"step": 742, "kl": 0.1782668326280345, "ce": 0.3323164660290417}, {"step": 743, "kl": 0.24438165328530576, "ce": 0.3497079559603086}, {"step": 744, "kl": 0.21399535537215036, "ce": 0.41856381425883626}, {"step": 745, "kl": 0.2237487520914663, "ce": 0.35365285812583397}, {"step": 746, "kl": 0.2168845478739113, "ce": 0.3403911301837568}, {"step": 747, "kl": 0.2935377965980467, "ce": 0.34765802819533137}, {"step": 748, "kl": 0.21281673150894453, "ce": 0.3914259142370107}, {"step": 749, "kl": 0.5173454861696153, "ce": 0.5032080096516348}, {"step": 750, "kl": 0.1777194664766519, "ce": 0.3817811448243238}, {"step": 751, "kl": 0.3063820790254243, "ce": 0.4231662029940823}, {"step": 752, "kl": 0.20717969644579828, "ce": 0.35358677867626254}, {"step": 753, "kl": 0.4088489558449587, "ce": 0.4146713869231361}, {"step": 754, "kl": 0.20125737205009342, "ce": 0.3397443499140198}, {"step": 755, "kl": 0.39810744201865744, "ce": 0.3890343053665111}, {"step": 756, "kl": 0.3541584159742069, "ce": 0.4121441912295213}, {"step": 757, "kl": 0.1915913003443448, "ce": 0.2960211384902649}, {"step": 758, "kl": 0.3457781565727648, "ce": 0.32382303677248153}, {"step": 759, "kl": 0.3464215243672685, "ce": 0.38002507306527394}, {"step": 760, "kl": 0.21480394378234957, "ce": 0.38727039408747693}, {"step": 761, "kl": 0.2473931894957564, "ce": 0.452175838772037}, {"step": 762, "kl": 0.28628130492066384, "ce": 0.43484555437265193}, {"step": 763, "kl": 0.25529671084258265, "ce": 0.4269324736370828}, {"step": 764, "kl": 0.29326096378360783, "ce": 0.41002791050065396}, {"step": 765, "kl": 0.25565260001496265, "ce": 0.43646866112919896}, {"step": 766, "kl": 0.1663306199566851, "ce": 0.349367698503138}, {"step": 767, "kl": 0.2258991684197415, "ce": 0.4337149777912136}, {"step": 768, "kl": 0.2160702546380196, "ce": 0.3201346374782343}, {"step": 769, "kl": 0.20155791093790346, "ce": 0.45780476472736964}, {"step": 770, "kl": 0.7390188282737105, "ce": 0.34091639206022334}, {"step": 771, "kl": 0.22969576036239459, "ce": 0.4348704036875765}, {"step": 772, "kl": 0.30063289696119166, "ce": 0.34771997379095415}, {"step": 773, "kl": 0.18815450385356455, "ce": 0.3513342829871336}, {"step": 774, "kl": 0.22080915909447754, "ce": 0.4477346098143919}, {"step": 775, "kl": 0.6329798716917593, "ce": 0.3827230089949566}, {"step": 776, "kl": 0.2205436928922061, "ce": 0.39053405806200214}, {"step": 777, "kl": 0.24508620281608737, "ce": 0.36343239022335316}, {"step": 778, "kl": 0.18469906863825558, "ce": 0.3265216160763899}, {"step": 779, "kl": 0.22501476042184754, "ce": 0.3193997379036331}, {"step": 780, "kl": 0.26993695124354933, "ce": 0.2708615383279289}, {"step": 781, "kl": 0.20900918890515172, "ce": 0.33767132877002287}, {"step": 782, "kl": 0.4499965839604042, "ce": 0.36999196496628617}, {"step": 783, "kl": 0.27021881744079446, "ce": 0.3439485266238828}, {"step": 784, "kl": 0.1981331030042272, "ce": 0.2857327189912786}, {"step": 785, "kl": 0.1928227098931644, "ce": 0.35724038068881764}, {"step": 786, "kl": 0.21634905770321017, "ce": 0.3177275198652608}, {"step": 787, "kl": 0.18713451341015286, "ce": 0.4050988001809032}, {"step": 788, "kl": 0.3776774009001628, "ce": 0.36032258862491257}, {"step": 789, "kl": 0.17797574052821277, "ce": 0.37663868892530683}, {"step": 790, "kl": 0.21698162501372226, "ce": 0.29219583524720383}, {"step": 791, "kl": 0.23190615274351561, "ce": 0.3660767796973181}, {"step": 792, "kl": 0.22677468147747074, "ce": 0.3602744499720622}, {"step": 793, "kl": 0.1827087498174363, "ce": 0.3165342392607363}, {"step": 794, "kl": 0.2275184848805769, "ce": 0.2760868627092923}, {"step": 795, "kl": 0.19428317442558832, "ce": 0.4194616572374599}, {"step": 796, "kl": 0.18437330797927434, "ce": 0.33211560166159343}, {"step": 797, "kl": 0.21337226726893815, "ce": 0.3272274888647213}, {"step": 798, "kl": 0.19772977332438943, "ce": 0.40553136559220043}, {"step": 799, "kl": 0.4566251610815668, "ce": 0.3341779807179244}, {"step": 800, "kl": 0.20523092339297455, "ce": 0.4035652096889145}, {"step": 801, "kl": 0.20854098507714416, "ce": 0.3598977141553048}, {"step": 802, "kl": 0.2857625344564661, "ce": 0.4528228473138096}, {"step": 803, "kl": 0.46188135807688646, "ce": 0.42118747343031904}, {"step": 804, "kl": 0.19562288647547268, "ce": 0.3454560197308057}, {"step": 805, "kl": 0.35938700263290185, "ce": 0.3653960987466516}, {"step": 806, "kl": 0.260355928490803, "ce": 0.3586192778522438}, {"step": 807, "kl": 0.24872458740587494, "ce": 0.36772411696094226}, {"step": 808, "kl": 0.18597769480402251, "ce": 0.3336022074707728}, {"step": 809, "kl": 0.30559191585627316, "ce": 0.3339131467369125}, {"step": 810, "kl": 0.25326468877032055, "ce": 0.3998748131157568}, {"step": 811, "kl": 0.3192067399858251, "ce": 0.27596826741040703}, {"step": 812, "kl": 0.1883010745761353, "ce": 0.3724397000878937}, {"step": 813, "kl": 0.2573967665965398, "ce": 0.4742661900379401}, {"step": 814, "kl": 0.2644112981936261, "ce": 0.32977829276569853}, {"step": 815, "kl": 0.21141069412507432, "ce": 0.2675618061281765}, {"step": 816, "kl": 0.18484628019089178, "ce": 0.4709403749104229}, {"step": 817, "kl": 0.22425539676274095, "ce": 0.47689911645611205}, {"step": 818, "kl": 0.20986669973104413, "ce": 0.32106835756145546}, {"step": 819, "kl": 0.23772003542683212, "ce": 0.2896221826167329}, {"step": 820, "kl": 0.27213381182576324, "ce": 0.4309760468152105}, {"step": 821, "kl": 0.20507955571107156, "ce": 0.4147885406284037}, {"step": 822, "kl": 0.22251145187027097, "ce": 0.39859526953315083}, {"step": 823, "kl": 0.222259638720934, "ce": 0.2996214671488626}, {"step": 824, "kl": 0.44824043189500334, "ce": 0.3512823645814066}, {"step": 825, "kl": 0.32373751544889195, "ce": 0.29354443711012856}, {"step": 826, "kl": 0.2133447899663366, "ce": 0.3869781395849018}, {"step": 827, "kl": 0.23329747966658143, "ce": 0.41302263775846515}, {"step": 828, "kl": 0.2385067158552067, "ce": 0.38849165461383833}, {"step": 829, "kl": 0.39198624122089304, "ce": 0.3432792914100941}, {"step": 830, "kl": 0.24121555376258938, "ce": 0.38610195201602787}, {"step": 831, "kl": 0.2234848078122247, "ce": 0.37943407361556447}, {"step": 832, "kl": 0.21589980439852766, "ce": 0.48929847472332005}, {"step": 833, "kl": 0.33413132883163754, "ce": 0.42627265825716526}, {"step": 834, "kl": 0.2026272428993867, "ce": 0.30283007643498827}, {"step": 835, "kl": 0.22163011166574048, "ce": 0.3460675969787994}, {"step": 836, "kl": 0.2117367287096478, "ce": 0.36660138975751894}, {"step": 837, "kl": 0.2415901521575355, "ce": 0.32327174489141913}, {"step": 838, "kl": 0.1943680034459464, "ce": 0.3570729227662848}, {"step": 839, "kl": 0.21263587194030237, "ce": 0.4595813588850858}, {"step": 840, "kl": 0.2226410098660554, "ce": 0.42313160133973426}, {"step": 841, "kl": 0.324178487449828, "ce": 0.41587597653674924}, {"step": 842, "kl": 0.42415559186114854, "ce": 0.301123751463638}, {"step": 843, "kl": 0.20719287520334906, "ce": 0.37045681938871544}, {"step": 844, "kl": 0.2553647070836211, "ce": 0.4270976976958443}, {"step": 845, "kl": 1.1035269080603822, "ce": 0.39048441232743747}, {"step": 846, "kl": 0.2525209146244067, "ce": 0.4704334231177275}, {"step": 847, "kl": 0.1830590032553365, "ce": 0.3481153256294563}, {"step": 848, "kl": 0.3111063769865931, "ce": 0.3904689788242208}, {"step": 849, "kl": 0.2057612739605041, "ce": 0.3192279265496901}, {"step": 850, "kl": 0.2590724447499151, "ce": 0.36591252247151385}, {"step": 851, "kl": 0.18053901769069525, "ce": 0.3421593074196188}, {"step": 852, "kl": 0.576866437769864, "ce": 0.32797104211253975}, {"step": 853, "kl": 0.4326815590644827, "ce": 0.4132566428627418}, {"step": 854, "kl": 0.3421517093581079, "ce": 0.3847798920916496}, {"step": 855, "kl": 0.2559351265786589, "ce": 0.4015336430228954}, {"step": 856, "kl": 0.22290337788886996, "ce": 0.45011315998753226}, {"step": 857, "kl": 0.2859759076750923, "ce": 0.25461624834767754}, {"step": 858, "kl": 0.2344681507586099, "ce": 0.3798463662973227}, {"step": 859, "kl": 0.21228314474995066, "ce": 0.37772366700181315}, {"step": 860, "kl": 0.20571019819460895, "ce": 0.36376544074036254}, {"step": 861, "kl": 0.19252483593353945, "ce": 0.3457482024944597}, {"step": 862, "kl": 0.20159457992470925, "ce": 0.28458628784343576}, {"step": 863, "kl": 0.2134506889050217, "ce": 0.3317053369984143}, {"step": 864, "kl": 0.26127358459520006, "ce": 0.3143044424140516}, {"step": 865, "kl": 0.22825309149355277, "ce": 0.382836341163445}, {"step": 866, "kl": 0.47066123540775057, "ce": 0.4279212372571293}, {"step": 867, "kl": 0.39085124042473696, "ce": 0.3827711558464666}, {"step": 868, "kl": 0.34191256018671784, "ce": 0.3688882652256224}, {"step": 869, "kl": 0.3698891372868838, "ce": 0.3977825034019401}, {"step": 870, "kl": 0.235772566835748, "ce": 0.32898233978025304}, {"step": 871, "kl": 0.20306062747203843, "ce": 0.34974141148633736}, {"step": 872, "kl": 0.19084588154806492, "ce": 0.4678978579176878}, {"step": 873, "kl": 0.23740076845479427, "ce": 0.2680651531479683}, {"step": 874, "kl": 0.20501452461520864, "ce": 0.29610007644262654}, {"step": 875, "kl": 0.18804004532329405, "ce": 0.32370482140161116}, {"step": 876, "kl": 0.2509505189467417, "ce": 0.4550923759737229}, {"step": 877, "kl": 0.2208733792026618, "ce": 0.26281510355970655}, {"step": 878, "kl": 0.30186097008753454, "ce": 0.32669521540603236}, {"step": 879, "kl": 0.3322428318597826, "ce": 0.3551616839755211}, {"step": 880, "kl": 0.2587243438066938, "ce": 0.41408781174677567}, {"step": 881, "kl": 0.20618821678243032, "ce": 0.42204717967821204}, {"step": 882, "kl": 0.18164617732619018, "ce": 0.3621269757500133}, {"step": 883, "kl": 0.287746484674251, "ce": 0.31244690681677123}, {"step": 884, "kl": 0.22808222874317546, "ce": 0.4918639097284674}, {"step": 885, "kl": 0.20799597636117412, "ce": 0.3756878293942714}, {"step": 886, "kl": 1.2378630308426366, "ce": 0.3528356850823651}, {"step": 887, "kl": 0.3817812655968468, "ce": 0.3806246310768335}, {"step": 888, "kl": 0.6027363355220198, "ce": 0.4626208175544698}, {"step": 889, "kl": 0.22140689047031778, "ce": 0.3519501339499858}, {"step": 890, "kl": 0.387308648477248, "ce": 0.46480252449972587}, {"step": 891, "kl": 0.2352074534859355, "ce": 0.3162647968102555}, {"step": 892, "kl": 0.1786959008273915, "ce": 0.39936701174717437}, {"step": 893, "kl": 0.18325630048869848, "ce": 0.5362487415856101}, {"step": 894, "kl": 0.21715271940038594, "ce": 0.5163477216025656}, {"step": 895, "kl": 0.2079609802979122, "ce": 0.41734602005501104}, {"step": 896, "kl": 0.22878385382183525, "ce": 0.28822768488309986}], "val": [{"step": 0, "math_kl": 0.15910778235068246, "math_ce": 0.6515277156879916, "code_kl": 0.14790875576132695, "code_ce": 0.30340147782401555, "math_hard_kl": 0.24894053959908363, "math_hard_ce": 0.6765219455834559}, {"step": 448, "math_kl": 0.24873583011186062, "math_ce": 0.44984783213262436, "code_kl": 0.1635836904596511, "code_ce": 0.3322650104861914, "math_hard_kl": 0.29838466209374986, "math_hard_ce": 0.5987757998844804}, {"step": 896, "math_kl": 0.25596919708371585, "math_ce": 0.4875917011939159, "code_kl": 0.16789859193652845, "code_ce": 0.33237521285888244, "math_hard_kl": 0.3207115241939215, "math_hard_ce": 0.6152356422562573}]}
|
seq_math_code_gt_sft/stage1_math/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd3218a61cebe4b49b79570f69aa44395f19acaf42073c3d9f110f0a43ed90b5
|
| 3 |
+
size 3087467144
|