Upload folder using huggingface_hub
Browse files
seq_code_math_kd_only/run_info.json
CHANGED
|
@@ -32,9 +32,38 @@
|
|
| 32 |
"math_hard_ce": 0.6718085009279865
|
| 33 |
},
|
| 34 |
"peak_gb_student": 33.80862855911255,
|
| 35 |
-
"peak_gb_teachers": 30.005428314208984
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
}
|
| 40 |
}
|
|
|
|
| 32 |
"math_hard_ce": 0.6718085009279865
|
| 33 |
},
|
| 34 |
"peak_gb_student": 33.80862855911255,
|
| 35 |
+
"peak_gb_teachers": 30.005428314208984
|
| 36 |
+
},
|
| 37 |
+
"stage2_math": {
|
| 38 |
+
"domain": "math",
|
| 39 |
+
"steps": 896,
|
| 40 |
+
"train_h": 2.814592224955559,
|
| 41 |
+
"val_start": {
|
| 42 |
+
"step": 0,
|
| 43 |
+
"math_kl": 0.16056643818369662,
|
| 44 |
+
"math_ce": 0.6179343579401348,
|
| 45 |
+
"code_kl": 0.07794113298743313,
|
| 46 |
+
"code_ce": 0.309922693351798,
|
| 47 |
+
"math_hard_kl": 0.24884287280595874,
|
| 48 |
+
"math_hard_ce": 0.6717120443366895
|
| 49 |
+
},
|
| 50 |
+
"val_end": {
|
| 51 |
+
"step": 896,
|
| 52 |
+
"math_kl": 0.0759878009343543,
|
| 53 |
+
"math_ce": 0.8331185948595244,
|
| 54 |
+
"code_kl": 0.10406180013954185,
|
| 55 |
+
"code_ce": 0.3197136727378907,
|
| 56 |
+
"math_hard_kl": 0.08557213517622467,
|
| 57 |
+
"math_hard_ce": 0.8143728766945073
|
| 58 |
+
},
|
| 59 |
+
"peak_gb_student": 36.68444871902466,
|
| 60 |
+
"peak_gb_teachers": 30.639182090759277
|
| 61 |
}
|
| 62 |
+
},
|
| 63 |
+
"resumed": {
|
| 64 |
+
"from": "stage1_code",
|
| 65 |
+
"gpu_student": "NVIDIA RTX 6000 Ada Generation",
|
| 66 |
+
"gpu_teachers": "NVIDIA RTX A6000",
|
| 67 |
+
"load_h": 0.008158521188629999
|
| 68 |
}
|
| 69 |
}
|
seq_code_math_kd_only/stage2_math/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 32768,
|
| 44 |
+
"max_window_layers": 21,
|
| 45 |
+
"model_type": "qwen2",
|
| 46 |
+
"num_attention_heads": 12,
|
| 47 |
+
"num_hidden_layers": 28,
|
| 48 |
+
"num_key_value_heads": 2,
|
| 49 |
+
"pad_token_id": null,
|
| 50 |
+
"rms_norm_eps": 1e-06,
|
| 51 |
+
"rope_parameters": {
|
| 52 |
+
"rope_theta": 1000000.0,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
},
|
| 55 |
+
"sliding_window": null,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "5.20.2",
|
| 58 |
+
"use_cache": false,
|
| 59 |
+
"use_sliding_window": false,
|
| 60 |
+
"vocab_size": 151936
|
| 61 |
+
}
|
seq_code_math_kd_only/stage2_math/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.20.2"
|
| 14 |
+
}
|
seq_code_math_kd_only/stage2_math/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.18535575502688115, "ce": 0.6080289652491528}, {"step": 2, "kl": 0.13458935512621897, "ce": 0.6830729696702553}, {"step": 3, "kl": 0.09752135854642935, "ce": 0.5604452858983943}, {"step": 4, "kl": 0.16698641723749535, "ce": 0.6072032048768619}, {"step": 5, "kl": 0.12971824808122046, "ce": 0.6832351160377059}, {"step": 6, "kl": 0.20616042498708093, "ce": 0.5131842409256608}, {"step": 7, "kl": 1.0263799179629223, "ce": 0.6390285014127068}, {"step": 8, "kl": 0.1220102485954327, "ce": 0.6730168665726424}, {"step": 9, "kl": 0.5153397653430583, "ce": 0.6389834706545006}, {"step": 10, "kl": 0.1823138039594845, "ce": 0.5956893136658644}, {"step": 11, "kl": 0.11674212548233828, "ce": 0.5749901422816205}, {"step": 12, "kl": 0.07769070220158497, "ce": 0.6309063964473466}, {"step": 13, "kl": 0.1300315132665754, "ce": 0.7280284913725228}, {"step": 14, "kl": 0.10892229513053837, "ce": 0.6445335923080543}, {"step": 15, "kl": 0.11309037060017386, "ce": 0.7289586926486089}, {"step": 16, "kl": 0.09621124067007036, "ce": 0.6145881812423346}, {"step": 17, "kl": 0.19117186307768658, "ce": 0.6228864467817772}, {"step": 18, "kl": 0.22430357986000757, "ce": 0.7012543221614171}, {"step": 19, "kl": 0.12310329751738724, "ce": 0.5629196954410066}, {"step": 20, "kl": 0.08705604625623733, "ce": 0.6883186625750358}, {"step": 21, "kl": 0.10235711433299652, "ce": 0.7200284959919164}, {"step": 22, "kl": 0.10214591235864502, "ce": 0.75625240006105}, {"step": 23, "kl": 0.2623657693374391, "ce": 0.6999439440275493}, {"step": 24, "kl": 0.11009451566452332, "ce": 0.6726482577309805}, {"step": 25, "kl": 0.0940696269693509, "ce": 0.6219754291603015}, {"step": 26, "kl": 0.07906259781880287, "ce": 0.6881114804519215}, {"step": 27, "kl": 0.10458909506288827, "ce": 0.7053655284811772}, {"step": 28, "kl": 0.11402789334200474, "ce": 0.6313123491301118}, {"step": 29, "kl": 0.09876827780225975, "ce": 0.6482442374649744}, {"step": 30, "kl": 0.0844230249535342, "ce": 0.7935909315729516}, {"step": 31, "kl": 0.10368030487740468, "ce": 0.6720425000876092}, {"step": 32, "kl": 0.12823635055520258, "ce": 0.7317876208191763}, {"step": 33, "kl": 0.1008596566788656, "ce": 0.8186552230248254}, {"step": 34, "kl": 0.08848803027969775, "ce": 0.7810076189893451}, {"step": 35, "kl": 0.09065507565420783, "ce": 0.7829634046668914}, {"step": 36, "kl": 0.10267979857245889, "ce": 0.8501025199473866}, {"step": 37, "kl": 0.13081253198119064, "ce": 0.8761714087909249}, {"step": 38, "kl": 0.09273876297139676, "ce": 0.7012541075851331}, {"step": 39, "kl": 0.09646818405585669, "ce": 0.7920290788187685}, {"step": 40, "kl": 0.08961728842969072, "ce": 0.848887714216002}, {"step": 41, "kl": 0.08939908328687274, "ce": 0.7566247325905059}, {"step": 42, "kl": 0.11806713616083972, "ce": 0.6790381884876773}, {"step": 43, "kl": 0.08111390443605798, "ce": 0.9252538218630487}, {"step": 44, "kl": 0.09505089429412536, "ce": 0.8508855935707793}, {"step": 45, "kl": 0.10726770085339347, "ce": 0.7110966482423359}, {"step": 46, "kl": 0.08128275642214616, "ce": 0.8800415446058745}, {"step": 47, "kl": 0.10421518048016395, "ce": 0.8535366308376585}, {"step": 48, "kl": 0.11567929963742442, "ce": 0.7552675975066374}, {"step": 49, "kl": 0.09394415722661585, "ce": 0.7142879919228338}, {"step": 50, "kl": 0.09979518252813878, "ce": 0.7478409200501976}, {"step": 51, "kl": 0.09191389904017336, "ce": 0.5996574992216296}, {"step": 52, "kl": 0.07778039797305993, "ce": 0.7760561675136961}, {"step": 53, "kl": 0.11160603020815694, "ce": 0.7874545203470544}, {"step": 54, "kl": 0.08442350591985597, "ce": 0.8636094637912286}, {"step": 55, "kl": 0.08102489177417378, "ce": 0.8270767579311458}, {"step": 56, "kl": 0.07936317511473232, "ce": 0.6455809016165452}, {"step": 57, "kl": 0.08514274734537852, "ce": 0.9169341577065959}, {"step": 58, "kl": 0.09017306883123857, "ce": 0.8623928139154897}, {"step": 59, "kl": 0.11090510742570642, "ce": 0.8501791577613339}, {"step": 60, "kl": 0.0974742392024368, "ce": 0.7405441609839735}, {"step": 61, "kl": 0.06746604450774185, "ce": 0.6226940351663176}, {"step": 62, "kl": 0.07984105906913502, "ce": 0.6899470130009439}, {"step": 63, "kl": 0.0866875949488444, "ce": 0.7913841776547654}, {"step": 64, "kl": 0.09106328321215437, "ce": 0.627807981739725}, {"step": 65, "kl": 0.08768035139992972, "ce": 0.7371943194886105}, {"step": 66, "kl": 0.08436565350242639, "ce": 0.6744204651916698}, {"step": 67, "kl": 0.10949085090285154, "ce": 0.8070377579654555}, {"step": 68, "kl": 0.08438449464378335, "ce": 0.7285067756048913}, {"step": 69, "kl": 0.09967878687885368, "ce": 0.7910900795884696}, {"step": 70, "kl": 0.10120416364905692, "ce": 0.8011570241191599}, {"step": 71, "kl": 0.08089340240261748, "ce": 0.6938429659852122}, {"step": 72, "kl": 0.09502218362125574, "ce": 0.7600983320865413}, {"step": 73, "kl": 0.07884666147960046, "ce": 0.6846920641184894}, {"step": 74, "kl": 0.08454774228237999, "ce": 0.9435066529164506}, {"step": 75, "kl": 0.08725673474937361, "ce": 0.7036431469128257}, {"step": 76, "kl": 0.0814771938273282, "ce": 0.792551894726842}, {"step": 77, "kl": 0.09483942717970732, "ce": 0.7713110699769744}, {"step": 78, "kl": 0.07338904231623478, "ce": 0.6628558902191036}, {"step": 79, "kl": 0.09643060420912766, "ce": 0.7476883745283962}, {"step": 80, "kl": 0.0933813890959843, "ce": 0.6860131590905851}, {"step": 81, "kl": 0.1082132948451034, "ce": 0.764335539763602}, {"step": 82, "kl": 0.09474485920257096, "ce": 0.9085680813259549}, {"step": 83, "kl": 0.0927906558175242, "ce": 0.6694921951691221}, {"step": 84, "kl": 0.11257417472353393, "ce": 0.8387099858983726}, {"step": 85, "kl": 0.07579681073954564, "ce": 0.6456336050322561}, {"step": 86, "kl": 0.08046171537258164, "ce": 0.7176481293203488}, {"step": 87, "kl": 0.11534658565929748, "ce": 0.7162610622518973}, {"step": 88, "kl": 0.1196702094439461, "ce": 0.9014399256812552}, {"step": 89, "kl": 0.09408402759697293, "ce": 0.8479565106288438}, {"step": 90, "kl": 0.07225920825909549, "ce": 0.6348202853880743}, {"step": 91, "kl": 0.09871582038733992, "ce": 0.791507104860264}, {"step": 92, "kl": 0.07415314747317601, "ce": 0.7271827379064293}, {"step": 93, "kl": 0.09524238600713036, "ce": 0.6637429305027689}, {"step": 94, "kl": 0.08682565494768517, "ce": 0.8446667446630427}, {"step": 95, "kl": 0.09448217281023287, "ce": 0.8633165974262331}, {"step": 96, "kl": 0.10158109679104352, "ce": 0.7521738250482559}, {"step": 97, "kl": 0.0728114323478092, "ce": 0.6674138120278097}, {"step": 98, "kl": 0.0770479802764789, "ce": 0.8696485399109387}, {"step": 99, "kl": 0.09433963188166257, "ce": 0.7036320143352353}, {"step": 100, "kl": 0.0844115750627064, "ce": 0.7264608630935658}, {"step": 101, "kl": 0.07916741644151984, "ce": 0.845371542573567}, {"step": 102, "kl": 0.08331934776090567, "ce": 0.7776991779084869}, {"step": 103, "kl": 0.08324803621469848, "ce": 0.7496868688788985}, {"step": 104, "kl": 0.15448308397491736, "ce": 0.9527729287383995}, {"step": 105, "kl": 0.1258275091264181, "ce": 0.7882585194649071}, {"step": 106, "kl": 0.10399895139664769, "ce": 0.9613232333792416}, {"step": 107, "kl": 0.10083297235484481, "ce": 0.7607469457011422}, {"step": 108, "kl": 0.07021005351696148, "ce": 0.7751300708134147}, {"step": 109, "kl": 0.09073511587885091, "ce": 0.8978931804975013}, {"step": 110, "kl": 0.10903923585497766, "ce": 0.8754774255676523}, {"step": 111, "kl": 0.09279005089537434, "ce": 0.8065274920155687}, {"step": 112, "kl": 0.07447299669843531, "ce": 0.7316749594389208}, {"step": 113, "kl": 0.09272993391158797, "ce": 0.7440162114127558}, {"step": 114, "kl": 0.07539335813789866, "ce": 0.6413704286573514}, {"step": 115, "kl": 0.06985685662472488, "ce": 0.7257674990128165}, {"step": 116, "kl": 0.06674355528980215, "ce": 0.8214297750109509}, {"step": 117, "kl": 0.08839994793053518, "ce": 0.8748870703643358}, {"step": 118, "kl": 0.0919755652321418, "ce": 0.705653030386048}, {"step": 119, "kl": 0.08462244304175516, "ce": 0.9022142672737381}, {"step": 120, "kl": 0.10794680482002689, "ce": 0.74660455808597}, {"step": 121, "kl": 0.08573289323680408, "ce": 0.7785114504573237}, {"step": 122, "kl": 0.07388344021211314, "ce": 0.7246546863883263}, {"step": 123, "kl": 0.06527631949389223, "ce": 0.7197324007612879}, {"step": 124, "kl": 0.08835533882922447, "ce": 0.8844166964119593}, {"step": 125, "kl": 0.07990717237384266, "ce": 0.7751070592905615}, {"step": 126, "kl": 0.08229803268562842, "ce": 0.843184286957145}, {"step": 127, "kl": 0.09933368638314741, "ce": 0.8478668057913503}, {"step": 128, "kl": 0.0714100966323568, "ce": 0.7682527632160759}, {"step": 129, "kl": 0.09264909573059467, "ce": 0.8879073057796079}, {"step": 130, "kl": 0.06936207169320856, "ce": 0.7827093795189367}, {"step": 131, "kl": 0.07547973690795634, "ce": 0.838979235686709}, {"step": 132, "kl": 0.0820354517643876, "ce": 0.853476071212223}, {"step": 133, "kl": 0.08971156327858414, "ce": 0.657119856137066}, {"step": 134, "kl": 0.07720365693042036, "ce": 0.7599106561232531}, {"step": 135, "kl": 0.06963652400541206, "ce": 0.7030078086349483}, {"step": 136, "kl": 0.09924134777746775, "ce": 0.7282806681405377}, {"step": 137, "kl": 0.07630268087300944, "ce": 0.7837927977661239}, {"step": 138, "kl": 0.1105610194551935, "ce": 0.81225686454361}, {"step": 139, "kl": 0.10437578710139105, "ce": 0.8135789195943324}, {"step": 140, "kl": 0.09827276076281015, "ce": 0.8188276815423763}, {"step": 141, "kl": 0.07843243279199417, "ce": 0.8885295758605474}, {"step": 142, "kl": 0.08750532040502887, "ce": 0.6535463671837742}, {"step": 143, "kl": 0.08829711591546234, "ce": 0.8524813848488337}, {"step": 144, "kl": 0.09607649386658959, "ce": 0.8138841681918404}, {"step": 145, "kl": 0.0842379282940378, "ce": 0.8786273388232471}, {"step": 146, "kl": 0.06867122457145963, "ce": 0.9646936167181575}, {"step": 147, "kl": 0.07093344275853326, "ce": 0.7070680860423746}, {"step": 148, "kl": 0.09922654433606784, "ce": 0.8454522538595589}, {"step": 149, "kl": 0.10771445226854187, "ce": 0.6757773295836416}, {"step": 150, "kl": 0.07179896844216815, "ce": 0.8500280534779584}, {"step": 151, "kl": 0.07948748113183922, "ce": 0.858109275985755}, {"step": 152, "kl": 0.1131230594298271, "ce": 0.8083491336640515}, {"step": 153, "kl": 0.07601941035424649, "ce": 0.7969790438574607}, {"step": 154, "kl": 0.08304136743986215, "ce": 0.8082462697296846}, {"step": 155, "kl": 0.1370003574038512, "ce": 0.7996793806384035}, {"step": 156, "kl": 0.10318682691634884, "ce": 0.6896806535464574}, {"step": 157, "kl": 0.09265745025908877, "ce": 0.7619838399700206}, {"step": 158, "kl": 0.07850087175913896, "ce": 0.687979014239838}, {"step": 159, "kl": 0.12829263175635572, "ce": 0.8249788075496455}, {"step": 160, "kl": 0.07537478429925722, "ce": 0.8116262792445057}, {"step": 161, "kl": 0.08707864357628034, "ce": 0.7071871641606235}, {"step": 162, "kl": 0.07468341837576287, "ce": 0.8214021578369406}, {"step": 163, "kl": 0.08883907070953007, "ce": 0.7950277760618201}, {"step": 164, "kl": 0.06879449778900681, "ce": 0.8085653195638208}, {"step": 165, "kl": 0.098717934604901, "ce": 0.741277392336649}, {"step": 166, "kl": 0.08798743414451014, "ce": 0.6788045588562271}, {"step": 167, "kl": 0.09898112509010598, "ce": 0.870793575340541}, {"step": 168, "kl": 0.09543240943542267, "ce": 0.7249036286007705}, {"step": 169, "kl": 0.07354843126560046, "ce": 0.7679436359773467}, {"step": 170, "kl": 0.08040904759363152, "ce": 0.720762140333038}, {"step": 171, "kl": 0.09557491958956074, "ce": 0.7362985030408875}, {"step": 172, "kl": 0.0735040000210569, "ce": 0.7151079170990541}, {"step": 173, "kl": 0.09525391870434964, "ce": 0.8658315313385896}, {"step": 174, "kl": 0.11010360298799166, "ce": 0.7859909774473048}, {"step": 175, "kl": 0.11039061690366328, "ce": 0.7846464400323446}, {"step": 176, "kl": 0.07062983642399587, "ce": 0.9585651247688894}, {"step": 177, "kl": 0.07856543721703219, "ce": 0.7551518314055403}, {"step": 178, "kl": 0.07628189911699099, "ce": 0.6735597457305316}, {"step": 179, "kl": 0.09362763837439317, "ce": 0.8234317980314555}, {"step": 180, "kl": 0.07291792430418874, "ce": 0.8178496981151353}, {"step": 181, "kl": 0.11888415097007407, "ce": 0.832612355800685}, {"step": 182, "kl": 0.09557367591727715, "ce": 0.7452490164262064}, {"step": 183, "kl": 0.07317527717987578, "ce": 0.8963086155896332}, {"step": 184, "kl": 0.0882329749926878, "ce": 0.6916578062274396}, {"step": 185, "kl": 0.0783383909256341, "ce": 0.8571223949926287}, {"step": 186, "kl": 0.08110806200555568, "ce": 0.8261895128475722}, {"step": 187, "kl": 0.09748734734009937, "ce": 0.7768389916104892}, {"step": 188, "kl": 0.08229358701844722, "ce": 0.7826954455326605}, {"step": 189, "kl": 0.11044174529540865, "ce": 0.7125613854640113}, {"step": 190, "kl": 0.06928221949580181, "ce": 0.7762854071579866}, {"step": 191, "kl": 0.10666112314514076, "ce": 0.8384732401261831}, {"step": 192, "kl": 0.08516508378233166, "ce": 0.9052017167497525}, {"step": 193, "kl": 0.0699182685347628, "ce": 0.8157406460978986}, {"step": 194, "kl": 0.1244523620822013, "ce": 0.8309696788885321}, {"step": 195, "kl": 0.07343793581814362, "ce": 0.881545542645198}, {"step": 196, "kl": 0.08724090261961866, "ce": 0.8744344896279532}, {"step": 197, "kl": 0.0892221292254351, "ce": 0.7257866744544682}, {"step": 198, "kl": 0.0722310621342463, "ce": 0.8649924430824538}, {"step": 199, "kl": 0.07120728182141893, "ce": 0.7772120184524693}, {"step": 200, "kl": 0.060987119260432446, "ce": 0.6982953033035978}, {"step": 201, "kl": 0.09682348313310804, "ce": 0.8102509405369265}, {"step": 202, "kl": 0.09146668643237435, "ce": 0.6548566633770724}, {"step": 203, "kl": 0.10669455179666049, "ce": 0.7986783027181973}, {"step": 204, "kl": 0.07037948635003843, "ce": 0.6908398581332849}, {"step": 205, "kl": 0.09502774186499878, "ce": 0.7105190533037765}, {"step": 206, "kl": 0.09659251870671591, "ce": 0.7893889509300237}, {"step": 207, "kl": 0.07913281597429997, "ce": 0.7197116880308837}, {"step": 208, "kl": 0.07615657741836585, "ce": 0.7237627085150459}, {"step": 209, "kl": 0.09266546550689676, "ce": 0.8029072302359122}, {"step": 210, "kl": 0.0941872178246396, "ce": 0.7513330392031969}, {"step": 211, "kl": 0.0717204356884519, "ce": 0.7736014787084432}, {"step": 212, "kl": 0.10120540265121013, "ce": 0.7946234089099875}, {"step": 213, "kl": 0.08407111084844263, "ce": 0.5804618268030091}, {"step": 214, "kl": 0.08767127542080906, "ce": 0.801889390136405}, {"step": 215, "kl": 0.07821501866874742, "ce": 0.8361637903432377}, {"step": 216, "kl": 0.08635197096604567, "ce": 0.8656621631147082}, {"step": 217, "kl": 0.06352963739800725, "ce": 0.7914393357932568}, {"step": 218, "kl": 0.09221283705470407, "ce": 0.7837710838317871}, {"step": 219, "kl": 0.1005075475299685, "ce": 0.7570964934777299}, {"step": 220, "kl": 0.10090231143601223, "ce": 0.7177851906560218}, {"step": 221, "kl": 0.07032261199907582, "ce": 0.7102214577363182}, {"step": 222, "kl": 0.08380962309899269, "ce": 0.7826024983330436}, {"step": 223, "kl": 0.10698234655533886, "ce": 0.8666737937424611}, {"step": 224, "kl": 0.08470426908991986, "ce": 0.8727942395456649}, {"step": 225, "kl": 0.09419251214730592, "ce": 0.8526342031043499}, {"step": 226, "kl": 0.07828523807643215, "ce": 0.7693397574075839}, {"step": 227, "kl": 0.07918407814577222, "ce": 0.7645557584923953}, {"step": 228, "kl": 0.08907570239269372, "ce": 0.7756548342833126}, {"step": 229, "kl": 0.08625301794395947, "ce": 0.8075586621326541}, {"step": 230, "kl": 0.08675045528125085, "ce": 0.7325805351692748}, {"step": 231, "kl": 0.08627399002394695, "ce": 0.791061576030125}, {"step": 232, "kl": 0.09536522355396436, "ce": 0.7378724086326746}, {"step": 233, "kl": 0.08135583126680135, "ce": 0.7226443835130828}, {"step": 234, "kl": 0.07807785026776103, "ce": 0.7413148790662345}, {"step": 235, "kl": 0.07940445640144635, "ce": 0.7412151417451747}, {"step": 236, "kl": 0.08257120989114738, "ce": 0.8206141484110606}, {"step": 237, "kl": 0.0872760158211542, "ce": 0.8093606529343209}, {"step": 238, "kl": 0.07971877063859889, "ce": 0.7437111869206605}, {"step": 239, "kl": 0.0732159027572312, "ce": 0.7615484068847196}, {"step": 240, "kl": 0.06861794308680089, "ce": 0.8318027813137361}, {"step": 241, "kl": 0.07240270186084503, "ce": 0.7147719244562273}, {"step": 242, "kl": 0.09998263928385605, "ce": 0.7500482008126611}, {"step": 243, "kl": 0.07680365304078507, "ce": 0.5985323361262123}, {"step": 244, "kl": 0.10250484028450249, "ce": 0.765898775308014}, {"step": 245, "kl": 0.07337756377673191, "ce": 0.7224505650586766}, {"step": 246, "kl": 0.0839791852889196, "ce": 0.6972248021980308}, {"step": 247, "kl": 0.0857139376792001, "ce": 0.8246326744505263}, {"step": 248, "kl": 0.08424300756203042, "ce": 0.795660786490703}, {"step": 249, "kl": 0.08255205199673975, "ce": 0.8186456765416672}, {"step": 250, "kl": 0.08269484365773049, "ce": 0.7648571270627184}, {"step": 251, "kl": 0.1030701137170559, "ce": 0.8661731980620082}, {"step": 252, "kl": 0.07399372303145657, "ce": 0.6549669723197309}, {"step": 253, "kl": 0.08585050348746391, "ce": 0.7919859423887744}, {"step": 254, "kl": 0.08146857228302938, "ce": 0.8059683904371225}, {"step": 255, "kl": 0.08681903439093597, "ce": 0.8274457692676728}, {"step": 256, "kl": 0.07983281405599033, "ce": 1.0007743667400881}, {"step": 257, "kl": 0.09524903199335717, "ce": 0.7083061951016374}, {"step": 258, "kl": 0.0945104592243708, "ce": 0.8090249862622823}, {"step": 259, "kl": 0.08237224549222899, "ce": 0.7946336739615998}, {"step": 260, "kl": 0.10875073261830687, "ce": 0.7409461868218783}, {"step": 261, "kl": 0.09911691530225292, "ce": 0.7844375781823654}, {"step": 262, "kl": 0.08154982236012318, "ce": 0.8361036460580027}, {"step": 263, "kl": 0.07154295391784118, "ce": 0.8155803756856549}, {"step": 264, "kl": 0.0828061391012763, "ce": 0.7926389087641402}, {"step": 265, "kl": 0.07941469806253021, "ce": 0.6490468947240352}, {"step": 266, "kl": 0.07087999457801468, "ce": 0.6915295491056045}, {"step": 267, "kl": 0.08984839500414911, "ce": 0.685395324793057}, {"step": 268, "kl": 0.1008035516401716, "ce": 0.7422764042724818}, {"step": 269, "kl": 0.06465210274029184, "ce": 0.8065592133221352}, {"step": 270, "kl": 0.09291330636540625, "ce": 0.7754901799507046}, {"step": 271, "kl": 0.08645094831040857, "ce": 0.8456374771327431}, {"step": 272, "kl": 0.08233589713029035, "ce": 0.7678668931644395}, {"step": 273, "kl": 0.0795812951734352, "ce": 0.7504508217857163}, {"step": 274, "kl": 0.0819950720695167, "ce": 0.7422723335175714}, {"step": 275, "kl": 0.07362249902307982, "ce": 0.7974140767419695}, {"step": 276, "kl": 0.0748502169065107, "ce": 0.8999102352986894}, {"step": 277, "kl": 0.08181274721402322, "ce": 0.7839889495340776}, {"step": 278, "kl": 0.07968656005817444, "ce": 0.6506331044410893}, {"step": 279, "kl": 0.07124751573362559, "ce": 0.7517192620706052}, {"step": 280, "kl": 0.08804003647822468, "ce": 0.8153644621490208}, {"step": 281, "kl": 0.08379063972954179, "ce": 0.8110568198907295}, {"step": 282, "kl": 0.07928866438759449, "ce": 0.6854925286086783}, {"step": 283, "kl": 0.07610064234482404, "ce": 0.7412413954523064}, {"step": 284, "kl": 0.09157360870970226, "ce": 0.7379719342065298}, {"step": 285, "kl": 0.06800058414656973, "ce": 0.7523379488257063}, {"step": 286, "kl": 0.08455206848248686, "ce": 0.8252053734088343}, {"step": 287, "kl": 0.07870188332918185, "ce": 0.8814385603052929}, {"step": 288, "kl": 0.09985900963972327, "ce": 0.9434386363468058}, {"step": 289, "kl": 0.0935414725722936, "ce": 0.7036757294990156}, {"step": 290, "kl": 0.07397150091835775, "ce": 0.6635080859796667}, {"step": 291, "kl": 0.07984835377250243, "ce": 0.7264859058526675}, {"step": 292, "kl": 0.1003927750897089, "ce": 0.7527840766135901}, {"step": 293, "kl": 0.08899059985677059, "ce": 0.7432607223787693}, {"step": 294, "kl": 0.07439212416201182, "ce": 0.7955849813378374}, {"step": 295, "kl": 0.08376303171048058, "ce": 0.66688250762705}, {"step": 296, "kl": 0.09727468814444293, "ce": 0.9259142560136882}, {"step": 297, "kl": 0.07295287053617974, "ce": 0.8213645381081369}, {"step": 298, "kl": 0.0870242823797773, "ce": 0.9082958919323043}, {"step": 299, "kl": 0.09650875183677016, "ce": 0.8389969721588302}, {"step": 300, "kl": 0.09020410033135351, "ce": 0.8357614391717978}, {"step": 301, "kl": 0.08136086851532909, "ce": 0.823291906596461}, {"step": 302, "kl": 0.08781440071385788, "ce": 0.7858250851423055}, {"step": 303, "kl": 0.08007921205957311, "ce": 0.7573814543303068}, {"step": 304, "kl": 0.10417475615323851, "ce": 0.8623180084356957}, {"step": 305, "kl": 0.0980950495271909, "ce": 0.883462519141886}, {"step": 306, "kl": 0.1015576144715343, "ce": 0.7997633814124224}, {"step": 307, "kl": 0.0757784712606551, "ce": 0.8031570438703246}, {"step": 308, "kl": 0.08280282342289567, "ce": 0.5954452854826779}, {"step": 309, "kl": 0.08797841132347475, "ce": 0.7890519642524789}, {"step": 310, "kl": 0.07330145269394056, "ce": 0.689859411160515}, {"step": 311, "kl": 0.08847115796042959, "ce": 0.8065636272472223}, {"step": 312, "kl": 0.0885416017500843, "ce": 0.7407546571750461}, {"step": 313, "kl": 0.07527721208752874, "ce": 0.7491040031508645}, {"step": 314, "kl": 0.08661476551509797, "ce": 0.789063951053497}, {"step": 315, "kl": 0.08091408730954275, "ce": 0.7453604443109829}, {"step": 316, "kl": 0.08268733454252704, "ce": 0.7905785702280367}, {"step": 317, "kl": 0.08097518980709842, "ce": 0.8791362451979565}, {"step": 318, "kl": 0.0873447534480524, "ce": 0.787988388882356}, {"step": 319, "kl": 0.07988813339135585, "ce": 0.7313035385984654}, {"step": 320, "kl": 0.0893066178830354, "ce": 0.819148338881115}, {"step": 321, "kl": 0.10635407190621533, "ce": 0.7173158471919345}, {"step": 322, "kl": 0.07980351557562396, "ce": 0.7307867479453642}, {"step": 323, "kl": 0.08394592058247113, "ce": 0.8971217812071727}, {"step": 324, "kl": 0.06999894618550097, "ce": 0.750976198576581}, {"step": 325, "kl": 0.08491208672833522, "ce": 0.8584962585687872}, {"step": 326, "kl": 0.06868096854951647, "ce": 0.8161952565017256}, {"step": 327, "kl": 0.09540839854010198, "ce": 0.8020573766897543}, {"step": 328, "kl": 0.07330690175712914, "ce": 0.6745405724868474}, {"step": 329, "kl": 0.05452521403163189, "ce": 0.8101622248866482}, {"step": 330, "kl": 0.08228849350833761, "ce": 0.7518668845739307}, {"step": 331, "kl": 0.08739436304982359, "ce": 0.6897740132634664}, {"step": 332, "kl": 0.08149579275130504, "ce": 0.8393199012673804}, {"step": 333, "kl": 0.08880333371343047, "ce": 0.7804001860840377}, {"step": 334, "kl": 0.07125630324748726, "ce": 0.6944199369844858}, {"step": 335, "kl": 0.0835952617534753, "ce": 0.7366316950650582}, {"step": 336, "kl": 0.09626354440705193, "ce": 0.925245736843372}, {"step": 337, "kl": 0.08100050848170404, "ce": 0.7984073799608391}, {"step": 338, "kl": 0.07993599091098025, "ce": 0.6691848052445278}, {"step": 339, "kl": 0.07546626573011181, "ce": 0.8185973223697474}, {"step": 340, "kl": 0.06131209014942173, "ce": 0.644436688701781}, {"step": 341, "kl": 0.0951545589115668, "ce": 0.7982653652617858}, {"step": 342, "kl": 0.07611459457855466, "ce": 0.8665218665951587}, {"step": 343, "kl": 0.07135813430413598, "ce": 0.6724058956191432}, {"step": 344, "kl": 0.07549562981940948, "ce": 0.8145811856953054}, {"step": 345, "kl": 0.06819846788101394, "ce": 0.775219294142641}, {"step": 346, "kl": 0.07355310042932237, "ce": 0.8196172586404671}, {"step": 347, "kl": 0.09214966569028805, "ce": 0.7712100304700459}, {"step": 348, "kl": 0.08506989479064941, "ce": 0.7954543272088206}, {"step": 349, "kl": 0.08365386157405298, "ce": 0.7387216026745541}, {"step": 350, "kl": 0.0814382255878747, "ce": 0.8210165253458058}, {"step": 351, "kl": 0.0909138244695321, "ce": 0.7939176066104469}, {"step": 352, "kl": 0.06389280802724567, "ce": 0.6858588249336345}, {"step": 353, "kl": 0.06121946619972262, "ce": 0.7024439758059287}, {"step": 354, "kl": 0.10168056459156642, "ce": 0.7686788799963737}, {"step": 355, "kl": 0.080049810766176, "ce": 0.7996228653003256}, {"step": 356, "kl": 0.08050194797827309, "ce": 0.7521928203267861}, {"step": 357, "kl": 0.07696637964350764, "ce": 0.7770264424147898}, {"step": 358, "kl": 0.08115691428960756, "ce": 0.7837762142224057}, {"step": 359, "kl": 0.05257508250597703, "ce": 0.7970709374525069}, {"step": 360, "kl": 0.06938905042672176, "ce": 0.7823337871605104}, {"step": 361, "kl": 0.0759534982104894, "ce": 0.728193978048234}, {"step": 362, "kl": 0.08704125205561247, "ce": 0.8903836024927034}, {"step": 363, "kl": 0.18175399417313692, "ce": 0.8435547503639251}, {"step": 364, "kl": 0.09289499785893936, "ce": 0.8514462594681318}, {"step": 365, "kl": 0.09457546853852901, "ce": 0.7532332520091206}, {"step": 366, "kl": 0.06687218503361188, "ce": 0.716267039893988}, {"step": 367, "kl": 0.06382273211666147, "ce": 0.7772420797717061}, {"step": 368, "kl": 0.0703723828634441, "ce": 0.7351085670906696}, {"step": 369, "kl": 0.0747227480610548, "ce": 0.7480449212899318}, {"step": 370, "kl": 0.06945088765651257, "ce": 0.8250693007861734}, {"step": 371, "kl": 0.07187552217997875, "ce": 0.7597884161236037}, {"step": 372, "kl": 0.08342957643599044, "ce": 0.8193648522641478}, {"step": 373, "kl": 0.07045289746974782, "ce": 0.704192396814456}, {"step": 374, "kl": 0.07057584590945434, "ce": 0.7857773202644366}, {"step": 375, "kl": 0.08318628320751377, "ce": 0.8501746998573722}, {"step": 376, "kl": 0.07192177115283271, "ce": 0.7738711859590264}, {"step": 377, "kl": 0.09788148682737709, "ce": 0.7848897349440909}, {"step": 378, "kl": 0.06962271535141698, "ce": 0.6857948900139608}, {"step": 379, "kl": 0.07849227817338313, "ce": 0.6761260177366473}, {"step": 380, "kl": 0.07891801213343452, "ce": 0.7412542958485758}, {"step": 381, "kl": 0.08108049173834463, "ce": 0.8135798235561005}, {"step": 382, "kl": 0.07908469922984106, "ce": 0.8036198110028732}, {"step": 383, "kl": 0.09750262327912267, "ce": 0.7521615251813616}, {"step": 384, "kl": 0.08970801271913663, "ce": 0.8476923102283225}, {"step": 385, "kl": 0.07771685141778631, "ce": 0.8164111241224024}, {"step": 386, "kl": 0.0824190618000056, "ce": 0.8403619897327589}, {"step": 387, "kl": 0.08051657543211024, "ce": 0.6934116672687909}, {"step": 388, "kl": 0.07982724209643634, "ce": 0.8659614256866036}, {"step": 389, "kl": 0.09055918657770179, "ce": 0.9324579797335636}, {"step": 390, "kl": 0.08068330173176254, "ce": 0.7464941288319966}, {"step": 391, "kl": 0.07593723241895475, "ce": 0.7588988344341661}, {"step": 392, "kl": 0.07523704616200223, "ce": 0.8098186700233317}, {"step": 393, "kl": 0.09496748308884116, "ce": 0.7514401361755337}, {"step": 394, "kl": 0.08483572568050339, "ce": 0.8668825022379557}, {"step": 395, "kl": 0.07958352369607624, "ce": 0.7912520619742522}, {"step": 396, "kl": 0.07492988674027229, "ce": 0.8817140288700331}, {"step": 397, "kl": 0.07330406118502647, "ce": 0.8495874999154848}, {"step": 398, "kl": 0.08204632430586759, "ce": 0.8109894022641252}, {"step": 399, "kl": 0.06809970875478162, "ce": 0.8002433766458366}, {"step": 400, "kl": 0.07784943687005985, "ce": 0.7408664643378526}, {"step": 401, "kl": 0.06166383265240262, "ce": 0.785373427919559}, {"step": 402, "kl": 0.08535049073077362, "ce": 0.8034263348233872}, {"step": 403, "kl": 0.08251614430627718, "ce": 0.7246871607853816}, {"step": 404, "kl": 0.06694062855595165, "ce": 0.8409644004344565}, {"step": 405, "kl": 0.0861043506607586, "ce": 0.8333227913851795}, {"step": 406, "kl": 0.08443734444806725, "ce": 0.6913473910447115}, {"step": 407, "kl": 0.07689932177401687, "ce": 0.8220026921959563}, {"step": 408, "kl": 0.07181119069933725, "ce": 0.8133268666234919}, {"step": 409, "kl": 0.09539313602724914, "ce": 0.9017441955566408}, {"step": 410, "kl": 0.09106170513864446, "ce": 0.8717582233416769}, {"step": 411, "kl": 0.09174609079010111, "ce": 0.7412538287203566}, {"step": 412, "kl": 0.07063069568404258, "ce": 0.7047071957456472}, {"step": 413, "kl": 0.06784677255840202, "ce": 0.6847306518110957}, {"step": 414, "kl": 0.091196057409415, "ce": 0.7380564610966422}, {"step": 415, "kl": 0.07121576641071836, "ce": 0.7397058080093537}, {"step": 416, "kl": 0.06876403498301226, "ce": 0.797682680356025}, {"step": 417, "kl": 0.059914147171727314, "ce": 0.8081401721204174}, {"step": 418, "kl": 0.07911160839593703, "ce": 0.7856726186293799}, {"step": 419, "kl": 0.0984684656426576, "ce": 0.8264198329536963}, {"step": 420, "kl": 0.08372695539610554, "ce": 0.8900691003816257}, {"step": 421, "kl": 0.08473294629022576, "ce": 0.8817062058182573}, {"step": 422, "kl": 0.07608767434430878, "ce": 0.7955098548937993}, {"step": 423, "kl": 0.08697396277075882, "ce": 0.8102262019656693}, {"step": 424, "kl": 0.0692998222305025, "ce": 0.8087194208908643}, {"step": 425, "kl": 0.08193103412280721, "ce": 0.7857853946218413}, {"step": 426, "kl": 0.08691309457830822, "ce": 0.8324069759533405}, {"step": 427, "kl": 0.06692191722378985, "ce": 0.7894779991249308}, {"step": 428, "kl": 0.08180244426580546, "ce": 0.7569871145262195}, {"step": 429, "kl": 0.09427950951345776, "ce": 0.8229778273539109}, {"step": 430, "kl": 0.08315314561258219, "ce": 0.6870928533178995}, {"step": 431, "kl": 0.07847502383088299, "ce": 0.6675509235919168}, {"step": 432, "kl": 0.07714194681435367, "ce": 0.7824596488221666}, {"step": 433, "kl": 0.07741941451281212, "ce": 0.7543572191193766}, {"step": 434, "kl": 0.0682737690206863, "ce": 0.8567359969176348}, {"step": 435, "kl": 0.07235497623568106, "ce": 0.8008919044664103}, {"step": 436, "kl": 0.08643650698795546, "ce": 0.7387443860500555}, {"step": 437, "kl": 0.13011121098509146, "ce": 0.780444652833584}, {"step": 438, "kl": 0.10704209177870405, "ce": 0.7951237396143761}, {"step": 439, "kl": 0.08226004652882417, "ce": 0.8650874152229193}, {"step": 440, "kl": 0.0927392704983785, "ce": 0.8015927784713273}, {"step": 441, "kl": 0.06381214013289525, "ce": 0.6792728354110905}, {"step": 442, "kl": 0.10292908284391078, "ce": 0.8583264379852283}, {"step": 443, "kl": 0.08724037356081263, "ce": 0.7332625313112874}, {"step": 444, "kl": 0.0706848157986507, "ce": 0.7068188034120153}, {"step": 445, "kl": 0.09051122633509812, "ce": 0.7949863698059347}, {"step": 446, "kl": 0.07845134748087398, "ce": 0.7759023971887895}, {"step": 447, "kl": 0.0779686110277707, "ce": 0.8175870899358466}, {"step": 448, "kl": 0.07190804288981271, "ce": 0.7966003752224808}, {"step": 449, "kl": 0.060116139078043425, "ce": 0.7354179896916812}, {"step": 450, "kl": 0.039566167090822196, "ce": 0.7297784199988226}, {"step": 451, "kl": 0.062204899165794525, "ce": 0.7794412618843327}, {"step": 452, "kl": 0.040711566824619884, "ce": 0.6925383647136019}, {"step": 453, "kl": 0.07016702186346391, "ce": 0.8824755868206277}, {"step": 454, "kl": 0.044917363529057466, "ce": 0.7509694656004939}, {"step": 455, "kl": 0.06896721349120434, "ce": 0.7785026568523302}, {"step": 456, "kl": 0.04241607583789663, "ce": 0.7368142131201747}, {"step": 457, "kl": 0.04931758365477405, "ce": 0.7154182615543672}, {"step": 458, "kl": 0.05780030957043056, "ce": 0.9048197765488194}, {"step": 459, "kl": 0.046767653130706036, "ce": 0.874922965306427}, {"step": 460, "kl": 0.043073371278265396, "ce": 0.9006298630353461}, {"step": 461, "kl": 0.04609956890705147, "ce": 0.8629136465157674}, {"step": 462, "kl": 0.043027237984511836, "ce": 0.7079194231731136}, {"step": 463, "kl": 0.046718351007940626, "ce": 0.8016121591363227}, {"step": 464, "kl": 0.04644138211005257, "ce": 0.6578685284122492}, {"step": 465, "kl": 0.09498524194978589, "ce": 0.8911546778073819}, {"step": 466, "kl": 0.047220213765768834, "ce": 0.7283361823768753}, {"step": 467, "kl": 0.047182268157202965, "ce": 0.7921240277256841}, {"step": 468, "kl": 0.06212939147147531, "ce": 0.8654785539877632}, {"step": 469, "kl": 0.062293886671316676, "ce": 0.7747411592655716}, {"step": 470, "kl": 0.08484492487161205, "ce": 0.9023195285109357}, {"step": 471, "kl": 0.04271719504061286, "ce": 0.7643395516780658}, {"step": 472, "kl": 0.06645516705843721, "ce": 0.849353239723316}, {"step": 473, "kl": 0.046374604802100636, "ce": 0.7797740312176027}, {"step": 474, "kl": 0.047725384835143936, "ce": 0.6886884664947336}, {"step": 475, "kl": 0.04600702564550204, "ce": 0.8067975372205193}, {"step": 476, "kl": 0.048526419928660684, "ce": 0.7541833239633893}, {"step": 477, "kl": 0.0363627933332304, "ce": 0.7149056036179676}, {"step": 478, "kl": 0.050481021400148596, "ce": 0.7924654879177149}, {"step": 479, "kl": 0.04841524843881432, "ce": 0.765916263101321}, {"step": 480, "kl": 0.045627052110839214, "ce": 0.7152581820430253}, {"step": 481, "kl": 0.040027925291512625, "ce": 0.6919362119326858}, {"step": 482, "kl": 0.04268831315658486, "ce": 0.7220475300432394}, {"step": 483, "kl": 0.09205166234927832, "ce": 0.8034171268006358}, {"step": 484, "kl": 0.03912579833803148, "ce": 0.956466729708876}, {"step": 485, "kl": 0.043782608105743206, "ce": 0.634488926017635}, {"step": 486, "kl": 0.0310942878574977, "ce": 0.7846050633981262}, {"step": 487, "kl": 0.04431131863631166, "ce": 0.6595758364608424}, {"step": 488, "kl": 0.050161281176079736, "ce": 0.6369065677696177}, {"step": 489, "kl": 0.03185024880938282, "ce": 0.7302266233942336}, {"step": 490, "kl": 0.03831273893829351, "ce": 0.7477012602185581}, {"step": 491, "kl": 0.058283581066669754, "ce": 0.8042972384868375}, {"step": 492, "kl": 0.037728809306478775, "ce": 0.9207443903462695}, {"step": 493, "kl": 0.034849264157698456, "ce": 0.8306321766349655}, {"step": 494, "kl": 0.05021773738004817, "ce": 0.743047636170632}, {"step": 495, "kl": 0.08772365837153595, "ce": 0.7149528046958467}, {"step": 496, "kl": 0.055429214453506834, "ce": 0.7918678647929253}, {"step": 497, "kl": 0.058101312993438625, "ce": 0.7164044235890636}, {"step": 498, "kl": 0.04582846030231525, "ce": 0.6559030810847846}, {"step": 499, "kl": 0.05548270367871287, "ce": 0.8124438890991559}, {"step": 500, "kl": 0.03795972768432722, "ce": 0.8999599516231611}, {"step": 501, "kl": 0.03846570253458532, "ce": 0.7573149426267138}, {"step": 502, "kl": 0.03825609438261688, "ce": 0.7805507211788737}, {"step": 503, "kl": 0.04989975734187642, "ce": 0.7911749460395896}, {"step": 504, "kl": 0.04027532795446609, "ce": 0.8044907366343254}, {"step": 505, "kl": 0.04584848417352602, "ce": 0.862472521110061}, {"step": 506, "kl": 0.03485433126293997, "ce": 0.7085251618231367}, {"step": 507, "kl": 0.03440753206611897, "ce": 0.74765457635244}, {"step": 508, "kl": 0.04126450645352381, "ce": 0.7952460743524887}, {"step": 509, "kl": 0.0335349953029914, "ce": 0.7787764055159371}, {"step": 510, "kl": 0.06586579392794667, "ce": 0.7706962135194977}, {"step": 511, "kl": 0.04197930662967133, "ce": 0.763510298739749}, {"step": 512, "kl": 0.047812678194253604, "ce": 0.7942531234922591}, {"step": 513, "kl": 0.042084650207538425, "ce": 0.8092555470971194}, {"step": 514, "kl": 0.053430352492380866, "ce": 0.8256193274681917}, {"step": 515, "kl": 0.062327314986406215, "ce": 0.7981763545153449}, {"step": 516, "kl": 0.041538119731051364, "ce": 0.8011650717162456}, {"step": 517, "kl": 0.03339634759306956, "ce": 0.726937224193473}, {"step": 518, "kl": 0.041556968039811876, "ce": 0.8250926427447176}, {"step": 519, "kl": 0.045676613395700595, "ce": 0.7590864588404286}, {"step": 520, "kl": 0.045706024781540365, "ce": 0.7482527971932877}, {"step": 521, "kl": 0.04438168401201577, "ce": 0.723929507340421}, {"step": 522, "kl": 0.05219497298825272, "ce": 0.5873016728037848}, {"step": 523, "kl": 0.052075822254190614, "ce": 0.7381272369539725}, {"step": 524, "kl": 0.04137477413754075, "ce": 0.654903566413919}, {"step": 525, "kl": 0.0542037042657012, "ce": 0.7989917513086287}, {"step": 526, "kl": 0.0472710476041089, "ce": 0.7715302157769078}, {"step": 527, "kl": 0.040800398095775216, "ce": 0.7469323478348711}, {"step": 528, "kl": 0.057871979497441564, "ce": 0.7970544829459822}, {"step": 529, "kl": 0.04901522260874678, "ce": 0.8265951636828355}, {"step": 530, "kl": 0.0437771970486494, "ce": 0.8345053341760877}, {"step": 531, "kl": 0.05550650276209904, "ce": 0.8525878517311528}, {"step": 532, "kl": 0.043167733112582325, "ce": 0.855088375440944}, {"step": 533, "kl": 0.05080021694780964, "ce": 0.6790854129301142}, {"step": 534, "kl": 0.057585023497698944, "ce": 0.8722870911260254}, {"step": 535, "kl": 0.04349516983776919, "ce": 0.7435916357831993}, {"step": 536, "kl": 0.04173616524988533, "ce": 0.7541986060188992}, {"step": 537, "kl": 0.048292420438812975, "ce": 0.8382919945669508}, {"step": 538, "kl": 0.06443033327526844, "ce": 0.8345536059486989}, {"step": 539, "kl": 0.04088332135536199, "ce": 0.8209674850048259}, {"step": 540, "kl": 0.059778610859305505, "ce": 0.8389138051750438}, {"step": 541, "kl": 0.041663619450160436, "ce": 0.829446787448809}, {"step": 542, "kl": 0.03533040511770368, "ce": 0.8308212906243257}, {"step": 543, "kl": 0.04742284825392495, "ce": 1.0062502291381867}, {"step": 544, "kl": 0.04047232679144743, "ce": 0.8037237247429087}, {"step": 545, "kl": 0.04323851668544605, "ce": 0.8400845409615533}, {"step": 546, "kl": 0.04865773201275331, "ce": 0.798169501998558}, {"step": 547, "kl": 0.04658279398286243, "ce": 0.8565703653051715}, {"step": 548, "kl": 0.048700262999808466, "ce": 0.7724900742700129}, {"step": 549, "kl": 0.04269422860329662, "ce": 0.6848258749977248}, {"step": 550, "kl": 0.05666291477755314, "ce": 0.7170696871800061}, {"step": 551, "kl": 0.04639861802618823, "ce": 0.7819133044428292}, {"step": 552, "kl": 0.058631219848096605, "ce": 0.8681180467693776}, {"step": 553, "kl": 0.058989864917046414, "ce": 0.9704208912315619}, {"step": 554, "kl": 0.052663461956169465, "ce": 0.7119371586263807}, {"step": 555, "kl": 0.04906541868312396, "ce": 0.7046778039550781}, {"step": 556, "kl": 0.03741462263342452, "ce": 0.8040238219651009}, {"step": 557, "kl": 0.04060706014988996, "ce": 0.8428733860246538}, {"step": 558, "kl": 0.06807292555566867, "ce": 0.7755370358880663}, {"step": 559, "kl": 0.05776121186333883, "ce": 0.959097483841623}, {"step": 560, "kl": 0.03251437226909575, "ce": 0.846064407452434}, {"step": 561, "kl": 0.04505226262848856, "ce": 0.8366432157050413}, {"step": 562, "kl": 0.04736335259368816, "ce": 0.7867931921739109}, {"step": 563, "kl": 0.04692697874060623, "ce": 0.7845287121744856}, {"step": 564, "kl": 0.04626824098172693, "ce": 0.9396011762389656}, {"step": 565, "kl": 0.041324778780901614, "ce": 0.7302579144681004}, {"step": 566, "kl": 0.04106670573841442, "ce": 0.8130325238365596}, {"step": 567, "kl": 0.04625402031697208, "ce": 0.9848614865506616}, {"step": 568, "kl": 0.061205336128649625, "ce": 0.7316776650403333}, {"step": 569, "kl": 0.04496313273028734, "ce": 0.8702042685069892}, {"step": 570, "kl": 0.0454629293979464, "ce": 0.8322359508082233}, {"step": 571, "kl": 0.04170596696994807, "ce": 0.8153465575410838}, {"step": 572, "kl": 0.05952594681855589, "ce": 0.815861207581914}, {"step": 573, "kl": 0.04136725550196331, "ce": 0.7252559919001846}, {"step": 574, "kl": 0.04780614432591758, "ce": 0.8390642002232076}, {"step": 575, "kl": 0.034118406517785284, "ce": 0.7072128833344301}, {"step": 576, "kl": 0.04284632088002335, "ce": 0.873032731065942}, {"step": 577, "kl": 0.04692037878303885, "ce": 0.7443235744093336}, {"step": 578, "kl": 0.04599973421137436, "ce": 0.9394851477228942}, {"step": 579, "kl": 0.04056746290734468, "ce": 0.7379954708042191}, {"step": 580, "kl": 0.04461994182630323, "ce": 0.8170369864266694}, {"step": 581, "kl": 0.0328342440256143, "ce": 0.7549868653532307}, {"step": 582, "kl": 0.03956125243466907, "ce": 0.7733722699440991}, {"step": 583, "kl": 0.04037676010725996, "ce": 0.8034105491102053}, {"step": 584, "kl": 0.039314069741457264, "ce": 0.8325148365432481}, {"step": 585, "kl": 0.042587774776015656, "ce": 0.8343604884735524}, {"step": 586, "kl": 0.04639940945103078, "ce": 0.7959544802372872}, {"step": 587, "kl": 0.04162624205362857, "ce": 0.7838573608398438}, {"step": 588, "kl": 0.041008394480399, "ce": 0.8088202620701322}, {"step": 589, "kl": 0.04188843447117643, "ce": 0.773973883061607}, {"step": 590, "kl": 0.041447190131032284, "ce": 0.8698342188179834}, {"step": 591, "kl": 0.04340827557110878, "ce": 0.8495415981077413}, {"step": 592, "kl": 0.061927643326360395, "ce": 0.8357097604859431}, {"step": 593, "kl": 0.04912638091307655, "ce": 0.8201896227587451}, {"step": 594, "kl": 0.04192001978556315, "ce": 0.8905397875621583}, {"step": 595, "kl": 0.052426727976938654, "ce": 0.7680698680338888}, {"step": 596, "kl": 0.04585298127155582, "ce": 0.59067530885956}, {"step": 597, "kl": 0.05193894720288905, "ce": 0.7166200989451489}, {"step": 598, "kl": 0.04252361452261729, "ce": 0.8957266288310484}, {"step": 599, "kl": 0.04009016905114916, "ce": 0.8333830156101868}, {"step": 600, "kl": 0.051880067939914516, "ce": 0.9341760012819956}, {"step": 601, "kl": 0.03955833614154623, "ce": 0.7024046789345437}, {"step": 602, "kl": 0.04238683866838619, "ce": 0.7427748050358548}, {"step": 603, "kl": 0.04526279160169247, "ce": 1.0095027791663618}, {"step": 604, "kl": 0.0590028344939577, "ce": 0.7059308253042146}, {"step": 605, "kl": 0.04643018861854278, "ce": 0.8276224416033978}, {"step": 606, "kl": 0.03555345917595025, "ce": 0.6914062644148642}, {"step": 607, "kl": 0.04317293227016887, "ce": 0.8245572049784947}, {"step": 608, "kl": 0.061011059092460865, "ce": 0.8331619388208265}, {"step": 609, "kl": 0.03930932121893366, "ce": 0.7349742229835812}, {"step": 610, "kl": 0.04320264767319238, "ce": 0.7412573839025742}, {"step": 611, "kl": 0.0694450990363307, "ce": 0.7902823793611209}, {"step": 612, "kl": 0.04499590900601528, "ce": 0.8031719549378352}, {"step": 613, "kl": 0.04144630171267503, "ce": 0.7165074604560765}, {"step": 614, "kl": 0.043598138898297674, "ce": 0.7936082991144494}, {"step": 615, "kl": 0.04491190473644281, "ce": 0.8399450936923478}, {"step": 616, "kl": 0.04055105687711186, "ce": 0.840704988873344}, {"step": 617, "kl": 0.042426813113068354, "ce": 0.7213399386840649}, {"step": 618, "kl": 0.05814004988117792, "ce": 0.8378770982474851}, {"step": 619, "kl": 0.03707636683263649, "ce": 0.7022758764483631}, {"step": 620, "kl": 0.049751305418061775, "ce": 0.673161607142209}, {"step": 621, "kl": 0.03975355294709196, "ce": 0.8824615360322061}, {"step": 622, "kl": 0.041642602302516096, "ce": 0.914088210628531}, {"step": 623, "kl": 0.06040609343300747, "ce": 0.8388291608248509}, {"step": 624, "kl": 0.06666901670167516, "ce": 0.8549194351350418}, {"step": 625, "kl": 0.045654145746698606, "ce": 0.9576918004524875}, {"step": 626, "kl": 0.03248631716073431, "ce": 0.9727422216907641}, {"step": 627, "kl": 0.035447963698021695, "ce": 0.76463593173346}, {"step": 628, "kl": 0.037013936390712834, "ce": 0.8472826720377266}, {"step": 629, "kl": 0.04875013855254329, "ce": 0.8457498373261916}, {"step": 630, "kl": 0.04319618899463663, "ce": 0.8667650599259098}, {"step": 631, "kl": 0.04843884261935455, "ce": 0.8366471952170491}, {"step": 632, "kl": 0.03846603377957062, "ce": 0.7836942712784541}, {"step": 633, "kl": 0.044014938871808316, "ce": 0.9716951888420677}, {"step": 634, "kl": 0.04738433007364508, "ce": 0.7895688335109312}, {"step": 635, "kl": 0.0689233866636684, "ce": 0.7281768465405039}, {"step": 636, "kl": 0.06213710786238038, "ce": 0.83371769750936}, {"step": 637, "kl": 0.0539367213442519, "ce": 0.7626839051619522}, {"step": 638, "kl": 0.054095022579328945, "ce": 0.698233207355026}, {"step": 639, "kl": 0.03924598287116317, "ce": 0.7316524256040503}, {"step": 640, "kl": 0.045146759472583266, "ce": 0.6786188275901115}, {"step": 641, "kl": 0.038685295820972326, "ce": 0.7703554141826374}, {"step": 642, "kl": 0.03718883671660236, "ce": 0.8450504015018414}, {"step": 643, "kl": 0.03750028251828565, "ce": 0.7606935357328635}, {"step": 644, "kl": 0.052980329730990136, "ce": 0.8481964734346001}, {"step": 645, "kl": 0.0457332639505765, "ce": 0.8381922156515417}, {"step": 646, "kl": 0.04072016601848446, "ce": 0.8646171934223011}, {"step": 647, "kl": 0.042768450991419335, "ce": 0.9622356627439974}, {"step": 648, "kl": 0.043501288160000776, "ce": 0.8741517227960255}, {"step": 649, "kl": 0.04534659446593858, "ce": 0.9674312245103487}, {"step": 650, "kl": 0.04834117749500974, "ce": 0.8735407427909734}, {"step": 651, "kl": 0.045841594994341, "ce": 0.6900637585876916}, {"step": 652, "kl": 0.05400406941626295, "ce": 0.8739863144473339}, {"step": 653, "kl": 0.05395058567970787, "ce": 0.8025702761118452}, {"step": 654, "kl": 0.058905874110438336, "ce": 0.8054333603331069}, {"step": 655, "kl": 0.042113442959874146, "ce": 0.9389587089375704}, {"step": 656, "kl": 0.04667951074900904, "ce": 0.8294600076878325}, {"step": 657, "kl": 0.04550039618042552, "ce": 0.8417265821814204}, {"step": 658, "kl": 0.05409167056395498, "ce": 0.8464997936946672}, {"step": 659, "kl": 0.04511129294080711, "ce": 0.7335764557641773}, {"step": 660, "kl": 0.04377937553968726, "ce": 0.7885964940866063}, {"step": 661, "kl": 0.06617889702470389, "ce": 0.8029259641656237}, {"step": 662, "kl": 0.03673304710503009, "ce": 0.7143671141271227}, {"step": 663, "kl": 0.05023837503758226, "ce": 0.8644396758714945}, {"step": 664, "kl": 0.05046772766113281, "ce": 0.721569675869412}, {"step": 665, "kl": 0.05129095743312566, "ce": 0.7568605046527593}, {"step": 666, "kl": 0.04828838291612306, "ce": 0.8661210017835848}, {"step": 667, "kl": 0.0437301502771581, "ce": 0.7141851280669936}, {"step": 668, "kl": 0.03480742055993072, "ce": 0.9262772502188417}, {"step": 669, "kl": 0.05194197729779949, "ce": 0.8003764286712924}, {"step": 670, "kl": 0.03693003951555896, "ce": 0.7069868112383377}, {"step": 671, "kl": 0.04982349631712609, "ce": 0.79270153489657}, {"step": 672, "kl": 0.04112825449001232, "ce": 0.7454936283274102}, {"step": 673, "kl": 0.03861922565966985, "ce": 0.976639709716862}, {"step": 674, "kl": 0.04682157535333429, "ce": 0.9174609669737174}, {"step": 675, "kl": 0.048072484541379246, "ce": 0.7831069805458856}, {"step": 676, "kl": 0.05267302310739154, "ce": 0.8805165203266432}, {"step": 677, "kl": 0.035481018291401795, "ce": 0.8122745117277945}, {"step": 678, "kl": 0.050503035278099635, "ce": 0.8375981814853054}, {"step": 679, "kl": 0.05640456373205113, "ce": 0.835802418594703}, {"step": 680, "kl": 0.045962068311599234, "ce": 0.7779742529658108}, {"step": 681, "kl": 0.04392665683045907, "ce": 0.7635261017281014}, {"step": 682, "kl": 0.03874028982688054, "ce": 0.735247844358957}, {"step": 683, "kl": 0.03956666659537934, "ce": 0.930033068819993}, {"step": 684, "kl": 0.03824469028212309, "ce": 0.7222537674486799}, {"step": 685, "kl": 0.03798407172703994, "ce": 0.7471165050873729}, {"step": 686, "kl": 0.04104666075643191, "ce": 0.8287047787256026}, {"step": 687, "kl": 0.03746441360175388, "ce": 0.8111928198948379}, {"step": 688, "kl": 0.04536826824109565, "ce": 0.7452371456451184}, {"step": 689, "kl": 0.049321694529472826, "ce": 0.9065935573520058}, {"step": 690, "kl": 0.04211207113592423, "ce": 0.7561666381544253}, {"step": 691, "kl": 0.05074254579413256, "ce": 0.8777169720199581}, {"step": 692, "kl": 0.056010376233188, "ce": 0.9064485964383103}, {"step": 693, "kl": 0.0511179971356293, "ce": 0.724542780490684}, {"step": 694, "kl": 0.041607222286936, "ce": 0.6634428943681612}, {"step": 695, "kl": 0.03723520695862762, "ce": 0.7193245026361091}, {"step": 696, "kl": 0.055302651437409436, "ce": 0.7834740830241546}, {"step": 697, "kl": 0.04562715004888512, "ce": 0.8567632489912235}, {"step": 698, "kl": 0.036842557006326486, "ce": 0.8051843355959079}, {"step": 699, "kl": 0.04590974282193851, "ce": 0.7327384638685838}, {"step": 700, "kl": 0.04121629029837748, "ce": 0.7139418592313231}, {"step": 701, "kl": 0.043484120338472466, "ce": 0.7675168932151769}, {"step": 702, "kl": 0.04144825196714143, "ce": 0.8439032363795099}, {"step": 703, "kl": 0.05961603602018538, "ce": 0.9067162087013771}, {"step": 704, "kl": 0.03828357888665391, "ce": 0.7941772135633537}, {"step": 705, "kl": 0.038453558348228806, "ce": 0.7719479394589258}, {"step": 706, "kl": 0.05072335014919452, "ce": 0.7671252160214473}, {"step": 707, "kl": 0.03594628523426131, "ce": 0.8092488154299461}, {"step": 708, "kl": 0.05166627412855663, "ce": 0.8325959570572166}, {"step": 709, "kl": 0.03971084170490145, "ce": 0.9067782334360742}, {"step": 710, "kl": 0.041782903150734504, "ce": 0.7780645913798054}, {"step": 711, "kl": 0.029094360653780953, "ce": 0.7373865533258771}, {"step": 712, "kl": 0.049281731948953175, "ce": 0.8222715591500572}, {"step": 713, "kl": 0.04593988234913167, "ce": 0.7652999676567369}, {"step": 714, "kl": 0.0417077243054698, "ce": 0.8346189288928557}, {"step": 715, "kl": 0.06128071702044943, "ce": 0.8867218332787327}, {"step": 716, "kl": 0.03537849973091918, "ce": 0.7607622175389371}, {"step": 717, "kl": 0.03739241131744932, "ce": 0.7878115306718767}, {"step": 718, "kl": 0.047287158432378094, "ce": 0.7457021728906484}, {"step": 719, "kl": 0.04443244474400606, "ce": 0.9826382501899376}, {"step": 720, "kl": 0.04154692647922681, "ce": 0.7127999056792934}, {"step": 721, "kl": 0.04531864981880682, "ce": 0.7037331280787347}, {"step": 722, "kl": 0.03953386865083741, "ce": 0.7557252255010513}, {"step": 723, "kl": 0.03790577651307229, "ce": 0.8267181705188199}, {"step": 724, "kl": 0.04340293419288707, "ce": 0.8653122461995111}, {"step": 725, "kl": 0.046932742951386, "ce": 0.8518348478196321}, {"step": 726, "kl": 0.03631917068173509, "ce": 0.8423254644833154}, {"step": 727, "kl": 0.044716929062044435, "ce": 0.764807790073651}, {"step": 728, "kl": 0.05311385197086932, "ce": 0.8878515135517436}, {"step": 729, "kl": 0.06686691647563474, "ce": 0.7140391683166455}, {"step": 730, "kl": 0.041520510924497066, "ce": 0.7548147857151994}, {"step": 731, "kl": 0.041650150663565005, "ce": 0.6922818081272556}, {"step": 732, "kl": 0.04986411643545051, "ce": 0.7666053455643338}, {"step": 733, "kl": 0.0354665696036387, "ce": 0.7203648431208634}, {"step": 734, "kl": 0.0372342991068295, "ce": 0.9000218910370665}, {"step": 735, "kl": 0.05780203473976962, "ce": 0.9217313325240315}, {"step": 736, "kl": 0.03915739997412486, "ce": 0.8047551074361461}, {"step": 737, "kl": 0.04063284680478103, "ce": 0.8317385089687562}, {"step": 738, "kl": 0.048066232929764634, "ce": 0.8072176605183756}, {"step": 739, "kl": 0.04106183668982658, "ce": 0.7720489619549546}, {"step": 740, "kl": 0.03601591329414913, "ce": 0.8171543795344891}, {"step": 741, "kl": 0.035409301572517496, "ce": 0.7448615165003595}, {"step": 742, "kl": 0.0446011341163732, "ce": 0.8521733179417271}, {"step": 743, "kl": 0.03937635643882041, "ce": 0.8643444561003264}, {"step": 744, "kl": 0.040835920994934875, "ce": 0.739088384598648}, {"step": 745, "kl": 0.04392400300455066, "ce": 0.7701928034424783}, {"step": 746, "kl": 0.051161379683359154, "ce": 0.7801137454063252}, {"step": 747, "kl": 0.042254784602619146, "ce": 0.7295330412865861}, {"step": 748, "kl": 0.03556837490828879, "ce": 0.7977189457162392}, {"step": 749, "kl": 0.0422635428747243, "ce": 0.7913425611258109}, {"step": 750, "kl": 0.05624337147204536, "ce": 0.7978433713628637}, {"step": 751, "kl": 0.04363060554075425, "ce": 0.8346529151308308}, {"step": 752, "kl": 0.04371546852785667, "ce": 0.709430215788053}, {"step": 753, "kl": 0.04210594145568797, "ce": 0.8083590849725512}, {"step": 754, "kl": 0.047153518473766136, "ce": 0.7206143131653033}, {"step": 755, "kl": 0.05185091029185565, "ce": 0.6945690838628714}, {"step": 756, "kl": 0.04476723594710276, "ce": 0.7541918526791862}, {"step": 757, "kl": 0.045968875720174086, "ce": 0.8043331635536322}, {"step": 758, "kl": 0.04170941165703962, "ce": 0.7821825810402507}, {"step": 759, "kl": 0.042246949923183126, "ce": 0.8318904253754655}, {"step": 760, "kl": 0.05320703267123716, "ce": 0.7898656750945766}, {"step": 761, "kl": 0.04370782216469756, "ce": 0.9515950587591664}, {"step": 762, "kl": 0.05029045924573276, "ce": 0.8634729005154158}, {"step": 763, "kl": 0.0490529689154295, "ce": 0.7488135739954288}, {"step": 764, "kl": 0.0397754411622829, "ce": 0.7199958471930873}, {"step": 765, "kl": 0.04293659689567613, "ce": 0.837289091317493}, {"step": 766, "kl": 0.04032289605837619, "ce": 0.857172880721803}, {"step": 767, "kl": 0.04113471701026486, "ce": 0.7541014252001111}, {"step": 768, "kl": 0.04392063847896048, "ce": 0.9249379657481624}, {"step": 769, "kl": 0.04897838900057067, "ce": 0.7136360346547475}, {"step": 770, "kl": 0.045398163420468186, "ce": 0.818416596181328}, {"step": 771, "kl": 0.04427390694364048, "ce": 0.8184240304150628}, {"step": 772, "kl": 0.04278822795326477, "ce": 0.8859725693222233}, {"step": 773, "kl": 0.03727445161363425, "ce": 0.98038618688951}, {"step": 774, "kl": 0.056269938340690086, "ce": 0.7694367526640803}, {"step": 775, "kl": 0.04749256181825848, "ce": 0.8289558771223569}, {"step": 776, "kl": 0.044277146567251575, "ce": 0.813469351503965}, {"step": 777, "kl": 0.052671414497926505, "ce": 0.7606293893075203}, {"step": 778, "kl": 0.04356424956901638, "ce": 0.9563440261618619}, {"step": 779, "kl": 0.05886701849929425, "ce": 0.9371516057506458}, {"step": 780, "kl": 0.04417963899082525, "ce": 0.9004002326651466}, {"step": 781, "kl": 0.0430466532163782, "ce": 0.8070314376142631}, {"step": 782, "kl": 0.04271516425878155, "ce": 0.773706781239222}, {"step": 783, "kl": 0.033165271195929553, "ce": 0.7430394424675658}, {"step": 784, "kl": 0.03957520534506084, "ce": 0.8923511343567775}, {"step": 785, "kl": 0.04471330317612478, "ce": 0.8094585435262809}, {"step": 786, "kl": 0.03898187648186293, "ce": 0.8543692607118953}, {"step": 787, "kl": 0.046840752061487786, "ce": 0.7654498988935416}, {"step": 788, "kl": 0.04483754238655658, "ce": 0.8443061902685073}, {"step": 789, "kl": 0.038719827761359536, "ce": 0.8353887681486505}, {"step": 790, "kl": 0.03501810776734183, "ce": 0.7298953939163962}, {"step": 791, "kl": 0.04549960939951708, "ce": 0.7204926551375707}, {"step": 792, "kl": 0.04083192573029579, "ce": 0.8829780811955196}, {"step": 793, "kl": 0.040446490838494095, "ce": 0.7401304471651036}, {"step": 794, "kl": 0.05789644579376989, "ce": 0.7875544733733627}, {"step": 795, "kl": 0.04125002502359863, "ce": 0.788966707041095}, {"step": 796, "kl": 0.04631145315148953, "ce": 0.8956689053166303}, {"step": 797, "kl": 0.045367741489145574, "ce": 0.7381216754047125}, {"step": 798, "kl": 0.057469080554373504, "ce": 0.8655390835608578}, {"step": 799, "kl": 0.03292325811267394, "ce": 0.9369711060189297}, {"step": 800, "kl": 0.0390988434332698, "ce": 0.826980481091288}, {"step": 801, "kl": 0.03298858051437089, "ce": 0.9079585671692031}, {"step": 802, "kl": 0.04562647965192309, "ce": 0.769865091686644}, {"step": 803, "kl": 0.03816334143185083, "ce": 0.8834539421834423}, {"step": 804, "kl": 0.041095816410840875, "ce": 0.8274137440689625}, {"step": 805, "kl": 0.04959712459798254, "ce": 0.734523805304709}, {"step": 806, "kl": 0.0465974687546742, "ce": 0.7092731685225047}, {"step": 807, "kl": 0.041252748393333864, "ce": 0.6952438892088983}, {"step": 808, "kl": 0.04780530678496857, "ce": 0.6534895402014227}, {"step": 809, "kl": 0.0498888410922296, "ce": 0.9060039410469254}, {"step": 810, "kl": 0.04344994975175522, "ce": 0.986089298736831}, {"step": 811, "kl": 0.04779282331033247, "ce": 0.7732413582379645}, {"step": 812, "kl": 0.03609940248924109, "ce": 0.8646145768529567}, {"step": 813, "kl": 0.046368963847094796, "ce": 0.7647362024734385}, {"step": 814, "kl": 0.04519615783950046, "ce": 0.6880575745306}, {"step": 815, "kl": 0.038952954281398576, "ce": 0.7719830528439798}, {"step": 816, "kl": 0.044618332915595735, "ce": 0.8485294921019044}, {"step": 817, "kl": 0.036968895932963784, "ce": 0.8150005812007817}, {"step": 818, "kl": 0.05019278339553352, "ce": 0.824971035956585}, {"step": 819, "kl": 0.0333153945083127, "ce": 0.8427155987619296}, {"step": 820, "kl": 0.044579625608376486, "ce": 0.8662423670274856}, {"step": 821, "kl": 0.04534669910858093, "ce": 0.8378869804985364}, {"step": 822, "kl": 0.05221344785509969, "ce": 0.6341877498153985}, {"step": 823, "kl": 0.03819579017704583, "ce": 0.7698204061596552}, {"step": 824, "kl": 0.03591815208198565, "ce": 0.7710948175816005}, {"step": 825, "kl": 0.041226070326320884, "ce": 0.7658340815220117}, {"step": 826, "kl": 0.04649971426694308, "ce": 0.7697456432745036}, {"step": 827, "kl": 0.056073231246326655, "ce": 0.7651522057818188}, {"step": 828, "kl": 0.04457290195936962, "ce": 0.7035475338206573}, {"step": 829, "kl": 0.03898883973245923, "ce": 0.8733852701712529}, {"step": 830, "kl": 0.0469447567993241, "ce": 0.796517013384547}, {"step": 831, "kl": 0.03957638768231278, "ce": 0.894304652615963}, {"step": 832, "kl": 0.038095538300909275, "ce": 0.8985944344346937}, {"step": 833, "kl": 0.03498097147546731, "ce": 0.8005270473659039}, {"step": 834, "kl": 0.04342830198952699, "ce": 0.7134146739264126}, {"step": 835, "kl": 0.04073578060480071, "ce": 0.6979444850481501}, {"step": 836, "kl": 0.05669124452158145, "ce": 0.8190961655087379}, {"step": 837, "kl": 0.04460615107588081, "ce": 0.9325063663362534}, {"step": 838, "kl": 0.043606886498452756, "ce": 0.7508021150681977}, {"step": 839, "kl": 0.053572875363640624, "ce": 0.7928876473870077}, {"step": 840, "kl": 0.05717370435865265, "ce": 0.8575241159379151}, {"step": 841, "kl": 0.04885380893937894, "ce": 0.9335476366547242}, {"step": 842, "kl": 0.053039059838240754, "ce": 0.7016045815383591}, {"step": 843, "kl": 0.03597567732976681, "ce": 0.6778231479367721}, {"step": 844, "kl": 0.04620096663223582, "ce": 0.8023363723446001}, {"step": 845, "kl": 0.06111938378370906, "ce": 0.6788439793189592}, {"step": 846, "kl": 0.04917535655645483, "ce": 0.8320772456103455}, {"step": 847, "kl": 0.05189344920750071, "ce": 0.6585243047379843}, {"step": 848, "kl": 0.04134340639467592, "ce": 0.7461820009375819}, {"step": 849, "kl": 0.03930955219645745, "ce": 0.7123806341288886}, {"step": 850, "kl": 0.04986087240143137, "ce": 0.805257393389332}, {"step": 851, "kl": 0.0369304477655072, "ce": 0.7332050533614034}, {"step": 852, "kl": 0.03130710265376862, "ce": 0.6934096351252224}, {"step": 853, "kl": 0.0397326610139386, "ce": 0.8982015244688075}, {"step": 854, "kl": 0.04606136448812587, "ce": 0.7401826040095809}, {"step": 855, "kl": 0.0502467356041714, "ce": 0.8521652342853314}, {"step": 856, "kl": 0.04205838063590335, "ce": 0.8194785126230274}, {"step": 857, "kl": 0.04801237943958923, "ce": 0.8070241140369601}, {"step": 858, "kl": 0.04102142830434461, "ce": 0.7249680136515257}, {"step": 859, "kl": 0.04533680843730876, "ce": 0.8290038107279017}, {"step": 860, "kl": 0.04907334331047898, "ce": 0.7627838026531596}, {"step": 861, "kl": 0.02844088983360767, "ce": 0.7120248152146912}, {"step": 862, "kl": 0.04494464911285244, "ce": 0.8766851682396033}, {"step": 863, "kl": 0.04210442721823871, "ce": 0.7071946438763426}, {"step": 864, "kl": 0.03634316083999695, "ce": 0.7579041783449739}, {"step": 865, "kl": 0.03830789218864796, "ce": 0.8081518084132961}, {"step": 866, "kl": 0.045897346487290644, "ce": 0.8858812339001969}, {"step": 867, "kl": 0.04484465074746892, "ce": 0.9078768989844215}, {"step": 868, "kl": 0.04425396869805648, "ce": 0.7357303289736562}, {"step": 869, "kl": 0.0352704737817124, "ce": 0.8021385279184952}, {"step": 870, "kl": 0.04848710036383921, "ce": 0.7658209833459864}, {"step": 871, "kl": 0.03756633138359321, "ce": 0.7813219440210262}, {"step": 872, "kl": 0.03553057380048363, "ce": 0.8072510870053855}, {"step": 873, "kl": 0.040889377847520086, "ce": 0.8574783771339265}, {"step": 874, "kl": 0.041807023593022165, "ce": 0.8299438568853564}, {"step": 875, "kl": 0.06465526783882078, "ce": 0.7932827456611541}, {"step": 876, "kl": 0.05183356767224963, "ce": 0.9002020983893397}, {"step": 877, "kl": 0.0621279206785646, "ce": 0.7644969718899062}, {"step": 878, "kl": 0.04288663233361068, "ce": 0.7909917816949361}, {"step": 879, "kl": 0.04442448537314487, "ce": 0.8644908732992347}, {"step": 880, "kl": 0.044497581430837894, "ce": 0.7470707993790384}, {"step": 881, "kl": 0.03698210909230189, "ce": 0.8279181313248993}, {"step": 882, "kl": 0.057151774601037736, "ce": 0.8255726031103644}, {"step": 883, "kl": 0.045019323950266366, "ce": 0.8681868577267955}, {"step": 884, "kl": 0.03574995416690869, "ce": 0.8517146235057234}, {"step": 885, "kl": 0.03667504021814086, "ce": 0.7662902235487334}, {"step": 886, "kl": 0.04713023486475171, "ce": 0.906566779936745}, {"step": 887, "kl": 0.04833863709585205, "ce": 0.788782012578104}, {"step": 888, "kl": 0.0455509568626135, "ce": 0.8021845033655617}, {"step": 889, "kl": 0.039922701906091346, "ce": 0.8995791266491149}, {"step": 890, "kl": 0.044222611425690374, "ce": 0.8396986932892958}, {"step": 891, "kl": 0.03427726282646921, "ce": 0.8673640492044079}, {"step": 892, "kl": 0.03646320059304166, "ce": 0.8876420958093194}, {"step": 893, "kl": 0.0411118227882246, "ce": 0.7563996947605023}, {"step": 894, "kl": 0.05910413009566063, "ce": 0.8005561125331523}, {"step": 895, "kl": 0.19370530857671914, "ce": 0.8137892216890306}, {"step": 896, "kl": 0.04798975803774011, "ce": 0.7484169705337018}], "val": [{"step": 0, "math_kl": 0.16056643818369662, "math_ce": 0.6179343579401348, "code_kl": 0.07794113298743313, "code_ce": 0.309922693351798, "math_hard_kl": 0.24884287280595874, "math_hard_ce": 0.6717120443366895}, {"step": 448, "math_kl": 0.07906220070788958, "math_ce": 0.8141582869835275, "code_kl": 0.09953198362042859, "code_ce": 0.3125779650988579, "math_hard_kl": 0.0919826829255345, "math_hard_ce": 0.8013446435133726}, {"step": 896, "math_kl": 0.0759878009343543, "math_ce": 0.8331185948595244, "code_kl": 0.10406180013954185, "code_ce": 0.3197136727378907, "math_hard_kl": 0.08557213517622467, "math_hard_ce": 0.8143728766945073}]}
|
seq_code_math_kd_only/stage2_math/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58ba0535b1f7d77921aa9f3513ccd28d9a6581c539a28d6fbebb8f9ea8c13d1a
|
| 3 |
+
size 3087467144
|