pmangesh commited on
Commit
4c10eb4
·
verified ·
1 Parent(s): 932967c

Upload folder using huggingface_hub

Browse files
seq_code_math_kd_only_seed1/run_info.json CHANGED
@@ -35,6 +35,37 @@
35
  "peak_gb_teachers": 30.005428314208984,
36
  "bench_h": 0.6688253919945822,
37
  "gpu_bench": "NVIDIA RTX A6000"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
 
 
 
 
 
 
39
  }
40
  }
 
35
  "peak_gb_teachers": 30.005428314208984,
36
  "bench_h": 0.6688253919945822,
37
  "gpu_bench": "NVIDIA RTX A6000"
38
+ },
39
+ "stage2_math": {
40
+ "domain": "math",
41
+ "steps": 896,
42
+ "train_h": 2.9952571921216116,
43
+ "val_start": {
44
+ "step": 0,
45
+ "math_kl": 0.16069652883738267,
46
+ "math_ce": 0.6128856295790037,
47
+ "code_kl": 0.07813702286999027,
48
+ "code_ce": 0.3094309619594328,
49
+ "math_hard_kl": 0.2467836188890191,
50
+ "math_hard_ce": 0.6738775405183716
51
+ },
52
+ "val_end": {
53
+ "step": 896,
54
+ "math_kl": 0.07573669431537612,
55
+ "math_ce": 0.8391097003532377,
56
+ "code_kl": 0.10414732518681599,
57
+ "code_ce": 0.3212356887956559,
58
+ "math_hard_kl": 0.08597009330105414,
59
+ "math_hard_ce": 0.8206646253872792
60
+ },
61
+ "peak_gb_student": 36.51224708557129,
62
+ "peak_gb_teachers": 29.517569541931152
63
  }
64
+ },
65
+ "resumed": {
66
+ "from": "stage1_code",
67
+ "gpu_student": "NVIDIA RTX A6000",
68
+ "gpu_teachers": "NVIDIA RTX A6000",
69
+ "load_h": 0.025301156838734944
70
  }
71
  }
seq_code_math_kd_only_seed1/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_seed1/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_seed1/stage2_math/log.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [{"step": 1, "kl": 0.1610110504048232, "ce": 0.5765495634997091}, {"step": 2, "kl": 0.15285242501311716, "ce": 0.6114058486422378}, {"step": 3, "kl": 0.17461360534456907, "ce": 0.5987833206789963}, {"step": 4, "kl": 0.14284631566248046, "ce": 0.6329487394024813}, {"step": 5, "kl": 0.09098183056385865, "ce": 0.6649750872670132}, {"step": 6, "kl": 0.14608640382309684, "ce": 0.7906927125455845}, {"step": 7, "kl": 0.10984499352034886, "ce": 0.7371260905737567}, {"step": 8, "kl": 0.14961928540671818, "ce": 0.6377887704707723}, {"step": 9, "kl": 0.1275546513972734, "ce": 0.5098610642120347}, {"step": 10, "kl": 0.2253391134411995, "ce": 0.5140107860053637}, {"step": 11, "kl": 0.09934978035385829, "ce": 0.5805363003298533}, {"step": 12, "kl": 0.12896007808238527, "ce": 0.5397136604062585}, {"step": 13, "kl": 0.21938867489420796, "ce": 0.7077422711326347}, {"step": 14, "kl": 0.15544720262295264, "ce": 0.6027542125039503}, {"step": 15, "kl": 0.12317688754554426, "ce": 0.6809006080529376}, {"step": 16, "kl": 0.10141431999873628, "ce": 0.7127916381452241}, {"step": 17, "kl": 0.15246618666651748, "ce": 0.6906842601072598}, {"step": 18, "kl": 0.12587530698095048, "ce": 0.6563383396224642}, {"step": 19, "kl": 0.6835542885800625, "ce": 0.6115422436779714}, {"step": 20, "kl": 0.15420933259577907, "ce": 0.7593983060288971}, {"step": 21, "kl": 0.1871206296631798, "ce": 0.6250328440424141}, {"step": 22, "kl": 0.08940297721797584, "ce": 0.5646484987936022}, {"step": 23, "kl": 0.097500714622373, "ce": 0.6191590350607167}, {"step": 24, "kl": 0.12049537989488394, "ce": 0.7157263320641413}, {"step": 25, "kl": 0.11485959780006136, "ce": 0.7837460764338461}, {"step": 26, "kl": 0.10871448594066296, "ce": 0.6415289242094926}, {"step": 27, "kl": 0.08892391149918319, "ce": 0.8036354145462721}, {"step": 28, "kl": 0.10474075892811788, "ce": 0.7217193559731439}, {"step": 29, "kl": 0.09388576242897043, "ce": 0.7850120139624388}, {"step": 30, "kl": 0.0995237649012466, "ce": 0.8247943529600181}, {"step": 31, "kl": 0.0922961457711565, "ce": 0.7896816834245849}, {"step": 32, "kl": 0.09629181949032434, "ce": 0.697716701895045}, {"step": 33, "kl": 0.10254598614736357, "ce": 0.642148438136446}, {"step": 34, "kl": 0.09617822192859732, "ce": 0.8132967501479242}, {"step": 35, "kl": 0.3407133686619601, "ce": 0.8689212223633458}, {"step": 36, "kl": 0.10559096359117712, "ce": 1.0017996401365548}, {"step": 37, "kl": 0.09837513576386286, "ce": 0.8126495590804388}, {"step": 38, "kl": 0.09574623686710376, "ce": 0.7976771886602614}, {"step": 39, "kl": 0.0996784366668822, "ce": 0.8823263954405672}, {"step": 40, "kl": 0.08178518268941488, "ce": 0.7447492747168128}, {"step": 41, "kl": 0.09374485403975183, "ce": 0.8725293182048461}, {"step": 42, "kl": 0.09195210445272706, "ce": 0.9070153332396642}, {"step": 43, "kl": 0.07322550623894475, "ce": 0.7757521804457839}, {"step": 44, "kl": 0.11485987392331722, "ce": 0.8320639861419628}, {"step": 45, "kl": 0.10499751672593906, "ce": 0.8350261446212353}, {"step": 46, "kl": 0.0806845187525679, "ce": 0.6728429377599899}, {"step": 47, "kl": 0.09268465075812998, "ce": 0.7663444589886313}, {"step": 48, "kl": 0.08700528922865747, "ce": 0.7506025423958448}, {"step": 49, "kl": 0.07680382797079187, "ce": 0.7726605412960509}, {"step": 50, "kl": 0.09287302180506546, "ce": 0.824436310376929}, {"step": 51, "kl": 0.07937308398175359, "ce": 0.7422083333287859}, {"step": 52, "kl": 0.174926495888884, "ce": 0.9689085203694456}, {"step": 53, "kl": 0.10486750603088713, "ce": 0.8948021163679147}, {"step": 54, "kl": 0.0965168355071258, "ce": 0.8187728685370841}, {"step": 55, "kl": 0.1113124626014682, "ce": 0.7942022835807502}, {"step": 56, "kl": 0.07980060299758134, "ce": 0.7364646780396072}, {"step": 57, "kl": 0.08466986149871197, "ce": 0.7409824233159982}, {"step": 58, "kl": 0.09220262193355014, "ce": 0.6467440090240382}, {"step": 59, "kl": 0.1338773473855523, "ce": 0.7878284896102198}, {"step": 60, "kl": 0.1291831062408243, "ce": 0.7328389115456371}, {"step": 61, "kl": 0.11614765930671721, "ce": 0.8153255637365444}, {"step": 62, "kl": 0.0901898691563007, "ce": 0.6899851554681447}, {"step": 63, "kl": 0.12509820693809479, "ce": 0.7770674192869627}, {"step": 64, "kl": 0.0960984231029631, "ce": 0.7782247221372735}, {"step": 65, "kl": 0.0800182882154226, "ce": 0.8788680474735001}, {"step": 66, "kl": 0.08568492525052415, "ce": 0.802449806750003}, {"step": 67, "kl": 0.0864706615492716, "ce": 0.8596746804190427}, {"step": 68, "kl": 0.08454404879414511, "ce": 0.6260973290911214}, {"step": 69, "kl": 0.09577567968258152, "ce": 0.742719560950271}, {"step": 70, "kl": 0.09384448431355885, "ce": 0.7723847871731958}, {"step": 71, "kl": 0.11663973620048995, "ce": 0.7825735532055483}, {"step": 72, "kl": 0.08758810667790445, "ce": 0.8448868899396285}, {"step": 73, "kl": 0.08096026651840171, "ce": 0.9689186363185314}, {"step": 74, "kl": 0.09475939935751038, "ce": 0.8897933814639136}, {"step": 75, "kl": 0.08219208373038603, "ce": 0.9470210288742015}, {"step": 76, "kl": 0.10181014367738256, "ce": 0.7122932934943046}, {"step": 77, "kl": 0.07851372672877181, "ce": 0.8205682032316634}, {"step": 78, "kl": 0.08872846704918788, "ce": 0.6964732488512896}, {"step": 79, "kl": 0.08187503129381679, "ce": 0.7454565625936719}, {"step": 80, "kl": 0.08460120155519338, "ce": 0.8347561801822785}, {"step": 81, "kl": 0.09909958511818456, "ce": 0.7160903480574057}, {"step": 82, "kl": 0.08111291105820412, "ce": 0.7267647525851055}, {"step": 83, "kl": 0.11069618135879228, "ce": 0.7649062838782458}, {"step": 84, "kl": 0.10152307173047789, "ce": 0.8436782426530983}, {"step": 85, "kl": 0.07726973991457273, "ce": 0.7235066931184444}, {"step": 86, "kl": 0.08078449380646098, "ce": 0.7154143248949381}, {"step": 87, "kl": 0.09219499859700994, "ce": 0.813069425880141}, {"step": 88, "kl": 0.08950278905570902, "ce": 0.7338144378011159}, {"step": 89, "kl": 0.0922897200743877, "ce": 1.010432022273467}, {"step": 90, "kl": 0.0932850822915528, "ce": 0.897628980822085}, {"step": 91, "kl": 0.07396250023813652, "ce": 0.8268917559587875}, {"step": 92, "kl": 0.08982332958118054, "ce": 0.7328392505812303}, {"step": 93, "kl": 0.06985195878285788, "ce": 0.8412201672464761}, {"step": 94, "kl": 0.0911400284063915, "ce": 0.7524342015414833}, {"step": 95, "kl": 0.10398279222148137, "ce": 0.7884526221499062}, {"step": 96, "kl": 0.07383796991700997, "ce": 0.6926575609206402}, {"step": 97, "kl": 0.08446912891222708, "ce": 0.8537151756021604}, {"step": 98, "kl": 0.07158553463133378, "ce": 0.8097669692018904}, {"step": 99, "kl": 0.14213059197633404, "ce": 0.7417402720881647}, {"step": 100, "kl": 0.0910124920413597, "ce": 0.727843509330974}, {"step": 101, "kl": 0.0827937380539018, "ce": 0.7258190682313668}, {"step": 102, "kl": 0.09744825677416352, "ce": 0.7401494143604477}, {"step": 103, "kl": 0.0806573718516053, "ce": 0.6864801570496476}, {"step": 104, "kl": 0.08279725440363345, "ce": 0.7120041509183065}, {"step": 105, "kl": 0.08469100870161744, "ce": 0.8224385337934969}, {"step": 106, "kl": 0.11153623145994704, "ce": 0.7628528819204292}, {"step": 107, "kl": 0.12458443378424419, "ce": 0.786137408853512}, {"step": 108, "kl": 0.09961716585667722, "ce": 0.9002489914540119}, {"step": 109, "kl": 0.10903501507812385, "ce": 0.7564007703470442}, {"step": 110, "kl": 0.07899807411367266, "ce": 0.6617023439051181}, {"step": 111, "kl": 0.06702921263673314, "ce": 0.8778682319376807}, {"step": 112, "kl": 0.09410544822507969, "ce": 0.7710459649615258}, {"step": 113, "kl": 0.12072259296261686, "ce": 0.9245268186386914}, {"step": 114, "kl": 0.08460548132317469, "ce": 0.7794855448334573}, {"step": 115, "kl": 0.09075325231276753, "ce": 0.8448894261322597}, {"step": 116, "kl": 0.103207866995649, "ce": 0.7752762771067448}, {"step": 117, "kl": 0.08400467037749294, "ce": 0.7552973119059461}, {"step": 118, "kl": 0.07856842342606847, "ce": 0.8608459321579132}, {"step": 119, "kl": 0.07566149882850619, "ce": 0.7557004426067817}, {"step": 120, "kl": 0.09680098362544926, "ce": 0.7524648031810262}, {"step": 121, "kl": 0.07631157034609633, "ce": 0.8150121764425353}, {"step": 122, "kl": 0.19051981061776904, "ce": 0.8133299032345681}, {"step": 123, "kl": 0.10306595816621189, "ce": 0.8725806868690685}, {"step": 124, "kl": 0.10395336067511413, "ce": 0.6319774982003719}, {"step": 125, "kl": 0.0733321451054132, "ce": 0.692317691400596}, {"step": 126, "kl": 0.08091420565497778, "ce": 0.8221527225031391}, {"step": 127, "kl": 0.08849791238248517, "ce": 0.6993248175756103}, {"step": 128, "kl": 0.0776241843866456, "ce": 0.8252384585934086}, {"step": 129, "kl": 0.08991560618082683, "ce": 0.7366909790629801}, {"step": 130, "kl": 0.09048640661919384, "ce": 0.7306844297903623}, {"step": 131, "kl": 0.09769452745399668, "ce": 0.7870282311847006}, {"step": 132, "kl": 0.09037825095792291, "ce": 0.878534908470884}, {"step": 133, "kl": 0.09930626752172787, "ce": 0.8782613522460725}, {"step": 134, "kl": 0.09551798464559826, "ce": 0.8397238765514128}, {"step": 135, "kl": 0.09106471374961846, "ce": 0.831439707350204}, {"step": 136, "kl": 0.06747512691761608, "ce": 0.6463224779682399}, {"step": 137, "kl": 0.08210894921510033, "ce": 0.777138502013654}, {"step": 138, "kl": 0.12045182647695593, "ce": 0.7096664962599796}, {"step": 139, "kl": 0.10381337049361493, "ce": 0.7959204826287938}, {"step": 140, "kl": 0.11745995305645296, "ce": 0.8098598435547117}, {"step": 141, "kl": 0.10017603094955206, "ce": 0.7496829371560702}, {"step": 142, "kl": 0.08161591704766355, "ce": 0.7858482860383533}, {"step": 143, "kl": 0.0830963331546622, "ce": 0.6523365725296706}, {"step": 144, "kl": 0.09594671241015791, "ce": 0.811831019429096}, {"step": 145, "kl": 0.08039544367016865, "ce": 0.8207797006073438}, {"step": 146, "kl": 0.0922680904410478, "ce": 0.8070372876846094}, {"step": 147, "kl": 0.08168940229323929, "ce": 0.7397017948459093}, {"step": 148, "kl": 0.08879343967381559, "ce": 0.7605120982361872}, {"step": 149, "kl": 0.07205631317537106, "ce": 0.9144678742133477}, {"step": 150, "kl": 0.07371135424881417, "ce": 0.7635444268173558}, {"step": 151, "kl": 0.11085637744774446, "ce": 0.7674701435803584}, {"step": 152, "kl": 0.0848029352913872, "ce": 0.6704415969057075}, {"step": 153, "kl": 0.07403241436585482, "ce": 0.8067272486234894}, {"step": 154, "kl": 0.12296982101919082, "ce": 0.9057749404830703}, {"step": 155, "kl": 0.08464520727548977, "ce": 0.905862264781199}, {"step": 156, "kl": 0.10317229468375198, "ce": 0.7425636011143042}, {"step": 157, "kl": 0.11135345120406967, "ce": 1.0075722416336501}, {"step": 158, "kl": 0.07992951749233908, "ce": 0.7453595334883059}, {"step": 159, "kl": 0.06816076071521315, "ce": 0.7648204117628159}, {"step": 160, "kl": 0.10651932989673485, "ce": 0.8015105660892863}, {"step": 161, "kl": 0.12583178981222332, "ce": 0.6302230790987482}, {"step": 162, "kl": 0.12540295103373283, "ce": 0.8066187551497308}, {"step": 163, "kl": 0.08547408315633048, "ce": 0.7685433237979161}, {"step": 164, "kl": 0.0921700065716419, "ce": 0.7735901057259296}, {"step": 165, "kl": 0.0988811359520959, "ce": 0.8496121872619556}, {"step": 166, "kl": 0.1076131556740638, "ce": 0.8042823968250983}, {"step": 167, "kl": 0.08413737704253209, "ce": 0.8605358967952095}, {"step": 168, "kl": 0.08490993240638561, "ce": 0.7851928834933396}, {"step": 169, "kl": 0.10886240731752836, "ce": 0.8616021938564814}, {"step": 170, "kl": 0.09566130127225601, "ce": 0.8422224761704864}, {"step": 171, "kl": 0.10088991232443743, "ce": 0.9077443313247695}, {"step": 172, "kl": 0.0758000236524315, "ce": 0.6666983903684005}, {"step": 173, "kl": 0.08607018312393577, "ce": 0.7799981684900528}, {"step": 174, "kl": 0.0850746867618417, "ce": 0.9125789251471436}, {"step": 175, "kl": 0.0957135727731664, "ce": 0.8526842199173311}, {"step": 176, "kl": 0.06572817321465, "ce": 0.6885612095176941}, {"step": 177, "kl": 0.07860493622499976, "ce": 0.9249015309111818}, {"step": 178, "kl": 0.06769477072512259, "ce": 0.7397145340729303}, {"step": 179, "kl": 0.09146953437971794, "ce": 0.7943172056401282}, {"step": 180, "kl": 0.0954393503041127, "ce": 0.7662058582792538}, {"step": 181, "kl": 0.06903047295628478, "ce": 0.820470203355855}, {"step": 182, "kl": 0.07822174743455704, "ce": 0.8185656786874508}, {"step": 183, "kl": 0.08784130220756728, "ce": 0.7857837007833548}, {"step": 184, "kl": 0.08910537111194101, "ce": 0.7747841657036048}, {"step": 185, "kl": 0.10411061417625718, "ce": 0.8135930674179327}, {"step": 186, "kl": 0.11455677088855923, "ce": 0.7687481893058332}, {"step": 187, "kl": 0.09081172044145658, "ce": 0.7757896172131515}, {"step": 188, "kl": 0.08982071534513446, "ce": 0.8257800549060315}, {"step": 189, "kl": 0.08711902828967671, "ce": 0.7883849190105305}, {"step": 190, "kl": 0.07843147782495125, "ce": 0.8280463290879452}, {"step": 191, "kl": 0.07398689279049069, "ce": 0.7273035227677054}, {"step": 192, "kl": 0.11089896807021873, "ce": 0.8824776724386072}, {"step": 193, "kl": 0.07472689312729597, "ce": 0.8410019666278457}, {"step": 194, "kl": 0.080538769087723, "ce": 0.8667402160992783}, {"step": 195, "kl": 0.096845682474937, "ce": 0.7790072302852755}, {"step": 196, "kl": 0.08062100790092579, "ce": 0.6807086312125907}, {"step": 197, "kl": 0.06412454443418265, "ce": 0.8610494087301315}, {"step": 198, "kl": 0.09411548996868799, "ce": 0.7451947850451782}, {"step": 199, "kl": 0.08895591998723912, "ce": 0.8638997290496526}, {"step": 200, "kl": 0.0959261199133477, "ce": 0.6877778348354495}, {"step": 201, "kl": 0.08028835732472968, "ce": 0.8337955812034115}, {"step": 202, "kl": 0.08483405215135618, "ce": 0.928071936506654}, {"step": 203, "kl": 0.08934922131295185, "ce": 0.8134573767884821}, {"step": 204, "kl": 0.09243218073076118, "ce": 0.7142446389477353}, {"step": 205, "kl": 0.10772365429052261, "ce": 0.8687525010774922}, {"step": 206, "kl": 0.08442791644802235, "ce": 0.6758549274470407}, {"step": 207, "kl": 0.15644933914388887, "ce": 0.7987965933962802}, {"step": 208, "kl": 0.08309562134737591, "ce": 0.7983166208595514}, {"step": 209, "kl": 0.08824088141989005, "ce": 0.8995486008534508}, {"step": 210, "kl": 0.0784001895897017, "ce": 0.7419424091409363}, {"step": 211, "kl": 0.08781911953952043, "ce": 0.7095790031586664}, {"step": 212, "kl": 0.08606413288274388, "ce": 0.812442289002931}, {"step": 213, "kl": 0.09310756645704571, "ce": 0.7810413785033173}, {"step": 214, "kl": 0.08601881244269927, "ce": 0.7874518449720869}, {"step": 215, "kl": 0.08542021177487916, "ce": 0.8075017785132278}, {"step": 216, "kl": 0.09272612180934786, "ce": 0.8441983378685803}, {"step": 217, "kl": 0.08195477705067002, "ce": 0.8699275723398971}, {"step": 218, "kl": 0.08909383982392348, "ce": 0.8920307738829119}, {"step": 219, "kl": 0.07450762915152465, "ce": 0.7609281212010423}, {"step": 220, "kl": 0.10069547244097349, "ce": 0.9373019637064106}, {"step": 221, "kl": 0.08313066412040243, "ce": 0.9040213388380038}, {"step": 222, "kl": 0.06966465950252367, "ce": 0.776630812820273}, {"step": 223, "kl": 0.07382284215747509, "ce": 0.7252026292559995}, {"step": 224, "kl": 0.0807178635259353, "ce": 0.7906172001016998}, {"step": 225, "kl": 0.08731466974887547, "ce": 0.6954303918475706}, {"step": 226, "kl": 0.06773119153992668, "ce": 0.7543455321070158}, {"step": 227, "kl": 0.10985855509991246, "ce": 0.8511101032928435}, {"step": 228, "kl": 0.0800812381299136, "ce": 0.8273030414168551}, {"step": 229, "kl": 0.08017661496844247, "ce": 0.6820819521910393}, {"step": 230, "kl": 0.07897427644080136, "ce": 0.6555726848257762}, {"step": 231, "kl": 0.08455479813167936, "ce": 0.7680613863337825}, {"step": 232, "kl": 0.07794802567748563, "ce": 0.9008645578197924}, {"step": 233, "kl": 0.0892321087006994, "ce": 0.7319638917859295}, {"step": 234, "kl": 0.07334123134465455, "ce": 0.7998086015918935}, {"step": 235, "kl": 0.0775077481251819, "ce": 0.8174369288885379}, {"step": 236, "kl": 0.09000571422341735, "ce": 0.7482812315725196}, {"step": 237, "kl": 0.06901504197842041, "ce": 0.853556049097246}, {"step": 238, "kl": 0.11112701114676826, "ce": 0.8351375072358421}, {"step": 239, "kl": 0.07571175612544166, "ce": 0.8341385836198659}, {"step": 240, "kl": 0.07336955390846024, "ce": 0.6914953361858022}, {"step": 241, "kl": 0.07982230021923445, "ce": 0.8194881053225368}, {"step": 242, "kl": 0.08122559425700422, "ce": 0.7582238642972674}, {"step": 243, "kl": 0.0706963102186517, "ce": 0.8564885323292996}, {"step": 244, "kl": 0.07381914263186247, "ce": 0.8473575249672404}, {"step": 245, "kl": 0.0961709611469156, "ce": 0.8585013560492103}, {"step": 246, "kl": 0.06963517433515376, "ce": 0.726673123761195}, {"step": 247, "kl": 0.06946349469365122, "ce": 0.7820019496345392}, {"step": 248, "kl": 0.0923872378043253, "ce": 0.8341976316587078}, {"step": 249, "kl": 0.08879861395692373, "ce": 0.7147466282499424}, {"step": 250, "kl": 0.0778354930890944, "ce": 0.8528901281010313}, {"step": 251, "kl": 0.071381428253439, "ce": 0.6548455685668348}, {"step": 252, "kl": 0.07962845321751598, "ce": 0.9134451007209446}, {"step": 253, "kl": 0.09709198676720743, "ce": 0.8539705544965503}, {"step": 254, "kl": 0.0900929296599969, "ce": 0.915459610401806}, {"step": 255, "kl": 0.0879009316878621, "ce": 0.8056749039248954}, {"step": 256, "kl": 0.09254567118514516, "ce": 0.7900118263664331}, {"step": 257, "kl": 0.09762051371206287, "ce": 0.7575215647770809}, {"step": 258, "kl": 0.08501329951628721, "ce": 0.7078289794921875}, {"step": 259, "kl": 0.07463583787022057, "ce": 0.7663405254118283}, {"step": 260, "kl": 0.06189540585903493, "ce": 0.7088640448791955}, {"step": 261, "kl": 0.09154002777735393, "ce": 0.7703239359028226}, {"step": 262, "kl": 0.08249167291626397, "ce": 0.7898190078424432}, {"step": 263, "kl": 0.07869183693047377, "ce": 0.7307780849539889}, {"step": 264, "kl": 0.06942633692061992, "ce": 0.8089061393557002}, {"step": 265, "kl": 0.06565611605272963, "ce": 0.8339211637621483}, {"step": 266, "kl": 0.0754869649462924, "ce": 0.6110647269359055}, {"step": 267, "kl": 0.07847828438683627, "ce": 0.716445627452097}, {"step": 268, "kl": 0.09032091720525051, "ce": 0.8059161800657271}, {"step": 269, "kl": 0.09725314685801331, "ce": 0.7051476953447717}, {"step": 270, "kl": 0.08695159408333432, "ce": 0.9037274725537088}, {"step": 271, "kl": 0.08389905106258908, "ce": 0.899373411709321}, {"step": 272, "kl": 0.06807221234761618, "ce": 0.7653094143721688}, {"step": 273, "kl": 0.09445144267177852, "ce": 0.8442421442705543}, {"step": 274, "kl": 0.07302338103138604, "ce": 0.7786556396484374}, {"step": 275, "kl": 0.07177723965989709, "ce": 0.64052229401815}, {"step": 276, "kl": 0.07760146425167447, "ce": 0.7763192404209702}, {"step": 277, "kl": 0.0751952217273214, "ce": 0.7939896715129703}, {"step": 278, "kl": 0.07625956909690278, "ce": 0.7307304341595575}, {"step": 279, "kl": 0.06643354418844319, "ce": 0.7243186531256356}, {"step": 280, "kl": 0.09686008058022272, "ce": 0.9081759349222713}, {"step": 281, "kl": 0.09179058459718907, "ce": 0.8334961438658065}, {"step": 282, "kl": 0.07351849471098479, "ce": 0.7813597106305401}, {"step": 283, "kl": 0.086442149761412, "ce": 0.8132497838884846}, {"step": 284, "kl": 0.06664828857698175, "ce": 0.6355210109420222}, {"step": 285, "kl": 0.08050001080830892, "ce": 0.8862281249696761}, {"step": 286, "kl": 0.07552954801742605, "ce": 0.7750521708742816}, {"step": 287, "kl": 0.07886996905567466, "ce": 0.7376785427299594}, {"step": 288, "kl": 0.0877824187047825, "ce": 0.8492133524510768}, {"step": 289, "kl": 0.07300138251290825, "ce": 0.8036856053775773}, {"step": 290, "kl": 0.07602307078463018, "ce": 0.7747717170287092}, {"step": 291, "kl": 0.06815173547213406, "ce": 0.7216945547667356}, {"step": 292, "kl": 0.09069608993092605, "ce": 0.7682102096764232}, {"step": 293, "kl": 0.08932015526752685, "ce": 0.8352127624072616}, {"step": 294, "kl": 0.0813635557928622, "ce": 0.7837349732372094}, {"step": 295, "kl": 0.0762031166348972, "ce": 0.7754526403215198}, {"step": 296, "kl": 0.09024364336926725, "ce": 0.8965808901144121}, {"step": 297, "kl": 0.08528247274451384, "ce": 0.8011758203412577}, {"step": 298, "kl": 0.07222164098816856, "ce": 0.6948281492009206}, {"step": 299, "kl": 0.07138155820293739, "ce": 0.7597634865948819}, {"step": 300, "kl": 0.07578608622477354, "ce": 0.8458871504646452}, {"step": 301, "kl": 0.08049752798618744, "ce": 0.789015028735407}, {"step": 302, "kl": 0.09667424649284846, "ce": 0.8304434901359236}, {"step": 303, "kl": 0.08669850846133034, "ce": 0.763610175964093}, {"step": 304, "kl": 0.08951782074892464, "ce": 0.7978608718952418}, {"step": 305, "kl": 0.07566919461785711, "ce": 0.6810862229677862}, {"step": 306, "kl": 0.07409740708185404, "ce": 0.7985178667735284}, {"step": 307, "kl": 0.10164237630133535, "ce": 0.7475486475917099}, {"step": 308, "kl": 0.07827100546610857, "ce": 0.6830788730879607}, {"step": 309, "kl": 0.08713084967936145, "ce": 0.6884403733384252}, {"step": 310, "kl": 0.09666586549024128, "ce": 0.6957636677067933}, {"step": 311, "kl": 0.08452439353224821, "ce": 0.8453433032632395}, {"step": 312, "kl": 0.07757742316918043, "ce": 0.764164198550432}, {"step": 313, "kl": 0.08034661921059214, "ce": 0.7370814736236428}, {"step": 314, "kl": 0.07429046209987603, "ce": 0.8348964071816225}, {"step": 315, "kl": 0.06984717350490624, "ce": 0.6395822488344632}, {"step": 316, "kl": 0.0811566734747125, "ce": 0.8274277688939046}, {"step": 317, "kl": 0.06993545939904133, "ce": 0.7214880359514567}, {"step": 318, "kl": 0.08763766060429368, "ce": 0.6794897012481406}, {"step": 319, "kl": 0.07748302072406679, "ce": 0.7098461848496248}, {"step": 320, "kl": 0.08257033416665654, "ce": 0.7659341813167209}, {"step": 321, "kl": 0.0806259243473766, "ce": 0.6890023974409533}, {"step": 322, "kl": 0.08209509668454622, "ce": 0.6937157734231698}, {"step": 323, "kl": 0.07661353241779859, "ce": 0.8235821071768954}, {"step": 324, "kl": 0.06387549091668475, "ce": 0.7767177057412826}, {"step": 325, "kl": 0.0804975869380867, "ce": 0.7696490374966176}, {"step": 326, "kl": 0.0828319167703904, "ce": 0.7721536986410245}, {"step": 327, "kl": 0.08772039431416627, "ce": 0.8810995314473751}, {"step": 328, "kl": 0.08939934486884603, "ce": 0.6748822905746066}, {"step": 329, "kl": 0.07764240038764295, "ce": 0.9359463494860816}, {"step": 330, "kl": 0.08222616083993245, "ce": 0.7537212200245333}, {"step": 331, "kl": 0.08633372558519858, "ce": 0.9454128366316431}, {"step": 332, "kl": 0.0862254243086423, "ce": 0.7068357216316994}, {"step": 333, "kl": 0.07074597460532328, "ce": 0.6928915341637001}, {"step": 334, "kl": 0.09256109068089947, "ce": 0.7317082884060417}, {"step": 335, "kl": 0.08286309961185864, "ce": 0.8676782638056769}, {"step": 336, "kl": 0.08684490325916512, "ce": 0.7876013492280343}, {"step": 337, "kl": 0.0869835728037932, "ce": 0.794039221925437}, {"step": 338, "kl": 0.07988586971517626, "ce": 0.8201970097444173}, {"step": 339, "kl": 0.07627284402822665, "ce": 0.8067383221962288}, {"step": 340, "kl": 0.10633088974491875, "ce": 0.750340801680169}, {"step": 341, "kl": 0.08373018951851163, "ce": 0.8353314648965741}, {"step": 342, "kl": 0.08897136960799862, "ce": 0.7493302480504952}, {"step": 343, "kl": 0.08688656298999693, "ce": 0.7845834468290128}, {"step": 344, "kl": 0.07134923335207666, "ce": 0.670533741520502}, {"step": 345, "kl": 0.08292938635440432, "ce": 0.6338914275832173}, {"step": 346, "kl": 0.08603503272429494, "ce": 0.790562502872003}, {"step": 347, "kl": 0.07570787921654167, "ce": 0.6852399887976708}, {"step": 348, "kl": 0.09550404364069, "ce": 0.8975725115400309}, {"step": 349, "kl": 0.09470526596406668, "ce": 0.7125105264320907}, {"step": 350, "kl": 0.07841640277864309, "ce": 0.8021239517670042}, {"step": 351, "kl": 0.07526312669979275, "ce": 0.8956005002823344}, {"step": 352, "kl": 0.09084080227938567, "ce": 0.8659891279481295}, {"step": 353, "kl": 0.07021162019703563, "ce": 0.7315250000999027}, {"step": 354, "kl": 0.06547034619452234, "ce": 0.7600210410970606}, {"step": 355, "kl": 0.06736267029131034, "ce": 0.8043696075208495}, {"step": 356, "kl": 0.0857480547290332, "ce": 0.7774914535942882}, {"step": 357, "kl": 0.06941767286257994, "ce": 0.7401435738072899}, {"step": 358, "kl": 0.0752814637729977, "ce": 0.7924679130694088}, {"step": 359, "kl": 0.06796300567926766, "ce": 0.8169523666881126}, {"step": 360, "kl": 0.06810818513045999, "ce": 0.7190565877997764}, {"step": 361, "kl": 0.06312505408509136, "ce": 0.7568268981527853}, {"step": 362, "kl": 0.08526252842907676, "ce": 0.8842977228818334}, {"step": 363, "kl": 0.10148780569545414, "ce": 0.8408497273854768}, {"step": 364, "kl": 0.08162742251355215, "ce": 0.854222582637353}, {"step": 365, "kl": 0.07284185603477751, "ce": 0.7760241784171324}, {"step": 366, "kl": 0.0787541217829765, "ce": 0.8538535609505566}, {"step": 367, "kl": 0.07181604445750939, "ce": 0.7822547295738569}, {"step": 368, "kl": 0.0921697745628049, "ce": 1.013266611316977}, {"step": 369, "kl": 0.09831716238138122, "ce": 0.8941440169810748}, {"step": 370, "kl": 0.08797876388442309, "ce": 0.9112772335476345}, {"step": 371, "kl": 0.07739995476625787, "ce": 0.7992206770061469}, {"step": 372, "kl": 0.0693955781948826, "ce": 0.759680576925134}, {"step": 373, "kl": 0.08776725826869007, "ce": 0.8211133755980743}, {"step": 374, "kl": 0.0970731533965239, "ce": 0.6668495386885757}, {"step": 375, "kl": 0.06817756349669153, "ce": 0.9206712636810651}, {"step": 376, "kl": 0.07718888866178057, "ce": 0.8933777094078523}, {"step": 377, "kl": 0.08336412474778687, "ce": 0.7783269846045513}, {"step": 378, "kl": 0.0723082904762332, "ce": 0.7618597267040748}, {"step": 379, "kl": 0.09801357337145344, "ce": 0.8113016010303779}, {"step": 380, "kl": 0.0988402429795423, "ce": 0.6955304743233871}, {"step": 381, "kl": 0.10093714646324281, "ce": 0.8286442716953163}, {"step": 382, "kl": 0.08237507688246874, "ce": 0.6961871734562693}, {"step": 383, "kl": 0.08751214615592087, "ce": 0.7037055308176714}, {"step": 384, "kl": 0.06693112644014934, "ce": 0.6065000900360638}, {"step": 385, "kl": 0.0852408906193873, "ce": 0.8967949005415599}, {"step": 386, "kl": 0.0822837074727821, "ce": 0.9090236773562239}, {"step": 387, "kl": 0.074810924952274, "ce": 0.7716776503505167}, {"step": 388, "kl": 0.07114274641486296, "ce": 0.8270395787356404}, {"step": 389, "kl": 0.10053941252650961, "ce": 0.7880547679180278}, {"step": 390, "kl": 0.07555786626923508, "ce": 0.7031456638481649}, {"step": 391, "kl": 0.07982836802583951, "ce": 0.8915264726949348}, {"step": 392, "kl": 0.07542551019760171, "ce": 0.8303038573910634}, {"step": 393, "kl": 0.07051880795232288, "ce": 0.7748514455075712}, {"step": 394, "kl": 0.11401985829114783, "ce": 0.842371132454}, {"step": 395, "kl": 0.09540242385891975, "ce": 0.7806642339242289}, {"step": 396, "kl": 0.08647390400859246, "ce": 0.8273685529063034}, {"step": 397, "kl": 0.07929070539141447, "ce": 0.7713972663000432}, {"step": 398, "kl": 0.08176475194867822, "ce": 0.7545364670300627}, {"step": 399, "kl": 0.0759325261482298, "ce": 0.8273797076192734}, {"step": 400, "kl": 0.1003020643218746, "ce": 0.9323451843329883}, {"step": 401, "kl": 0.0697395664650328, "ce": 0.6963996091574306}, {"step": 402, "kl": 0.0794568990106104, "ce": 0.7537105025042419}, {"step": 403, "kl": 0.06512784707813811, "ce": 0.6914188429702979}, {"step": 404, "kl": 0.06743983797800873, "ce": 0.9000448556954351}, {"step": 405, "kl": 0.10691733318885611, "ce": 0.7967065831889277}, {"step": 406, "kl": 0.10375044536242661, "ce": 0.8582425896913723}, {"step": 407, "kl": 0.09030435017654231, "ce": 0.8264298275131181}, {"step": 408, "kl": 0.08845382878505814, "ce": 0.6694721161562593}, {"step": 409, "kl": 0.08493160041720885, "ce": 0.9388090994820667}, {"step": 410, "kl": 0.0703643450320679, "ce": 0.8195739484514508}, {"step": 411, "kl": 0.10752330055369497, "ce": 0.8713504734580337}, {"step": 412, "kl": 0.09507514650383139, "ce": 0.8074778423443913}, {"step": 413, "kl": 0.07426131485345668, "ce": 0.6509220581964452}, {"step": 414, "kl": 0.06336875179785915, "ce": 0.6317069495662295}, {"step": 415, "kl": 0.10007571715307655, "ce": 0.7870530969956341}, {"step": 416, "kl": 0.07799218673750224, "ce": 0.7335757287891328}, {"step": 417, "kl": 0.08023444726577939, "ce": 0.821351196194818}, {"step": 418, "kl": 0.08328762059486587, "ce": 0.8488164453120246}, {"step": 419, "kl": 0.07134641257316669, "ce": 0.7406102270431479}, {"step": 420, "kl": 0.08417309450238696, "ce": 0.8079105257654745}, {"step": 421, "kl": 0.06869607164022946, "ce": 0.7221616237918544}, {"step": 422, "kl": 0.06817234195493249, "ce": 0.6660619483511715}, {"step": 423, "kl": 0.08251055466083156, "ce": 0.827915843969325}, {"step": 424, "kl": 0.09745711950171392, "ce": 0.7557537609340957}, {"step": 425, "kl": 0.07158515625794296, "ce": 0.843042612378444}, {"step": 426, "kl": 0.07549661281988641, "ce": 0.9316420745849608}, {"step": 427, "kl": 0.0687062584113682, "ce": 0.8217324549791469}, {"step": 428, "kl": 0.11047132262794077, "ce": 0.797641181054318}, {"step": 429, "kl": 0.07260004013542115, "ce": 0.6487233705366}, {"step": 430, "kl": 0.07945274532356178, "ce": 0.8455388935520088}, {"step": 431, "kl": 0.08700175961763346, "ce": 0.9614800393331999}, {"step": 432, "kl": 0.09445060058936594, "ce": 0.7942229937962815}, {"step": 433, "kl": 0.079620790018382, "ce": 0.6456912895615672}, {"step": 434, "kl": 0.08664651635034887, "ce": 0.724826434678794}, {"step": 435, "kl": 0.07780768201428248, "ce": 0.6938849216112246}, {"step": 436, "kl": 0.07486827491265341, "ce": 0.6651449454328705}, {"step": 437, "kl": 0.07210904248294372, "ce": 0.7760887009833688}, {"step": 438, "kl": 0.09950143176105998, "ce": 0.9260887572287855}, {"step": 439, "kl": 0.0927055050899136, "ce": 0.8371000345628183}, {"step": 440, "kl": 0.06007536644980721, "ce": 0.8778934234451615}, {"step": 441, "kl": 0.07098920783245637, "ce": 0.8257116064506986}, {"step": 442, "kl": 0.08368920921383048, "ce": 0.8808585272894967}, {"step": 443, "kl": 0.0866273038008267, "ce": 0.7886792795181571}, {"step": 444, "kl": 0.07960679827184233, "ce": 0.7388495353484996}, {"step": 445, "kl": 0.08125795210257848, "ce": 0.8156337458208393}, {"step": 446, "kl": 0.07657455873597879, "ce": 0.740011392753815}, {"step": 447, "kl": 0.08686273994746509, "ce": 0.9007944576186577}, {"step": 448, "kl": 0.07722065763184707, "ce": 0.7069983769220879}, {"step": 449, "kl": 0.04873139580457228, "ce": 0.7743428076282068}, {"step": 450, "kl": 0.04807320808477771, "ce": 0.8735892927175248}, {"step": 451, "kl": 0.04740057511827487, "ce": 0.6222010201825497}, {"step": 452, "kl": 0.045050821078050834, "ce": 0.7433357611772679}, {"step": 453, "kl": 0.043866966458648564, "ce": 0.7838397788669496}, {"step": 454, "kl": 0.051592214161838276, "ce": 0.6504157975947291}, {"step": 455, "kl": 0.05465239827858204, "ce": 0.7557005666274227}, {"step": 456, "kl": 0.051454250214699015, "ce": 0.7808713426776961}, {"step": 457, "kl": 0.06386234383369999, "ce": 0.7967575180572475}, {"step": 458, "kl": 0.04637300942752407, "ce": 0.7719438066214279}, {"step": 459, "kl": 0.04847971863688396, "ce": 0.7867486705756853}, {"step": 460, "kl": 0.03960313302705796, "ce": 0.8149703529828418}, {"step": 461, "kl": 0.04353996021386193, "ce": 0.836481228562542}, {"step": 462, "kl": 0.038599133359124384, "ce": 0.8775181956105419}, {"step": 463, "kl": 0.0495478269782941, "ce": 0.7780933228217357}, {"step": 464, "kl": 0.06065537620022761, "ce": 0.8602995369693539}, {"step": 465, "kl": 0.04189232345205327, "ce": 0.7461162461723895}, {"step": 466, "kl": 0.043717125810569, "ce": 0.7779150495433925}, {"step": 467, "kl": 0.05361570605451198, "ce": 0.764403438693764}, {"step": 468, "kl": 0.05333588037024872, "ce": 0.7951189906133747}, {"step": 469, "kl": 0.04563202655796181, "ce": 0.776552202680888}, {"step": 470, "kl": 0.05046496374504904, "ce": 0.7586386623419462}, {"step": 471, "kl": 0.06908582530498598, "ce": 0.938137406447937}, {"step": 472, "kl": 0.03954715525218781, "ce": 0.6042399450868128}, {"step": 473, "kl": 0.07067525297354718, "ce": 0.7901938022711338}, {"step": 474, "kl": 0.05012488991129786, "ce": 0.7417746863711551}, {"step": 475, "kl": 0.04365949208147491, "ce": 0.7965164402744814}, {"step": 476, "kl": 0.03527848641264547, "ce": 0.794203015584275}, {"step": 477, "kl": 0.03835963817836761, "ce": 0.7444192330668291}, {"step": 478, "kl": 0.05514765025505261, "ce": 0.8434227509437378}, {"step": 479, "kl": 0.05053445745406321, "ce": 0.8278283449834238}, {"step": 480, "kl": 0.0428676529185051, "ce": 0.753454666123357}, {"step": 481, "kl": 0.049123829344435876, "ce": 0.7489266630146096}, {"step": 482, "kl": 0.053140288564571016, "ce": 0.8610679114737163}, {"step": 483, "kl": 0.042648618909703076, "ce": 0.8048953902769279}, {"step": 484, "kl": 0.0469409565961216, "ce": 0.9195901110491473}, {"step": 485, "kl": 0.04629734983301953, "ce": 0.7490878983480818}, {"step": 486, "kl": 0.05420049090621518, "ce": 0.6616147875176702}, {"step": 487, "kl": 0.054969591931834545, "ce": 0.7400304609210179}, {"step": 488, "kl": 0.05333668308822079, "ce": 0.7555446327677438}, {"step": 489, "kl": 0.04847280676233038, "ce": 0.78820118470281}, {"step": 490, "kl": 0.038498526041354605, "ce": 0.7463573894881602}, {"step": 491, "kl": 0.050067050738015366, "ce": 0.7547483489378772}, {"step": 492, "kl": 0.04770952874280114, "ce": 0.8513575773718453}, {"step": 493, "kl": 0.042869108724128586, "ce": 0.8705772031844881}, {"step": 494, "kl": 0.04310913363050519, "ce": 0.7470384324240952}, {"step": 495, "kl": 0.03289243290635058, "ce": 0.7541719135485198}, {"step": 496, "kl": 0.04224864153582183, "ce": 0.952398069091918}, {"step": 497, "kl": 0.04545248483959562, "ce": 0.7558025189779742}, {"step": 498, "kl": 0.055794023913006446, "ce": 0.8137775875094061}, {"step": 499, "kl": 0.0321347635890694, "ce": 0.8518508259375491}, {"step": 500, "kl": 0.04760854267061357, "ce": 0.8034993040537374}, {"step": 501, "kl": 0.03996210153174895, "ce": 0.9159272694934124}, {"step": 502, "kl": 0.049059049308825, "ce": 0.9085723036193346}, {"step": 503, "kl": 0.04923070540896021, "ce": 0.7706733587050033}, {"step": 504, "kl": 0.04625437207920906, "ce": 0.832318842261524}, {"step": 505, "kl": 0.034772468395671476, "ce": 0.8069418297744377}, {"step": 506, "kl": 0.05122110082976848, "ce": 0.7615916626861323}, {"step": 507, "kl": 0.0484480784060276, "ce": 0.8461670556798325}, {"step": 508, "kl": 0.052701515187179165, "ce": 0.902419232524757}, {"step": 509, "kl": 0.05571721244293342, "ce": 0.638949108877943}, {"step": 510, "kl": 0.06275980180816046, "ce": 0.7310161600184981}, {"step": 511, "kl": 0.03499867732400766, "ce": 0.8069683392907079}, {"step": 512, "kl": 0.05670531878653881, "ce": 0.7243622204857151}, {"step": 513, "kl": 0.04438949217920657, "ce": 0.743585267143299}, {"step": 514, "kl": 0.03416763627038034, "ce": 0.9530432289212595}, {"step": 515, "kl": 0.056561755070580415, "ce": 0.6222836689237972}, {"step": 516, "kl": 0.05748026654592413, "ce": 0.848670650797726}, {"step": 517, "kl": 0.0371664538352423, "ce": 0.7802278806475683}, {"step": 518, "kl": 0.056326485019877026, "ce": 0.8705003722613339}, {"step": 519, "kl": 0.04415717752942811, "ce": 0.7699143774614571}, {"step": 520, "kl": 0.03951678595356945, "ce": 0.7806890185735401}, {"step": 521, "kl": 0.04738867381186302, "ce": 0.9263088108586094}, {"step": 522, "kl": 0.04179307577840412, "ce": 0.9328792538684554}, {"step": 523, "kl": 0.045652838073049595, "ce": 0.7790419370748363}, {"step": 524, "kl": 0.05095281690017005, "ce": 0.7955849946396975}, {"step": 525, "kl": 0.03577692439863791, "ce": 0.750913938841185}, {"step": 526, "kl": 0.04568346990788173, "ce": 0.8517815219992191}, {"step": 527, "kl": 0.03421375739085282, "ce": 0.7805730233423417}, {"step": 528, "kl": 0.046468929186727674, "ce": 0.7041169957902789}, {"step": 529, "kl": 0.040044756051361055, "ce": 0.8677771599566351}, {"step": 530, "kl": 0.04659179116685646, "ce": 0.9326436742035948}, {"step": 531, "kl": 0.050371899112345894, "ce": 0.801336149892585}, {"step": 532, "kl": 0.045864408800755124, "ce": 0.7606770255792177}, {"step": 533, "kl": 0.052033999310527254, "ce": 0.7617129253891279}, {"step": 534, "kl": 0.039520668725949656, "ce": 0.8698039216577168}, {"step": 535, "kl": 0.05500576438017683, "ce": 0.819490742339573}, {"step": 536, "kl": 0.04410063603604801, "ce": 0.829903406116498}, {"step": 537, "kl": 0.04706442189546725, "ce": 0.7529719154875414}, {"step": 538, "kl": 0.04022204006286492, "ce": 0.8248514662714597}, {"step": 539, "kl": 0.04224244892115494, "ce": 0.7898901976349808}, {"step": 540, "kl": 0.042798573978055025, "ce": 0.8923999045289167}, {"step": 541, "kl": 0.043295355359460136, "ce": 0.9139378555696731}, {"step": 542, "kl": 0.034164069325958245, "ce": 0.6852623198371781}, {"step": 543, "kl": 0.04924280490314352, "ce": 0.8318346245276561}, {"step": 544, "kl": 0.03818057420738143, "ce": 0.840549490006494}, {"step": 545, "kl": 0.04707616571572136, "ce": 0.6902138369559428}, {"step": 546, "kl": 0.04695718837483519, "ce": 0.7522372351848}, {"step": 547, "kl": 0.042609777857525725, "ce": 0.7969925587623033}, {"step": 548, "kl": 0.04484116174999811, "ce": 0.9592226903057127}, {"step": 549, "kl": 0.04145997670943296, "ce": 0.7475090662214773}, {"step": 550, "kl": 0.04731135004150288, "ce": 0.5887473252885582}, {"step": 551, "kl": 0.03857508166502409, "ce": 0.8940016396373551}, {"step": 552, "kl": 0.04081811381469461, "ce": 0.8930064217963424}, {"step": 553, "kl": 0.04158830177460321, "ce": 0.7481307014095873}, {"step": 554, "kl": 0.043824139937017496, "ce": 0.8356043920440265}, {"step": 555, "kl": 0.04428239623045407, "ce": 0.8242886176247043}, {"step": 556, "kl": 0.03641649422548194, "ce": 0.9251337420835298}, {"step": 557, "kl": 0.04019121364926017, "ce": 0.8423047475126749}, {"step": 558, "kl": 0.04308047665348002, "ce": 0.7136849226570162}, {"step": 559, "kl": 0.03726206327063054, "ce": 0.8303646261701111}, {"step": 560, "kl": 0.058643793208747824, "ce": 0.7021344124908773}, {"step": 561, "kl": 0.049475345061399265, "ce": 0.7730962427314955}, {"step": 562, "kl": 0.037198634400670144, "ce": 0.7948573496687875}, {"step": 563, "kl": 0.05933712064145956, "ce": 0.7993952237642727}, {"step": 564, "kl": 0.04585509602816737, "ce": 0.8426715365716257}, {"step": 565, "kl": 0.04550977066168019, "ce": 0.6460777531530897}, {"step": 566, "kl": 0.03597037965419908, "ce": 0.7546978597438083}, {"step": 567, "kl": 0.04381062355563678, "ce": 0.8196900178500851}, {"step": 568, "kl": 0.03144069144524998, "ce": 0.8715565416625951}, {"step": 569, "kl": 0.04717671421986029, "ce": 0.7798195036331026}, {"step": 570, "kl": 0.07645915554484495, "ce": 0.8851622928042626}, {"step": 571, "kl": 0.034769925197257856, "ce": 0.6893841380407767}, {"step": 572, "kl": 0.039233709402186824, "ce": 0.8686968112651796}, {"step": 573, "kl": 0.04456268908159212, "ce": 0.8479925399292171}, {"step": 574, "kl": 0.03898283322421353, "ce": 0.8251460369695477}, {"step": 575, "kl": 0.04127345594586822, "ce": 0.8715187340809476}, {"step": 576, "kl": 0.03740439944525163, "ce": 0.8019246716459665}, {"step": 577, "kl": 0.0555568358604296, "ce": 0.7901718304814347}, {"step": 578, "kl": 0.041675183519520306, "ce": 0.7480730602098415}, {"step": 579, "kl": 0.057604490588049506, "ce": 0.7741405063686129}, {"step": 580, "kl": 0.06405211511747572, "ce": 0.7256523533119842}, {"step": 581, "kl": 0.05025242223376869, "ce": 0.9396038936301706}, {"step": 582, "kl": 0.042181135203740366, "ce": 0.7316439280695578}, {"step": 583, "kl": 0.06652784975412798, "ce": 0.7869692033988858}, {"step": 584, "kl": 0.048070023132702075, "ce": 0.747100552904034}, {"step": 585, "kl": 0.04854675502730911, "ce": 0.7341584967012214}, {"step": 586, "kl": 0.04035103946375186, "ce": 0.9977790876943438}, {"step": 587, "kl": 0.039235267231759526, "ce": 0.7440802462220343}, {"step": 588, "kl": 0.06221748773324207, "ce": 0.6971899632585126}, {"step": 589, "kl": 0.046222614542745406, "ce": 0.6624341950153044}, {"step": 590, "kl": 0.03189293037605523, "ce": 0.8407877500476754}, {"step": 591, "kl": 0.040638114685407206, "ce": 0.7485764108134613}, {"step": 592, "kl": 0.04204429479891765, "ce": 0.742092759212674}, {"step": 593, "kl": 0.042145077044908566, "ce": 0.7745326432314785}, {"step": 594, "kl": 0.045400399307175016, "ce": 0.7912965488293981}, {"step": 595, "kl": 0.06376001094517567, "ce": 0.7428208284307983}, {"step": 596, "kl": 0.047353655527824834, "ce": 0.8761772728039303}, {"step": 597, "kl": 0.049791807115266984, "ce": 0.8295257328155747}, {"step": 598, "kl": 0.04770140328609114, "ce": 0.8417796113403175}, {"step": 599, "kl": 0.04981531407103063, "ce": 0.8754521905244588}, {"step": 600, "kl": 0.03779930010812239, "ce": 0.7749241428357402}, {"step": 601, "kl": 0.04911251023607415, "ce": 0.8208830068662384}, {"step": 602, "kl": 0.03829074798718659, "ce": 0.6891410802006054}, {"step": 603, "kl": 0.03829810871313494, "ce": 0.8933423454862504}, {"step": 604, "kl": 0.03619654817730433, "ce": 0.7222070656054238}, {"step": 605, "kl": 0.04405700177986788, "ce": 0.8116088471212438}, {"step": 606, "kl": 0.061429791454171295, "ce": 0.9060035605461884}, {"step": 607, "kl": 0.039279156767819276, "ce": 0.8345508722788275}, {"step": 608, "kl": 0.04668612298634138, "ce": 0.8133909756079654}, {"step": 609, "kl": 0.035773049353696934, "ce": 0.808618921750293}, {"step": 610, "kl": 0.042954886857813825, "ce": 0.7951466651849307}, {"step": 611, "kl": 0.05497331040446799, "ce": 0.802639912118157}, {"step": 612, "kl": 0.05308527961367258, "ce": 0.9289623104605773}, {"step": 613, "kl": 0.0394538710727395, "ce": 0.8548887301201884}, {"step": 614, "kl": 0.03974308392502468, "ce": 0.7607894309348385}, {"step": 615, "kl": 0.04477694949168217, "ce": 0.8235135866116188}, {"step": 616, "kl": 0.04266261461935501, "ce": 0.729628817493697}, {"step": 617, "kl": 0.05075219771804668, "ce": 0.8924731636401607}, {"step": 618, "kl": 0.047460651588426786, "ce": 0.8846823566197795}, {"step": 619, "kl": 0.04053171715070378, "ce": 0.721714273912516}, {"step": 620, "kl": 0.07946995056387204, "ce": 0.7252883338548447}, {"step": 621, "kl": 0.0449440580515381, "ce": 0.7821667617094432}, {"step": 622, "kl": 0.045045427868580984, "ce": 0.890190326682964}, {"step": 623, "kl": 0.036573067576865785, "ce": 1.0008830520266672}, {"step": 624, "kl": 0.052890052528024825, "ce": 0.861515194912211}, {"step": 625, "kl": 0.039599143028678355, "ce": 0.8324538521144702}, {"step": 626, "kl": 0.0599262534954815, "ce": 0.7125595481998399}, {"step": 627, "kl": 0.040366135293689966, "ce": 0.7923828507242645}, {"step": 628, "kl": 0.06014337972086286, "ce": 0.848928516349126}, {"step": 629, "kl": 0.04577542490986519, "ce": 0.8101671306850982}, {"step": 630, "kl": 0.044643313462065334, "ce": 0.7465162916856118}, {"step": 631, "kl": 0.0585822720281345, "ce": 0.8757049611815381}, {"step": 632, "kl": 0.03449260560996338, "ce": 0.7967528305090443}, {"step": 633, "kl": 0.052378811554892706, "ce": 0.9395028899561806}, {"step": 634, "kl": 0.04834370201653377, "ce": 0.9089395147685957}, {"step": 635, "kl": 0.04977445410240807, "ce": 0.8942912377089433}, {"step": 636, "kl": 0.05590485450420356, "ce": 0.8074464195342491}, {"step": 637, "kl": 0.05066341161727905, "ce": 0.9046870169635342}, {"step": 638, "kl": 0.044146078417662465, "ce": 0.8155165059581949}, {"step": 639, "kl": 0.03524130952326114, "ce": 0.8138125516463065}, {"step": 640, "kl": 0.04615417200460747, "ce": 0.8374882699104396}, {"step": 641, "kl": 0.04717077861966671, "ce": 0.8430934492827064}, {"step": 642, "kl": 0.052143104791540364, "ce": 0.9768110220289548}, {"step": 643, "kl": 0.10103835547947909, "ce": 0.723702313936428}, {"step": 644, "kl": 0.049427312556930045, "ce": 0.7438605557251939}, {"step": 645, "kl": 0.038983941895368045, "ce": 0.746303368877891}, {"step": 646, "kl": 0.03040791764666821, "ce": 0.8601825323223623}, {"step": 647, "kl": 0.038811839905338014, "ce": 0.8204985446014669}, {"step": 648, "kl": 0.0405845138710886, "ce": 0.8208838671339028}, {"step": 649, "kl": 0.0479250042093282, "ce": 0.7764905627020473}, {"step": 650, "kl": 0.05141086147038105, "ce": 0.8348460145209246}, {"step": 651, "kl": 0.04425702778395885, "ce": 0.7896164165070177}, {"step": 652, "kl": 0.03929068451230996, "ce": 0.739436917005637}, {"step": 653, "kl": 0.03476281720613999, "ce": 0.822324621343167}, {"step": 654, "kl": 0.041227596040769594, "ce": 0.8544173830654955}, {"step": 655, "kl": 0.032436029314482306, "ce": 0.7631974508531407}, {"step": 656, "kl": 0.03782932423194981, "ce": 0.7859867722099462}, {"step": 657, "kl": 0.03726481657810022, "ce": 0.7886153151052067}, {"step": 658, "kl": 0.05551867169880705, "ce": 0.7313789216098405}, {"step": 659, "kl": 0.04251224874158378, "ce": 0.6688676762138527}, {"step": 660, "kl": 0.04037272600108472, "ce": 0.8338332658038105}, {"step": 661, "kl": 0.06492162259102516, "ce": 0.9741466596761581}, {"step": 662, "kl": 0.039331441721552604, "ce": 0.7861101999345207}, {"step": 663, "kl": 0.04145662355318854, "ce": 0.727165126833186}, {"step": 664, "kl": 0.03728127465948184, "ce": 0.7613070672709449}, {"step": 665, "kl": 0.06093467334926769, "ce": 0.8178240322870463}, {"step": 666, "kl": 0.04452168075440439, "ce": 0.9159214063902323}, {"step": 667, "kl": 0.04319365210470192, "ce": 0.8039241376492718}, {"step": 668, "kl": 0.044872239572756635, "ce": 0.7778207453506253}, {"step": 669, "kl": 0.04762977479994428, "ce": 0.8395991288311149}, {"step": 670, "kl": 0.0439814985345263, "ce": 0.8390422294406044}, {"step": 671, "kl": 0.05946522924926254, "ce": 0.7786293141050726}, {"step": 672, "kl": 0.03688363923270246, "ce": 0.7647015517692217}, {"step": 673, "kl": 0.040158609414435525, "ce": 0.8244688629690673}, {"step": 674, "kl": 0.03646135176722818, "ce": 0.7699022417303105}, {"step": 675, "kl": 0.04012570241608818, "ce": 0.7852140149756341}, {"step": 676, "kl": 0.047351673793915465, "ce": 0.6800572684480196}, {"step": 677, "kl": 0.04656208941720063, "ce": 0.6936669455207809}, {"step": 678, "kl": 0.04434823850927349, "ce": 0.6933677888524976}, {"step": 679, "kl": 0.04343096975657412, "ce": 0.7918325312219133}, {"step": 680, "kl": 0.05427413676807091, "ce": 0.9874036099122545}, {"step": 681, "kl": 0.041643874631322686, "ce": 0.7862634304323325}, {"step": 682, "kl": 0.05018082181238594, "ce": 0.7615216930326985}, {"step": 683, "kl": 0.04497550820344969, "ce": 0.814049801946913}, {"step": 684, "kl": 0.05128535214453871, "ce": 0.851117258538817}, {"step": 685, "kl": 0.035485210943401055, "ce": 0.840123350646934}, {"step": 686, "kl": 0.038191989013711486, "ce": 0.7661673943935297}, {"step": 687, "kl": 0.041213012950448664, "ce": 0.836126703860942}, {"step": 688, "kl": 0.04473458048027133, "ce": 0.7554603331179955}, {"step": 689, "kl": 0.04552471803089868, "ce": 0.9510551540141137}, {"step": 690, "kl": 0.05158998487938441, "ce": 0.9284285338659249}, {"step": 691, "kl": 0.0486974172081328, "ce": 0.8605057811009065}, {"step": 692, "kl": 0.04697280845917273, "ce": 0.7769278486967564}, {"step": 693, "kl": 0.062408530783339924, "ce": 0.6303822509113278}, {"step": 694, "kl": 0.05021617328281271, "ce": 0.7804166087575765}, {"step": 695, "kl": 0.0447241431957364, "ce": 0.7423565712968432}, {"step": 696, "kl": 0.04708684725797678, "ce": 0.7066102473117117}, {"step": 697, "kl": 0.044220963358585365, "ce": 0.9088266003545671}, {"step": 698, "kl": 0.04476824531205659, "ce": 0.8606442931039936}, {"step": 699, "kl": 0.05640029432098199, "ce": 0.9069745872288798}, {"step": 700, "kl": 0.04315597881363238, "ce": 0.7672337182884008}, {"step": 701, "kl": 0.04691040444253492, "ce": 0.9281376660762368}, {"step": 702, "kl": 0.04394590173425243, "ce": 0.8615202347155427}, {"step": 703, "kl": 0.03222748227417469, "ce": 0.9350641197817201}, {"step": 704, "kl": 0.044679402983518204, "ce": 0.783583402979926}, {"step": 705, "kl": 0.03897174007629008, "ce": 0.7354179359732387}, {"step": 706, "kl": 0.040585807666825714, "ce": 0.7468326063637107}, {"step": 707, "kl": 0.04173757823879924, "ce": 0.9843559583322774}, {"step": 708, "kl": 0.04323377516455279, "ce": 0.7421668195664407}, {"step": 709, "kl": 0.050718542025543975, "ce": 0.7159592581246387}, {"step": 710, "kl": 0.0375735491349072, "ce": 0.8132658591017594}, {"step": 711, "kl": 0.07603284398623314, "ce": 0.8077077775926421}, {"step": 712, "kl": 0.05923717562569488, "ce": 0.7232866830776392}, {"step": 713, "kl": 0.047545648836239886, "ce": 0.9131421896656748}, {"step": 714, "kl": 0.048078152024099416, "ce": 0.9185022998688365}, {"step": 715, "kl": 0.05482638127230309, "ce": 0.9289924636689744}, {"step": 716, "kl": 0.06461955799223969, "ce": 0.9510680416029931}, {"step": 717, "kl": 0.036474414565930216, "ce": 0.7022263146470399}, {"step": 718, "kl": 0.06411675617929308, "ce": 0.8572094158848846}, {"step": 719, "kl": 0.043198071287786424, "ce": 0.8671300065117329}, {"step": 720, "kl": 0.04623376165734003, "ce": 0.8704879650498991}, {"step": 721, "kl": 0.031101229999341676, "ce": 0.8313443714306532}, {"step": 722, "kl": 0.035109372777392574, "ce": 0.7189918003513918}, {"step": 723, "kl": 0.04065527085213805, "ce": 0.903540092514742}, {"step": 724, "kl": 0.04432779358433612, "ce": 0.9104168277630112}, {"step": 725, "kl": 0.07433302320947059, "ce": 0.7400047197323184}, {"step": 726, "kl": 0.04900051364197599, "ce": 0.7668456535655985}, {"step": 727, "kl": 0.0459297679674351, "ce": 0.7964234636699041}, {"step": 728, "kl": 0.04133663690047364, "ce": 0.650663789876302}, {"step": 729, "kl": 0.03241524254960576, "ce": 0.8938347610931842}, {"step": 730, "kl": 0.05569866479989088, "ce": 0.7159143552241886}, {"step": 731, "kl": 0.04747103337999279, "ce": 0.7249877357176755}, {"step": 732, "kl": 0.043275069003306466, "ce": 0.7821760733366567}, {"step": 733, "kl": 0.04455096060758052, "ce": 0.9535343078699366}, {"step": 734, "kl": 0.03429216088969894, "ce": 0.7307157218580392}, {"step": 735, "kl": 0.04572247914572031, "ce": 0.8969318364820877}, {"step": 736, "kl": 0.047427487308472044, "ce": 0.7233764073452914}, {"step": 737, "kl": 0.03858535965424123, "ce": 0.7425144986758863}, {"step": 738, "kl": 0.0416287370874703, "ce": 0.8814870945651383}, {"step": 739, "kl": 0.041588349845864944, "ce": 0.7737681520694626}, {"step": 740, "kl": 0.047831066672205685, "ce": 0.8544367366345478}, {"step": 741, "kl": 0.06165452082863659, "ce": 0.9180113055428484}, {"step": 742, "kl": 0.039731078751028465, "ce": 0.7838985626190813}, {"step": 743, "kl": 0.04529213208661889, "ce": 0.7266443195493202}, {"step": 744, "kl": 0.044813589948163646, "ce": 0.7973083715666311}, {"step": 745, "kl": 0.04254828512180001, "ce": 0.8374010942170719}, {"step": 746, "kl": 0.0496243638882833, "ce": 0.7047922314462152}, {"step": 747, "kl": 0.037653642139621094, "ce": 0.8884842808085277}, {"step": 748, "kl": 0.04520060804306948, "ce": 0.7831965682928131}, {"step": 749, "kl": 0.04387995520904137, "ce": 0.9190253922700311}, {"step": 750, "kl": 0.039754094150990946, "ce": 0.7942852070615691}, {"step": 751, "kl": 0.04453697685305638, "ce": 0.7530704579127183}, {"step": 752, "kl": 0.04824979770426602, "ce": 0.8978394131584099}, {"step": 753, "kl": 0.039801216002473216, "ce": 0.8644730675232359}, {"step": 754, "kl": 0.05176171438186444, "ce": 0.8671857754266612}, {"step": 755, "kl": 0.04086700637523945, "ce": 0.8823595249906498}, {"step": 756, "kl": 0.052697558408118635, "ce": 0.8408068016722406}, {"step": 757, "kl": 0.05062609628815704, "ce": 0.7089374742283744}, {"step": 758, "kl": 0.0371487178493877, "ce": 0.9133230059218466}, {"step": 759, "kl": 0.03363809964170399, "ce": 0.7438585964453674}, {"step": 760, "kl": 0.03957992795766163, "ce": 0.8081604183858274}, {"step": 761, "kl": 0.031375135083661035, "ce": 0.7975334470854963}, {"step": 762, "kl": 0.031081979888820548, "ce": 0.7465814875101218}, {"step": 763, "kl": 0.042726720935178694, "ce": 0.809384970522261}, {"step": 764, "kl": 0.03411603431682602, "ce": 0.6971073985021176}, {"step": 765, "kl": 0.03362271311581016, "ce": 0.9395660971063208}, {"step": 766, "kl": 0.037650202971751, "ce": 0.8291485009027494}, {"step": 767, "kl": 0.050141246646795395, "ce": 0.8765907016057782}, {"step": 768, "kl": 0.051758295089312525, "ce": 0.8656529789763654}, {"step": 769, "kl": 0.03468913085018871, "ce": 0.7433903048419481}, {"step": 770, "kl": 0.04515747633322488, "ce": 0.801512801833128}, {"step": 771, "kl": 0.04920141336304131, "ce": 0.7621987208495411}, {"step": 772, "kl": 0.03952279261576193, "ce": 0.823809706331965}, {"step": 773, "kl": 0.04310224050081279, "ce": 0.8444259823161723}, {"step": 774, "kl": 0.042882561168651176, "ce": 0.6695156064545676}, {"step": 775, "kl": 0.03785128757157807, "ce": 0.7061012255975448}, {"step": 776, "kl": 0.047482817896296464, "ce": 0.8455056658777458}, {"step": 777, "kl": 0.05695762386050266, "ce": 0.673509711581938}, {"step": 778, "kl": 0.04111306822978371, "ce": 0.9193254999183664}, {"step": 779, "kl": 0.02907356945445191, "ce": 0.8193342960743575}, {"step": 780, "kl": 0.046475162077320976, "ce": 0.8414992099627059}, {"step": 781, "kl": 0.03757732809518356, "ce": 0.8272892790261407}, {"step": 782, "kl": 0.05146112768586472, "ce": 0.9712490452830815}, {"step": 783, "kl": 0.04069870164068307, "ce": 0.7835151175166783}, {"step": 784, "kl": 0.043500464017725886, "ce": 0.8095144058374503}, {"step": 785, "kl": 0.05708077780069459, "ce": 0.84907871353082}, {"step": 786, "kl": 0.041814121675726505, "ce": 0.8783255940272081}, {"step": 787, "kl": 0.06658823329389434, "ce": 0.9959936854916911}, {"step": 788, "kl": 0.046812753602994875, "ce": 0.7949585240092086}, {"step": 789, "kl": 0.04962333217115183, "ce": 0.8573662817788247}, {"step": 790, "kl": 0.053002691175907654, "ce": 0.8008971831959145}, {"step": 791, "kl": 0.04675119027581607, "ce": 1.00431086481489}, {"step": 792, "kl": 0.03758966851073685, "ce": 0.717115508106}, {"step": 793, "kl": 0.05053526213710204, "ce": 0.7905444863776326}, {"step": 794, "kl": 0.03081336700437126, "ce": 0.7215486161755447}, {"step": 795, "kl": 0.04363705022151091, "ce": 0.8265797832224628}, {"step": 796, "kl": 0.05711698778448936, "ce": 0.8111745734217037}, {"step": 797, "kl": 0.03411556521049365, "ce": 0.7726909688257351}, {"step": 798, "kl": 0.04139946474030457, "ce": 0.7958279018474593}, {"step": 799, "kl": 0.0354705775230857, "ce": 0.8448394924986596}, {"step": 800, "kl": 0.032296077322667115, "ce": 0.8254290391624225}, {"step": 801, "kl": 0.05193667687299626, "ce": 0.8659924212343344}, {"step": 802, "kl": 0.04125621494104666, "ce": 0.8302105015116829}, {"step": 803, "kl": 0.049998664122987875, "ce": 0.8629809112890188}, {"step": 804, "kl": 0.06870896714269292, "ce": 0.8937314497492137}, {"step": 805, "kl": 0.03295067417311713, "ce": 0.7158050753333768}, {"step": 806, "kl": 0.05447953987465662, "ce": 0.8964080640546042}, {"step": 807, "kl": 0.04075798554569238, "ce": 0.8716905693649974}, {"step": 808, "kl": 0.04567317984735062, "ce": 0.8278490314411907}, {"step": 809, "kl": 0.062447734914402524, "ce": 0.9084187580060354}, {"step": 810, "kl": 0.043286125688653705, "ce": 0.8836813147495153}, {"step": 811, "kl": 0.050821944468582896, "ce": 0.7226575551261417}, {"step": 812, "kl": 0.043905757021612084, "ce": 0.840737402873202}, {"step": 813, "kl": 0.034926977399821695, "ce": 0.6274502575926089}, {"step": 814, "kl": 0.04161070840071694, "ce": 0.7318625788163635}, {"step": 815, "kl": 0.03426494784262227, "ce": 0.7983847828416767}, {"step": 816, "kl": 0.033204961433892864, "ce": 0.6583851481182538}, {"step": 817, "kl": 0.04209755599229944, "ce": 0.6330258960338205}, {"step": 818, "kl": 0.03984371016949802, "ce": 0.7609830776850381}, {"step": 819, "kl": 0.053224305367042216, "ce": 0.7737367796115873}, {"step": 820, "kl": 0.04317579520614327, "ce": 0.7449961283838471}, {"step": 821, "kl": 0.03649337004876833, "ce": 0.7870300690624032}, {"step": 822, "kl": 0.04096634426109502, "ce": 0.8468553612631852}, {"step": 823, "kl": 0.03932482974229729, "ce": 0.7671045222038118}, {"step": 824, "kl": 0.03794527619582906, "ce": 0.8388937567122221}, {"step": 825, "kl": 0.06597889264123437, "ce": 0.8615762848959361}, {"step": 826, "kl": 0.03748901694534365, "ce": 0.79986181198715}, {"step": 827, "kl": 0.04264199968719589, "ce": 0.8379330648481247}, {"step": 828, "kl": 0.0519737639215165, "ce": 0.8351777206819496}, {"step": 829, "kl": 0.037843628134128546, "ce": 0.8556863268175527}, {"step": 830, "kl": 0.04540259149840375, "ce": 0.9510165644085303}, {"step": 831, "kl": 0.048508849461923784, "ce": 0.8216603279113769}, {"step": 832, "kl": 0.04272793362956827, "ce": 0.7699093673984809}, {"step": 833, "kl": 0.036889592399426824, "ce": 0.8410114751797971}, {"step": 834, "kl": 0.04375401643092233, "ce": 0.8178513502900335}, {"step": 835, "kl": 0.04317261998028954, "ce": 0.7290647690577076}, {"step": 836, "kl": 0.039176808040270086, "ce": 0.9406551610153567}, {"step": 837, "kl": 0.04101685254968975, "ce": 0.6048724666522566}, {"step": 838, "kl": 0.04668192865965937, "ce": 0.9295197454549498}, {"step": 839, "kl": 0.10103933609861279, "ce": 0.9096296635309454}, {"step": 840, "kl": 0.04071413468346812, "ce": 0.9674778206314973}, {"step": 841, "kl": 0.030941468009753545, "ce": 0.8419648039915442}, {"step": 842, "kl": 0.17847523486723074, "ce": 1.0479068267830491}, {"step": 843, "kl": 0.05839866645603061, "ce": 0.8890521003460061}, {"step": 844, "kl": 0.046743348678965804, "ce": 0.869752385066106}, {"step": 845, "kl": 0.04382247716396838, "ce": 0.9135256508728573}, {"step": 846, "kl": 0.04361910133025128, "ce": 0.7416353615558664}, {"step": 847, "kl": 0.040301761537847786, "ce": 0.7831505148327303}, {"step": 848, "kl": 0.04751123000586419, "ce": 0.9429526155645197}, {"step": 849, "kl": 0.06071671283680694, "ce": 0.8024605254423781}, {"step": 850, "kl": 0.04668915356283595, "ce": 0.8095065988592911}, {"step": 851, "kl": 0.04723562717020099, "ce": 0.8491016394096447}, {"step": 852, "kl": 0.034840111802442564, "ce": 0.834144993612972}, {"step": 853, "kl": 0.04201881780668541, "ce": 0.7164351658089451}, {"step": 854, "kl": 0.04423530170720298, "ce": 0.9091433438895344}, {"step": 855, "kl": 0.055818930893916555, "ce": 0.7183547523067201}, {"step": 856, "kl": 0.06188295723949361, "ce": 0.751342816179206}, {"step": 857, "kl": 0.04567202331281319, "ce": 0.825963009041291}, {"step": 858, "kl": 0.0357143800082966, "ce": 0.7488571358212028}, {"step": 859, "kl": 0.033581190018554766, "ce": 0.8329288144654866}, {"step": 860, "kl": 0.039973128363061945, "ce": 0.8452784242793924}, {"step": 861, "kl": 0.039474580922516905, "ce": 0.6723031995664013}, {"step": 862, "kl": 0.04506119271126764, "ce": 0.7875926695169981}, {"step": 863, "kl": 0.03807524281657672, "ce": 0.737377305097193}, {"step": 864, "kl": 0.03347219232858009, "ce": 0.688922431645511}, {"step": 865, "kl": 0.04166394938254264, "ce": 0.8715483194610452}, {"step": 866, "kl": 0.05221182092758839, "ce": 0.7943596980969512}, {"step": 867, "kl": 0.035817924670749, "ce": 0.8956758751059479}, {"step": 868, "kl": 0.04676594460845753, "ce": 0.838846655019015}, {"step": 869, "kl": 0.03830618548711449, "ce": 0.7087632674065188}, {"step": 870, "kl": 0.05490019422343249, "ce": 0.7309504113523349}, {"step": 871, "kl": 0.041356220965059184, "ce": 0.8413180376535438}, {"step": 872, "kl": 0.04017700330064452, "ce": 0.9908874193019798}, {"step": 873, "kl": 0.04616375974655009, "ce": 0.7630806764580568}, {"step": 874, "kl": 0.05275107294421418, "ce": 0.8833316940241247}, {"step": 875, "kl": 0.04283524368418896, "ce": 0.6669486673790441}, {"step": 876, "kl": 0.038757691262638734, "ce": 0.7969018583858083}, {"step": 877, "kl": 0.044918953297511305, "ce": 0.7848466338852266}, {"step": 878, "kl": 0.05439586237375102, "ce": 0.7561181827421051}, {"step": 879, "kl": 0.05134922871075626, "ce": 0.7676595908453763}, {"step": 880, "kl": 0.041201087293319935, "ce": 0.7469557213970995}, {"step": 881, "kl": 0.048640330876583336, "ce": 0.7737127372126502}, {"step": 882, "kl": 0.03526863176414153, "ce": 0.800620976250017}, {"step": 883, "kl": 0.04957616250808419, "ce": 0.7466945216264674}, {"step": 884, "kl": 0.05107055635378894, "ce": 0.8605333016731678}, {"step": 885, "kl": 0.03782497080825589, "ce": 0.9033692344093921}, {"step": 886, "kl": 0.050299029970834325, "ce": 0.9379260641991057}, {"step": 887, "kl": 0.04053969940761768, "ce": 1.0200602013624565}, {"step": 888, "kl": 0.043152930397247685, "ce": 0.6770081637234803}, {"step": 889, "kl": 0.04168946232139125, "ce": 0.8165373450768842}, {"step": 890, "kl": 0.05919788679245212, "ce": 0.6828994273467908}, {"step": 891, "kl": 0.052145704818840725, "ce": 0.8225742925563909}, {"step": 892, "kl": 0.037744556540154295, "ce": 0.897791071002986}, {"step": 893, "kl": 0.04263205742076906, "ce": 0.8593158674147213}, {"step": 894, "kl": 0.04096026107002496, "ce": 0.8576331197019793}, {"step": 895, "kl": 0.0386553846410974, "ce": 0.7432841028084093}, {"step": 896, "kl": 0.05220698504704962, "ce": 0.7028786166133529}], "val": [{"step": 0, "math_kl": 0.16069652883738267, "math_ce": 0.6128856295790037, "code_kl": 0.07813702286999027, "code_ce": 0.3094309619594328, "math_hard_kl": 0.2467836188890191, "math_hard_ce": 0.6738775405183716}, {"step": 448, "math_kl": 0.07856080564162193, "math_ce": 0.8005119775060042, "code_kl": 0.1007884762093319, "code_ce": 0.3161948721421794, "math_hard_kl": 0.09167742512758625, "math_hard_ce": 0.7957679612038403}, {"step": 896, "math_kl": 0.07573669431537612, "math_ce": 0.8391097003532377, "code_kl": 0.10414732518681599, "code_ce": 0.3212356887956559, "math_hard_kl": 0.08597009330105414, "math_hard_ce": 0.8206646253872792}]}
seq_code_math_kd_only_seed1/stage2_math/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa7603d946a42a8a194c337e3fec5a2e1131c97e23b0ea0ced2146f4d27f4b9
3
+ size 3087467144