jajamken commited on
Commit
dfbca57
·
verified ·
1 Parent(s): d544e1b

remove kd results from the runs with the rope bf16 rounding bug

Browse files
Files changed (40) hide show
  1. abl_kl_only_math/results_stage1_math/gsm8k.jsonl +0 -0
  2. abl_kl_only_math/results_stage1_math/humaneval.jsonl +0 -0
  3. abl_kl_only_math/results_stage1_math/humaneval_eval_results.json +0 -0
  4. abl_kl_only_math/results_stage1_math/mbpp.jsonl +0 -0
  5. abl_kl_only_math/results_stage1_math/mbpp_eval_results.json +0 -0
  6. abl_kl_only_math/results_stage1_math/summary.json +0 -1
  7. abl_kl_only_math/stage1_math/config.json +0 -57
  8. abl_kl_only_math/stage1_math/generation_config.json +0 -14
  9. abl_kl_only_math/stage1_math/log.json +0 -1
  10. abl_kl_only_math/stage1_math/model.safetensors +0 -3
  11. seq_code_math/results_stage1_code/gsm8k.jsonl +0 -0
  12. seq_code_math/results_stage1_code/humaneval.jsonl +0 -0
  13. seq_code_math/results_stage1_code/humaneval_eval_results.json +0 -0
  14. seq_code_math/results_stage1_code/mbpp.jsonl +0 -0
  15. seq_code_math/results_stage1_code/mbpp_eval_results.json +0 -0
  16. seq_code_math/results_stage1_code/summary.json +0 -1
  17. seq_code_math/stage1_code/config.json +0 -57
  18. seq_code_math/stage1_code/generation_config.json +0 -14
  19. seq_code_math/stage1_code/log.json +0 -1
  20. seq_code_math/stage1_code/model.safetensors +0 -3
  21. seq_math_code/results_stage1_math/gsm8k.jsonl +0 -0
  22. seq_math_code/results_stage1_math/humaneval.jsonl +0 -0
  23. seq_math_code/results_stage1_math/humaneval_eval_results.json +0 -0
  24. seq_math_code/results_stage1_math/mbpp.jsonl +0 -0
  25. seq_math_code/results_stage1_math/mbpp_eval_results.json +0 -0
  26. seq_math_code/results_stage1_math/summary.json +0 -1
  27. seq_math_code/results_stage2_code/gsm8k.jsonl +0 -0
  28. seq_math_code/results_stage2_code/humaneval.jsonl +0 -0
  29. seq_math_code/results_stage2_code/humaneval_eval_results.json +0 -0
  30. seq_math_code/results_stage2_code/mbpp.jsonl +0 -0
  31. seq_math_code/results_stage2_code/mbpp_eval_results.json +0 -0
  32. seq_math_code/results_stage2_code/summary.json +0 -1
  33. seq_math_code/stage1_math/config.json +0 -57
  34. seq_math_code/stage1_math/generation_config.json +0 -14
  35. seq_math_code/stage1_math/log.json +0 -1
  36. seq_math_code/stage1_math/model.safetensors +0 -3
  37. seq_math_code/stage2_code/config.json +0 -57
  38. seq_math_code/stage2_code/generation_config.json +0 -14
  39. seq_math_code/stage2_code/log.json +0 -1
  40. seq_math_code/stage2_code/model.safetensors +0 -3
abl_kl_only_math/results_stage1_math/gsm8k.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_math/results_stage1_math/humaneval.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_math/results_stage1_math/humaneval_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_math/results_stage1_math/mbpp.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_math/results_stage1_math/mbpp_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_math/results_stage1_math/summary.json DELETED
@@ -1 +0,0 @@
1
- {"model": "stage1_math", "gsm8k": 0.510235026535254, "mbpp": 0.48677248677248675, "mbpp_plus": 0.42063492063492064, "humaneval": 0.34146341463414637, "humaneval_plus": 0.2804878048780488, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
 
 
abl_kl_only_math/stage1_math/config.json DELETED
@@ -1,57 +0,0 @@
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": 896,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 4864,
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
- ],
39
- "max_position_embeddings": 32768,
40
- "max_window_layers": 21,
41
- "model_type": "qwen2",
42
- "num_attention_heads": 14,
43
- "num_hidden_layers": 24,
44
- "num_key_value_heads": 2,
45
- "pad_token_id": null,
46
- "rms_norm_eps": 1e-06,
47
- "rope_parameters": {
48
- "rope_theta": 1000000.0,
49
- "rope_type": "default"
50
- },
51
- "sliding_window": null,
52
- "tie_word_embeddings": true,
53
- "transformers_version": "5.20.2",
54
- "use_cache": true,
55
- "use_sliding_window": false,
56
- "vocab_size": 151936
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
abl_kl_only_math/stage1_math/generation_config.json DELETED
@@ -1,14 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
abl_kl_only_math/stage1_math/log.json DELETED
@@ -1 +0,0 @@
1
- {"train": [{"step": 1, "kl": 0.11493205343229973, "ce": 0.8080925811042935}, {"step": 2, "kl": 0.12443150206420578, "ce": 0.7568737392830607}, {"step": 3, "kl": 0.11685623066835289, "ce": 0.7540257561509593}, {"step": 4, "kl": 0.12856018306113842, "ce": 0.9040041084749153}, {"step": 5, "kl": 0.13524528931808363, "ce": 0.886436813126749}, {"step": 6, "kl": 0.12142585893876391, "ce": 0.8248355963563158}, {"step": 7, "kl": 0.11766777556886568, "ce": 0.8042514434531973}, {"step": 8, "kl": 0.10271241865203617, "ce": 0.7823621624436787}, {"step": 9, "kl": 0.1290002071095761, "ce": 0.7715848847708628}, {"step": 10, "kl": 0.10600208879882055, "ce": 0.7613049329995503}, {"step": 11, "kl": 0.10843208565098528, "ce": 0.7909986866349867}, {"step": 12, "kl": 0.11295883178710939, "ce": 0.8047459271998187}, {"step": 13, "kl": 0.14916728287731282, "ce": 0.7880463412497336}, {"step": 14, "kl": 0.12112490025170936, "ce": 0.7543999043738421}, {"step": 15, "kl": 0.107443009609291, "ce": 0.7894714485030061}, {"step": 16, "kl": 0.12405737472315534, "ce": 0.8590614529237346}, {"step": 17, "kl": 0.10001568712560324, "ce": 0.6873307275772095}, {"step": 18, "kl": 0.1554754781971276, "ce": 0.7518357602158033}, {"step": 19, "kl": 0.12217823734238588, "ce": 0.7688625641633992}, {"step": 20, "kl": 0.11991075842745903, "ce": 0.8580521836391715}, {"step": 21, "kl": 0.11603084449604345, "ce": 0.7869284322371614}, {"step": 22, "kl": 0.13211752692177742, "ce": 0.7334202190182968}, {"step": 23, "kl": 0.10974358735952756, "ce": 0.7388710316475844}, {"step": 24, "kl": 0.11542125735225336, "ce": 0.8566531980591735}, {"step": 25, "kl": 0.11501775792333781, "ce": 0.7695523908738422}, {"step": 26, "kl": 0.11556676785378014, "ce": 0.7674122952294412}, {"step": 27, "kl": 0.14489485988014328, "ce": 0.8482452088920631}, {"step": 28, "kl": 0.1180605010762213, "ce": 0.739914811774713}, {"step": 29, "kl": 0.10922275893721688, "ce": 0.794767747780018}, {"step": 30, "kl": 0.12143426826039072, "ce": 0.783046411431354}, {"step": 31, "kl": 0.1176143957474261, "ce": 0.7283749443432681}, {"step": 32, "kl": 0.1209934935698638, "ce": 0.8078572922296223}, {"step": 33, "kl": 0.0851864845676418, "ce": 0.799548375244557}, {"step": 34, "kl": 0.15108936391781908, "ce": 0.8127833275215878}, {"step": 35, "kl": 0.14259908901665636, "ce": 0.826702131576356}, {"step": 36, "kl": 0.10691626288585275, "ce": 0.801245869213645}, {"step": 37, "kl": 0.12624377697123035, "ce": 0.8125765841064084}, {"step": 38, "kl": 0.13242634445271165, "ce": 0.8419945938384654}, {"step": 39, "kl": 0.12110810509614145, "ce": 0.776636301042478}, {"step": 40, "kl": 0.11717485550594205, "ce": 0.7593770779048581}, {"step": 41, "kl": 0.1308915880859075, "ce": 0.8265830922728357}, {"step": 42, "kl": 0.13803971999431636, "ce": 0.8109883229072713}, {"step": 43, "kl": 0.11283840258800874, "ce": 0.6665538999769423}, {"step": 44, "kl": 0.11312345831856165, "ce": 0.7443112233463202}, {"step": 45, "kl": 0.11641000289086302, "ce": 0.740228186915401}, {"step": 46, "kl": 0.08475306909069337, "ce": 0.7877710994302869}, {"step": 47, "kl": 0.11248210003667146, "ce": 0.6948165557001824}, {"step": 48, "kl": 0.117935500139398, "ce": 0.7508952162515412}, {"step": 49, "kl": 0.10556809839643838, "ce": 0.7531330641824439}, {"step": 50, "kl": 0.14076074682766793, "ce": 0.8062575969484689}, {"step": 51, "kl": 0.12432832968558834, "ce": 0.8105435906884505}, {"step": 52, "kl": 0.11026884576595879, "ce": 0.7959038892531778}, {"step": 53, "kl": 0.10705416041712341, "ce": 0.8117904218655188}, {"step": 54, "kl": 0.11624425343244002, "ce": 0.7926042975663433}, {"step": 55, "kl": 0.11701742245178064, "ce": 0.8331191712055875}, {"step": 56, "kl": 0.10532210714302197, "ce": 0.7700038935175004}, {"step": 57, "kl": 0.11339066038570644, "ce": 0.7772358641184363}, {"step": 58, "kl": 0.20203996186209197, "ce": 0.7759798335997754}, {"step": 59, "kl": 0.1153253378409875, "ce": 0.6663750630837899}, {"step": 60, "kl": 0.10026488526749872, "ce": 0.7900844806341956}, {"step": 61, "kl": 0.11869993408228774, "ce": 0.7735568509783064}, {"step": 62, "kl": 0.11409701448789743, "ce": 0.6541183400335262}, {"step": 63, "kl": 0.10928827985567893, "ce": 0.8014926030797865}, {"step": 64, "kl": 0.11074339981775184, "ce": 0.8271979225633683}, {"step": 65, "kl": 0.11477535494606858, "ce": 0.8261565650755854}, {"step": 66, "kl": 0.123530961659162, "ce": 0.8451373578625944}, {"step": 67, "kl": 0.1306375432957593, "ce": 0.7969688942761926}, {"step": 68, "kl": 0.12906031593581785, "ce": 0.8247599607093312}, {"step": 69, "kl": 0.13211069140182136, "ce": 0.7535370565335006}, {"step": 70, "kl": 0.11786023814328038, "ce": 0.7645858998149533}, {"step": 71, "kl": 0.11568281072429124, "ce": 0.8570915002347045}, {"step": 72, "kl": 0.11146824701236815, "ce": 0.830160946877587}, {"step": 73, "kl": 0.13523615027425867, "ce": 0.8045763206024222}, {"step": 74, "kl": 0.11820924134784697, "ce": 0.7790030881881153}, {"step": 75, "kl": 0.1255611045583444, "ce": 0.7733923299739298}, {"step": 76, "kl": 0.09427772213785582, "ce": 0.6826047626268648}, {"step": 77, "kl": 0.13665978928916472, "ce": 0.8700013751723719}, {"step": 78, "kl": 0.10333352957289822, "ce": 0.7852428947720873}, {"step": 79, "kl": 0.1646314338040169, "ce": 0.7381112170014297}, {"step": 80, "kl": 0.14977505025585575, "ce": 0.7628514197643952}, {"step": 81, "kl": 0.119706633274488, "ce": 0.8444794850144732}, {"step": 82, "kl": 0.15081768248179186, "ce": 0.8230806993948749}, {"step": 83, "kl": 0.1260692882309564, "ce": 0.7405934615070486}, {"step": 84, "kl": 0.1273626391469139, "ce": 0.7670993882636223}, {"step": 85, "kl": 0.12517405912253782, "ce": 0.7685028310189089}, {"step": 86, "kl": 0.1305166396789358, "ce": 0.8081633551939533}, {"step": 87, "kl": 0.10863022580878823, "ce": 0.7795704046094398}, {"step": 88, "kl": 0.11695584678178648, "ce": 0.85549668927059}, {"step": 89, "kl": 0.10495057746545593, "ce": 0.7556581675506729}, {"step": 90, "kl": 0.13222541144785105, "ce": 0.8118730016125423}, {"step": 91, "kl": 0.13215714741841822, "ce": 0.8205212535235227}, {"step": 92, "kl": 0.11559573641281795, "ce": 0.7462489091937837}, {"step": 93, "kl": 0.084288764431999, "ce": 0.7482080382350078}, {"step": 94, "kl": 0.10588246875813194, "ce": 0.8150275720555599}, {"step": 95, "kl": 0.10549504035412446, "ce": 0.7929600381201232}, {"step": 96, "kl": 0.12303856726055154, "ce": 0.7955713269303757}, {"step": 97, "kl": 0.1175308346106114, "ce": 0.8148791032136926}, {"step": 98, "kl": 0.11397704803549169, "ce": 0.721755469437829}, {"step": 99, "kl": 0.12768088696206947, "ce": 0.8359176929694342}, {"step": 100, "kl": 0.10551698103476045, "ce": 0.8207080604673737}, {"step": 101, "kl": 0.1085693840998612, "ce": 0.8066733752979952}, {"step": 102, "kl": 0.10315470642460127, "ce": 0.7866209581163195}, {"step": 103, "kl": 0.10689803346366518, "ce": 0.7952502820425422}, {"step": 104, "kl": 0.10088044972065746, "ce": 0.8781204623863346}, {"step": 105, "kl": 0.1058811562665195, "ce": 0.8386364146797173}, {"step": 106, "kl": 0.14685638560367073, "ce": 0.8359796181392215}, {"step": 107, "kl": 0.10402939414619679, "ce": 0.7856716940588985}, {"step": 108, "kl": 0.11710326320557457, "ce": 0.8165940275574237}, {"step": 109, "kl": 0.10292958397008978, "ce": 0.8307131290736256}, {"step": 110, "kl": 0.10973047787494035, "ce": 0.7614739425783235}, {"step": 111, "kl": 0.12806730781177855, "ce": 0.7773539797286249}, {"step": 112, "kl": 0.12636754242463122, "ce": 0.8540711988592163}, {"step": 113, "kl": 0.10966515093173045, "ce": 0.7023008768990536}, {"step": 114, "kl": 0.09914868405890528, "ce": 0.7440625493252615}, {"step": 115, "kl": 0.11848359056249379, "ce": 0.7932369263386712}, {"step": 116, "kl": 0.11002338672008889, "ce": 0.8367848930211601}, {"step": 117, "kl": 0.11687970180087337, "ce": 0.8754917015097297}, {"step": 118, "kl": 0.1054106048654019, "ce": 0.8090883332103334}, {"step": 119, "kl": 0.127490819376767, "ce": 0.7868754465600125}, {"step": 120, "kl": 0.10756901075255196, "ce": 0.7743255072699653}, {"step": 121, "kl": 0.10380817296588668, "ce": 0.7306854831185311}, {"step": 122, "kl": 0.13586971617936824, "ce": 0.6748634330643798}, {"step": 123, "kl": 0.11494232952576525, "ce": 0.757648647636185}, {"step": 124, "kl": 0.12378130478251914, "ce": 0.8104013792936466}, {"step": 125, "kl": 0.12370930594718402, "ce": 0.9046808833759941}, {"step": 126, "kl": 0.1608305959279243, "ce": 0.8129655316730999}, {"step": 127, "kl": 0.13348548325387538, "ce": 0.8036459270403634}, {"step": 128, "kl": 0.10680510106492444, "ce": 0.8263267306512074}, {"step": 129, "kl": 0.10544916755090826, "ce": 0.7688282898720786}, {"step": 130, "kl": 0.10338839371527456, "ce": 0.6841702579322193}, {"step": 131, "kl": 0.107032789030109, "ce": 0.7946002226203669}, {"step": 132, "kl": 0.09257374517346147, "ce": 0.7544791665587925}, {"step": 133, "kl": 0.09905977769618883, "ce": 0.7296208992278833}, {"step": 134, "kl": 0.09609754534594406, "ce": 0.7572691413507353}, {"step": 135, "kl": 0.10427142264182987, "ce": 0.700342762684161}, {"step": 136, "kl": 0.14640129803080315, "ce": 0.8475993863112634}, {"step": 137, "kl": 0.10689397374977828, "ce": 0.8240841131223703}, {"step": 138, "kl": 0.10653938524650805, "ce": 0.8345313549540705}, {"step": 139, "kl": 0.11632372622773218, "ce": 0.8556495407922914}, {"step": 140, "kl": 0.10204254970040502, "ce": 0.8442913287414598}, {"step": 141, "kl": 0.0955013264626084, "ce": 0.8259711666066101}, {"step": 142, "kl": 0.127158256274732, "ce": 0.7813096475446881}, {"step": 143, "kl": 0.12102065317297056, "ce": 0.7952831169227501}, {"step": 144, "kl": 0.11639035818733459, "ce": 0.8401039068449276}, {"step": 145, "kl": 0.12801771845869342, "ce": 0.8144970225053414}, {"step": 146, "kl": 0.10049124544741528, "ce": 0.7830429219753943}, {"step": 147, "kl": 0.10939327849587656, "ce": 0.7067231898489551}, {"step": 148, "kl": 0.0903832228180678, "ce": 0.8339885618922308}, {"step": 149, "kl": 0.10640539531086535, "ce": 0.8123430958256176}, {"step": 150, "kl": 0.11139997786736379, "ce": 0.8002155584209097}, {"step": 151, "kl": 0.09881545886673647, "ce": 0.8448644131705011}, {"step": 152, "kl": 0.10334513391365344, "ce": 0.792010730571961}, {"step": 153, "kl": 0.17285241945173416, "ce": 0.805701976728807}, {"step": 154, "kl": 0.11238919981661993, "ce": 0.7389518843662926}, {"step": 155, "kl": 0.09254526098569234, "ce": 0.7350848096188757}, {"step": 156, "kl": 0.11048426758740049, "ce": 0.85203580409976}, {"step": 157, "kl": 0.11855809760816169, "ce": 0.8243450321816359}, {"step": 158, "kl": 0.09165282206065996, "ce": 0.8014256403996395}, {"step": 159, "kl": 0.09480006863640028, "ce": 0.7358747651516935}, {"step": 160, "kl": 0.12979014060302932, "ce": 0.8400329642505663}, {"step": 161, "kl": 0.11842357226854566, "ce": 0.8695639737732908}, {"step": 162, "kl": 0.11668591704311465, "ce": 0.8715902598116412}, {"step": 163, "kl": 0.13005658072056064, "ce": 0.713130038194705}, {"step": 164, "kl": 0.10515097904709501, "ce": 0.8496152491351359}, {"step": 165, "kl": 0.13026255279880264, "ce": 0.7854764218590132}, {"step": 166, "kl": 0.0882788410356512, "ce": 0.7851910949384096}, {"step": 167, "kl": 0.10664354838248385, "ce": 0.7052075058273288}, {"step": 168, "kl": 0.1305138344732707, "ce": 0.7796947356516486}, {"step": 169, "kl": 0.11438306850301215, "ce": 0.8918832255150987}, {"step": 170, "kl": 0.10922351962697403, "ce": 0.806459457770572}, {"step": 171, "kl": 0.11286201473570535, "ce": 0.7856865041860095}, {"step": 172, "kl": 0.10820445127779708, "ce": 0.7570057806077894}, {"step": 173, "kl": 0.11510489784309681, "ce": 0.8417423134282543}, {"step": 174, "kl": 0.11565438391080252, "ce": 0.8494821776119373}, {"step": 175, "kl": 0.10054074371375912, "ce": 0.800282129442303}, {"step": 176, "kl": 0.11663166504182021, "ce": 0.7950658118013386}, {"step": 177, "kl": 0.09894974597966177, "ce": 0.827878878615468}, {"step": 178, "kl": 0.08483897090059472, "ce": 0.7807833049635476}, {"step": 179, "kl": 0.10271393565259943, "ce": 0.8354167362384715}, {"step": 180, "kl": 0.12199377866292203, "ce": 0.7749237707861012}, {"step": 181, "kl": 0.10246361311677685, "ce": 0.7721246743679916}, {"step": 182, "kl": 0.09709539773095259, "ce": 0.7134605664663365}, {"step": 183, "kl": 0.12523803681683687, "ce": 0.7878546644314169}, {"step": 184, "kl": 0.11091238611031576, "ce": 0.8246093345538568}, {"step": 185, "kl": 0.10269410348229614, "ce": 0.7816142133001746}, {"step": 186, "kl": 0.11586187162819622, "ce": 0.7797493690668151}, {"step": 187, "kl": 0.09674482441890872, "ce": 0.7265849712506012}, {"step": 188, "kl": 0.10292450029489011, "ce": 0.8128177986121012}, {"step": 189, "kl": 0.10916591922072008, "ce": 0.8375600850807046}, {"step": 190, "kl": 0.12067336347802081, "ce": 0.8604232938874098}, {"step": 191, "kl": 0.10566211421682772, "ce": 0.8067910972370609}, {"step": 192, "kl": 0.13009902263374484, "ce": 0.9102622853787448}, {"step": 193, "kl": 0.10978503678646648, "ce": 0.7947310684644021}, {"step": 194, "kl": 0.11481162354227059, "ce": 0.741128581305588}, {"step": 195, "kl": 0.10643404516467433, "ce": 0.8092279443406492}, {"step": 196, "kl": 0.10283704691432548, "ce": 0.8723815708054193}, {"step": 197, "kl": 0.11168607524317553, "ce": 0.7493024689757419}, {"step": 198, "kl": 0.10338945132441464, "ce": 0.8095836392846137}, {"step": 199, "kl": 0.0886585790861674, "ce": 0.794862904365048}, {"step": 200, "kl": 0.07970701575481628, "ce": 0.8608032737138921}, {"step": 201, "kl": 0.11615424733525435, "ce": 0.80891681640625}, {"step": 202, "kl": 0.11984927782550356, "ce": 0.8738203699084892}, {"step": 203, "kl": 0.09206929545957604, "ce": 0.6906633324898486}, {"step": 204, "kl": 0.11454237012062438, "ce": 0.8395140671930392}, {"step": 205, "kl": 0.10308694414825409, "ce": 0.7695405936960371}, {"step": 206, "kl": 0.20237422608897043, "ce": 0.7773167328538398}, {"step": 207, "kl": 0.10654819761415989, "ce": 0.863947461498454}, {"step": 208, "kl": 0.1208721377253896, "ce": 0.845971182764104}, {"step": 209, "kl": 0.10279837288017767, "ce": 0.7700221433108951}, {"step": 210, "kl": 0.09824833020989392, "ce": 0.7824306624011413}, {"step": 211, "kl": 0.10372511301960477, "ce": 0.8442033726870103}, {"step": 212, "kl": 0.10848583812632495, "ce": 0.8198332677854112}, {"step": 213, "kl": 0.09509823222651273, "ce": 0.8032468190156012}, {"step": 214, "kl": 0.09502511181976177, "ce": 0.831723038780498}, {"step": 215, "kl": 0.11558055624775206, "ce": 0.8124102009065723}, {"step": 216, "kl": 0.10521010896185937, "ce": 0.7411667222283521}, {"step": 217, "kl": 0.12335350267960916, "ce": 0.7800847137323483}, {"step": 218, "kl": 0.10960454650845167, "ce": 0.8523416480752671}, {"step": 219, "kl": 0.10905687068010043, "ce": 0.8246673246016585}, {"step": 220, "kl": 0.11526058933635222, "ce": 0.8116857502178038}, {"step": 221, "kl": 0.11331216649818596, "ce": 0.6967746381877831}, {"step": 222, "kl": 0.106873617100552, "ce": 0.7198920870742664}, {"step": 223, "kl": 0.09711092624845738, "ce": 0.8084828914699459}, {"step": 224, "kl": 0.11162613509537338, "ce": 0.7837136134139009}, {"step": 225, "kl": 0.0933332173358744, "ce": 0.809263296871024}, {"step": 226, "kl": 0.10833675317896677, "ce": 0.8350427548227215}, {"step": 227, "kl": 0.0800844523387715, "ce": 0.8044228703720765}, {"step": 228, "kl": 0.07925860244398031, "ce": 0.816902942632407}, {"step": 229, "kl": 0.06034230924393621, "ce": 0.7620887860716938}, {"step": 230, "kl": 0.06435750333897419, "ce": 0.8874977111816406}, {"step": 231, "kl": 0.059508669759325415, "ce": 0.7826145252183876}, {"step": 232, "kl": 0.06718860650700946, "ce": 0.82494143626729}, {"step": 233, "kl": 0.06013327730519741, "ce": 0.7724363916763688}, {"step": 234, "kl": 0.08201403322654455, "ce": 0.8917786533182317}, {"step": 235, "kl": 0.046988594574436174, "ce": 0.8405525925739621}, {"step": 236, "kl": 0.04922765209020842, "ce": 0.7909035963368407}, {"step": 237, "kl": 0.0623055791684952, "ce": 0.7996449528959817}, {"step": 238, "kl": 0.058026085069318944, "ce": 0.7768670403994973}, {"step": 239, "kl": 0.06283235848157087, "ce": 0.8583121960158752}, {"step": 240, "kl": 0.06578605611997944, "ce": 0.850269564910718}, {"step": 241, "kl": 0.056273508391924354, "ce": 0.8482977082096921}, {"step": 242, "kl": 0.061895103291758374, "ce": 0.8213245669151124}, {"step": 243, "kl": 0.06189706110768957, "ce": 0.8438008626302083}, {"step": 244, "kl": 0.053345801184465025, "ce": 0.8552968852982015}, {"step": 245, "kl": 0.07004148531939983, "ce": 0.8192634821535651}, {"step": 246, "kl": 0.0690244959648545, "ce": 0.8464861082457994}, {"step": 247, "kl": 0.06136693494502492, "ce": 0.8048549444950281}, {"step": 248, "kl": 0.0743767006619798, "ce": 0.8109309001200378}, {"step": 249, "kl": 0.06174579470556099, "ce": 0.8198294107281758}, {"step": 250, "kl": 0.06940657357189142, "ce": 0.8046327481513992}, {"step": 251, "kl": 0.10374141977417761, "ce": 0.8200261141051356}, {"step": 252, "kl": 0.056945640865166014, "ce": 0.8248079063569435}, {"step": 253, "kl": 0.06321944499892058, "ce": 0.9507588218240178}, {"step": 254, "kl": 0.059581001190810376, "ce": 0.844735950957468}, {"step": 255, "kl": 0.07465106182129891, "ce": 0.8075158214096011}, {"step": 256, "kl": 0.05434692548193064, "ce": 0.804260531425775}, {"step": 257, "kl": 0.0650815420125556, "ce": 0.8471533811284995}, {"step": 258, "kl": 0.05580186860192795, "ce": 0.8187188036110239}, {"step": 259, "kl": 0.053776291873261634, "ce": 0.8169198895491109}, {"step": 260, "kl": 0.0912763708870506, "ce": 0.8450483640560433}, {"step": 261, "kl": 0.06465736041662241, "ce": 0.7787468228938196}, {"step": 262, "kl": 0.06382698074385029, "ce": 0.9007664733618236}, {"step": 263, "kl": 0.06015140663359556, "ce": 0.8814941612133692}, {"step": 264, "kl": 0.05863589125598588, "ce": 0.8383585426287521}, {"step": 265, "kl": 0.06098892860936547, "ce": 0.8325151425960663}, {"step": 266, "kl": 0.054403165728100784, "ce": 0.7624777569322639}, {"step": 267, "kl": 0.05831828087517397, "ce": 0.7643551546754395}, {"step": 268, "kl": 0.06578035194202408, "ce": 0.8719413782014817}, {"step": 269, "kl": 0.0507388401372367, "ce": 0.7266840984440651}, {"step": 270, "kl": 0.053780574441864425, "ce": 0.7808420668553262}, {"step": 271, "kl": 0.06851420567704554, "ce": 0.828304666130712}, {"step": 272, "kl": 0.05685836583838343, "ce": 0.8296478789986915}, {"step": 273, "kl": 0.052050484876081535, "ce": 0.8248942276654153}, {"step": 274, "kl": 0.05514381009147055, "ce": 0.8296349644472625}, {"step": 275, "kl": 0.06719287166208847, "ce": 0.8940537914374899}, {"step": 276, "kl": 0.057279589129906744, "ce": 0.804969969249907}, {"step": 277, "kl": 0.06326771738983022, "ce": 0.791633025736233}, {"step": 278, "kl": 0.07028059954245455, "ce": 0.8612886766924907}, {"step": 279, "kl": 0.05833443184026611, "ce": 0.7863402498981549}, {"step": 280, "kl": 0.05649058638569416, "ce": 0.8556798607159753}, {"step": 281, "kl": 0.06163006842536903, "ce": 0.8079882409349199}, {"step": 282, "kl": 0.0505837363621498, "ce": 0.8137266322210186}, {"step": 283, "kl": 0.054345109513108156, "ce": 0.7867850603217061}, {"step": 284, "kl": 0.07022048819152846, "ce": 0.9481120082919159}, {"step": 285, "kl": 0.05482570086520142, "ce": 0.8222524672124912}, {"step": 286, "kl": 0.05440120209027191, "ce": 0.780988258583615}, {"step": 287, "kl": 0.06474167769405582, "ce": 0.8393220257829057}, {"step": 288, "kl": 0.07411634294863215, "ce": 0.8708957092671454}, {"step": 289, "kl": 0.08460843195419192, "ce": 0.7725385672315604}, {"step": 290, "kl": 0.0555553868108201, "ce": 0.8225456168524796}, {"step": 291, "kl": 0.06034113306855951, "ce": 0.8500169612118081}, {"step": 292, "kl": 0.06926253875951185, "ce": 0.8200873165142992}, {"step": 293, "kl": 0.05595577354733545, "ce": 0.7520512551577831}, {"step": 294, "kl": 0.05987710282588539, "ce": 0.7842941011789749}, {"step": 295, "kl": 0.05429072093558461, "ce": 0.781734437159757}, {"step": 296, "kl": 0.06716309952465702, "ce": 0.8996236805500718}, {"step": 297, "kl": 0.06459839458985399, "ce": 0.8899907532531977}, {"step": 298, "kl": 0.06814828701932045, "ce": 0.8315974287895564}, {"step": 299, "kl": 0.05987943147940818, "ce": 0.8086853950352321}, {"step": 300, "kl": 0.05290167500653606, "ce": 0.8141552587619691}, {"step": 301, "kl": 0.07000890010438679, "ce": 0.8980215948309329}, {"step": 302, "kl": 0.05311308577822718, "ce": 0.8502733984375}, {"step": 303, "kl": 0.08064844592224293, "ce": 0.9069728648735467}, {"step": 304, "kl": 0.05710302414822371, "ce": 0.8620372676537367}, {"step": 305, "kl": 0.05605158047230846, "ce": 0.8919298183166525}, {"step": 306, "kl": 0.055429971279041645, "ce": 0.8617955049574288}, {"step": 307, "kl": 0.06656853512778801, "ce": 0.8368913836801393}, {"step": 308, "kl": 0.06730262063068979, "ce": 0.8604815809990125}, {"step": 309, "kl": 0.06504838971754133, "ce": 0.9415657020817878}, {"step": 310, "kl": 0.0699398209761096, "ce": 0.8683271832626623}, {"step": 311, "kl": 0.06737471597776568, "ce": 0.8407621142363259}, {"step": 312, "kl": 0.064160225089502, "ce": 0.8617488246750179}, {"step": 313, "kl": 0.06279930336346765, "ce": 0.8573333749925572}, {"step": 314, "kl": 0.05814971964082989, "ce": 0.8925047712006329}, {"step": 315, "kl": 0.05889532014245036, "ce": 0.9201305615334672}, {"step": 316, "kl": 0.056210696441107114, "ce": 0.9387959054836218}, {"step": 317, "kl": 0.08203812723323387, "ce": 0.957222430602364}, {"step": 318, "kl": 0.049549523555639276, "ce": 0.76718699463114}, {"step": 319, "kl": 0.04771512658221217, "ce": 0.8273434460689875}, {"step": 320, "kl": 0.05284465286616139, "ce": 0.8022890371985895}, {"step": 321, "kl": 0.06969379705336642, "ce": 0.7881945438950371}, {"step": 322, "kl": 0.06134554033434332, "ce": 0.8984409656023482}, {"step": 323, "kl": 0.06526990840980895, "ce": 0.7813617993621963}, {"step": 324, "kl": 0.06876269485188251, "ce": 0.8874451560220769}, {"step": 325, "kl": 0.06407353554231394, "ce": 0.8627774945303757}, {"step": 326, "kl": 0.06163799156412147, "ce": 0.8106862166280787}, {"step": 327, "kl": 0.05886365453172511, "ce": 0.780893602952533}, {"step": 328, "kl": 0.059306946656503136, "ce": 0.8661861166076447}, {"step": 329, "kl": 0.05843192756950081, "ce": 0.8709923734812461}, {"step": 330, "kl": 0.05705939010804664, "ce": 0.8439838084651622}, {"step": 331, "kl": 0.06363911877585525, "ce": 0.8210392850737331}, {"step": 332, "kl": 0.05995586912758383, "ce": 0.8159534977491356}, {"step": 333, "kl": 0.059505976163423985, "ce": 0.8626217227596623}, {"step": 334, "kl": 0.07387292889597571, "ce": 0.8192854792434976}, {"step": 335, "kl": 0.0628873543205805, "ce": 0.844999251827117}, {"step": 336, "kl": 0.05607178755434185, "ce": 0.9107044312820721}, {"step": 337, "kl": 0.05678482631195946, "ce": 0.8708001028269339}, {"step": 338, "kl": 0.05789515034847761, "ce": 0.7872023227960767}, {"step": 339, "kl": 0.05168875808051716, "ce": 0.8254893801753718}, {"step": 340, "kl": 0.06650148764288759, "ce": 0.8146013157968303}, {"step": 341, "kl": 0.0497086585197605, "ce": 0.7673868507352639}, {"step": 342, "kl": 0.05801678789552227, "ce": 0.8079437340454186}, {"step": 343, "kl": 0.0660498894898176, "ce": 0.8552726400824024}, {"step": 344, "kl": 0.06249654789718321, "ce": 0.8341729668803061}, {"step": 345, "kl": 0.05563322487628317, "ce": 0.8376595332704742}, {"step": 346, "kl": 0.055047537104874714, "ce": 0.8493685466487233}, {"step": 347, "kl": 0.061356267225765836, "ce": 0.8546849085073001}, {"step": 348, "kl": 0.06123562026076035, "ce": 0.8683481295930023}, {"step": 349, "kl": 0.05713281667612254, "ce": 0.7672401605859605}, {"step": 350, "kl": 0.05849394781828044, "ce": 0.825114740950338}, {"step": 351, "kl": 0.05680083737616244, "ce": 0.8417537758901833}, {"step": 352, "kl": 0.05580889981095962, "ce": 0.9016559793773327}, {"step": 353, "kl": 0.06011176648722515, "ce": 0.7960980414387695}, {"step": 354, "kl": 0.05616186282301622, "ce": 0.8146149589032728}, {"step": 355, "kl": 0.05211106507803129, "ce": 0.820563124573749}, {"step": 356, "kl": 0.06964680779613468, "ce": 0.8824550186345828}, {"step": 357, "kl": 0.047757773703239116, "ce": 0.6958223248572591}, {"step": 358, "kl": 0.06438314510668891, "ce": 0.9402976119834292}, {"step": 359, "kl": 0.06021167995335164, "ce": 0.8661172099040535}, {"step": 360, "kl": 0.05647208269904641, "ce": 0.844048528387995}, {"step": 361, "kl": 0.06448834915294747, "ce": 0.9233154413963719}, {"step": 362, "kl": 0.05228474597252244, "ce": 0.76127294921875}, {"step": 363, "kl": 0.054621388881197865, "ce": 0.8522985873941603}, {"step": 364, "kl": 0.05344358302144459, "ce": 0.8750205015012731}, {"step": 365, "kl": 0.0545808959608562, "ce": 0.9269163610295126}, {"step": 366, "kl": 0.06699194582031606, "ce": 0.77012720703125}, {"step": 367, "kl": 0.0610584184607495, "ce": 0.7754876671495685}, {"step": 368, "kl": 0.04770632078921554, "ce": 0.8229486861637489}, {"step": 369, "kl": 0.06538312127985106, "ce": 0.9428761752816134}, {"step": 370, "kl": 0.05097586980342458, "ce": 0.871971520606989}, {"step": 371, "kl": 0.05605547869934535, "ce": 0.860662650113082}, {"step": 372, "kl": 0.05202798033558695, "ce": 0.8210448531417159}, {"step": 373, "kl": 0.08378886349969691, "ce": 0.8188959958525044}, {"step": 374, "kl": 0.06029829161596152, "ce": 0.8047234214490062}, {"step": 375, "kl": 0.07021162640809891, "ce": 0.7966485945661748}, {"step": 376, "kl": 0.05437874677654151, "ce": 0.8073294265312836}, {"step": 377, "kl": 0.05952546745698905, "ce": 0.8127788108823377}, {"step": 378, "kl": 0.06408659550221839, "ce": 0.8879979943306984}, {"step": 379, "kl": 0.05855093904837115, "ce": 0.8978369907507292}, {"step": 380, "kl": 0.04545220949495278, "ce": 0.7469757281810186}, {"step": 381, "kl": 0.05789510216174266, "ce": 0.8904044411399149}, {"step": 382, "kl": 0.07369931151959479, "ce": 0.8720258852649503}, {"step": 383, "kl": 0.06599622065385166, "ce": 0.9168181979336804}, {"step": 384, "kl": 0.05463675630784279, "ce": 0.8281109005139405}, {"step": 385, "kl": 0.058288385655224276, "ce": 0.7915888187959901}, {"step": 386, "kl": 0.06529410985174611, "ce": 0.8243584999241089}, {"step": 387, "kl": 0.05296050153482448, "ce": 0.9186499817659797}, {"step": 388, "kl": 0.08599372637561069, "ce": 0.9254038699038393}, {"step": 389, "kl": 0.05339610045779798, "ce": 0.8648253868177045}, {"step": 390, "kl": 0.06707239377813509, "ce": 0.8246083340903585}, {"step": 391, "kl": 0.055795153388650466, "ce": 0.9029891567237084}, {"step": 392, "kl": 0.06211469910333471, "ce": 0.8789631503274393}, {"step": 393, "kl": 0.05171249756914086, "ce": 0.758839676798224}, {"step": 394, "kl": 0.05736284074481452, "ce": 0.81365870347479}, {"step": 395, "kl": 0.06187433200768133, "ce": 0.8669977292103062}, {"step": 396, "kl": 0.05860619127581251, "ce": 0.7855392859277208}, {"step": 397, "kl": 0.05560836784264653, "ce": 0.7723250527052009}, {"step": 398, "kl": 0.05680125466287771, "ce": 0.8293534202713579}, {"step": 399, "kl": 0.060329297622600635, "ce": 0.843365335101989}, {"step": 400, "kl": 0.05335615844254936, "ce": 0.7978431495174114}, {"step": 401, "kl": 0.05420761721105341, "ce": 0.8681684991343713}, {"step": 402, "kl": 0.05311471506272524, "ce": 0.7551258890388297}, {"step": 403, "kl": 0.057797521641866814, "ce": 0.8271946185144973}, {"step": 404, "kl": 0.055581833259918646, "ce": 0.84136099427142}, {"step": 405, "kl": 0.06424906480406085, "ce": 0.8624260418063752}, {"step": 406, "kl": 0.06412821434411223, "ce": 0.8575955405567444}, {"step": 407, "kl": 0.06110454255450992, "ce": 0.8169389370672717}, {"step": 408, "kl": 0.05368501489812678, "ce": 0.8242623330050839}, {"step": 409, "kl": 0.0494797767230066, "ce": 0.8489300601911134}, {"step": 410, "kl": 0.05612296412108103, "ce": 0.8324465097231211}, {"step": 411, "kl": 0.059612431950794624, "ce": 0.872041186135284}, {"step": 412, "kl": 0.047508131381062454, "ce": 0.7694899724247246}, {"step": 413, "kl": 0.06613591494450832, "ce": 0.9046480668736583}, {"step": 414, "kl": 0.05993899719856112, "ce": 0.8852489337372702}, {"step": 415, "kl": 0.05295548990347747, "ce": 0.7806700914369884}, {"step": 416, "kl": 0.060570532369064234, "ce": 0.8210757306102308}, {"step": 417, "kl": 0.05881825844905002, "ce": 0.7768988372586297}, {"step": 418, "kl": 0.04464857138677171, "ce": 0.8101247614585229}, {"step": 419, "kl": 0.05314488306461532, "ce": 0.8396862030029297}, {"step": 420, "kl": 0.061702669405351754, "ce": 0.7949316512163337}, {"step": 421, "kl": 0.06064262734106285, "ce": 0.77496639743258}, {"step": 422, "kl": 0.0558208359665849, "ce": 0.841988918748818}, {"step": 423, "kl": 0.06129149472536266, "ce": 0.8557896551911516}, {"step": 424, "kl": 0.05274618999823515, "ce": 0.8108393011908217}, {"step": 425, "kl": 0.0661064269088422, "ce": 0.8740270090016293}, {"step": 426, "kl": 0.06669510124388874, "ce": 0.8772944383218255}, {"step": 427, "kl": 0.0727576443952799, "ce": 0.9233248388040087}, {"step": 428, "kl": 0.05591526433299362, "ce": 0.8394120126580461}, {"step": 429, "kl": 0.05960276202196117, "ce": 0.776946161434945}, {"step": 430, "kl": 0.04660333218563414, "ce": 0.767997269391467}, {"step": 431, "kl": 0.06720538941783391, "ce": 0.8519800567626953}, {"step": 432, "kl": 0.0701307779813085, "ce": 0.8767722379524041}, {"step": 433, "kl": 0.056768902953790154, "ce": 0.8408610905420268}, {"step": 434, "kl": 0.05582737894934617, "ce": 0.8777926467873987}, {"step": 435, "kl": 0.05072760584591063, "ce": 0.889326557642977}, {"step": 436, "kl": 0.055586041967181185, "ce": 0.793383552468911}, {"step": 437, "kl": 0.058282449206072506, "ce": 0.8316347516924093}, {"step": 438, "kl": 0.05950858848418613, "ce": 0.9532057026503431}, {"step": 439, "kl": 0.05630254315900373, "ce": 0.8018807694242118}, {"step": 440, "kl": 0.04589613752577812, "ce": 0.907665002040374}, {"step": 441, "kl": 0.0579993676237333, "ce": 0.8351706561064897}, {"step": 442, "kl": 0.054294112044790475, "ce": 0.7489430605526752}, {"step": 443, "kl": 0.059155255205906476, "ce": 0.884183525755966}, {"step": 444, "kl": 0.04464853547139652, "ce": 0.7139297289909403}, {"step": 445, "kl": 0.06097656343041398, "ce": 0.8491600490285665}, {"step": 446, "kl": 0.07708016429439181, "ce": 0.834176601016697}, {"step": 447, "kl": 0.0782123665742951, "ce": 0.8753948157603346}, {"step": 448, "kl": 0.057084097501245955, "ce": 0.844701622908209}, {"step": 449, "kl": 0.05962344537331614, "ce": 0.9188560477783461}, {"step": 450, "kl": 0.05617888784572365, "ce": 0.9039366036370993}, {"step": 451, "kl": 0.06569209559986515, "ce": 0.8244912135641546}, {"step": 452, "kl": 0.05137835724634297, "ce": 0.7767323947659303}], "val": [{"step": 0, "math_kl": 0.17059537193969265, "math_ce": 0.8387106338797149, "code_kl": 0.22116874322487284, "code_ce": 0.36744983409730037}, {"step": 226, "math_kl": 0.12185130448928927, "math_ce": 0.8414972361566747, "code_kl": 0.24209495179121884, "code_ce": 0.3830698060414367}, {"step": 452, "math_kl": 0.11775552433611566, "math_ce": 0.8859353039222084, "code_kl": 0.2453931718649158, "code_ce": 0.38684329472481443}]}
 
 
abl_kl_only_math/stage1_math/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7924359a1d856f10b0680e4c324a83f2baddaca3c00cb15c1f7ae162788c7331
3
- size 988097824
 
 
 
 
seq_code_math/results_stage1_code/gsm8k.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_code_math/results_stage1_code/humaneval.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_code_math/results_stage1_code/humaneval_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
seq_code_math/results_stage1_code/mbpp.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_code_math/results_stage1_code/mbpp_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
seq_code_math/results_stage1_code/summary.json DELETED
@@ -1 +0,0 @@
1
- {"model": "stage1_code", "gsm8k": 0.45943896891584535, "mbpp": 0.5105820105820106, "mbpp_plus": 0.4365079365079365, "humaneval": 0.32926829268292684, "humaneval_plus": 0.3048780487804878, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
 
 
seq_code_math/stage1_code/config.json DELETED
@@ -1,57 +0,0 @@
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": 896,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 4864,
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
- ],
39
- "max_position_embeddings": 32768,
40
- "max_window_layers": 21,
41
- "model_type": "qwen2",
42
- "num_attention_heads": 14,
43
- "num_hidden_layers": 24,
44
- "num_key_value_heads": 2,
45
- "pad_token_id": null,
46
- "rms_norm_eps": 1e-06,
47
- "rope_parameters": {
48
- "rope_theta": 1000000.0,
49
- "rope_type": "default"
50
- },
51
- "sliding_window": null,
52
- "tie_word_embeddings": true,
53
- "transformers_version": "5.20.2",
54
- "use_cache": true,
55
- "use_sliding_window": false,
56
- "vocab_size": 151936
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seq_code_math/stage1_code/generation_config.json DELETED
@@ -1,14 +0,0 @@
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/stage1_code/log.json DELETED
@@ -1 +0,0 @@
1
- {"train": [{"step": 1, "kl": 0.21629283957570156, "ce": 0.38630337465738546}, {"step": 2, "kl": 0.24030088861941712, "ce": 0.41445943905082233}, {"step": 3, "kl": 0.20484516600230973, "ce": 0.3729742327447047}, {"step": 4, "kl": 0.2532756125163562, "ce": 0.3337403704430763}, {"step": 5, "kl": 0.2335743349545518, "ce": 0.396668016825037}, {"step": 6, "kl": 0.19522915543020034, "ce": 0.31597226637381093}, {"step": 7, "kl": 0.20646203872178415, "ce": 0.3179169204823836}, {"step": 8, "kl": 0.20180939185136276, "ce": 0.28543984353005347}, {"step": 9, "kl": 0.22810072218600994, "ce": 0.3270446956937169}, {"step": 10, "kl": 0.23985511161538864, "ce": 0.3513314029119126}, {"step": 11, "kl": 0.2231768621695044, "ce": 0.3050994973940527}, {"step": 12, "kl": 0.23231482720969945, "ce": 0.38428482302181366}, {"step": 13, "kl": 0.21437748637013998, "ce": 0.32936501594794027}, {"step": 14, "kl": 0.23352432389491348, "ce": 0.35785947402054696}, {"step": 15, "kl": 0.1985343484640579, "ce": 0.27636562817469595}, {"step": 16, "kl": 0.21746938249568123, "ce": 0.36893995815945657}, {"step": 17, "kl": 0.1887202163012982, "ce": 0.29814990966515276}, {"step": 18, "kl": 0.2306561159900231, "ce": 0.34748595439630386}, {"step": 19, "kl": 0.20587008685210392, "ce": 0.3296070439890118}, {"step": 20, "kl": 0.18376534881651377, "ce": 0.2612742239231358}, {"step": 21, "kl": 0.20701144167919033, "ce": 0.3566029622463749}, {"step": 22, "kl": 0.21956782136093117, "ce": 0.33505945549902133}, {"step": 23, "kl": 0.22985891743710168, "ce": 0.33853947234556436}, {"step": 24, "kl": 0.21721803697972664, "ce": 0.3164908974113872}, {"step": 25, "kl": 0.18890998136756743, "ce": 0.32242764536052837}, {"step": 26, "kl": 0.19577736373408394, "ce": 0.3020648626877648}, {"step": 27, "kl": 0.22583231303201112, "ce": 0.3212029245228919}, {"step": 28, "kl": 0.206690922739529, "ce": 0.3004675508769386}, {"step": 29, "kl": 0.16675343860841185, "ce": 0.2953803727542951}, {"step": 30, "kl": 0.19702829883285616, "ce": 0.33438686745058566}, {"step": 31, "kl": 0.19063365894389245, "ce": 0.3269322097133583}, {"step": 32, "kl": 0.18818771281475935, "ce": 0.2862056306845635}, {"step": 33, "kl": 0.17464566011063978, "ce": 0.2968676090953666}, {"step": 34, "kl": 0.217780565336259, "ce": 0.34600343697672176}, {"step": 35, "kl": 0.17801612616733115, "ce": 0.3230881767135377}, {"step": 36, "kl": 0.15959712932101686, "ce": 0.2731320955155884}, {"step": 37, "kl": 0.16782186403049257, "ce": 0.24821305182330813}, {"step": 38, "kl": 0.18227579505434008, "ce": 0.3011642346843314}, {"step": 39, "kl": 0.2113174220235588, "ce": 0.3412951910966138}, {"step": 40, "kl": 0.17656744284495435, "ce": 0.29496372301775714}, {"step": 41, "kl": 0.19310101549579556, "ce": 0.2928680110041892}, {"step": 42, "kl": 0.16188372714064275, "ce": 0.26943109926645537}, {"step": 43, "kl": 0.19410933063269226, "ce": 0.3729617659702874}, {"step": 44, "kl": 0.21866165883232214, "ce": 0.30715767222357593}, {"step": 45, "kl": 0.22890833338528976, "ce": 0.30963454650808014}, {"step": 46, "kl": 0.18912065671255215, "ce": 0.326179568462225}, {"step": 47, "kl": 0.1826942648819025, "ce": 0.27791804817196175}, {"step": 48, "kl": 0.19995055009344925, "ce": 0.32452866144676307}, {"step": 49, "kl": 0.19433055729809212, "ce": 0.29972052557771556}, {"step": 50, "kl": 0.1838536560535431, "ce": 0.3210752560721193}, {"step": 51, "kl": 0.17896040975750188, "ce": 0.26720747227007313}, {"step": 52, "kl": 0.19526536339274883, "ce": 0.29869937841314553}, {"step": 53, "kl": 0.17496054562370408, "ce": 0.2687588618631195}, {"step": 54, "kl": 0.20682052862168215, "ce": 0.3004736869944449}, {"step": 55, "kl": 0.19234756847164827, "ce": 0.28802015256748886}, {"step": 56, "kl": 0.18338030744835504, "ce": 0.2883601624882936}, {"step": 57, "kl": 0.17850525393101058, "ce": 0.24043777708023312}, {"step": 58, "kl": 0.1468619994702045, "ce": 0.25135637759240037}, {"step": 59, "kl": 0.21787859241083338, "ce": 0.3849340480813771}, {"step": 60, "kl": 0.17386059214311, "ce": 0.27274650177293214}, {"step": 61, "kl": 0.21044895424266322, "ce": 0.3452910363884286}, {"step": 62, "kl": 0.214819483722382, "ce": 0.3334240224081307}, {"step": 63, "kl": 0.16731740657471486, "ce": 0.30364873060010467}, {"step": 64, "kl": 0.1487763769404563, "ce": 0.2576688037881596}, {"step": 65, "kl": 0.1788420065207173, "ce": 0.33395413529647666}, {"step": 66, "kl": 0.15200495924256535, "ce": 0.2595484456681551}, {"step": 67, "kl": 0.20514294281406353, "ce": 0.37384998162766275}, {"step": 68, "kl": 0.18508115734020691, "ce": 0.3181179070632405}, {"step": 69, "kl": 0.17258583708741454, "ce": 0.3052249430318502}, {"step": 70, "kl": 0.1979174290901351, "ce": 0.3183873739541829}, {"step": 71, "kl": 0.16178532792730327, "ce": 0.26621605745173194}, {"step": 72, "kl": 0.21318656354963517, "ce": 0.29021613698369186}, {"step": 73, "kl": 0.1712370558873119, "ce": 0.37507997191794334}, {"step": 74, "kl": 0.19898662564000033, "ce": 0.29692801850833783}, {"step": 75, "kl": 0.17458545326544192, "ce": 0.2688782547132984}, {"step": 76, "kl": 0.16125978410812536, "ce": 0.21321243547252944}, {"step": 77, "kl": 0.1786932934100389, "ce": 0.27045578679940807}, {"step": 78, "kl": 0.21162806274793317, "ce": 0.3222665203693026}, {"step": 79, "kl": 0.1725527369311881, "ce": 0.30844238422386583}, {"step": 80, "kl": 0.196076143914153, "ce": 0.2810716582916595}, {"step": 81, "kl": 0.18845869820559946, "ce": 0.2977644505917983}, {"step": 82, "kl": 0.16302698028660648, "ce": 0.3190915895995563}, {"step": 83, "kl": 0.19744848743561777, "ce": 0.3277766679105385}, {"step": 84, "kl": 0.18399009750075107, "ce": 0.2763210813670937}, {"step": 85, "kl": 0.19990844524370066, "ce": 0.3342191291026113}, {"step": 86, "kl": 0.17412331433248723, "ce": 0.291165538858163}, {"step": 87, "kl": 0.20730787044961513, "ce": 0.3793085545487971}, {"step": 88, "kl": 0.15034604269265084, "ce": 0.2596397202435662}, {"step": 89, "kl": 0.1908668898520547, "ce": 0.321520220701531}, {"step": 90, "kl": 0.1756154633417614, "ce": 0.2930169543694541}, {"step": 91, "kl": 0.18660301503127183, "ce": 0.28803155471600606}, {"step": 92, "kl": 0.17375010154517018, "ce": 0.25627739876741384}, {"step": 93, "kl": 0.17198354233911028, "ce": 0.32277583794862985}, {"step": 94, "kl": 0.17862208055933548, "ce": 0.2801265405330347}, {"step": 95, "kl": 0.20564664262830806, "ce": 0.33378450598960885}, {"step": 96, "kl": 0.15254716186719566, "ce": 0.2799180122801495}, {"step": 97, "kl": 0.18326249651213275, "ce": 0.2943698478633148}, {"step": 98, "kl": 0.17061246570603295, "ce": 0.26355770393510863}, {"step": 99, "kl": 0.16985139180562214, "ce": 0.26905558154728176}, {"step": 100, "kl": 0.15739526448895114, "ce": 0.3101010415987768}, {"step": 101, "kl": 0.18414462706980633, "ce": 0.29836136732644186}, {"step": 102, "kl": 0.15751513611708112, "ce": 0.3156860363863015}, {"step": 103, "kl": 0.17165723395825944, "ce": 0.29832228758372187}, {"step": 104, "kl": 0.18728030821956296, "ce": 0.3126747494652158}, {"step": 105, "kl": 0.2068516831743078, "ce": 0.3478677257007321}, {"step": 106, "kl": 0.22016159023404655, "ce": 0.3054094365161607}, {"step": 107, "kl": 0.19996184319564977, "ce": 0.3206376770043589}, {"step": 108, "kl": 0.17713419396673616, "ce": 0.2595120520818801}, {"step": 109, "kl": 0.1835806131720901, "ce": 0.3183645541948524}, {"step": 110, "kl": 0.15328502879914602, "ce": 0.24953190590620358}, {"step": 111, "kl": 0.17525502386133673, "ce": 0.2694607923175491}, {"step": 112, "kl": 0.18251216706021742, "ce": 0.3054075578196082}, {"step": 113, "kl": 0.1697007369488325, "ce": 0.28256851540582434}, {"step": 114, "kl": 0.18833978787017852, "ce": 0.31615402107531854}, {"step": 115, "kl": 0.15143570048678962, "ce": 0.2602981158812343}, {"step": 116, "kl": 0.17717361710848387, "ce": 0.28015881879156185}, {"step": 117, "kl": 0.16769319494091842, "ce": 0.29988646588708834}, {"step": 118, "kl": 0.14628328131390855, "ce": 0.3228968905936986}, {"step": 119, "kl": 0.15671906772970368, "ce": 0.2990585321968944}, {"step": 120, "kl": 0.15405008819794108, "ce": 0.2612375958959885}, {"step": 121, "kl": 0.17623503650590605, "ce": 0.283371826781967}, {"step": 122, "kl": 0.16011617647721463, "ce": 0.26309060058882194}, {"step": 123, "kl": 0.19065463826985254, "ce": 0.2841889151783835}, {"step": 124, "kl": 0.16807934315733633, "ce": 0.34130005276153325}, {"step": 125, "kl": 0.1592436181415943, "ce": 0.2949346345632532}, {"step": 126, "kl": 0.14665233429640084, "ce": 0.244282227918289}, {"step": 127, "kl": 0.192295802198856, "ce": 0.26304845169071195}, {"step": 128, "kl": 0.17680559068502022, "ce": 0.2771269854844298}, {"step": 129, "kl": 0.1652803034528345, "ce": 0.2724240272736802}, {"step": 130, "kl": 0.15015037950494248, "ce": 0.27774166109672627}, {"step": 131, "kl": 0.15319518054403908, "ce": 0.3151996611578908}, {"step": 132, "kl": 0.1583747284088372, "ce": 0.2935136018583009}, {"step": 133, "kl": 0.18218210072291013, "ce": 0.33998017236286143}, {"step": 134, "kl": 0.2067372417703813, "ce": 0.34723458929462103}, {"step": 135, "kl": 0.13780064473321393, "ce": 0.26673095796737206}, {"step": 136, "kl": 0.15771430753119678, "ce": 0.27599894838635197}, {"step": 137, "kl": 0.20892812571935643, "ce": 0.33041170812097975}, {"step": 138, "kl": 0.1575618668457301, "ce": 0.31519562986184724}, {"step": 139, "kl": 0.17373464399295105, "ce": 0.30767532455291013}, {"step": 140, "kl": 0.19081915536252925, "ce": 0.27058984652240625}, {"step": 141, "kl": 0.1503272489282753, "ce": 0.327573871042193}, {"step": 142, "kl": 0.16406298042779946, "ce": 0.3187626075868563}, {"step": 143, "kl": 0.13685927257739694, "ce": 0.257805265460098}, {"step": 144, "kl": 0.1817870160668064, "ce": 0.31627096365043517}, {"step": 145, "kl": 0.18019087884107582, "ce": 0.29395656269289294}, {"step": 146, "kl": 0.21635504697306468, "ce": 0.33673574601443124}, {"step": 147, "kl": 0.17588135097548485, "ce": 0.3068500901081923}, {"step": 148, "kl": 0.1633594172389556, "ce": 0.24643833379594393}, {"step": 149, "kl": 0.15349760474022267, "ce": 0.27062302563731094}, {"step": 150, "kl": 0.19024767125009956, "ce": 0.30634362462728953}, {"step": 151, "kl": 0.1724188359250578, "ce": 0.2855557528409091}, {"step": 152, "kl": 0.19622249777118367, "ce": 0.30173532996264885}, {"step": 153, "kl": 0.19718043694218385, "ce": 0.30053264417146386}, {"step": 154, "kl": 0.15285739988228525, "ce": 0.308987141841948}, {"step": 155, "kl": 0.20407857844934169, "ce": 0.270195680408569}, {"step": 156, "kl": 0.17615734251552806, "ce": 0.26557960931588354}, {"step": 157, "kl": 0.1278796317877252, "ce": 0.2566217530030714}, {"step": 158, "kl": 0.12188984334800593, "ce": 0.24084781613768422}, {"step": 159, "kl": 0.1871830470511775, "ce": 0.3486069403588772}, {"step": 160, "kl": 0.16753019552087878, "ce": 0.2778098747937604}, {"step": 161, "kl": 0.1638100238946768, "ce": 0.31382109039855016}, {"step": 162, "kl": 0.17400216937362403, "ce": 0.2941840814905462}, {"step": 163, "kl": 0.16950812503083112, "ce": 0.29111684540132376}, {"step": 164, "kl": 0.15808589976728676, "ce": 0.3309149641941635}, {"step": 165, "kl": 0.14687934515230022, "ce": 0.23647225812119815}, {"step": 166, "kl": 0.22600115757550177, "ce": 0.2741353056502095}, {"step": 167, "kl": 0.18439586799060462, "ce": 0.2730539830642266}, {"step": 168, "kl": 0.1659079502946155, "ce": 0.2777115447340217}, {"step": 169, "kl": 0.1515956209143814, "ce": 0.2859274046652396}, {"step": 170, "kl": 0.18672893088644313, "ce": 0.22614450650672388}, {"step": 171, "kl": 0.17410804016489378, "ce": 0.2608913602565117}, {"step": 172, "kl": 0.1644178560014405, "ce": 0.25412826159858165}, {"step": 173, "kl": 0.152249864154504, "ce": 0.24429442805628623}, {"step": 174, "kl": 0.19471134397128315, "ce": 0.32931197832853165}, {"step": 175, "kl": 0.18358105840847858, "ce": 0.27917535855219916}, {"step": 176, "kl": 0.15122224105954785, "ce": 0.271754286331845}, {"step": 177, "kl": 0.13516253880607726, "ce": 0.2426377633807162}, {"step": 178, "kl": 0.15132228286808272, "ce": 0.2903362656111181}, {"step": 179, "kl": 0.168097526801316, "ce": 0.3647375108709383}, {"step": 180, "kl": 0.17966181838354348, "ce": 0.3153769401699128}, {"step": 181, "kl": 0.15155824638615728, "ce": 0.28491857884380123}, {"step": 182, "kl": 0.1858878017568622, "ce": 0.2692420186150639}, {"step": 183, "kl": 0.1626236618077158, "ce": 0.2979116054519409}, {"step": 184, "kl": 0.16547024887810918, "ce": 0.3376465694720928}, {"step": 185, "kl": 0.15565011138521967, "ce": 0.2761162757873535}, {"step": 186, "kl": 0.15481317776009337, "ce": 0.28169231589628274}, {"step": 187, "kl": 0.15606510269958362, "ce": 0.2749444817652672}, {"step": 188, "kl": 0.1697574649756419, "ce": 0.3104434143142605}, {"step": 189, "kl": 0.14685204515973438, "ce": 0.24440315682837305}, {"step": 190, "kl": 0.1597409575322049, "ce": 0.3243967512679298}, {"step": 191, "kl": 0.1852883455446654, "ce": 0.2857685376000254}, {"step": 192, "kl": 0.1259805178821812, "ce": 0.24039446142755777}, {"step": 193, "kl": 0.18413458641223107, "ce": 0.2441241748159572}, {"step": 194, "kl": 0.14680524754355642, "ce": 0.23906084224007818}, {"step": 195, "kl": 0.1648002778946458, "ce": 0.2589094156501163}, {"step": 196, "kl": 0.1625592744609713, "ce": 0.2902321781918268}, {"step": 197, "kl": 0.1690415231268358, "ce": 0.2989338527556175}, {"step": 198, "kl": 0.13834149980852242, "ce": 0.32455923330138364}, {"step": 199, "kl": 0.15918818130447532, "ce": 0.2781482903383118}, {"step": 200, "kl": 0.14971492133334507, "ce": 0.24502596089708747}, {"step": 201, "kl": 0.17113974870671278, "ce": 0.3215094110069823}, {"step": 202, "kl": 0.16169993912744623, "ce": 0.29600845866439845}, {"step": 203, "kl": 0.15456795175688526, "ce": 0.28418987623857495}, {"step": 204, "kl": 0.17772583306534606, "ce": 0.325833130819126}, {"step": 205, "kl": 0.1760979031708281, "ce": 0.24976311917948477}, {"step": 206, "kl": 0.13852312023081678, "ce": 0.30772962799767195}, {"step": 207, "kl": 0.1522280279304053, "ce": 0.30841384605064986}, {"step": 208, "kl": 0.16497526326022308, "ce": 0.29319734009141357}, {"step": 209, "kl": 0.14912207663655486, "ce": 0.28652324199787893}, {"step": 210, "kl": 0.13248483125850066, "ce": 0.2296222299337387}, {"step": 211, "kl": 0.18329973791786108, "ce": 0.32879255130242674}, {"step": 212, "kl": 0.18970856680406367, "ce": 0.2548889620550748}, {"step": 213, "kl": 0.1480980688376359, "ce": 0.2720411706287023}, {"step": 214, "kl": 0.14959428718432222, "ce": 0.29747733046043157}, {"step": 215, "kl": 0.14575651406889653, "ce": 0.28274816940671693}, {"step": 216, "kl": 0.17948326556385458, "ce": 0.32597058378363125}, {"step": 217, "kl": 0.1982841762832687, "ce": 0.34237314735819374}, {"step": 218, "kl": 0.1830469891516981, "ce": 0.3094526993695007}, {"step": 219, "kl": 0.17079084797909383, "ce": 0.30040670767555566}, {"step": 220, "kl": 0.14610722238464813, "ce": 0.26215068816269127}, {"step": 221, "kl": 0.19344352908327073, "ce": 0.3150108247006674}, {"step": 222, "kl": 0.18148400804900827, "ce": 0.32281801228811724}, {"step": 223, "kl": 0.13574068130008757, "ce": 0.25868225704539904}, {"step": 224, "kl": 0.16082421282861625, "ce": 0.23094532859309247}, {"step": 225, "kl": 0.15837066743113992, "ce": 0.2651980737411299}, {"step": 226, "kl": 0.1609924102089983, "ce": 0.2673852228614968}, {"step": 227, "kl": 0.1696301505665622, "ce": 0.2976521178587435}, {"step": 228, "kl": 0.14176598519596606, "ce": 0.201739610397405}, {"step": 229, "kl": 0.12360975226356613, "ce": 0.21991851746880356}, {"step": 230, "kl": 0.10589985503733954, "ce": 0.22451435682934934}, {"step": 231, "kl": 0.1067440402549031, "ce": 0.20557038334832678}, {"step": 232, "kl": 0.13720466352424474, "ce": 0.20880989179219284}, {"step": 233, "kl": 0.14558700810587213, "ce": 0.2516114713650188}, {"step": 234, "kl": 0.13001371879675858, "ce": 0.18549817834196788}, {"step": 235, "kl": 0.106567316733203, "ce": 0.20389419215357663}, {"step": 236, "kl": 0.1084269964961635, "ce": 0.21025227521763273}, {"step": 237, "kl": 0.11918011718217969, "ce": 0.206123705429354}, {"step": 238, "kl": 0.11071906503945658, "ce": 0.17445783565738487}, {"step": 239, "kl": 0.10854281981446523, "ce": 0.21694903620108283}, {"step": 240, "kl": 0.10902104699039634, "ce": 0.2268791452367255}, {"step": 241, "kl": 0.11463447713312822, "ce": 0.19900362649520015}, {"step": 242, "kl": 0.11139747793980712, "ce": 0.2214954698490812}, {"step": 243, "kl": 0.12327339525203942, "ce": 0.22003042700546788}, {"step": 244, "kl": 0.14137348104190428, "ce": 0.22518037606284258}, {"step": 245, "kl": 0.12752640239766502, "ce": 0.19150260024381807}, {"step": 246, "kl": 0.11128539005324134, "ce": 0.16316833356934707}, {"step": 247, "kl": 0.12775919791392365, "ce": 0.20310787688520618}, {"step": 248, "kl": 0.11677747948844866, "ce": 0.2030845516059625}, {"step": 249, "kl": 0.11308198407810167, "ce": 0.2151024327133641}, {"step": 250, "kl": 0.11410143173387288, "ce": 0.2162029436280594}, {"step": 251, "kl": 0.12856212100638323, "ce": 0.22818785236185085}, {"step": 252, "kl": 0.12096636341469916, "ce": 0.185789395650784}, {"step": 253, "kl": 0.15016572092402708, "ce": 0.20880610273853958}, {"step": 254, "kl": 0.12330879955843829, "ce": 0.19941719809731284}, {"step": 255, "kl": 0.1275866981910636, "ce": 0.16977194777342006}, {"step": 256, "kl": 0.11504154384158667, "ce": 0.19771851900995152}, {"step": 257, "kl": 0.11155362558554843, "ce": 0.19931331921175038}, {"step": 258, "kl": 0.12111487497785123, "ce": 0.18328459013460646}, {"step": 259, "kl": 0.12193452416813118, "ce": 0.21244770125949214}, {"step": 260, "kl": 0.10967625193551726, "ce": 0.18357077041858344}, {"step": 261, "kl": 0.08950755080726783, "ce": 0.17980380426638973}, {"step": 262, "kl": 0.123405463029446, "ce": 0.20294461820962223}, {"step": 263, "kl": 0.11651511351585535, "ce": 0.21704692205800874}, {"step": 264, "kl": 0.11091298371710392, "ce": 0.2236691030156517}, {"step": 265, "kl": 0.11674625606615961, "ce": 0.22225557462839768}, {"step": 266, "kl": 0.11729500662861428, "ce": 0.22109042168795756}, {"step": 267, "kl": 0.13484766604019935, "ce": 0.18887568845959207}, {"step": 268, "kl": 0.11104299030699794, "ce": 0.1884177951362189}, {"step": 269, "kl": 0.1306753458914819, "ce": 0.22641126611339513}, {"step": 270, "kl": 0.09895072875103958, "ce": 0.17995685538065803}, {"step": 271, "kl": 0.11498920660273211, "ce": 0.21368578073181999}, {"step": 272, "kl": 0.11113674764534076, "ce": 0.1842363515220295}, {"step": 273, "kl": 0.11513368576919476, "ce": 0.22514376961433913}, {"step": 274, "kl": 0.139997103117324, "ce": 0.23108215738932292}, {"step": 275, "kl": 0.10960681736216749, "ce": 0.20159047424769932}, {"step": 276, "kl": 0.1342233861262551, "ce": 0.2308205165123488}, {"step": 277, "kl": 0.1102093577158745, "ce": 0.18832972750064114}, {"step": 278, "kl": 0.11416883120942437, "ce": 0.19500145071985936}, {"step": 279, "kl": 0.11028115109919451, "ce": 0.2336104245811055}, {"step": 280, "kl": 0.14840777378504622, "ce": 0.2540096597171625}, {"step": 281, "kl": 0.11828066705537979, "ce": 0.21255524219717212}, {"step": 282, "kl": 0.12384178551659854, "ce": 0.22246556359654907}, {"step": 283, "kl": 0.10978986611560594, "ce": 0.19716996223695815}, {"step": 284, "kl": 0.09273803030272032, "ce": 0.18125531119666316}, {"step": 285, "kl": 0.11230293402665321, "ce": 0.17101188751312346}, {"step": 286, "kl": 0.12367081795849122, "ce": 0.20694638162419415}, {"step": 287, "kl": 0.1276812231479741, "ce": 0.2630789831980763}, {"step": 288, "kl": 0.10846904312925873, "ce": 0.19535259628809776}, {"step": 289, "kl": 0.09975896439275811, "ce": 0.2245150700870584}, {"step": 290, "kl": 0.12937870670057955, "ce": 0.20531303232366388}, {"step": 291, "kl": 0.11036984095909051, "ce": 0.20283375788633956}, {"step": 292, "kl": 0.12021357393510984, "ce": 0.21689660696362803}, {"step": 293, "kl": 0.13588659011207688, "ce": 0.21856790194281575}, {"step": 294, "kl": 0.13606743143960398, "ce": 0.1634005402047093}, {"step": 295, "kl": 0.11600761559918105, "ce": 0.22398838711511324}, {"step": 296, "kl": 0.1048549257319558, "ce": 0.1745439638366454}, {"step": 297, "kl": 0.11049014868328254, "ce": 0.2184119691609793}, {"step": 298, "kl": 0.12038655127359879, "ce": 0.21513770613323097}, {"step": 299, "kl": 0.11787315526088718, "ce": 0.20817526313696014}, {"step": 300, "kl": 0.10806328898440941, "ce": 0.20284336850704848}, {"step": 301, "kl": 0.11342503391206264, "ce": 0.1913045626018319}, {"step": 302, "kl": 0.10747772474272002, "ce": 0.1799072684895059}, {"step": 303, "kl": 0.1322109269049298, "ce": 0.2541577001443705}, {"step": 304, "kl": 0.11468289396583914, "ce": 0.20834190702389846}, {"step": 305, "kl": 0.11674608642860457, "ce": 0.1892419640166888}, {"step": 306, "kl": 0.10923239784290784, "ce": 0.21406031666945705}, {"step": 307, "kl": 0.10205546021998757, "ce": 0.2205730672132477}, {"step": 308, "kl": 0.12695485545874252, "ce": 0.21886335764329892}, {"step": 309, "kl": 0.11707591681103957, "ce": 0.19558423764269872}, {"step": 310, "kl": 0.13512382831235242, "ce": 0.20105353981040802}, {"step": 311, "kl": 0.12263796513572928, "ce": 0.21017418292495474}, {"step": 312, "kl": 0.09524747563874386, "ce": 0.1786245592665861}, {"step": 313, "kl": 0.10956980982586915, "ce": 0.21140979326060427}, {"step": 314, "kl": 0.1197074338040795, "ce": 0.20635761203670344}, {"step": 315, "kl": 0.12244114900431308, "ce": 0.22857650442316174}, {"step": 316, "kl": 0.09966950382997301, "ce": 0.21548782319896861}, {"step": 317, "kl": 0.12982244665877937, "ce": 0.2079023598862913}, {"step": 318, "kl": 0.12325701836277456, "ce": 0.2586137371381403}, {"step": 319, "kl": 0.11429656262139898, "ce": 0.2151901233217508}, {"step": 320, "kl": 0.12680951382074707, "ce": 0.21321109349165504}, {"step": 321, "kl": 0.12676111790265637, "ce": 0.2003265988779258}, {"step": 322, "kl": 0.09922438610750353, "ce": 0.20562754931580043}, {"step": 323, "kl": 0.11398323726358799, "ce": 0.2154451511374992}, {"step": 324, "kl": 0.1051012454319862, "ce": 0.23996701945795393}, {"step": 325, "kl": 0.10219451303093464, "ce": 0.17879334839721595}, {"step": 326, "kl": 0.12133003012387222, "ce": 0.2502796441337354}, {"step": 327, "kl": 0.10081076862753692, "ce": 0.17239869010250397}, {"step": 328, "kl": 0.11865269520899634, "ce": 0.1877625822069946}, {"step": 329, "kl": 0.1168285505941295, "ce": 0.2029577906127113}, {"step": 330, "kl": 0.11376437918715389, "ce": 0.20923080033711905}, {"step": 331, "kl": 0.11357531177526338, "ce": 0.1979939833425744}, {"step": 332, "kl": 0.11382202953802426, "ce": 0.2496826443938645}, {"step": 333, "kl": 0.13324006821780082, "ce": 0.21599911625792342}, {"step": 334, "kl": 0.10535908514886484, "ce": 0.19011196963297347}, {"step": 335, "kl": 0.12806359658086122, "ce": 0.19396601795534504}, {"step": 336, "kl": 0.11512037887390127, "ce": 0.23493885469810383}, {"step": 337, "kl": 0.1150899961650462, "ce": 0.17454575102361874}, {"step": 338, "kl": 0.13802470983417447, "ce": 0.19333943033713372}, {"step": 339, "kl": 0.09462938208836603, "ce": 0.1984657456150349}, {"step": 340, "kl": 0.09194174616994497, "ce": 0.21300097546986974}, {"step": 341, "kl": 0.1014969189231483, "ce": 0.19973933418557469}, {"step": 342, "kl": 0.10530634104886796, "ce": 0.18530946212951646}, {"step": 343, "kl": 0.1123995254230168, "ce": 0.18190318782155107}, {"step": 344, "kl": 0.08160595364438261, "ce": 0.18316016780862082}, {"step": 345, "kl": 0.10121189172982419, "ce": 0.19572121280056615}, {"step": 346, "kl": 0.11845985654642768, "ce": 0.21325522540343}, {"step": 347, "kl": 0.11077358687564119, "ce": 0.1633752228854602}, {"step": 348, "kl": 0.11884591001901569, "ce": 0.20352940279910348}, {"step": 349, "kl": 0.13196832511938425, "ce": 0.24891982310695188}, {"step": 350, "kl": 0.09591166452387581, "ce": 0.1762986053094847}, {"step": 351, "kl": 0.14109711953605553, "ce": 0.2153378754460601}, {"step": 352, "kl": 0.10485253467272862, "ce": 0.13859550904803483}, {"step": 353, "kl": 0.11977141767720499, "ce": 0.21889387902113688}, {"step": 354, "kl": 0.13946490470552608, "ce": 0.22261624710780653}, {"step": 355, "kl": 0.1263381491987929, "ce": 0.1465673392571664}, {"step": 356, "kl": 0.1320712162912212, "ce": 0.2352190364900774}, {"step": 357, "kl": 0.10909232244719311, "ce": 0.1946317411983231}, {"step": 358, "kl": 0.16011348797261798, "ce": 0.25839101925842445}, {"step": 359, "kl": 0.1126010365563141, "ce": 0.20769048305826449}, {"step": 360, "kl": 0.12438719038517379, "ce": 0.21942531311307115}, {"step": 361, "kl": 0.11480005528187812, "ce": 0.2258190297357075}, {"step": 362, "kl": 0.11080674679917844, "ce": 0.19679128216347902}, {"step": 363, "kl": 0.1125444954953989, "ce": 0.1812903221513404}, {"step": 364, "kl": 0.0961823858538765, "ce": 0.1860495802330201}, {"step": 365, "kl": 0.11061444755728918, "ce": 0.23563140302658492}, {"step": 366, "kl": 0.1159934892419402, "ce": 0.18920805993510753}, {"step": 367, "kl": 0.1048147590128908, "ce": 0.1901020298549107}, {"step": 368, "kl": 0.10391917528610217, "ce": 0.16145544995811154}, {"step": 369, "kl": 0.07832463525902043, "ce": 0.17013586032654007}, {"step": 370, "kl": 0.08582449501012436, "ce": 0.17944726181229684}, {"step": 371, "kl": 0.11282196428972929, "ce": 0.23538383158734752}, {"step": 372, "kl": 0.11834613208113046, "ce": 0.18933680423975446}, {"step": 373, "kl": 0.12320349097683439, "ce": 0.18828544936589975}, {"step": 374, "kl": 0.10848287212335404, "ce": 0.19999103076501532}, {"step": 375, "kl": 0.09861260298209314, "ce": 0.20613077212729447}, {"step": 376, "kl": 0.10807160006787439, "ce": 0.16744106658803376}, {"step": 377, "kl": 0.13808717538834836, "ce": 0.21678717884771792}, {"step": 378, "kl": 0.1287085588206823, "ce": 0.22549954691667842}, {"step": 379, "kl": 0.10732206531535987, "ce": 0.1901317767781287}, {"step": 380, "kl": 0.10967543553220287, "ce": 0.2110256977135288}, {"step": 381, "kl": 0.11492817189381513, "ce": 0.1890246902065777}, {"step": 382, "kl": 0.14290170338671898, "ce": 0.19688140476868077}, {"step": 383, "kl": 0.11998122658273401, "ce": 0.18555059869857637}, {"step": 384, "kl": 0.11356805632107536, "ce": 0.19093247156355975}, {"step": 385, "kl": 0.1266028764860761, "ce": 0.20631432280847956}, {"step": 386, "kl": 0.1322923594332756, "ce": 0.2040598032162573}, {"step": 387, "kl": 0.10497462306814784, "ce": 0.19153442016254998}, {"step": 388, "kl": 0.1157612128777592, "ce": 0.19574382156477788}, {"step": 389, "kl": 0.13337874527873875, "ce": 0.211906356445647}, {"step": 390, "kl": 0.09685010878834366, "ce": 0.1944731179769937}, {"step": 391, "kl": 0.10582020140360696, "ce": 0.19498872222166966}, {"step": 392, "kl": 0.09521966992469641, "ce": 0.17379483232508777}, {"step": 393, "kl": 0.11311249668676712, "ce": 0.17788121327250994}, {"step": 394, "kl": 0.1122671817117035, "ce": 0.21132855973905748}, {"step": 395, "kl": 0.08848789064411024, "ce": 0.1655265073598542}, {"step": 396, "kl": 0.10308732366414261, "ce": 0.1935524320271767}, {"step": 397, "kl": 0.14548917765524486, "ce": 0.22090789469043215}, {"step": 398, "kl": 0.13179725599032116, "ce": 0.21878773222880302}, {"step": 399, "kl": 0.1256148471174569, "ce": 0.24279909691859256}, {"step": 400, "kl": 0.10042208924552204, "ce": 0.2340185887700327}, {"step": 401, "kl": 0.12204456583387877, "ce": 0.1875264563724344}, {"step": 402, "kl": 0.10714677898167882, "ce": 0.2428077242931193}, {"step": 403, "kl": 0.12988744040950337, "ce": 0.2373298516722538}, {"step": 404, "kl": 0.11343218868640813, "ce": 0.21778272065206916}, {"step": 405, "kl": 0.1043309603605842, "ce": 0.1815138919812413}, {"step": 406, "kl": 0.1384132624945506, "ce": 0.18831077921929673}, {"step": 407, "kl": 0.13181936678592437, "ce": 0.2049274165938195}, {"step": 408, "kl": 0.112642291694934, "ce": 0.2314106024897889}, {"step": 409, "kl": 0.12950281720524184, "ce": 0.20167336360135243}, {"step": 410, "kl": 0.10999865041059606, "ce": 0.19584465497999634}, {"step": 411, "kl": 0.13862170060701762, "ce": 0.25835307536204755}, {"step": 412, "kl": 0.1174670875315346, "ce": 0.2302421819621265}, {"step": 413, "kl": 0.09192117573525668, "ce": 0.16209356292717206}, {"step": 414, "kl": 0.08919523575079107, "ce": 0.17180564382153563}, {"step": 415, "kl": 0.1131878412115768, "ce": 0.1907227173478207}, {"step": 416, "kl": 0.09960084997012839, "ce": 0.17925914959766154}, {"step": 417, "kl": 0.08680766921663782, "ce": 0.1903218558274532}, {"step": 418, "kl": 0.13195095733699122, "ce": 0.2020573151203001}, {"step": 419, "kl": 0.10030407160945357, "ce": 0.18602844516255285}, {"step": 420, "kl": 0.09534148677213834, "ce": 0.17651741717011524}, {"step": 421, "kl": 0.09180320671012811, "ce": 0.17989922794920793}, {"step": 422, "kl": 0.11924732870652131, "ce": 0.20687075643144415}, {"step": 423, "kl": 0.12428296698152529, "ce": 0.18348308793249407}, {"step": 424, "kl": 0.13290641558532068, "ce": 0.21132528904020656}, {"step": 425, "kl": 0.11006769648951534, "ce": 0.20690213930633325}, {"step": 426, "kl": 0.11464045280094606, "ce": 0.17919779120024687}, {"step": 427, "kl": 0.07918136183110785, "ce": 0.20566027184645186}, {"step": 428, "kl": 0.09791428088984318, "ce": 0.17846767207829198}, {"step": 429, "kl": 0.11556597508378505, "ce": 0.19180924403000052}, {"step": 430, "kl": 0.15151162833430712, "ce": 0.23576095044030787}, {"step": 431, "kl": 0.12554156765301738, "ce": 0.22916817615532822}, {"step": 432, "kl": 0.10854098212466917, "ce": 0.20261460059082986}, {"step": 433, "kl": 0.09521194221262655, "ce": 0.14552553470382457}, {"step": 434, "kl": 0.11244730035412753, "ce": 0.23143953493342934}, {"step": 435, "kl": 0.12961801405278794, "ce": 0.19084713900457542}, {"step": 436, "kl": 0.1134399820018459, "ce": 0.21384792052087964}, {"step": 437, "kl": 0.10477706577412244, "ce": 0.26461226812892014}, {"step": 438, "kl": 0.11278231763718595, "ce": 0.24826760836455403}, {"step": 439, "kl": 0.11278462943465711, "ce": 0.17650766559171258}, {"step": 440, "kl": 0.1225179926036998, "ce": 0.20318802313201992}, {"step": 441, "kl": 0.11161683092253386, "ce": 0.21260809539375947}, {"step": 442, "kl": 0.10954162712134097, "ce": 0.1719156152583257}, {"step": 443, "kl": 0.11659191924502517, "ce": 0.1876613522437083}, {"step": 444, "kl": 0.10993807865380197, "ce": 0.22351029409935966}, {"step": 445, "kl": 0.09746144507168594, "ce": 0.17511946331433048}, {"step": 446, "kl": 0.1134366323781568, "ce": 0.22313376704554932}, {"step": 447, "kl": 0.10405689154632289, "ce": 0.18795294600230988}, {"step": 448, "kl": 0.11266038728436298, "ce": 0.21197277318433644}, {"step": 449, "kl": 0.1050894846490486, "ce": 0.17748088013611413}, {"step": 450, "kl": 0.10444710419428543, "ce": 0.18884691923498995}, {"step": 451, "kl": 0.12779712259105594, "ce": 0.23480876838101933}, {"step": 452, "kl": 0.10714566056395627, "ce": 0.18480506909028588}, {"step": 453, "kl": 0.118298197536511, "ce": 0.2087545442864619}, {"step": 454, "kl": 0.11076728421814588, "ce": 0.1783803478702084}], "val": [{"step": 0, "math_kl": 0.17064335946551992, "math_ce": 0.8387106338797149, "code_kl": 0.22128492102940375, "code_ce": 0.36744983409730037}, {"step": 227, "math_kl": 0.17851292490413978, "math_ce": 0.7559874551841125, "code_kl": 0.17002756730470805, "code_ce": 0.294655845964488}, {"step": 454, "math_kl": 0.18309472424367448, "math_ce": 0.7728381256840412, "code_kl": 0.16207903510989155, "code_ce": 0.2930570245420335}]}
 
 
seq_code_math/stage1_code/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d53bb379cd97b148fd55ca8eef0728776a914fa7a558f6244ab879a1f092bb2c
3
- size 988097824
 
 
 
 
seq_math_code/results_stage1_math/gsm8k.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage1_math/humaneval.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage1_math/humaneval_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage1_math/mbpp.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage1_math/mbpp_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage1_math/summary.json DELETED
@@ -1 +0,0 @@
1
- {"model": "stage1_math", "gsm8k": 0.41925701288855194, "mbpp": 0.4603174603174603, "mbpp_plus": 0.3888888888888889, "humaneval": 0.3170731707317073, "humaneval_plus": 0.2865853658536585, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
 
 
seq_math_code/results_stage2_code/gsm8k.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/humaneval.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/humaneval_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/mbpp.jsonl DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/mbpp_eval_results.json DELETED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/summary.json DELETED
@@ -1 +0,0 @@
1
- {"model": "stage2_code", "gsm8k": 0.4275966641394996, "mbpp": 0.49206349206349204, "mbpp_plus": 0.42857142857142855, "humaneval": 0.35365853658536583, "humaneval_plus": 0.3231707317073171, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
 
 
seq_math_code/stage1_math/config.json DELETED
@@ -1,57 +0,0 @@
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": 896,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 4864,
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
- ],
39
- "max_position_embeddings": 32768,
40
- "max_window_layers": 21,
41
- "model_type": "qwen2",
42
- "num_attention_heads": 14,
43
- "num_hidden_layers": 24,
44
- "num_key_value_heads": 2,
45
- "pad_token_id": null,
46
- "rms_norm_eps": 1e-06,
47
- "rope_parameters": {
48
- "rope_theta": 1000000.0,
49
- "rope_type": "default"
50
- },
51
- "sliding_window": null,
52
- "tie_word_embeddings": true,
53
- "transformers_version": "5.20.2",
54
- "use_cache": true,
55
- "use_sliding_window": false,
56
- "vocab_size": 151936
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seq_math_code/stage1_math/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.1,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "5.20.2"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seq_math_code/stage1_math/log.json DELETED
@@ -1 +0,0 @@
1
- {"train": [{"step": 1, "kl": 0.11480725864322953, "ce": 0.8080925811042935}, {"step": 2, "kl": 0.12464279600803654, "ce": 0.7568737392830607}, {"step": 3, "kl": 0.11688388028670647, "ce": 0.7516716620799571}, {"step": 4, "kl": 0.1291475374820487, "ce": 0.8644150544664266}, {"step": 5, "kl": 0.13646082791874847, "ce": 0.7736669648583255}, {"step": 6, "kl": 0.12342201891720699, "ce": 0.6292343537288874}, {"step": 7, "kl": 0.12178253977008206, "ce": 0.6058252519059022}, {"step": 8, "kl": 0.11236868202111033, "ce": 0.542436748330951}, {"step": 9, "kl": 0.13997640896063757, "ce": 0.5520169436576398}, {"step": 10, "kl": 0.11640932618727295, "ce": 0.525698872922941}, {"step": 11, "kl": 0.1215036657580385, "ce": 0.5172294360537477}, {"step": 12, "kl": 0.12879101825016798, "ce": 0.548645433413437}, {"step": 13, "kl": 0.16246793404922896, "ce": 0.5652527006779953}, {"step": 14, "kl": 0.13068362963394792, "ce": 0.4878172995125307}, {"step": 15, "kl": 0.11138974243716052, "ce": 0.489910283267199}, {"step": 16, "kl": 0.12727180543900365, "ce": 0.5971274742713342}, {"step": 17, "kl": 0.10323828847981292, "ce": 0.44966070890426635}, {"step": 18, "kl": 0.15761358469641107, "ce": 0.5500064342697232}, {"step": 19, "kl": 0.12764032131592573, "ce": 0.541708585313687}, {"step": 20, "kl": 0.12397368770667021, "ce": 0.6370012055626212}, {"step": 21, "kl": 0.1216461368030587, "ce": 0.510365263813949}, {"step": 22, "kl": 0.14083641083292178, "ce": 0.4943190643965263}, {"step": 23, "kl": 0.11332968857689996, "ce": 0.4649785015693949}, {"step": 24, "kl": 0.12329887938997862, "ce": 0.6297620187098832}, {"step": 25, "kl": 0.12233939685028587, "ce": 0.505680367576043}, {"step": 26, "kl": 0.11919694895068313, "ce": 0.5378070786478625}, {"step": 27, "kl": 0.15152330299458325, "ce": 0.5742943379416394}, {"step": 28, "kl": 0.12528755085412532, "ce": 0.5252886007486433}, {"step": 29, "kl": 0.11519809059101349, "ce": 0.5448577985473992}, {"step": 30, "kl": 0.1259457265354324, "ce": 0.5154699061227882}, {"step": 31, "kl": 0.12125498919794905, "ce": 0.4788745750646367}, {"step": 32, "kl": 0.12461201930690458, "ce": 0.5418000167893248}, {"step": 33, "kl": 0.08893451000501659, "ce": 0.5196508578740058}, {"step": 34, "kl": 0.158045995281479, "ce": 0.5569429249726524}, {"step": 35, "kl": 0.15149120032667873, "ce": 0.5692120395013995}, {"step": 36, "kl": 0.11225517498837449, "ce": 0.531276556543318}, {"step": 37, "kl": 0.135960638541046, "ce": 0.5697093541047165}, {"step": 38, "kl": 0.13888206360832095, "ce": 0.5692835348275164}, {"step": 39, "kl": 0.133500901630685, "ce": 0.5201919862888004}, {"step": 40, "kl": 0.12537432742944954, "ce": 0.5412070196552557}, {"step": 41, "kl": 0.14121654399989364, "ce": 0.5589613642192298}, {"step": 42, "kl": 0.1510018705881644, "ce": 0.5630755672228154}, {"step": 43, "kl": 0.119386845160984, "ce": 0.45733737733629015}, {"step": 44, "kl": 0.11810483080965711, "ce": 0.5049335837403142}, {"step": 45, "kl": 0.12711578329511364, "ce": 0.515711035290833}, {"step": 46, "kl": 0.0918182206513955, "ce": 0.5244490151168678}, {"step": 47, "kl": 0.11763732110706492, "ce": 0.43914150682027997}, {"step": 48, "kl": 0.12624365601245915, "ce": 0.5197361206610395}, {"step": 49, "kl": 0.1097771160564647, "ce": 0.49326662144735}, {"step": 50, "kl": 0.15424430785805546, "ce": 0.5863280774733733}, {"step": 51, "kl": 0.133445706184477, "ce": 0.5505480154312867}, {"step": 52, "kl": 0.11661801678367491, "ce": 0.5245642458053834}, {"step": 53, "kl": 0.11615374709745388, "ce": 0.5579103735272553}, {"step": 54, "kl": 0.12227450113973876, "ce": 0.5228604946946642}, {"step": 55, "kl": 0.12405532269405406, "ce": 0.5540201905179007}, {"step": 56, "kl": 0.11335698667188823, "ce": 0.5184035042263815}, {"step": 57, "kl": 0.11637968039412877, "ce": 0.5019830812018069}, {"step": 58, "kl": 0.23841069060977144, "ce": 0.5333052291845078}, {"step": 59, "kl": 0.1204877069803831, "ce": 0.43413229783376056}, {"step": 60, "kl": 0.10921031372431948, "ce": 0.5293197292966891}, {"step": 61, "kl": 0.1271167914640455, "ce": 0.4986792128426688}, {"step": 62, "kl": 0.12054646613806215, "ce": 0.42755854443316565}, {"step": 63, "kl": 0.11842688449854019, "ce": 0.5430092394930646}, {"step": 64, "kl": 0.12042623625524024, "ce": 0.544638586430075}, {"step": 65, "kl": 0.1205752526373124, "ce": 0.5415648621464543}, {"step": 66, "kl": 0.12742400389124825, "ce": 0.593000150194355}, {"step": 67, "kl": 0.13482921167111608, "ce": 0.5379040234780248}, {"step": 68, "kl": 0.13649400354582547, "ce": 0.5305868188020225}, {"step": 69, "kl": 0.13860748744480217, "ce": 0.5097008130800805}, {"step": 70, "kl": 0.12837871198735476, "ce": 0.5167031532434805}, {"step": 71, "kl": 0.12255233350681499, "ce": 0.5909371928940839}, {"step": 72, "kl": 0.11862837328217711, "ce": 0.557912789906887}, {"step": 73, "kl": 0.14584629062666626, "ce": 0.5251923392069925}, {"step": 74, "kl": 0.1259452558314482, "ce": 0.5523333469346996}, {"step": 75, "kl": 0.13246376884632288, "ce": 0.5166188074142971}, {"step": 76, "kl": 0.10164674485816608, "ce": 0.4371947552190578}, {"step": 77, "kl": 0.14349860166892028, "ce": 0.6168641938859963}, {"step": 78, "kl": 0.11249626939669966, "ce": 0.5307931794451611}, {"step": 79, "kl": 0.18077950018242903, "ce": 0.48943109973071824}, {"step": 80, "kl": 0.15814341459391978, "ce": 0.5038759946593356}, {"step": 81, "kl": 0.12462260476161606, "ce": 0.5595395157322087}, {"step": 82, "kl": 0.1573954469537082, "ce": 0.605853743567145}, {"step": 83, "kl": 0.13386813230309078, "ce": 0.534967864593024}, {"step": 84, "kl": 0.1319257017658542, "ce": 0.5256574099357507}, {"step": 85, "kl": 0.1320299701051026, "ce": 0.5459361706088802}, {"step": 86, "kl": 0.13700987319833785, "ce": 0.564668751772882}, {"step": 87, "kl": 0.11606838494762885, "ce": 0.490307262920424}, {"step": 88, "kl": 0.12551742809417363, "ce": 0.5372350988655447}, {"step": 89, "kl": 0.11492110551694172, "ce": 0.4892400720671329}, {"step": 90, "kl": 0.13505715634505308, "ce": 0.5584287106109034}, {"step": 91, "kl": 0.13745328211666347, "ce": 0.5248165860331819}, {"step": 92, "kl": 0.119288409108605, "ce": 0.486186595761804}, {"step": 93, "kl": 0.09047094876133827, "ce": 0.4649918077890747}, {"step": 94, "kl": 0.1150112981793894, "ce": 0.470847472768699}, {"step": 95, "kl": 0.11162326058192609, "ce": 0.5325017737633233}, {"step": 96, "kl": 0.132409382809704, "ce": 0.5408920855210964}, {"step": 97, "kl": 0.1259629122706009, "ce": 0.5370027698756417}, {"step": 98, "kl": 0.12185947944864588, "ce": 0.46707602775938406}, {"step": 99, "kl": 0.1329616428749737, "ce": 0.537377379195285}, {"step": 100, "kl": 0.11189951357202817, "ce": 0.550417977723577}, {"step": 101, "kl": 0.11513382883814333, "ce": 0.5053491844850427}, {"step": 102, "kl": 0.1123866205630095, "ce": 0.5348453030056424}, {"step": 103, "kl": 0.11420926323011342, "ce": 0.5342864990234375}, {"step": 104, "kl": 0.10837354517203956, "ce": 0.5668102827228484}, {"step": 105, "kl": 0.11161969064912242, "ce": 0.5485348624201248}, {"step": 106, "kl": 0.1615474652697662, "ce": 0.5629309868016569}, {"step": 107, "kl": 0.11032125163146678, "ce": 0.5103334885578168}, {"step": 108, "kl": 0.12491246218387941, "ce": 0.5345077792448305}, {"step": 109, "kl": 0.10866005948277749, "ce": 0.5378277639810891}, {"step": 110, "kl": 0.1166256743262129, "ce": 0.461038695441352}, {"step": 111, "kl": 0.1353325298770409, "ce": 0.5125571539609814}, {"step": 112, "kl": 0.12888235792916478, "ce": 0.5779740064604103}, {"step": 113, "kl": 0.11582007724248779, "ce": 0.4306544284692546}, {"step": 114, "kl": 0.10422742544062683, "ce": 0.45596696766857275}, {"step": 115, "kl": 0.12183943695423675, "ce": 0.5184054269664613}, {"step": 116, "kl": 0.11584954470982169, "ce": 0.5424234544908678}, {"step": 117, "kl": 0.12676335009852924, "ce": 0.5660224298579835}, {"step": 118, "kl": 0.10907545324994172, "ce": 0.5381752197408649}, {"step": 119, "kl": 0.13837304594398955, "ce": 0.48422330939359215}, {"step": 120, "kl": 0.11397036927170788, "ce": 0.4899260163483796}, {"step": 121, "kl": 0.11144209423116688, "ce": 0.429913970990461}, {"step": 122, "kl": 0.15438927235104452, "ce": 0.4043311569971908}, {"step": 123, "kl": 0.12131498532641904, "ce": 0.48074247870823644}, {"step": 124, "kl": 0.1300507621912296, "ce": 0.5312606155773826}, {"step": 125, "kl": 0.1304733204217646, "ce": 0.5836875466423048}, {"step": 126, "kl": 0.17786708505268134, "ce": 0.5146268329349174}, {"step": 127, "kl": 0.14226203730532824, "ce": 0.5258989904680823}, {"step": 128, "kl": 0.11187150628645602, "ce": 0.5460632308020459}, {"step": 129, "kl": 0.11057361546102376, "ce": 0.4995777234187224}, {"step": 130, "kl": 0.11067246947396991, "ce": 0.4340610953144108}, {"step": 131, "kl": 0.11575771735656304, "ce": 0.46924958517314985}, {"step": 132, "kl": 0.09962642632714336, "ce": 0.5175571380971219}, {"step": 133, "kl": 0.10182062769777268, "ce": 0.41621316319746937}, {"step": 134, "kl": 0.1016143180207564, "ce": 0.47284637328856927}, {"step": 135, "kl": 0.10970261915206697, "ce": 0.42039045424095767}, {"step": 136, "kl": 0.15995754432998532, "ce": 0.5881690111777764}, {"step": 137, "kl": 0.11276945508485206, "ce": 0.5769509292752345}, {"step": 138, "kl": 0.11333000791059467, "ce": 0.5410625349988827}, {"step": 139, "kl": 0.12406740874039666, "ce": 0.5909643772598472}, {"step": 140, "kl": 0.11040134364773069, "ce": 0.5040177836429164}, {"step": 141, "kl": 0.10147027690569735, "ce": 0.5260972449527913}, {"step": 142, "kl": 0.13648000703201127, "ce": 0.5121365519403254}, {"step": 143, "kl": 0.1307194618927538, "ce": 0.5006875422093775}, {"step": 144, "kl": 0.12387873615297851, "ce": 0.5649777353885802}, {"step": 145, "kl": 0.13700149507773524, "ce": 0.5292826645246899}, {"step": 146, "kl": 0.11339647965646749, "ce": 0.46625444358754387}, {"step": 147, "kl": 0.1138708045494419, "ce": 0.4517610642723081}, {"step": 148, "kl": 0.0954492078835951, "ce": 0.5431984316335329}, {"step": 149, "kl": 0.1176450251811717, "ce": 0.5608343456580702}, {"step": 150, "kl": 0.12048307396452504, "ce": 0.5179931117175345}, {"step": 151, "kl": 0.10427458669840992, "ce": 0.5049892038706814}, {"step": 152, "kl": 0.11031042267208896, "ce": 0.4812440041745647}, {"step": 153, "kl": 0.201316516121888, "ce": 0.4926630263755355}, {"step": 154, "kl": 0.12049082344538839, "ce": 0.462928012862542}, {"step": 155, "kl": 0.10129070281982422, "ce": 0.4581100919147512}, {"step": 156, "kl": 0.11699848445838176, "ce": 0.5396782052147601}, {"step": 157, "kl": 0.12731394758128156, "ce": 0.516565339369825}, {"step": 158, "kl": 0.10030872264286451, "ce": 0.46254651232701}, {"step": 159, "kl": 0.10297650483079761, "ce": 0.49110524991255866}, {"step": 160, "kl": 0.14091076362123406, "ce": 0.5724572968064693}, {"step": 161, "kl": 0.12573156476085634, "ce": 0.4860785405977823}, {"step": 162, "kl": 0.1260729918100197, "ce": 0.5658091300445077}, {"step": 163, "kl": 0.1340959174252992, "ce": 0.46337403910398417}, {"step": 164, "kl": 0.1102934764041412, "ce": 0.5515018612730737}, {"step": 165, "kl": 0.14294987895628172, "ce": 0.5201835190883102}, {"step": 166, "kl": 0.09579103857776931, "ce": 0.4891792256996115}, {"step": 167, "kl": 0.11493377198045626, "ce": 0.4194086315306564}, {"step": 168, "kl": 0.14371157892598402, "ce": 0.5183020783973539}, {"step": 169, "kl": 0.12130870377340626, "ce": 0.5779703433443639}, {"step": 170, "kl": 0.1159162554094918, "ce": 0.5101017520404233}, {"step": 171, "kl": 0.12140692477787011, "ce": 0.5141405194592913}, {"step": 172, "kl": 0.1134916844151351, "ce": 0.46151484237922413}, {"step": 173, "kl": 0.12446925124871311, "ce": 0.5435805430489281}, {"step": 174, "kl": 0.12710922521034407, "ce": 0.5444613258721477}, {"step": 175, "kl": 0.10935189359607887, "ce": 0.505617141107763}, {"step": 176, "kl": 0.1256101723109398, "ce": 0.4788693312821256}, {"step": 177, "kl": 0.10779780859244457, "ce": 0.49211785574740174}, {"step": 178, "kl": 0.09012263775276955, "ce": 0.46928131623304054}, {"step": 179, "kl": 0.10900624529660234, "ce": 0.5444413054084896}, {"step": 180, "kl": 0.12989239296353336, "ce": 0.5114956705378929}, {"step": 181, "kl": 0.10850043116272091, "ce": 0.46720748651223104}, {"step": 182, "kl": 0.10526120657521923, "ce": 0.43273751352735135}, {"step": 183, "kl": 0.13633292730600557, "ce": 0.5198471487449308}, {"step": 184, "kl": 0.1186955444975049, "ce": 0.526957007829757}, {"step": 185, "kl": 0.11536414795260583, "ce": 0.4358428046548155}, {"step": 186, "kl": 0.1248602234411966, "ce": 0.45112253529156826}, {"step": 187, "kl": 0.10410416704886821, "ce": 0.4528608465913552}, {"step": 188, "kl": 0.10861539514376833, "ce": 0.5186818064647023}, {"step": 189, "kl": 0.1197266259706192, "ce": 0.5402444299661888}, {"step": 190, "kl": 0.13178262747163585, "ce": 0.5467176938991771}, {"step": 191, "kl": 0.11517769531223211, "ce": 0.5295748660820275}, {"step": 192, "kl": 0.15118620026095247, "ce": 0.5590220579028087}, {"step": 193, "kl": 0.11599589815855806, "ce": 0.5249311980360876}, {"step": 194, "kl": 0.1221563834829085, "ce": 0.4468622741895726}, {"step": 195, "kl": 0.11407202207277237, "ce": 0.5066083170049402}, {"step": 196, "kl": 0.11192412590739462, "ce": 0.5498193065494621}, {"step": 197, "kl": 0.12154417445516993, "ce": 0.4386360648087066}, {"step": 198, "kl": 0.11333120469721708, "ce": 0.5264154420927892}, {"step": 199, "kl": 0.09697100769139189, "ce": 0.4762470345567482}, {"step": 200, "kl": 0.0872196827355791, "ce": 0.523428793608332}, {"step": 201, "kl": 0.12594013411032295, "ce": 0.537036337890625}, {"step": 202, "kl": 0.13035780489741078, "ce": 0.5451559547151286}, {"step": 203, "kl": 0.10115924163806235, "ce": 0.4129366796429759}, {"step": 204, "kl": 0.12414330069655566, "ce": 0.5024593711233273}, {"step": 205, "kl": 0.11333499095379987, "ce": 0.48334292596516426}, {"step": 206, "kl": 0.2587690155551753, "ce": 0.5075633178343489}, {"step": 207, "kl": 0.11558795629682309, "ce": 0.5545031622113514}, {"step": 208, "kl": 0.13238837685520075, "ce": 0.5223258499550609}, {"step": 209, "kl": 0.11022819472097828, "ce": 0.47025038954534815}, {"step": 210, "kl": 0.10591252909325523, "ce": 0.471659239437081}, {"step": 211, "kl": 0.1118915351461118, "ce": 0.5489897748381354}, {"step": 212, "kl": 0.11749962619378349, "ce": 0.523275773758809}, {"step": 213, "kl": 0.1029091052445189, "ce": 0.486328189633976}, {"step": 214, "kl": 0.10317040546800313, "ce": 0.4768886464164856}, {"step": 215, "kl": 0.12834871987516533, "ce": 0.5409969941495496}, {"step": 216, "kl": 0.11510489434246915, "ce": 0.44594172399864507}, {"step": 217, "kl": 0.1299080759330809, "ce": 0.4884070206220512}, {"step": 218, "kl": 0.11884020736297894, "ce": 0.5291785369727778}, {"step": 219, "kl": 0.11562268188971905, "ce": 0.5452608018890536}, {"step": 220, "kl": 0.12612724262010572, "ce": 0.5142106662752769}, {"step": 221, "kl": 0.12289408049122509, "ce": 0.4328716315653425}, {"step": 222, "kl": 0.11757151230395341, "ce": 0.43130463338855257}, {"step": 223, "kl": 0.10334080825617285, "ce": 0.5122578943033583}, {"step": 224, "kl": 0.12206914886870943, "ce": 0.48016585908916914}, {"step": 225, "kl": 0.10276479430510427, "ce": 0.5408451810287824}, {"step": 226, "kl": 0.12259941083990934, "ce": 0.5128791942839034}, {"step": 227, "kl": 0.11658948893543081, "ce": 0.38802391867967523}, {"step": 228, "kl": 0.11336547785897996, "ce": 0.3708006048014537}, {"step": 229, "kl": 0.0864702116636733, "ce": 0.34796751833810036}, {"step": 230, "kl": 0.09705627535224015, "ce": 0.3850275631608634}, {"step": 231, "kl": 0.08485747026038293, "ce": 0.34339666140587977}, {"step": 232, "kl": 0.10014669439860693, "ce": 0.35484753968285737}, {"step": 233, "kl": 0.08783948200976996, "ce": 0.2902553566319033}, {"step": 234, "kl": 0.12749736266000866, "ce": 0.38334947011687537}, {"step": 235, "kl": 0.07188220804696405, "ce": 0.3354771873243748}, {"step": 236, "kl": 0.07682949160187759, "ce": 0.2871188209810684}, {"step": 237, "kl": 0.09411176059061666, "ce": 0.31314261285782485}, {"step": 238, "kl": 0.08445457420377356, "ce": 0.3063304949258028}, {"step": 239, "kl": 0.09578796783601777, "ce": 0.380362873182128}, {"step": 240, "kl": 0.09835680910541433, "ce": 0.36365126684803284}, {"step": 241, "kl": 0.08571506746663343, "ce": 0.38555473764687964}, {"step": 242, "kl": 0.09214766431696711, "ce": 0.32493009666298395}, {"step": 243, "kl": 0.09748593737232014, "ce": 0.35621237334620454}, {"step": 244, "kl": 0.08248047400932632, "ce": 0.35807064553263157}, {"step": 245, "kl": 0.10501878273164007, "ce": 0.35624183568739354}, {"step": 246, "kl": 0.11634833109282902, "ce": 0.378911341284011}, {"step": 247, "kl": 0.0901755446430812, "ce": 0.3367105013380054}, {"step": 248, "kl": 0.11093609100507862, "ce": 0.3196754480090336}, {"step": 249, "kl": 0.08987299798869208, "ce": 0.32815024375595825}, {"step": 250, "kl": 0.10179652355665482, "ce": 0.3427948595784756}, {"step": 251, "kl": 0.19097850607178438, "ce": 0.33022853862439927}, {"step": 252, "kl": 0.08721515653964994, "ce": 0.3485197408665765}, {"step": 253, "kl": 0.09093663377285788, "ce": 0.4826007403579413}, {"step": 254, "kl": 0.09538806916448944, "ce": 0.3839755639021183}, {"step": 255, "kl": 0.1108147552372622, "ce": 0.35363998613449377}, {"step": 256, "kl": 0.08321739466736792, "ce": 0.3446250669109145}, {"step": 257, "kl": 0.09560277354901761, "ce": 0.36940390074916546}, {"step": 258, "kl": 0.0843661237021412, "ce": 0.29060811732654634}, {"step": 259, "kl": 0.08152523796084477, "ce": 0.3032586220640487}, {"step": 260, "kl": 0.12702918048030332, "ce": 0.36624169972317283}, {"step": 261, "kl": 0.0988255219516493, "ce": 0.3217176146939429}, {"step": 262, "kl": 0.09642560375222975, "ce": 0.3743816694556094}, {"step": 263, "kl": 0.09064683589403844, "ce": 0.36649347075433386}, {"step": 264, "kl": 0.08656676113134687, "ce": 0.32008686185951374}, {"step": 265, "kl": 0.09292473140204432, "ce": 0.36349457338107777}, {"step": 266, "kl": 0.08250149480149632, "ce": 0.2843468120350706}, {"step": 267, "kl": 0.08452597733716362, "ce": 0.2667747602250114}, {"step": 268, "kl": 0.09812872685366716, "ce": 0.3578748116601247}, {"step": 269, "kl": 0.07644769393021875, "ce": 0.30037485715721834}, {"step": 270, "kl": 0.08426049883606196, "ce": 0.28431438529578434}, {"step": 271, "kl": 0.10124720154854114, "ce": 0.3516416331450508}, {"step": 272, "kl": 0.08973253626109884, "ce": 0.3236464488522851}, {"step": 273, "kl": 0.08062618375868388, "ce": 0.34070219194002765}, {"step": 274, "kl": 0.08489329426068618, "ce": 0.3244004440910255}, {"step": 275, "kl": 0.10247919542061619, "ce": 0.38169262191187314}, {"step": 276, "kl": 0.08459352019858433, "ce": 0.3110750716607444}, {"step": 277, "kl": 0.09654970273127514, "ce": 0.2957320159240275}, {"step": 278, "kl": 0.11005063041447302, "ce": 0.33390144112826897}, {"step": 279, "kl": 0.08273302467687459, "ce": 0.3226681113878084}, {"step": 280, "kl": 0.08936270815400324, "ce": 0.34855014657427946}, {"step": 281, "kl": 0.09274441908003477, "ce": 0.340921149422313}, {"step": 282, "kl": 0.07855741964053561, "ce": 0.28511816741041995}, {"step": 283, "kl": 0.08137161085303399, "ce": 0.2651399308336516}, {"step": 284, "kl": 0.09737788516709828, "ce": 0.3886900107953802}, {"step": 285, "kl": 0.08756793663232186, "ce": 0.33253901061162827}, {"step": 286, "kl": 0.08318960038415979, "ce": 0.3038342610937836}, {"step": 287, "kl": 0.09852877566944321, "ce": 0.34807626719889906}, {"step": 288, "kl": 0.10650190858200803, "ce": 0.34037659077704707}, {"step": 289, "kl": 0.13352201375049005, "ce": 0.3159703820131954}, {"step": 290, "kl": 0.08392039840049038, "ce": 0.3194706665711953}, {"step": 291, "kl": 0.09209616583304343, "ce": 0.33286449941249413}, {"step": 292, "kl": 0.0984765637305475, "ce": 0.3495992416688794}, {"step": 293, "kl": 0.08641841903754457, "ce": 0.2682139673330678}, {"step": 294, "kl": 0.09200734949308484, "ce": 0.32746262691191985}, {"step": 295, "kl": 0.08466025554480254, "ce": 0.2906051226796417}, {"step": 296, "kl": 0.10134327410364949, "ce": 0.3682718217897617}, {"step": 297, "kl": 0.09914355248025378, "ce": 0.3571643630921918}, {"step": 298, "kl": 0.10735196957100343, "ce": 0.3316670805491613}, {"step": 299, "kl": 0.09510976006933311, "ce": 0.2950624734950802}, {"step": 300, "kl": 0.08292867905824515, "ce": 0.32055612086661794}, {"step": 301, "kl": 0.11002827334579827, "ce": 0.3424565106115655}, {"step": 302, "kl": 0.08277851912835452, "ce": 0.34858207275390624}, {"step": 303, "kl": 0.12517387695193163, "ce": 0.363115043627859}, {"step": 304, "kl": 0.0881565113626391, "ce": 0.32434305837916183}, {"step": 305, "kl": 0.08842341380941028, "ce": 0.3650760670345568}, {"step": 306, "kl": 0.08437229980209751, "ce": 0.3519046857983491}, {"step": 307, "kl": 0.09927383976279144, "ce": 0.3530919043213683}, {"step": 308, "kl": 0.10330783365024297, "ce": 0.3126745305047832}, {"step": 309, "kl": 0.10328144790112426, "ce": 0.38445874222662046}, {"step": 310, "kl": 0.1076382508840441, "ce": 0.3668767947715734}, {"step": 311, "kl": 0.10363461978665725, "ce": 0.3532119012377312}, {"step": 312, "kl": 0.09477248795605372, "ce": 0.34654270077419463}, {"step": 313, "kl": 0.0990485077507993, "ce": 0.3336188085270746}, {"step": 314, "kl": 0.0886203362588597, "ce": 0.36624113729433655}, {"step": 315, "kl": 0.0917461903036112, "ce": 0.37268900259110016}, {"step": 316, "kl": 0.09103335167260557, "ce": 0.3733527371222379}, {"step": 317, "kl": 0.12933108563620435, "ce": 0.3992927359498065}, {"step": 318, "kl": 0.08078685044094226, "ce": 0.28159935600185365}, {"step": 319, "kl": 0.07425891372332495, "ce": 0.30372412686117806}, {"step": 320, "kl": 0.08310997147680832, "ce": 0.3089381769426367}, {"step": 321, "kl": 0.10718973904242424, "ce": 0.3190397206037167}, {"step": 322, "kl": 0.09386313600719373, "ce": 0.35340453447153547}, {"step": 323, "kl": 0.09936027541862145, "ce": 0.3167184112539743}, {"step": 324, "kl": 0.10603977968144389, "ce": 0.3370609235506725}, {"step": 325, "kl": 0.09649115450104664, "ce": 0.33053648898752597}, {"step": 326, "kl": 0.09167374710146774, "ce": 0.30690965649390445}, {"step": 327, "kl": 0.08985368589394303, "ce": 0.30537600823642785}, {"step": 328, "kl": 0.08493042071421009, "ce": 0.3342369672216011}, {"step": 329, "kl": 0.09290937159484601, "ce": 0.3278720912048082}, {"step": 330, "kl": 0.08719646048111958, "ce": 0.3265582961265487}, {"step": 331, "kl": 0.10380812216368018, "ce": 0.3116452467508157}, {"step": 332, "kl": 0.09543482167805858, "ce": 0.32182799233205883}, {"step": 333, "kl": 0.09383560998633579, "ce": 0.33690357748127525}, {"step": 334, "kl": 0.10777407124325453, "ce": 0.34440201706027396}, {"step": 335, "kl": 0.09589375814845312, "ce": 0.3349088748677921}, {"step": 336, "kl": 0.09282554258682013, "ce": 0.3534247889108432}, {"step": 337, "kl": 0.08685931098286918, "ce": 0.3207034355619103}, {"step": 338, "kl": 0.08929330419308545, "ce": 0.30993703994823385}, {"step": 339, "kl": 0.07867134160648781, "ce": 0.3501804299237415}, {"step": 340, "kl": 0.09883317777276224, "ce": 0.32450153870133647}, {"step": 341, "kl": 0.0761434062078714, "ce": 0.3032853271725224}, {"step": 342, "kl": 0.08826883329936933, "ce": 0.2914948704667333}, {"step": 343, "kl": 0.1016980223139446, "ce": 0.35433606891477376}, {"step": 344, "kl": 0.09344510207447608, "ce": 0.34076244727042676}, {"step": 345, "kl": 0.088029070978615, "ce": 0.32554018869384366}, {"step": 346, "kl": 0.09030783751410089, "ce": 0.32700489788520626}, {"step": 347, "kl": 0.09180288569040163, "ce": 0.346056541067655}, {"step": 348, "kl": 0.0923982687017328, "ce": 0.35391741349085765}, {"step": 349, "kl": 0.08622186471848634, "ce": 0.3183778919655069}, {"step": 350, "kl": 0.08775986755581663, "ce": 0.3542766753207432}, {"step": 351, "kl": 0.08723140522238396, "ce": 0.34769516227903635}, {"step": 352, "kl": 0.08694371678603238, "ce": 0.39599656797196353}, {"step": 353, "kl": 0.0964091382954455, "ce": 0.2795071246352175}, {"step": 354, "kl": 0.08765576490102034, "ce": 0.31141464170819677}, {"step": 355, "kl": 0.08047235525130486, "ce": 0.31361061852911243}, {"step": 356, "kl": 0.10154816735424015, "ce": 0.358023162446631}, {"step": 357, "kl": 0.07618946017470794, "ce": 0.2454904150495963}, {"step": 358, "kl": 0.10063220492839864, "ce": 0.4010042271572955}, {"step": 359, "kl": 0.09517940985748827, "ce": 0.3489937575911607}, {"step": 360, "kl": 0.08711900230215378, "ce": 0.32368350516844896}, {"step": 361, "kl": 0.10068646663124632, "ce": 0.3478668952678445}, {"step": 362, "kl": 0.07931384523688512, "ce": 0.30286566162109374}, {"step": 363, "kl": 0.08961639331109335, "ce": 0.33576371579492853}, {"step": 364, "kl": 0.08691685536664095, "ce": 0.3732027882680843}, {"step": 365, "kl": 0.08402943541114241, "ce": 0.36450958251953125}, {"step": 366, "kl": 0.10470895114990948, "ce": 0.30189445922851565}, {"step": 367, "kl": 0.09370698497847402, "ce": 0.33562687050706985}, {"step": 368, "kl": 0.07567859456131351, "ce": 0.33177087128331983}, {"step": 369, "kl": 0.09997566472777071, "ce": 0.44643532686455306}, {"step": 370, "kl": 0.0828227027678062, "ce": 0.32457555568686586}, {"step": 371, "kl": 0.08851120330509316, "ce": 0.3553932626449054}, {"step": 372, "kl": 0.08241230727392664, "ce": 0.31136461470743393}, {"step": 373, "kl": 0.13863748171779178, "ce": 0.31859838035895105}, {"step": 374, "kl": 0.09516439723429207, "ce": 0.3053656721838237}, {"step": 375, "kl": 0.10872056627346957, "ce": 0.3294112981234626}, {"step": 376, "kl": 0.08820884918884735, "ce": 0.2849656401052923}, {"step": 377, "kl": 0.09088973408487633, "ce": 0.3503973851003494}, {"step": 378, "kl": 0.09804420711974822, "ce": 0.3483380146942805}, {"step": 379, "kl": 0.0907266586044185, "ce": 0.37646052387641693}, {"step": 380, "kl": 0.0729539093027134, "ce": 0.24114665081515893}, {"step": 381, "kl": 0.08828340035602139, "ce": 0.3095833291812819}, {"step": 382, "kl": 0.11313552936501918, "ce": 0.36193437295224756}, {"step": 383, "kl": 0.1085339305757707, "ce": 0.37737955843578136}, {"step": 384, "kl": 0.08672349282092202, "ce": 0.307382148208645}, {"step": 385, "kl": 0.08701057045526887, "ce": 0.33806760421275384}, {"step": 386, "kl": 0.10274766568027352, "ce": 0.36162481671554253}, {"step": 387, "kl": 0.08138832304520752, "ce": 0.3735917497594168}, {"step": 388, "kl": 0.14315041184746674, "ce": 0.3800831957980319}, {"step": 389, "kl": 0.0861662004192928, "ce": 0.3419213522864125}, {"step": 390, "kl": 0.10365904657576033, "ce": 0.34256407981695136}, {"step": 391, "kl": 0.08807528932499323, "ce": 0.3481888275530561}, {"step": 392, "kl": 0.10086998398484413, "ce": 0.3725677016146438}, {"step": 393, "kl": 0.08208362537753654, "ce": 0.2859139154268965}, {"step": 394, "kl": 0.086171540573567, "ce": 0.3147166494805384}, {"step": 395, "kl": 0.09561329188151725, "ce": 0.33728387770245977}, {"step": 396, "kl": 0.09621078451240304, "ce": 0.33808467265462017}, {"step": 397, "kl": 0.08797577160851011, "ce": 0.28145398313894215}, {"step": 398, "kl": 0.0852165018825897, "ce": 0.34724305422729934}, {"step": 399, "kl": 0.09281914550941307, "ce": 0.3326975671521696}, {"step": 400, "kl": 0.08709957199863072, "ce": 0.2729059056554049}, {"step": 401, "kl": 0.08530706995270577, "ce": 0.38302564929694966}, {"step": 402, "kl": 0.08408810665604659, "ce": 0.27037358655264515}, {"step": 403, "kl": 0.09374020744204672, "ce": 0.3140663231487601}, {"step": 404, "kl": 0.08679872498547941, "ce": 0.3283612765163424}, {"step": 405, "kl": 0.09922208083322842, "ce": 0.36486439848150815}, {"step": 406, "kl": 0.09751721096768573, "ce": 0.3683685744104307}, {"step": 407, "kl": 0.09398771629425823, "ce": 0.28922114384010583}, {"step": 408, "kl": 0.08020839083537447, "ce": 0.3345338145756122}, {"step": 409, "kl": 0.07641579125585181, "ce": 0.31500411713922266}, {"step": 410, "kl": 0.08636399408656, "ce": 0.32433037106804197}, {"step": 411, "kl": 0.09128027821075436, "ce": 0.3597152086142825}, {"step": 412, "kl": 0.07539592802065721, "ce": 0.29519272365911475}, {"step": 413, "kl": 0.10122645345235055, "ce": 0.34305299264826306}, {"step": 414, "kl": 0.0931194843989328, "ce": 0.3452777178692911}, {"step": 415, "kl": 0.08297829009160054, "ce": 0.27664602832166485}, {"step": 416, "kl": 0.09473007337864371, "ce": 0.33732428399075887}, {"step": 417, "kl": 0.08840536791883216, "ce": 0.3218764221696425}, {"step": 418, "kl": 0.07333115683201855, "ce": 0.29556353846419103}, {"step": 419, "kl": 0.08543778325162314, "ce": 0.331722849293759}, {"step": 420, "kl": 0.095102778961326, "ce": 0.31279410939510277}, {"step": 421, "kl": 0.09342298626397318, "ce": 0.3034583113082452}, {"step": 422, "kl": 0.08671624897586644, "ce": 0.3623239768254775}, {"step": 423, "kl": 0.09282410596858529, "ce": 0.35732140958024894}, {"step": 424, "kl": 0.07912685800139765, "ce": 0.30772055850491553}, {"step": 425, "kl": 0.10199860113198554, "ce": 0.34972385297635145}, {"step": 426, "kl": 0.10332823897422183, "ce": 0.34412663688122386}, {"step": 427, "kl": 0.11507408460339673, "ce": 0.34732608548374144}, {"step": 428, "kl": 0.08943645042288895, "ce": 0.3352178466815966}, {"step": 429, "kl": 0.09598837866653126, "ce": 0.32501702472572175}, {"step": 430, "kl": 0.07783468727789658, "ce": 0.32051678559759034}, {"step": 431, "kl": 0.09687743342503329, "ce": 0.32828513526916503}, {"step": 432, "kl": 0.107367930949026, "ce": 0.3486971428169455}, {"step": 433, "kl": 0.08958954713782485, "ce": 0.32375718929694736}, {"step": 434, "kl": 0.08592067887127608, "ce": 0.3651128933022826}, {"step": 435, "kl": 0.07946587887860738, "ce": 0.35140374411999337}, {"step": 436, "kl": 0.08940417184341307, "ce": 0.306287761135432}, {"step": 437, "kl": 0.09075707821998896, "ce": 0.3300011554441517}, {"step": 438, "kl": 0.09190212303590785, "ce": 0.4247170742159665}, {"step": 439, "kl": 0.08902660848491403, "ce": 0.30606276196353543}, {"step": 440, "kl": 0.07376999132297882, "ce": 0.32606181731590855}, {"step": 441, "kl": 0.08834940124696693, "ce": 0.3636312039099007}, {"step": 442, "kl": 0.08252756885661904, "ce": 0.2578935793095285}, {"step": 443, "kl": 0.09209335084562771, "ce": 0.36635346310722}, {"step": 444, "kl": 0.07006276085051245, "ce": 0.27746621119681836}, {"step": 445, "kl": 0.09684710231253771, "ce": 0.3415611974069657}, {"step": 446, "kl": 0.12053460466795413, "ce": 0.33957415763313675}, {"step": 447, "kl": 0.11459754639357173, "ce": 0.3544771714097872}, {"step": 448, "kl": 0.09168224692099353, "ce": 0.30531919798862217}, {"step": 449, "kl": 0.09256706807414392, "ce": 0.3440982814575324}, {"step": 450, "kl": 0.09009113107505146, "ce": 0.3806915261285876}, {"step": 451, "kl": 0.0995817425404363, "ce": 0.35596741906378837}, {"step": 452, "kl": 0.07947110023065439, "ce": 0.3120886014828423}], "val": [{"step": 0, "math_kl": 0.17064335946551992, "math_ce": 0.8387106338797149, "code_kl": 0.22128492102940375, "code_ce": 0.36744983409730037}, {"step": 226, "math_kl": 0.1357702922933198, "math_ce": 0.540446689701753, "code_kl": 0.2462009959834339, "code_ce": 0.400443535566501}, {"step": 452, "math_kl": 0.13313634227681406, "math_ce": 0.5616576171145959, "code_kl": 0.24510269807345364, "code_ce": 0.3993136689672137}]}
 
 
seq_math_code/stage1_math/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8949a71a410c392ce243178e1b81dbf63b92cc45938a5f68a11a98be6d0ebc5c
3
- size 988097824
 
 
 
 
seq_math_code/stage2_code/config.json DELETED
@@ -1,57 +0,0 @@
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": 896,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 4864,
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
- ],
39
- "max_position_embeddings": 32768,
40
- "max_window_layers": 21,
41
- "model_type": "qwen2",
42
- "num_attention_heads": 14,
43
- "num_hidden_layers": 24,
44
- "num_key_value_heads": 2,
45
- "pad_token_id": null,
46
- "rms_norm_eps": 1e-06,
47
- "rope_parameters": {
48
- "rope_theta": 1000000.0,
49
- "rope_type": "default"
50
- },
51
- "sliding_window": null,
52
- "tie_word_embeddings": true,
53
- "transformers_version": "5.20.2",
54
- "use_cache": true,
55
- "use_sliding_window": false,
56
- "vocab_size": 151936
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seq_math_code/stage2_code/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.1,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "5.20.2"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
seq_math_code/stage2_code/log.json DELETED
@@ -1 +0,0 @@
1
- {"train": [{"step": 1, "kl": 0.2942881423062624, "ce": 0.45912709573121874}, {"step": 2, "kl": 0.2498457270679604, "ce": 0.3559412316742128}, {"step": 3, "kl": 0.239502315532323, "ce": 0.39118547196659903}, {"step": 4, "kl": 0.23581648234923616, "ce": 0.3597318666503506}, {"step": 5, "kl": 0.22017238504910228, "ce": 0.38592072812147404}, {"step": 6, "kl": 0.22808398440979463, "ce": 0.3526393298517655}, {"step": 7, "kl": 0.2469648986370429, "ce": 0.3469629657610271}, {"step": 8, "kl": 0.23462845055002712, "ce": 0.44165503343576273}, {"step": 9, "kl": 0.26667254028320314, "ce": 0.3040211332356272}, {"step": 10, "kl": 0.25892714323544813, "ce": 0.3308506032052933}, {"step": 11, "kl": 0.2006358187590424, "ce": 0.30646027659141967}, {"step": 12, "kl": 0.2192247925542867, "ce": 0.3516804163343484}, {"step": 13, "kl": 0.23483168089754197, "ce": 0.3311675396347495}, {"step": 14, "kl": 0.17795306483721965, "ce": 0.3079506926840924}, {"step": 15, "kl": 0.18964408538358807, "ce": 0.32306125590515833}, {"step": 16, "kl": 0.22718809510109184, "ce": 0.3227326632763921}, {"step": 17, "kl": 0.22247155565099147, "ce": 0.3302726527430966}, {"step": 18, "kl": 0.2216670651174934, "ce": 0.30534989246932154}, {"step": 19, "kl": 0.20799054660647273, "ce": 0.3005198338382559}, {"step": 20, "kl": 0.19366294536658113, "ce": 0.28584075023354044}, {"step": 21, "kl": 0.1995479078584283, "ce": 0.3235913089080402}, {"step": 22, "kl": 0.2339519461163543, "ce": 0.3398250712511941}, {"step": 23, "kl": 0.22323922565894713, "ce": 0.33620200297309555}, {"step": 24, "kl": 0.21052763078740455, "ce": 0.2923483505007396}, {"step": 25, "kl": 0.20092651265663458, "ce": 0.2933901601886957}, {"step": 26, "kl": 0.20442843672379615, "ce": 0.3122937430307664}, {"step": 27, "kl": 0.25593469672072255, "ce": 0.3453954409246575}, {"step": 28, "kl": 0.2181364255692811, "ce": 0.3825252198617559}, {"step": 29, "kl": 0.20249582955921291, "ce": 0.2918620316147033}, {"step": 30, "kl": 0.19935939471720276, "ce": 0.35073329924655505}, {"step": 31, "kl": 0.22889219311720652, "ce": 0.3620610726597797}, {"step": 32, "kl": 0.20034884804297204, "ce": 0.2807414081658157}, {"step": 33, "kl": 0.21095967640290544, "ce": 0.344075267520103}, {"step": 34, "kl": 0.1928335718270447, "ce": 0.3316920479050974}, {"step": 35, "kl": 0.18282854950333075, "ce": 0.33644997847181723}, {"step": 36, "kl": 0.20199708693306945, "ce": 0.3216475320655539}, {"step": 37, "kl": 0.16975309933848093, "ce": 0.287461809420756}, {"step": 38, "kl": 0.20368634329133833, "ce": 0.34799581231294974}, {"step": 39, "kl": 0.24068942015782774, "ce": 0.35933722227431186}, {"step": 40, "kl": 0.1968981996775735, "ce": 0.2746492626430752}, {"step": 41, "kl": 0.23166831884821132, "ce": 0.36957816958551476}, {"step": 42, "kl": 0.1866440659922823, "ce": 0.24472807048721334}, {"step": 43, "kl": 0.1679754817281934, "ce": 0.29321577888534106}, {"step": 44, "kl": 0.2022440787801797, "ce": 0.32570514520847804}, {"step": 45, "kl": 0.18542116329343108, "ce": 0.3242652950802365}, {"step": 46, "kl": 0.1738602184834569, "ce": 0.2706419633427559}, {"step": 47, "kl": 0.17826821166754092, "ce": 0.2543074914936764}, {"step": 48, "kl": 0.21384360710640152, "ce": 0.3616511126382136}, {"step": 49, "kl": 0.17304418887599368, "ce": 0.30992024248763517}, {"step": 50, "kl": 0.17468995190975464, "ce": 0.30460872878116446}, {"step": 51, "kl": 0.1760391424807886, "ce": 0.24858467172600004}, {"step": 52, "kl": 0.18785735107958315, "ce": 0.3384899375076693}, {"step": 53, "kl": 0.20186900603666105, "ce": 0.3421944962978476}, {"step": 54, "kl": 0.18001963287754785, "ce": 0.25911618938465564}, {"step": 55, "kl": 0.19998378939989614, "ce": 0.3118209698764044}, {"step": 56, "kl": 0.17779265254376883, "ce": 0.3015620410916588}, {"step": 57, "kl": 0.2043360318830565, "ce": 0.33499351423369933}, {"step": 58, "kl": 0.19704710012590246, "ce": 0.318745528239919}, {"step": 59, "kl": 0.2084072983561886, "ce": 0.34458907642279396}, {"step": 60, "kl": 0.15123598994320012, "ce": 0.24370939673868125}, {"step": 61, "kl": 0.20828148296365204, "ce": 0.30764570858369433}, {"step": 62, "kl": 0.18453564643859863, "ce": 0.3146812456817075}, {"step": 63, "kl": 0.1968836493318232, "ce": 0.2772528713274717}, {"step": 64, "kl": 0.18869649911228614, "ce": 0.3294005201570615}, {"step": 65, "kl": 0.1838330007956474, "ce": 0.3022898744977821}, {"step": 66, "kl": 0.20232711963015373, "ce": 0.2903926077084323}, {"step": 67, "kl": 0.18267935946664896, "ce": 0.2623489868524479}, {"step": 68, "kl": 0.17113537561325798, "ce": 0.36926424353326165}, {"step": 69, "kl": 0.19672705363119025, "ce": 0.26279318178956274}, {"step": 70, "kl": 0.18671492510191073, "ce": 0.2926934053039212}, {"step": 71, "kl": 0.21026273925652667, "ce": 0.3082284923205465}, {"step": 72, "kl": 0.1923200477712103, "ce": 0.3396456433559272}, {"step": 73, "kl": 0.1770172466223443, "ce": 0.3268544586443696}, {"step": 74, "kl": 0.18654820424458485, "ce": 0.3057988532473811}, {"step": 75, "kl": 0.20219324276716, "ce": 0.31441253638575484}, {"step": 76, "kl": 0.14559229478555513, "ce": 0.2426848398889452}, {"step": 77, "kl": 0.18434250826632156, "ce": 0.2697735400255197}, {"step": 78, "kl": 0.20074174972414394, "ce": 0.3250701869524412}, {"step": 79, "kl": 0.223855502121236, "ce": 0.35632169097560307}, {"step": 80, "kl": 0.15833303180189445, "ce": 0.2810800020472184}, {"step": 81, "kl": 0.2002077955756501, "ce": 0.3649411755938863}, {"step": 82, "kl": 0.1981715101333232, "ce": 0.29330323401578345}, {"step": 83, "kl": 0.18475210028986946, "ce": 0.2975572848634144}, {"step": 84, "kl": 0.17189913740682713, "ce": 0.28954856872558593}, {"step": 85, "kl": 0.16623350487014235, "ce": 0.36021768461052495}, {"step": 86, "kl": 0.2080011907755659, "ce": 0.3008128861338931}, {"step": 87, "kl": 0.19072531673886362, "ce": 0.33577034866984595}, {"step": 88, "kl": 0.17357487682250214, "ce": 0.29017178448379666}, {"step": 89, "kl": 0.16737464875853292, "ce": 0.26413126955750166}, {"step": 90, "kl": 0.20422418044908397, "ce": 0.2572241213571353}, {"step": 91, "kl": 0.18397602672026225, "ce": 0.30472974609910397}, {"step": 92, "kl": 0.16997077205393574, "ce": 0.28051646870321684}, {"step": 93, "kl": 0.18259461851208547, "ce": 0.2987223842687774}, {"step": 94, "kl": 0.15866514072296725, "ce": 0.2801934219778179}, {"step": 95, "kl": 0.1698844897230483, "ce": 0.2901383216762029}, {"step": 96, "kl": 0.16745804613696494, "ce": 0.2782315153627728}, {"step": 97, "kl": 0.17823760200205102, "ce": 0.3355757252507995}, {"step": 98, "kl": 0.19501223309433097, "ce": 0.26101148120202255}, {"step": 99, "kl": 0.18279269433790638, "ce": 0.29200660059735434}, {"step": 100, "kl": 0.15427630007061055, "ce": 0.2486157462065679}, {"step": 101, "kl": 0.1651940953188199, "ce": 0.2691344339339459}, {"step": 102, "kl": 0.1404113914913527, "ce": 0.2589645442641571}, {"step": 103, "kl": 0.1625903862870543, "ce": 0.2671843770369905}, {"step": 104, "kl": 0.17342590759007676, "ce": 0.2857227646457693}, {"step": 105, "kl": 0.1596164929675546, "ce": 0.27663007163124703}, {"step": 106, "kl": 0.14658673133746075, "ce": 0.2655600539247476}, {"step": 107, "kl": 0.171162233142359, "ce": 0.3187402364570959}, {"step": 108, "kl": 0.19866924515004236, "ce": 0.3363720637337428}, {"step": 109, "kl": 0.20339741408163664, "ce": 0.2796784008496887}, {"step": 110, "kl": 0.18430043737596252, "ce": 0.3630029559852126}, {"step": 111, "kl": 0.1562478504167635, "ce": 0.26469460322476146}, {"step": 112, "kl": 0.18886357745894317, "ce": 0.3667596202756503}, {"step": 113, "kl": 0.18745260963107402, "ce": 0.3280503606418552}, {"step": 114, "kl": 0.19979609652389532, "ce": 0.3253284573359247}, {"step": 115, "kl": 0.19258604579799166, "ce": 0.3692918716376362}, {"step": 116, "kl": 0.191772473349074, "ce": 0.2873147398369498}, {"step": 117, "kl": 0.178505845117889, "ce": 0.28506685077019456}, {"step": 118, "kl": 0.16716650014888787, "ce": 0.2705052968826525}, {"step": 119, "kl": 0.17879735453401185, "ce": 0.282942099119662}, {"step": 120, "kl": 0.16489740638276282, "ce": 0.2809482611109113}, {"step": 121, "kl": 0.1772127109759988, "ce": 0.2952376053505819}, {"step": 122, "kl": 0.21058671674857046, "ce": 0.34652699360094574}, {"step": 123, "kl": 0.18922250020353984, "ce": 0.34569484513738885}, {"step": 124, "kl": 0.1571246484830494, "ce": 0.31088914670419554}, {"step": 125, "kl": 0.2237123442337652, "ce": 0.3158295737679201}, {"step": 126, "kl": 0.1966710287891358, "ce": 0.3018271976047092}, {"step": 127, "kl": 0.13182672230219933, "ce": 0.2187597556044107}, {"step": 128, "kl": 0.15234694440889682, "ce": 0.3162862008877015}, {"step": 129, "kl": 0.18040719274129846, "ce": 0.30197640689643657}, {"step": 130, "kl": 0.1530740915037698, "ce": 0.2811449139869525}, {"step": 131, "kl": 0.18198864316751062, "ce": 0.2613570626583212}, {"step": 132, "kl": 0.15389787666274748, "ce": 0.28094262553167126}, {"step": 133, "kl": 0.19022904751639286, "ce": 0.3099281563057198}, {"step": 134, "kl": 0.17056382553460966, "ce": 0.27348490629106403}, {"step": 135, "kl": 0.1329748956232123, "ce": 0.2565693681568018}, {"step": 136, "kl": 0.1739778589772793, "ce": 0.27277142741802946}, {"step": 137, "kl": 0.15222364725713347, "ce": 0.2484849122868795}, {"step": 138, "kl": 0.1785919039735399, "ce": 0.2712352324019225}, {"step": 139, "kl": 0.17977039166281228, "ce": 0.25740153908555236}, {"step": 140, "kl": 0.17399773424487724, "ce": 0.2682691891005806}, {"step": 141, "kl": 0.1772996512757475, "ce": 0.28201977163732206}, {"step": 142, "kl": 0.1762981170393602, "ce": 0.2426461083165177}, {"step": 143, "kl": 0.155532461086483, "ce": 0.2608602273252589}, {"step": 144, "kl": 0.16916911957382402, "ce": 0.2658732911202044}, {"step": 145, "kl": 0.15976992836686232, "ce": 0.29899969509895646}, {"step": 146, "kl": 0.18903355338722524, "ce": 0.3161215117800784}, {"step": 147, "kl": 0.14119075253913116, "ce": 0.23243799335078186}, {"step": 148, "kl": 0.1883910112300529, "ce": 0.33630100117091816}, {"step": 149, "kl": 0.20315348289825103, "ce": 0.33121910758160056}, {"step": 150, "kl": 0.16257227624586337, "ce": 0.28558162962350975}, {"step": 151, "kl": 0.16517854846313665, "ce": 0.3037801078482385}, {"step": 152, "kl": 0.17617875237935052, "ce": 0.24578790456616048}, {"step": 153, "kl": 0.1852911712440775, "ce": 0.26606384956076}, {"step": 154, "kl": 0.15532887555843078, "ce": 0.25150057035703544}, {"step": 155, "kl": 0.13947932131667315, "ce": 0.25346153813719857}, {"step": 156, "kl": 0.14999092100943628, "ce": 0.31334928956205005}, {"step": 157, "kl": 0.1637995236753567, "ce": 0.2909349298801552}, {"step": 158, "kl": 0.16340882062188777, "ce": 0.30969340728004635}, {"step": 159, "kl": 0.14818460221668545, "ce": 0.29033232522667}, {"step": 160, "kl": 0.19312072263767635, "ce": 0.3048777445470345}, {"step": 161, "kl": 0.1880823762279205, "ce": 0.31279192865521754}, {"step": 162, "kl": 0.15141931569801187, "ce": 0.2889524347135813}, {"step": 163, "kl": 0.20727696634936743, "ce": 0.31873561324053223}, {"step": 164, "kl": 0.1748611743906428, "ce": 0.28592142849841395}, {"step": 165, "kl": 0.1570766678333792, "ce": 0.2593956823556475}, {"step": 166, "kl": 0.16134480881073632, "ce": 0.2967586508707351}, {"step": 167, "kl": 0.1719023906411161, "ce": 0.25148641266356053}, {"step": 168, "kl": 0.14954091564438046, "ce": 0.28782887724614925}, {"step": 169, "kl": 0.14850826128367645, "ce": 0.2550925262004969}, {"step": 170, "kl": 0.19537847740934197, "ce": 0.3007689356284046}, {"step": 171, "kl": 0.15845641765030052, "ce": 0.259279463108769}, {"step": 172, "kl": 0.1769330061777906, "ce": 0.29618148506461806}, {"step": 173, "kl": 0.19431903837726938, "ce": 0.29067664129083803}, {"step": 174, "kl": 0.17662968236988455, "ce": 0.2940860711611234}, {"step": 175, "kl": 0.1498061805345211, "ce": 0.25416944661271684}, {"step": 176, "kl": 0.15143366479993464, "ce": 0.22655610513532815}, {"step": 177, "kl": 0.13866267095099327, "ce": 0.245873449520748}, {"step": 178, "kl": 0.16608160800971558, "ce": 0.31189672012775266}, {"step": 179, "kl": 0.18087312088000687, "ce": 0.27934024847795674}, {"step": 180, "kl": 0.16936565763743397, "ce": 0.3074775864917431}, {"step": 181, "kl": 0.16259314779104372, "ce": 0.3269340183687125}, {"step": 182, "kl": 0.17233790972979712, "ce": 0.2847726276419671}, {"step": 183, "kl": 0.1776429811746618, "ce": 0.3494542930351854}, {"step": 184, "kl": 0.1499674758749835, "ce": 0.28510127072217983}, {"step": 185, "kl": 0.16933627674976984, "ce": 0.3091695337395713}, {"step": 186, "kl": 0.1680817351504575, "ce": 0.28888292792889714}, {"step": 187, "kl": 0.20636310366052008, "ce": 0.3281631173694871}, {"step": 188, "kl": 0.19126136995818682, "ce": 0.34867681894037456}, {"step": 189, "kl": 0.12825185489876156, "ce": 0.24834620744924513}, {"step": 190, "kl": 0.17003606430071683, "ce": 0.31011236050217883}, {"step": 191, "kl": 0.17708983604018855, "ce": 0.31241946790777325}, {"step": 192, "kl": 0.19144515814194824, "ce": 0.361418467883248}, {"step": 193, "kl": 0.1557454693831825, "ce": 0.28659285340128066}, {"step": 194, "kl": 0.15960687478036165, "ce": 0.23686028017176455}, {"step": 195, "kl": 0.18451036738549603, "ce": 0.32734771069185237}, {"step": 196, "kl": 0.15778564798840156, "ce": 0.2612321887779882}, {"step": 197, "kl": 0.17409566291435108, "ce": 0.25918821767274186}, {"step": 198, "kl": 0.15468427247306038, "ce": 0.2810806219257904}, {"step": 199, "kl": 0.1559658264083782, "ce": 0.24533395233525554}, {"step": 200, "kl": 0.17714612499164167, "ce": 0.2890450516380552}, {"step": 201, "kl": 0.172537946633392, "ce": 0.3345418793761325}, {"step": 202, "kl": 0.12867032632349662, "ce": 0.28892208664760943}, {"step": 203, "kl": 0.14723297411005865, "ce": 0.260622093439954}, {"step": 204, "kl": 0.17714642032201455, "ce": 0.3351135838658652}, {"step": 205, "kl": 0.15468871837483936, "ce": 0.24520115311771695}, {"step": 206, "kl": 0.18804568063749894, "ce": 0.3262886277553392}, {"step": 207, "kl": 0.16359689060544658, "ce": 0.31787913750783825}, {"step": 208, "kl": 0.1934939589012753, "ce": 0.30968029728139423}, {"step": 209, "kl": 0.15857953067031205, "ce": 0.28172904635788104}, {"step": 210, "kl": 0.12621641356681068, "ce": 0.2285844704812947}, {"step": 211, "kl": 0.14622443906466168, "ce": 0.23560684452464353}, {"step": 212, "kl": 0.12998625127735647, "ce": 0.2187544725369308}, {"step": 213, "kl": 0.15576651222364515, "ce": 0.22907518268397328}, {"step": 214, "kl": 0.21864916904773551, "ce": 0.3243888109529093}, {"step": 215, "kl": 0.1797850975246267, "ce": 0.2926350299792272}, {"step": 216, "kl": 0.15723976224449857, "ce": 0.30438685893549955}, {"step": 217, "kl": 0.18179358708774965, "ce": 0.31380616602163053}, {"step": 218, "kl": 0.15197864595328742, "ce": 0.27718226478361707}, {"step": 219, "kl": 0.14037945658470866, "ce": 0.2497818166450998}, {"step": 220, "kl": 0.17948976899356772, "ce": 0.28330442256067284}, {"step": 221, "kl": 0.14796320762812998, "ce": 0.25683891054454155}, {"step": 222, "kl": 0.16624579051062882, "ce": 0.3560333150946136}, {"step": 223, "kl": 0.15509096367491615, "ce": 0.26728944109550473}, {"step": 224, "kl": 0.15155609299631287, "ce": 0.32493930179412633}, {"step": 225, "kl": 0.14027248483012178, "ce": 0.319578301044672}, {"step": 226, "kl": 0.14978655848232594, "ce": 0.28273246763350396}, {"step": 227, "kl": 0.17441898072262163, "ce": 0.24729547227659335}, {"step": 228, "kl": 0.1385600083342562, "ce": 0.22676707092878218}, {"step": 229, "kl": 0.12909638987996402, "ce": 0.1868830060780938}, {"step": 230, "kl": 0.12463748092037169, "ce": 0.2300934381978228}, {"step": 231, "kl": 0.14075610092956956, "ce": 0.2305890247546108}, {"step": 232, "kl": 0.13270760518553212, "ce": 0.21950639517283138}, {"step": 233, "kl": 0.12381818288803755, "ce": 0.19115930500989345}, {"step": 234, "kl": 0.11493500883277205, "ce": 0.2097463642383285}, {"step": 235, "kl": 0.1319676169319456, "ce": 0.23296170727165502}, {"step": 236, "kl": 0.10147031827482367, "ce": 0.1953299149222996}, {"step": 237, "kl": 0.10825009111949638, "ce": 0.2036683469437206}, {"step": 238, "kl": 0.141126109602479, "ce": 0.2031902537073911}, {"step": 239, "kl": 0.13567360220448488, "ce": 0.18506932620084357}, {"step": 240, "kl": 0.11112574669270238, "ce": 0.20918263626834271}, {"step": 241, "kl": 0.12460810723756205, "ce": 0.19743012187443798}, {"step": 242, "kl": 0.10442350210732972, "ce": 0.21160946023673982}, {"step": 243, "kl": 0.14752405976102112, "ce": 0.2549802719131958}, {"step": 244, "kl": 0.13391632946480841, "ce": 0.20571271951187756}, {"step": 245, "kl": 0.11213520808212449, "ce": 0.18730994031151496}, {"step": 246, "kl": 0.09852003917014174, "ce": 0.2075325292547723}, {"step": 247, "kl": 0.10261091337144962, "ce": 0.21722587025653695}, {"step": 248, "kl": 0.09951259247774404, "ce": 0.20087814652563096}, {"step": 249, "kl": 0.11133122520938205, "ce": 0.19509306808997845}, {"step": 250, "kl": 0.12079461843139237, "ce": 0.22054501387113568}, {"step": 251, "kl": 0.13767425328584254, "ce": 0.19376351723987917}, {"step": 252, "kl": 0.10200882735651806, "ce": 0.19323668225560245}, {"step": 253, "kl": 0.11564404911445318, "ce": 0.18496093486803983}, {"step": 254, "kl": 0.12590034036075368, "ce": 0.22907119831710893}, {"step": 255, "kl": 0.12631040651297032, "ce": 0.24303233076256578}, {"step": 256, "kl": 0.12722325619467986, "ce": 0.21635334341922083}, {"step": 257, "kl": 0.10440392064348457, "ce": 0.16914213310551088}, {"step": 258, "kl": 0.12381844477686296, "ce": 0.18840598387035082}, {"step": 259, "kl": 0.11638158734861787, "ce": 0.21478969203194048}, {"step": 260, "kl": 0.1207967203234206, "ce": 0.19257151238828263}, {"step": 261, "kl": 0.13083156176636834, "ce": 0.2544252926123876}, {"step": 262, "kl": 0.12044770273418937, "ce": 0.1984685215123025}, {"step": 263, "kl": 0.1314062272996125, "ce": 0.20870736943802598}, {"step": 264, "kl": 0.13048575212458247, "ce": 0.19484535741605397}, {"step": 265, "kl": 0.11366424492488048, "ce": 0.2253375095523152}, {"step": 266, "kl": 0.12482578246760606, "ce": 0.2152367742064572}, {"step": 267, "kl": 0.10501524841963698, "ce": 0.18433910916718732}, {"step": 268, "kl": 0.11316214713685999, "ce": 0.21573518605708164}, {"step": 269, "kl": 0.1041958424414283, "ce": 0.20713623263537698}, {"step": 270, "kl": 0.14649958273544034, "ce": 0.19333254677908762}, {"step": 271, "kl": 0.10416016690276532, "ce": 0.177592169502492}, {"step": 272, "kl": 0.13637607681232447, "ce": 0.2610883391572631}, {"step": 273, "kl": 0.11564692949455574, "ce": 0.20339123312427917}, {"step": 274, "kl": 0.13595869487252166, "ce": 0.1961556164401143}, {"step": 275, "kl": 0.10585820356450984, "ce": 0.19563858348249621}, {"step": 276, "kl": 0.1196164057557616, "ce": 0.23240424067018764}, {"step": 277, "kl": 0.10198562204445066, "ce": 0.19738611744742016}, {"step": 278, "kl": 0.11175044404796501, "ce": 0.1930562542687833}, {"step": 279, "kl": 0.12706209047775985, "ce": 0.18852036541433326}, {"step": 280, "kl": 0.10398786352653, "ce": 0.21777808251732414}, {"step": 281, "kl": 0.1062711587595145, "ce": 0.21466096887515373}, {"step": 282, "kl": 0.14455916303428124, "ce": 0.23562680486735776}, {"step": 283, "kl": 0.1362503655713657, "ce": 0.2197408104762216}, {"step": 284, "kl": 0.11139443956560612, "ce": 0.21908741563247888}, {"step": 285, "kl": 0.1328737929799985, "ce": 0.21864680544053947}, {"step": 286, "kl": 0.11187441480421267, "ce": 0.21685027995522885}, {"step": 287, "kl": 0.12940201107861665, "ce": 0.23392407633463547}, {"step": 288, "kl": 0.10804374142910572, "ce": 0.18703001063707295}, {"step": 289, "kl": 0.12331051259549314, "ce": 0.21455528302980914}, {"step": 290, "kl": 0.10389707916325769, "ce": 0.19290334110322682}, {"step": 291, "kl": 0.10442934875135068, "ce": 0.18091574067735486}, {"step": 292, "kl": 0.11616579220476297, "ce": 0.20430631319123116}, {"step": 293, "kl": 0.128912489534004, "ce": 0.18593569722796752}, {"step": 294, "kl": 0.13365435047389385, "ce": 0.2154040333641636}, {"step": 295, "kl": 0.09499672032356929, "ce": 0.20230482093583174}, {"step": 296, "kl": 0.13729611689402998, "ce": 0.29931780326864943}, {"step": 297, "kl": 0.10228177439853249, "ce": 0.2120750640690443}, {"step": 298, "kl": 0.13358399481697075, "ce": 0.22044716389755287}, {"step": 299, "kl": 0.09645562721769851, "ce": 0.20600086176359944}, {"step": 300, "kl": 0.13129887596463488, "ce": 0.20767367300200815}, {"step": 301, "kl": 0.10302115205982447, "ce": 0.19207207189464778}, {"step": 302, "kl": 0.10534303808976911, "ce": 0.17593116126890124}, {"step": 303, "kl": 0.11684840547876171, "ce": 0.21268469675804041}, {"step": 304, "kl": 0.10383956254878861, "ce": 0.1696094574715927}, {"step": 305, "kl": 0.10215492685096621, "ce": 0.17620057602451272}, {"step": 306, "kl": 0.12447571028534055, "ce": 0.17499315323024947}, {"step": 307, "kl": 0.12442578792132811, "ce": 0.21044157024375898}, {"step": 308, "kl": 0.128300742167543, "ce": 0.21204906209090235}, {"step": 309, "kl": 0.08849254373386414, "ce": 0.20638344229244796}, {"step": 310, "kl": 0.12001367851357939, "ce": 0.21108126055387103}, {"step": 311, "kl": 0.11571406923467711, "ce": 0.19788600129493158}, {"step": 312, "kl": 0.11394749866073427, "ce": 0.17338485471480594}, {"step": 313, "kl": 0.09746216232778168, "ce": 0.19336257363231388}, {"step": 314, "kl": 0.11133645143299413, "ce": 0.1794978317408636}, {"step": 315, "kl": 0.13307997479600897, "ce": 0.20992096750166828}, {"step": 316, "kl": 0.12881776355504804, "ce": 0.20259036631719302}, {"step": 317, "kl": 0.10651590981785905, "ce": 0.19572664325441452}, {"step": 318, "kl": 0.12930772335678123, "ce": 0.2029745550338007}, {"step": 319, "kl": 0.11916430348002696, "ce": 0.20583787268020687}, {"step": 320, "kl": 0.10608592414855958, "ce": 0.18439377092221146}, {"step": 321, "kl": 0.10333989636768534, "ce": 0.2053719362793568}, {"step": 322, "kl": 0.126514736996623, "ce": 0.2638567688627052}, {"step": 323, "kl": 0.12585750219661954, "ce": 0.2266603710057525}, {"step": 324, "kl": 0.10606893378583242, "ce": 0.18519655393501405}, {"step": 325, "kl": 0.09593516238852415, "ce": 0.20232279915839319}, {"step": 326, "kl": 0.12997901328685385, "ce": 0.2337811544471707}, {"step": 327, "kl": 0.1135031526436443, "ce": 0.2208277068577143}, {"step": 328, "kl": 0.11278415471439912, "ce": 0.19944304779186453}, {"step": 329, "kl": 0.11839284355332047, "ce": 0.18963510116990692}, {"step": 330, "kl": 0.12015649931336422, "ce": 0.18685520414262274}, {"step": 331, "kl": 0.14246960661074168, "ce": 0.24633853629051303}, {"step": 332, "kl": 0.11719578761337658, "ce": 0.2505505623662332}, {"step": 333, "kl": 0.10492617541391254, "ce": 0.16677189004470425}, {"step": 334, "kl": 0.11717966943712885, "ce": 0.22675986636468695}, {"step": 335, "kl": 0.09008562431710623, "ce": 0.20015837569108513}, {"step": 336, "kl": 0.11763119136752243, "ce": 0.19773666921819794}, {"step": 337, "kl": 0.10012591236833346, "ce": 0.15547489794860053}, {"step": 338, "kl": 0.11544903479386705, "ce": 0.20711777125297742}, {"step": 339, "kl": 0.11362317034662986, "ce": 0.21900054788349965}, {"step": 340, "kl": 0.09633989840350422, "ce": 0.17023441701883107}, {"step": 341, "kl": 0.13626560303270163, "ce": 0.19425205383017424}, {"step": 342, "kl": 0.11884088529582787, "ce": 0.20060734131679017}, {"step": 343, "kl": 0.11868175907313469, "ce": 0.19601744784037745}, {"step": 344, "kl": 0.1301890887091439, "ce": 0.1972151250509957}, {"step": 345, "kl": 0.10903938370937917, "ce": 0.17762246502601048}, {"step": 346, "kl": 0.10854771978803761, "ce": 0.19655391732301494}, {"step": 347, "kl": 0.11275522498361391, "ce": 0.1791994201404422}, {"step": 348, "kl": 0.1076085938856393, "ce": 0.18070895943362986}, {"step": 349, "kl": 0.11186850799861675, "ce": 0.1930819216316551}, {"step": 350, "kl": 0.09944753998567425, "ce": 0.19653721114269013}, {"step": 351, "kl": 0.09971236725146297, "ce": 0.2070856841605681}, {"step": 352, "kl": 0.12617354455844898, "ce": 0.2042969654293122}, {"step": 353, "kl": 0.11384842411021312, "ce": 0.20538443310160032}, {"step": 354, "kl": 0.11004768466553747, "ce": 0.20287028543644445}, {"step": 355, "kl": 0.13839290126688503, "ce": 0.22207580427777912}, {"step": 356, "kl": 0.12814623051176202, "ce": 0.2446663805709262}, {"step": 357, "kl": 0.11995560146680709, "ce": 0.23617517919714812}, {"step": 358, "kl": 0.10873049387861766, "ce": 0.19150825414236133}, {"step": 359, "kl": 0.11708564537407903, "ce": 0.2193987077536042}, {"step": 360, "kl": 0.0961231199986679, "ce": 0.19067695111898925}, {"step": 361, "kl": 0.15275985360076139, "ce": 0.2630927695391753}, {"step": 362, "kl": 0.12694165658920023, "ce": 0.2295261123060514}, {"step": 363, "kl": 0.09068168855459066, "ce": 0.1825664527434155}, {"step": 364, "kl": 0.10903889650253672, "ce": 0.19645823032323984}, {"step": 365, "kl": 0.09145838866716388, "ce": 0.1925165637699977}, {"step": 366, "kl": 0.09807068899582914, "ce": 0.21677685246435216}, {"step": 367, "kl": 0.11357532301657919, "ce": 0.1607245005464217}, {"step": 368, "kl": 0.11324115064036978, "ce": 0.16826862102647328}, {"step": 369, "kl": 0.10601645622601566, "ce": 0.18587913006635437}, {"step": 370, "kl": 0.12439023638310363, "ce": 0.1926460653628241}, {"step": 371, "kl": 0.1074171112480378, "ce": 0.16761460563627747}, {"step": 372, "kl": 0.12195067385352015, "ce": 0.20549269561910452}, {"step": 373, "kl": 0.12047288735394479, "ce": 0.22878044631880554}, {"step": 374, "kl": 0.132952006321454, "ce": 0.1887433098697927}, {"step": 375, "kl": 0.11024907117125757, "ce": 0.20910548095703124}, {"step": 376, "kl": 0.12309365606148269, "ce": 0.22409939819944352}, {"step": 377, "kl": 0.11699590141741474, "ce": 0.2286400024616333}, {"step": 378, "kl": 0.13581243151767236, "ce": 0.27645909387522144}, {"step": 379, "kl": 0.11532186497327802, "ce": 0.2038697618002156}, {"step": 380, "kl": 0.0923943845911179, "ce": 0.1886240895589193}, {"step": 381, "kl": 0.10675498065968571, "ce": 0.1696746175574027}, {"step": 382, "kl": 0.11676613347385505, "ce": 0.18980494121577116}, {"step": 383, "kl": 0.10983029636952883, "ce": 0.22567728508481819}, {"step": 384, "kl": 0.1572076129660366, "ce": 0.212025082160416}, {"step": 385, "kl": 0.10568274639199278, "ce": 0.2164543409741061}, {"step": 386, "kl": 0.12194988437370355, "ce": 0.17396013954422787}, {"step": 387, "kl": 0.09251761841063469, "ce": 0.16470842351315504}, {"step": 388, "kl": 0.10917548391817028, "ce": 0.18937837231773505}, {"step": 389, "kl": 0.10432916180189776, "ce": 0.18152202871687184}, {"step": 390, "kl": 0.1174283000722803, "ce": 0.1910395865808587}, {"step": 391, "kl": 0.12393044726240321, "ce": 0.2925696523565995}, {"step": 392, "kl": 0.1231957774854395, "ce": 0.21022592737023202}, {"step": 393, "kl": 0.09723254489034323, "ce": 0.19104496915984065}, {"step": 394, "kl": 0.12542038635526975, "ce": 0.24565146857225745}, {"step": 395, "kl": 0.11170888059226725, "ce": 0.20768397902384003}, {"step": 396, "kl": 0.13165906759408805, "ce": 0.21070252695391253}, {"step": 397, "kl": 0.09547399701414981, "ce": 0.18742248195963854}, {"step": 398, "kl": 0.08935392000206746, "ce": 0.2058113894556366}, {"step": 399, "kl": 0.12596077509490458, "ce": 0.17724007837450437}, {"step": 400, "kl": 0.0984111258232134, "ce": 0.1757323160204281}, {"step": 401, "kl": 0.1198215080119508, "ce": 0.2031427626581917}, {"step": 402, "kl": 0.09519671785098695, "ce": 0.19785614987637135}, {"step": 403, "kl": 0.1036944338174261, "ce": 0.19413500334958395}, {"step": 404, "kl": 0.11629848538774004, "ce": 0.18516420442695958}, {"step": 405, "kl": 0.11310455880162527, "ce": 0.18765445052801188}, {"step": 406, "kl": 0.10270726519045623, "ce": 0.1915353536318376}, {"step": 407, "kl": 0.09812789140703698, "ce": 0.23824683816631337}, {"step": 408, "kl": 0.1104836578670103, "ce": 0.19020983986961548}, {"step": 409, "kl": 0.134637601548733, "ce": 0.23729235901284287}, {"step": 410, "kl": 0.11837672621277036, "ce": 0.19147278477471966}, {"step": 411, "kl": 0.13090946955971217, "ce": 0.18401403988108914}, {"step": 412, "kl": 0.11953499501258864, "ce": 0.2124706245437612}, {"step": 413, "kl": 0.10542584339213992, "ce": 0.14308104393624657}, {"step": 414, "kl": 0.11566984004175494, "ce": 0.26973432181344303}, {"step": 415, "kl": 0.1201476599589846, "ce": 0.1689859721915194}, {"step": 416, "kl": 0.10087799124151763, "ce": 0.1825734583009163}, {"step": 417, "kl": 0.11572485865973149, "ce": 0.22124100125688517}, {"step": 418, "kl": 0.11407325025080017, "ce": 0.17099980066077203}, {"step": 419, "kl": 0.12629763723358395, "ce": 0.19081165444708909}, {"step": 420, "kl": 0.12044993822156691, "ce": 0.21683266093655892}, {"step": 421, "kl": 0.11893486707686443, "ce": 0.20803599484519814}, {"step": 422, "kl": 0.0953828477936036, "ce": 0.1695153329126721}, {"step": 423, "kl": 0.13337696853133577, "ce": 0.20975184521396137}, {"step": 424, "kl": 0.1088290718498894, "ce": 0.20418656828818726}, {"step": 425, "kl": 0.13051281126966424, "ce": 0.256125382425868}, {"step": 426, "kl": 0.10921934864167485, "ce": 0.2019569596352505}, {"step": 427, "kl": 0.09763685242332185, "ce": 0.17066939084108565}, {"step": 428, "kl": 0.11537027270672895, "ce": 0.19117797597995137}, {"step": 429, "kl": 0.11792359468527902, "ce": 0.1861696334442986}, {"step": 430, "kl": 0.10673900779085746, "ce": 0.1844387720852123}, {"step": 431, "kl": 0.10243904648894826, "ce": 0.18890812714928096}, {"step": 432, "kl": 0.10831264150932818, "ce": 0.19253524166658723}, {"step": 433, "kl": 0.13338677348077155, "ce": 0.19456921113217662}, {"step": 434, "kl": 0.11370971300185877, "ce": 0.2096577052888961}, {"step": 435, "kl": 0.09657316834857703, "ce": 0.22615440521357696}, {"step": 436, "kl": 0.12479389216317685, "ce": 0.20734897516150672}, {"step": 437, "kl": 0.12475624868374889, "ce": 0.21834918573453582}, {"step": 438, "kl": 0.10369133103357853, "ce": 0.15898654766699322}, {"step": 439, "kl": 0.11087217378601437, "ce": 0.1826454164322983}, {"step": 440, "kl": 0.11282343722213194, "ce": 0.18744349217676853}, {"step": 441, "kl": 0.10969941454770496, "ce": 0.2131949517835505}, {"step": 442, "kl": 0.10470365625710441, "ce": 0.22246665840613603}, {"step": 443, "kl": 0.10517379877919929, "ce": 0.2015117490356706}, {"step": 444, "kl": 0.11331360832567788, "ce": 0.2570792884842942}, {"step": 445, "kl": 0.13174633547659048, "ce": 0.20041126223117078}, {"step": 446, "kl": 0.1091380112635972, "ce": 0.25532027805855245}, {"step": 447, "kl": 0.09124471486541275, "ce": 0.17625062678363812}, {"step": 448, "kl": 0.09573738038129628, "ce": 0.17131474368682242}, {"step": 449, "kl": 0.11678474513963721, "ce": 0.21076986299338915}, {"step": 450, "kl": 0.13091791945814063, "ce": 0.18238386364774772}, {"step": 451, "kl": 0.12139296910119435, "ce": 0.22561684681755326}, {"step": 452, "kl": 0.11044876952416341, "ce": 0.20818864975692336}, {"step": 453, "kl": 0.11802319976046013, "ce": 0.21082247795665715}, {"step": 454, "kl": 0.1285804073122448, "ce": 0.19748650650553806}], "val": [{"step": 0, "math_kl": 0.1330653788388266, "math_ce": 0.5623124645095477, "code_kl": 0.24520690705204787, "code_ce": 0.399327636078645}, {"step": 227, "math_kl": 0.14483410309268557, "math_ce": 0.5592349891601713, "code_kl": 0.16969436328369075, "code_ce": 0.2966060364115647}, {"step": 454, "math_kl": 0.15209920736881358, "math_ce": 0.5723041478842336, "code_kl": 0.1623846335587957, "code_ce": 0.2927603319761217}]}
 
 
seq_math_code/stage2_code/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9f801170f546f498b5ff63c6cea97e4df6908178d8b53eedf620c9eff0300b9
3
- size 988097824