jajamken commited on
Commit
bd7db1a
·
verified ·
1 Parent(s): 1e82773

Upload folder using huggingface_hub

Browse files
seq_math_code/results_stage2_code/gsm8k.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/humaneval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/humaneval_eval_results.json ADDED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/mbpp.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/mbpp_eval_results.json ADDED
The diff for this file is too large to render. See raw diff
 
seq_math_code/results_stage2_code/summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "stage2_code", "gsm8k": 0.42532221379833207, "mbpp": 0.4973544973544973, "mbpp_plus": 0.42328042328042326, "humaneval": 0.34146341463414637, "humaneval_plus": 0.31097560975609756, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
seq_math_code/stage2_code/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "5.20.2"
14
+ }
seq_math_code/stage2_code/log.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [{"step": 1, "kl": 0.29487281807288607, "ce": 0.4581295185991693}, {"step": 2, "kl": 0.2503688135874323, "ce": 0.35579803688027806}, {"step": 3, "kl": 0.23967265861107817, "ce": 0.39107478863298717}, {"step": 4, "kl": 0.23640015136442705, "ce": 0.35931856501190457}, {"step": 5, "kl": 0.22039569246291185, "ce": 0.3863263239841064}, {"step": 6, "kl": 0.2280768545191239, "ce": 0.35295295841618635}, {"step": 7, "kl": 0.24662664688205918, "ce": 0.3463147649762717}, {"step": 8, "kl": 0.23441321366536783, "ce": 0.4409619545107211}, {"step": 9, "kl": 0.2668015055338542, "ce": 0.30394340146538673}, {"step": 10, "kl": 0.2579108770731081, "ce": 0.330204828879897}, {"step": 11, "kl": 0.20002708865032381, "ce": 0.3060855663556057}, {"step": 12, "kl": 0.21915754169447962, "ce": 0.35275020338758173}, {"step": 13, "kl": 0.23523418399604487, "ce": 0.33180492028190334}, {"step": 14, "kl": 0.17880413340370085, "ce": 0.30759293738831867}, {"step": 15, "kl": 0.1892779233797396, "ce": 0.32241114259146}, {"step": 16, "kl": 0.22669342875632292, "ce": 0.3228222553064805}, {"step": 17, "kl": 0.2217402740312358, "ce": 0.33022162004866057}, {"step": 18, "kl": 0.22158061578858004, "ce": 0.30474950065877426}, {"step": 19, "kl": 0.20788168644931845, "ce": 0.3008411747342847}, {"step": 20, "kl": 0.19390581588252487, "ce": 0.28583426183047256}, {"step": 21, "kl": 0.1994461046373205, "ce": 0.3225931919934698}, {"step": 22, "kl": 0.23366638845648646, "ce": 0.3401301827536826}, {"step": 23, "kl": 0.22333126740751352, "ce": 0.3367249343127106}, {"step": 24, "kl": 0.2104314208976124, "ce": 0.29258120333685916}, {"step": 25, "kl": 0.2010704665448978, "ce": 0.2935089111328125}, {"step": 26, "kl": 0.2040898967465402, "ce": 0.31217348026130387}, {"step": 27, "kl": 0.2561391885936607, "ce": 0.3453968926948747}, {"step": 28, "kl": 0.2174490235603231, "ce": 0.38326106236275537}, {"step": 29, "kl": 0.20228070186551292, "ce": 0.2912496384675071}, {"step": 30, "kl": 0.19974328076045328, "ce": 0.35075899621810547}, {"step": 31, "kl": 0.22929514266382295, "ce": 0.36243884534720916}, {"step": 32, "kl": 0.20052894473020788, "ce": 0.2803892046827812}, {"step": 33, "kl": 0.21119101781808833, "ce": 0.34349464609821895}, {"step": 34, "kl": 0.1927706548923769, "ce": 0.3307324471004693}, {"step": 35, "kl": 0.18295002526119436, "ce": 0.3361753219341352}, {"step": 36, "kl": 0.2018750083893049, "ce": 0.3217087881905692}, {"step": 37, "kl": 0.16967481463448839, "ce": 0.28836187400914576}, {"step": 38, "kl": 0.2039257951673692, "ce": 0.3481123141727795}, {"step": 39, "kl": 0.24043118657164314, "ce": 0.358896638843315}, {"step": 40, "kl": 0.19682134728503886, "ce": 0.2746340743056288}, {"step": 41, "kl": 0.23133886189842692, "ce": 0.36886440122288794}, {"step": 42, "kl": 0.18616061633597125, "ce": 0.24365889728878554}, {"step": 43, "kl": 0.16824980357571084, "ce": 0.2934221586140038}, {"step": 44, "kl": 0.2022006961899239, "ce": 0.3255831625736469}, {"step": 45, "kl": 0.18507344613799886, "ce": 0.3236310094884924}, {"step": 46, "kl": 0.1734754882882508, "ce": 0.2706718452691196}, {"step": 47, "kl": 0.17833905659990038, "ce": 0.25447332784677734}, {"step": 48, "kl": 0.21396205479734184, "ce": 0.3624647171627212}, {"step": 49, "kl": 0.17321140544245409, "ce": 0.3097445309911211}, {"step": 50, "kl": 0.17466419327482463, "ce": 0.30418235505244645}, {"step": 51, "kl": 0.1760563231473431, "ce": 0.24754866478675158}, {"step": 52, "kl": 0.1877118680626154, "ce": 0.33884776489896923}, {"step": 53, "kl": 0.20174912944885218, "ce": 0.34163993909696827}, {"step": 54, "kl": 0.18025444016430547, "ce": 0.25893848774499023}, {"step": 55, "kl": 0.20037508342312216, "ce": 0.31228706034512643}, {"step": 56, "kl": 0.17790289158453773, "ce": 0.3014917427855585}, {"step": 57, "kl": 0.2042807736767961, "ce": 0.3341983454895338}, {"step": 58, "kl": 0.19698004817699755, "ce": 0.31898045214669324}, {"step": 59, "kl": 0.2082872424685658, "ce": 0.34431144324753266}, {"step": 60, "kl": 0.15166617123456838, "ce": 0.24338936185264892}, {"step": 61, "kl": 0.2077374227960498, "ce": 0.30727163424394377}, {"step": 62, "kl": 0.18432670373183033, "ce": 0.31444343123834606}, {"step": 63, "kl": 0.19670810296759725, "ce": 0.27780074985244557}, {"step": 64, "kl": 0.18861159674728972, "ce": 0.32990834277675385}, {"step": 65, "kl": 0.18358250966435818, "ce": 0.3018910103738612}, {"step": 66, "kl": 0.20179082535039028, "ce": 0.2904538280832534}, {"step": 67, "kl": 0.18311379132827055, "ce": 0.2622639995906777}, {"step": 68, "kl": 0.17095348303658622, "ce": 0.3688548307783187}, {"step": 69, "kl": 0.19681704680657136, "ce": 0.26288471374579564}, {"step": 70, "kl": 0.1869100651463757, "ce": 0.2935604357343333}, {"step": 71, "kl": 0.21048968628551185, "ce": 0.30815008247538667}, {"step": 72, "kl": 0.19162655755821534, "ce": 0.3395217806559746}, {"step": 73, "kl": 0.17711414796721564, "ce": 0.3269514088329163}, {"step": 74, "kl": 0.1868745978567298, "ce": 0.3053907148774843}, {"step": 75, "kl": 0.202172109701187, "ce": 0.31452547848879636}, {"step": 76, "kl": 0.14502351999238164, "ce": 0.2429147894346577}, {"step": 77, "kl": 0.18356116781549625, "ce": 0.2697312686398844}, {"step": 78, "kl": 0.20129753779903048, "ce": 0.32553287725011976}, {"step": 79, "kl": 0.2244441498796419, "ce": 0.356623565659947}, {"step": 80, "kl": 0.15870981174418577, "ce": 0.2806497222586509}, {"step": 81, "kl": 0.20062758422171742, "ce": 0.3646151242167016}, {"step": 82, "kl": 0.1981399119626504, "ce": 0.29314558060285884}, {"step": 83, "kl": 0.18493180152207397, "ce": 0.2968126389721425}, {"step": 84, "kl": 0.1719622363361844, "ce": 0.290240915988354}, {"step": 85, "kl": 0.1658432352770853, "ce": 0.3599947126338087}, {"step": 86, "kl": 0.20836092113109117, "ce": 0.3017482660837908}, {"step": 87, "kl": 0.19054245730058864, "ce": 0.33556080533107274}, {"step": 88, "kl": 0.17397290742741628, "ce": 0.2905556474329361}, {"step": 89, "kl": 0.16711561884132914, "ce": 0.2634392391738071}, {"step": 90, "kl": 0.2042061810566084, "ce": 0.25704665452893505}, {"step": 91, "kl": 0.1840995788574219, "ce": 0.30559948298629525}, {"step": 92, "kl": 0.1702700180582481, "ce": 0.2813598184759616}, {"step": 93, "kl": 0.18222030041619888, "ce": 0.29801013199510934}, {"step": 94, "kl": 0.1579994645956107, "ce": 0.2802685207430913}, {"step": 95, "kl": 0.17016041414247224, "ce": 0.29061586082088675}, {"step": 96, "kl": 0.16778929126951658, "ce": 0.27865199923872974}, {"step": 97, "kl": 0.17774339820359308, "ce": 0.3355296450798477}, {"step": 98, "kl": 0.19466810429116763, "ce": 0.2613398615076152}, {"step": 99, "kl": 0.18257124142543682, "ce": 0.291488753172401}, {"step": 100, "kl": 0.15424984718457332, "ce": 0.2486744735015457}, {"step": 101, "kl": 0.1653765974501761, "ce": 0.269026665609391}, {"step": 102, "kl": 0.14028150512684617, "ce": 0.2589211975006617}, {"step": 103, "kl": 0.1627020822758524, "ce": 0.2674764469611799}, {"step": 104, "kl": 0.1741786614082348, "ce": 0.2856432480108542}, {"step": 105, "kl": 0.15988343571596603, "ce": 0.27693846750797413}, {"step": 106, "kl": 0.146200004699493, "ce": 0.2661465883592231}, {"step": 107, "kl": 0.1712424301727773, "ce": 0.3187483908372548}, {"step": 108, "kl": 0.19831138916532287, "ce": 0.33593665147124313}, {"step": 109, "kl": 0.20351493201945134, "ce": 0.27940631928441817}, {"step": 110, "kl": 0.18396568133086974, "ce": 0.36292080774097024}, {"step": 111, "kl": 0.1554002458217995, "ce": 0.264702254436743}, {"step": 112, "kl": 0.18910329836748754, "ce": 0.36641250779090145}, {"step": 113, "kl": 0.18703416117299587, "ce": 0.3283380138059929}, {"step": 114, "kl": 0.19992054788145341, "ce": 0.3245905608379195}, {"step": 115, "kl": 0.19223935180626936, "ce": 0.3688191858474894}, {"step": 116, "kl": 0.19184188135313718, "ce": 0.28740538941126437}, {"step": 117, "kl": 0.17849173361823062, "ce": 0.28446462955114976}, {"step": 118, "kl": 0.1667134061047612, "ce": 0.27012954418772517}, {"step": 119, "kl": 0.17847075820528846, "ce": 0.28367265838835154}, {"step": 120, "kl": 0.16549144443745215, "ce": 0.2812167758365781}, {"step": 121, "kl": 0.17703600741925365, "ce": 0.2952107102011998}, {"step": 122, "kl": 0.2104917715594497, "ce": 0.346801807604338}, {"step": 123, "kl": 0.18982474232473534, "ce": 0.3449916304021642}, {"step": 124, "kl": 0.15676219109939415, "ce": 0.31028743758578364}, {"step": 125, "kl": 0.22400469202631795, "ce": 0.31570800251277586}, {"step": 126, "kl": 0.19696252152973462, "ce": 0.3013867313825487}, {"step": 127, "kl": 0.1319157300781016, "ce": 0.21853244197261226}, {"step": 128, "kl": 0.15236676391772258, "ce": 0.31670078534758495}, {"step": 129, "kl": 0.1809146305198448, "ce": 0.3020723228519028}, {"step": 130, "kl": 0.153690108941325, "ce": 0.2807999125926568}, {"step": 131, "kl": 0.1815879083583566, "ce": 0.26117760339725676}, {"step": 132, "kl": 0.15378412643908496, "ce": 0.28117762845287775}, {"step": 133, "kl": 0.19004210830664672, "ce": 0.30968411954434905}, {"step": 134, "kl": 0.17048717675556285, "ce": 0.2730868205742043}, {"step": 135, "kl": 0.13318920802242387, "ce": 0.2558807330503783}, {"step": 136, "kl": 0.17367950861289602, "ce": 0.272855780850729}, {"step": 137, "kl": 0.1525590940741568, "ce": 0.24816697087496853}, {"step": 138, "kl": 0.1786665889707563, "ce": 0.2710326715441216}, {"step": 139, "kl": 0.17917449699230395, "ce": 0.2570920362088036}, {"step": 140, "kl": 0.1731621802423014, "ce": 0.26860286403444733}, {"step": 141, "kl": 0.17748186702787894, "ce": 0.2817842427165984}, {"step": 142, "kl": 0.17718462974580926, "ce": 0.24366168082898126}, {"step": 143, "kl": 0.15538418584099972, "ce": 0.2611861424192169}, {"step": 144, "kl": 0.16887762149837504, "ce": 0.2650800677585663}, {"step": 145, "kl": 0.15969807411428472, "ce": 0.29871100267791206}, {"step": 146, "kl": 0.1886211649686567, "ce": 0.31529568698580224}, {"step": 147, "kl": 0.14113511251573935, "ce": 0.23352210324509698}, {"step": 148, "kl": 0.1886181645699711, "ce": 0.33670073534717704}, {"step": 149, "kl": 0.2029110719869425, "ce": 0.3312406519199954}, {"step": 150, "kl": 0.16228067241265873, "ce": 0.2857193953806286}, {"step": 151, "kl": 0.16492556790908788, "ce": 0.3042985145984688}, {"step": 152, "kl": 0.17648227082383922, "ce": 0.24473240241249583}, {"step": 153, "kl": 0.18494133355596726, "ce": 0.26612797390024573}, {"step": 154, "kl": 0.15534698654845996, "ce": 0.25118090964511874}, {"step": 155, "kl": 0.13981915350536636, "ce": 0.2533687291921378}, {"step": 156, "kl": 0.14962088291919415, "ce": 0.31288992896894363}, {"step": 157, "kl": 0.16351360589356964, "ce": 0.29107102807146623}, {"step": 158, "kl": 0.16343791162602056, "ce": 0.3103396713530244}, {"step": 159, "kl": 0.14797448004790553, "ce": 0.29000347032459506}, {"step": 160, "kl": 0.1929348620739612, "ce": 0.304758936865199}, {"step": 161, "kl": 0.1882973990034865, "ce": 0.3126123971582011}, {"step": 162, "kl": 0.15137593218032336, "ce": 0.28897842954395586}, {"step": 163, "kl": 0.20713105590208758, "ce": 0.319001834246136}, {"step": 164, "kl": 0.17491848282107242, "ce": 0.28540962612965554}, {"step": 165, "kl": 0.1570159141369381, "ce": 0.2594720700228921}, {"step": 166, "kl": 0.16109168685122882, "ce": 0.2968124448309544}, {"step": 167, "kl": 0.17181321305178585, "ce": 0.25135984663410194}, {"step": 168, "kl": 0.14943734710738504, "ce": 0.2881629987245805}, {"step": 169, "kl": 0.1484405961775761, "ce": 0.25519298271209623}, {"step": 170, "kl": 0.1953148124939964, "ce": 0.30102356864083435}, {"step": 171, "kl": 0.15811689947651195, "ce": 0.25942435328636}, {"step": 172, "kl": 0.17692913409431835, "ce": 0.29698205427689983}, {"step": 173, "kl": 0.19463569562895028, "ce": 0.2902931111653646}, {"step": 174, "kl": 0.17716010594942194, "ce": 0.2936067914629316}, {"step": 175, "kl": 0.15004878093592852, "ce": 0.25494411474031736}, {"step": 176, "kl": 0.1517053516066853, "ce": 0.22639413975589096}, {"step": 177, "kl": 0.13844479160261125, "ce": 0.2463683773842063}, {"step": 178, "kl": 0.16440198605360762, "ce": 0.3119615631172156}, {"step": 179, "kl": 0.18106465495028645, "ce": 0.2799772433920884}, {"step": 180, "kl": 0.1690000638666958, "ce": 0.30738870931040635}, {"step": 181, "kl": 0.1628325345942779, "ce": 0.3269794693401801}, {"step": 182, "kl": 0.17217255013748983, "ce": 0.28418808862023526}, {"step": 183, "kl": 0.1776941661715865, "ce": 0.349626755027614}, {"step": 184, "kl": 0.14983167219147586, "ce": 0.2854495417897294}, {"step": 185, "kl": 0.1689381299629098, "ce": 0.3088271150581659}, {"step": 186, "kl": 0.16818384666092315, "ce": 0.28945055110849066}, {"step": 187, "kl": 0.2062787454874562, "ce": 0.32817394719552473}, {"step": 188, "kl": 0.19156373730359594, "ce": 0.34847753412193727}, {"step": 189, "kl": 0.12822021124992694, "ce": 0.24843738137221916}, {"step": 190, "kl": 0.17040289015997023, "ce": 0.31008737579706697}, {"step": 191, "kl": 0.17641569248944275, "ce": 0.3118866240578975}, {"step": 192, "kl": 0.19161164120750104, "ce": 0.36174212505701697}, {"step": 193, "kl": 0.15562278546714425, "ce": 0.28627875026268296}, {"step": 194, "kl": 0.1592163267986571, "ce": 0.23621576958062207}, {"step": 195, "kl": 0.18477056060326177, "ce": 0.32758933016302166}, {"step": 196, "kl": 0.15780660015069395, "ce": 0.2621125921167264}, {"step": 197, "kl": 0.17378226062754218, "ce": 0.259537859001623}, {"step": 198, "kl": 0.15512679801986, "ce": 0.28165200566221443}, {"step": 199, "kl": 0.15667224156467127, "ce": 0.2453201813709417}, {"step": 200, "kl": 0.17740563086683303, "ce": 0.2885805145841927}, {"step": 201, "kl": 0.17234663923474944, "ce": 0.3341360259735692}, {"step": 202, "kl": 0.12879363611904066, "ce": 0.2891638928606022}, {"step": 203, "kl": 0.14760612223812944, "ce": 0.26138065636465596}, {"step": 204, "kl": 0.17702056334237667, "ce": 0.33636626482568244}, {"step": 205, "kl": 0.1546354134108526, "ce": 0.2450070236935348}, {"step": 206, "kl": 0.18798753986996625, "ce": 0.3259385649025091}, {"step": 207, "kl": 0.16328639631349576, "ce": 0.3173616592132581}, {"step": 208, "kl": 0.19351547516205095, "ce": 0.30916754800653967}, {"step": 209, "kl": 0.15854698162900205, "ce": 0.28110371962964353}, {"step": 210, "kl": 0.125740942174875, "ce": 0.22815656081778196}, {"step": 211, "kl": 0.14616954874992372, "ce": 0.23501184682758758}, {"step": 212, "kl": 0.1298802033276625, "ce": 0.21841366135883886}, {"step": 213, "kl": 0.15534206960177285, "ce": 0.22927400846297533}, {"step": 214, "kl": 0.21971922946552325, "ce": 0.32504919431473983}, {"step": 215, "kl": 0.17999730944614326, "ce": 0.29324380573306097}, {"step": 216, "kl": 0.15776160127265085, "ce": 0.3039600746014185}, {"step": 217, "kl": 0.1812285755363217, "ce": 0.31508003156931175}, {"step": 218, "kl": 0.15260931735917788, "ce": 0.2764413038435251}, {"step": 219, "kl": 0.1403656891624994, "ce": 0.25080997175314845}, {"step": 220, "kl": 0.17949281955565166, "ce": 0.2844984862389328}, {"step": 221, "kl": 0.14781143175899908, "ce": 0.2565227149053576}, {"step": 222, "kl": 0.16596544398817906, "ce": 0.356384479357727}, {"step": 223, "kl": 0.15481836713022656, "ce": 0.2676926375050626}, {"step": 224, "kl": 0.15116064044154492, "ce": 0.32498475692364936}, {"step": 225, "kl": 0.14009321230472682, "ce": 0.3186711583970253}, {"step": 226, "kl": 0.14989125593348543, "ce": 0.28166982748558134}, {"step": 227, "kl": 0.1745888536857017, "ce": 0.2472792622945873}, {"step": 228, "kl": 0.13832478622792244, "ce": 0.22656536674065755}, {"step": 229, "kl": 0.12909009577738956, "ce": 0.18691018090319278}, {"step": 230, "kl": 0.12475881453031087, "ce": 0.2297286144229648}, {"step": 231, "kl": 0.14047821281224682, "ce": 0.22949183874741}, {"step": 232, "kl": 0.1328761456101829, "ce": 0.21980537606041528}, {"step": 233, "kl": 0.12370754375333527, "ce": 0.19096717786927614}, {"step": 234, "kl": 0.11542426273308345, "ce": 0.21042987126969656}, {"step": 235, "kl": 0.13170536680921519, "ce": 0.2330558228497537}, {"step": 236, "kl": 0.10159680070893776, "ce": 0.1949453776733556}, {"step": 237, "kl": 0.10807742466710873, "ce": 0.20320575507215724}, {"step": 238, "kl": 0.14059063942082686, "ce": 0.20315739440291838}, {"step": 239, "kl": 0.13508830820809511, "ce": 0.18567348673851303}, {"step": 240, "kl": 0.11121978753697065, "ce": 0.2092585999934505}, {"step": 241, "kl": 0.12498908949564644, "ce": 0.1973545993055078}, {"step": 242, "kl": 0.10467987523699965, "ce": 0.21175706596345326}, {"step": 243, "kl": 0.147810018840934, "ce": 0.2543873301723547}, {"step": 244, "kl": 0.13423014606270833, "ce": 0.205349178429631}, {"step": 245, "kl": 0.11237234315588626, "ce": 0.1874468346230952}, {"step": 246, "kl": 0.09862971838557963, "ce": 0.2069293719567728}, {"step": 247, "kl": 0.10305800236568999, "ce": 0.21788897105002697}, {"step": 248, "kl": 0.09981991327028149, "ce": 0.20078467920868395}, {"step": 249, "kl": 0.111281998683481, "ce": 0.1952252170957368}, {"step": 250, "kl": 0.12008454402639389, "ce": 0.21920876614443502}, {"step": 251, "kl": 0.13799661803500732, "ce": 0.19424695690268243}, {"step": 252, "kl": 0.10216856250239797, "ce": 0.19345249302169132}, {"step": 253, "kl": 0.11574355905220349, "ce": 0.1853212444573551}, {"step": 254, "kl": 0.12598664020521072, "ce": 0.22902087176287617}, {"step": 255, "kl": 0.1266070582083148, "ce": 0.24263406248760447}, {"step": 256, "kl": 0.12745932728171055, "ce": 0.21616198555017907}, {"step": 257, "kl": 0.10420304257748095, "ce": 0.16907619710005592}, {"step": 258, "kl": 0.12360338138075148, "ce": 0.18874277291200323}, {"step": 259, "kl": 0.116417568713635, "ce": 0.21507798059600458}, {"step": 260, "kl": 0.12049895841972741, "ce": 0.19306667215131187}, {"step": 261, "kl": 0.1307305693329814, "ce": 0.2543848681601749}, {"step": 262, "kl": 0.12011159946355254, "ce": 0.1984232096654463}, {"step": 263, "kl": 0.13155117701516478, "ce": 0.20875055357111372}, {"step": 264, "kl": 0.13064358088698935, "ce": 0.19587517434335908}, {"step": 265, "kl": 0.1139490908538519, "ce": 0.22525220840465027}, {"step": 266, "kl": 0.12401811800108797, "ce": 0.21597902062216195}, {"step": 267, "kl": 0.10447021342680987, "ce": 0.18452061754431162}, {"step": 268, "kl": 0.11300856471874866, "ce": 0.2160872893527255}, {"step": 269, "kl": 0.10423862791235339, "ce": 0.20739027761322743}, {"step": 270, "kl": 0.14652296309064355, "ce": 0.1927914337884812}, {"step": 271, "kl": 0.10364787925312724, "ce": 0.17754304855265082}, {"step": 272, "kl": 0.13649797462718885, "ce": 0.26110464242788467}, {"step": 273, "kl": 0.11575855412732489, "ce": 0.2036960324187163}, {"step": 274, "kl": 0.13633865129449624, "ce": 0.19665555041221894}, {"step": 275, "kl": 0.10577357598990375, "ce": 0.19567095235786683}, {"step": 276, "kl": 0.1206472763277342, "ce": 0.23237354747145114}, {"step": 277, "kl": 0.10171040942447776, "ce": 0.19772946383140533}, {"step": 278, "kl": 0.11184834146972071, "ce": 0.1931063101457129}, {"step": 279, "kl": 0.12678464559726405, "ce": 0.18931475838462075}, {"step": 280, "kl": 0.10441389596458411, "ce": 0.21801947928381343}, {"step": 281, "kl": 0.10573109917341403, "ce": 0.21460292766263048}, {"step": 282, "kl": 0.14440928628386762, "ce": 0.23543522091707583}, {"step": 283, "kl": 0.1364625169968482, "ce": 0.22002659797021606}, {"step": 284, "kl": 0.1119361975500315, "ce": 0.21925308423321438}, {"step": 285, "kl": 0.13247906088871783, "ce": 0.21891522949076558}, {"step": 286, "kl": 0.11162201640056123, "ce": 0.21714548227902952}, {"step": 287, "kl": 0.1292071032606228, "ce": 0.2344666697184245}, {"step": 288, "kl": 0.10828587958153257, "ce": 0.18697347319725752}, {"step": 289, "kl": 0.12326412337858735, "ce": 0.21398529795695054}, {"step": 290, "kl": 0.10404929775353543, "ce": 0.19333529017971746}, {"step": 291, "kl": 0.10447835692992577, "ce": 0.18062951870929406}, {"step": 292, "kl": 0.11656421492360426, "ce": 0.2042314432207855}, {"step": 293, "kl": 0.12892491311269602, "ce": 0.18674026871634034}, {"step": 294, "kl": 0.132845087333324, "ce": 0.21533349192852158}, {"step": 295, "kl": 0.09482892779713596, "ce": 0.20196274503006625}, {"step": 296, "kl": 0.1372817037780374, "ce": 0.29978855208947897}, {"step": 297, "kl": 0.10258394535026374, "ce": 0.2114387806727141}, {"step": 298, "kl": 0.13346252794015365, "ce": 0.2196982261546193}, {"step": 299, "kl": 0.09620398432043177, "ce": 0.20622947816855303}, {"step": 300, "kl": 0.13144812526141572, "ce": 0.20805963938288935}, {"step": 301, "kl": 0.10277929048830282, "ce": 0.19201665452142083}, {"step": 302, "kl": 0.10546225762863445, "ce": 0.17647408202048281}, {"step": 303, "kl": 0.11637269675100444, "ce": 0.21292189298058783}, {"step": 304, "kl": 0.10386132394331067, "ce": 0.1695790734850926}, {"step": 305, "kl": 0.10211825037572411, "ce": 0.17596591848683218}, {"step": 306, "kl": 0.12462247474438115, "ce": 0.1749315372681629}, {"step": 307, "kl": 0.12499229052259324, "ce": 0.21072754563692817}, {"step": 308, "kl": 0.12879540867564393, "ce": 0.21286186938202423}, {"step": 309, "kl": 0.0881566976068719, "ce": 0.20648750223097254}, {"step": 310, "kl": 0.1202889642296883, "ce": 0.2113839300153768}, {"step": 311, "kl": 0.11572942256755905, "ce": 0.19709658515726508}, {"step": 312, "kl": 0.11403025624342424, "ce": 0.1734124224624653}, {"step": 313, "kl": 0.09741835524009271, "ce": 0.19251299770083985}, {"step": 314, "kl": 0.11136726132246841, "ce": 0.18025739214061634}, {"step": 315, "kl": 0.13306756184443463, "ce": 0.20964040302531411}, {"step": 316, "kl": 0.12937078940903884, "ce": 0.20321451719955877}, {"step": 317, "kl": 0.10664280931315762, "ce": 0.1954632856382103}, {"step": 318, "kl": 0.129174190266558, "ce": 0.20284985433949662}, {"step": 319, "kl": 0.11916903526789234, "ce": 0.20679604176724894}, {"step": 320, "kl": 0.1059401861273724, "ce": 0.18399141575127267}, {"step": 321, "kl": 0.10385834022175491, "ce": 0.20518243740046205}, {"step": 322, "kl": 0.12667602511184078, "ce": 0.2642347261672446}, {"step": 323, "kl": 0.12602082067368808, "ce": 0.22674098789269923}, {"step": 324, "kl": 0.10618425816653734, "ce": 0.18470976302141903}, {"step": 325, "kl": 0.09577453142854342, "ce": 0.2026215619911157}, {"step": 326, "kl": 0.12960718286554082, "ce": 0.23397437091027212}, {"step": 327, "kl": 0.11373452514680382, "ce": 0.22071974344870776}, {"step": 328, "kl": 0.1126304319146762, "ce": 0.19954287947791233}, {"step": 329, "kl": 0.11816390493314724, "ce": 0.18912438946463925}, {"step": 330, "kl": 0.1198663334736879, "ce": 0.18660262019025586}, {"step": 331, "kl": 0.14232904931349485, "ce": 0.24654790698055454}, {"step": 332, "kl": 0.1172591117846649, "ce": 0.25039920270851845}, {"step": 333, "kl": 0.10477160752088786, "ce": 0.16741956252437087}, {"step": 334, "kl": 0.1168099930340109, "ce": 0.22643552381962093}, {"step": 335, "kl": 0.09022640120806268, "ce": 0.2004963751235626}, {"step": 336, "kl": 0.1175840991974631, "ce": 0.1979254445174264}, {"step": 337, "kl": 0.10028620127954085, "ce": 0.15550028864493107}, {"step": 338, "kl": 0.11534409340250368, "ce": 0.20717005030419477}, {"step": 339, "kl": 0.11374866532306283, "ce": 0.2187084557057781}, {"step": 340, "kl": 0.09629121848515101, "ce": 0.16962445911324422}, {"step": 341, "kl": 0.1367179245519743, "ce": 0.19473939858439238}, {"step": 342, "kl": 0.11902186385061961, "ce": 0.20025015970324167}, {"step": 343, "kl": 0.11882411706944448, "ce": 0.19521136909684553}, {"step": 344, "kl": 0.1301217613626288, "ce": 0.19712919987452127}, {"step": 345, "kl": 0.10918082177072326, "ce": 0.17731480095714044}, {"step": 346, "kl": 0.10866364999113579, "ce": 0.19671893577694946}, {"step": 347, "kl": 0.11295664404147321, "ce": 0.1793221074109637}, {"step": 348, "kl": 0.10728124908374015, "ce": 0.18053337232872144}, {"step": 349, "kl": 0.11188204131902364, "ce": 0.19348474014167222}, {"step": 350, "kl": 0.09935994659001095, "ce": 0.19678885387305298}, {"step": 351, "kl": 0.09968185180820213, "ce": 0.2070069556544826}, {"step": 352, "kl": 0.1264127661321358, "ce": 0.20442755013993644}, {"step": 353, "kl": 0.11416962671806341, "ce": 0.20525119942678532}, {"step": 354, "kl": 0.11005091935696515, "ce": 0.2032288269233874}, {"step": 355, "kl": 0.1385224915848762, "ce": 0.22228950066871733}, {"step": 356, "kl": 0.1285833596195664, "ce": 0.2440949510462915}, {"step": 357, "kl": 0.12019254982239731, "ce": 0.23605321049532269}, {"step": 358, "kl": 0.10854681021044948, "ce": 0.1921433404685292}, {"step": 359, "kl": 0.11707147218146775, "ce": 0.2198794201723079}, {"step": 360, "kl": 0.09589997941319395, "ce": 0.1899130357302426}, {"step": 361, "kl": 0.15323028497801455, "ce": 0.26424342665262207}, {"step": 362, "kl": 0.12660202385919028, "ce": 0.22965491950178943}, {"step": 363, "kl": 0.09051471662194013, "ce": 0.18238448290000286}, {"step": 364, "kl": 0.10910599500199025, "ce": 0.19678660921183735}, {"step": 365, "kl": 0.09146691873592945, "ce": 0.19237767267993258}, {"step": 366, "kl": 0.09845699535177246, "ce": 0.21721633167433346}, {"step": 367, "kl": 0.11359891800899842, "ce": 0.16092042201222131}, {"step": 368, "kl": 0.11332272110360393, "ce": 0.16870986840952346}, {"step": 369, "kl": 0.10607959145517362, "ce": 0.1853940283801631}, {"step": 370, "kl": 0.12436648572313039, "ce": 0.19303053290511668}, {"step": 371, "kl": 0.10721766119478193, "ce": 0.1675351175979062}, {"step": 372, "kl": 0.12225582318149962, "ce": 0.20612065801013274}, {"step": 373, "kl": 0.12029942282584061, "ce": 0.22909280773750212}, {"step": 374, "kl": 0.13271763322718763, "ce": 0.18905192197400128}, {"step": 375, "kl": 0.11002125605848412, "ce": 0.20941807076590402}, {"step": 376, "kl": 0.1231014673533296, "ce": 0.22478885330870835}, {"step": 377, "kl": 0.11664485334216151, "ce": 0.22930496155771224}, {"step": 378, "kl": 0.13559861560799955, "ce": 0.27626375825584404}, {"step": 379, "kl": 0.11547616165597581, "ce": 0.20392806582535924}, {"step": 380, "kl": 0.09249952248080592, "ce": 0.18906827290852865}, {"step": 381, "kl": 0.10674723176296738, "ce": 0.16901250847744126}, {"step": 382, "kl": 0.11652013490052074, "ce": 0.18802166225126127}, {"step": 383, "kl": 0.10969709710291015, "ce": 0.2260434761399823}, {"step": 384, "kl": 0.15674654440369679, "ce": 0.21173391126310875}, {"step": 385, "kl": 0.105821363179566, "ce": 0.21593771742769663}, {"step": 386, "kl": 0.1232013002062623, "ce": 0.17360813824912763}, {"step": 387, "kl": 0.09249523272182766, "ce": 0.16419884198276952}, {"step": 388, "kl": 0.10916918146403197, "ce": 0.18904111680326874}, {"step": 389, "kl": 0.104446182583973, "ce": 0.1814734529993711}, {"step": 390, "kl": 0.11757859442839469, "ce": 0.19113037563703505}, {"step": 391, "kl": 0.12430668809430223, "ce": 0.2926824268541838}, {"step": 392, "kl": 0.12304100416032769, "ce": 0.21050617602952656}, {"step": 393, "kl": 0.09719200105465431, "ce": 0.19170438527154376}, {"step": 394, "kl": 0.12524625084792093, "ce": 0.24487638045981913}, {"step": 395, "kl": 0.11196788705303662, "ce": 0.2075842828255441}, {"step": 396, "kl": 0.1307577314565647, "ce": 0.20964205275438302}, {"step": 397, "kl": 0.09558856510539757, "ce": 0.1875884756588525}, {"step": 398, "kl": 0.08914862978181522, "ce": 0.2058246581769627}, {"step": 399, "kl": 0.12518645860930105, "ce": 0.17693610322001657}, {"step": 400, "kl": 0.09873031621977676, "ce": 0.17519601349978103}, {"step": 401, "kl": 0.11988111600295184, "ce": 0.20334121436403507}, {"step": 402, "kl": 0.09492130578598038, "ce": 0.19791164641684675}, {"step": 403, "kl": 0.10360577860011772, "ce": 0.19434601015474565}, {"step": 404, "kl": 0.11720577666992327, "ce": 0.18540813372286927}, {"step": 405, "kl": 0.1127523814287304, "ce": 0.18782658021386697}, {"step": 406, "kl": 0.1031023530545442, "ce": 0.19141791394051796}, {"step": 407, "kl": 0.09796711325194465, "ce": 0.2383963470688637}, {"step": 408, "kl": 0.110991714597924, "ce": 0.190819735221501}, {"step": 409, "kl": 0.13450246583150086, "ce": 0.23707486663729682}, {"step": 410, "kl": 0.11842290398275108, "ce": 0.19125828449902732}, {"step": 411, "kl": 0.131221270263851, "ce": 0.18440832830324513}, {"step": 412, "kl": 0.1197184217851714, "ce": 0.21260056314589101}, {"step": 413, "kl": 0.10573354915336325, "ce": 0.14282674773537923}, {"step": 414, "kl": 0.11538088735264668, "ce": 0.26899949937912665}, {"step": 415, "kl": 0.12029330636983365, "ce": 0.16894747929301723}, {"step": 416, "kl": 0.10083947351397761, "ce": 0.18263024435223604}, {"step": 417, "kl": 0.11566346069421514, "ce": 0.22131765554048838}, {"step": 418, "kl": 0.11405510952562375, "ce": 0.17083046285024975}, {"step": 419, "kl": 0.12600619429991314, "ce": 0.19032114862532462}, {"step": 420, "kl": 0.12033209086824725, "ce": 0.21715987429557182}, {"step": 421, "kl": 0.11852856003538503, "ce": 0.2080650657850765}, {"step": 422, "kl": 0.09540388786964968, "ce": 0.16940280418783554}, {"step": 423, "kl": 0.13365622619579726, "ce": 0.21041346985787013}, {"step": 424, "kl": 0.10878874373012441, "ce": 0.20401309607646836}, {"step": 425, "kl": 0.130284282518431, "ce": 0.2555321506742569}, {"step": 426, "kl": 0.10879097554868394, "ce": 0.20236150134870498}, {"step": 427, "kl": 0.09731057670348461, "ce": 0.17098288842923065}, {"step": 428, "kl": 0.11495885216514021, "ce": 0.19158729336944613}, {"step": 429, "kl": 0.11795896532964104, "ce": 0.18595649396282574}, {"step": 430, "kl": 0.10662244066603323, "ce": 0.1846286189292417}, {"step": 431, "kl": 0.1024051239992591, "ce": 0.18875141678193957}, {"step": 432, "kl": 0.10828398060729937, "ce": 0.19232887470240043}, {"step": 433, "kl": 0.13338317205563693, "ce": 0.19492335704860447}, {"step": 434, "kl": 0.11393729920556267, "ce": 0.21042212029208787}, {"step": 435, "kl": 0.09682720207535417, "ce": 0.226096350748416}, {"step": 436, "kl": 0.12487816853925239, "ce": 0.20790036889506305}, {"step": 437, "kl": 0.12513980907315994, "ce": 0.21919937995273986}, {"step": 438, "kl": 0.10375750578151997, "ce": 0.1591728918495218}, {"step": 439, "kl": 0.1099174988712977, "ce": 0.18249270776880644}, {"step": 440, "kl": 0.11289034039483901, "ce": 0.18753978451864167}, {"step": 441, "kl": 0.10951534071307173, "ce": 0.21353112342817923}, {"step": 442, "kl": 0.10510665119706358, "ce": 0.2227331085660983}, {"step": 443, "kl": 0.10499205008421901, "ce": 0.20125629114329008}, {"step": 444, "kl": 0.11310485645853571, "ce": 0.25639610111433575}, {"step": 445, "kl": 0.13159593471074468, "ce": 0.20085543262353006}, {"step": 446, "kl": 0.10914915306872439, "ce": 0.25566605797747466}, {"step": 447, "kl": 0.09120162593746552, "ce": 0.176999075237951}, {"step": 448, "kl": 0.0957918851659244, "ce": 0.17117292380322666}, {"step": 449, "kl": 0.11657578457360979, "ce": 0.21089613353106995}, {"step": 450, "kl": 0.13129266175623, "ce": 0.18264347963624386}, {"step": 451, "kl": 0.1213925253777277, "ce": 0.22522314123831985}, {"step": 452, "kl": 0.11000174185032902, "ce": 0.20787952638120397}, {"step": 453, "kl": 0.11836689287020566, "ce": 0.21141866501296283}, {"step": 454, "kl": 0.12859088117549222, "ce": 0.1979912097706726}], "val": [{"step": 0, "math_kl": 0.13315830432588285, "math_ce": 0.5614735253198577, "code_kl": 0.24534189434498116, "code_ce": 0.39927407628515066}, {"step": 227, "math_kl": 0.14494801838694252, "math_ce": 0.5586222285425995, "code_kl": 0.16950146931781482, "code_ce": 0.29657570140409756}, {"step": 454, "math_kl": 0.15212079420380073, "math_ce": 0.571090878931138, "code_kl": 0.1621094999988278, "code_ce": 0.2924594899349143}]}
seq_math_code/stage2_code/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc7d4c97463e4f66959ecb0acec593f2721abf7f59a0c7257fa542e9143083c
3
+ size 988097824