Upload folder using huggingface_hub
Browse files- abl_kl_only_code_math_seed2/results_stage1_code/gsm8k.jsonl +0 -0
- abl_kl_only_code_math_seed2/results_stage1_code/humaneval.jsonl +0 -0
- abl_kl_only_code_math_seed2/results_stage1_code/humaneval_eval_results.json +0 -0
- abl_kl_only_code_math_seed2/results_stage1_code/mbpp.jsonl +0 -0
- abl_kl_only_code_math_seed2/results_stage1_code/mbpp_eval_results.json +0 -0
- abl_kl_only_code_math_seed2/results_stage1_code/summary.json +1 -0
- abl_kl_only_code_math_seed2/stage1_code/config.json +57 -0
- abl_kl_only_code_math_seed2/stage1_code/generation_config.json +14 -0
- abl_kl_only_code_math_seed2/stage1_code/log.json +1 -0
- abl_kl_only_code_math_seed2/stage1_code/model.safetensors +3 -0
abl_kl_only_code_math_seed2/results_stage1_code/gsm8k.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
abl_kl_only_code_math_seed2/results_stage1_code/humaneval.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
abl_kl_only_code_math_seed2/results_stage1_code/humaneval_eval_results.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
abl_kl_only_code_math_seed2/results_stage1_code/mbpp.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
abl_kl_only_code_math_seed2/results_stage1_code/mbpp_eval_results.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
abl_kl_only_code_math_seed2/results_stage1_code/summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "stage1_code", "gsm8k": 0.4624715693707354, "mbpp": 0.5, "mbpp_plus": 0.43386243386243384, "humaneval": 0.34146341463414637, "humaneval_plus": 0.29878048780487804, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
|
abl_kl_only_code_math_seed2/stage1_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 |
+
}
|
abl_kl_only_code_math_seed2/stage1_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 |
+
}
|
abl_kl_only_code_math_seed2/stage1_code/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.24332350870434225, "ce": 0.3676286061915638}, {"step": 2, "kl": 0.20261966783674884, "ce": 0.33414719163673906}, {"step": 3, "kl": 0.21912206120269243, "ce": 0.3595087426785587}, {"step": 4, "kl": 0.20298251834163356, "ce": 0.33687082926432294}, {"step": 5, "kl": 0.22411915377766345, "ce": 0.37500230542523605}, {"step": 6, "kl": 0.18910746331767286, "ce": 0.3509176773196247}, {"step": 7, "kl": 0.22690638197106944, "ce": 0.3640239411267153}, {"step": 8, "kl": 0.20642073132728833, "ce": 0.38287344648532085}, {"step": 9, "kl": 0.2022634987676514, "ce": 0.43716397642336846}, {"step": 10, "kl": 0.23268972988187578, "ce": 0.45473497556567244}, {"step": 11, "kl": 0.21360213207122666, "ce": 0.432323474540648}, {"step": 12, "kl": 0.20498201656789286, "ce": 0.46252359210522703}, {"step": 13, "kl": 0.17979885737577622, "ce": 0.3574155151422838}, {"step": 14, "kl": 0.20511640950443621, "ce": 0.41151487631224953}, {"step": 15, "kl": 0.1969547360525007, "ce": 0.40337722124599984}, {"step": 16, "kl": 0.18396863128270788, "ce": 0.37585008147013116}, {"step": 17, "kl": 0.17991958187415255, "ce": 0.3796209995578726}, {"step": 18, "kl": 0.2085845463977542, "ce": 0.3612411697286693}, {"step": 19, "kl": 0.17678550233461088, "ce": 0.32516443587309823}, {"step": 20, "kl": 0.20852114245724027, "ce": 0.42012025400772945}, {"step": 21, "kl": 0.18186686301106558, "ce": 0.3769461664062007}, {"step": 22, "kl": 0.18255984956084967, "ce": 0.42328726283482143}, {"step": 23, "kl": 0.16551400198499455, "ce": 0.326448096056436}, {"step": 24, "kl": 0.1446269205426279, "ce": 0.3290899344308036}, {"step": 25, "kl": 0.1639596342060032, "ce": 0.31150048248959283}, {"step": 26, "kl": 0.21054411530395364, "ce": 0.4417107109078563}, {"step": 27, "kl": 0.18829828831321874, "ce": 0.39155164915815555}, {"step": 28, "kl": 0.14097197652687504, "ce": 0.2809496994248419}, {"step": 29, "kl": 0.15641593348693156, "ce": 0.3316148519515991}, {"step": 30, "kl": 0.1809841935972759, "ce": 0.3827740465058584}, {"step": 31, "kl": 0.1896646311912943, "ce": 0.4050459287942901}, {"step": 32, "kl": 0.17961276348266492, "ce": 0.3355635783537546}, {"step": 33, "kl": 0.1813559879014044, "ce": 0.41751002388387265}, {"step": 34, "kl": 0.16366891808943315, "ce": 0.3178047629185647}, {"step": 35, "kl": 0.2106540925575025, "ce": 0.34246233077926475}, {"step": 36, "kl": 0.1933547576680793, "ce": 0.387008705644615}, {"step": 37, "kl": 0.22361307733556463, "ce": 0.3950088802040254}, {"step": 38, "kl": 0.1861057690013033, "ce": 0.3501498007748182}, {"step": 39, "kl": 0.1845972541801772, "ce": 0.3189805223823084}, {"step": 40, "kl": 0.1653054809714345, "ce": 0.3986067504882812}, {"step": 41, "kl": 0.15469994872557366, "ce": 0.3337138486936085}, {"step": 42, "kl": 0.1958097250864342, "ce": 0.4290036521591507}, {"step": 43, "kl": 0.16849754888943785, "ce": 0.38594264818274454}, {"step": 44, "kl": 0.16771671869477153, "ce": 0.3121449225977498}, {"step": 45, "kl": 0.15543211232209034, "ce": 0.24935184265952773}, {"step": 46, "kl": 0.1727470351397834, "ce": 0.3455805797163001}, {"step": 47, "kl": 0.16579407408335678, "ce": 0.37582221203011196}, {"step": 48, "kl": 0.17599172625743165, "ce": 0.3718548555241365}, {"step": 49, "kl": 0.1990055523127432, "ce": 0.4044329408607362}, {"step": 50, "kl": 0.17747075650322353, "ce": 0.37731743566622766}, {"step": 51, "kl": 0.16474979865704376, "ce": 0.3579808773042438}, {"step": 52, "kl": 0.20893014057636186, "ce": 0.37053739335436153}, {"step": 53, "kl": 0.18544879019836813, "ce": 0.4273538137631846}, {"step": 54, "kl": 0.1938245703862671, "ce": 0.40488683517188995}, {"step": 55, "kl": 0.19001759474435495, "ce": 0.37886273742850435}, {"step": 56, "kl": 0.17000305041085076, "ce": 0.35680492192358526}, {"step": 57, "kl": 0.1586490935402503, "ce": 0.3009374725106594}, {"step": 58, "kl": 0.17835317472808046, "ce": 0.38364265852640855}, {"step": 59, "kl": 0.1882455396346808, "ce": 0.43796782396792944}, {"step": 60, "kl": 0.15673422747947657, "ce": 0.3523929958682325}, {"step": 61, "kl": 0.1805602881177586, "ce": 0.36951021523481836}, {"step": 62, "kl": 0.13554577536969936, "ce": 0.34064325427551345}, {"step": 63, "kl": 0.15519887678105893, "ce": 0.35119133248653384}, {"step": 64, "kl": 0.17425629541373883, "ce": 0.45181313941218926}, {"step": 65, "kl": 0.17098735058665465, "ce": 0.327524946013658}, {"step": 66, "kl": 0.1719966681107231, "ce": 0.34383453898012817}, {"step": 67, "kl": 0.18623118833702462, "ce": 0.3962533669076692}, {"step": 68, "kl": 0.16652107796811405, "ce": 0.3286861941747092}, {"step": 69, "kl": 0.18295770948982068, "ce": 0.31986244851241324}, {"step": 70, "kl": 0.15789237032833975, "ce": 0.3377776712672056}, {"step": 71, "kl": 0.18720932795247136, "ce": 0.3890271000627346}, {"step": 72, "kl": 0.19235994336449513, "ce": 0.3524814172091389}, {"step": 73, "kl": 0.16699937866816342, "ce": 0.3681732676960491}, {"step": 74, "kl": 0.1793807058650565, "ce": 0.4346876446666613}, {"step": 75, "kl": 0.17592678272096055, "ce": 0.34589531894492387}, {"step": 76, "kl": 0.15841140764339198, "ce": 0.3170870261819355}, {"step": 77, "kl": 0.19934127538306265, "ce": 0.34643865222465703}, {"step": 78, "kl": 0.1813684561380496, "ce": 0.3826848061879476}, {"step": 79, "kl": 0.1560671716838263, "ce": 0.35780034905786595}, {"step": 80, "kl": 0.16239030270647697, "ce": 0.37757163014131434}, {"step": 81, "kl": 0.17229630605719626, "ce": 0.3707751102708158}, {"step": 82, "kl": 0.16070941116551996, "ce": 0.3762307524969734}, {"step": 83, "kl": 0.15782222268010332, "ce": 0.3688827989339782}, {"step": 84, "kl": 0.11708211229377896, "ce": 0.31424004655080184}, {"step": 85, "kl": 0.15078009870197648, "ce": 0.34601674719743714}, {"step": 86, "kl": 0.18765109842718808, "ce": 0.3901634396672531}, {"step": 87, "kl": 0.19278778559690518, "ce": 0.39808375547210084}, {"step": 88, "kl": 0.14459199918313548, "ce": 0.3487401092047372}, {"step": 89, "kl": 0.16018088117748955, "ce": 0.3658756918024543}, {"step": 90, "kl": 0.17928120589402238, "ce": 0.37882354936224927}, {"step": 91, "kl": 0.17135245236942653, "ce": 0.3477451210711646}, {"step": 92, "kl": 0.18659567511553418, "ce": 0.3792076477412675}, {"step": 93, "kl": 0.1480234248792952, "ce": 0.2964899074881907}, {"step": 94, "kl": 0.21057728113037516, "ce": 0.35697549087769165}, {"step": 95, "kl": 0.18032970858869563, "ce": 0.4001804892856018}, {"step": 96, "kl": 0.13154518345574284, "ce": 0.3865577477910094}, {"step": 97, "kl": 0.17110312254415394, "ce": 0.384314736829916}, {"step": 98, "kl": 0.20214824073980625, "ce": 0.37635927857844337}, {"step": 99, "kl": 0.17398996618492513, "ce": 0.39545436542387047}, {"step": 100, "kl": 0.1670403735080207, "ce": 0.36713156690578425}, {"step": 101, "kl": 0.15164857580362634, "ce": 0.3506845321693174}, {"step": 102, "kl": 0.18420939352324353, "ce": 0.383100096128429}, {"step": 103, "kl": 0.17296350315285655, "ce": 0.38660320775103774}, {"step": 104, "kl": 0.16760609238580132, "ce": 0.364095702396147}, {"step": 105, "kl": 0.16062776391226027, "ce": 0.3371419512397276}, {"step": 106, "kl": 0.17878970516821183, "ce": 0.4264111239779588}, {"step": 107, "kl": 0.20393038981653222, "ce": 0.49358254175054594}, {"step": 108, "kl": 0.22041803752647038, "ce": 0.4492304852330754}, {"step": 109, "kl": 0.16840971054433726, "ce": 0.33618821222088335}, {"step": 110, "kl": 0.1448605329017813, "ce": 0.3644315917084559}, {"step": 111, "kl": 0.17165614114273464, "ce": 0.4326899706384909}, {"step": 112, "kl": 0.1340140935426536, "ce": 0.39265213646255176}, {"step": 113, "kl": 0.14651245082122225, "ce": 0.33431038755179704}, {"step": 114, "kl": 0.16756602610534807, "ce": 0.34155633101740096}, {"step": 115, "kl": 0.17294978196649496, "ce": 0.3343639538897284}, {"step": 116, "kl": 0.20660133811928177, "ce": 0.40604505656780093}, {"step": 117, "kl": 0.18873153869655224, "ce": 0.353769190791344}, {"step": 118, "kl": 0.1900352483925347, "ce": 0.3725911269907309}, {"step": 119, "kl": 0.13514688336316433, "ce": 0.3946217528176964}, {"step": 120, "kl": 0.15075649033073615, "ce": 0.35625816204150074}, {"step": 121, "kl": 0.14390952141392774, "ce": 0.3568544330018939}, {"step": 122, "kl": 0.15484665498245426, "ce": 0.42683934749008706}, {"step": 123, "kl": 0.17661795553224177, "ce": 0.3941880019547576}, {"step": 124, "kl": 0.15842506536550757, "ce": 0.38953338397720966}, {"step": 125, "kl": 0.1545174028791892, "ce": 0.3741330003435543}, {"step": 126, "kl": 0.1430839370655757, "ce": 0.3706837847298234}, {"step": 127, "kl": 0.1849141418487503, "ce": 0.32176963383849}, {"step": 128, "kl": 0.15341055183233002, "ce": 0.3059722875996078}, {"step": 129, "kl": 0.1673905311566819, "ce": 0.4023559213711033}, {"step": 130, "kl": 0.16194535925312786, "ce": 0.40511520350825053}, {"step": 131, "kl": 0.17845231950015766, "ce": 0.3839101683599473}, {"step": 132, "kl": 0.14962338942105696, "ce": 0.39602545681026363}, {"step": 133, "kl": 0.13349188819710944, "ce": 0.26258312348876667}, {"step": 134, "kl": 0.17470631761681676, "ce": 0.35948834834259735}, {"step": 135, "kl": 0.17576822938326606, "ce": 0.3558934269233504}, {"step": 136, "kl": 0.1868308719387361, "ce": 0.37121943253114215}, {"step": 137, "kl": 0.14732015181978936, "ce": 0.3403303689440681}, {"step": 138, "kl": 0.1999727549862479, "ce": 0.3790198122374223}, {"step": 139, "kl": 0.17458828986280578, "ce": 0.3492246145461429}, {"step": 140, "kl": 0.2005485153695433, "ce": 0.3524705485177201}, {"step": 141, "kl": 0.15486567973142593, "ce": 0.3748693508024002}, {"step": 142, "kl": 0.15650077062494616, "ce": 0.40834373713636174}, {"step": 143, "kl": 0.16346230700209335, "ce": 0.40365646652463977}, {"step": 144, "kl": 0.17805288934707642, "ce": 0.42935274620487757}, {"step": 145, "kl": 0.14756656630070447, "ce": 0.35244594428836573}, {"step": 146, "kl": 0.18537226474572924, "ce": 0.365643979000296}, {"step": 147, "kl": 0.15973843874269106, "ce": 0.35937223096922977}, {"step": 148, "kl": 0.14445209308773121, "ce": 0.3279336769821751}, {"step": 149, "kl": 0.17757090190917318, "ce": 0.36625900924376564}, {"step": 150, "kl": 0.15005090773524474, "ce": 0.3242145693624082}, {"step": 151, "kl": 0.1272397409517272, "ce": 0.334881438008115}, {"step": 152, "kl": 0.19133171583679076, "ce": 0.39091899786504136}, {"step": 153, "kl": 0.16714911570666288, "ce": 0.37485615154773927}, {"step": 154, "kl": 0.15296187152187696, "ce": 0.39638667224236146}, {"step": 155, "kl": 0.13543683102458076, "ce": 0.36917650131952195}, {"step": 156, "kl": 0.16231922891288064, "ce": 0.34966343286127366}, {"step": 157, "kl": 0.15762300561489045, "ce": 0.3509183189651932}, {"step": 158, "kl": 0.17439874232824923, "ce": 0.3532347447981603}, {"step": 159, "kl": 0.1512201494983869, "ce": 0.3238847258907036}, {"step": 160, "kl": 0.17427070100488817, "ce": 0.3127968857886279}, {"step": 161, "kl": 0.17164854846471328, "ce": 0.37085771651842403}, {"step": 162, "kl": 0.16155710940699702, "ce": 0.34432185175701424}, {"step": 163, "kl": 0.1689092246415647, "ce": 0.3635699267954553}, {"step": 164, "kl": 0.15408308582792518, "ce": 0.3472403219235479}, {"step": 165, "kl": 0.16429987710930566, "ce": 0.3888106217479789}, {"step": 166, "kl": 0.1502611249649935, "ce": 0.3749571505512536}, {"step": 167, "kl": 0.14784073194510444, "ce": 0.3646808368235266}, {"step": 168, "kl": 0.15969332076796333, "ce": 0.3877547933321977}, {"step": 169, "kl": 0.17312223988435463, "ce": 0.3419861570335041}, {"step": 170, "kl": 0.1621225669398379, "ce": 0.3770355291607351}, {"step": 171, "kl": 0.16466640210443248, "ce": 0.36142877779280425}, {"step": 172, "kl": 0.15218977256619476, "ce": 0.3623573204533971}, {"step": 173, "kl": 0.14225341773447997, "ce": 0.3687079058551668}, {"step": 174, "kl": 0.17863213708636883, "ce": 0.45329878801546186}, {"step": 175, "kl": 0.16129407726231632, "ce": 0.33398602522260235}, {"step": 176, "kl": 0.14863084117446948, "ce": 0.3491564708150876}, {"step": 177, "kl": 0.12716244160123297, "ce": 0.3427864583333334}, {"step": 178, "kl": 0.1521186216317444, "ce": 0.3983964827328604}, {"step": 179, "kl": 0.15172626384200996, "ce": 0.3871925726996528}, {"step": 180, "kl": 0.1755334215515112, "ce": 0.4373750745757552}, {"step": 181, "kl": 0.1181430959127927, "ce": 0.3784496364974418}, {"step": 182, "kl": 0.15033335487301447, "ce": 0.41378716020831463}, {"step": 183, "kl": 0.1590388995945138, "ce": 0.37516038671864577}, {"step": 184, "kl": 0.1760224322923355, "ce": 0.35443903656450526}, {"step": 185, "kl": 0.17114934775083313, "ce": 0.4797375011891826}, {"step": 186, "kl": 0.14612569647641918, "ce": 0.29977437554183545}, {"step": 187, "kl": 0.15003928269264502, "ce": 0.3543463208193314}, {"step": 188, "kl": 0.16342063895233028, "ce": 0.3909820738660841}, {"step": 189, "kl": 0.10651973151253, "ce": 0.3419524444750005}, {"step": 190, "kl": 0.14613808807809572, "ce": 0.30993335215193074}, {"step": 191, "kl": 0.12255657530691402, "ce": 0.3243247912480281}, {"step": 192, "kl": 0.15963600720013227, "ce": 0.4070697975638912}, {"step": 193, "kl": 0.1768719832931379, "ce": 0.4369890433926317}, {"step": 194, "kl": 0.16503164900721873, "ce": 0.30422322498227605}, {"step": 195, "kl": 0.12652915571864068, "ce": 0.37893289964513416}, {"step": 196, "kl": 0.1693012492230082, "ce": 0.35657908853352355}, {"step": 197, "kl": 0.1521915297268489, "ce": 0.38663233863261154}, {"step": 198, "kl": 0.12334554657163357, "ce": 0.3578117048654339}, {"step": 199, "kl": 0.170227090452275, "ce": 0.377976594377918}, {"step": 200, "kl": 0.17103851450412444, "ce": 0.39087866918211844}, {"step": 201, "kl": 0.15383072414105434, "ce": 0.39112451542486953}, {"step": 202, "kl": 0.14061112761333522, "ce": 0.34277562848891385}, {"step": 203, "kl": 0.14093293590712302, "ce": 0.3038007279342149}, {"step": 204, "kl": 0.16880916213454988, "ce": 0.3838238633352174}, {"step": 205, "kl": 0.14070952676304882, "ce": 0.3560042942098191}, {"step": 206, "kl": 0.13198806005070138, "ce": 0.359416620114935}, {"step": 207, "kl": 0.1788952904161017, "ce": 0.31598460764716857}, {"step": 208, "kl": 0.13407970210284179, "ce": 0.33830682032934367}, {"step": 209, "kl": 0.16316050914577435, "ce": 0.39033235492128315}, {"step": 210, "kl": 0.1684938719649623, "ce": 0.373857462805874}, {"step": 211, "kl": 0.1665284843939867, "ce": 0.39518220615121424}, {"step": 212, "kl": 0.17821506349597843, "ce": 0.3918975516339905}, {"step": 213, "kl": 0.16937770587987827, "ce": 0.437086350027175}, {"step": 214, "kl": 0.1599500497905978, "ce": 0.382127463434369}, {"step": 215, "kl": 0.16319441926370154, "ce": 0.38846451667390824}, {"step": 216, "kl": 0.16535168364606365, "ce": 0.3100498183798476}, {"step": 217, "kl": 0.15803144855305917, "ce": 0.3539013192927094}, {"step": 218, "kl": 0.16267336090230883, "ce": 0.3641622803577693}, {"step": 219, "kl": 0.14865673792335088, "ce": 0.3512647751479121}, {"step": 220, "kl": 0.1374271114567766, "ce": 0.36903719306351845}, {"step": 221, "kl": 0.17930014506117292, "ce": 0.3796456798561601}, {"step": 222, "kl": 0.10685443033896322, "ce": 0.3360553732250939}, {"step": 223, "kl": 0.1319569922178714, "ce": 0.338689401433943}, {"step": 224, "kl": 0.11760785678160435, "ce": 0.3345420514679375}, {"step": 225, "kl": 0.12295864397249757, "ce": 0.38630612841870493}, {"step": 226, "kl": 0.16526471067414533, "ce": 0.3833649104977082}, {"step": 227, "kl": 0.19022631664169906, "ce": 0.4319048661089356}, {"step": 228, "kl": 0.0931644320310317, "ce": 0.345282582757901}, {"step": 229, "kl": 0.09615636555185603, "ce": 0.37331869334259804}, {"step": 230, "kl": 0.11088213365371913, "ce": 0.35527180923993806}, {"step": 231, "kl": 0.11358938858420826, "ce": 0.4168583506917194}, {"step": 232, "kl": 0.09823197647107669, "ce": 0.3601315431107266}, {"step": 233, "kl": 0.10514343094727899, "ce": 0.354817470527324}, {"step": 234, "kl": 0.09763061405626286, "ce": 0.4232212302070864}, {"step": 235, "kl": 0.10900184850292752, "ce": 0.36898874854793906}, {"step": 236, "kl": 0.10335091447296056, "ce": 0.34697168014955937}, {"step": 237, "kl": 0.09874640132128018, "ce": 0.37064928249406076}, {"step": 238, "kl": 0.08702464567803803, "ce": 0.327097913198554}, {"step": 239, "kl": 0.08574110689225001, "ce": 0.37273275619312074}, {"step": 240, "kl": 0.0926880080393077, "ce": 0.32332987819512266}, {"step": 241, "kl": 0.082941060457986, "ce": 0.354247527988225}, {"step": 242, "kl": 0.09037438791747376, "ce": 0.36098029452504843}, {"step": 243, "kl": 0.09442928894749714, "ce": 0.36272509369784217}, {"step": 244, "kl": 0.10827303705358315, "ce": 0.3416901522477982}, {"step": 245, "kl": 0.10323904060845937, "ce": 0.39096299821830666}, {"step": 246, "kl": 0.09560175306319192, "ce": 0.3887522938637141}, {"step": 247, "kl": 0.0819820267664052, "ce": 0.34658384334300363}, {"step": 248, "kl": 0.09655429050254194, "ce": 0.4158170820245449}, {"step": 249, "kl": 0.10191614913347163, "ce": 0.35439964605215646}, {"step": 250, "kl": 0.09946927814368114, "ce": 0.35956704692476116}, {"step": 251, "kl": 0.0726219847943826, "ce": 0.3268944948160896}, {"step": 252, "kl": 0.09156080285670345, "ce": 0.3310290769546751}, {"step": 253, "kl": 0.10673338515790223, "ce": 0.35575700334227267}, {"step": 254, "kl": 0.09547204209378773, "ce": 0.3681392731713092}, {"step": 255, "kl": 0.10103813137030279, "ce": 0.3699940925306153}, {"step": 256, "kl": 0.09939176638839725, "ce": 0.36470469587716753}, {"step": 257, "kl": 0.09349276867942785, "ce": 0.39782650849730483}, {"step": 258, "kl": 0.09255706503036173, "ce": 0.3491001633994369}, {"step": 259, "kl": 0.09904967030906714, "ce": 0.3662613801348248}, {"step": 260, "kl": 0.10498138091988096, "ce": 0.4632311451517337}, {"step": 261, "kl": 0.11016181533352679, "ce": 0.3874915000274747}, {"step": 262, "kl": 0.09261364177441425, "ce": 0.32431493045856075}, {"step": 263, "kl": 0.09588657505810261, "ce": 0.3471251370242645}, {"step": 264, "kl": 0.08611208986977326, "ce": 0.3498153632921134}, {"step": 265, "kl": 0.09323142316013988, "ce": 0.35970244821310554}, {"step": 266, "kl": 0.10644630976787922, "ce": 0.37263181714210875}, {"step": 267, "kl": 0.09235630520117927, "ce": 0.34529390460426707}, {"step": 268, "kl": 0.07990344441261664, "ce": 0.37997684287189853}, {"step": 269, "kl": 0.08547119673661435, "ce": 0.3471226806640625}, {"step": 270, "kl": 0.08998829118335873, "ce": 0.44468694073813303}, {"step": 271, "kl": 0.10713432631948133, "ce": 0.3565822021535697}, {"step": 272, "kl": 0.09537609971937586, "ce": 0.4207927257871249}, {"step": 273, "kl": 0.08680219555375587, "ce": 0.3489887629778847}, {"step": 274, "kl": 0.0892372935534091, "ce": 0.344516874504351}, {"step": 275, "kl": 0.10064588711585527, "ce": 0.3292663808353207}, {"step": 276, "kl": 0.08511554842092553, "ce": 0.3520180599450614}, {"step": 277, "kl": 0.081868214202501, "ce": 0.3346876859455594}, {"step": 278, "kl": 0.09131694578188432, "ce": 0.3490314383781393}, {"step": 279, "kl": 0.09202382264870115, "ce": 0.3605540271233467}, {"step": 280, "kl": 0.08586658721949196, "ce": 0.3367605489726886}, {"step": 281, "kl": 0.08178280864911233, "ce": 0.308989609743991}, {"step": 282, "kl": 0.0727660501958172, "ce": 0.35329506364022234}, {"step": 283, "kl": 0.09741914898036788, "ce": 0.39712719143783287}, {"step": 284, "kl": 0.0851097936562443, "ce": 0.35085583017833194}, {"step": 285, "kl": 0.10616745262952101, "ce": 0.41406407946152574}, {"step": 286, "kl": 0.08364673878637219, "ce": 0.3213424959107137}, {"step": 287, "kl": 0.09163798754601964, "ce": 0.35965449687762135}, {"step": 288, "kl": 0.08152592015418, "ce": 0.31860031410808004}, {"step": 289, "kl": 0.10419126542828785, "ce": 0.3622799514884173}, {"step": 290, "kl": 0.11476178268624425, "ce": 0.37093986058375605}, {"step": 291, "kl": 0.09220413324200288, "ce": 0.3335228433483721}, {"step": 292, "kl": 0.09598973684136969, "ce": 0.3959602280575598}, {"step": 293, "kl": 0.08732962348622175, "ce": 0.35555280847672477}, {"step": 294, "kl": 0.08615507370215557, "ce": 0.34352999514187216}, {"step": 295, "kl": 0.06612516472441922, "ce": 0.3190856887143859}, {"step": 296, "kl": 0.10406140089937793, "ce": 0.3660354750924083}, {"step": 297, "kl": 0.11339578121773017, "ce": 0.3688451000348548}, {"step": 298, "kl": 0.09106065144063756, "ce": 0.3177464457703708}, {"step": 299, "kl": 0.09964201757816149, "ce": 0.35924856910786557}, {"step": 300, "kl": 0.11090570493148977, "ce": 0.3515957148558037}, {"step": 301, "kl": 0.10727971633943849, "ce": 0.39104649105974226}, {"step": 302, "kl": 0.08234414528535719, "ce": 0.3245383201002263}, {"step": 303, "kl": 0.09933927567737677, "ce": 0.379246986875769}, {"step": 304, "kl": 0.09336758040984196, "ce": 0.38649596674726894}, {"step": 305, "kl": 0.1058604324954843, "ce": 0.4045608371722221}, {"step": 306, "kl": 0.08047700768432074, "ce": 0.3275065379876012}, {"step": 307, "kl": 0.08644793618896843, "ce": 0.39814920504667745}, {"step": 308, "kl": 0.09474141326488444, "ce": 0.40874183516364976}, {"step": 309, "kl": 0.10398520088997207, "ce": 0.34074371337890624}, {"step": 310, "kl": 0.07614020482999434, "ce": 0.38470089845786626}, {"step": 311, "kl": 0.08442950154136586, "ce": 0.36830796925647946}, {"step": 312, "kl": 0.08405077213782088, "ce": 0.4307093953724759}, {"step": 313, "kl": 0.08877270669418327, "ce": 0.40970188600620927}, {"step": 314, "kl": 0.09440084204736393, "ce": 0.2911043489414818}, {"step": 315, "kl": 0.07511683078696745, "ce": 0.37784636780455866}, {"step": 316, "kl": 0.09682623148395926, "ce": 0.3549140129397347}, {"step": 317, "kl": 0.09655326804756986, "ce": 0.34275526510979876}, {"step": 318, "kl": 0.09102990519032975, "ce": 0.40066896697984955}, {"step": 319, "kl": 0.09377453985046268, "ce": 0.3185738281968687}, {"step": 320, "kl": 0.09165292794345949, "ce": 0.3233650859032073}, {"step": 321, "kl": 0.10014579814760485, "ce": 0.3988077773730592}, {"step": 322, "kl": 0.07935194546101491, "ce": 0.31819192071465424}, {"step": 323, "kl": 0.0776668308737749, "ce": 0.3226099301435081}, {"step": 324, "kl": 0.08847283150951936, "ce": 0.35623966513328176}, {"step": 325, "kl": 0.10145675172054691, "ce": 0.37855541298044576}, {"step": 326, "kl": 0.08791865326351805, "ce": 0.3672714450855418}, {"step": 327, "kl": 0.09221790983799823, "ce": 0.31025163291806146}, {"step": 328, "kl": 0.09068926291575263, "ce": 0.3464884528670936}, {"step": 329, "kl": 0.06953123024329036, "ce": 0.303039974534589}, {"step": 330, "kl": 0.08874712482139965, "ce": 0.3626450861374555}, {"step": 331, "kl": 0.08298170559162192, "ce": 0.32070657792785356}, {"step": 332, "kl": 0.08608196743671105, "ce": 0.34680586058781704}, {"step": 333, "kl": 0.0846472702395748, "ce": 0.4473547037514555}, {"step": 334, "kl": 0.09876562085041551, "ce": 0.3826229302831908}, {"step": 335, "kl": 0.0988513437678685, "ce": 0.32058053206230885}, {"step": 336, "kl": 0.08887404147118898, "ce": 0.3399053778781359}, {"step": 337, "kl": 0.08011475934099149, "ce": 0.36395908901557017}, {"step": 338, "kl": 0.08527521549857212, "ce": 0.3761373070197377}, {"step": 339, "kl": 0.09286863449695915, "ce": 0.32640718175671274}, {"step": 340, "kl": 0.08906429125724402, "ce": 0.3456350843695337}, {"step": 341, "kl": 0.09087646811578266, "ce": 0.3234230914264284}, {"step": 342, "kl": 0.07937117367058534, "ce": 0.3742648495623835}, {"step": 343, "kl": 0.09205944729221198, "ce": 0.3508509633257385}, {"step": 344, "kl": 0.07919331954573655, "ce": 0.2755165895000574}, {"step": 345, "kl": 0.10052704157620011, "ce": 0.3275691787401835}, {"step": 346, "kl": 0.08231392519969363, "ce": 0.42569070476820425}, {"step": 347, "kl": 0.08233801573020977, "ce": 0.3736351298853744}, {"step": 348, "kl": 0.08123094908986747, "ce": 0.32764612669504384}, {"step": 349, "kl": 0.07618478173652715, "ce": 0.3347054331789735}, {"step": 350, "kl": 0.11016698231424654, "ce": 0.3632178711852099}, {"step": 351, "kl": 0.09230335449868798, "ce": 0.29624172657680353}, {"step": 352, "kl": 0.09875960350036622, "ce": 0.35641095172633735}, {"step": 353, "kl": 0.09920626183337229, "ce": 0.357784843838092}, {"step": 354, "kl": 0.09164622412316667, "ce": 0.39377437693649253}, {"step": 355, "kl": 0.10320050122739793, "ce": 0.35002068511771506}, {"step": 356, "kl": 0.10906364826521468, "ce": 0.33201075677305975}, {"step": 357, "kl": 0.09108648762436636, "ce": 0.3558507183543389}, {"step": 358, "kl": 0.07785598816170548, "ce": 0.31261868269371995}, {"step": 359, "kl": 0.09367860548700076, "ce": 0.3390949742249437}, {"step": 360, "kl": 0.0812099440302462, "ce": 0.3861050288039976}, {"step": 361, "kl": 0.07857774704905447, "ce": 0.3147190073679707}, {"step": 362, "kl": 0.0896747641319776, "ce": 0.38504752998184544}, {"step": 363, "kl": 0.08628740511101193, "ce": 0.36053213735265055}, {"step": 364, "kl": 0.08791113784434076, "ce": 0.3650140305169675}, {"step": 365, "kl": 0.0903976297266694, "ce": 0.3314952116935484}, {"step": 366, "kl": 0.10138221518173829, "ce": 0.365460409911178}, {"step": 367, "kl": 0.08304501056194782, "ce": 0.33984306327902836}, {"step": 368, "kl": 0.09387322903987895, "ce": 0.3255973851569345}, {"step": 369, "kl": 0.0930586551311465, "ce": 0.3346526599528754}, {"step": 370, "kl": 0.07791293273189785, "ce": 0.3097719792178388}, {"step": 371, "kl": 0.09472158409650498, "ce": 0.2726447594000159}, {"step": 372, "kl": 0.08517590783096168, "ce": 0.3698351139566241}, {"step": 373, "kl": 0.09908151261636018, "ce": 0.3853886729287066}, {"step": 374, "kl": 0.07456952961008581, "ce": 0.36643162831125903}, {"step": 375, "kl": 0.0926916670759541, "ce": 0.3702430936278683}, {"step": 376, "kl": 0.10383299742353722, "ce": 0.3876966169634069}, {"step": 377, "kl": 0.08146771647115944, "ce": 0.3746483937156247}, {"step": 378, "kl": 0.07105736067378213, "ce": 0.3454538753585658}, {"step": 379, "kl": 0.09700747720455673, "ce": 0.3889714131828483}, {"step": 380, "kl": 0.08457993838308339, "ce": 0.31818491640677615}, {"step": 381, "kl": 0.08211758520679542, "ce": 0.35972726390274373}, {"step": 382, "kl": 0.08744900355835615, "ce": 0.3206266803102203}, {"step": 383, "kl": 0.09053842913384406, "ce": 0.3330847032318229}, {"step": 384, "kl": 0.08409848182001851, "ce": 0.3618493613581804}, {"step": 385, "kl": 0.0943872125437667, "ce": 0.3620268793982625}, {"step": 386, "kl": 0.07296617399285721, "ce": 0.3224625881587234}, {"step": 387, "kl": 0.09282863495260238, "ce": 0.33114721912103695}, {"step": 388, "kl": 0.09767953794405888, "ce": 0.3956449473705408}, {"step": 389, "kl": 0.08998725523721195, "ce": 0.3593067822155652}, {"step": 390, "kl": 0.08408841107857559, "ce": 0.339182525681057}, {"step": 391, "kl": 0.07365248862525212, "ce": 0.3006355135355184}, {"step": 392, "kl": 0.0646878530912631, "ce": 0.3186149695527159}, {"step": 393, "kl": 0.09438542656062804, "ce": 0.3691432470602839}, {"step": 394, "kl": 0.09841390809966277, "ce": 0.39021412205747846}, {"step": 395, "kl": 0.08389916194760587, "ce": 0.4367671416607819}, {"step": 396, "kl": 0.08028053692156364, "ce": 0.3249138292059841}, {"step": 397, "kl": 0.09844301499312111, "ce": 0.3338467151115142}, {"step": 398, "kl": 0.07193381694571072, "ce": 0.3282743347393583}, {"step": 399, "kl": 0.08079086934595198, "ce": 0.3762126234769543}, {"step": 400, "kl": 0.08867017220759736, "ce": 0.32451076913048893}, {"step": 401, "kl": 0.06720739306819948, "ce": 0.3853750679078893}, {"step": 402, "kl": 0.10314297346971318, "ce": 0.3862767186966255}, {"step": 403, "kl": 0.07399948166348758, "ce": 0.31829240955010557}, {"step": 404, "kl": 0.06794083139090955, "ce": 0.3690931079877492}, {"step": 405, "kl": 0.07626397190732437, "ce": 0.3632579820885506}, {"step": 406, "kl": 0.07499584503244405, "ce": 0.34944330887723796}, {"step": 407, "kl": 0.10841744776003089, "ce": 0.40985234766482426}, {"step": 408, "kl": 0.09770095937605593, "ce": 0.35195293779248427}, {"step": 409, "kl": 0.07053499213716345, "ce": 0.35840259164844124}, {"step": 410, "kl": 0.0736392733543127, "ce": 0.29095772413919513}, {"step": 411, "kl": 0.07914749267769548, "ce": 0.3219252016118085}, {"step": 412, "kl": 0.08890893558738718, "ce": 0.34185973924115376}, {"step": 413, "kl": 0.08315583545447017, "ce": 0.2806975914966101}, {"step": 414, "kl": 0.0882439528075668, "ce": 0.35344968059109955}, {"step": 415, "kl": 0.07524013930423121, "ce": 0.27869301020820125}, {"step": 416, "kl": 0.07499400532046711, "ce": 0.3478129650517471}, {"step": 417, "kl": 0.09581440790177825, "ce": 0.3519644358233578}, {"step": 418, "kl": 0.0877706669633677, "ce": 0.346132423918126}, {"step": 419, "kl": 0.09896781974368625, "ce": 0.35668977011959196}, {"step": 420, "kl": 0.08992677986867144, "ce": 0.3508718495131105}, {"step": 421, "kl": 0.07967017769063793, "ce": 0.32843268837773365}, {"step": 422, "kl": 0.0739370150345432, "ce": 0.34096571265592346}, {"step": 423, "kl": 0.09414212494466326, "ce": 0.35410747893956224}, {"step": 424, "kl": 0.08601565162524594, "ce": 0.3727068327150622}, {"step": 425, "kl": 0.0667210750365525, "ce": 0.3012390119790872}, {"step": 426, "kl": 0.09161696117617751, "ce": 0.41004005517373543}, {"step": 427, "kl": 0.10862667595182247, "ce": 0.36141478109348313}, {"step": 428, "kl": 0.10309195775802463, "ce": 0.35158471385662254}, {"step": 429, "kl": 0.07800311633699933, "ce": 0.30412677051575204}, {"step": 430, "kl": 0.09080921537892606, "ce": 0.40014897235676816}, {"step": 431, "kl": 0.07993216563148628, "ce": 0.34005970015309306}, {"step": 432, "kl": 0.11149597438811017, "ce": 0.40596029869997713}, {"step": 433, "kl": 0.0989503076437567, "ce": 0.3520671487441791}, {"step": 434, "kl": 0.08806414770962138, "ce": 0.3317251988495849}, {"step": 435, "kl": 0.06807801306507819, "ce": 0.31840244511484106}, {"step": 436, "kl": 0.11005685218152769, "ce": 0.3878960263375907}, {"step": 437, "kl": 0.08820651251587998, "ce": 0.32241352578038596}, {"step": 438, "kl": 0.0898814938032943, "ce": 0.3888732576560694}, {"step": 439, "kl": 0.08504138516352214, "ce": 0.3026534691874597}, {"step": 440, "kl": 0.09594571135078704, "ce": 0.3315614694615949}, {"step": 441, "kl": 0.08714375140169282, "ce": 0.37074466532665984}, {"step": 442, "kl": 0.08207731609866384, "ce": 0.3923874167261513}, {"step": 443, "kl": 0.08440321319114405, "ce": 0.29702009958020315}, {"step": 444, "kl": 0.08603157246317253, "ce": 0.3765409165089198}, {"step": 445, "kl": 0.07837759931640188, "ce": 0.325998534747806}, {"step": 446, "kl": 0.0770342420630606, "ce": 0.3647773982593848}, {"step": 447, "kl": 0.09613997930296816, "ce": 0.4442784801424605}, {"step": 448, "kl": 0.08167144764965058, "ce": 0.3646506882233345}, {"step": 449, "kl": 0.08618145326929769, "ce": 0.3687515185288151}, {"step": 450, "kl": 0.08243897784534823, "ce": 0.34368788976071063}, {"step": 451, "kl": 0.0978026468180048, "ce": 0.36155240788620047}, {"step": 452, "kl": 0.09241105513108634, "ce": 0.39797770241849784}, {"step": 453, "kl": 0.10122908937667885, "ce": 0.424094624829179}, {"step": 454, "kl": 0.10166685687688706, "ce": 0.37042714302866875}], "val": [{"step": 0, "math_kl": 0.17059537193969265, "math_ce": 0.8387106338797149, "code_kl": 0.22116874322487284, "code_ce": 0.36744983409730037}, {"step": 227, "math_kl": 0.17830047884065933, "math_ce": 0.7560344076006861, "code_kl": 0.16034362610312897, "code_ce": 0.3718112688446071}, {"step": 454, "math_kl": 0.1824759058776002, "math_ce": 0.7621970800024556, "code_kl": 0.1529255793992233, "code_ce": 0.3678276281722018}]}
|
abl_kl_only_code_math_seed2/stage1_code/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cee74c4164b5b5cc0b5bfbb11cf909df95062af0f27b306a5b8c7b67453d0dae
|
| 3 |
+
size 988097824
|