jajamken commited on
Commit
8e8dc5e
·
verified ·
1 Parent(s): 7be05ba

Upload folder using huggingface_hub

Browse files
abl_sft_math_code_seed2/results_stage1_math/gsm8k.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
abl_sft_math_code_seed2/results_stage1_math/humaneval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
abl_sft_math_code_seed2/results_stage1_math/humaneval_eval_results.json ADDED
The diff for this file is too large to render. See raw diff
 
abl_sft_math_code_seed2/results_stage1_math/mbpp.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
abl_sft_math_code_seed2/results_stage1_math/mbpp_eval_results.json ADDED
The diff for this file is too large to render. See raw diff
 
abl_sft_math_code_seed2/results_stage1_math/summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "stage1_math", "gsm8k": 0.37225170583775585, "mbpp": 0.4444444444444444, "mbpp_plus": 0.37037037037037035, "humaneval": 0.31097560975609756, "humaneval_plus": 0.27439024390243905, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
abl_sft_math_code_seed2/stage1_math/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_sft_math_code_seed2/stage1_math/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "5.20.2"
14
+ }
abl_sft_math_code_seed2/stage1_math/log.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [{"step": 1, "kl": 0.13710788488145123, "ce": 0.7985215966918793}, {"step": 2, "kl": 0.13350899260451535, "ce": 0.8258947381621188}, {"step": 3, "kl": 0.11198459655880955, "ce": 0.7994970421192509}, {"step": 4, "kl": 0.12023301434403555, "ce": 0.7505437002876127}, {"step": 5, "kl": 0.11682451286528119, "ce": 0.6616704768322884}, {"step": 6, "kl": 0.12343183865778636, "ce": 0.613908408459714}, {"step": 7, "kl": 0.17695423945876385, "ce": 0.5233819184384971}, {"step": 8, "kl": 0.13933341353879564, "ce": 0.5584101818176184}, {"step": 9, "kl": 0.1361665278077251, "ce": 0.5321610286757226}, {"step": 10, "kl": 0.1236114774337359, "ce": 0.47731449521821123}, {"step": 11, "kl": 0.13518503491764405, "ce": 0.5374088978036864}, {"step": 12, "kl": 0.17880416138073563, "ce": 0.5294579377183984}, {"step": 13, "kl": 0.17604609418708042, "ce": 0.5606276316601628}, {"step": 14, "kl": 0.16947120308342467, "ce": 0.5321529576425915}, {"step": 15, "kl": 0.18549793921833746, "ce": 0.5374499632635362}, {"step": 16, "kl": 0.2203132758765566, "ce": 0.531901787022032}, {"step": 17, "kl": 0.2102297863872345, "ce": 0.48379274490062457}, {"step": 18, "kl": 0.24080081822134863, "ce": 0.5287017103963517}, {"step": 19, "kl": 0.2324574897816987, "ce": 0.5402382315462652}, {"step": 20, "kl": 0.25414422527217184, "ce": 0.5685369251704375}, {"step": 21, "kl": 0.3060426336927692, "ce": 0.47454615643973586}, {"step": 22, "kl": 0.24466822214367268, "ce": 0.5692526329455343}, {"step": 23, "kl": 0.23707237568490624, "ce": 0.47750217686822155}, {"step": 24, "kl": 0.24258758389828633, "ce": 0.5720005585767821}, {"step": 25, "kl": 0.23064529610332632, "ce": 0.4063576836034421}, {"step": 26, "kl": 0.24980111566268312, "ce": 0.5512016558101915}, {"step": 27, "kl": 0.25472208775511573, "ce": 0.5547673854604699}, {"step": 28, "kl": 0.2641187328870924, "ce": 0.4974835367543151}, {"step": 29, "kl": 0.2673551966274026, "ce": 0.5277528035496272}, {"step": 30, "kl": 0.27030908225016115, "ce": 0.606163252074011}, {"step": 31, "kl": 0.25924805121368977, "ce": 0.4387237209293463}, {"step": 32, "kl": 0.25631927978916597, "ce": 0.5321320698089806}, {"step": 33, "kl": 0.3208999284077982, "ce": 0.5911082176741478}, {"step": 34, "kl": 0.27855042038549666, "ce": 0.5388146585668186}, {"step": 35, "kl": 0.2699908748134101, "ce": 0.5738686856903737}, {"step": 36, "kl": 0.2722481275202324, "ce": 0.5258562347170777}, {"step": 37, "kl": 0.24886457427429043, "ce": 0.45704042208557316}, {"step": 38, "kl": 0.25515130104713424, "ce": 0.46580083015153134}, {"step": 39, "kl": 0.246224087616273, "ce": 0.555794119754516}, {"step": 40, "kl": 0.29264395675624855, "ce": 0.6709438587914258}, {"step": 41, "kl": 0.2513921952802523, "ce": 0.5127961832135381}, {"step": 42, "kl": 0.28667282530224564, "ce": 0.5161845865524973}, {"step": 43, "kl": 0.24363667190966418, "ce": 0.5750513571101404}, {"step": 44, "kl": 0.24093481252453722, "ce": 0.5063166544533366}, {"step": 45, "kl": 0.2584066611772925, "ce": 0.5349126202293272}, {"step": 46, "kl": 0.2516683482695424, "ce": 0.5477695660622234}, {"step": 47, "kl": 0.2751410285219327, "ce": 0.5601215462672116}, {"step": 48, "kl": 0.247940337365189, "ce": 0.47199840184101677}, {"step": 49, "kl": 0.2547702303799716, "ce": 0.4634069430321372}, {"step": 50, "kl": 0.2606522939433052, "ce": 0.5979070755151603}, {"step": 51, "kl": 0.25655904142851993, "ce": 0.5115709541060028}, {"step": 52, "kl": 0.24514873952027225, "ce": 0.5505986668999883}, {"step": 53, "kl": 0.2587582154560655, "ce": 0.5191548423161583}, {"step": 54, "kl": 0.23999181759382338, "ce": 0.4154306967729007}, {"step": 55, "kl": 0.24554465093720546, "ce": 0.538055875710463}, {"step": 56, "kl": 0.2621368778113163, "ce": 0.5544094518234169}, {"step": 57, "kl": 0.2670964385386652, "ce": 0.4570365964112728}, {"step": 58, "kl": 0.2806337364198384, "ce": 0.48967399705694203}, {"step": 59, "kl": 0.29328519132662645, "ce": 0.5138712173853165}, {"step": 60, "kl": 0.28069630678684093, "ce": 0.5639170232621135}, {"step": 61, "kl": 0.28230915572018583, "ce": 0.5894568316845864}, {"step": 62, "kl": 0.2613521607713608, "ce": 0.4699937777503893}, {"step": 63, "kl": 0.2595207948844364, "ce": 0.5545494874423913}, {"step": 64, "kl": 0.5693891365211327, "ce": 0.5145640985085546}, {"step": 65, "kl": 0.272860554336731, "ce": 0.5524311783463747}, {"step": 66, "kl": 0.2650796633520308, "ce": 0.5072079136590666}, {"step": 67, "kl": 0.27252844030986856, "ce": 0.46003807590912693}, {"step": 68, "kl": 0.28443324360476313, "ce": 0.6153306213999059}, {"step": 69, "kl": 0.29425280530016856, "ce": 0.5079346204564009}, {"step": 70, "kl": 0.2582028787796497, "ce": 0.6222566275142756}, {"step": 71, "kl": 0.27892665950042367, "ce": 0.5834630141593197}, {"step": 72, "kl": 0.25277631635473746, "ce": 0.5163269457477242}, {"step": 73, "kl": 0.2750820422177653, "ce": 0.6140013200253156}, {"step": 74, "kl": 0.2630724771375822, "ce": 0.4837972230354785}, {"step": 75, "kl": 0.26016478477117844, "ce": 0.4734861267399666}, {"step": 76, "kl": 0.2713024773304047, "ce": 0.4905506394664693}, {"step": 77, "kl": 0.25499884284465785, "ce": 0.47055611829981403}, {"step": 78, "kl": 0.25757069606140115, "ce": 0.5336774388506578}, {"step": 79, "kl": 0.28174324020244057, "ce": 0.6252593872653451}, {"step": 80, "kl": 0.2777055481862525, "ce": 0.5728761234140037}, {"step": 81, "kl": 0.27911609806602083, "ce": 0.48692742717255477}, {"step": 82, "kl": 0.27561866714183736, "ce": 0.47896664608888523}, {"step": 83, "kl": 0.3011772270794352, "ce": 0.6197554667920802}, {"step": 84, "kl": 0.25118311930909815, "ce": 0.49444960195122034}, {"step": 85, "kl": 0.2647491965832571, "ce": 0.49573816601544807}, {"step": 86, "kl": 0.27975662448984057, "ce": 0.48659479764521263}, {"step": 87, "kl": 0.2605318042833732, "ce": 0.4950741654268671}, {"step": 88, "kl": 0.2798913625187565, "ce": 0.4916191363467414}, {"step": 89, "kl": 0.3226802921327542, "ce": 0.5764282448728854}, {"step": 90, "kl": 0.2719538686237125, "ce": 0.5919500491788783}, {"step": 91, "kl": 0.2889589856018373, "ce": 0.4683093768829027}, {"step": 92, "kl": 0.28438089201692346, "ce": 0.5159806914069275}, {"step": 93, "kl": 0.29621608817220013, "ce": 0.49319708068235263}, {"step": 94, "kl": 0.32596036731205236, "ce": 0.5713217696801429}, {"step": 95, "kl": 0.29626566135056026, "ce": 0.5167190615579865}, {"step": 96, "kl": 0.35823767617893765, "ce": 0.5896886937758502}, {"step": 97, "kl": 0.3009497988876419, "ce": 0.48573456397076314}, {"step": 98, "kl": 0.27972683012865474, "ce": 0.551518440246582}, {"step": 99, "kl": 0.2824326457250499, "ce": 0.531589007658117}, {"step": 100, "kl": 0.28883235801542456, "ce": 0.5508720451898973}, {"step": 101, "kl": 0.2737595849975921, "ce": 0.46970607064575826}, {"step": 102, "kl": 0.2973065831682463, "ce": 0.510907420991783}, {"step": 103, "kl": 0.2780083121799193, "ce": 0.515625136498034}, {"step": 104, "kl": 0.2786988535418806, "ce": 0.5506906506296015}, {"step": 105, "kl": 0.3325161509572724, "ce": 0.5002556392991107}, {"step": 106, "kl": 0.2684978069261626, "ce": 0.5462995601917902}, {"step": 107, "kl": 0.2692524902243559, "ce": 0.46614796946513554}, {"step": 108, "kl": 0.28029619057223715, "ce": 0.5354622029209298}, {"step": 109, "kl": 0.2820294907550296, "ce": 0.5560043731993354}, {"step": 110, "kl": 0.2877032270262417, "ce": 0.5521607935823352}, {"step": 111, "kl": 0.2877783360643621, "ce": 0.5159392767295777}, {"step": 112, "kl": 0.30388616686971137, "ce": 0.5218849855310776}, {"step": 113, "kl": 0.3241773969108985, "ce": 0.4564800202659679}, {"step": 114, "kl": 0.3070872257770481, "ce": 0.5193342460593597}, {"step": 115, "kl": 0.279303089960666, "ce": 0.5317125294629699}, {"step": 116, "kl": 0.31706079436252443, "ce": 0.5736443615599767}, {"step": 117, "kl": 0.2936462056109855, "ce": 0.5582239749657847}, {"step": 118, "kl": 0.29003328320481203, "ce": 0.5068960135817393}, {"step": 119, "kl": 0.27485939859396524, "ce": 0.48536185295351086}, {"step": 120, "kl": 0.2844560363851421, "ce": 0.446942887841699}, {"step": 121, "kl": 0.3047168997633642, "ce": 0.5613104434788899}, {"step": 122, "kl": 0.269715761177433, "ce": 0.47363283627499075}, {"step": 123, "kl": 0.2797465936904548, "ce": 0.4739534861456921}, {"step": 124, "kl": 0.34857173596510516, "ce": 0.5307632920869384}, {"step": 125, "kl": 0.2703474284792616, "ce": 0.5492560472039786}, {"step": 126, "kl": 0.2708383243667548, "ce": 0.5000255799293518}, {"step": 127, "kl": 0.33866491976469765, "ce": 0.527483966149584}, {"step": 128, "kl": 0.3113804478799143, "ce": 0.4466222720645094}, {"step": 129, "kl": 0.29519323018197147, "ce": 0.5483580235623876}, {"step": 130, "kl": 0.3023381860180979, "ce": 0.4928382876001821}, {"step": 131, "kl": 0.2977823416221062, "ce": 0.5154418567218612}, {"step": 132, "kl": 0.2842650377755655, "ce": 0.4977537367357205}, {"step": 133, "kl": 0.29856920799893083, "ce": 0.544126385033376}, {"step": 134, "kl": 0.2689965193076034, "ce": 0.48971418113469145}, {"step": 135, "kl": 0.28723431937302213, "ce": 0.5419102985078463}, {"step": 136, "kl": 0.33090565129309213, "ce": 0.541162105336948}, {"step": 137, "kl": 0.2785429751522438, "ce": 0.4631413218310422}, {"step": 138, "kl": 0.2846389147257131, "ce": 0.501548181609835}, {"step": 139, "kl": 0.28497519623515977, "ce": 0.4982358820090431}, {"step": 140, "kl": 0.2736019172938517, "ce": 0.4968269971592997}, {"step": 141, "kl": 0.2839945756683643, "ce": 0.5891326065089868}, {"step": 142, "kl": 0.2985514961157224, "ce": 0.49018849762582395}, {"step": 143, "kl": 0.26551191289812975, "ce": 0.4903574008243392}, {"step": 144, "kl": 0.2733346847073907, "ce": 0.4678270624334162}, {"step": 145, "kl": 0.26357376560005236, "ce": 0.4210203287506557}, {"step": 146, "kl": 0.3516029850497549, "ce": 0.5715146949957689}, {"step": 147, "kl": 0.2708138154268572, "ce": 0.49613096235770815}, {"step": 148, "kl": 0.30922704224192765, "ce": 0.5410618123624347}, {"step": 149, "kl": 0.3080172103651203, "ce": 0.569780132353898}, {"step": 150, "kl": 0.290732850453964, "ce": 0.5299815470508189}, {"step": 151, "kl": 0.2934977033721616, "ce": 0.5308857955699303}, {"step": 152, "kl": 0.30016585907453336, "ce": 0.5117733383376466}, {"step": 153, "kl": 0.31153643404940484, "ce": 0.4421773823824796}, {"step": 154, "kl": 0.3093808364297468, "ce": 0.5447533436310596}, {"step": 155, "kl": 0.28814798644005746, "ce": 0.4509008369095828}, {"step": 156, "kl": 0.27382912217589445, "ce": 0.5153016727099152}, {"step": 157, "kl": 0.30323313921532635, "ce": 0.4796288794572654}, {"step": 158, "kl": 0.30070941371719495, "ce": 0.5079307501695567}, {"step": 159, "kl": 0.30112603913231395, "ce": 0.5190303508191209}, {"step": 160, "kl": 0.2870911742128828, "ce": 0.5795015057313789}, {"step": 161, "kl": 0.28905263971126544, "ce": 0.4997692981340996}, {"step": 162, "kl": 0.32335019374894125, "ce": 0.5785122566149739}, {"step": 163, "kl": 0.2603937425322279, "ce": 0.47213290747544523}, {"step": 164, "kl": 0.2718250238772843, "ce": 0.4988623725043403}, {"step": 165, "kl": 0.26774784880092517, "ce": 0.4622393920005552}, {"step": 166, "kl": 0.32531691529634055, "ce": 0.5228258226905141}, {"step": 167, "kl": 0.30139852722539096, "ce": 0.49797967699767465}, {"step": 168, "kl": 0.28947337331729717, "ce": 0.5049228609434813}, {"step": 169, "kl": 0.27027970505460985, "ce": 0.48754138456825524}, {"step": 170, "kl": 0.2926497088401064, "ce": 0.5300390766764017}, {"step": 171, "kl": 0.26184074725500184, "ce": 0.4826056120105047}, {"step": 172, "kl": 0.31566411279707873, "ce": 0.5434174453391308}, {"step": 173, "kl": 0.28374218331690515, "ce": 0.5353773690512379}, {"step": 174, "kl": 0.26924490524373784, "ce": 0.43448999966767105}, {"step": 175, "kl": 0.26568012155753684, "ce": 0.5280050772207755}, {"step": 176, "kl": 0.2596172671065147, "ce": 0.41327415108467314}, {"step": 177, "kl": 0.2612672814782228, "ce": 0.46981129226968676}, {"step": 178, "kl": 0.27806658863052525, "ce": 0.5021481846193867}, {"step": 179, "kl": 0.2657609678698869, "ce": 0.5118526127027428}, {"step": 180, "kl": 0.3042230403082419, "ce": 0.5994222551248498}, {"step": 181, "kl": 0.2834751343668819, "ce": 0.5413924202241741}, {"step": 182, "kl": 0.2681640184200885, "ce": 0.5122914625250774}, {"step": 183, "kl": 0.29808744048059066, "ce": 0.5039535572746219}, {"step": 184, "kl": 0.3815301044353696, "ce": 0.47704671666104753}, {"step": 185, "kl": 0.2630468621718145, "ce": 0.5139281607894416}, {"step": 186, "kl": 0.2875552445266899, "ce": 0.4786221407239421}, {"step": 187, "kl": 0.30204851101147007, "ce": 0.543799521796926}, {"step": 188, "kl": 0.2655205254668669, "ce": 0.6522922279225389}, {"step": 189, "kl": 0.29933689800710267, "ce": 0.46135686845921764}, {"step": 190, "kl": 0.25493085693155376, "ce": 0.5084877714213465}, {"step": 191, "kl": 0.2674225043881245, "ce": 0.4632871502498911}, {"step": 192, "kl": 0.2857560145102466, "ce": 0.5094847526891326}, {"step": 193, "kl": 0.3518410608250748, "ce": 0.5468343908136541}, {"step": 194, "kl": 0.2568727107711429, "ce": 0.4295859884417228}, {"step": 195, "kl": 0.275053063280813, "ce": 0.5149568171363168}, {"step": 196, "kl": 0.26990076084329623, "ce": 0.4817874077818089}, {"step": 197, "kl": 0.2813095399444431, "ce": 0.5321622912309024}, {"step": 198, "kl": 0.2988356196626704, "ce": 0.5015164903179951}, {"step": 199, "kl": 0.2792074196198069, "ce": 0.5060164929236074}, {"step": 200, "kl": 0.26961586752147315, "ce": 0.47154550047905686}, {"step": 201, "kl": 0.27685030801753524, "ce": 0.4660765613721348}, {"step": 202, "kl": 0.30444803008243304, "ce": 0.47813740668375404}, {"step": 203, "kl": 0.28806365899225744, "ce": 0.47839140756879894}, {"step": 204, "kl": 0.2947177324349519, "ce": 0.5671307247781384}, {"step": 205, "kl": 0.30036342173740455, "ce": 0.5128610692492169}, {"step": 206, "kl": 0.308062732833165, "ce": 0.4882475808310615}, {"step": 207, "kl": 0.2848374024660649, "ce": 0.5048170227572106}, {"step": 208, "kl": 0.3167804153197202, "ce": 0.4934181047120914}, {"step": 209, "kl": 0.29410907901358485, "ce": 0.5323811520812332}, {"step": 210, "kl": 0.2911141295108024, "ce": 0.5035204850247301}, {"step": 211, "kl": 0.2735937081437516, "ce": 0.5849587128869332}, {"step": 212, "kl": 0.2846449915204009, "ce": 0.4868062637577489}, {"step": 213, "kl": 0.29204446738722634, "ce": 0.5409863108047868}, {"step": 214, "kl": 0.2722479342141987, "ce": 0.5654261978217839}, {"step": 215, "kl": 0.472080243633762, "ce": 0.572575183027925}, {"step": 216, "kl": 0.3117645627940049, "ce": 0.6350157803052092}, {"step": 217, "kl": 0.27444371630736775, "ce": 0.5141511994728253}, {"step": 218, "kl": 0.2768827865986324, "ce": 0.4538301960415035}, {"step": 219, "kl": 0.27553614980476443, "ce": 0.5215725345244546}, {"step": 220, "kl": 0.308813815826206, "ce": 0.5784725566229402}, {"step": 221, "kl": 0.29787257535469963, "ce": 0.5646255931105139}, {"step": 222, "kl": 0.2721894251168423, "ce": 0.4586582454607092}, {"step": 223, "kl": 0.3007021146427105, "ce": 0.4755910354479047}, {"step": 224, "kl": 0.2789243897372339, "ce": 0.4410317948162147}, {"step": 225, "kl": 0.2894960883698449, "ce": 0.46593607061831377}, {"step": 226, "kl": 0.34345618039982795, "ce": 0.48958630293733624}, {"step": 227, "kl": 0.283319046365972, "ce": 0.3154310990579816}, {"step": 228, "kl": 0.2859004595464328, "ce": 0.3685362612513544}, {"step": 229, "kl": 0.28538348529711355, "ce": 0.2815604269859571}, {"step": 230, "kl": 0.2972226620775742, "ce": 0.31565302302024617}, {"step": 231, "kl": 0.2802705082938398, "ce": 0.34760739278933167}, {"step": 232, "kl": 0.2984264074538048, "ce": 0.3509900219351511}, {"step": 233, "kl": 0.2877576322601862, "ce": 0.3971799973824724}, {"step": 234, "kl": 0.30108118011189644, "ce": 0.3017033765304363}, {"step": 235, "kl": 0.33707730698020194, "ce": 0.4203257072004915}, {"step": 236, "kl": 0.33166303709657263, "ce": 0.3570643803700856}, {"step": 237, "kl": 0.3046721589895798, "ce": 0.33998402481373674}, {"step": 238, "kl": 0.26103991937561233, "ce": 0.26909461504896404}, {"step": 239, "kl": 0.2617244523344391, "ce": 0.30953006380721976}, {"step": 240, "kl": 0.2787541579104368, "ce": 0.36349728005358795}, {"step": 241, "kl": 0.262873730596395, "ce": 0.3162688190630848}, {"step": 242, "kl": 0.2900084849721248, "ce": 0.3575026126183586}, {"step": 243, "kl": 0.2936142610449708, "ce": 0.28187678525342835}, {"step": 244, "kl": 0.2779373730558083, "ce": 0.3525781610722642}, {"step": 245, "kl": 0.2714406242320121, "ce": 0.3927949679057635}, {"step": 246, "kl": 0.2685783063861686, "ce": 0.3333576765171317}, {"step": 247, "kl": 0.27082489141662575, "ce": 0.28843063496073296}, {"step": 248, "kl": 0.30603712574211056, "ce": 0.3072324322511948}, {"step": 249, "kl": 0.3097563422347537, "ce": 0.3500833416077309}, {"step": 250, "kl": 0.26859667158387346, "ce": 0.29292525239959166}, {"step": 251, "kl": 0.2842702274041393, "ce": 0.3076930140774886}, {"step": 252, "kl": 0.26954645952478445, "ce": 0.32438805745586186}, {"step": 253, "kl": 0.27800711156752267, "ce": 0.2902662797862776}, {"step": 254, "kl": 0.2848729274902089, "ce": 0.335229857584064}, {"step": 255, "kl": 0.2651817544782902, "ce": 0.31682265587751157}, {"step": 256, "kl": 0.2766356941691972, "ce": 0.3043673354498964}, {"step": 257, "kl": 0.30039704796798183, "ce": 0.32183836378056696}, {"step": 258, "kl": 0.2768522847556013, "ce": 0.3050414933733201}, {"step": 259, "kl": 0.2887111278580398, "ce": 0.31752421945517345}, {"step": 260, "kl": 0.30487674210471166, "ce": 0.3903126973591879}, {"step": 261, "kl": 0.27316058022938516, "ce": 0.3284882094417025}, {"step": 262, "kl": 0.28796904509489957, "ce": 0.39796107160691396}, {"step": 263, "kl": 0.25229347033173455, "ce": 0.28997130446568026}, {"step": 264, "kl": 0.2879203556928826, "ce": 0.3103230437876027}, {"step": 265, "kl": 0.2602540108493877, "ce": 0.28596188981012005}, {"step": 266, "kl": 0.28335583434019523, "ce": 0.2965158559934311}, {"step": 267, "kl": 0.29518870798847946, "ce": 0.35567431510951936}, {"step": 268, "kl": 0.29829340025436046, "ce": 0.3540860832164459}, {"step": 269, "kl": 0.25488998599838575, "ce": 0.3394370712416794}, {"step": 270, "kl": 0.3128118670381327, "ce": 0.3094625241445916}, {"step": 271, "kl": 0.2920610477184427, "ce": 0.3538219023773078}, {"step": 272, "kl": 0.29114744358153144, "ce": 0.379496887687623}, {"step": 273, "kl": 0.2828008489237315, "ce": 0.3309274318636144}, {"step": 274, "kl": 0.2843375247699526, "ce": 0.34531165263419433}, {"step": 275, "kl": 0.27371974204434324, "ce": 0.31535361989515676}, {"step": 276, "kl": 0.27810440629618366, "ce": 0.28960088469546863}, {"step": 277, "kl": 0.30228139097626144, "ce": 0.3519536267529737}, {"step": 278, "kl": 0.29023370971749135, "ce": 0.3098819957914807}, {"step": 279, "kl": 0.30229007437098077, "ce": 0.383114719151853}, {"step": 280, "kl": 0.32234063225646736, "ce": 0.33132738926391214}, {"step": 281, "kl": 0.3023490173894522, "ce": 0.2974732142263993}, {"step": 282, "kl": 0.26294901070591314, "ce": 0.2989572159038698}, {"step": 283, "kl": 0.29232127586570944, "ce": 0.3427668746461103}, {"step": 284, "kl": 0.2721466559075071, "ce": 0.27071462376498245}, {"step": 285, "kl": 0.2777787788667827, "ce": 0.34655475927909785}, {"step": 286, "kl": 0.27818476336131504, "ce": 0.35199079263415156}, {"step": 287, "kl": 0.2755534014313487, "ce": 0.32418179121173796}, {"step": 288, "kl": 0.31215678171327493, "ce": 0.32978699512970755}, {"step": 289, "kl": 0.2686477643250882, "ce": 0.316872450501617}, {"step": 290, "kl": 0.2657155432393672, "ce": 0.29088473426240935}, {"step": 291, "kl": 0.2752993742242767, "ce": 0.31035247203861216}, {"step": 292, "kl": 0.2663391777369095, "ce": 0.3267358661371436}, {"step": 293, "kl": 0.5805862913028549, "ce": 0.32908144818896107}, {"step": 294, "kl": 0.2759018050743114, "ce": 0.29946669237483303}, {"step": 295, "kl": 0.2942335734122439, "ce": 0.32897922462356355}, {"step": 296, "kl": 0.2686054030008181, "ce": 0.3183847470704529}, {"step": 297, "kl": 0.275726352397464, "ce": 0.3015949468665751}, {"step": 298, "kl": 0.3408078135173521, "ce": 0.3043870043284591}, {"step": 299, "kl": 0.281340871510534, "ce": 0.35279952457026503}, {"step": 300, "kl": 0.259731622854185, "ce": 0.2903292084620888}, {"step": 301, "kl": 0.2789680540597518, "ce": 0.37889316676098045}, {"step": 302, "kl": 0.3027928176435452, "ce": 0.28607521832248817}, {"step": 303, "kl": 0.4331859384868336, "ce": 0.3017452591206664}, {"step": 304, "kl": 0.3541008251212835, "ce": 0.3478723251870215}, {"step": 305, "kl": 0.26754521745568355, "ce": 0.35062010723437087}, {"step": 306, "kl": 0.2817744571254874, "ce": 0.32922562460862953}, {"step": 307, "kl": 0.2731402560583251, "ce": 0.3587722726348961}, {"step": 308, "kl": 0.2900695672245594, "ce": 0.3645509773155582}, {"step": 309, "kl": 0.295209811394165, "ce": 0.336072466333989}, {"step": 310, "kl": 0.28780875448453225, "ce": 0.28411497490874515}, {"step": 311, "kl": 0.26933179219306735, "ce": 0.2885882116297386}, {"step": 312, "kl": 0.28834085081328253, "ce": 0.32503439077045015}, {"step": 313, "kl": 0.27104363756298555, "ce": 0.28597106341333056}, {"step": 314, "kl": 0.2902847511180933, "ce": 0.3463590171034197}, {"step": 315, "kl": 0.27605020866570196, "ce": 0.3345162065339025}, {"step": 316, "kl": 0.2924715670805302, "ce": 0.3150337663642232}, {"step": 317, "kl": 0.29354922209713163, "ce": 0.3625225816118641}, {"step": 318, "kl": 0.2897819928946731, "ce": 0.2723474848050413}, {"step": 319, "kl": 0.2933219901577412, "ce": 0.3708617761552477}, {"step": 320, "kl": 0.2803469607629241, "ce": 0.3244579271770044}, {"step": 321, "kl": 0.2708702979227294, "ce": 0.3200143034200937}, {"step": 322, "kl": 0.28328524885073675, "ce": 0.3279291592400759}, {"step": 323, "kl": 0.2779557939231802, "ce": 0.36874763802963395}, {"step": 324, "kl": 0.34704379198994384, "ce": 0.2996975314392526}, {"step": 325, "kl": 0.27170977486246084, "ce": 0.3457840995392585}, {"step": 326, "kl": 0.2950456601726229, "ce": 0.2928061647957384}, {"step": 327, "kl": 0.2815908845096224, "ce": 0.33962625777639827}, {"step": 328, "kl": 0.2800525780351388, "ce": 0.2992682356583445}, {"step": 329, "kl": 0.29704262722953884, "ce": 0.3589749839621634}, {"step": 330, "kl": 0.27090100042834253, "ce": 0.3292384006009243}, {"step": 331, "kl": 0.28756518534653397, "ce": 0.3210138626968012}, {"step": 332, "kl": 0.2916749928207815, "ce": 0.35364076808510425}, {"step": 333, "kl": 0.3706399660788578, "ce": 0.3978210691849672}, {"step": 334, "kl": 0.3353441661336308, "ce": 0.3206160095916397}, {"step": 335, "kl": 0.28539068545994273, "ce": 0.3111348846119038}, {"step": 336, "kl": 0.2743166743708739, "ce": 0.31240023416186136}, {"step": 337, "kl": 0.29473666848484315, "ce": 0.3254657588027634}, {"step": 338, "kl": 0.2729289801420362, "ce": 0.29621261097768165}, {"step": 339, "kl": 0.2843062207271192, "ce": 0.3187311857410867}, {"step": 340, "kl": 0.27590839538362477, "ce": 0.33805944422333034}, {"step": 341, "kl": 0.26891066206920744, "ce": 0.3311930150874441}, {"step": 342, "kl": 0.28962648767867427, "ce": 0.33457117175739076}, {"step": 343, "kl": 0.26361700992456216, "ce": 0.33117489578592174}, {"step": 344, "kl": 0.28338848034691044, "ce": 0.33062545868349175}, {"step": 345, "kl": 0.2738853032698704, "ce": 0.3369558112398002}, {"step": 346, "kl": 0.29013328492297996, "ce": 0.27614322548292797}, {"step": 347, "kl": 0.2605294904675086, "ce": 0.359783367983824}, {"step": 348, "kl": 0.28591505127312966, "ce": 0.2905538744150892}, {"step": 349, "kl": 0.2572363342962193, "ce": 0.29032169801426044}, {"step": 350, "kl": 0.32231553212488234, "ce": 0.39347770132274645}, {"step": 351, "kl": 0.27979397026670744, "ce": 0.31910760220775924}, {"step": 352, "kl": 0.28846280738370583, "ce": 0.2917504522258868}, {"step": 353, "kl": 0.29396168708441794, "ce": 0.29884692241567046}, {"step": 354, "kl": 0.3182396786876041, "ce": 0.3339541845085207}, {"step": 355, "kl": 0.28714617552211763, "ce": 0.3063644779562303}, {"step": 356, "kl": 0.3040669892175748, "ce": 0.3085336007442571}, {"step": 357, "kl": 0.2786049601215811, "ce": 0.33948295366790704}, {"step": 358, "kl": 0.2883343469528925, "ce": 0.33895529929641666}, {"step": 359, "kl": 0.30604737059483084, "ce": 0.3401813018955028}, {"step": 360, "kl": 0.2744734601920841, "ce": 0.2929405552130302}, {"step": 361, "kl": 0.2927482594652225, "ce": 0.36066028050013954}, {"step": 362, "kl": 0.28780852083311803, "ce": 0.28074985811080055}, {"step": 363, "kl": 0.285095949442213, "ce": 0.3190586362387826}, {"step": 364, "kl": 0.2828736680056204, "ce": 0.2997113080939861}, {"step": 365, "kl": 0.2791709485218409, "ce": 0.3804762136784864}, {"step": 366, "kl": 0.266364412492002, "ce": 0.31742689930475676}, {"step": 367, "kl": 0.2779704451611723, "ce": 0.3074593246183274}, {"step": 368, "kl": 0.2724749738817772, "ce": 0.36473276674626887}, {"step": 369, "kl": 0.28673834932386133, "ce": 0.36906078379143353}, {"step": 370, "kl": 0.29562917892166674, "ce": 0.35617558540863653}, {"step": 371, "kl": 0.277006130995107, "ce": 0.2911685017319323}, {"step": 372, "kl": 0.2982202561320396, "ce": 0.3473745432521398}, {"step": 373, "kl": 0.28579614660242103, "ce": 0.3203907554083838}, {"step": 374, "kl": 0.2858732464434854, "ce": 0.31859642610399624}, {"step": 375, "kl": 0.3019176109962955, "ce": 0.3042375993864489}, {"step": 376, "kl": 0.27279446527960144, "ce": 0.3048216499928049}, {"step": 377, "kl": 0.3037535165186259, "ce": 0.3417008882828419}, {"step": 378, "kl": 0.29869499402455524, "ce": 0.3637311436511852}, {"step": 379, "kl": 0.289102624963831, "ce": 0.3199350128784402}, {"step": 380, "kl": 0.3563191777050907, "ce": 0.393809453211188}, {"step": 381, "kl": 0.27337589078211405, "ce": 0.3653030347021034}, {"step": 382, "kl": 0.28125125639193954, "ce": 0.39371211503088205}, {"step": 383, "kl": 0.2909595474859855, "ce": 0.33801672021440266}, {"step": 384, "kl": 0.2979142541765837, "ce": 0.3419199185108575}, {"step": 385, "kl": 0.291627953854401, "ce": 0.3774930347861988}, {"step": 386, "kl": 0.2846501241258969, "ce": 0.31208208441405916}, {"step": 387, "kl": 0.3058250152512808, "ce": 0.2868827283382416}, {"step": 388, "kl": 0.2669177205004842, "ce": 0.3063179030103613}, {"step": 389, "kl": 0.2869484849539752, "ce": 0.2832632882254464}, {"step": 390, "kl": 0.2802394469184459, "ce": 0.36999346484508067}, {"step": 391, "kl": 0.252003211844137, "ce": 0.3419208087524894}, {"step": 392, "kl": 0.2877150860584021, "ce": 0.34308114455190264}, {"step": 393, "kl": 0.26911145244595036, "ce": 0.29023366460458633}, {"step": 394, "kl": 0.3111098531373387, "ce": 0.31151428598488495}, {"step": 395, "kl": 0.2693157355740169, "ce": 0.35076098684119134}, {"step": 396, "kl": 0.2927548830466502, "ce": 0.3259613951301382}, {"step": 397, "kl": 0.29337528577460514, "ce": 0.33190804386445566}, {"step": 398, "kl": 0.286440830861851, "ce": 0.2805250461765977}, {"step": 399, "kl": 0.31435320035479675, "ce": 0.3171756211959756}, {"step": 400, "kl": 0.27085698324561586, "ce": 0.2935436978871037}, {"step": 401, "kl": 0.27770514548530095, "ce": 0.2552719562954925}, {"step": 402, "kl": 0.27295509892562125, "ce": 0.28988066985158606}, {"step": 403, "kl": 0.2754116309046155, "ce": 0.33746163534655793}, {"step": 404, "kl": 0.2796606041697888, "ce": 0.3050299051126245}, {"step": 405, "kl": 0.2747748695931783, "ce": 0.33686611057388777}, {"step": 406, "kl": 0.2808491685258961, "ce": 0.4065104262106089}, {"step": 407, "kl": 0.27483633613010316, "ce": 0.3962176781196099}, {"step": 408, "kl": 0.2874188957184056, "ce": 0.3063160824861486}, {"step": 409, "kl": 0.282984505070066, "ce": 0.34598249810611215}, {"step": 410, "kl": 0.37339110614139503, "ce": 0.30594113460280425}, {"step": 411, "kl": 0.2807697148807503, "ce": 0.3688800806832653}, {"step": 412, "kl": 0.2940433200596615, "ce": 0.28372091039672226}, {"step": 413, "kl": 0.2730547688411396, "ce": 0.36753434707045385}, {"step": 414, "kl": 0.2808440440748369, "ce": 0.3736345359373336}, {"step": 415, "kl": 0.2765910053395301, "ce": 0.3484763138851519}, {"step": 416, "kl": 0.2936701654807502, "ce": 0.3399882115066184}, {"step": 417, "kl": 0.2994748613366104, "ce": 0.41700012773030726}, {"step": 418, "kl": 0.28630610346417285, "ce": 0.28858722508649415}, {"step": 419, "kl": 0.31727686880458206, "ce": 0.31438774979391765}, {"step": 420, "kl": 0.2849719322186852, "ce": 0.32767026531162546}, {"step": 421, "kl": 0.2529430260713835, "ce": 0.34656670803272804}, {"step": 422, "kl": 0.2802555930852768, "ce": 0.3013761896421779}, {"step": 423, "kl": 0.280977838160773, "ce": 0.35044639019926715}, {"step": 424, "kl": 0.2818719207263384, "ce": 0.366455493270057}, {"step": 425, "kl": 0.259127400142377, "ce": 0.2659740131474303}, {"step": 426, "kl": 0.32980520089946325, "ce": 0.3020917410178354}, {"step": 427, "kl": 0.2900674732995606, "ce": 0.3265310386740716}, {"step": 428, "kl": 0.28221577874247394, "ce": 0.24792374673830614}, {"step": 429, "kl": 0.2656128698005177, "ce": 0.3277098198223831}, {"step": 430, "kl": 0.2837535117863953, "ce": 0.35246101333418034}, {"step": 431, "kl": 0.4335067105955419, "ce": 0.3597044630009476}, {"step": 432, "kl": 0.29268260979613836, "ce": 0.2829677625802847}, {"step": 433, "kl": 0.27273800506486384, "ce": 0.305986794944333}, {"step": 434, "kl": 0.31981588650746484, "ce": 0.34294509370798665}, {"step": 435, "kl": 0.265668857322248, "ce": 0.26109274823182}, {"step": 436, "kl": 0.29179240167827725, "ce": 0.3083994188331602}, {"step": 437, "kl": 0.3299604347455148, "ce": 0.3294263026245075}, {"step": 438, "kl": 0.2906686861308856, "ce": 0.3389036396610745}, {"step": 439, "kl": 0.3100423925696451, "ce": 0.36848494986113717}, {"step": 440, "kl": 0.28727976571078456, "ce": 0.3264574138976169}, {"step": 441, "kl": 0.2975910256358407, "ce": 0.30711029515121924}, {"step": 442, "kl": 0.2946836931444439, "ce": 0.3321300082736545}, {"step": 443, "kl": 0.2863229977091259, "ce": 0.30161660735553153}, {"step": 444, "kl": 0.28099925131411163, "ce": 0.3106359690049441}, {"step": 445, "kl": 0.29616914414457457, "ce": 0.31325405529027256}, {"step": 446, "kl": 0.25438899236185064, "ce": 0.3060789102582789}, {"step": 447, "kl": 0.2724148037137167, "ce": 0.31922108219359735}, {"step": 448, "kl": 0.2975794804358153, "ce": 0.4159858976604799}, {"step": 449, "kl": 0.2731268708447777, "ce": 0.2819515177654271}, {"step": 450, "kl": 0.27365213300451907, "ce": 0.3095330965763026}, {"step": 451, "kl": 0.28676652845000206, "ce": 0.3230189053564342}, {"step": 452, "kl": 0.2678299208394492, "ce": 0.28474316514222736}], "val": [{"step": 0, "math_kl": 0.17059537193969265, "math_ce": 0.8387106338797149, "code_kl": 0.22116874322487284, "code_ce": 0.36744983409730037}, {"step": 226, "math_kl": 0.3170463335711894, "math_ce": 0.5382360695921073, "code_kl": 0.26155933840781004, "code_ce": 0.41313826973061246}, {"step": 452, "math_kl": 0.3111284448635371, "math_ce": 0.5593880869078782, "code_kl": 0.25701336478032866, "code_ce": 0.4099855431769864}]}
abl_sft_math_code_seed2/stage1_math/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a22cbfc09741846ab200ea6816ae08bd81649c42bc9d476e640737ed60986d1
3
+ size 988097824