jajamken commited on
Commit
3473c2c
·
verified ·
1 Parent(s): d8a98be

Upload folder using huggingface_hub

Browse files
abl_kl_only_code_math_seed2/results_stage2_math/gsm8k.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_code_math_seed2/results_stage2_math/humaneval.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_code_math_seed2/results_stage2_math/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_stage2_math/mbpp.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
abl_kl_only_code_math_seed2/results_stage2_math/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_stage2_math/summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "stage2_math", "gsm8k": 0.5072024260803639, "mbpp": 0.47354497354497355, "mbpp_plus": 0.41798941798941797, "humaneval": 0.3597560975609756, "humaneval_plus": 0.3231707317073171, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
abl_kl_only_code_math_seed2/stage2_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_kl_only_code_math_seed2/stage2_math/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "5.20.2"
14
+ }
abl_kl_only_code_math_seed2/stage2_math/log.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [{"step": 1, "kl": 0.13908143490048538, "ce": 0.7487105860574236}, {"step": 2, "kl": 0.14578089425324905, "ce": 0.6924710767022495}, {"step": 3, "kl": 0.15894616191232083, "ce": 0.6709063539894415}, {"step": 4, "kl": 0.13358119600478083, "ce": 0.6427811114789477}, {"step": 5, "kl": 0.17182009256928904, "ce": 0.731796079434378}, {"step": 6, "kl": 0.12821812778667263, "ce": 0.6786622856602524}, {"step": 7, "kl": 0.12204364810963056, "ce": 0.6485160584690765}, {"step": 8, "kl": 0.14592863567420358, "ce": 0.753650105999984}, {"step": 9, "kl": 0.12132575455786901, "ce": 0.7197163228646273}, {"step": 10, "kl": 0.1357098884708417, "ce": 0.7097837785078791}, {"step": 11, "kl": 0.1108454984777114, "ce": 0.7299813508134916}, {"step": 12, "kl": 0.15079021361556436, "ce": 0.8100239656862884}, {"step": 13, "kl": 0.12524537270113548, "ce": 0.7345622358029053}, {"step": 14, "kl": 0.1141632048697582, "ce": 0.7322460754262298}, {"step": 15, "kl": 0.16182809655247343, "ce": 0.8684129077448202}, {"step": 16, "kl": 0.11809636036165483, "ce": 0.6814004176638904}, {"step": 17, "kl": 0.12310112534116821, "ce": 0.7199947078053544}, {"step": 18, "kl": 0.12348197812335267, "ce": 0.8008555934927558}, {"step": 19, "kl": 0.12409449986049108, "ce": 0.7886172316448131}, {"step": 20, "kl": 0.12172092119888066, "ce": 0.781189873749923}, {"step": 21, "kl": 0.11969313651081716, "ce": 0.767516621235136}, {"step": 22, "kl": 0.13160020948512408, "ce": 0.8072106280225387}, {"step": 23, "kl": 0.12319668258379322, "ce": 0.8050048582015499}, {"step": 24, "kl": 0.12403925463684602, "ce": 0.7072491743067447}, {"step": 25, "kl": 0.12198117751180251, "ce": 0.7489471521949983}, {"step": 26, "kl": 0.1240473774742465, "ce": 0.7657652743799891}, {"step": 27, "kl": 0.12550950780717254, "ce": 0.822895491337715}, {"step": 28, "kl": 0.11049852013187716, "ce": 0.7399327603000906}, {"step": 29, "kl": 0.12697169164948116, "ce": 0.8283473537279212}, {"step": 30, "kl": 0.13088557652505145, "ce": 0.8785188006084783}, {"step": 31, "kl": 0.10904450238621383, "ce": 0.8437601247228178}, {"step": 32, "kl": 0.11502501493208324, "ce": 0.7243379522120801}, {"step": 33, "kl": 0.13793789188502203, "ce": 0.9318404385196895}, {"step": 34, "kl": 0.14738213523985846, "ce": 0.7484055844099162}, {"step": 35, "kl": 0.12662994384765625, "ce": 0.7977697228672375}, {"step": 36, "kl": 0.11229575771465579, "ce": 0.8431212829821038}, {"step": 37, "kl": 0.11608228423353256, "ce": 0.8316662824029968}, {"step": 38, "kl": 0.13676148219216697, "ce": 0.8312909196062785}, {"step": 39, "kl": 0.1274528229822878, "ce": 0.781090807225562}, {"step": 40, "kl": 0.1302279385653409, "ce": 0.8093942483640689}, {"step": 41, "kl": 0.14524369076830812, "ce": 0.8363610681879361}, {"step": 42, "kl": 0.1053233327135707, "ce": 0.8257202483362502}, {"step": 43, "kl": 0.14865974408696064, "ce": 0.855383378368313}, {"step": 44, "kl": 0.11585687156481453, "ce": 0.7696664449394447}, {"step": 45, "kl": 0.1175531303387108, "ce": 0.7899832478170095}, {"step": 46, "kl": 0.0925498821389609, "ce": 0.6674934532375215}, {"step": 47, "kl": 0.12741394562227493, "ce": 0.7621087166032707}, {"step": 48, "kl": 0.10841673895476778, "ce": 0.7365949943090564}, {"step": 49, "kl": 0.12197697681366311, "ce": 0.7911297319539734}, {"step": 50, "kl": 0.12763666194414125, "ce": 0.7678889611339312}, {"step": 51, "kl": 0.0965438531713568, "ce": 0.7278302279385653}, {"step": 52, "kl": 0.13827263304204224, "ce": 0.7119766144943991}, {"step": 53, "kl": 0.15451540968069818, "ce": 0.8116036622084178}, {"step": 54, "kl": 0.11640670821812898, "ce": 0.8144347494998175}, {"step": 55, "kl": 0.12943068200114807, "ce": 0.7745937457983045}, {"step": 56, "kl": 0.12067269198148037, "ce": 0.7723804099667998}, {"step": 57, "kl": 0.1105000138097188, "ce": 0.8781049890192576}, {"step": 58, "kl": 0.11686957215436981, "ce": 0.8607634382415903}, {"step": 59, "kl": 0.28121299515690085, "ce": 0.8676304797842314}, {"step": 60, "kl": 0.12827099604440168, "ce": 0.7953939252943213}, {"step": 61, "kl": 0.10733736379808625, "ce": 0.8155754683111671}, {"step": 62, "kl": 0.11963585291345954, "ce": 0.7889905891233406}, {"step": 63, "kl": 0.1004112369636341, "ce": 0.7047191371296282}, {"step": 64, "kl": 0.11574962422277348, "ce": 0.740307017560965}, {"step": 65, "kl": 0.12938529954165118, "ce": 0.74837874181931}, {"step": 66, "kl": 0.1235914165064847, "ce": 0.7900463607538086}, {"step": 67, "kl": 0.1158290692944893, "ce": 0.7809137849726229}, {"step": 68, "kl": 0.11379509281161186, "ce": 0.7668494575902036}, {"step": 69, "kl": 0.11027671496438882, "ce": 0.7926425661359515}, {"step": 70, "kl": 0.1268070299818969, "ce": 0.796902964370202}, {"step": 71, "kl": 0.12671084011050224, "ce": 0.7736021850325183}, {"step": 72, "kl": 0.11526724275580306, "ce": 0.8931135433660692}, {"step": 73, "kl": 0.13055835304279412, "ce": 0.7981260774281104}, {"step": 74, "kl": 0.1251573689165104, "ce": 0.7999928289632234}, {"step": 75, "kl": 0.09421535834788733, "ce": 0.8168376689479798}, {"step": 76, "kl": 0.1243881206046511, "ce": 0.8080891555484209}, {"step": 77, "kl": 0.11658996509518335, "ce": 0.835935402255287}, {"step": 78, "kl": 0.12682251125428734, "ce": 0.7589508703287872}, {"step": 79, "kl": 0.10228208314132929, "ce": 0.7038284415244411}, {"step": 80, "kl": 0.09905235126248944, "ce": 0.7795651063224338}, {"step": 81, "kl": 0.1849303472037073, "ce": 0.7523697723177942}, {"step": 82, "kl": 0.08500459791528372, "ce": 0.7437128686285638}, {"step": 83, "kl": 0.09868341867884897, "ce": 0.8172366157782422}, {"step": 84, "kl": 0.12667191709111075, "ce": 0.8077087836517324}, {"step": 85, "kl": 0.12171183207380137, "ce": 0.7954652753421025}, {"step": 86, "kl": 0.13753621296793025, "ce": 0.8537975159775337}, {"step": 87, "kl": 0.14643736600439988, "ce": 0.9289854564690481}, {"step": 88, "kl": 0.1216174492587666, "ce": 0.7931621477420083}, {"step": 89, "kl": 0.14823034636531335, "ce": 0.7718926806912608}, {"step": 90, "kl": 0.12172703654212177, "ce": 0.8045332417382419}, {"step": 91, "kl": 0.1261197189354545, "ce": 0.9397606135153829}, {"step": 92, "kl": 0.11315496229377467, "ce": 0.7893471590409634}, {"step": 93, "kl": 0.1625874907897827, "ce": 0.7943207969789874}, {"step": 94, "kl": 0.12980592112723596, "ce": 0.8381461945001463}, {"step": 95, "kl": 0.10034068487182986, "ce": 0.7712321751554247}, {"step": 96, "kl": 0.1281720269074474, "ce": 0.7735612575112907}, {"step": 97, "kl": 0.1405546864297265, "ce": 0.8459237905649037}, {"step": 98, "kl": 0.11797783555845145, "ce": 0.7345472395049859}, {"step": 99, "kl": 0.12639752619104042, "ce": 0.8554792530151063}, {"step": 100, "kl": 0.12358754253248286, "ce": 0.8438348396511972}, {"step": 101, "kl": 0.11339515309330965, "ce": 0.7857801230889709}, {"step": 102, "kl": 0.10317980247569229, "ce": 0.7863652675679675}, {"step": 103, "kl": 0.1254149462083452, "ce": 0.8473952026025636}, {"step": 104, "kl": 0.09896276634433969, "ce": 0.7738283961492134}, {"step": 105, "kl": 0.11602279534888442, "ce": 0.7879096131559176}, {"step": 106, "kl": 0.11656444380197664, "ce": 0.8497458372812641}, {"step": 107, "kl": 0.10630538763520984, "ce": 0.79211575004307}, {"step": 108, "kl": 0.09939364159917641, "ce": 0.7441808986153832}, {"step": 109, "kl": 0.11856896220060069, "ce": 0.7661833477020263}, {"step": 110, "kl": 0.1141408963619641, "ce": 0.7870608199936155}, {"step": 111, "kl": 0.10405821365331594, "ce": 0.7832945165322456}, {"step": 112, "kl": 0.10593072874905658, "ce": 0.756564808771787}, {"step": 113, "kl": 0.11065028020141976, "ce": 0.7832111348759943}, {"step": 114, "kl": 0.11358779502776732, "ce": 0.7960686501386574}, {"step": 115, "kl": 0.10364836419893614, "ce": 0.8496479841306169}, {"step": 116, "kl": 0.11533254004796131, "ce": 0.9172520491442282}, {"step": 117, "kl": 0.11553883042013315, "ce": 0.83887389088405}, {"step": 118, "kl": 0.12713220584563895, "ce": 0.86858379977873}, {"step": 119, "kl": 0.08994965734267586, "ce": 0.8089622442353134}, {"step": 120, "kl": 0.13079913317447986, "ce": 0.8302202274847251}, {"step": 121, "kl": 0.11200967827439005, "ce": 0.7265782686946978}, {"step": 122, "kl": 0.12315978513422571, "ce": 0.8669682249623047}, {"step": 123, "kl": 0.10868366286204564, "ce": 0.8608194202868732}, {"step": 124, "kl": 0.09878228463347648, "ce": 0.7559231031895496}, {"step": 125, "kl": 0.10683442032683439, "ce": 0.7988787035989745}, {"step": 126, "kl": 0.10145809703913272, "ce": 0.76628497640748}, {"step": 127, "kl": 0.09641655191611119, "ce": 0.8415630601856807}, {"step": 128, "kl": 0.13152616025516506, "ce": 0.8564464565878067}, {"step": 129, "kl": 0.10980777979337614, "ce": 0.7493483087547951}, {"step": 130, "kl": 0.0933382583965124, "ce": 0.7660007085165946}, {"step": 131, "kl": 0.11305611596509466, "ce": 0.773313284392404}, {"step": 132, "kl": 0.11049985185433613, "ce": 0.7559929241736729}, {"step": 133, "kl": 0.10638977164057498, "ce": 0.7412316871411873}, {"step": 134, "kl": 0.09593297091842642, "ce": 0.7029675050979144}, {"step": 135, "kl": 0.1377048587232128, "ce": 0.8779928765329374}, {"step": 136, "kl": 0.10015326955042193, "ce": 0.7499782032698803}, {"step": 137, "kl": 0.10313788682931865, "ce": 0.7766829526217585}, {"step": 138, "kl": 0.12535156826528554, "ce": 0.8061592056637719}, {"step": 139, "kl": 0.11201635276603472, "ce": 0.9176914662197045}, {"step": 140, "kl": 0.10621316570125214, "ce": 0.8267355078981634}, {"step": 141, "kl": 0.1146092890887887, "ce": 0.7708179537077626}, {"step": 142, "kl": 0.11356034082230537, "ce": 0.9057482879369286}, {"step": 143, "kl": 0.13917502253704356, "ce": 0.782308701383047}, {"step": 144, "kl": 0.1192532955589941, "ce": 0.8716638723494808}, {"step": 145, "kl": 0.1113382313026231, "ce": 0.7945330847991756}, {"step": 146, "kl": 0.10477479810263025, "ce": 0.7268942773403815}, {"step": 147, "kl": 0.09345736104097188, "ce": 0.658810728534138}, {"step": 148, "kl": 0.11451710817468076, "ce": 0.8370385217231935}, {"step": 149, "kl": 0.10882076153908872, "ce": 0.8237637565986953}, {"step": 150, "kl": 0.11226204549435835, "ce": 0.8344974585699441}, {"step": 151, "kl": 0.14422496207674643, "ce": 0.7922201397514628}, {"step": 152, "kl": 0.12266801520488625, "ce": 0.8045073427560835}, {"step": 153, "kl": 0.1045197231698101, "ce": 0.7991371598928435}, {"step": 154, "kl": 0.11117032874616303, "ce": 0.8357399767345243}, {"step": 155, "kl": 0.10048167207962468, "ce": 0.7447276155974711}, {"step": 156, "kl": 0.1281127415264887, "ce": 0.7817836657820547}, {"step": 157, "kl": 0.11302067250040852, "ce": 0.8643815571192096}, {"step": 158, "kl": 0.09743539482216619, "ce": 0.8127774275565001}, {"step": 159, "kl": 0.1164390317222806, "ce": 0.7839980108577876}, {"step": 160, "kl": 0.09852372730216435, "ce": 0.8147531064148705}, {"step": 161, "kl": 0.12650159048825496, "ce": 0.8206080255054293}, {"step": 162, "kl": 0.10629847506399917, "ce": 0.811470069374477}, {"step": 163, "kl": 0.0953725277752222, "ce": 0.7767246679202064}, {"step": 164, "kl": 0.11952638886219447, "ce": 0.7861250389568258}, {"step": 165, "kl": 0.09913972030251711, "ce": 0.7653145525962897}, {"step": 166, "kl": 0.09968271763073183, "ce": 0.7451617314667021}, {"step": 167, "kl": 0.10717530806020702, "ce": 0.7581566057227961}, {"step": 168, "kl": 0.11416850265252394, "ce": 0.9125479049041492}, {"step": 169, "kl": 0.11101949661005397, "ce": 0.7641620252786019}, {"step": 170, "kl": 0.11873147265335933, "ce": 0.8806620620367096}, {"step": 171, "kl": 0.12078491763802662, "ce": 0.7737475055197012}, {"step": 172, "kl": 0.11059795312926955, "ce": 0.7883119136816459}, {"step": 173, "kl": 0.09730849056028988, "ce": 0.747278466103501}, {"step": 174, "kl": 0.10093934647457993, "ce": 0.7226119675932756}, {"step": 175, "kl": 0.08271481069273384, "ce": 0.7629487863740216}, {"step": 176, "kl": 0.1051840223159981, "ce": 0.8568710535295612}, {"step": 177, "kl": 0.10139892245078484, "ce": 0.7600265833770712}, {"step": 178, "kl": 0.10062588903264791, "ce": 0.8397927006856226}, {"step": 179, "kl": 0.09979555976189824, "ce": 0.8195013154930089}, {"step": 180, "kl": 0.10482867646791103, "ce": 0.9070941038911489}, {"step": 181, "kl": 0.13241290512170395, "ce": 0.7901691010242372}, {"step": 182, "kl": 0.14540624945423108, "ce": 0.702763713647358}, {"step": 183, "kl": 0.10413452928150745, "ce": 0.7898856493782846}, {"step": 184, "kl": 0.10878652540215394, "ce": 0.8325867134880555}, {"step": 185, "kl": 0.11301233255703204, "ce": 0.8269735005148968}, {"step": 186, "kl": 0.11865652606654742, "ce": 0.7751217184599882}, {"step": 187, "kl": 0.09019149685218159, "ce": 0.773811601472381}, {"step": 188, "kl": 0.09852268719121546, "ce": 0.7905292347164974}, {"step": 189, "kl": 0.08101447730326546, "ce": 0.7907468916271427}, {"step": 190, "kl": 0.10571688189570229, "ce": 0.7718916403567508}, {"step": 191, "kl": 0.10531924171793218, "ce": 0.7370964202788437}, {"step": 192, "kl": 0.12171553237712562, "ce": 0.928646356287137}, {"step": 193, "kl": 0.10116212047534649, "ce": 0.7025216451938464}, {"step": 194, "kl": 0.11233871568643891, "ce": 0.8258473698895678}, {"step": 195, "kl": 0.104669693313322, "ce": 0.8606827574558993}, {"step": 196, "kl": 0.09387692871348699, "ce": 0.790675523546007}, {"step": 197, "kl": 0.10965537718399586, "ce": 0.7650349610339396}, {"step": 198, "kl": 0.11547854523774428, "ce": 0.813130405078525}, {"step": 199, "kl": 0.11139965557426995, "ce": 0.78691223829678}, {"step": 200, "kl": 0.0968432163418096, "ce": 0.7647111036059545}, {"step": 201, "kl": 0.105216610587065, "ce": 0.7506338004227522}, {"step": 202, "kl": 0.10472995999912817, "ce": 0.7395232706195393}, {"step": 203, "kl": 0.11987429475524826, "ce": 0.8777593379140809}, {"step": 204, "kl": 0.0956049696637082, "ce": 0.708339310527631}, {"step": 205, "kl": 0.08725289796426632, "ce": 0.7240105022192375}, {"step": 206, "kl": 0.11553666116489093, "ce": 0.8801708474193266}, {"step": 207, "kl": 0.12201265821892518, "ce": 0.768994641333707}, {"step": 208, "kl": 0.1076278983012475, "ce": 0.850112238588629}, {"step": 209, "kl": 0.1188092153648748, "ce": 0.7966861704641414}, {"step": 210, "kl": 0.11088966124014595, "ce": 0.7408497104293893}, {"step": 211, "kl": 0.10370257147961007, "ce": 0.7842317474832897}, {"step": 212, "kl": 0.11193713028999479, "ce": 0.8195649766953722}, {"step": 213, "kl": 0.11624954558990815, "ce": 0.8300903754305207}, {"step": 214, "kl": 0.1065092766540539, "ce": 0.7560885549487386}, {"step": 215, "kl": 0.110477564430946, "ce": 0.8022579545940924}, {"step": 216, "kl": 0.09635226992229518, "ce": 0.7057493165103611}, {"step": 217, "kl": 0.09767423439416015, "ce": 0.7667543927539191}, {"step": 218, "kl": 0.12978305672140425, "ce": 0.8291862288023593}, {"step": 219, "kl": 0.09764573705790505, "ce": 0.8231770438151478}, {"step": 220, "kl": 0.1065345095354682, "ce": 0.8044141946569426}, {"step": 221, "kl": 0.10874551008587424, "ce": 0.9047164380550384}, {"step": 222, "kl": 0.1194077839565883, "ce": 0.8088979992808286}, {"step": 223, "kl": 0.12148828628672996, "ce": 0.8123150731646824}, {"step": 224, "kl": 0.1368575983939411, "ce": 0.754598830816314}, {"step": 225, "kl": 0.09925829048814444, "ce": 0.7478868629317889}, {"step": 226, "kl": 0.11679101096500723, "ce": 0.8232779652608165}, {"step": 227, "kl": 0.062410100714602394, "ce": 0.7671452883548914}, {"step": 228, "kl": 0.06156133214676403, "ce": 0.7926874054767098}, {"step": 229, "kl": 0.06578423603586461, "ce": 0.827942235911282}, {"step": 230, "kl": 0.051839591485622234, "ce": 0.7701047997659223}, {"step": 231, "kl": 0.08188010094399456, "ce": 0.8463376785115891}, {"step": 232, "kl": 0.060232754325618025, "ce": 0.8611554546287382}, {"step": 233, "kl": 0.0650525831938914, "ce": 0.8392871340906776}, {"step": 234, "kl": 0.06318325588939923, "ce": 0.8426409534230602}, {"step": 235, "kl": 0.05435154401602663, "ce": 0.7857819178333021}, {"step": 236, "kl": 0.07682737027874526, "ce": 0.8107759365625461}, {"step": 237, "kl": 0.0651819523484674, "ce": 0.8067142197701146}, {"step": 238, "kl": 0.060788741058029894, "ce": 0.7703008752231524}, {"step": 239, "kl": 0.07214333685490903, "ce": 0.8394572107250503}, {"step": 240, "kl": 0.05960738733587886, "ce": 0.8739007774240435}, {"step": 241, "kl": 0.06662506136132547, "ce": 0.851034064545606}, {"step": 242, "kl": 0.06491084175506852, "ce": 0.8237295147388152}, {"step": 243, "kl": 0.06710252922216244, "ce": 0.7549912095508008}, {"step": 244, "kl": 0.06021103644593476, "ce": 0.7891691852507707}, {"step": 245, "kl": 0.06425670600630894, "ce": 0.8474631054437953}, {"step": 246, "kl": 0.06345293371509012, "ce": 0.8631656508965398}, {"step": 247, "kl": 0.059939835216432355, "ce": 0.8314165518012606}, {"step": 248, "kl": 0.058314200654920226, "ce": 0.7727550734705725}, {"step": 249, "kl": 0.06765538019247949, "ce": 0.8629285742839177}, {"step": 250, "kl": 0.06962129657114624, "ce": 0.839452977070915}, {"step": 251, "kl": 0.07173679576200598, "ce": 0.7940828750250067}, {"step": 252, "kl": 0.06670131972829166, "ce": 0.7572622457127662}, {"step": 253, "kl": 0.047429918925488264, "ce": 0.831733710928137}, {"step": 254, "kl": 0.06226004880143697, "ce": 0.7627025146484375}, {"step": 255, "kl": 0.0691053116861979, "ce": 0.8158819656573374}, {"step": 256, "kl": 0.07396792685512989, "ce": 0.8667496904775014}, {"step": 257, "kl": 0.06144145418618763, "ce": 0.8364035009675147}, {"step": 258, "kl": 0.058895047609413234, "ce": 0.8349426732634789}, {"step": 259, "kl": 0.06912411155039175, "ce": 0.8388718431148062}, {"step": 260, "kl": 0.059026115551302036, "ce": 0.7580817406028094}, {"step": 261, "kl": 0.05958133508277392, "ce": 0.9285065312379358}, {"step": 262, "kl": 0.08339284130173084, "ce": 0.8852684584666242}, {"step": 263, "kl": 0.05810468360358745, "ce": 0.7961785985425095}, {"step": 264, "kl": 0.064747070474199, "ce": 0.8680489331193916}, {"step": 265, "kl": 0.06703495692057782, "ce": 0.9213953921669409}, {"step": 266, "kl": 0.058009215616932924, "ce": 0.8941362612524102}, {"step": 267, "kl": 0.06801387180226903, "ce": 0.8932641694229745}, {"step": 268, "kl": 0.06373682059428651, "ce": 0.8520380610721288}, {"step": 269, "kl": 0.05495018005371094, "ce": 0.8135590170907987}, {"step": 270, "kl": 0.054745872578331786, "ce": 0.8082815690879444}, {"step": 271, "kl": 0.05608302147887098, "ce": 0.8764474772110269}, {"step": 272, "kl": 0.05343654004422716, "ce": 0.7725278992848073}, {"step": 273, "kl": 0.06185249069671706, "ce": 0.9383086944718844}, {"step": 274, "kl": 0.06889529853372409, "ce": 0.7734830478827158}, {"step": 275, "kl": 0.0656231509891429, "ce": 0.7955234795447989}, {"step": 276, "kl": 0.0611622433582063, "ce": 0.8313568105589123}, {"step": 277, "kl": 0.056785204252450476, "ce": 0.8214549007917868}, {"step": 278, "kl": 0.05678646994494789, "ce": 0.7680508361563472}, {"step": 279, "kl": 0.049166145922979194, "ce": 0.7797111307849479}, {"step": 280, "kl": 0.07213981779332507, "ce": 0.8041700100987315}, {"step": 281, "kl": 0.062252829263846746, "ce": 0.8933600028296027}, {"step": 282, "kl": 0.061808110613462766, "ce": 0.7769484816781873}, {"step": 283, "kl": 0.06309561137979317, "ce": 0.9015313130530267}, {"step": 284, "kl": 0.07922916420398006, "ce": 0.9484912490085331}, {"step": 285, "kl": 0.054068462472470574, "ce": 0.8220926773429338}, {"step": 286, "kl": 0.07511373380335366, "ce": 0.8006872744012171}, {"step": 287, "kl": 0.058230692108117287, "ce": 0.8780685040765687}, {"step": 288, "kl": 0.049927827522844345, "ce": 0.7447192899850105}, {"step": 289, "kl": 0.054513129887369255, "ce": 0.9090996517497263}, {"step": 290, "kl": 0.053793948656221814, "ce": 0.7923785748541249}, {"step": 291, "kl": 0.06153929617934505, "ce": 0.8389563872672348}, {"step": 292, "kl": 0.05270916518389968, "ce": 0.8205295778670401}, {"step": 293, "kl": 0.05524257500930966, "ce": 0.80446034753192}, {"step": 294, "kl": 0.052710841034914, "ce": 0.8666419919353054}, {"step": 295, "kl": 0.06111325670897447, "ce": 0.8298001865965391}, {"step": 296, "kl": 0.05885912670409362, "ce": 0.769086112176554}, {"step": 297, "kl": 0.06215295749676993, "ce": 0.8586832648258458}, {"step": 298, "kl": 0.06675824167852384, "ce": 0.7785336623838798}, {"step": 299, "kl": 0.06104727528521404, "ce": 0.8474872171410055}, {"step": 300, "kl": 0.06231736474692969, "ce": 0.7966032139374377}, {"step": 301, "kl": 0.0478747818998234, "ce": 0.7815851183231675}, {"step": 302, "kl": 0.06099600526303109, "ce": 0.8692579705576666}, {"step": 303, "kl": 0.04797887122248983, "ce": 0.7100987842067298}, {"step": 304, "kl": 0.08302788856701973, "ce": 0.9102670501430709}, {"step": 305, "kl": 0.08010076617076543, "ce": 0.8547314453125001}, {"step": 306, "kl": 0.051113502017295476, "ce": 0.7778250672512406}, {"step": 307, "kl": 0.060340198824136174, "ce": 0.8223138690348548}, {"step": 308, "kl": 0.060524610191768975, "ce": 0.7795644318905468}, {"step": 309, "kl": 0.06140338108549882, "ce": 0.8586267477600812}, {"step": 310, "kl": 0.06272402439770847, "ce": 0.8926252021321563}, {"step": 311, "kl": 0.05132009115813915, "ce": 0.7274999390862664}, {"step": 312, "kl": 0.057837195303711966, "ce": 0.7740784291948948}, {"step": 313, "kl": 0.05178342299385613, "ce": 0.7313013332556947}, {"step": 314, "kl": 0.05252821431941494, "ce": 0.7912638006562065}, {"step": 315, "kl": 0.061893708865511765, "ce": 0.7746418704860072}, {"step": 316, "kl": 0.05662585576032215, "ce": 0.9220015333203846}, {"step": 317, "kl": 0.06211646048038297, "ce": 0.7663637130841578}, {"step": 318, "kl": 0.05570588266585922, "ce": 0.8193034598103388}, {"step": 319, "kl": 0.05830273585313387, "ce": 0.9166276205120065}, {"step": 320, "kl": 0.053830794380011066, "ce": 0.8928722814436555}, {"step": 321, "kl": 0.05221878483365414, "ce": 0.792411366482952}, {"step": 322, "kl": 0.055222462210556135, "ce": 0.8203430502638567}, {"step": 323, "kl": 0.056787643255675715, "ce": 0.7795363098304731}, {"step": 324, "kl": 0.050220638860927196, "ce": 0.7458106341590962}, {"step": 325, "kl": 0.06274348009552518, "ce": 0.8213779351410697}, {"step": 326, "kl": 0.05906358826062574, "ce": 0.7590585758088302}, {"step": 327, "kl": 0.06348207338384197, "ce": 0.7969387129546022}, {"step": 328, "kl": 0.0669336328628166, "ce": 0.8148228960043181}, {"step": 329, "kl": 0.066336383151637, "ce": 0.83743027672065}, {"step": 330, "kl": 0.05570299409312868, "ce": 0.8158693081793322}, {"step": 331, "kl": 0.05793914865002045, "ce": 0.7806963288382199}, {"step": 332, "kl": 0.058041943158529306, "ce": 0.8690842696226361}, {"step": 333, "kl": 0.051115947788273955, "ce": 0.9113755813184021}, {"step": 334, "kl": 0.04888048096889632, "ce": 0.756912938933026}, {"step": 335, "kl": 0.06740302615604943, "ce": 0.9129355294363839}, {"step": 336, "kl": 0.0505999989211429, "ce": 0.8562508502409825}, {"step": 337, "kl": 0.055399279856328455, "ce": 0.7811984646543347}, {"step": 338, "kl": 0.060708988071641656, "ce": 0.8147978513668745}, {"step": 339, "kl": 0.059040458937481985, "ce": 0.7651179784962371}, {"step": 340, "kl": 0.06078807407503798, "ce": 0.7942606211131497}, {"step": 341, "kl": 0.06183640071100962, "ce": 0.8270634488648212}, {"step": 342, "kl": 0.06110732430128479, "ce": 0.8926150968470703}, {"step": 343, "kl": 0.07659098259324508, "ce": 0.9197781820955542}, {"step": 344, "kl": 0.06423097161508473, "ce": 0.8257366461502877}, {"step": 345, "kl": 0.058659799842322315, "ce": 0.7866432131163329}, {"step": 346, "kl": 0.06206616880667156, "ce": 0.8656860746328153}, {"step": 347, "kl": 0.052023740055822706, "ce": 0.8155896591760473}, {"step": 348, "kl": 0.06160713414841874, "ce": 0.8162538264347956}, {"step": 349, "kl": 0.05675396802147007, "ce": 0.8447891463687378}, {"step": 350, "kl": 0.06657128244441679, "ce": 0.9149304533368254}, {"step": 351, "kl": 0.07276034629207918, "ce": 0.8089001961112756}, {"step": 352, "kl": 0.06488980504804684, "ce": 0.8101824951171875}, {"step": 353, "kl": 0.05724569748639098, "ce": 0.7890149563431581}, {"step": 354, "kl": 0.0579817404662274, "ce": 0.7581877198166513}, {"step": 355, "kl": 0.0446158636609925, "ce": 0.8564482975335335}, {"step": 356, "kl": 0.0514423061420452, "ce": 0.892296880998143}, {"step": 357, "kl": 0.059219433055013364, "ce": 0.8635346060213835}, {"step": 358, "kl": 0.06363889055082561, "ce": 0.8728310406827878}, {"step": 359, "kl": 0.055903396361050794, "ce": 0.8212469276071661}, {"step": 360, "kl": 0.05396938293114692, "ce": 0.7749036068143604}, {"step": 361, "kl": 0.0724716907093378, "ce": 0.9306999516720055}, {"step": 362, "kl": 0.05391644571812147, "ce": 0.8060427923343937}, {"step": 363, "kl": 0.05857099428932934, "ce": 0.8721683511703453}, {"step": 364, "kl": 0.05536987379988118, "ce": 0.8523880584070976}, {"step": 365, "kl": 0.06672875686200473, "ce": 0.888606833943642}, {"step": 366, "kl": 0.05271396575899819, "ce": 0.843112547600145}, {"step": 367, "kl": 0.05519820702703376, "ce": 0.8725895954862222}, {"step": 368, "kl": 0.05421499999937941, "ce": 0.886461551995392}, {"step": 369, "kl": 0.05680693742398095, "ce": 0.8776660211905157}, {"step": 370, "kl": 0.0625910703089235, "ce": 0.7662670817596233}, {"step": 371, "kl": 0.06210787018733238, "ce": 0.7893783453018073}, {"step": 372, "kl": 0.049148323312012604, "ce": 0.8732442139429031}, {"step": 373, "kl": 0.055519355254647615, "ce": 0.8181387697292688}, {"step": 374, "kl": 0.05627688919854512, "ce": 0.8965562347239808}, {"step": 375, "kl": 0.07264454865501566, "ce": 0.7356278391314517}, {"step": 376, "kl": 0.0627000697554264, "ce": 0.8402991673058003}, {"step": 377, "kl": 0.07135625786111471, "ce": 0.7882462033800259}, {"step": 378, "kl": 0.05232244153600607, "ce": 0.8836587125457609}, {"step": 379, "kl": 0.06237727167632465, "ce": 0.8322834646464974}, {"step": 380, "kl": 0.07469345623225637, "ce": 0.845762455691579}, {"step": 381, "kl": 0.05066709216783807, "ce": 0.7985514329342773}, {"step": 382, "kl": 0.0549704670806143, "ce": 0.830350501761252}, {"step": 383, "kl": 0.061515261332194, "ce": 0.8660017149654591}, {"step": 384, "kl": 0.06678527633094246, "ce": 0.8601812248938477}, {"step": 385, "kl": 0.07932868537914912, "ce": 0.9021524370395071}, {"step": 386, "kl": 0.07212739847272331, "ce": 0.8570289224406393}, {"step": 387, "kl": 0.06453171439792799, "ce": 0.8163439639538608}, {"step": 388, "kl": 0.05369531092354035, "ce": 0.8536388634494618}, {"step": 389, "kl": 0.05179153953333776, "ce": 0.8341149189063077}, {"step": 390, "kl": 0.0927801729430893, "ce": 0.9193613143353774}, {"step": 391, "kl": 0.06128081713250817, "ce": 0.842104220153453}, {"step": 392, "kl": 0.06108666444829671, "ce": 0.7816635956151025}, {"step": 393, "kl": 0.05678267620161184, "ce": 0.8583051548146587}, {"step": 394, "kl": 0.05089020970384227, "ce": 0.7711571494301596}, {"step": 395, "kl": 0.0587504249238614, "ce": 0.8826801876227061}, {"step": 396, "kl": 0.060255346578413777, "ce": 0.7896307047369089}, {"step": 397, "kl": 0.05139386302989707, "ce": 0.9145675922173349}, {"step": 398, "kl": 0.05527516947469456, "ce": 0.833111834962726}, {"step": 399, "kl": 0.0700312441318508, "ce": 0.9777263890518577}, {"step": 400, "kl": 0.05785307546383732, "ce": 0.8796182459173542}, {"step": 401, "kl": 0.05436021686238136, "ce": 0.700926397945929}, {"step": 402, "kl": 0.073881778553675, "ce": 0.8985244371972956}, {"step": 403, "kl": 0.06052027116803563, "ce": 0.9649168614889586}, {"step": 404, "kl": 0.06111105705515858, "ce": 0.8244623735497559}, {"step": 405, "kl": 0.06354123548990177, "ce": 0.8748450993841936}, {"step": 406, "kl": 0.061603098670758104, "ce": 0.7990012698703343}, {"step": 407, "kl": 0.055414999645458984, "ce": 0.8718079756957303}, {"step": 408, "kl": 0.06835205859199378, "ce": 0.7988705849056665}, {"step": 409, "kl": 0.0682339497654227, "ce": 0.8141498839683938}, {"step": 410, "kl": 0.060213510501718345, "ce": 0.7256517513642906}, {"step": 411, "kl": 0.05298092224197659, "ce": 0.8199830254595801}, {"step": 412, "kl": 0.05668787099060125, "ce": 0.7681801491071129}, {"step": 413, "kl": 0.10370364518955402, "ce": 0.8729840577250779}, {"step": 414, "kl": 0.05332413330453957, "ce": 0.8615586006240776}, {"step": 415, "kl": 0.06673245344345445, "ce": 0.861954596103766}, {"step": 416, "kl": 0.05725037599324053, "ce": 0.896318504577928}, {"step": 417, "kl": 0.04562883836522075, "ce": 0.7801602142344504}, {"step": 418, "kl": 0.06801137337652045, "ce": 0.8520789815755889}, {"step": 419, "kl": 0.06876942938200067, "ce": 0.7486362876472892}, {"step": 420, "kl": 0.052202965348740984, "ce": 0.7796079309276764}, {"step": 421, "kl": 0.061728411862178034, "ce": 0.8357028802500389}, {"step": 422, "kl": 0.05956158771532123, "ce": 0.8085881512110231}, {"step": 423, "kl": 0.052619681006945376, "ce": 0.8208602408742129}, {"step": 424, "kl": 0.05568744546903709, "ce": 0.8133822350001116}, {"step": 425, "kl": 0.05706001365119642, "ce": 0.8865321666789505}, {"step": 426, "kl": 0.06409089610958808, "ce": 0.8558032387181332}, {"step": 427, "kl": 0.06916208506380922, "ce": 0.8220455514446291}, {"step": 428, "kl": 0.08854257678033339, "ce": 0.8333637050621739}, {"step": 429, "kl": 0.06403889796689112, "ce": 0.8306636029965601}, {"step": 430, "kl": 0.05858037192062293, "ce": 0.8140247798338085}, {"step": 431, "kl": 0.06022326594301741, "ce": 0.8572109282580835}, {"step": 432, "kl": 0.0580945276992255, "ce": 0.758422731344436}, {"step": 433, "kl": 0.05443550232076673, "ce": 0.773831134397867}, {"step": 434, "kl": 0.06714490150600032, "ce": 0.7810941516843616}, {"step": 435, "kl": 0.05561476995196761, "ce": 0.7702596569446343}, {"step": 436, "kl": 0.06238900322192578, "ce": 0.8228945384197368}, {"step": 437, "kl": 0.058449562418976544, "ce": 0.7437924392787075}, {"step": 438, "kl": 0.06339121051637765, "ce": 0.8282751935593625}, {"step": 439, "kl": 0.0546454212157221, "ce": 0.7589322156866882}, {"step": 440, "kl": 0.05415778408879819, "ce": 0.811885371100842}, {"step": 441, "kl": 0.0559101613975048, "ce": 0.8218209797221493}, {"step": 442, "kl": 0.06541447165157128, "ce": 0.889889742844672}, {"step": 443, "kl": 0.05672981710528186, "ce": 0.8170552984620936}, {"step": 444, "kl": 0.05393231417327119, "ce": 0.7343699011204515}, {"step": 445, "kl": 0.06526618036225654, "ce": 0.825124628157111}, {"step": 446, "kl": 0.05413069866021281, "ce": 0.7815890609126388}, {"step": 447, "kl": 0.05069756486413717, "ce": 0.8148356949808023}, {"step": 448, "kl": 0.05841659877438817, "ce": 0.7939169427437635}, {"step": 449, "kl": 0.07076692003799631, "ce": 0.9006188545753482}, {"step": 450, "kl": 0.04840860376217095, "ce": 0.8619985467953264}, {"step": 451, "kl": 0.05998472401782797, "ce": 0.9299373949207546}, {"step": 452, "kl": 0.07930181199064221, "ce": 0.6900320197239327}], "val": [{"step": 0, "math_kl": 0.18258294918389784, "math_ce": 0.7625056700192647, "code_kl": 0.15285228025721925, "code_ce": 0.3675716286642528}, {"step": 226, "math_kl": 0.12257460683027342, "math_ce": 0.8434851139266772, "code_kl": 0.1691840969929724, "code_ce": 0.3716076417041461}, {"step": 452, "math_kl": 0.11870312600389393, "math_ce": 0.8786445487658298, "code_kl": 0.17295239515537902, "code_ce": 0.3761366171526216}]}
abl_kl_only_code_math_seed2/stage2_math/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5c2ff63cc74b61f89bebc570dcc421386cf44b895ad86a5aa804871d7c9b67
3
+ size 988097824