Upload folder using huggingface_hub
Browse files- seq_math_code_seed2/results_stage2_code/gsm8k.jsonl +0 -0
- seq_math_code_seed2/results_stage2_code/humaneval.jsonl +0 -0
- seq_math_code_seed2/results_stage2_code/humaneval_eval_results.json +0 -0
- seq_math_code_seed2/results_stage2_code/mbpp.jsonl +0 -0
- seq_math_code_seed2/results_stage2_code/mbpp_eval_results.json +0 -0
- seq_math_code_seed2/results_stage2_code/summary.json +1 -0
- seq_math_code_seed2/stage2_code/config.json +57 -0
- seq_math_code_seed2/stage2_code/generation_config.json +14 -0
- seq_math_code_seed2/stage2_code/log.json +1 -0
- seq_math_code_seed2/stage2_code/model.safetensors +3 -0
seq_math_code_seed2/results_stage2_code/gsm8k.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code_seed2/results_stage2_code/humaneval.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code_seed2/results_stage2_code/humaneval_eval_results.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code_seed2/results_stage2_code/mbpp.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code_seed2/results_stage2_code/mbpp_eval_results.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code_seed2/results_stage2_code/summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "stage2_code", "gsm8k": 0.4382107657316149, "mbpp": 0.5026455026455027, "mbpp_plus": 0.42857142857142855, "humaneval": 0.35365853658536583, "humaneval_plus": 0.32926829268292684, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
|
seq_math_code_seed2/stage2_code/config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 21,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"num_attention_heads": 14,
|
| 43 |
+
"num_hidden_layers": 24,
|
| 44 |
+
"num_key_value_heads": 2,
|
| 45 |
+
"pad_token_id": null,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_parameters": {
|
| 48 |
+
"rope_theta": 1000000.0,
|
| 49 |
+
"rope_type": "default"
|
| 50 |
+
},
|
| 51 |
+
"sliding_window": null,
|
| 52 |
+
"tie_word_embeddings": true,
|
| 53 |
+
"transformers_version": "5.20.2",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"use_sliding_window": false,
|
| 56 |
+
"vocab_size": 151936
|
| 57 |
+
}
|
seq_math_code_seed2/stage2_code/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.20.2"
|
| 14 |
+
}
|
seq_math_code_seed2/stage2_code/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.24891521700679636, "ce": 0.38248973886129783}, {"step": 2, "kl": 0.27678330468621715, "ce": 0.42144909292244803}, {"step": 3, "kl": 0.23111390644162774, "ce": 0.38767092335905595}, {"step": 4, "kl": 0.23673262317832358, "ce": 0.37122631292692654}, {"step": 5, "kl": 0.27973040315892594, "ce": 0.36900727770965247}, {"step": 6, "kl": 0.2423086580471, "ce": 0.3519619886262774}, {"step": 7, "kl": 0.2506402012373621, "ce": 0.3215024567158904}, {"step": 8, "kl": 0.2628475120300914, "ce": 0.3548986898986727}, {"step": 9, "kl": 0.3012114387801008, "ce": 0.38490232690634374}, {"step": 10, "kl": 0.23604036510842435, "ce": 0.33345613420379827}, {"step": 11, "kl": 0.2601829696309465, "ce": 0.3477138841111963}, {"step": 12, "kl": 0.21232077039324201, "ce": 0.31816474758848856}, {"step": 13, "kl": 0.19784049523946448, "ce": 0.3102387983685543}, {"step": 14, "kl": 0.19719598495566815, "ce": 0.34059083482989283}, {"step": 15, "kl": 0.2358576075582478, "ce": 0.3155814905819987}, {"step": 16, "kl": 0.19547025755333403, "ce": 0.2868476922258095}, {"step": 17, "kl": 0.18897441434753406, "ce": 0.33422820136422543}, {"step": 18, "kl": 0.19647130088713785, "ce": 0.2680958754812216}, {"step": 19, "kl": 0.21935684267899444, "ce": 0.365861145695665}, {"step": 20, "kl": 0.21670541725005493, "ce": 0.3241510966518924}, {"step": 21, "kl": 0.20405350235532646, "ce": 0.2818853393014431}, {"step": 22, "kl": 0.239580943735912, "ce": 0.3694774604086005}, {"step": 23, "kl": 0.24186839312725356, "ce": 0.31457656265414286}, {"step": 24, "kl": 0.19077629032376628, "ce": 0.2888297587811249}, {"step": 25, "kl": 0.20808418392422948, "ce": 0.3479914323804998}, {"step": 26, "kl": 0.20332377873545146, "ce": 0.334143166245655}, {"step": 27, "kl": 0.19322605711715501, "ce": 0.30816526876642575}, {"step": 28, "kl": 0.2048471953564438, "ce": 0.32651477381659155}, {"step": 29, "kl": 0.1964091392681506, "ce": 0.2906285732865174}, {"step": 30, "kl": 0.2280498783369571, "ce": 0.3011418418016361}, {"step": 31, "kl": 0.19451180641567156, "ce": 0.2783357332538626}, {"step": 32, "kl": 0.20757844889275381, "ce": 0.31912691374433155}, {"step": 33, "kl": 0.20651116992738316, "ce": 0.30821864425353374}, {"step": 34, "kl": 0.2259958156283722, "ce": 0.32376237745166386}, {"step": 35, "kl": 0.19531373891550585, "ce": 0.32993063205202555}, {"step": 36, "kl": 0.17467706603514668, "ce": 0.2890376226609337}, {"step": 37, "kl": 0.19066295236349107, "ce": 0.3375388090544418}, {"step": 38, "kl": 0.1902419717758168, "ce": 0.27051039835991786}, {"step": 39, "kl": 0.18686612316013612, "ce": 0.2752480792063427}, {"step": 40, "kl": 0.18477467060993924, "ce": 0.2513986927452463}, {"step": 41, "kl": 0.19968133154212397, "ce": 0.3102809128252048}, {"step": 42, "kl": 0.18720628683188759, "ce": 0.3190863337843323}, {"step": 43, "kl": 0.19075981651646165, "ce": 0.3448840659961366}, {"step": 44, "kl": 0.16916796281413848, "ce": 0.30228416019284277}, {"step": 45, "kl": 0.19684709178209903, "ce": 0.31999261373277416}, {"step": 46, "kl": 0.20558326670406907, "ce": 0.3635685735129667}, {"step": 47, "kl": 0.18266023929858616, "ce": 0.2976960498790451}, {"step": 48, "kl": 0.1969394470549785, "ce": 0.28740247555486625}, {"step": 49, "kl": 0.19160986559326018, "ce": 0.2779422243444079}, {"step": 50, "kl": 0.19043291525933592, "ce": 0.2722228208356421}, {"step": 51, "kl": 0.19561805366723176, "ce": 0.2599797010717925}, {"step": 52, "kl": 0.20089578598123037, "ce": 0.32577141951864785}, {"step": 53, "kl": 0.1926507027628647, "ce": 0.3600555784077932}, {"step": 54, "kl": 0.21417687529199064, "ce": 0.3111570403612328}, {"step": 55, "kl": 0.18853626339335602, "ce": 0.35716376860819143}, {"step": 56, "kl": 0.1803585258202386, "ce": 0.3380853634403408}, {"step": 57, "kl": 0.2183172661092994, "ce": 0.3688346445624865}, {"step": 58, "kl": 0.17912969179702543, "ce": 0.2665126338291051}, {"step": 59, "kl": 0.19248955496269615, "ce": 0.2816355947944654}, {"step": 60, "kl": 0.19802685414333118, "ce": 0.2921961664637446}, {"step": 61, "kl": 0.18308776985777092, "ce": 0.29342162150409207}, {"step": 62, "kl": 0.17679423255288468, "ce": 0.3116482019758157}, {"step": 63, "kl": 0.18809274519537725, "ce": 0.3616415015257878}, {"step": 64, "kl": 0.17175686893100744, "ce": 0.2655983959799718}, {"step": 65, "kl": 0.17609814856503464, "ce": 0.30921067118669504}, {"step": 66, "kl": 0.19352871591289272, "ce": 0.307967539135267}, {"step": 67, "kl": 0.19936049678983525, "ce": 0.30658171748832563}, {"step": 68, "kl": 0.19234917269728657, "ce": 0.33208031453619014}, {"step": 69, "kl": 0.20311220303962108, "ce": 0.29920010311571527}, {"step": 70, "kl": 0.17534955652559675, "ce": 0.34657353646521843}, {"step": 71, "kl": 0.19062541075250775, "ce": 0.2817237142706587}, {"step": 72, "kl": 0.16150970816404003, "ce": 0.2763852150619944}, {"step": 73, "kl": 0.17508282192768515, "ce": 0.27997757729264744}, {"step": 74, "kl": 0.20010424470860133, "ce": 0.32871187953322145}, {"step": 75, "kl": 0.16582797588499534, "ce": 0.2225254593442995}, {"step": 76, "kl": 0.19936685664679415, "ce": 0.33077026599865667}, {"step": 77, "kl": 0.19940669774377862, "ce": 0.3151129127931212}, {"step": 78, "kl": 0.1686034630556257, "ce": 0.30768174719051566}, {"step": 79, "kl": 0.18757725365657496, "ce": 0.3191900955565874}, {"step": 80, "kl": 0.16443014772950454, "ce": 0.2670890264370045}, {"step": 81, "kl": 0.2020222882556308, "ce": 0.32231387085819585}, {"step": 82, "kl": 0.17984849489413118, "ce": 0.3104847689094146}, {"step": 83, "kl": 0.16665858552637675, "ce": 0.29136622400047796}, {"step": 84, "kl": 0.1827896137580809, "ce": 0.29741982606773265}, {"step": 85, "kl": 0.1865112323479112, "ce": 0.3047256428108656}, {"step": 86, "kl": 0.18489870290941546, "ce": 0.3135624425932607}, {"step": 87, "kl": 0.18992744679324614, "ce": 0.2992080890756658}, {"step": 88, "kl": 0.180623021986786, "ce": 0.3096322333880904}, {"step": 89, "kl": 0.17261350311731036, "ce": 0.32599172170538654}, {"step": 90, "kl": 0.18098242918491203, "ce": 0.29953848743861555}, {"step": 91, "kl": 0.15812452658977671, "ce": 0.2966615301808677}, {"step": 92, "kl": 0.18980638276490333, "ce": 0.30147687914132804}, {"step": 93, "kl": 0.15341312191315248, "ce": 0.285250106307022}, {"step": 94, "kl": 0.19159896888527392, "ce": 0.3464656259821749}, {"step": 95, "kl": 0.1521938664236402, "ce": 0.269316158174286}, {"step": 96, "kl": 0.18766784805882605, "ce": 0.2518689721224984}, {"step": 97, "kl": 0.18444282243100657, "ce": 0.3152493946952001}, {"step": 98, "kl": 0.19613451630950113, "ce": 0.317653106092702}, {"step": 99, "kl": 0.17491246686123385, "ce": 0.2886839997982551}, {"step": 100, "kl": 0.16668798478780478, "ce": 0.2852069321531241}, {"step": 101, "kl": 0.17232608656505777, "ce": 0.2684013801633157}, {"step": 102, "kl": 0.16998494028534938, "ce": 0.3211910658148655}, {"step": 103, "kl": 0.1832360727642667, "ce": 0.2926783466131841}, {"step": 104, "kl": 0.17358763527383608, "ce": 0.282272070106191}, {"step": 105, "kl": 0.1718149890002612, "ce": 0.2966790134082814}, {"step": 106, "kl": 0.20140506774648426, "ce": 0.34873511047636}, {"step": 107, "kl": 0.18408681797515308, "ce": 0.29503207035534035}, {"step": 108, "kl": 0.15313408023574873, "ce": 0.27734173736433043}, {"step": 109, "kl": 0.1975522250142591, "ce": 0.2866807796614934}, {"step": 110, "kl": 0.18690216554934994, "ce": 0.3083805164018}, {"step": 111, "kl": 0.2022707088320863, "ce": 0.34118064544995286}, {"step": 112, "kl": 0.18553050816243297, "ce": 0.3488672757805592}, {"step": 113, "kl": 0.15993756913046803, "ce": 0.26169313142207873}, {"step": 114, "kl": 0.17879786483115623, "ce": 0.2855082718829157}, {"step": 115, "kl": 0.1807111569272688, "ce": 0.27035311250786775}, {"step": 116, "kl": 0.16097636255309583, "ce": 0.2651020681782133}, {"step": 117, "kl": 0.15364486483450518, "ce": 0.2885111086793678}, {"step": 118, "kl": 0.22782086805083757, "ce": 0.28488471714810193}, {"step": 119, "kl": 0.19009059138952358, "ce": 0.30223222212357953}, {"step": 120, "kl": 0.16437236869007077, "ce": 0.24948252616062516}, {"step": 121, "kl": 0.16628813406228327, "ce": 0.2456041589973754}, {"step": 122, "kl": 0.16093926758692978, "ce": 0.3001108535621022}, {"step": 123, "kl": 0.14353854270474023, "ce": 0.2956773111774822}, {"step": 124, "kl": 0.16791792236932435, "ce": 0.26881009432935965}, {"step": 125, "kl": 0.18488305672720615, "ce": 0.260267849726779}, {"step": 126, "kl": 0.17628793173440477, "ce": 0.33683203092656355}, {"step": 127, "kl": 0.14910005482720518, "ce": 0.250637212358508}, {"step": 128, "kl": 0.16973574028851413, "ce": 0.24318385692263764}, {"step": 129, "kl": 0.1798391312580323, "ce": 0.2789791521940041}, {"step": 130, "kl": 0.17306256645951543, "ce": 0.3369212673626577}, {"step": 131, "kl": 0.14643632723285738, "ce": 0.2607868645261612}, {"step": 132, "kl": 0.1542378385816916, "ce": 0.2391439186342969}, {"step": 133, "kl": 0.16217058957225144, "ce": 0.24512255359703386}, {"step": 134, "kl": 0.18589197584805028, "ce": 0.29515973810564006}, {"step": 135, "kl": 0.18134105899489755, "ce": 0.3052312690793103}, {"step": 136, "kl": 0.15286262273198792, "ce": 0.2981616124437839}, {"step": 137, "kl": 0.1968827242211268, "ce": 0.3324727227308243}, {"step": 138, "kl": 0.21057578592643122, "ce": 0.3597420836565927}, {"step": 139, "kl": 0.1605708280869637, "ce": 0.2798164507489758}, {"step": 140, "kl": 0.1378666711938562, "ce": 0.27654799867147173}, {"step": 141, "kl": 0.17066578228523915, "ce": 0.2843763287467246}, {"step": 142, "kl": 0.1645993695598943, "ce": 0.29569019503301586}, {"step": 143, "kl": 0.18141902383091596, "ce": 0.2856554500965259}, {"step": 144, "kl": 0.1747882267078721, "ce": 0.33383601562657644}, {"step": 145, "kl": 0.1873931365140885, "ce": 0.31024644340674956}, {"step": 146, "kl": 0.1548583138541917, "ce": 0.2745512512665761}, {"step": 147, "kl": 0.1878975650871614, "ce": 0.3092789168685502}, {"step": 148, "kl": 0.14485956373234776, "ce": 0.2934714572917487}, {"step": 149, "kl": 0.1684931592506142, "ce": 0.2848152111975854}, {"step": 150, "kl": 0.1735729103634577, "ce": 0.27777076151626895}, {"step": 151, "kl": 0.16195069573309517, "ce": 0.3369986592756492}, {"step": 152, "kl": 0.18308350015338254, "ce": 0.3057258342408416}, {"step": 153, "kl": 0.1659514407448871, "ce": 0.2441811219734304}, {"step": 154, "kl": 0.17597640396208877, "ce": 0.3103632917823573}, {"step": 155, "kl": 0.14954300224504113, "ce": 0.27305952561138574}, {"step": 156, "kl": 0.14847792412346048, "ce": 0.2518605348863644}, {"step": 157, "kl": 0.1708040066975584, "ce": 0.2820911847592443}, {"step": 158, "kl": 0.1448102327493521, "ce": 0.2618150717680776}, {"step": 159, "kl": 0.20545363399921995, "ce": 0.3006899653502463}, {"step": 160, "kl": 0.200722273501604, "ce": 0.2708582792011501}, {"step": 161, "kl": 0.15100055156785241, "ce": 0.31509478628266546}, {"step": 162, "kl": 0.18027548965245352, "ce": 0.3067735785524343}, {"step": 163, "kl": 0.13521775020223537, "ce": 0.2823706536853474}, {"step": 164, "kl": 0.16198834886449937, "ce": 0.2708923461028884}, {"step": 165, "kl": 0.17270617246020112, "ce": 0.3645391794269004}, {"step": 166, "kl": 0.17802641335854, "ce": 0.2877571674333609}, {"step": 167, "kl": 0.1647780738132423, "ce": 0.2796688484268133}, {"step": 168, "kl": 0.1883317240898478, "ce": 0.31264330920899175}, {"step": 169, "kl": 0.17112278194246333, "ce": 0.2775813228345315}, {"step": 170, "kl": 0.16284275715930396, "ce": 0.26694125718566536}, {"step": 171, "kl": 0.18243017962404184, "ce": 0.32657871578628594}, {"step": 172, "kl": 0.1414742246182834, "ce": 0.24268576439390793}, {"step": 173, "kl": 0.1559863374944319, "ce": 0.2751289907040047}, {"step": 174, "kl": 0.16741747061562542, "ce": 0.30071373044708627}, {"step": 175, "kl": 0.20026431373383222, "ce": 0.35823603445322727}, {"step": 176, "kl": 0.13070538730790773, "ce": 0.33461137919798356}, {"step": 177, "kl": 0.19014991105198567, "ce": 0.2742361071462098}, {"step": 178, "kl": 0.17212973908368134, "ce": 0.26098589339142886}, {"step": 179, "kl": 0.17939335003548462, "ce": 0.30632010884116806}, {"step": 180, "kl": 0.13916478081118713, "ce": 0.2719231697084068}, {"step": 181, "kl": 0.17149297396341961, "ce": 0.25715145760597985}, {"step": 182, "kl": 0.16987199098295977, "ce": 0.3388309838199326}, {"step": 183, "kl": 0.188765809617498, "ce": 0.26275641478264733}, {"step": 184, "kl": 0.15672862902010593, "ce": 0.23521295188691965}, {"step": 185, "kl": 0.14969971326065978, "ce": 0.2608344273093046}, {"step": 186, "kl": 0.1615331629260472, "ce": 0.30202898185223315}, {"step": 187, "kl": 0.14672339618290092, "ce": 0.26807734096530855}, {"step": 188, "kl": 0.1336754519851896, "ce": 0.25616451540538665}, {"step": 189, "kl": 0.18078451808474166, "ce": 0.3131495501230719}, {"step": 190, "kl": 0.16157126637039215, "ce": 0.2664459899135921}, {"step": 191, "kl": 0.19200722653086386, "ce": 0.2984253266540411}, {"step": 192, "kl": 0.15460648987909106, "ce": 0.2565430282527565}, {"step": 193, "kl": 0.17196276942918093, "ce": 0.30889387917470645}, {"step": 194, "kl": 0.1671185140494222, "ce": 0.30844289837837047}, {"step": 195, "kl": 0.16915352643987105, "ce": 0.2828527970747514}, {"step": 196, "kl": 0.1466469154187752, "ce": 0.2666110996747885}, {"step": 197, "kl": 0.14321858858077127, "ce": 0.2565966741135131}, {"step": 198, "kl": 0.13939083437153427, "ce": 0.28486007247308287}, {"step": 199, "kl": 0.1864186696817298, "ce": 0.32721960920933674}, {"step": 200, "kl": 0.1766548209250174, "ce": 0.3283722177419674}, {"step": 201, "kl": 0.18038565428682074, "ce": 0.30488162231445315}, {"step": 202, "kl": 0.16837303001002263, "ce": 0.2521601561833313}, {"step": 203, "kl": 0.171510822031226, "ce": 0.25528448529065106}, {"step": 204, "kl": 0.14292384373268344, "ce": 0.29922597804751566}, {"step": 205, "kl": 0.17598316365925035, "ce": 0.24229084779997423}, {"step": 206, "kl": 0.17813108110945647, "ce": 0.273998761140251}, {"step": 207, "kl": 0.1564230152699808, "ce": 0.23520587980984944}, {"step": 208, "kl": 0.1919166265436299, "ce": 0.31130242483460047}, {"step": 209, "kl": 0.1578665821849635, "ce": 0.2615862209605706}, {"step": 210, "kl": 0.1912622360060159, "ce": 0.279959631566272}, {"step": 211, "kl": 0.18044282829709854, "ce": 0.34753574643816265}, {"step": 212, "kl": 0.16648174258180376, "ce": 0.2637147071911585}, {"step": 213, "kl": 0.15277636136687678, "ce": 0.26727649418994637}, {"step": 214, "kl": 0.21210932573247468, "ce": 0.4060761704310061}, {"step": 215, "kl": 0.16773587297677617, "ce": 0.35704600797919095}, {"step": 216, "kl": 0.16411320556746958, "ce": 0.28801344349490376}, {"step": 217, "kl": 0.15134976172706302, "ce": 0.2536777168706935}, {"step": 218, "kl": 0.1532966187318529, "ce": 0.2660389624170126}, {"step": 219, "kl": 0.17897905592194577, "ce": 0.34737201765471815}, {"step": 220, "kl": 0.14608099379877812, "ce": 0.26152950028931965}, {"step": 221, "kl": 0.1657903580099571, "ce": 0.31974233061941526}, {"step": 222, "kl": 0.16079044497870154, "ce": 0.2718867195505945}, {"step": 223, "kl": 0.15222861067901483, "ce": 0.30502933485318073}, {"step": 224, "kl": 0.16949451531574228, "ce": 0.2670313169799643}, {"step": 225, "kl": 0.18373906318821123, "ce": 0.26467983605857337}, {"step": 226, "kl": 0.14372095313983901, "ce": 0.25265478067921227}, {"step": 227, "kl": 0.17137230098701756, "ce": 0.3191066402738229}, {"step": 228, "kl": 0.1267280545786821, "ce": 0.1935229428250592}, {"step": 229, "kl": 0.11123462870754271, "ce": 0.2065221791290262}, {"step": 230, "kl": 0.1036874826422057, "ce": 0.23117570305275092}, {"step": 231, "kl": 0.107252238206439, "ce": 0.1923691803914872}, {"step": 232, "kl": 0.1220858654675183, "ce": 0.25899944919327916}, {"step": 233, "kl": 0.12822131329606726, "ce": 0.20367291411326585}, {"step": 234, "kl": 0.1047110472910503, "ce": 0.22825147228559137}, {"step": 235, "kl": 0.11162690704792602, "ce": 0.20713605126704052}, {"step": 236, "kl": 0.11276808136992136, "ce": 0.1817826591344358}, {"step": 237, "kl": 0.1329506376370031, "ce": 0.2166934372276388}, {"step": 238, "kl": 0.1120521692308645, "ce": 0.18356473931335693}, {"step": 239, "kl": 0.12260565406162502, "ce": 0.20396452333094447}, {"step": 240, "kl": 0.09707924318330441, "ce": 0.1797469598632588}, {"step": 241, "kl": 0.12391492910130442, "ce": 0.2311278616014249}, {"step": 242, "kl": 0.09919315580305998, "ce": 0.23762493598751905}, {"step": 243, "kl": 0.1187279187614241, "ce": 0.17740524276253367}, {"step": 244, "kl": 0.11307004769144226, "ce": 0.22457189982263975}, {"step": 245, "kl": 0.12488605910428331, "ce": 0.22164116307129014}, {"step": 246, "kl": 0.1242442867724593, "ce": 0.19469862302465796}, {"step": 247, "kl": 0.12307658403122118, "ce": 0.17796014192817988}, {"step": 248, "kl": 0.10003179831560269, "ce": 0.20041674504987017}, {"step": 249, "kl": 0.12688117739227084, "ce": 0.17575557412050952}, {"step": 250, "kl": 0.14683929051061517, "ce": 0.22612347979878267}, {"step": 251, "kl": 0.11965188364074159, "ce": 0.21843301128427328}, {"step": 252, "kl": 0.1330567897285755, "ce": 0.24030655861791334}, {"step": 253, "kl": 0.11424019353758455, "ce": 0.2401423972550608}, {"step": 254, "kl": 0.1287692538944941, "ce": 0.2140799422507427}, {"step": 255, "kl": 0.14539516698695198, "ce": 0.19833953686932612}, {"step": 256, "kl": 0.12123428816912432, "ce": 0.21004186132581906}, {"step": 257, "kl": 0.14263773966923332, "ce": 0.20802273696896414}, {"step": 258, "kl": 0.10524658380467214, "ce": 0.19529138174001667}, {"step": 259, "kl": 0.12979959004649466, "ce": 0.2435784442306789}, {"step": 260, "kl": 0.11838035518356524, "ce": 0.2260893154188582}, {"step": 261, "kl": 0.11198712107621682, "ce": 0.20012880451986184}, {"step": 262, "kl": 0.12061369155973775, "ce": 0.1838785804712949}, {"step": 263, "kl": 0.12237660440242355, "ce": 0.23558488947579323}, {"step": 264, "kl": 0.14631699195865658, "ce": 0.22578854423037842}, {"step": 265, "kl": 0.14275128124734154, "ce": 0.23023144854603877}, {"step": 266, "kl": 0.12012401522108859, "ce": 0.21749423303449517}, {"step": 267, "kl": 0.08825125532192096, "ce": 0.1938614307860842}, {"step": 268, "kl": 0.11360446820520946, "ce": 0.1938437638075455}, {"step": 269, "kl": 0.11688558699737167, "ce": 0.23374789497154055}, {"step": 270, "kl": 0.12132195407786911, "ce": 0.20721484489276998}, {"step": 271, "kl": 0.13359746454163868, "ce": 0.23403955355234554}, {"step": 272, "kl": 0.1299133680322162, "ce": 0.2171234895145588}, {"step": 273, "kl": 0.13150334966791286, "ce": 0.16634886293373158}, {"step": 274, "kl": 0.10497852964075935, "ce": 0.20218206689141774}, {"step": 275, "kl": 0.1296636334957407, "ce": 0.22484500715847805}, {"step": 276, "kl": 0.11758723955647357, "ce": 0.2116236093023483}, {"step": 277, "kl": 0.08864492542766596, "ce": 0.17445350809300197}, {"step": 278, "kl": 0.12213827545101644, "ce": 0.24226155330428922}, {"step": 279, "kl": 0.11653797958755562, "ce": 0.20005001697640698}, {"step": 280, "kl": 0.0924511278531828, "ce": 0.2031906609568459}, {"step": 281, "kl": 0.11990917045753319, "ce": 0.22095796455530822}, {"step": 282, "kl": 0.11572236775909595, "ce": 0.19074959379101264}, {"step": 283, "kl": 0.11808060468657039, "ce": 0.20554232532579417}, {"step": 284, "kl": 0.1191861042321897, "ce": 0.18489318210174657}, {"step": 285, "kl": 0.12587300737462065, "ce": 0.1917949849866178}, {"step": 286, "kl": 0.10702039181709652, "ce": 0.21633503140151672}, {"step": 287, "kl": 0.0989688743283243, "ce": 0.1761408021414079}, {"step": 288, "kl": 0.11546854663843259, "ce": 0.2026728611559948}, {"step": 289, "kl": 0.12776767078886198, "ce": 0.24534523886567536}, {"step": 290, "kl": 0.1144103766682029, "ce": 0.20730506233547047}, {"step": 291, "kl": 0.1279561253931991, "ce": 0.20816028710212453}, {"step": 292, "kl": 0.11444041415330065, "ce": 0.17522736150946758}, {"step": 293, "kl": 0.1099956861717162, "ce": 0.16593990721169813}, {"step": 294, "kl": 0.14327605099645013, "ce": 0.2024811813270086}, {"step": 295, "kl": 0.09522985989356049, "ce": 0.16383946076878964}, {"step": 296, "kl": 0.13129259796760342, "ce": 0.2390358407305737}, {"step": 297, "kl": 0.12532409789525314, "ce": 0.24958300034118452}, {"step": 298, "kl": 0.10653084154545146, "ce": 0.1972735210002828}, {"step": 299, "kl": 0.11606432554186355, "ce": 0.22162318533569197}, {"step": 300, "kl": 0.13433557616020814, "ce": 0.21718687271521037}, {"step": 301, "kl": 0.10936313402060276, "ce": 0.19877641867773482}, {"step": 302, "kl": 0.12127834296273465, "ce": 0.24074158813145}, {"step": 303, "kl": 0.13283312103446054, "ce": 0.2002541744396975}, {"step": 304, "kl": 0.09962857304910253, "ce": 0.20338831435383484}, {"step": 305, "kl": 0.13284239828808908, "ce": 0.20009701918693495}, {"step": 306, "kl": 0.12169587072664804, "ce": 0.18127281353877808}, {"step": 307, "kl": 0.10857373917812566, "ce": 0.2159298205919822}, {"step": 308, "kl": 0.1171721464230766, "ce": 0.21047775744352076}, {"step": 309, "kl": 0.08879041992592625, "ce": 0.14390339263497967}, {"step": 310, "kl": 0.1289610934741711, "ce": 0.23650345405017906}, {"step": 311, "kl": 0.11538111670514424, "ce": 0.1841730137506391}, {"step": 312, "kl": 0.10497255990781705, "ce": 0.24344274929126608}, {"step": 313, "kl": 0.12257322133690318, "ce": 0.2397351634745695}, {"step": 314, "kl": 0.1297148022466555, "ce": 0.17143410130550987}, {"step": 315, "kl": 0.12252914088233961, "ce": 0.2394295491612038}, {"step": 316, "kl": 0.1104080733590169, "ce": 0.1869460853057483}, {"step": 317, "kl": 0.12187825615505307, "ce": 0.2283445851896614}, {"step": 318, "kl": 0.10703581156806978, "ce": 0.20139265960881142}, {"step": 319, "kl": 0.13300889072864772, "ce": 0.18056267927234299}, {"step": 320, "kl": 0.13165897154903794, "ce": 0.20997982727173725}, {"step": 321, "kl": 0.11484553428910535, "ce": 0.20237385715195055}, {"step": 322, "kl": 0.11701090645244103, "ce": 0.19522259647076443}, {"step": 323, "kl": 0.10776414954144023, "ce": 0.2509190153227125}, {"step": 324, "kl": 0.12094918773798767, "ce": 0.2500709176708215}, {"step": 325, "kl": 0.12975737692932024, "ce": 0.21905498865324333}, {"step": 326, "kl": 0.09971986160401428, "ce": 0.22287788139702594}, {"step": 327, "kl": 0.0978920865988345, "ce": 0.1830774191585364}, {"step": 328, "kl": 0.10780025508010899, "ce": 0.1869430964552236}, {"step": 329, "kl": 0.13089023170727393, "ce": 0.2247621288858198}, {"step": 330, "kl": 0.12037750189662638, "ce": 0.23252932533097198}, {"step": 331, "kl": 0.11474014181129122, "ce": 0.21132831207511135}, {"step": 332, "kl": 0.10939025422794184, "ce": 0.16042200893600198}, {"step": 333, "kl": 0.12529103374330064, "ce": 0.2329201682028917}, {"step": 334, "kl": 0.10784505822549914, "ce": 0.18663713921582578}, {"step": 335, "kl": 0.11498678722543051, "ce": 0.21380438353002662}, {"step": 336, "kl": 0.13685732174958273, "ce": 0.24896424967400843}, {"step": 337, "kl": 0.0891280111253814, "ce": 0.18044664900535975}, {"step": 338, "kl": 0.12492622992277788, "ce": 0.1901779142748408}, {"step": 339, "kl": 0.1305638676237317, "ce": 0.2148486302602533}, {"step": 340, "kl": 0.14265480944836265, "ce": 0.23373256666691544}, {"step": 341, "kl": 0.1187609897455214, "ce": 0.23715234673541524}, {"step": 342, "kl": 0.10819408810809471, "ce": 0.19945984544425174}, {"step": 343, "kl": 0.11225564368553716, "ce": 0.19525702931688207}, {"step": 344, "kl": 0.12393984197692422, "ce": 0.2019423040217743}, {"step": 345, "kl": 0.1033833950455268, "ce": 0.20796519012412076}, {"step": 346, "kl": 0.11913473795970785, "ce": 0.20541138911569096}, {"step": 347, "kl": 0.10664469521839273, "ce": 0.21827954521611417}, {"step": 348, "kl": 0.11218043530835267, "ce": 0.1859456656802697}, {"step": 349, "kl": 0.09634185760652199, "ce": 0.19333795202161655}, {"step": 350, "kl": 0.13126464777482136, "ce": 0.20955107529208805}, {"step": 351, "kl": 0.11138308475530792, "ce": 0.20537807743493214}, {"step": 352, "kl": 0.1339178417372437, "ce": 0.19638504146409336}, {"step": 353, "kl": 0.11082059477946397, "ce": 0.18914819388358944}, {"step": 354, "kl": 0.1084048920944024, "ce": 0.18750977720040238}, {"step": 355, "kl": 0.11616242287669654, "ce": 0.19641248897665578}, {"step": 356, "kl": 0.096683656317586, "ce": 0.18366558808369388}, {"step": 357, "kl": 0.1282069255451949, "ce": 0.23426121041317843}, {"step": 358, "kl": 0.0966134733331335, "ce": 0.16969430379566305}, {"step": 359, "kl": 0.1033383883197416, "ce": 0.19984037810962904}, {"step": 360, "kl": 0.09037462780584438, "ce": 0.21250550545817706}, {"step": 361, "kl": 0.1131765154934434, "ce": 0.20034308917780796}, {"step": 362, "kl": 0.09844767614346936, "ce": 0.19803515513647377}, {"step": 363, "kl": 0.0928520485261855, "ce": 0.21797156235403264}, {"step": 364, "kl": 0.1176510391827976, "ce": 0.204911324374647}, {"step": 365, "kl": 0.10995822202580757, "ce": 0.19542780050782343}, {"step": 366, "kl": 0.09803937871223563, "ce": 0.1788144122283471}, {"step": 367, "kl": 0.12902347950628965, "ce": 0.20083887233996167}, {"step": 368, "kl": 0.10459220764110055, "ce": 0.19775138774388273}, {"step": 369, "kl": 0.10353778289245055, "ce": 0.20410696729151662}, {"step": 370, "kl": 0.1234302973735206, "ce": 0.20909989483043379}, {"step": 371, "kl": 0.11444006280930522, "ce": 0.2162115407153099}, {"step": 372, "kl": 0.09701026139381791, "ce": 0.22730754870028536}, {"step": 373, "kl": 0.10698812169421189, "ce": 0.19675601224104564}, {"step": 374, "kl": 0.1332898844340337, "ce": 0.2214680323595244}, {"step": 375, "kl": 0.12032467167968294, "ce": 0.19004331701735708}, {"step": 376, "kl": 0.09793390189567656, "ce": 0.1828614075401452}, {"step": 377, "kl": 0.13808133163987008, "ce": 0.17741258264804072}, {"step": 378, "kl": 0.10404604608999515, "ce": 0.19737434505651366}, {"step": 379, "kl": 0.13443015862646157, "ce": 0.21636378953499194}, {"step": 380, "kl": 0.11432568942156325, "ce": 0.21289061050463357}, {"step": 381, "kl": 0.11022240101845188, "ce": 0.18892367466587004}, {"step": 382, "kl": 0.11314633220591871, "ce": 0.1792430580045316}, {"step": 383, "kl": 0.13232612692834772, "ce": 0.18299722534355242}, {"step": 384, "kl": 0.11145474902887631, "ce": 0.1841219827170237}, {"step": 385, "kl": 0.10567906795828964, "ce": 0.205854093576713}, {"step": 386, "kl": 0.09763029528609553, "ce": 0.18017495964534788}, {"step": 387, "kl": 0.12257105684574207, "ce": 0.22446659818885423}, {"step": 388, "kl": 0.10068348604090074, "ce": 0.19011601363963976}, {"step": 389, "kl": 0.11499413991389562, "ce": 0.21561064575014063}, {"step": 390, "kl": 0.10621205435402682, "ce": 0.21483873960761193}, {"step": 391, "kl": 0.13329246814697046, "ce": 0.18248152905616205}, {"step": 392, "kl": 0.09147048255308671, "ce": 0.17675582641926652}, {"step": 393, "kl": 0.11792112767527849, "ce": 0.1691186601796306}, {"step": 394, "kl": 0.11472164948334855, "ce": 0.1935170634601912}, {"step": 395, "kl": 0.111437156835981, "ce": 0.21069911485418977}, {"step": 396, "kl": 0.11258838021097656, "ce": 0.23640336430777234}, {"step": 397, "kl": 0.10533843168560315, "ce": 0.17819062299621424}, {"step": 398, "kl": 0.1147744823146511, "ce": 0.21118124383153608}, {"step": 399, "kl": 0.10641607962861427, "ce": 0.18314301675308764}, {"step": 400, "kl": 0.0991053686090348, "ce": 0.1747124351073648}, {"step": 401, "kl": 0.1027853873181614, "ce": 0.1569156642223677}, {"step": 402, "kl": 0.10099472945455043, "ce": 0.18398346125091045}, {"step": 403, "kl": 0.09524129735844214, "ce": 0.1744450220951239}, {"step": 404, "kl": 0.10418471968817891, "ce": 0.19430446787618028}, {"step": 405, "kl": 0.11272711546815076, "ce": 0.17425945021990263}, {"step": 406, "kl": 0.10306007483194972, "ce": 0.1813495765579702}, {"step": 407, "kl": 0.11931976470100614, "ce": 0.1830823876787793}, {"step": 408, "kl": 0.11958711784304554, "ce": 0.1900204772627473}, {"step": 409, "kl": 0.12764403953727207, "ce": 0.18730567764712724}, {"step": 410, "kl": 0.12057008717809525, "ce": 0.22372889377005373}, {"step": 411, "kl": 0.10290934422700668, "ce": 0.1935087876406916}, {"step": 412, "kl": 0.12783949073760992, "ce": 0.22741416766787645}, {"step": 413, "kl": 0.10877089181636902, "ce": 0.19057822096447508}, {"step": 414, "kl": 0.12592414817795988, "ce": 0.20696458212042967}, {"step": 415, "kl": 0.12882261109696072, "ce": 0.19206048789371663}, {"step": 416, "kl": 0.12198026467057299, "ce": 0.18016016548212124}, {"step": 417, "kl": 0.12252657801927655, "ce": 0.20387238291232976}, {"step": 418, "kl": 0.10666215463377607, "ce": 0.19081678363435545}, {"step": 419, "kl": 0.08870975673777837, "ce": 0.17817790478393247}, {"step": 420, "kl": 0.13370710179425668, "ce": 0.18524911789826945}, {"step": 421, "kl": 0.1238931517756453, "ce": 0.17798402839767669}, {"step": 422, "kl": 0.13074782351633052, "ce": 0.21096290616878072}, {"step": 423, "kl": 0.10086866714158416, "ce": 0.19983038801591613}, {"step": 424, "kl": 0.11938842828987795, "ce": 0.22947673742428584}, {"step": 425, "kl": 0.09716041365416275, "ce": 0.2071203035097239}, {"step": 426, "kl": 0.10897545888650272, "ce": 0.19467852340074882}, {"step": 427, "kl": 0.10801516932187197, "ce": 0.18246296208079266}, {"step": 428, "kl": 0.11894795025603708, "ce": 0.2085364577088128}, {"step": 429, "kl": 0.1130691692705239, "ce": 0.21022541893003674}, {"step": 430, "kl": 0.09552642392708285, "ce": 0.22917052308196886}, {"step": 431, "kl": 0.10199397640676652, "ce": 0.20021724810874048}, {"step": 432, "kl": 0.12048273615950326, "ce": 0.1806378835053064}, {"step": 433, "kl": 0.11555806127916864, "ce": 0.20954160482428574}, {"step": 434, "kl": 0.11514848766357036, "ce": 0.1860287094709213}, {"step": 435, "kl": 0.12961922277360272, "ce": 0.2261969114874003}, {"step": 436, "kl": 0.11498594973011525, "ce": 0.18866390497519678}, {"step": 437, "kl": 0.11060523868163304, "ce": 0.20949190592192804}, {"step": 438, "kl": 0.12039269902660066, "ce": 0.1804121135292253}, {"step": 439, "kl": 0.1455517708517798, "ce": 0.27310339731269073}, {"step": 440, "kl": 0.13338068345481482, "ce": 0.22387454285442027}, {"step": 441, "kl": 0.09327637796380481, "ce": 0.17882536246060163}, {"step": 442, "kl": 0.12360993011982976, "ce": 0.2014202192269344}, {"step": 443, "kl": 0.09651506075476084, "ce": 0.19423068668388477}, {"step": 444, "kl": 0.11482535813968882, "ce": 0.20689126240054254}, {"step": 445, "kl": 0.10740696485510234, "ce": 0.19266984269425677}, {"step": 446, "kl": 0.11239852624780992, "ce": 0.2084787088587183}, {"step": 447, "kl": 0.12034108345968682, "ce": 0.2212311051358359}, {"step": 448, "kl": 0.129307865729433, "ce": 0.207471471453531}, {"step": 449, "kl": 0.11326785795553282, "ce": 0.21447308039521307}, {"step": 450, "kl": 0.11693342609722158, "ce": 0.1802758035367502}, {"step": 451, "kl": 0.12216547910528902, "ce": 0.24076601996628322}, {"step": 452, "kl": 0.09383689786916898, "ce": 0.17091645564195676}, {"step": 453, "kl": 0.11780370238662571, "ce": 0.2253434685037163}, {"step": 454, "kl": 0.10985673501536303, "ce": 0.2073160115108695}], "val": [{"step": 0, "math_kl": 0.13414361874729797, "math_ce": 0.5567842008328209, "code_kl": 0.24272848649640924, "code_ce": 0.39698887571778496}, {"step": 227, "math_kl": 0.14552594552114245, "math_ce": 0.560507619147111, "code_kl": 0.1703196380803912, "code_ce": 0.29493016548014694}, {"step": 454, "math_kl": 0.15278990159981176, "math_ce": 0.5718611987422842, "code_kl": 0.1642052145388151, "code_ce": 0.29368356716375066}]}
|
seq_math_code_seed2/stage2_code/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a39470caac0eaacc1ba2369f94c39cddbf6f69821d33b2f503db6e10e9730b15
|
| 3 |
+
size 988097824
|