Upload folder using huggingface_hub
Browse files- seq_math_code/results_stage2_code/gsm8k.jsonl +0 -0
- seq_math_code/results_stage2_code/humaneval.jsonl +0 -0
- seq_math_code/results_stage2_code/humaneval_eval_results.json +0 -0
- seq_math_code/results_stage2_code/mbpp.jsonl +0 -0
- seq_math_code/results_stage2_code/mbpp_eval_results.json +0 -0
- seq_math_code/results_stage2_code/summary.json +1 -0
- seq_math_code/stage2_code/config.json +57 -0
- seq_math_code/stage2_code/generation_config.json +14 -0
- seq_math_code/stage2_code/log.json +1 -0
- seq_math_code/stage2_code/model.safetensors +3 -0
seq_math_code/results_stage2_code/gsm8k.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code/results_stage2_code/humaneval.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code/results_stage2_code/humaneval_eval_results.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code/results_stage2_code/mbpp.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code/results_stage2_code/mbpp_eval_results.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
seq_math_code/results_stage2_code/summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "stage2_code", "gsm8k": 0.4275966641394996, "mbpp": 0.49206349206349204, "mbpp_plus": 0.42857142857142855, "humaneval": 0.35365853658536583, "humaneval_plus": 0.3231707317073171, "n_gsm8k": 1319, "n_mbpp": 378, "n_humaneval": 164}
|
seq_math_code/stage2_code/config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 21,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"num_attention_heads": 14,
|
| 43 |
+
"num_hidden_layers": 24,
|
| 44 |
+
"num_key_value_heads": 2,
|
| 45 |
+
"pad_token_id": null,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_parameters": {
|
| 48 |
+
"rope_theta": 1000000.0,
|
| 49 |
+
"rope_type": "default"
|
| 50 |
+
},
|
| 51 |
+
"sliding_window": null,
|
| 52 |
+
"tie_word_embeddings": true,
|
| 53 |
+
"transformers_version": "5.20.2",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"use_sliding_window": false,
|
| 56 |
+
"vocab_size": 151936
|
| 57 |
+
}
|
seq_math_code/stage2_code/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.20.2"
|
| 14 |
+
}
|
seq_math_code/stage2_code/log.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train": [{"step": 1, "kl": 0.2942881423062624, "ce": 0.45912709573121874}, {"step": 2, "kl": 0.2498457270679604, "ce": 0.3559412316742128}, {"step": 3, "kl": 0.239502315532323, "ce": 0.39118547196659903}, {"step": 4, "kl": 0.23581648234923616, "ce": 0.3597318666503506}, {"step": 5, "kl": 0.22017238504910228, "ce": 0.38592072812147404}, {"step": 6, "kl": 0.22808398440979463, "ce": 0.3526393298517655}, {"step": 7, "kl": 0.2469648986370429, "ce": 0.3469629657610271}, {"step": 8, "kl": 0.23462845055002712, "ce": 0.44165503343576273}, {"step": 9, "kl": 0.26667254028320314, "ce": 0.3040211332356272}, {"step": 10, "kl": 0.25892714323544813, "ce": 0.3308506032052933}, {"step": 11, "kl": 0.2006358187590424, "ce": 0.30646027659141967}, {"step": 12, "kl": 0.2192247925542867, "ce": 0.3516804163343484}, {"step": 13, "kl": 0.23483168089754197, "ce": 0.3311675396347495}, {"step": 14, "kl": 0.17795306483721965, "ce": 0.3079506926840924}, {"step": 15, "kl": 0.18964408538358807, "ce": 0.32306125590515833}, {"step": 16, "kl": 0.22718809510109184, "ce": 0.3227326632763921}, {"step": 17, "kl": 0.22247155565099147, "ce": 0.3302726527430966}, {"step": 18, "kl": 0.2216670651174934, "ce": 0.30534989246932154}, {"step": 19, "kl": 0.20799054660647273, "ce": 0.3005198338382559}, {"step": 20, "kl": 0.19366294536658113, "ce": 0.28584075023354044}, {"step": 21, "kl": 0.1995479078584283, "ce": 0.3235913089080402}, {"step": 22, "kl": 0.2339519461163543, "ce": 0.3398250712511941}, {"step": 23, "kl": 0.22323922565894713, "ce": 0.33620200297309555}, {"step": 24, "kl": 0.21052763078740455, "ce": 0.2923483505007396}, {"step": 25, "kl": 0.20092651265663458, "ce": 0.2933901601886957}, {"step": 26, "kl": 0.20442843672379615, "ce": 0.3122937430307664}, {"step": 27, "kl": 0.25593469672072255, "ce": 0.3453954409246575}, {"step": 28, "kl": 0.2181364255692811, "ce": 0.3825252198617559}, {"step": 29, "kl": 0.20249582955921291, "ce": 0.2918620316147033}, {"step": 30, "kl": 0.19935939471720276, "ce": 0.35073329924655505}, {"step": 31, "kl": 0.22889219311720652, "ce": 0.3620610726597797}, {"step": 32, "kl": 0.20034884804297204, "ce": 0.2807414081658157}, {"step": 33, "kl": 0.21095967640290544, "ce": 0.344075267520103}, {"step": 34, "kl": 0.1928335718270447, "ce": 0.3316920479050974}, {"step": 35, "kl": 0.18282854950333075, "ce": 0.33644997847181723}, {"step": 36, "kl": 0.20199708693306945, "ce": 0.3216475320655539}, {"step": 37, "kl": 0.16975309933848093, "ce": 0.287461809420756}, {"step": 38, "kl": 0.20368634329133833, "ce": 0.34799581231294974}, {"step": 39, "kl": 0.24068942015782774, "ce": 0.35933722227431186}, {"step": 40, "kl": 0.1968981996775735, "ce": 0.2746492626430752}, {"step": 41, "kl": 0.23166831884821132, "ce": 0.36957816958551476}, {"step": 42, "kl": 0.1866440659922823, "ce": 0.24472807048721334}, {"step": 43, "kl": 0.1679754817281934, "ce": 0.29321577888534106}, {"step": 44, "kl": 0.2022440787801797, "ce": 0.32570514520847804}, {"step": 45, "kl": 0.18542116329343108, "ce": 0.3242652950802365}, {"step": 46, "kl": 0.1738602184834569, "ce": 0.2706419633427559}, {"step": 47, "kl": 0.17826821166754092, "ce": 0.2543074914936764}, {"step": 48, "kl": 0.21384360710640152, "ce": 0.3616511126382136}, {"step": 49, "kl": 0.17304418887599368, "ce": 0.30992024248763517}, {"step": 50, "kl": 0.17468995190975464, "ce": 0.30460872878116446}, {"step": 51, "kl": 0.1760391424807886, "ce": 0.24858467172600004}, {"step": 52, "kl": 0.18785735107958315, "ce": 0.3384899375076693}, {"step": 53, "kl": 0.20186900603666105, "ce": 0.3421944962978476}, {"step": 54, "kl": 0.18001963287754785, "ce": 0.25911618938465564}, {"step": 55, "kl": 0.19998378939989614, "ce": 0.3118209698764044}, {"step": 56, "kl": 0.17779265254376883, "ce": 0.3015620410916588}, {"step": 57, "kl": 0.2043360318830565, "ce": 0.33499351423369933}, {"step": 58, "kl": 0.19704710012590246, "ce": 0.318745528239919}, {"step": 59, "kl": 0.2084072983561886, "ce": 0.34458907642279396}, {"step": 60, "kl": 0.15123598994320012, "ce": 0.24370939673868125}, {"step": 61, "kl": 0.20828148296365204, "ce": 0.30764570858369433}, {"step": 62, "kl": 0.18453564643859863, "ce": 0.3146812456817075}, {"step": 63, "kl": 0.1968836493318232, "ce": 0.2772528713274717}, {"step": 64, "kl": 0.18869649911228614, "ce": 0.3294005201570615}, {"step": 65, "kl": 0.1838330007956474, "ce": 0.3022898744977821}, {"step": 66, "kl": 0.20232711963015373, "ce": 0.2903926077084323}, {"step": 67, "kl": 0.18267935946664896, "ce": 0.2623489868524479}, {"step": 68, "kl": 0.17113537561325798, "ce": 0.36926424353326165}, {"step": 69, "kl": 0.19672705363119025, "ce": 0.26279318178956274}, {"step": 70, "kl": 0.18671492510191073, "ce": 0.2926934053039212}, {"step": 71, "kl": 0.21026273925652667, "ce": 0.3082284923205465}, {"step": 72, "kl": 0.1923200477712103, "ce": 0.3396456433559272}, {"step": 73, "kl": 0.1770172466223443, "ce": 0.3268544586443696}, {"step": 74, "kl": 0.18654820424458485, "ce": 0.3057988532473811}, {"step": 75, "kl": 0.20219324276716, "ce": 0.31441253638575484}, {"step": 76, "kl": 0.14559229478555513, "ce": 0.2426848398889452}, {"step": 77, "kl": 0.18434250826632156, "ce": 0.2697735400255197}, {"step": 78, "kl": 0.20074174972414394, "ce": 0.3250701869524412}, {"step": 79, "kl": 0.223855502121236, "ce": 0.35632169097560307}, {"step": 80, "kl": 0.15833303180189445, "ce": 0.2810800020472184}, {"step": 81, "kl": 0.2002077955756501, "ce": 0.3649411755938863}, {"step": 82, "kl": 0.1981715101333232, "ce": 0.29330323401578345}, {"step": 83, "kl": 0.18475210028986946, "ce": 0.2975572848634144}, {"step": 84, "kl": 0.17189913740682713, "ce": 0.28954856872558593}, {"step": 85, "kl": 0.16623350487014235, "ce": 0.36021768461052495}, {"step": 86, "kl": 0.2080011907755659, "ce": 0.3008128861338931}, {"step": 87, "kl": 0.19072531673886362, "ce": 0.33577034866984595}, {"step": 88, "kl": 0.17357487682250214, "ce": 0.29017178448379666}, {"step": 89, "kl": 0.16737464875853292, "ce": 0.26413126955750166}, {"step": 90, "kl": 0.20422418044908397, "ce": 0.2572241213571353}, {"step": 91, "kl": 0.18397602672026225, "ce": 0.30472974609910397}, {"step": 92, "kl": 0.16997077205393574, "ce": 0.28051646870321684}, {"step": 93, "kl": 0.18259461851208547, "ce": 0.2987223842687774}, {"step": 94, "kl": 0.15866514072296725, "ce": 0.2801934219778179}, {"step": 95, "kl": 0.1698844897230483, "ce": 0.2901383216762029}, {"step": 96, "kl": 0.16745804613696494, "ce": 0.2782315153627728}, {"step": 97, "kl": 0.17823760200205102, "ce": 0.3355757252507995}, {"step": 98, "kl": 0.19501223309433097, "ce": 0.26101148120202255}, {"step": 99, "kl": 0.18279269433790638, "ce": 0.29200660059735434}, {"step": 100, "kl": 0.15427630007061055, "ce": 0.2486157462065679}, {"step": 101, "kl": 0.1651940953188199, "ce": 0.2691344339339459}, {"step": 102, "kl": 0.1404113914913527, "ce": 0.2589645442641571}, {"step": 103, "kl": 0.1625903862870543, "ce": 0.2671843770369905}, {"step": 104, "kl": 0.17342590759007676, "ce": 0.2857227646457693}, {"step": 105, "kl": 0.1596164929675546, "ce": 0.27663007163124703}, {"step": 106, "kl": 0.14658673133746075, "ce": 0.2655600539247476}, {"step": 107, "kl": 0.171162233142359, "ce": 0.3187402364570959}, {"step": 108, "kl": 0.19866924515004236, "ce": 0.3363720637337428}, {"step": 109, "kl": 0.20339741408163664, "ce": 0.2796784008496887}, {"step": 110, "kl": 0.18430043737596252, "ce": 0.3630029559852126}, {"step": 111, "kl": 0.1562478504167635, "ce": 0.26469460322476146}, {"step": 112, "kl": 0.18886357745894317, "ce": 0.3667596202756503}, {"step": 113, "kl": 0.18745260963107402, "ce": 0.3280503606418552}, {"step": 114, "kl": 0.19979609652389532, "ce": 0.3253284573359247}, {"step": 115, "kl": 0.19258604579799166, "ce": 0.3692918716376362}, {"step": 116, "kl": 0.191772473349074, "ce": 0.2873147398369498}, {"step": 117, "kl": 0.178505845117889, "ce": 0.28506685077019456}, {"step": 118, "kl": 0.16716650014888787, "ce": 0.2705052968826525}, {"step": 119, "kl": 0.17879735453401185, "ce": 0.282942099119662}, {"step": 120, "kl": 0.16489740638276282, "ce": 0.2809482611109113}, {"step": 121, "kl": 0.1772127109759988, "ce": 0.2952376053505819}, {"step": 122, "kl": 0.21058671674857046, "ce": 0.34652699360094574}, {"step": 123, "kl": 0.18922250020353984, "ce": 0.34569484513738885}, {"step": 124, "kl": 0.1571246484830494, "ce": 0.31088914670419554}, {"step": 125, "kl": 0.2237123442337652, "ce": 0.3158295737679201}, {"step": 126, "kl": 0.1966710287891358, "ce": 0.3018271976047092}, {"step": 127, "kl": 0.13182672230219933, "ce": 0.2187597556044107}, {"step": 128, "kl": 0.15234694440889682, "ce": 0.3162862008877015}, {"step": 129, "kl": 0.18040719274129846, "ce": 0.30197640689643657}, {"step": 130, "kl": 0.1530740915037698, "ce": 0.2811449139869525}, {"step": 131, "kl": 0.18198864316751062, "ce": 0.2613570626583212}, {"step": 132, "kl": 0.15389787666274748, "ce": 0.28094262553167126}, {"step": 133, "kl": 0.19022904751639286, "ce": 0.3099281563057198}, {"step": 134, "kl": 0.17056382553460966, "ce": 0.27348490629106403}, {"step": 135, "kl": 0.1329748956232123, "ce": 0.2565693681568018}, {"step": 136, "kl": 0.1739778589772793, "ce": 0.27277142741802946}, {"step": 137, "kl": 0.15222364725713347, "ce": 0.2484849122868795}, {"step": 138, "kl": 0.1785919039735399, "ce": 0.2712352324019225}, {"step": 139, "kl": 0.17977039166281228, "ce": 0.25740153908555236}, {"step": 140, "kl": 0.17399773424487724, "ce": 0.2682691891005806}, {"step": 141, "kl": 0.1772996512757475, "ce": 0.28201977163732206}, {"step": 142, "kl": 0.1762981170393602, "ce": 0.2426461083165177}, {"step": 143, "kl": 0.155532461086483, "ce": 0.2608602273252589}, {"step": 144, "kl": 0.16916911957382402, "ce": 0.2658732911202044}, {"step": 145, "kl": 0.15976992836686232, "ce": 0.29899969509895646}, {"step": 146, "kl": 0.18903355338722524, "ce": 0.3161215117800784}, {"step": 147, "kl": 0.14119075253913116, "ce": 0.23243799335078186}, {"step": 148, "kl": 0.1883910112300529, "ce": 0.33630100117091816}, {"step": 149, "kl": 0.20315348289825103, "ce": 0.33121910758160056}, {"step": 150, "kl": 0.16257227624586337, "ce": 0.28558162962350975}, {"step": 151, "kl": 0.16517854846313665, "ce": 0.3037801078482385}, {"step": 152, "kl": 0.17617875237935052, "ce": 0.24578790456616048}, {"step": 153, "kl": 0.1852911712440775, "ce": 0.26606384956076}, {"step": 154, "kl": 0.15532887555843078, "ce": 0.25150057035703544}, {"step": 155, "kl": 0.13947932131667315, "ce": 0.25346153813719857}, {"step": 156, "kl": 0.14999092100943628, "ce": 0.31334928956205005}, {"step": 157, "kl": 0.1637995236753567, "ce": 0.2909349298801552}, {"step": 158, "kl": 0.16340882062188777, "ce": 0.30969340728004635}, {"step": 159, "kl": 0.14818460221668545, "ce": 0.29033232522667}, {"step": 160, "kl": 0.19312072263767635, "ce": 0.3048777445470345}, {"step": 161, "kl": 0.1880823762279205, "ce": 0.31279192865521754}, {"step": 162, "kl": 0.15141931569801187, "ce": 0.2889524347135813}, {"step": 163, "kl": 0.20727696634936743, "ce": 0.31873561324053223}, {"step": 164, "kl": 0.1748611743906428, "ce": 0.28592142849841395}, {"step": 165, "kl": 0.1570766678333792, "ce": 0.2593956823556475}, {"step": 166, "kl": 0.16134480881073632, "ce": 0.2967586508707351}, {"step": 167, "kl": 0.1719023906411161, "ce": 0.25148641266356053}, {"step": 168, "kl": 0.14954091564438046, "ce": 0.28782887724614925}, {"step": 169, "kl": 0.14850826128367645, "ce": 0.2550925262004969}, {"step": 170, "kl": 0.19537847740934197, "ce": 0.3007689356284046}, {"step": 171, "kl": 0.15845641765030052, "ce": 0.259279463108769}, {"step": 172, "kl": 0.1769330061777906, "ce": 0.29618148506461806}, {"step": 173, "kl": 0.19431903837726938, "ce": 0.29067664129083803}, {"step": 174, "kl": 0.17662968236988455, "ce": 0.2940860711611234}, {"step": 175, "kl": 0.1498061805345211, "ce": 0.25416944661271684}, {"step": 176, "kl": 0.15143366479993464, "ce": 0.22655610513532815}, {"step": 177, "kl": 0.13866267095099327, "ce": 0.245873449520748}, {"step": 178, "kl": 0.16608160800971558, "ce": 0.31189672012775266}, {"step": 179, "kl": 0.18087312088000687, "ce": 0.27934024847795674}, {"step": 180, "kl": 0.16936565763743397, "ce": 0.3074775864917431}, {"step": 181, "kl": 0.16259314779104372, "ce": 0.3269340183687125}, {"step": 182, "kl": 0.17233790972979712, "ce": 0.2847726276419671}, {"step": 183, "kl": 0.1776429811746618, "ce": 0.3494542930351854}, {"step": 184, "kl": 0.1499674758749835, "ce": 0.28510127072217983}, {"step": 185, "kl": 0.16933627674976984, "ce": 0.3091695337395713}, {"step": 186, "kl": 0.1680817351504575, "ce": 0.28888292792889714}, {"step": 187, "kl": 0.20636310366052008, "ce": 0.3281631173694871}, {"step": 188, "kl": 0.19126136995818682, "ce": 0.34867681894037456}, {"step": 189, "kl": 0.12825185489876156, "ce": 0.24834620744924513}, {"step": 190, "kl": 0.17003606430071683, "ce": 0.31011236050217883}, {"step": 191, "kl": 0.17708983604018855, "ce": 0.31241946790777325}, {"step": 192, "kl": 0.19144515814194824, "ce": 0.361418467883248}, {"step": 193, "kl": 0.1557454693831825, "ce": 0.28659285340128066}, {"step": 194, "kl": 0.15960687478036165, "ce": 0.23686028017176455}, {"step": 195, "kl": 0.18451036738549603, "ce": 0.32734771069185237}, {"step": 196, "kl": 0.15778564798840156, "ce": 0.2612321887779882}, {"step": 197, "kl": 0.17409566291435108, "ce": 0.25918821767274186}, {"step": 198, "kl": 0.15468427247306038, "ce": 0.2810806219257904}, {"step": 199, "kl": 0.1559658264083782, "ce": 0.24533395233525554}, {"step": 200, "kl": 0.17714612499164167, "ce": 0.2890450516380552}, {"step": 201, "kl": 0.172537946633392, "ce": 0.3345418793761325}, {"step": 202, "kl": 0.12867032632349662, "ce": 0.28892208664760943}, {"step": 203, "kl": 0.14723297411005865, "ce": 0.260622093439954}, {"step": 204, "kl": 0.17714642032201455, "ce": 0.3351135838658652}, {"step": 205, "kl": 0.15468871837483936, "ce": 0.24520115311771695}, {"step": 206, "kl": 0.18804568063749894, "ce": 0.3262886277553392}, {"step": 207, "kl": 0.16359689060544658, "ce": 0.31787913750783825}, {"step": 208, "kl": 0.1934939589012753, "ce": 0.30968029728139423}, {"step": 209, "kl": 0.15857953067031205, "ce": 0.28172904635788104}, {"step": 210, "kl": 0.12621641356681068, "ce": 0.2285844704812947}, {"step": 211, "kl": 0.14622443906466168, "ce": 0.23560684452464353}, {"step": 212, "kl": 0.12998625127735647, "ce": 0.2187544725369308}, {"step": 213, "kl": 0.15576651222364515, "ce": 0.22907518268397328}, {"step": 214, "kl": 0.21864916904773551, "ce": 0.3243888109529093}, {"step": 215, "kl": 0.1797850975246267, "ce": 0.2926350299792272}, {"step": 216, "kl": 0.15723976224449857, "ce": 0.30438685893549955}, {"step": 217, "kl": 0.18179358708774965, "ce": 0.31380616602163053}, {"step": 218, "kl": 0.15197864595328742, "ce": 0.27718226478361707}, {"step": 219, "kl": 0.14037945658470866, "ce": 0.2497818166450998}, {"step": 220, "kl": 0.17948976899356772, "ce": 0.28330442256067284}, {"step": 221, "kl": 0.14796320762812998, "ce": 0.25683891054454155}, {"step": 222, "kl": 0.16624579051062882, "ce": 0.3560333150946136}, {"step": 223, "kl": 0.15509096367491615, "ce": 0.26728944109550473}, {"step": 224, "kl": 0.15155609299631287, "ce": 0.32493930179412633}, {"step": 225, "kl": 0.14027248483012178, "ce": 0.319578301044672}, {"step": 226, "kl": 0.14978655848232594, "ce": 0.28273246763350396}, {"step": 227, "kl": 0.17441898072262163, "ce": 0.24729547227659335}, {"step": 228, "kl": 0.1385600083342562, "ce": 0.22676707092878218}, {"step": 229, "kl": 0.12909638987996402, "ce": 0.1868830060780938}, {"step": 230, "kl": 0.12463748092037169, "ce": 0.2300934381978228}, {"step": 231, "kl": 0.14075610092956956, "ce": 0.2305890247546108}, {"step": 232, "kl": 0.13270760518553212, "ce": 0.21950639517283138}, {"step": 233, "kl": 0.12381818288803755, "ce": 0.19115930500989345}, {"step": 234, "kl": 0.11493500883277205, "ce": 0.2097463642383285}, {"step": 235, "kl": 0.1319676169319456, "ce": 0.23296170727165502}, {"step": 236, "kl": 0.10147031827482367, "ce": 0.1953299149222996}, {"step": 237, "kl": 0.10825009111949638, "ce": 0.2036683469437206}, {"step": 238, "kl": 0.141126109602479, "ce": 0.2031902537073911}, {"step": 239, "kl": 0.13567360220448488, "ce": 0.18506932620084357}, {"step": 240, "kl": 0.11112574669270238, "ce": 0.20918263626834271}, {"step": 241, "kl": 0.12460810723756205, "ce": 0.19743012187443798}, {"step": 242, "kl": 0.10442350210732972, "ce": 0.21160946023673982}, {"step": 243, "kl": 0.14752405976102112, "ce": 0.2549802719131958}, {"step": 244, "kl": 0.13391632946480841, "ce": 0.20571271951187756}, {"step": 245, "kl": 0.11213520808212449, "ce": 0.18730994031151496}, {"step": 246, "kl": 0.09852003917014174, "ce": 0.2075325292547723}, {"step": 247, "kl": 0.10261091337144962, "ce": 0.21722587025653695}, {"step": 248, "kl": 0.09951259247774404, "ce": 0.20087814652563096}, {"step": 249, "kl": 0.11133122520938205, "ce": 0.19509306808997845}, {"step": 250, "kl": 0.12079461843139237, "ce": 0.22054501387113568}, {"step": 251, "kl": 0.13767425328584254, "ce": 0.19376351723987917}, {"step": 252, "kl": 0.10200882735651806, "ce": 0.19323668225560245}, {"step": 253, "kl": 0.11564404911445318, "ce": 0.18496093486803983}, {"step": 254, "kl": 0.12590034036075368, "ce": 0.22907119831710893}, {"step": 255, "kl": 0.12631040651297032, "ce": 0.24303233076256578}, {"step": 256, "kl": 0.12722325619467986, "ce": 0.21635334341922083}, {"step": 257, "kl": 0.10440392064348457, "ce": 0.16914213310551088}, {"step": 258, "kl": 0.12381844477686296, "ce": 0.18840598387035082}, {"step": 259, "kl": 0.11638158734861787, "ce": 0.21478969203194048}, {"step": 260, "kl": 0.1207967203234206, "ce": 0.19257151238828263}, {"step": 261, "kl": 0.13083156176636834, "ce": 0.2544252926123876}, {"step": 262, "kl": 0.12044770273418937, "ce": 0.1984685215123025}, {"step": 263, "kl": 0.1314062272996125, "ce": 0.20870736943802598}, {"step": 264, "kl": 0.13048575212458247, "ce": 0.19484535741605397}, {"step": 265, "kl": 0.11366424492488048, "ce": 0.2253375095523152}, {"step": 266, "kl": 0.12482578246760606, "ce": 0.2152367742064572}, {"step": 267, "kl": 0.10501524841963698, "ce": 0.18433910916718732}, {"step": 268, "kl": 0.11316214713685999, "ce": 0.21573518605708164}, {"step": 269, "kl": 0.1041958424414283, "ce": 0.20713623263537698}, {"step": 270, "kl": 0.14649958273544034, "ce": 0.19333254677908762}, {"step": 271, "kl": 0.10416016690276532, "ce": 0.177592169502492}, {"step": 272, "kl": 0.13637607681232447, "ce": 0.2610883391572631}, {"step": 273, "kl": 0.11564692949455574, "ce": 0.20339123312427917}, {"step": 274, "kl": 0.13595869487252166, "ce": 0.1961556164401143}, {"step": 275, "kl": 0.10585820356450984, "ce": 0.19563858348249621}, {"step": 276, "kl": 0.1196164057557616, "ce": 0.23240424067018764}, {"step": 277, "kl": 0.10198562204445066, "ce": 0.19738611744742016}, {"step": 278, "kl": 0.11175044404796501, "ce": 0.1930562542687833}, {"step": 279, "kl": 0.12706209047775985, "ce": 0.18852036541433326}, {"step": 280, "kl": 0.10398786352653, "ce": 0.21777808251732414}, {"step": 281, "kl": 0.1062711587595145, "ce": 0.21466096887515373}, {"step": 282, "kl": 0.14455916303428124, "ce": 0.23562680486735776}, {"step": 283, "kl": 0.1362503655713657, "ce": 0.2197408104762216}, {"step": 284, "kl": 0.11139443956560612, "ce": 0.21908741563247888}, {"step": 285, "kl": 0.1328737929799985, "ce": 0.21864680544053947}, {"step": 286, "kl": 0.11187441480421267, "ce": 0.21685027995522885}, {"step": 287, "kl": 0.12940201107861665, "ce": 0.23392407633463547}, {"step": 288, "kl": 0.10804374142910572, "ce": 0.18703001063707295}, {"step": 289, "kl": 0.12331051259549314, "ce": 0.21455528302980914}, {"step": 290, "kl": 0.10389707916325769, "ce": 0.19290334110322682}, {"step": 291, "kl": 0.10442934875135068, "ce": 0.18091574067735486}, {"step": 292, "kl": 0.11616579220476297, "ce": 0.20430631319123116}, {"step": 293, "kl": 0.128912489534004, "ce": 0.18593569722796752}, {"step": 294, "kl": 0.13365435047389385, "ce": 0.2154040333641636}, {"step": 295, "kl": 0.09499672032356929, "ce": 0.20230482093583174}, {"step": 296, "kl": 0.13729611689402998, "ce": 0.29931780326864943}, {"step": 297, "kl": 0.10228177439853249, "ce": 0.2120750640690443}, {"step": 298, "kl": 0.13358399481697075, "ce": 0.22044716389755287}, {"step": 299, "kl": 0.09645562721769851, "ce": 0.20600086176359944}, {"step": 300, "kl": 0.13129887596463488, "ce": 0.20767367300200815}, {"step": 301, "kl": 0.10302115205982447, "ce": 0.19207207189464778}, {"step": 302, "kl": 0.10534303808976911, "ce": 0.17593116126890124}, {"step": 303, "kl": 0.11684840547876171, "ce": 0.21268469675804041}, {"step": 304, "kl": 0.10383956254878861, "ce": 0.1696094574715927}, {"step": 305, "kl": 0.10215492685096621, "ce": 0.17620057602451272}, {"step": 306, "kl": 0.12447571028534055, "ce": 0.17499315323024947}, {"step": 307, "kl": 0.12442578792132811, "ce": 0.21044157024375898}, {"step": 308, "kl": 0.128300742167543, "ce": 0.21204906209090235}, {"step": 309, "kl": 0.08849254373386414, "ce": 0.20638344229244796}, {"step": 310, "kl": 0.12001367851357939, "ce": 0.21108126055387103}, {"step": 311, "kl": 0.11571406923467711, "ce": 0.19788600129493158}, {"step": 312, "kl": 0.11394749866073427, "ce": 0.17338485471480594}, {"step": 313, "kl": 0.09746216232778168, "ce": 0.19336257363231388}, {"step": 314, "kl": 0.11133645143299413, "ce": 0.1794978317408636}, {"step": 315, "kl": 0.13307997479600897, "ce": 0.20992096750166828}, {"step": 316, "kl": 0.12881776355504804, "ce": 0.20259036631719302}, {"step": 317, "kl": 0.10651590981785905, "ce": 0.19572664325441452}, {"step": 318, "kl": 0.12930772335678123, "ce": 0.2029745550338007}, {"step": 319, "kl": 0.11916430348002696, "ce": 0.20583787268020687}, {"step": 320, "kl": 0.10608592414855958, "ce": 0.18439377092221146}, {"step": 321, "kl": 0.10333989636768534, "ce": 0.2053719362793568}, {"step": 322, "kl": 0.126514736996623, "ce": 0.2638567688627052}, {"step": 323, "kl": 0.12585750219661954, "ce": 0.2266603710057525}, {"step": 324, "kl": 0.10606893378583242, "ce": 0.18519655393501405}, {"step": 325, "kl": 0.09593516238852415, "ce": 0.20232279915839319}, {"step": 326, "kl": 0.12997901328685385, "ce": 0.2337811544471707}, {"step": 327, "kl": 0.1135031526436443, "ce": 0.2208277068577143}, {"step": 328, "kl": 0.11278415471439912, "ce": 0.19944304779186453}, {"step": 329, "kl": 0.11839284355332047, "ce": 0.18963510116990692}, {"step": 330, "kl": 0.12015649931336422, "ce": 0.18685520414262274}, {"step": 331, "kl": 0.14246960661074168, "ce": 0.24633853629051303}, {"step": 332, "kl": 0.11719578761337658, "ce": 0.2505505623662332}, {"step": 333, "kl": 0.10492617541391254, "ce": 0.16677189004470425}, {"step": 334, "kl": 0.11717966943712885, "ce": 0.22675986636468695}, {"step": 335, "kl": 0.09008562431710623, "ce": 0.20015837569108513}, {"step": 336, "kl": 0.11763119136752243, "ce": 0.19773666921819794}, {"step": 337, "kl": 0.10012591236833346, "ce": 0.15547489794860053}, {"step": 338, "kl": 0.11544903479386705, "ce": 0.20711777125297742}, {"step": 339, "kl": 0.11362317034662986, "ce": 0.21900054788349965}, {"step": 340, "kl": 0.09633989840350422, "ce": 0.17023441701883107}, {"step": 341, "kl": 0.13626560303270163, "ce": 0.19425205383017424}, {"step": 342, "kl": 0.11884088529582787, "ce": 0.20060734131679017}, {"step": 343, "kl": 0.11868175907313469, "ce": 0.19601744784037745}, {"step": 344, "kl": 0.1301890887091439, "ce": 0.1972151250509957}, {"step": 345, "kl": 0.10903938370937917, "ce": 0.17762246502601048}, {"step": 346, "kl": 0.10854771978803761, "ce": 0.19655391732301494}, {"step": 347, "kl": 0.11275522498361391, "ce": 0.1791994201404422}, {"step": 348, "kl": 0.1076085938856393, "ce": 0.18070895943362986}, {"step": 349, "kl": 0.11186850799861675, "ce": 0.1930819216316551}, {"step": 350, "kl": 0.09944753998567425, "ce": 0.19653721114269013}, {"step": 351, "kl": 0.09971236725146297, "ce": 0.2070856841605681}, {"step": 352, "kl": 0.12617354455844898, "ce": 0.2042969654293122}, {"step": 353, "kl": 0.11384842411021312, "ce": 0.20538443310160032}, {"step": 354, "kl": 0.11004768466553747, "ce": 0.20287028543644445}, {"step": 355, "kl": 0.13839290126688503, "ce": 0.22207580427777912}, {"step": 356, "kl": 0.12814623051176202, "ce": 0.2446663805709262}, {"step": 357, "kl": 0.11995560146680709, "ce": 0.23617517919714812}, {"step": 358, "kl": 0.10873049387861766, "ce": 0.19150825414236133}, {"step": 359, "kl": 0.11708564537407903, "ce": 0.2193987077536042}, {"step": 360, "kl": 0.0961231199986679, "ce": 0.19067695111898925}, {"step": 361, "kl": 0.15275985360076139, "ce": 0.2630927695391753}, {"step": 362, "kl": 0.12694165658920023, "ce": 0.2295261123060514}, {"step": 363, "kl": 0.09068168855459066, "ce": 0.1825664527434155}, {"step": 364, "kl": 0.10903889650253672, "ce": 0.19645823032323984}, {"step": 365, "kl": 0.09145838866716388, "ce": 0.1925165637699977}, {"step": 366, "kl": 0.09807068899582914, "ce": 0.21677685246435216}, {"step": 367, "kl": 0.11357532301657919, "ce": 0.1607245005464217}, {"step": 368, "kl": 0.11324115064036978, "ce": 0.16826862102647328}, {"step": 369, "kl": 0.10601645622601566, "ce": 0.18587913006635437}, {"step": 370, "kl": 0.12439023638310363, "ce": 0.1926460653628241}, {"step": 371, "kl": 0.1074171112480378, "ce": 0.16761460563627747}, {"step": 372, "kl": 0.12195067385352015, "ce": 0.20549269561910452}, {"step": 373, "kl": 0.12047288735394479, "ce": 0.22878044631880554}, {"step": 374, "kl": 0.132952006321454, "ce": 0.1887433098697927}, {"step": 375, "kl": 0.11024907117125757, "ce": 0.20910548095703124}, {"step": 376, "kl": 0.12309365606148269, "ce": 0.22409939819944352}, {"step": 377, "kl": 0.11699590141741474, "ce": 0.2286400024616333}, {"step": 378, "kl": 0.13581243151767236, "ce": 0.27645909387522144}, {"step": 379, "kl": 0.11532186497327802, "ce": 0.2038697618002156}, {"step": 380, "kl": 0.0923943845911179, "ce": 0.1886240895589193}, {"step": 381, "kl": 0.10675498065968571, "ce": 0.1696746175574027}, {"step": 382, "kl": 0.11676613347385505, "ce": 0.18980494121577116}, {"step": 383, "kl": 0.10983029636952883, "ce": 0.22567728508481819}, {"step": 384, "kl": 0.1572076129660366, "ce": 0.212025082160416}, {"step": 385, "kl": 0.10568274639199278, "ce": 0.2164543409741061}, {"step": 386, "kl": 0.12194988437370355, "ce": 0.17396013954422787}, {"step": 387, "kl": 0.09251761841063469, "ce": 0.16470842351315504}, {"step": 388, "kl": 0.10917548391817028, "ce": 0.18937837231773505}, {"step": 389, "kl": 0.10432916180189776, "ce": 0.18152202871687184}, {"step": 390, "kl": 0.1174283000722803, "ce": 0.1910395865808587}, {"step": 391, "kl": 0.12393044726240321, "ce": 0.2925696523565995}, {"step": 392, "kl": 0.1231957774854395, "ce": 0.21022592737023202}, {"step": 393, "kl": 0.09723254489034323, "ce": 0.19104496915984065}, {"step": 394, "kl": 0.12542038635526975, "ce": 0.24565146857225745}, {"step": 395, "kl": 0.11170888059226725, "ce": 0.20768397902384003}, {"step": 396, "kl": 0.13165906759408805, "ce": 0.21070252695391253}, {"step": 397, "kl": 0.09547399701414981, "ce": 0.18742248195963854}, {"step": 398, "kl": 0.08935392000206746, "ce": 0.2058113894556366}, {"step": 399, "kl": 0.12596077509490458, "ce": 0.17724007837450437}, {"step": 400, "kl": 0.0984111258232134, "ce": 0.1757323160204281}, {"step": 401, "kl": 0.1198215080119508, "ce": 0.2031427626581917}, {"step": 402, "kl": 0.09519671785098695, "ce": 0.19785614987637135}, {"step": 403, "kl": 0.1036944338174261, "ce": 0.19413500334958395}, {"step": 404, "kl": 0.11629848538774004, "ce": 0.18516420442695958}, {"step": 405, "kl": 0.11310455880162527, "ce": 0.18765445052801188}, {"step": 406, "kl": 0.10270726519045623, "ce": 0.1915353536318376}, {"step": 407, "kl": 0.09812789140703698, "ce": 0.23824683816631337}, {"step": 408, "kl": 0.1104836578670103, "ce": 0.19020983986961548}, {"step": 409, "kl": 0.134637601548733, "ce": 0.23729235901284287}, {"step": 410, "kl": 0.11837672621277036, "ce": 0.19147278477471966}, {"step": 411, "kl": 0.13090946955971217, "ce": 0.18401403988108914}, {"step": 412, "kl": 0.11953499501258864, "ce": 0.2124706245437612}, {"step": 413, "kl": 0.10542584339213992, "ce": 0.14308104393624657}, {"step": 414, "kl": 0.11566984004175494, "ce": 0.26973432181344303}, {"step": 415, "kl": 0.1201476599589846, "ce": 0.1689859721915194}, {"step": 416, "kl": 0.10087799124151763, "ce": 0.1825734583009163}, {"step": 417, "kl": 0.11572485865973149, "ce": 0.22124100125688517}, {"step": 418, "kl": 0.11407325025080017, "ce": 0.17099980066077203}, {"step": 419, "kl": 0.12629763723358395, "ce": 0.19081165444708909}, {"step": 420, "kl": 0.12044993822156691, "ce": 0.21683266093655892}, {"step": 421, "kl": 0.11893486707686443, "ce": 0.20803599484519814}, {"step": 422, "kl": 0.0953828477936036, "ce": 0.1695153329126721}, {"step": 423, "kl": 0.13337696853133577, "ce": 0.20975184521396137}, {"step": 424, "kl": 0.1088290718498894, "ce": 0.20418656828818726}, {"step": 425, "kl": 0.13051281126966424, "ce": 0.256125382425868}, {"step": 426, "kl": 0.10921934864167485, "ce": 0.2019569596352505}, {"step": 427, "kl": 0.09763685242332185, "ce": 0.17066939084108565}, {"step": 428, "kl": 0.11537027270672895, "ce": 0.19117797597995137}, {"step": 429, "kl": 0.11792359468527902, "ce": 0.1861696334442986}, {"step": 430, "kl": 0.10673900779085746, "ce": 0.1844387720852123}, {"step": 431, "kl": 0.10243904648894826, "ce": 0.18890812714928096}, {"step": 432, "kl": 0.10831264150932818, "ce": 0.19253524166658723}, {"step": 433, "kl": 0.13338677348077155, "ce": 0.19456921113217662}, {"step": 434, "kl": 0.11370971300185877, "ce": 0.2096577052888961}, {"step": 435, "kl": 0.09657316834857703, "ce": 0.22615440521357696}, {"step": 436, "kl": 0.12479389216317685, "ce": 0.20734897516150672}, {"step": 437, "kl": 0.12475624868374889, "ce": 0.21834918573453582}, {"step": 438, "kl": 0.10369133103357853, "ce": 0.15898654766699322}, {"step": 439, "kl": 0.11087217378601437, "ce": 0.1826454164322983}, {"step": 440, "kl": 0.11282343722213194, "ce": 0.18744349217676853}, {"step": 441, "kl": 0.10969941454770496, "ce": 0.2131949517835505}, {"step": 442, "kl": 0.10470365625710441, "ce": 0.22246665840613603}, {"step": 443, "kl": 0.10517379877919929, "ce": 0.2015117490356706}, {"step": 444, "kl": 0.11331360832567788, "ce": 0.2570792884842942}, {"step": 445, "kl": 0.13174633547659048, "ce": 0.20041126223117078}, {"step": 446, "kl": 0.1091380112635972, "ce": 0.25532027805855245}, {"step": 447, "kl": 0.09124471486541275, "ce": 0.17625062678363812}, {"step": 448, "kl": 0.09573738038129628, "ce": 0.17131474368682242}, {"step": 449, "kl": 0.11678474513963721, "ce": 0.21076986299338915}, {"step": 450, "kl": 0.13091791945814063, "ce": 0.18238386364774772}, {"step": 451, "kl": 0.12139296910119435, "ce": 0.22561684681755326}, {"step": 452, "kl": 0.11044876952416341, "ce": 0.20818864975692336}, {"step": 453, "kl": 0.11802319976046013, "ce": 0.21082247795665715}, {"step": 454, "kl": 0.1285804073122448, "ce": 0.19748650650553806}], "val": [{"step": 0, "math_kl": 0.1330653788388266, "math_ce": 0.5623124645095477, "code_kl": 0.24520690705204787, "code_ce": 0.399327636078645}, {"step": 227, "math_kl": 0.14483410309268557, "math_ce": 0.5592349891601713, "code_kl": 0.16969436328369075, "code_ce": 0.2966060364115647}, {"step": 454, "math_kl": 0.15209920736881358, "math_ce": 0.5723041478842336, "code_kl": 0.1623846335587957, "code_ce": 0.2927603319761217}]}
|
seq_math_code/stage2_code/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9f801170f546f498b5ff63c6cea97e4df6908178d8b53eedf620c9eff0300b9
|
| 3 |
+
size 988097824
|