Upload SeRL checkpoints with ZipNN compression

.gitattributes

@@ -33,3 +33,17 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+serl_CodeMMLU_qwen25_0_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_CodeMMLU_qwen25_0_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+serl_DivLogicEval_qwen25_0_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_DivLogicEval_qwen25_0_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+serl_DivLogicEval_qwen25_1_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_DivLogicEval_qwen25_1_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+serl_JAMA_qwen25_0_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_JAMA_qwen25_0_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+serl_JAMA_qwen25_1_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_JAMA_qwen25_1_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+serl_SocialIQA_qwen25_0_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_SocialIQA_qwen25_0_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+serl_arce_qwen25_1_5b/model.safetensors.znn filter=lfs diff=lfs merge=lfs -text
+serl_arce_qwen25_1_5b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+tags:
+  - serl
+  - reinforcement-learning
+  - qwen2.5
+  - checkpoints
+---
+
+# SeRL Training Checkpoints
+
+Compressed checkpoints from SeRL (Self-Evolving Reinforcement Learning) experiments.
+Files use **ZipNN lossless compression** (~33% smaller, transparent loading).
+
+## Quick Start
+
+```bash
+pip install zipnn huggingface_hub transformers
+```
+
+```python
+# Enable ZipNN transparent loading
+from zipnn import zipnn_hf
+zipnn_hf()
+
+from huggingface_hub import snapshot_download
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Download specific checkpoint
+path = snapshot_download(
+    "AshwinKM2005/serl-checkpoints",
+    allow_patterns="serl_arce_qwen25_1_5b/huggingface/*"
+)
+
+# Load model (auto-decompresses .znn files)
+model = AutoModelForCausalLM.from_pretrained(
+    f"{path}/serl_arce_qwen25_1_5b/huggingface/global_step200_hf"
+)
+```
+
+## Experiments
+
+| Experiment | Base Model | Dataset |
+|------------|-----------|---------|
+| serl_arcc_qwen25_0_5b | Qwen2.5-0.5B | ARC-Challenge |
+| serl_ARC-c_qwen25_1_5b | Qwen2.5-1.5B | ARC-Challenge |
+| serl_arce_qwen25_0_5b | Qwen2.5-0.5B | ARC-Easy |
+| serl_arce_qwen25_1_5b | Qwen2.5-1.5B | ARC-Easy |
+
+## Structure
+
+```
+serl-checkpoints/
+├── serl_arcc_qwen25_0_5b/
+│   ├── huggingface/global_step100_hf/
+│   └── deepspeed/global_step100/
+├── serl_ARC-c_qwen25_1_5b/
+│   └── ...
+└── ...
+```
+
+## Compression
+
+Files ending in `.safetensors.znn` are ZipNN compressed.
+The `zipnn_hf()` hook enables transparent loading.

serl_ARC-c_qwen25_1_5b/training_timing_stats.txt

@@ -0,0 +1,1466 @@
+1,0.000000,12.546154
+2,6.947293,8.183690
+3,4.889451,8.316977
+4,7.105500,8.184348
+5,5.591309,8.175122
+6,6.900859,8.121256
+7,7.112567,8.324215
+8,7.049313,8.204970
+9,3.406816,8.081860
+10,3.438205,8.097709
+11,7.183734,8.193633
+12,6.947315,8.232837
+13,3.492036,8.349909
+14,8.403210,8.466539
+15,3.491345,8.078977
+16,3.519540,8.241562
+17,5.210850,8.097374
+18,3.615512,8.276508
+19,7.090774,8.237534
+20,3.453997,8.075641
+21,3.476606,8.129417
+22,6.889049,8.163299
+23,7.305551,8.228626
+24,3.503333,8.108772
+25,7.046717,15.634496
+26,7.693178,8.502627
+27,6.345366,9.084667
+28,8.110234,9.960069
+29,8.798420,10.370176
+30,4.220302,9.091196
+31,5.728630,8.471597
+32,7.209500,8.311925
+33,5.043008,8.416613
+34,3.598608,8.294558
+35,7.252034,8.296997
+36,7.402415,8.197070
+37,3.681936,8.336353
+38,7.248360,8.207301
+39,7.197008,8.264694
+40,7.379287,8.482009
+41,3.659496,8.259499
+42,7.003443,8.169184
+43,3.591176,8.294058
+44,5.431638,8.174016
+45,7.119986,8.369754
+46,3.806911,8.178271
+47,3.584865,8.196851
+48,3.578960,8.309763
+49,7.409914,8.536479
+50,3.888513,17.867330
+51,6.000092,9.404345
+52,3.973357,10.862399
+53,4.941118,12.357617
+54,10.132410,10.704614
+55,10.109367,11.182086
+56,8.435169,13.462467
+57,9.905578,12.736109
+58,8.229158,12.333770
+59,4.435403,10.555849
+60,9.253622,10.308327
+61,8.065496,10.752323
+62,9.419687,11.934385
+63,9.239064,14.012817
+64,4.632997,12.316933
+65,7.402201,10.772622
+66,9.223090,11.330353
+67,6.730875,10.961633
+68,4.684238,11.515585
+69,4.925063,10.297019
+70,7.371338,10.954585
+71,4.814506,12.035136
+72,5.040534,14.153552
+73,8.339542,13.707400
+74,4.556248,11.241838
+75,9.380427,22.076396
+76,4.934629,13.298496
+77,12.779183,12.390107
+78,32.159382,12.981033
+79,11.246286,12.485973
+80,11.080122,12.253801
+81,11.413594,11.338376
+82,5.226402,14.051123
+83,8.143976,13.674404
+84,10.396559,14.439722
+85,13.969483,13.303272
+86,7.674526,12.352826
+87,11.206858,12.318669
+88,13.469477,12.221793
+89,11.119939,13.627894
+90,8.829072,13.970922
+91,10.921315,12.197886
+92,11.055584,10.951849
+93,16.043319,10.595812
+94,8.733879,10.592872
+95,10.834621,11.397439
+96,13.406411,12.561706
+97,14.387190,13.153865
+98,9.906538,14.531824
+99,10.867961,14.378087
+100,10.693682,69.184718
+101,11.260742,17.085649
+102,8.470123,15.864311
+103,11.499705,15.315227
+104,10.560239,12.532072
+105,10.491935,13.994461
+106,11.694002,11.814347
+107,12.800346,11.248486
+108,19.058496,14.552065
+109,8.739029,11.643851
+110,9.556482,11.764879
+111,14.728099,14.052668
+112,28.324187,18.496364
+113,12.990664,14.308965
+114,5.669870,13.609738
+115,10.663683,13.481256
+116,17.761383,13.259112
+117,12.821582,11.298711
+118,10.449486,13.340239
+119,10.497109,14.353459
+120,13.804360,10.701314
+121,11.484640,12.452858
+122,11.177660,10.868674
+123,13.956106,10.678640
+124,11.131136,12.264486
+125,11.283822,24.183312
+126,19.370163,13.795317
+127,25.081738,12.870965
+128,10.524442,8.381500
+129,9.412849,8.383737
+130,5.825131,8.314142
+131,7.317703,8.583417
+132,15.618291,8.397719
+133,9.466331,8.440944
+134,11.329569,8.353695
+135,13.113999,8.467626
+136,13.133681,8.215668
+137,8.841544,8.283321
+138,7.317351,8.731859
+139,5.832173,8.402423
+140,17.492416,8.314644
+141,5.851475,8.247889
+142,9.506876,8.406058
+143,9.557750,8.396875
+144,13.175830,8.393870
+145,15.225758,8.682770
+146,3.866297,8.728018
+147,11.532264,8.734574
+148,7.731613,8.380020
+149,10.310719,9.401865
+150,8.989150,18.668348
+151,23.991764,11.019589
+152,21.256495,10.377827
+153,14.714244,8.385178
+154,9.519653,9.149561
+155,12.605994,11.552042
+156,11.066446,9.090016
+157,10.955400,11.373014
+158,8.361418,9.958966
+159,12.716452,14.805407
+160,23.847940,11.706841
+161,24.752522,8.620050
+162,20.918706,9.460128
+163,15.432169,11.421418
+164,9.430162,10.345292
+165,22.507233,8.462144
+166,14.183616,8.458165
+167,19.445802,10.106485
+168,12.807416,10.256570
+169,8.278263,12.073224
+170,15.074885,8.513409
+171,9.403810,10.611704
+172,12.275525,11.430043
+173,8.820737,8.969373
+174,22.921264,12.176172
+175,11.083954,19.983920
+176,8.083707,10.514847
+177,11.733255,10.206887
+178,8.511545,11.970629
+179,18.972895,11.713221
+180,11.179301,8.776436
+181,18.061968,9.942386
+182,26.625215,8.452732
+183,21.374196,8.701072
+184,10.414564,10.424971
+185,7.089982,10.163381
+186,32.558753,8.540419
+187,8.974996,8.971447
+188,12.807069,12.175053
+189,12.718896,8.747252
+190,17.622136,12.111754
+191,27.484385,12.250682
+192,18.823611,12.275498
+193,9.714684,9.129271
+194,11.415498,8.380236
+195,13.164354,11.251007
+196,17.398866,10.371340
+197,21.701434,12.253167
+198,8.909070,9.636744
+199,26.595570,8.798573
+200,7.725955,45.784911
+201,25.650834,9.001069
+202,9.407831,8.440014
+203,24.572957,8.673229
+204,7.559720,10.065246
+205,18.572680,11.251381
+206,25.622284,9.353485
+207,22.827085,12.375175
+208,34.613295,10.960804
+209,17.498391,9.460973
+210,22.801100,11.290627
+211,17.584198,8.482635
+212,16.037982,8.464016
+213,16.999116,8.839337
+214,15.057762,9.034429
+215,16.757467,11.568022
+216,15.352568,9.149329
+217,11.818580,11.277108
+218,7.417142,9.507099
+219,11.319788,10.181233
+220,15.909170,8.440289
+221,13.645548,11.563344
+222,11.485924,8.794940
+223,12.949943,12.158892
+224,13.003150,10.398147
+225,15.924174,17.455174
+226,8.040323,12.121357
+227,17.083103,9.425482
+228,18.499319,9.762918
+229,11.662152,9.767719
+230,4.764211,8.395089
+231,10.145259,8.509601
+232,9.435905,8.606951
+233,30.676155,8.527153
+234,11.695792,9.417902
+235,15.223864,12.538899
+236,7.633298,12.186359
+237,13.883426,10.034384
+238,15.541242,8.633824
+239,18.918196,9.257272
+240,9.118019,11.008200
+241,11.597069,9.530029
+242,11.209933,9.045381
+243,15.078021,11.245020
+244,19.708741,12.050072
+245,7.719344,11.581393
+246,14.389858,10.574204
+247,12.960304,9.260185
+248,18.460314,8.475018
+249,9.095656,9.672633
+250,11.777728,15.841395
+251,9.951417,8.816411
+252,9.236021,11.951406
+253,22.290688,9.806257
+254,21.988624,8.493109
+255,9.013155,9.748726
+256,8.553496,11.121406
+257,18.339216,10.809411
+258,27.578237,9.471465
+259,15.027393,11.735718
+260,10.512530,11.107432
+261,15.250364,9.392331
+262,13.029341,10.359440
+263,15.546803,10.090991
+264,12.297097,9.496078
+265,12.413639,12.092536
+266,21.798911,10.377987
+267,8.432152,10.424137
+268,10.846450,8.455839
+269,14.379782,8.740517
+270,17.922738,10.074199
+271,14.579208,10.064563
+272,10.603516,10.491617
+273,16.690365,8.866502
+274,12.881485,10.370968
+275,12.635572,19.471760
+276,17.050956,12.400131
+277,14.740474,10.220449
+278,10.458505,9.434527
+279,9.127989,8.423988
+280,10.657123,10.153452
+281,15.113239,8.771906
+282,7.730263,12.163685
+283,13.927379,12.058284
+284,17.131650,8.855976
+285,15.320302,8.945936
+286,13.133669,8.473225
+287,17.322769,11.940594
+288,13.789412,8.443046
+289,16.791471,8.575014
+290,13.486051,8.500811
+291,6.121768,11.794900
+292,5.329837,8.443333
+293,9.118075,8.443149
+294,7.692473,8.393972
+295,11.572171,8.802708
+296,18.295736,8.489636
+297,13.195748,8.655987
+298,12.358208,10.072093
+299,10.450527,10.504251
+300,7.633783,40.853457
+301,7.686350,8.459062
+302,21.703084,9.756393
+303,18.762672,9.253102
+304,14.753291,11.170884
+305,9.448078,8.684945
+306,6.074125,10.105799
+307,13.015641,12.099464
+308,9.171600,8.638444
+309,19.327645,10.658824
+310,8.260590,8.722040
+311,9.108150,8.391286
+312,8.637628,10.239977
+313,9.194643,8.553857
+314,10.325377,8.456543
+315,6.264062,8.520888
+316,11.463853,11.457451
+317,14.669024,9.252110
+318,16.534415,8.529820
+319,5.287520,9.018057
+320,8.385239,9.969165
+321,14.532432,12.095598
+322,6.159452,8.460713
+323,14.416436,8.814455
+324,9.946703,10.134729
+325,8.569791,16.165866
+326,12.691652,8.510509
+327,16.378078,9.374897
+328,7.660657,8.669303
+329,10.311100,8.656256
+330,7.668857,8.380474
+331,13.244406,8.717755
+332,5.943524,8.424557
+333,7.618994,8.493773
+334,8.484128,10.510882
+335,9.800298,10.907364
+336,5.877879,8.562921
+337,9.329766,8.514571
+338,11.771987,12.417670
+339,7.913412,8.564361
+340,8.984140,8.695434
+341,7.679417,8.592687
+342,9.240184,12.335826
+343,13.434859,8.457405
+344,6.364257,9.834636
+345,12.450036,12.265553
+346,7.636199,8.406558
+347,7.737220,8.514682
+348,7.712282,12.242822
+349,5.191939,8.469255
+350,7.703733,17.792976
+351,9.098651,9.291064
+352,8.686169,8.718648
+353,3.843715,10.752220
+354,4.425107,8.665501
+355,3.823049,8.519405
+356,9.332875,8.436101
+357,12.931822,9.218553
+358,11.856864,9.195596
+359,6.676022,8.544528
+360,6.979132,11.925171
+361,9.168586,11.234407
+362,9.605111,8.385573
+363,11.688365,8.461882
+364,4.355367,10.569857
+365,13.065011,8.753498
+366,11.861243,9.388102
+367,3.832550,8.445619
+368,6.131487,8.462533
+369,5.387374,10.973905
+370,13.696560,8.544863
+371,7.694462,8.509377
+372,7.640783,11.067369
+373,8.016623,8.444536
+374,9.522417,8.611777
+375,13.055490,16.111840
+376,3.789046,8.596974
+377,4.281873,10.519167
+378,5.450340,8.718897
+379,7.648836,8.549492
+380,10.570285,8.965788
+381,7.712970,9.161588
+382,8.453530,8.587402
+383,7.981870,12.056535
+384,9.166279,8.364928
+385,7.661857,8.501046
+386,5.383723,8.873774
+387,7.722108,8.477407
+388,14.426041,8.809732
+389,6.729740,8.544753
+390,10.757520,8.470314
+391,7.695045,8.582100
+392,9.397529,8.482071
+393,7.857524,8.549918
+394,7.894527,9.277409
+395,8.657647,8.508529
+396,15.243329,8.730362
+397,6.180750,8.720987
+398,5.702435,11.620787
+399,7.893276,8.545377
+400,6.117523,42.295575
+401,9.207214,8.571816
+402,3.827884,8.663687
+403,3.833202,8.496088
+404,3.827169,10.338620
+405,8.639668,8.594035
+406,3.362980,8.691444
+407,7.624664,8.789770
+408,7.731071,8.502423
+409,9.158296,9.540103
+410,10.043055,8.612616
+411,7.657988,11.275653
+412,12.104040,8.423308
+413,13.185754,10.208623
+414,12.248649,8.560615
+415,7.686045,8.491792
+416,13.814644,8.439420
+417,9.571677,8.584857
+418,14.450019,8.630272
+419,11.056028,8.582715
+420,25.895899,8.664906
+421,12.865673,8.623515
+422,7.987050,8.514325
+423,18.923071,8.728272
+424,16.864987,10.738515
+425,13.946259,16.692698
+426,20.278600,8.552969
+427,9.149480,8.829705
+428,10.711457,8.611899
+429,11.140727,8.561524
+430,13.271681,9.928883
+431,9.592034,8.708351
+432,27.521312,10.271967
+433,14.589381,8.721727
+434,14.846122,8.891899
+435,19.237454,8.750436
+436,9.270891,8.615066
+437,13.951992,11.363423
+438,25.499666,10.151430
+439,13.165318,8.726351
+440,9.437883,9.553249
+441,13.542406,8.488058
+442,22.705439,8.697451
+443,12.281293,8.737565
+444,13.705395,9.202405
+445,19.453378,12.041771
+446,8.003252,8.566484
+447,12.488588,8.623403
+448,23.702259,8.750721
+449,10.821598,9.526616
+450,31.915386,14.524833
+451,12.657916,12.364509
+452,13.925364,8.771642
+453,14.680818,8.582470
+454,4.469010,10.529279
+455,11.008260,8.623593
+456,10.862163,8.946932
+457,13.896300,8.621002
+458,17.716844,8.864685
+459,13.591192,8.842842
+460,20.702214,8.573341
+461,12.539674,8.745934
+462,15.851238,8.848713
+463,6.925294,12.132199
+464,19.992498,8.453527
+465,15.315760,8.379399
+466,19.957037,8.510989
+467,11.735504,9.352196
+468,17.027996,11.627693
+469,8.408073,8.715364
+470,9.230883,8.463449
+471,6.999884,9.046503
+472,15.410763,8.719818
+473,27.667579,8.724042
+474,15.500953,8.598282
+475,15.447080,15.760968
+476,10.803980,8.487530
+477,11.169264,8.532197
+478,6.954185,9.541437
+479,14.906768,8.493994
+480,13.449630,9.140448
+481,13.819371,8.848175
+482,12.261868,8.420603
+483,10.793283,8.523967
+484,9.237199,8.550068
+485,19.465272,10.193947
+486,12.434042,8.596158
+487,9.310393,12.249688
+488,16.819386,8.985688
+489,18.951488,8.700751
+490,12.354980,9.087582
+491,13.970678,8.594914
+492,13.772277,8.518599
+493,6.902007,8.618961
+494,9.946620,8.575821
+495,16.669503,8.747813
+496,13.939253,8.704324
+497,5.453159,8.514197
+498,11.420327,9.633506
+499,15.129791,8.784295
+500,20.066033,38.612260
+501,12.706926,8.457684
+502,17.235587,9.362040
+503,16.269056,8.682905
+504,27.419346,8.528640
+505,13.789560,11.288892
+506,11.253194,8.438394
+507,11.551731,8.420410
+508,23.161956,8.819880
+509,15.434067,8.991037
+510,15.645542,11.425602
+511,6.902162,9.013553
+512,22.481056,12.036184
+513,15.337764,8.859162
+514,18.357724,8.780129
+515,16.727768,8.559600
+516,12.249088,8.401796
+517,15.271274,9.358966
+518,18.760209,8.591603
+519,22.600399,12.422860
+520,8.551633,8.530214
+521,13.969469,8.850070
+522,17.289001,8.498377
+523,8.479854,8.685382
+524,18.494181,8.592627
+525,17.231383,14.294654
+526,23.915187,8.831071
+527,15.403667,8.525702
+528,15.272798,8.610045
+529,13.849963,8.633970
+530,24.025482,8.631559
+531,19.967220,9.009626
+532,15.245186,8.602949
+533,22.572414,8.859966
+534,16.424779,9.480492
+535,12.257291,8.500328
+536,16.888236,8.682008
+537,7.194251,8.589786
+538,13.824731,8.537958
+539,12.237201,9.524809
+540,19.399405,11.630632
+541,10.322428,8.495245
+542,22.193713,8.468013
+543,18.969028,8.533307
+544,5.354660,8.680586
+545,9.310320,12.033802
+546,20.853629,8.712252
+547,12.388023,8.662747
+548,10.560196,8.878525
+549,14.594241,8.609514
+550,6.919265,15.312393
+551,6.923746,8.442855
+552,10.795007,8.460694
+553,14.008079,8.592733
+554,11.604808,8.503535
+555,25.508468,8.838292
+556,21.562899,8.498262
+557,7.673021,8.799317
+558,11.151541,10.973943
+559,20.358583,9.755923
+560,31.707127,12.025072
+561,13.870422,8.765615
+562,23.975327,8.825994
+563,16.929936,8.666597
+564,18.813747,10.738091
+565,16.857159,8.646325
+566,24.090924,8.658564
+567,23.599192,8.528554
+568,10.762817,8.694821
+569,3.856997,8.646930
+570,15.694858,8.542183
+571,12.313939,8.853120
+572,17.149807,8.668622
+573,6.898319,8.945712
+574,16.799831,8.509195
+575,12.387004,13.771472
+576,20.638824,8.881204
+577,28.784618,8.579996
+578,9.422093,8.555833
+579,16.163764,8.595220
+580,15.751643,8.768209
+581,25.566844,8.976931
+582,9.987832,8.688214
+583,13.195470,8.753329
+584,5.328199,11.992289
+585,26.232778,8.861941
+586,13.863190,8.453178
+587,10.613222,9.212619
+588,15.666698,8.528259
+589,19.552533,8.493759
+590,15.339558,8.702627
+591,9.204967,11.494401
+592,12.737506,8.657196
+593,20.766443,8.461051
+594,8.712033,10.996534
+595,15.637882,8.684129
+596,8.433641,8.525464
+597,5.901099,10.915180
+598,17.167090,8.679723
+599,14.861223,8.541945
+600,15.852498,39.360176
+601,10.730843,8.540390
+602,5.305184,11.176115
+603,18.764532,8.458355
+604,20.774744,10.007191
+605,17.159744,8.663084
+606,15.341626,8.589092
+607,13.325160,10.303199
+608,7.165154,8.708036
+609,15.456835,9.811336
+610,28.826532,8.763345
+611,15.322218,8.641492
+612,5.365320,8.605284
+613,24.057079,8.575353
+614,12.305972,8.564802
+615,12.588483,8.603070
+616,12.324169,12.185554
+617,12.260738,8.557926
+618,16.902797,8.620366
+619,18.507073,9.671871
+620,15.085691,8.471202
+621,7.753322,12.279468
+622,13.661455,8.508614
+623,17.773750,8.578009
+624,15.726590,8.906376
+625,6.950213,16.408617
+626,12.332495,8.725158
+627,13.863618,11.173642
+628,17.964346,8.609659
+629,34.604120,11.812235
+630,12.313478,8.898848
+631,23.804685,8.554959
+632,24.773892,8.691432
+633,7.912421,8.528547
+634,14.019572,11.445072
+635,12.587270,11.877375
+636,13.795233,8.594335
+637,14.112688,8.901908
+638,6.850000,11.071108
+639,17.264544,8.518843
+640,18.398166,8.916332
+641,5.704041,12.105965
+642,15.451902,8.549619
+643,13.915113,8.613436
+644,18.530009,8.392908
+645,17.212982,8.439939
+646,9.475452,8.601625
+647,12.672643,11.127380
+648,11.020913,8.642021
+649,15.276080,8.645985
+650,9.950641,13.991989
+651,12.302447,9.460234
+652,18.032850,9.067513
+653,15.280554,8.583000
+654,10.721634,12.169389
+655,21.106962,10.435251
+656,7.816828,8.561308
+657,9.977857,10.305523
+658,13.433733,8.795226
+659,15.203045,8.530414
+660,13.744576,9.561425
+661,9.570431,8.684174
+662,11.215579,11.764971
+663,23.024848,8.585931
+664,9.127165,8.805648
+665,11.301982,8.564166
+666,18.746738,11.492065
+667,10.708376,8.535563
+668,17.808819,9.572044
+669,13.706058,8.498022
+670,26.962177,8.993617
+671,10.767138,8.495497
+672,9.174749,12.309203
+673,12.908441,10.334972
+674,4.531523,8.466454
+675,12.146709,13.996406
+676,13.711688,8.572719
+677,29.840963,8.531461
+678,15.287585,8.499927
+679,18.002666,10.858244
+680,15.613859,11.632506
+681,16.683851,8.490286
+682,12.329109,8.683733
+683,10.656038,8.844954
+684,10.735443,12.160420
+685,6.860961,8.575657
+686,17.897514,8.897139
+687,11.595215,9.046712
+688,19.818848,8.881521
+689,13.409459,11.267334
+690,5.322669,8.614492
+691,11.411795,8.665280
+692,15.136668,8.524828
+693,19.956900,8.675310
+694,25.061719,10.675399
+695,12.956894,8.825785
+696,12.255547,8.589912
+697,13.403058,11.533422
+698,15.505577,8.674002
+699,18.682841,8.581449
+700,17.713265,38.720052
+701,12.274404,8.633938
+702,27.181261,8.735440
+703,12.423930,11.480358
+704,18.674956,9.081774
+705,10.687219,8.681066
+706,14.193059,11.601174
+707,12.206794,8.507735
+708,16.778471,8.669359
+709,13.869236,8.502151
+710,18.520512,8.622063
+711,6.923887,8.557662
+712,16.887766,8.815669
+713,12.982932,9.151842
+714,15.543100,8.588439
+715,13.762436,8.754273
+716,26.337673,8.461936
+717,16.149655,8.633848
+718,14.082116,8.702288
+719,13.700060,8.544842
+720,3.755409,8.529186
+721,26.566622,8.611914
+722,27.902964,9.282455
+723,8.120714,8.454992
+724,16.778556,10.878504
+725,14.433478,15.160279
+726,25.360125,8.550521
+727,10.019400,10.055185
+728,13.760972,8.506939
+729,30.084679,8.607246
+730,11.049616,10.179736
+731,15.236043,8.730592
+732,21.657725,10.045993
+733,12.222320,12.122910
+734,17.595484,8.964493
+735,11.295931,8.468785
+736,18.291373,8.524668
+737,30.119359,10.206937
+738,13.751794,8.793911
+739,18.458721,8.684343
+740,13.754240,8.687658
+741,13.795074,10.809745
+742,11.407214,8.378109
+743,14.917179,9.092369
+744,8.403518,8.988675
+745,16.702652,9.135744
+746,34.791435,8.617017
+747,6.944085,8.803949
+748,21.408244,8.524054
+749,19.812835,8.565706
+750,22.384541,13.169229
+751,26.760834,8.617004
+752,20.082345,8.595350
+753,20.855643,9.535274
+754,11.419123,8.551315
+755,8.776803,10.760838
+756,26.704486,8.718752
+757,18.425619,8.534422
+758,11.459945,8.592165
+759,9.923173,8.690943
+760,25.228387,8.620435
+761,21.396423,8.724038
+762,19.899537,8.496192
+763,21.351447,8.941355
+764,40.921659,8.498117
+765,35.247529,8.753748
+766,10.536441,8.650860
+767,26.638427,8.554264
+768,13.674141,8.561972
+769,15.117472,8.760338
+770,21.342708,9.084225
+771,16.766971,8.852960
+772,25.305033,8.776796
+773,28.391164,8.762191
+774,21.437701,8.788876
+775,14.123967,15.169616
+776,18.383292,9.033595
+777,16.628120,8.429128
+778,16.579882,9.047347
+779,33.049486,8.581836
+780,33.015748,10.207260
+781,14.515566,8.769251
+782,31.267757,11.256631
+783,11.271597,8.778874
+784,17.134442,11.555669
+785,13.688210,8.764285
+786,20.647758,9.993469
+787,14.982504,8.577476
+788,27.807076,8.701185
+789,12.116225,12.698124
+790,25.882554,8.604565
+791,25.955013,8.565273
+792,18.303376,12.059222
+793,28.422289,8.591780
+794,8.681142,8.459399
+795,12.994440,8.749278
+796,31.639024,12.086473
+797,24.828178,9.505162
+798,14.780389,8.689548
+799,29.867942,8.678550
+800,11.062006,79.184980
+801,15.335213,11.109173
+802,17.701899,9.288951
+803,20.076291,8.536983
+804,19.854903,8.649333
+805,6.835492,8.783472
+806,26.359104,8.683912
+807,12.147459,12.298016
+808,30.395764,8.546178
+809,16.815606,8.688360
+810,12.470505,8.608042
+811,13.743068,8.537247
+812,31.480558,8.892655
+813,10.994858,9.710961
+814,23.552055,8.503437
+815,25.230889,8.446240
+816,21.932336,8.930546
+817,21.085267,8.584696
+818,26.692541,8.912628
+819,13.734879,8.555725
+820,18.338627,8.606332
+821,18.529784,8.745759
+822,22.774637,8.692586
+823,32.082810,8.523837
+824,12.153277,8.454200
+825,21.541171,13.389710
+826,24.524666,8.678421
+827,21.386879,8.614065
+828,15.841985,10.525848
+829,28.323339,8.702476
+830,8.402745,8.905910
+831,19.862813,8.886934
+832,26.885194,8.797194
+833,15.148175,12.367922
+834,10.692553,8.523978
+835,31.218049,8.788000
+836,19.795947,8.611771
+837,12.143123,8.452323
+838,16.814744,8.564549
+839,18.329947,8.726798
+840,5.478825,8.758901
+841,22.932889,9.423826
+842,27.330443,8.431771
+843,17.024937,8.563029
+844,26.629584,9.160039
+845,29.879411,8.495027
+846,29.369220,8.764054
+847,29.656712,8.588537
+848,16.655863,8.640324
+849,32.334081,9.689068
+850,20.034171,13.177553
+851,33.517640,8.487117
+852,20.136885,9.269336
+853,18.390585,8.527825
+854,12.209326,12.285570
+855,5.396239,8.813269
+856,12.963397,8.675607
+857,51.287163,8.736316
+858,18.361832,8.562428
+859,6.859348,8.626914
+860,28.720731,11.025361
+861,29.139580,8.706227
+862,3.799852,10.970224
+863,14.086808,8.410870
+864,20.524296,9.116335
+865,23.468688,8.705625
+866,19.943231,12.580741
+867,20.059637,8.761234
+868,9.984134,11.306369
+869,24.196056,8.609524
+870,30.920674,8.808269
+871,17.958089,9.241853
+872,21.399741,8.577266
+873,12.071575,8.601375
+874,32.776102,8.791923
+875,13.738522,13.400005
+876,18.385251,11.263072
+877,23.419317,8.551812
+878,18.395445,8.544259
+879,9.960961,8.453221
+880,26.381295,8.787278
+881,17.080562,8.736081
+882,12.396873,8.692271
+883,32.870847,8.452934
+884,13.709316,8.460294
+885,25.496519,8.550831
+886,49.604934,8.534433
+887,7.946606,8.500278
+888,25.342999,8.745223
+889,24.226219,9.224278
+890,16.968744,8.763868
+891,24.546431,8.591278
+892,6.849531,8.742754
+893,27.726267,8.451846
+894,9.447858,11.568907
+895,23.492604,8.535331
+896,16.728058,8.699580
+897,21.444743,8.640163
+898,16.863312,8.547085
+899,48.266158,8.512798
+900,15.575788,48.625840
+901,15.451199,11.757553
+902,34.513306,9.659135
+903,13.933579,9.117891
+904,13.199329,9.848895
+905,19.299884,8.727217
+906,22.929790,9.186885
+907,15.565794,10.448976
+908,13.630712,9.459364
+909,30.825338,11.737132
+910,27.458479,8.638280
+911,22.171843,8.747855
+912,23.963306,8.600039
+913,20.813745,10.995353
+914,14.145892,8.538834
+915,13.638735,11.949740
+916,13.617712,8.785205
+917,42.186300,11.438252
+918,22.010734,8.479805
+919,15.221359,8.810380
+920,18.717529,8.699597
+921,41.995774,8.709990
+922,31.402247,11.827141
+923,12.220123,8.709656
+924,17.528541,8.576394
+925,24.144989,12.795435
+926,13.685923,11.903373
+927,35.237115,8.418230
+928,15.431148,11.606011
+929,22.692762,9.014232
+930,23.757956,9.632377
+931,30.349438,8.559770
+932,27.700899,8.925931
+933,17.879182,8.741369
+934,18.314172,8.515998
+935,12.575890,8.554427
+936,28.232583,8.663953
+937,18.441696,8.572388
+938,12.436363,8.460183
+939,26.907623,10.314138
+940,23.657395,8.610402
+941,31.970567,8.542090
+942,22.511030,10.659183
+943,22.773717,8.613865
+944,13.743500,8.636520
+945,31.495874,8.853508
+946,15.410725,8.427064
+947,17.374866,8.537411
+948,29.231325,8.734400
+949,15.456849,8.422544
+950,29.489594,13.020999
+951,16.816476,8.508658
+952,18.328775,9.047069
+953,22.784301,8.605943
+954,13.637793,12.242308
+955,13.614271,9.016486
+956,26.638043,8.714969
+957,22.475350,8.695362
+958,17.746325,8.474110
+959,15.205929,8.738430
+960,20.562747,8.850891
+961,23.536193,8.618873
+962,15.441044,8.642785
+963,25.818536,10.869263
+964,17.041084,8.568349
+965,20.533034,8.797706
+966,23.602971,9.017106
+967,24.336982,8.883460
+968,35.484087,8.458022
+969,15.262380,8.820765
+970,17.483722,8.431542
+971,34.962707,8.897336
+972,50.884620,8.593503
+973,29.388705,8.429049
+974,12.093856,8.508907
+975,22.976806,12.784168
+976,12.103643,8.953184
+977,33.853453,9.244103
+978,12.170195,8.493590
+979,19.327017,8.617779
+980,41.982864,8.474978
+981,17.191972,8.756265
+982,25.689833,8.913922
+983,39.415329,8.556759
+984,13.709539,8.576024
+985,20.142117,8.660511
+986,21.766164,8.509468
+987,19.004332,10.103152
+988,42.640372,8.488175
+989,22.843143,8.655364
+990,20.465218,8.543329
+991,19.071471,8.477045
+992,17.820258,8.477318
+993,8.399015,8.434196
+994,21.363173,8.453828
+995,20.239250,8.607400
+996,24.345367,8.723274
+997,22.743410,9.202550
+998,20.200999,8.513436
+999,21.997911,8.515400
+1000,20.941672,125.211651
+1001,27.018556,10.027137
+1002,16.879859,8.543328
+1003,21.420841,8.533423
+1004,26.908590,8.461120
+1005,10.690204,8.413837
+1006,13.697106,8.671322
+1007,15.234562,8.536975
+1008,24.653158,8.749399
+1009,22.084662,8.456779
+1010,52.938320,8.514926
+1011,20.463820,8.575439
+1012,25.881581,8.601624
+1013,26.781665,8.984711
+1014,9.068846,9.623758
+1015,29.259455,8.673833
+1016,25.793883,8.537051
+1017,34.989312,8.714788
+1018,21.220424,8.603877
+1019,15.054076,8.794886
+1020,18.209005,8.504219
+1021,12.956723,8.551861
+1022,13.584954,8.578976
+1023,39.818336,8.436380
+1024,16.516264,8.843086
+1025,9.506261,12.720903
+1026,15.261996,8.688643
+1027,8.423440,8.660460
+1028,22.130291,8.544563
+1029,19.816548,8.519449
+1030,16.623320,8.784085
+1031,19.479476,8.735431
+1032,22.001758,8.518686
+1033,12.162749,9.133934
+1034,14.012121,8.653772
+1035,12.735815,8.625228
+1036,23.751666,8.667071
+1037,13.757333,8.655986
+1038,10.598233,8.506618
+1039,19.056669,9.036843
+1040,19.608543,8.551932
+1041,15.180581,8.781243
+1042,26.612315,10.080551
+1043,18.594924,8.850177
+1044,30.090052,8.702312
+1045,30.004980,8.531185
+1046,11.887988,8.718877
+1047,18.377074,8.397192
+1048,18.201081,8.454809
+1049,16.254528,8.795400
+1050,34.005669,12.657259
+1051,20.447875,8.907785
+1052,13.768474,8.642414
+1053,16.214879,8.554509
+1054,28.179906,8.494913
+1055,34.362247,8.446154
+1056,15.422854,8.570122
+1057,17.795416,8.517177
+1058,19.020078,8.700811
+1059,25.359536,8.485960
+1060,12.231890,8.641972
+1061,13.682409,8.570890
+1062,8.703281,8.871637
+1063,16.661000,8.889458
+1064,12.195019,8.728369
+1065,20.556323,8.980573
+1066,29.974234,8.505212
+1067,15.420242,9.508101
+1068,23.200855,8.673975
+1069,19.182148,8.578299
+1070,32.017013,8.864052
+1071,28.478559,8.518219
+1072,18.263948,8.517811
+1073,7.180144,8.470724
+1074,21.990340,8.598601
+1075,23.279910,12.723716
+1076,27.259304,8.488260
+1077,41.735809,8.560015
+1078,15.192334,8.543325
+1079,13.729306,8.484744
+1080,38.965474,8.736698
+1081,21.462202,8.496744
+1082,31.921227,8.767856
+1083,36.583140,8.460810
+1084,24.427097,8.851716
+1085,34.938135,8.604874
+1086,13.785620,9.073618
+1087,22.044612,8.605203
+1088,15.242456,8.489891
+1089,26.977713,8.715139
+1090,24.781969,8.640840
+1091,23.715315,8.519279
+1092,8.432013,8.915714
+1093,10.612547,8.581020
+1094,18.218376,8.502476
+1095,22.717296,8.462350
+1096,10.604055,8.445139
+1097,10.712097,8.619762
+1098,25.826982,8.606601
+1099,13.727249,8.635407
+1100,23.978697,55.611032
+1101,15.491846,8.500908
+1102,22.094085,8.470295
+1103,19.813591,8.441177
+1104,28.246127,8.730654
+1105,23.618419,8.505873
+1106,37.726712,8.564694
+1107,21.285418,8.436423
+1108,14.034129,8.481136
+1109,15.947706,8.621946
+1110,13.709097,8.702500
+1111,23.539342,8.767709
+1112,13.644084,9.065207
+1113,23.542944,8.583261
+1114,38.225118,8.721667
+1115,20.881775,8.727460
+1116,24.036957,8.566279
+1117,16.682200,8.713509
+1118,13.185973,8.569798
+1119,15.231532,8.611525
+1120,18.178186,8.427008
+1121,15.296058,8.662460
+1122,29.119560,8.845981
+1123,18.594891,9.019203
+1124,22.288565,8.785548
+1125,30.608180,13.037254
+1126,30.445712,8.679302
+1127,13.545384,8.517394
+1128,23.626534,8.605023
+1129,25.022370,8.443189
+1130,15.518846,8.556321
+1131,15.406970,8.609900
+1132,22.033391,8.573389
+1133,25.098711,8.596051
+1134,15.265831,8.592151
+1135,24.904246,8.599992
+1136,16.817054,8.722389
+1137,28.541866,8.691890
+1138,18.920815,8.585890
+1139,15.272381,8.796561
+1140,25.312568,8.527088
+1141,12.186569,12.524625
+1142,10.726473,8.525366
+1143,16.778526,8.752598
+1144,27.306276,8.590934
+1145,25.872072,8.643139
+1146,19.073981,8.602534
+1147,5.610236,8.472095
+1148,15.530444,8.601365
+1149,29.065196,8.523678
+1150,23.534909,12.787798
+1151,12.956922,8.744725
+1152,9.372814,8.505080
+1153,20.563171,9.026822
+1154,18.834483,8.638639
+1155,25.217087,8.467503
+1156,14.178041,8.982469
+1157,27.667490,8.836162
+1158,14.611475,8.711306
+1159,25.282857,8.439826
+1160,31.617947,8.438061
+1161,8.393570,8.751196
+1162,27.390186,8.581503
+1163,19.818997,8.858776
+1164,15.274063,8.675132
+1165,30.666505,8.538500
+1166,17.424683,10.891328
+1167,25.528805,8.818191
+1168,11.458195,8.510787
+1169,34.791397,8.788159
+1170,16.418937,8.640726
+1171,15.549563,8.507533
+1172,19.810567,8.539999
+1173,19.846779,8.673590
+1174,15.242189,8.591076
+1175,23.023322,12.793839
+1176,26.617535,8.624256
+1177,16.814129,8.503359
+1178,18.550820,8.465498
+1179,33.319772,8.500558
+1180,21.456780,8.618291
+1181,18.373227,8.518934
+1182,20.052030,8.557175
+1183,24.360902,8.721993
+1184,19.800308,8.460385
+1185,17.473583,8.669790
+1186,16.983946,8.617075
+1187,13.683919,8.517992
+1188,9.072606,8.904154
+1189,16.733035,8.949876
+1190,33.798444,8.467619
+1191,24.987141,8.641396
+1192,20.104411,8.445718
+1193,28.122258,8.460896
+1194,15.437676,8.581419
+1195,37.440547,8.529303
+1196,16.665246,8.531033
+1197,12.124170,8.475281
+1198,8.366767,8.401331
+1199,25.536767,8.638975
+1200,22.052702,36.939775
+1201,33.730398,8.489136
+1202,21.065752,8.519103
+1203,23.504162,8.561072
+1204,15.167681,8.762579
+1205,28.776918,8.748693
+1206,15.146057,8.801777
+1207,29.245655,8.704615
+1208,10.578574,8.891268
+1209,25.511502,8.453125
+1210,15.569901,8.524378
+1211,15.476819,8.647450
+1212,12.075218,8.498537
+1213,20.495203,8.509263
+1214,32.525795,8.563902
+1215,27.443314,8.728484
+1216,15.287710,8.451389
+1217,34.836718,8.487308
+1218,15.123710,8.564434
+1219,16.751446,8.622795
+1220,12.547004,8.512351
+1221,16.045907,8.490438
+1222,8.264322,8.783386
+1223,16.297576,8.497193
+1224,23.575417,8.797348
+1225,10.678384,16.996847
+1226,21.567059,8.625865
+1227,20.478679,8.854251
+1228,23.589470,8.630457
+1229,12.199387,9.049323
+1230,11.142366,8.594713
+1231,14.798396,8.581694
+1232,11.003333,8.500019
+1233,23.513636,8.472520
+1234,15.589737,8.679107
+1235,18.321112,9.179847
+1236,27.548833,8.366527
+1237,21.203553,8.559169
+1238,12.144283,8.692422
+1239,23.587189,8.620797
+1240,9.009990,8.713064
+1241,14.308561,8.444581
+1242,21.318464,8.543748
+1243,10.911527,8.691092
+1244,9.109405,8.857384
+1245,20.663300,9.262737
+1246,30.274029,8.727913
+1247,51.039202,8.607109
+1248,16.623384,8.501096
+1249,12.350930,8.686879
+1250,17.513201,12.840170
+1251,17.004326,8.395379
+1252,30.196074,8.848849
+1253,16.829321,8.697766
+1254,42.534400,8.532194
+1255,49.977162,8.685643
+1256,20.650573,8.443435
+1257,33.617544,8.440451
+1258,9.471485,8.623743
+1259,21.246083,8.417122
+1260,12.132443,8.545593
+1261,22.867478,8.680652
+1262,18.140031,8.427901
+1263,9.965196,8.524105
+1264,21.286557,8.514434
+1265,27.190664,8.577269
+1266,19.763229,8.534422
+1267,22.051884,8.781494
+1268,23.656693,8.569510
+1269,16.723859,8.543995
+1270,26.148321,8.674281
+1271,23.442520,8.770206
+1272,25.091928,8.416350
+1273,31.112361,8.485265
+1274,20.362624,8.524704
+1275,24.596439,12.961661
+1276,21.390537,8.531034
+1277,23.957904,8.509552
+1278,20.901484,8.744099
+1279,18.994609,8.563580
+1280,16.640297,8.671263
+1281,37.139062,8.547795
+1282,15.554218,8.573393
+1283,10.653203,8.576623
+1284,17.109294,9.094343
+1285,35.636380,8.469565
+1286,13.877850,8.554368
+1287,19.972275,10.142418
+1288,14.733844,8.635495
+1289,43.255553,8.810956
+1290,29.872070,8.865963
+1291,29.670075,8.556863
+1292,20.867394,8.722281
+1293,28.100202,8.459169
+1294,9.048690,8.800013
+1295,19.931201,8.603034
+1296,20.428486,8.553555
+1297,31.832617,8.663690
+1298,28.275699,9.285201
+1299,18.972760,8.678845
+1300,19.309013,48.911778
+1301,22.665505,8.536052
+1302,41.410309,8.507990
+1303,24.392338,9.179422
+1304,22.756602,8.517948
+1305,15.570235,8.479268
+1306,18.242892,8.886845
+1307,27.730175,8.451216
+1308,15.922689,8.496737
+1309,21.139305,8.715433
+1310,33.763785,8.701897
+1311,15.235241,8.874814
+1312,15.156148,8.599797
+1313,12.123395,8.504791
+1314,22.096334,11.100183
+1315,14.220019,8.650670
+1316,15.229444,8.653102
+1317,18.467377,8.506919
+1318,19.640184,8.605951
+1319,19.146583,8.453611
+1320,24.202457,8.639787
+1321,22.713305,8.670669
+1322,10.621335,9.123600
+1323,21.630911,8.536047
+1324,21.971652,8.698892
+1325,36.896599,12.953173
+1326,16.032393,8.511987
+1327,13.685131,8.480705
+1328,18.915212,8.571499
+1329,10.547773,9.151560
+1330,19.149187,8.935734
+1331,19.801350,8.548930
+1332,9.895663,8.498791
+1333,18.235337,9.121523
+1334,21.989012,8.403902
+1335,12.087460,8.596785
+1336,20.806350,8.758546
+1337,19.222519,8.458137
+1338,9.447511,8.415171
+1339,12.045956,8.494079
+1340,24.688747,8.573419
+1341,24.790639,9.087486
+1342,22.022279,8.453864
+1343,20.699044,8.912148
+1344,12.005403,8.646365
+1345,18.334889,9.101140
+1346,24.263460,8.539208
+1347,19.728248,8.854693
+1348,16.974846,8.527271
+1349,8.317833,8.654656
+1350,15.289655,12.967218
+1351,19.824006,8.551005
+1352,15.200700,8.508769
+1353,12.954229,8.696483
+1354,24.322455,8.520565
+1355,13.661165,8.848237
+1356,17.055499,8.482360
+1357,32.984041,8.573108
+1358,27.094042,8.476552
+1359,18.760587,10.428650
+1360,26.588624,8.783318
+1361,18.328171,8.560199
+1362,9.810666,8.822276
+1363,27.575481,8.541882
+1364,32.256584,8.521710
+1365,29.665332,8.625028
+1366,18.219864,9.145011
+1367,37.704810,8.612847
+1368,25.853616,8.635670
+1369,14.330236,8.740973
+1370,25.056401,8.475556
+1371,24.461224,8.828162
+1372,31.951975,8.710616
+1373,16.675344,8.769236
+1374,49.337700,8.529406
+1375,40.034190,14.123459
+1376,26.439704,8.516282
+1377,25.783697,8.568526
+1378,29.245459,8.547344
+1379,23.892798,8.789177
+1380,53.246269,9.092178
+1381,44.547000,8.515173
+1382,73.432584,8.460031
+1383,37.280039,8.515781
+1384,58.370196,8.783062
+1385,39.600893,8.581988
+1386,65.447384,8.703155
+1387,44.149410,8.898965
+1388,21.269027,8.973963
+1389,12.855083,8.720055
+1390,29.439521,8.557418
+1391,28.445862,8.854427
+1392,31.728243,8.891325
+1393,49.682270,8.593899
+1394,31.262301,8.742234
+1395,23.217855,8.440150
+1396,42.992031,8.532705
+1397,87.911717,8.641362
+1398,26.736799,8.466991
+1399,41.182725,8.539319
+1400,16.494585,39.682413
+1401,27.620600,9.145168
+1402,58.161390,8.704721
+1403,87.089899,8.772347
+1404,22.274195,8.669444
+1405,63.768324,8.888775
+1406,127.068054,8.652920
+1407,152.036795,8.648285
+1408,193.450182,8.926062
+1409,162.567360,8.577731
+1410,245.518041,8.528428
+1411,73.478950,9.237147
+1412,63.238066,8.629887
+1413,108.850156,8.526208
+1414,110.488020,8.666559
+1415,144.015269,8.907648
+1416,207.049020,8.650737
+1417,208.976501,8.879845
+1418,576.721968,8.424718
+1419,732.488096,8.683488
+1420,354.306057,8.642267
+1421,221.127151,8.488566
+1422,249.854813,8.640063
+1423,610.739116,8.574610
+1424,276.407117,8.708749
+1425,426.549336,16.051170
+1426,401.968124,8.491413
+1427,488.473355,8.943881
+1428,698.093243,8.688473
+1429,693.639974,8.724647
+1430,1114.026720,8.660046
+1431,483.557106,8.454951
+1432,495.323833,8.558883
+1433,298.488058,8.653656
+1434,948.956598,8.629574
+1435,1260.344112,8.674369
+1436,566.605193,8.643137
+1437,801.763678,8.657714
+1438,392.020588,8.411982
+1439,294.049883,8.721498
+1440,751.168975,8.730385
+1441,818.935166,9.041846
+1442,433.574482,8.525113
+1443,426.416136,8.808225
+1444,792.941651,8.704712
+1445,1444.045683,8.924119
+1446,1106.974478,8.728170
+1447,3163.741308,8.663944
+1448,1249.816360,8.885565
+1449,609.012150,8.874445
+1450,3720.470537,16.189996
+1451,2217.566521,8.819806
+1452,2602.890025,8.738554
+1453,2292.988311,8.755250
+1454,5949.451853,8.765294
+1455,2444.292551,8.668035
+1456,8614.871264,8.577951
+1457,3962.766319,8.676346
+1458,10133.734029,8.673020
+1459,11066.748454,8.962419
+1460,3935.660649,8.614036
+1461,12844.942424,8.666709
+1462,8047.148486,9.881188
+1463,8299.374063,9.969499
+1464,4312.286935,8.650630
+1465,3351.221331,9.147377
+1466,4927.489757,8.751425

serl_CodeMMLU_qwen25_0_5b/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

serl_CodeMMLU_qwen25_0_5b/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

serl_CodeMMLU_qwen25_0_5b/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

serl_CodeMMLU_qwen25_0_5b/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

serl_CodeMMLU_qwen25_0_5b/model.safetensors.znn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bdc481b4f9468fa636752e663e86a15f7200d20ec6a21c6e3cac922df75f73
+size 658235163

serl_CodeMMLU_qwen25_0_5b/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

serl_CodeMMLU_qwen25_0_5b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

serl_CodeMMLU_qwen25_0_5b/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

serl_CodeMMLU_qwen25_0_5b/training_timing_stats.txt

@@ -0,0 +1,467 @@
+1,0.000000,4.671853
+2,6.773643,3.034820
+3,5.263478,2.996708
+4,10.633549,2.952454
+5,19.661575,3.007727
+6,4.200341,2.996574
+7,18.594657,2.982067
+8,9.326620,3.063694
+9,17.517881,3.047274
+10,8.354532,3.110648
+11,4.028999,2.948293
+12,10.160984,3.060176
+13,10.569419,3.089721
+14,3.057245,3.008789
+15,12.849201,3.080920
+1,0.000000,4.604696
+2,11.644218,2.982839
+3,10.749479,2.995088
+4,10.612057,2.927888
+5,13.073142,2.971744
+6,2.980792,2.937122
+7,6.228379,3.243595
+8,12.292090,3.073818
+9,12.407048,3.091738
+10,6.486163,3.012695
+11,3.615505,3.086605
+12,5.803253,3.068847
+13,12.704308,2.962528
+14,17.869705,3.094239
+15,11.746775,3.149012
+16,8.271463,3.047272
+17,10.464438,3.058011
+18,12.540347,3.097700
+19,2.973199,3.008020
+20,8.724079,3.160262
+21,12.593986,2.991690
+22,9.416880,3.003658
+23,19.822816,2.993702
+24,7.204312,2.974257
+25,17.161876,111.328707
+26,6.474792,3.023837
+27,13.535604,2.982115
+28,11.076575,3.249124
+29,12.744550,3.009000
+30,11.624028,3.081378
+31,8.175010,3.220113
+32,6.093505,3.012760
+33,13.892340,3.105084
+34,11.069781,3.061796
+35,9.490412,3.019814
+36,10.949995,2.971648
+37,10.319576,3.100444
+38,6.161354,2.957520
+39,5.179917,2.962793
+40,13.427141,3.190542
+41,12.295295,2.989681
+42,11.990419,2.982777
+43,15.178988,3.095139
+44,17.250989,3.107391
+45,5.063251,3.034812
+46,11.235049,3.099728
+47,6.734540,3.048400
+48,12.151039,3.031929
+49,11.794649,3.155914
+1,0.000000,4.938501
+2,21.333171,4.496764
+3,20.240555,4.558744
+4,12.828145,4.692261
+5,34.349775,4.674294
+6,10.163747,4.726840
+7,15.158993,3.777157
+8,6.389358,3.020436
+9,6.571153,3.100401
+10,11.600342,3.271439
+11,17.567987,3.146554
+12,12.025645,3.167277
+13,11.455191,3.137716
+14,7.876769,2.979743
+15,15.151291,3.063867
+16,5.604344,3.131213
+17,6.536801,2.973885
+18,9.859431,3.085242
+19,11.954660,3.274586
+1,0.000000,5.848600
+2,30.284069,4.694692
+3,6.692274,4.232724
+4,28.892647,4.219824
+5,15.522935,4.197688
+6,11.867409,4.474980
+7,16.352646,4.218034
+8,15.570859,4.239979
+9,13.068557,4.162902
+10,10.836221,4.984784
+11,3.880128,4.268750
+12,7.268735,4.113845
+13,8.159795,4.302345
+14,21.884626,4.217528
+15,13.201536,4.450361
+16,16.512207,4.660499
+17,10.309585,4.288996
+18,11.279558,4.365938
+19,6.281261,4.242755
+20,11.451839,4.670532
+21,7.030181,4.788728
+22,6.716266,4.354739
+23,20.459330,4.277636
+24,13.913929,4.249309
+25,10.711888,155.909092
+26,8.339432,5.145005
+27,17.115858,4.210727
+28,7.237779,4.184950
+29,8.442263,4.211865
+30,14.466983,4.275123
+31,18.625684,4.257428
+32,10.065987,4.468746
+33,14.522141,4.362208
+34,7.190547,4.150711
+35,7.483550,4.289419
+36,10.220000,4.293073
+37,10.969880,4.223164
+38,18.789984,4.193484
+39,10.968979,4.205701
+40,17.993284,4.309455
+41,14.928675,4.270360
+42,10.115572,4.305429
+43,5.957733,4.620828
+44,22.498720,4.408779
+45,28.281246,4.460776
+46,20.944214,4.272228
+47,14.352614,5.073153
+48,8.054336,4.123072
+49,8.984505,4.236765
+50,5.270642,154.265826
+51,6.659408,4.479795
+52,5.414080,4.557190
+53,15.811080,4.976661
+54,10.487754,4.269002
+55,17.966576,4.576193
+56,9.743145,4.375576
+57,17.266369,4.291231
+58,17.241358,4.732213
+59,12.465452,5.418700
+60,19.296269,4.071054
+61,8.765313,4.187583
+62,7.409617,4.880477
+63,19.081847,6.160572
+64,17.476648,7.346890
+65,18.984052,4.309022
+66,14.565430,4.272478
+67,5.346760,4.239164
+68,22.080962,4.899118
+69,15.887311,4.639301
+70,20.609174,5.279956
+71,9.835207,4.272556
+72,6.528574,4.793405
+73,6.785266,5.217536
+74,10.368050,4.263471
+75,7.809199,159.796058
+76,17.824511,4.282447
+77,21.390822,4.229612
+78,5.607736,4.227192
+79,13.650598,4.436509
+80,15.765881,4.285128
+81,17.037513,4.220685
+82,12.014945,5.409095
+83,9.132333,5.305970
+84,16.910908,4.327079
+85,17.348843,4.671426
+86,8.223034,4.461082
+87,13.455518,4.213298
+88,25.467849,4.532320
+89,14.661458,4.249644
+90,24.720682,4.274655
+91,17.810200,4.197618
+92,16.336687,4.894569
+93,13.752386,4.415168
+94,14.771433,4.627637
+95,18.388429,4.782457
+96,21.940440,4.622070
+97,6.812855,4.230013
+98,28.880808,4.286797
+99,20.864009,4.276698
+100,19.212574,161.346202
+101,21.204663,4.295381
+102,20.000715,4.583290
+103,12.816428,4.246263
+104,24.702609,4.808953
+105,15.341647,4.579972
+106,16.637773,4.159853
+107,12.857543,5.086674
+108,17.574840,4.995930
+109,12.536122,4.512929
+110,17.292923,4.878267
+111,17.865241,4.278919
+112,27.842752,4.374020
+113,29.114094,4.265122
+114,18.478463,4.258359
+115,13.629879,4.585581
+116,16.092220,4.289201
+117,24.049084,5.429255
+118,15.206857,4.103765
+119,16.594601,5.729389
+120,13.060644,5.328304
+121,33.418987,4.694337
+122,17.284419,4.332378
+123,11.930345,4.334104
+124,9.387192,4.631361
+125,16.359142,155.351185
+126,16.486189,4.298743
+127,10.510626,4.797482
+128,48.404223,4.958235
+129,25.379497,4.180818
+130,29.329743,4.511004
+131,44.033211,5.542739
+132,21.792012,4.246512
+133,16.113233,4.312226
+134,28.423992,4.411811
+135,23.404507,4.616759
+136,15.816371,4.313910
+137,15.395804,4.281030
+138,24.609701,4.245353
+139,17.299629,4.444300
+140,25.867170,4.303433
+141,50.430364,4.305682
+142,11.887269,4.172261
+143,16.407411,4.257832
+144,34.567763,4.241143
+145,24.712131,4.331734
+146,20.576994,4.577103
+147,43.418956,4.413754
+148,11.939057,4.196107
+149,21.218218,4.205113
+150,25.332071,153.051342
+151,29.700986,4.262352
+152,11.573387,4.200287
+153,50.700393,4.277909
+154,34.621719,4.261281
+155,17.063092,4.146803
+156,21.960377,4.246491
+157,35.539493,5.526902
+158,24.864509,5.136505
+159,37.308559,4.314604
+160,42.538922,4.298986
+161,18.832244,4.241497
+162,25.533337,4.247201
+163,4.973307,4.204369
+164,42.407616,4.257123
+165,9.871160,4.231145
+166,34.915594,5.119907
+167,26.312248,5.017767
+168,32.066928,4.602430
+169,20.911252,4.290483
+170,50.529248,4.461933
+171,65.482608,4.878184
+172,20.193885,4.294199
+173,39.943361,4.258081
+174,37.932262,4.321357
+175,40.687680,149.815545
+176,75.630092,4.833133
+177,28.177365,4.253484
+178,42.684106,4.484600
+179,41.353396,4.769772
+180,52.212155,4.311520
+181,83.929751,4.194989
+182,23.615442,4.253009
+183,37.597353,4.517926
+184,56.962057,4.283784
+185,58.772810,4.267120
+186,74.954084,4.265174
+187,49.123185,4.167335
+188,36.768044,6.016750
+189,49.288043,4.269515
+190,61.539554,4.361585
+191,54.237906,4.248995
+192,43.530181,6.559972
+193,22.719910,4.388037
+194,72.419733,4.258062
+195,49.297784,4.319465
+196,41.431498,4.351345
+197,78.331681,5.517626
+198,18.102999,4.171701
+199,44.417981,5.290207
+200,78.860776,152.168602
+201,54.313354,4.249561
+202,68.897563,4.367527
+203,29.084748,5.166762
+204,38.444829,4.893777
+205,29.242590,4.369283
+206,22.070157,4.330277
+207,123.509932,4.359090
+208,42.233707,4.266383
+209,54.782090,4.269588
+210,90.515483,4.251932
+211,62.572642,4.197357
+212,50.272633,4.510203
+213,26.062182,4.701779
+214,31.368775,4.271348
+215,56.784177,4.253511
+216,43.187614,4.210930
+217,40.677711,4.317078
+218,38.063309,4.308579
+219,28.955111,4.940386
+220,66.724510,4.237915
+221,62.326713,4.287534
+222,35.167189,4.520448
+223,29.014932,4.019990
+224,35.523907,4.183534
+225,99.925933,140.813205
+226,61.929674,4.020711
+227,102.013792,4.349355
+228,80.578938,4.351834
+229,137.489186,4.262271
+230,69.196930,4.334373
+231,99.057522,4.261880
+232,108.809981,4.259279
+233,146.577171,4.320172
+234,57.274408,4.246873
+235,74.264826,4.352492
+236,70.919023,4.338320
+237,85.343447,4.272143
+238,104.095550,4.265505
+239,123.126234,4.475868
+240,104.770064,4.376316
+241,129.663726,4.347389
+242,48.156440,4.271896
+243,179.290092,4.385027
+244,108.616976,4.370534
+245,270.736912,4.511404
+246,63.146037,4.213949
+247,71.603322,4.352710
+248,73.525713,4.271523
+249,177.411297,4.337808
+250,159.587929,141.962952
+251,75.217705,4.180389
+252,123.997477,4.269934
+253,146.333410,4.301265
+254,60.203723,4.278902
+255,66.010572,4.300990
+256,99.669237,4.478164
+257,64.641262,3.945834
+258,86.746532,4.318271
+259,250.693903,4.305593
+260,61.669217,4.201940
+261,46.592907,4.293123
+262,152.128133,4.265671
+263,128.309919,4.211738
+264,190.153276,4.160458
+265,81.315827,4.399302
+266,162.833816,4.359743
+267,110.532591,4.294369
+268,143.060616,4.320109
+269,119.228752,4.286176
+270,222.258872,4.292250
+271,191.603101,4.339400
+272,60.563835,4.325671
+273,80.277283,4.268290
+274,122.048832,4.180081
+275,55.551114,142.302250
+276,271.399557,4.276995
+277,144.577573,4.463318
+278,126.849601,4.195298
+279,345.974153,4.348982
+280,286.213339,4.153704
+281,70.585388,4.205653
+282,272.803495,4.296716
+283,161.143536,4.385654
+284,379.760515,4.371074
+285,118.613361,4.330158
+286,498.280245,4.299901
+287,435.252292,4.245602
+288,297.088021,4.264015
+289,493.368183,4.215956
+290,345.201070,4.469946
+291,338.032975,4.368542
+292,115.789123,4.452393
+293,262.304137,4.232430
+294,588.955305,4.235238
+295,394.118763,4.368038
+296,210.195462,4.449405
+297,570.860066,4.218055
+298,150.415147,4.293681
+299,448.392584,4.327936
+300,177.653786,145.558486
+301,790.051153,4.270066
+302,287.007885,4.651150
+303,519.508043,4.308103
+304,536.048231,4.333453
+305,282.384373,4.281546
+306,382.208699,4.427145
+307,730.138353,4.308648
+308,655.313662,4.345971
+309,195.611289,4.318386
+310,482.204752,4.370110
+311,685.610018,4.322612
+312,554.491975,4.464754
+313,639.273383,4.288941
+314,688.985031,4.292386
+315,446.703219,4.460622
+316,545.371723,4.323574
+317,675.807840,4.237408
+318,515.694405,4.276959
+319,451.740099,4.219907
+320,543.193202,4.335401
+321,586.500094,4.352762
+322,185.924358,4.255064
+323,319.586725,4.343580
+324,420.810762,4.263867
+325,355.977719,138.527768
+326,1290.343341,4.207276
+327,382.950855,4.282326
+328,521.773742,4.417524
+329,633.154624,4.351104
+330,523.631354,4.223712
+331,895.433306,4.287033
+332,1327.851948,4.304249
+333,381.603868,4.293777
+334,748.777153,4.360112
+335,341.802611,4.601258
+336,218.443909,4.390739
+337,1734.450915,4.363779
+338,876.672643,4.377830
+339,1239.711744,4.305480
+340,450.657608,4.418622
+341,1493.722239,4.243132
+342,2357.032304,4.210893
+343,409.392043,4.469448
+344,2185.346273,4.364550
+345,642.156119,4.315278
+346,1120.939460,4.467007
+347,2007.824688,4.334083
+348,4333.855599,4.357631
+349,650.822417,4.440809
+350,2171.278517,135.349681
+351,1812.859582,4.262601
+352,1853.041912,4.814510
+353,3892.674949,4.230783
+354,3176.251088,4.435172
+355,4976.762320,4.350934
+356,1733.174432,4.309169
+357,957.692641,4.393023
+358,3363.770232,4.436702
+359,1780.473650,4.387096
+360,4021.018830,4.321968
+361,6567.562792,4.406597
+362,2669.143101,4.297415
+363,2488.757043,4.277946
+364,5742.757558,4.218677
+365,6031.929646,4.381268
+366,5339.289840,4.378769
+367,7799.529309,4.702289
+368,5469.882157,4.404432
+369,5786.105254,4.351921
+370,9857.716898,12.636060
+371,6665.813731,4.395682
+372,6734.796435,29.578099
+373,5624.284122,4.446107
+374,6918.786368,3.143477
+375,5508.820814,103.761558
+376,1761.169832,3.290249
+377,5836.549090,3.241497
+378,5544.851838,3.153251
+379,2729.995335,3.250418
+380,4185.956390,3.287526
+381,967.122041,3.245682
+382,7333.045042,3.215058
+383,8865.338225,3.096833
+384,3859.571447,3.177098

serl_DivLogicEval_qwen25_0_5b/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

serl_DivLogicEval_qwen25_0_5b/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

serl_DivLogicEval_qwen25_0_5b/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

serl_DivLogicEval_qwen25_0_5b/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

serl_DivLogicEval_qwen25_0_5b/model.safetensors.znn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055b0a6600f4b3df1e3302c210df11b5b317bc2fa1cecaf617097fedc3324e40
+size 658237826

serl_DivLogicEval_qwen25_0_5b/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

serl_DivLogicEval_qwen25_0_5b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

serl_DivLogicEval_qwen25_0_5b/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

serl_DivLogicEval_qwen25_0_5b/training_timing_stats.txt

@@ -0,0 +1,240 @@
+1,0.000000,5.082071
+2,23.343911,4.437374
+3,29.165637,4.773586
+4,71.118464,5.096967
+5,59.646944,4.457138
+6,11.533109,4.820175
+7,44.675471,4.692322
+8,39.580576,4.735603
+9,28.446486,4.304353
+10,31.254596,4.777687
+11,41.358984,4.452837
+12,60.069898,4.414303
+13,54.163654,4.377126
+14,20.247023,4.371125
+15,51.596245,5.026279
+16,19.218695,4.723294
+17,49.651001,4.430423
+18,35.806930,4.463583
+19,51.336409,4.502892
+20,49.984129,4.343937
+21,57.400926,4.417849
+22,66.955026,5.232855
+23,54.445244,4.376263
+24,14.789761,4.371193
+25,20.716249,9.383080
+26,27.689011,4.416118
+27,67.112613,4.786923
+28,38.662317,4.229846
+29,59.764342,4.652889
+30,31.009341,4.511538
+31,52.102931,6.843754
+32,21.235242,5.978946
+33,53.246092,4.997544
+34,33.165758,4.971465
+35,26.222840,4.988286
+36,62.780119,4.745119
+37,38.346222,5.061878
+38,62.928481,5.194136
+39,30.619853,4.948794
+40,80.934617,4.194616
+41,69.092320,4.400535
+42,53.575978,4.415893
+43,47.181106,4.435529
+44,72.879434,4.830038
+45,20.932670,4.352065
+46,59.880546,5.945335
+47,52.057860,4.389300
+48,67.450343,4.327315
+49,32.151786,4.379604
+50,71.316633,11.933076
+51,50.954456,4.344166
+52,89.264377,6.130891
+53,33.923474,4.944231
+54,32.255949,5.205481
+55,45.098401,4.276014
+56,57.823288,4.504692
+57,56.520793,4.466918
+58,28.972739,5.536888
+59,27.661917,4.479847
+60,53.832944,4.387299
+61,52.360878,4.386467
+62,46.752243,5.471852
+63,26.101086,4.381067
+64,90.941244,4.489826
+65,58.493021,5.763259
+66,29.039556,5.188767
+67,104.540026,5.618186
+68,85.683128,4.424098
+69,43.514757,4.201650
+70,73.345927,5.404974
+71,111.377193,4.604003
+72,98.990363,4.816526
+73,67.747581,4.466772
+74,93.945955,4.426785
+75,48.106715,10.916191
+76,41.715907,4.457997
+77,51.833608,4.588645
+78,75.814548,4.413421
+79,121.305105,4.439640
+80,71.384869,5.018787
+81,72.315969,4.404001
+82,81.648096,4.429075
+83,75.623952,4.329841
+84,35.189298,4.377547
+85,66.276297,4.419978
+86,120.453299,4.308613
+87,35.725921,4.362154
+88,91.382529,4.335529
+89,74.617570,4.656166
+90,31.350552,4.851995
+91,104.417489,4.471592
+92,39.861748,4.400469
+93,84.711869,4.451278
+94,59.909546,4.691974
+95,77.982385,4.360954
+96,80.951027,5.009480
+97,46.037983,4.407079
+98,71.308764,6.249437
+99,101.493818,4.439319
+100,115.588326,20.813649
+101,30.184126,5.221971
+102,71.952502,4.433097
+103,102.662750,4.402790
+104,58.871214,4.437341
+105,153.674703,4.464880
+106,49.254428,4.491958
+107,83.573501,5.081364
+108,143.831954,4.314705
+109,47.619878,5.405372
+110,67.357944,4.443033
+111,145.697050,4.809496
+112,83.034991,6.563850
+113,104.990268,4.461771
+114,117.832246,4.563348
+115,85.486798,4.454287
+116,83.886964,4.398485
+117,78.168350,5.745471
+118,182.674416,4.792571
+119,72.300917,4.441147
+120,132.386850,4.441580
+121,209.695849,4.498136
+122,254.925629,4.379076
+123,237.227642,4.358326
+124,95.076377,4.456376
+125,267.942653,10.833124
+126,187.471734,4.447010
+127,102.422439,5.214560
+128,132.760214,4.402928
+129,78.072616,4.169803
+130,106.431456,4.450302
+131,409.281026,4.381754
+132,77.709974,4.379629
+133,44.748852,4.408122
+134,306.412024,4.446736
+135,399.823545,4.410878
+136,385.750319,4.431360
+137,388.459488,4.432269
+138,138.133087,4.367367
+139,192.165449,4.427276
+140,79.972575,4.431563
+141,168.776347,4.262083
+142,464.430520,4.671600
+143,237.665247,4.531344
+144,517.038101,4.424723
+145,441.697744,4.435209
+146,347.803968,4.470179
+147,481.190511,4.395966
+148,242.496571,4.611574
+149,761.948156,4.376536
+150,477.383099,10.439751
+151,997.035156,4.471328
+152,660.181178,4.332556
+153,506.220364,4.413736
+154,509.156979,4.431436
+155,1040.275226,4.486830
+156,1105.034831,4.436360
+157,315.709018,4.491812
+158,935.034815,4.451886
+159,459.055218,4.456975
+160,576.445513,4.252332
+161,494.708502,4.645729
+162,819.244929,4.415672
+163,406.422048,4.434959
+164,305.492133,4.451517
+165,504.754201,4.559851
+166,1295.637072,4.296475
+167,265.401861,4.475107
+168,636.653002,4.416459
+169,497.162306,4.445129
+170,138.727417,4.403041
+171,1209.405294,4.457506
+172,1080.565137,4.444360
+173,726.530572,4.313740
+174,1462.282337,4.367068
+175,997.020233,11.479211
+176,257.385082,4.355011
+177,1155.236681,4.504972
+178,569.972842,4.344678
+179,1176.326787,4.499127
+180,827.954691,4.472258
+181,1544.591122,4.520805
+182,1311.779399,4.490487
+183,372.391124,4.490347
+184,1297.828476,4.407010
+185,557.679660,4.395456
+186,544.138641,4.459730
+187,1274.327063,4.395143
+188,535.382596,4.424845
+189,775.159088,4.313752
+190,684.866195,4.512029
+191,1846.294482,4.514859
+192,576.394976,4.497850
+193,1458.045964,4.383441
+194,454.234083,4.624582
+195,2208.461359,4.588054
+196,846.867998,4.414042
+197,493.716381,4.400737
+198,1406.978776,4.439997
+199,989.319712,4.400209
+200,1077.968862,19.789387
+201,910.076205,4.378968
+202,921.668028,4.406018
+203,988.076073,4.301996
+204,1015.632528,4.775373
+205,804.330358,4.631374
+206,1063.883659,4.417552
+207,1271.832771,4.448085
+208,640.838506,4.445318
+209,2230.781863,4.924688
+210,2664.974735,4.494701
+211,3295.139768,4.785919
+212,1723.218234,4.495645
+213,2857.889971,4.272377
+214,3476.185508,4.488955
+215,1829.333825,4.432227
+216,2272.262623,4.308544
+217,2569.488925,4.231528
+218,3558.359938,4.570888
+219,1742.356068,4.530211
+220,5052.881146,4.422307
+221,3018.368170,4.404658
+222,2030.786036,4.458096
+223,4688.846037,4.487912
+224,3192.546812,4.561647
+225,1652.469825,10.399626
+226,4172.048542,4.429956
+227,3547.645504,4.451240
+228,2809.242348,4.878609
+229,1724.214743,4.520738
+230,2071.087252,4.664246
+231,2998.014744,4.474138
+232,4026.460938,4.415263
+233,4950.958816,4.431537
+234,2148.719248,4.529800
+235,2760.051476,4.712254
+236,3778.813716,4.484581
+237,2539.603752,4.430357
+238,4789.364270,4.424970
+239,4282.208250,32.036909
+240,8384.455937,4.492592

serl_DivLogicEval_qwen25_1_5b/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

serl_DivLogicEval_qwen25_1_5b/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

serl_DivLogicEval_qwen25_1_5b/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

serl_DivLogicEval_qwen25_1_5b/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

serl_DivLogicEval_qwen25_1_5b/model.safetensors.znn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6fc35d151cad39ed76f65426d41dcfc6e9614bd1a844ba41e8c1ae9adbe464
+size 2052927774

serl_DivLogicEval_qwen25_1_5b/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

serl_DivLogicEval_qwen25_1_5b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

serl_DivLogicEval_qwen25_1_5b/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

serl_DivLogicEval_qwen25_1_5b/training_timing_stats.txt

@@ -0,0 +1,290 @@
+1,0.000000,15.698836
+2,184.987508,10.345038
+3,103.938607,10.498641
+4,68.911921,10.580388
+5,99.559404,12.915764
+6,174.189785,10.492529
+7,100.906598,10.538512
+8,91.030383,10.322251
+9,182.224193,10.453360
+10,152.490580,13.323854
+11,73.477410,10.473754
+12,132.006975,12.153858
+13,80.794707,11.152888
+14,133.585990,10.400352
+15,75.749267,10.431479
+16,160.985606,10.404630
+17,130.160357,10.718128
+18,63.720487,10.310087
+19,66.178441,11.416169
+20,90.448696,11.215881
+21,34.715647,11.402522
+22,164.089567,11.329571
+23,99.724153,11.346273
+24,137.800511,10.291355
+25,80.949987,24.467692
+26,86.025284,10.627170
+27,149.314025,12.410472
+28,89.872534,10.910424
+29,118.125247,10.406943
+30,68.375848,11.158947
+31,117.985047,11.228525
+32,89.765095,10.375960
+33,92.484772,10.270487
+34,67.969764,10.431308
+35,38.727997,10.453233
+36,81.539613,10.555570
+37,65.302186,10.363026
+38,136.512347,13.694187
+39,131.082296,10.483441
+40,108.505246,10.434555
+41,81.728958,10.631183
+42,112.078072,10.734416
+43,61.606022,10.836647
+44,161.309504,11.675478
+45,123.796322,11.399962
+46,124.661973,10.385393
+47,66.639424,10.325962
+48,92.287244,10.430293
+49,76.078432,13.126994
+50,57.406429,23.638066
+51,24.628727,10.800908
+52,136.218714,10.367422
+53,84.715218,10.343595
+54,170.423961,10.395314
+55,78.812956,10.910109
+56,25.507323,11.743608
+57,81.988382,10.688170
+58,100.594773,10.556817
+59,56.640305,10.494340
+60,59.387946,10.180170
+61,82.741410,10.545004
+62,191.213876,10.566794
+63,77.617310,10.679645
+64,93.493824,10.863822
+65,172.238645,12.408879
+66,180.668720,11.449890
+67,110.902835,10.267483
+68,107.003035,10.340877
+69,72.813377,10.315245
+70,105.758984,11.126300
+71,178.932309,10.311546
+72,66.607448,10.284820
+73,249.523871,10.422338
+74,90.374553,13.139014
+75,126.294924,24.835312
+76,69.197300,10.305389
+77,173.349219,10.397904
+78,81.362846,11.082625
+79,156.336583,10.484347
+80,52.766700,10.373012
+81,111.694799,10.539055
+82,57.288537,10.307555
+83,90.315186,10.364358
+84,125.684930,10.359657
+85,237.944341,10.217921
+86,154.075909,10.596973
+87,43.949450,10.165861
+88,119.588435,10.409825
+89,115.904641,10.588985
+90,202.182536,10.326030
+91,94.884858,10.547875
+92,95.940911,10.367332
+93,203.521574,11.243781
+94,48.585025,10.353364
+95,84.552584,10.318451
+96,362.343082,10.630170
+97,111.145493,10.446539
+98,163.403445,10.401875
+99,243.814408,10.618612
+100,75.314287,51.734538
+101,205.861077,10.373703
+102,138.976372,10.672942
+103,67.994825,10.308849
+104,179.751992,10.414715
+105,107.546092,10.259610
+106,122.528399,10.353075
+107,217.517554,10.359187
+108,184.882719,10.607034
+109,200.132362,10.546498
+110,315.539017,10.942140
+111,235.715224,11.220093
+112,295.172544,10.295614
+113,199.856941,10.846652
+114,147.890420,10.359087
+115,343.481835,10.330173
+116,67.054739,10.316074
+117,290.193641,10.359518
+118,64.714304,10.338304
+119,349.718614,13.280542
+120,142.434099,10.427106
+121,154.802179,10.373414
+122,170.196727,10.257911
+123,205.280597,10.298558
+124,284.155960,10.501913
+125,251.942002,24.807129
+126,295.088821,10.519242
+127,461.982353,10.358028
+128,129.003008,10.498513
+129,148.256617,10.355275
+130,82.785005,12.792143
+131,335.493966,10.300151
+132,54.910005,10.366421
+133,296.944017,10.376741
+134,205.594261,10.513313
+135,157.931079,10.183274
+136,364.736765,10.365680
+137,493.502985,10.301424
+138,143.586016,10.394180
+139,194.381928,10.317837
+140,468.289440,10.391477
+141,233.198032,10.241279
+142,222.554898,10.367633
+143,297.994604,10.362619
+144,359.475340,10.402225
+145,437.508947,12.947945
+146,308.647602,10.340099
+147,318.787815,10.330218
+148,196.132370,10.274851
+149,395.979308,10.321117
+150,181.057203,24.403876
+151,394.677798,10.361365
+152,220.416360,10.307717
+153,210.896633,10.313026
+154,291.938728,10.538779
+155,246.883940,10.250967
+156,364.124931,10.405989
+157,336.141034,13.710377
+158,327.842043,10.385385
+159,263.634674,10.390614
+160,196.912327,10.373214
+161,127.016288,10.559906
+162,262.768896,10.603637
+163,465.739898,10.319807
+164,311.816285,10.272088
+165,583.210448,10.353450
+166,85.767775,10.534317
+167,157.219223,10.317628
+168,272.338921,10.778442
+169,160.769764,10.413409
+170,179.692313,10.259976
+171,307.935774,10.320118
+172,408.021101,10.382061
+173,301.968292,10.379475
+174,394.674145,10.387112
+175,157.004974,24.047220
+176,227.232786,10.357343
+177,316.165427,10.554898
+178,306.817406,10.294874
+179,252.520170,10.302618
+180,295.587541,10.351486
+181,139.265189,10.315967
+182,310.716072,10.391189
+183,514.906683,10.637845
+184,606.402852,10.238038
+185,255.231913,10.335776
+186,420.934797,10.611113
+187,723.985130,10.344620
+188,127.505721,10.374084
+189,694.248238,10.614646
+190,673.565478,10.316399
+191,958.843695,10.354174
+192,265.808472,10.391091
+193,487.516794,10.342684
+194,185.545358,10.472155
+195,374.931987,10.311778
+196,363.759989,11.271532
+197,701.422930,10.304204
+198,659.806950,10.358045
+199,319.573756,10.328583
+200,772.273627,54.154051
+201,1554.056841,11.385306
+202,472.447142,10.258459
+203,317.440373,10.331579
+204,434.138134,11.795364
+205,573.523036,10.370666
+206,627.841935,10.359764
+207,127.407100,10.554827
+208,478.304078,10.399034
+209,628.895759,10.349231
+210,813.709906,10.418691
+211,471.664288,10.319722
+212,1138.330524,10.294362
+213,439.359026,10.357647
+214,750.019768,10.445812
+215,838.128383,10.416840
+216,1145.517378,10.264691
+217,651.397760,10.455513
+218,969.287465,10.384638
+219,488.614331,10.234636
+220,164.864097,10.327320
+221,617.080286,10.249316
+222,1154.923687,10.317888
+223,787.137010,10.260962
+224,204.931807,10.236206
+225,1059.883523,23.155853
+226,862.266250,10.411027
+227,601.103378,10.655200
+228,778.842776,10.324252
+229,1364.552765,10.418200
+230,216.897372,10.464373
+231,994.385693,10.536700
+232,349.093651,10.334594
+233,1132.340451,10.422615
+234,1577.918352,10.464365
+235,627.152066,10.446992
+236,872.541699,10.458946
+237,490.458248,10.611597
+238,518.245569,10.448639
+239,796.103124,10.465015
+240,444.134007,10.375207
+241,1906.248109,10.385483
+242,1912.198202,10.414903
+243,1223.860068,10.337654
+244,567.924021,10.394179
+245,830.418917,10.454145
+246,1034.841175,10.598189
+247,720.193746,10.548746
+248,927.159583,10.383527
+249,1173.334494,10.321650
+250,1491.489526,24.009165
+251,132.780114,10.409952
+252,1292.732244,10.385482
+253,1563.305991,10.432625
+254,794.568629,10.491808
+255,696.089651,10.616449
+256,386.258356,10.312712
+257,129.186141,10.365726
+258,360.206299,10.480694
+259,740.057115,10.427691
+260,586.984112,10.453576
+261,881.214020,10.328007
+262,307.927006,10.420080
+263,1303.368131,10.607352
+264,1450.917753,10.575745
+265,430.871833,10.396615
+266,1279.840251,10.487655
+267,1812.929206,10.529718
+268,3524.408739,10.400036
+269,1857.125871,10.481780
+270,2012.887201,10.448032
+271,547.739757,10.658019
+272,414.533708,10.399931
+273,333.999070,10.343612
+274,698.566981,10.365754
+275,2347.554100,23.747646
+276,808.409178,10.467098
+277,1547.641830,10.407040
+278,911.117812,10.587830
+279,1366.625034,10.351751
+280,1126.297115,10.447034
+281,404.943487,10.476286
+282,118.232876,10.440877
+283,964.232723,10.455859
+284,1219.345646,10.493052
+285,3259.672975,10.471967
+286,2770.894740,10.414941
+287,9120.124205,10.471986
+288,8810.347919,10.581931
+289,9647.505481,10.349897
+290,24602.797602,10.405019

serl_GSM-MC_qwen25_1_5b/training_timing_stats.txt

@@ -0,0 +1,20 @@
+1,0.000000,31.982644
+2,6.265109,10.446789
+3,17.009502,10.934864
+4,6.500108,13.137776
+5,12.750072,13.419653
+6,4.245906,12.884458
+7,8.981158,8.507783
+8,5.856088,10.684534
+9,10.540212,12.902983
+10,5.112955,12.028255
+11,5.547032,13.341068
+12,10.912244,10.548071
+13,4.800225,12.591822
+14,8.797457,10.311805
+15,8.506101,13.410530
+16,5.171409,10.229419
+17,12.951681,14.539927
+18,13.508169,18.485901
+1,0.000000,22.898594
+2,10.716990,14.351388

serl_JAMA_qwen25_0_5b/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

serl_JAMA_qwen25_0_5b/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

serl_JAMA_qwen25_0_5b/config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

serl_JAMA_qwen25_0_5b/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

serl_JAMA_qwen25_0_5b/model.safetensors.znn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07bc1567b3383dbaa64f7cbbfcc887ff46973919c25f4263e49ff14f4dd925b
+size 658237276

serl_JAMA_qwen25_0_5b/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

serl_JAMA_qwen25_0_5b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

serl_JAMA_qwen25_0_5b/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

serl_JAMA_qwen25_0_5b/training_timing_stats.txt

@@ -0,0 +1,260 @@
+1,0.000000,5.638542
+2,61.073200,4.468168
+3,43.787101,4.274712
+4,50.694855,4.157968
+5,17.063731,4.902809
+6,26.257459,4.092501
+7,111.273807,5.280484
+8,42.965338,4.933420
+9,73.593122,5.426455
+10,50.446524,4.134868
+11,55.202881,4.274416
+12,60.252769,4.238946
+13,95.801712,4.362028
+14,45.937465,4.266160
+15,24.546429,4.252639
+16,68.974261,4.683931
+17,81.428509,4.953014
+18,59.343128,4.519352
+19,27.588414,4.143443
+20,132.273009,4.430651
+21,65.236826,6.798901
+22,32.507043,4.039201
+23,76.842795,4.173211
+24,76.735697,5.182050
+25,41.544386,22.945195
+26,35.921764,6.616991
+27,97.002586,5.305187
+28,62.151785,5.803974
+29,121.534839,4.240996
+30,111.514705,4.284079
+31,40.754700,5.189211
+32,40.778229,4.094471
+33,111.283914,6.473455
+34,96.007354,4.871316
+35,81.693250,4.219647
+36,60.453301,5.297679
+37,45.121193,4.162423
+38,39.863759,4.102179
+39,65.094592,4.161562
+40,58.933715,4.139425
+41,109.093013,4.462523
+42,45.694715,4.574333
+43,82.374785,5.688078
+44,49.265024,4.810124
+45,83.530681,4.217392
+46,49.537532,5.692872
+47,39.080723,4.097369
+48,94.085934,4.981208
+49,34.804034,4.663019
+50,57.751571,17.882665
+51,103.404226,4.233790
+52,24.474700,4.185228
+53,57.115004,4.854055
+54,96.106415,4.158576
+55,62.293439,5.004621
+56,103.994095,4.761114
+57,36.022518,3.717734
+58,88.012617,4.063317
+59,33.437691,4.204981
+60,78.454958,4.245547
+61,34.434848,4.171341
+62,50.208802,4.009061
+63,78.223347,4.190795
+64,98.741564,4.086397
+65,17.473649,4.816165
+66,12.408057,4.079040
+67,93.494271,4.260850
+68,100.682670,4.185536
+69,99.927799,4.191690
+70,48.635432,3.849377
+71,73.786551,4.749009
+72,81.921921,4.615372
+73,45.452050,4.114689
+74,45.131884,4.328579
+75,70.273558,16.719918
+76,102.723972,4.117456
+77,66.349106,4.120658
+78,110.579396,4.297837
+79,78.285211,4.199404
+80,110.384186,4.100422
+81,18.174144,5.881428
+82,112.334190,5.326608
+83,105.782024,5.331400
+84,56.064380,4.201853
+85,176.656375,4.191485
+86,39.667786,5.338857
+87,68.347150,4.630957
+88,109.038959,6.110158
+89,45.177677,4.868446
+90,69.803427,4.238461
+91,165.499282,4.316974
+92,113.520036,4.321542
+93,85.452108,4.143183
+94,74.030433,4.175925
+95,48.738755,6.479228
+96,81.615341,4.187810
+97,125.127976,4.219762
+98,120.916214,4.223078
+99,94.902023,3.971183
+100,98.686471,25.004826
+101,112.302802,4.621962
+102,86.861613,4.350319
+103,70.721306,4.395035
+104,98.942415,4.786612
+105,95.589941,4.824575
+106,160.211125,4.325841
+107,93.727891,4.187752
+108,112.571321,4.224102
+109,113.525795,4.321146
+110,206.272802,4.071795
+111,72.150858,4.261307
+112,66.314898,4.233427
+113,146.045037,4.263626
+114,57.166170,4.557730
+115,169.276625,4.451139
+116,83.127122,4.155577
+117,105.575844,4.193693
+118,147.889923,4.275190
+119,179.363430,4.266527
+120,93.798384,4.490682
+121,152.887703,4.330657
+122,168.503100,4.324728
+123,246.556234,4.272055
+124,255.012913,4.310576
+125,413.669806,16.730066
+126,311.032099,4.812243
+127,171.642399,4.056125
+128,162.927696,4.207760
+129,234.712160,4.330100
+130,241.515855,4.165414
+131,175.218343,4.188054
+132,296.115855,4.217968
+133,203.445509,4.254251
+134,179.319989,4.260509
+135,367.716759,4.251330
+136,489.233332,3.650317
+137,386.073172,4.222274
+138,508.886730,4.322600
+139,266.278765,4.211603
+140,335.060658,4.307387
+141,413.109163,4.193956
+142,577.376846,4.305003
+143,523.087433,4.196958
+144,323.638043,4.300330
+145,472.990095,4.099222
+146,526.929818,4.196184
+147,470.334106,4.226068
+148,413.128022,4.190172
+149,676.307394,4.242815
+150,332.884312,17.232611
+151,483.885679,4.286422
+152,416.368013,4.239461
+153,455.711863,5.855738
+154,516.019256,4.283398
+155,552.737028,4.362178
+156,481.001750,4.217543
+157,268.122855,4.218116
+158,559.899966,4.237198
+159,198.340678,4.199824
+160,724.531978,4.400863
+161,398.935331,4.152549
+162,695.474007,4.297462
+163,310.346267,4.303225
+164,791.417735,4.164111
+165,823.887684,4.226874
+166,403.432182,4.243482
+167,272.478215,4.043776
+168,1472.387187,4.283116
+169,427.064281,4.268148
+170,848.329988,4.270886
+171,875.045300,4.321143
+172,1423.918570,4.335100
+173,1770.620134,4.222162
+174,919.669010,4.312443
+175,911.568682,17.705517
+176,1547.954208,4.248280
+177,627.320133,4.244479
+178,1625.220206,4.334549
+179,289.361169,4.265906
+180,147.000143,4.248412
+181,658.390609,4.539253
+182,407.733986,4.287198
+183,755.092941,4.374910
+184,1119.467211,4.162309
+185,1150.993639,4.266017
+186,1247.616182,4.303346
+187,932.461628,4.212638
+188,1901.739016,4.257504
+189,973.484359,4.293121
+190,425.081819,4.297563
+191,1254.183985,4.258930
+192,739.246797,4.210436
+193,1031.276169,4.323449
+194,1409.753098,4.348031
+195,818.726296,4.399934
+196,1194.503003,4.239021
+197,591.388711,4.260958
+198,1886.307853,4.212524
+199,1267.067362,4.219634
+200,1913.975779,25.397486
+201,808.946089,4.158391
+202,1140.821244,4.372936
+203,1047.912347,4.316469
+204,1056.521821,4.599998
+205,1710.206602,4.313450
+206,1735.443314,4.289861
+207,596.790286,4.370477
+208,2990.103977,4.236632
+209,2637.011892,4.312227
+210,2418.108553,4.241091
+211,1851.092344,4.296292
+212,1767.825472,4.263005
+213,1054.248887,4.081251
+214,1379.669254,4.287922
+215,2536.816870,4.281880
+216,1327.872878,4.288512
+217,1460.230701,4.296818
+218,741.432253,4.248370
+219,577.473991,4.246345
+220,1860.411193,4.360601
+221,1902.671692,4.307790
+222,1525.913008,4.205896
+223,569.074651,4.080820
+224,527.142943,4.293460
+225,3436.938648,16.893482
+226,1500.667094,4.197104
+227,2901.873081,4.293402
+228,2247.600949,4.223164
+229,945.209480,4.312220
+230,2778.158174,4.301870
+231,2638.953059,4.307287
+232,1325.956824,4.140131
+233,2143.303290,4.279625
+234,2342.042998,4.115192
+235,1792.692995,4.296393
+236,1495.814685,4.618195
+237,2084.017382,4.221761
+238,460.940315,4.261731
+239,4038.722852,4.221348
+240,939.333135,4.310095
+241,1989.946972,4.322113
+242,601.887236,4.246985
+243,3226.632349,4.290357
+244,1473.852399,4.196680
+245,490.197897,4.355975
+246,2093.722418,4.278485
+247,1178.531813,4.279603
+248,3233.513552,4.427789
+249,6028.347517,13.026602
+250,1530.253056,16.795754
+251,1372.218560,4.261721
+252,2849.677707,4.233879
+253,2610.492019,30.342332
+254,1558.092889,4.286047
+255,2308.843817,4.243480
+256,2693.467690,4.327823
+257,1448.421527,4.174306
+258,1679.541604,4.151366
+259,2623.722935,4.239807
+260,319.420089,4.150184

serl_JAMA_qwen25_1_5b/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

serl_JAMA_qwen25_1_5b/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}