vitaleantonio's picture
Upload checkpoint DeepSeek-Coder-CONTROL-LEETCODE-6.7B-Base-9 at epoch 9
7723ce3 verified
Raw
History Blame Contribute Delete
22.8 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.0,
"eval_steps": 500,
"global_step": 612,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07428040854224698,
"grad_norm": 0.0166015625,
"learning_rate": 4.970588235294118e-05,
"loss": 0.6377665996551514,
"step": 5
},
{
"epoch": 0.14856081708449395,
"grad_norm": 0.0146484375,
"learning_rate": 4.933823529411765e-05,
"loss": 0.6021791934967041,
"step": 10
},
{
"epoch": 0.22284122562674094,
"grad_norm": 0.01373291015625,
"learning_rate": 4.897058823529412e-05,
"loss": 0.6274982929229737,
"step": 15
},
{
"epoch": 0.2971216341689879,
"grad_norm": 0.0135498046875,
"learning_rate": 4.860294117647059e-05,
"loss": 0.599825382232666,
"step": 20
},
{
"epoch": 0.3714020427112349,
"grad_norm": 0.0159912109375,
"learning_rate": 4.823529411764706e-05,
"loss": 0.6859479427337647,
"step": 25
},
{
"epoch": 0.4456824512534819,
"grad_norm": 0.01422119140625,
"learning_rate": 4.7867647058823535e-05,
"loss": 0.636006212234497,
"step": 30
},
{
"epoch": 0.5199628597957289,
"grad_norm": 0.01116943359375,
"learning_rate": 4.75e-05,
"loss": 0.6127719879150391,
"step": 35
},
{
"epoch": 0.5942432683379758,
"grad_norm": 0.01531982421875,
"learning_rate": 4.713235294117647e-05,
"loss": 0.5927554130554199,
"step": 40
},
{
"epoch": 0.6685236768802229,
"grad_norm": 0.011474609375,
"learning_rate": 4.6764705882352944e-05,
"loss": 0.6282303333282471,
"step": 45
},
{
"epoch": 0.7428040854224698,
"grad_norm": 0.015869140625,
"learning_rate": 4.639705882352942e-05,
"loss": 0.5779662609100342,
"step": 50
},
{
"epoch": 0.8170844939647168,
"grad_norm": 0.01318359375,
"learning_rate": 4.6029411764705885e-05,
"loss": 0.617146348953247,
"step": 55
},
{
"epoch": 0.8913649025069638,
"grad_norm": 0.0130615234375,
"learning_rate": 4.566176470588235e-05,
"loss": 0.5746903896331788,
"step": 60
},
{
"epoch": 0.9656453110492108,
"grad_norm": 0.0108642578125,
"learning_rate": 4.5294117647058826e-05,
"loss": 0.5909358024597168,
"step": 65
},
{
"epoch": 1.0297121634168989,
"grad_norm": 0.00994873046875,
"learning_rate": 4.49264705882353e-05,
"loss": 0.5567221164703369,
"step": 70
},
{
"epoch": 1.1039925719591457,
"grad_norm": 0.01031494140625,
"learning_rate": 4.455882352941177e-05,
"loss": 0.5583184242248536,
"step": 75
},
{
"epoch": 1.1782729805013927,
"grad_norm": 0.01214599609375,
"learning_rate": 4.4191176470588235e-05,
"loss": 0.5047792911529541,
"step": 80
},
{
"epoch": 1.2525533890436398,
"grad_norm": 0.014892578125,
"learning_rate": 4.382352941176471e-05,
"loss": 0.509721040725708,
"step": 85
},
{
"epoch": 1.3268337975858868,
"grad_norm": 0.0162353515625,
"learning_rate": 4.345588235294118e-05,
"loss": 0.522771167755127,
"step": 90
},
{
"epoch": 1.4011142061281336,
"grad_norm": 0.01263427734375,
"learning_rate": 4.308823529411765e-05,
"loss": 0.48066258430480957,
"step": 95
},
{
"epoch": 1.4753946146703807,
"grad_norm": 0.02294921875,
"learning_rate": 4.272058823529412e-05,
"loss": 0.5085556030273437,
"step": 100
},
{
"epoch": 1.5496750232126275,
"grad_norm": 0.01287841796875,
"learning_rate": 4.235294117647059e-05,
"loss": 0.4806520462036133,
"step": 105
},
{
"epoch": 1.6239554317548746,
"grad_norm": 0.0107421875,
"learning_rate": 4.198529411764706e-05,
"loss": 0.48960013389587403,
"step": 110
},
{
"epoch": 1.6982358402971216,
"grad_norm": 0.0120849609375,
"learning_rate": 4.161764705882353e-05,
"loss": 0.47647743225097655,
"step": 115
},
{
"epoch": 1.7725162488393686,
"grad_norm": 0.0230712890625,
"learning_rate": 4.125e-05,
"loss": 0.5240037918090821,
"step": 120
},
{
"epoch": 1.8467966573816157,
"grad_norm": 0.0152587890625,
"learning_rate": 4.0882352941176474e-05,
"loss": 0.5106610298156739,
"step": 125
},
{
"epoch": 1.9210770659238627,
"grad_norm": 0.01312255859375,
"learning_rate": 4.051470588235294e-05,
"loss": 0.5423622608184815,
"step": 130
},
{
"epoch": 1.9953574744661096,
"grad_norm": 0.01214599609375,
"learning_rate": 4.0147058823529415e-05,
"loss": 0.48050861358642577,
"step": 135
},
{
"epoch": 2.0594243268337977,
"grad_norm": 0.01177978515625,
"learning_rate": 3.977941176470588e-05,
"loss": 0.4528938293457031,
"step": 140
},
{
"epoch": 2.1337047353760448,
"grad_norm": 0.0135498046875,
"learning_rate": 3.9411764705882356e-05,
"loss": 0.4708698749542236,
"step": 145
},
{
"epoch": 2.2079851439182914,
"grad_norm": 0.015869140625,
"learning_rate": 3.9044117647058823e-05,
"loss": 0.40610790252685547,
"step": 150
},
{
"epoch": 2.2822655524605384,
"grad_norm": 0.020263671875,
"learning_rate": 3.86764705882353e-05,
"loss": 0.4004369735717773,
"step": 155
},
{
"epoch": 2.3565459610027855,
"grad_norm": 0.01495361328125,
"learning_rate": 3.830882352941177e-05,
"loss": 0.402101993560791,
"step": 160
},
{
"epoch": 2.4308263695450325,
"grad_norm": 0.01519775390625,
"learning_rate": 3.794117647058824e-05,
"loss": 0.41231889724731446,
"step": 165
},
{
"epoch": 2.5051067780872796,
"grad_norm": 0.01611328125,
"learning_rate": 3.7573529411764706e-05,
"loss": 0.4784365653991699,
"step": 170
},
{
"epoch": 2.5793871866295266,
"grad_norm": 0.0174560546875,
"learning_rate": 3.720588235294118e-05,
"loss": 0.4141225814819336,
"step": 175
},
{
"epoch": 2.6536675951717736,
"grad_norm": 0.0189208984375,
"learning_rate": 3.6838235294117654e-05,
"loss": 0.44509315490722656,
"step": 180
},
{
"epoch": 2.7279480037140207,
"grad_norm": 0.018310546875,
"learning_rate": 3.6470588235294114e-05,
"loss": 0.4210689067840576,
"step": 185
},
{
"epoch": 2.8022284122562673,
"grad_norm": 0.0272216796875,
"learning_rate": 3.610294117647059e-05,
"loss": 0.4066977024078369,
"step": 190
},
{
"epoch": 2.8765088207985143,
"grad_norm": 0.0128173828125,
"learning_rate": 3.573529411764706e-05,
"loss": 0.4026792049407959,
"step": 195
},
{
"epoch": 2.9507892293407614,
"grad_norm": 0.0174560546875,
"learning_rate": 3.5367647058823536e-05,
"loss": 0.44449539184570314,
"step": 200
},
{
"epoch": 3.0148560817084493,
"grad_norm": 0.016357421875,
"learning_rate": 3.5e-05,
"loss": 0.36432900428771975,
"step": 205
},
{
"epoch": 3.0891364902506964,
"grad_norm": 0.01904296875,
"learning_rate": 3.463235294117647e-05,
"loss": 0.31903977394104005,
"step": 210
},
{
"epoch": 3.1634168987929434,
"grad_norm": 0.02587890625,
"learning_rate": 3.4264705882352945e-05,
"loss": 0.36570186614990235,
"step": 215
},
{
"epoch": 3.2376973073351905,
"grad_norm": 0.0272216796875,
"learning_rate": 3.389705882352941e-05,
"loss": 0.3146202087402344,
"step": 220
},
{
"epoch": 3.3119777158774375,
"grad_norm": 0.02099609375,
"learning_rate": 3.352941176470588e-05,
"loss": 0.3360214948654175,
"step": 225
},
{
"epoch": 3.386258124419684,
"grad_norm": 0.0166015625,
"learning_rate": 3.3161764705882353e-05,
"loss": 0.310416054725647,
"step": 230
},
{
"epoch": 3.460538532961931,
"grad_norm": 0.017822265625,
"learning_rate": 3.279411764705883e-05,
"loss": 0.32846100330352784,
"step": 235
},
{
"epoch": 3.534818941504178,
"grad_norm": 0.0196533203125,
"learning_rate": 3.2426470588235295e-05,
"loss": 0.3553309917449951,
"step": 240
},
{
"epoch": 3.6090993500464252,
"grad_norm": 0.0186767578125,
"learning_rate": 3.205882352941177e-05,
"loss": 0.3320646286010742,
"step": 245
},
{
"epoch": 3.6833797585886723,
"grad_norm": 0.021484375,
"learning_rate": 3.1691176470588236e-05,
"loss": 0.32249722480773924,
"step": 250
},
{
"epoch": 3.7576601671309193,
"grad_norm": 0.022216796875,
"learning_rate": 3.132352941176471e-05,
"loss": 0.3548262596130371,
"step": 255
},
{
"epoch": 3.8319405756731664,
"grad_norm": 0.02685546875,
"learning_rate": 3.095588235294118e-05,
"loss": 0.32151591777801514,
"step": 260
},
{
"epoch": 3.9062209842154134,
"grad_norm": 0.0216064453125,
"learning_rate": 3.058823529411765e-05,
"loss": 0.3099962711334229,
"step": 265
},
{
"epoch": 3.98050139275766,
"grad_norm": 0.021484375,
"learning_rate": 3.022058823529412e-05,
"loss": 0.34290590286254885,
"step": 270
},
{
"epoch": 4.044568245125348,
"grad_norm": 0.017822265625,
"learning_rate": 2.985294117647059e-05,
"loss": 0.29376044273376467,
"step": 275
},
{
"epoch": 4.1188486536675954,
"grad_norm": 0.02685546875,
"learning_rate": 2.948529411764706e-05,
"loss": 0.26094722747802734,
"step": 280
},
{
"epoch": 4.1931290622098425,
"grad_norm": 0.0211181640625,
"learning_rate": 2.9117647058823534e-05,
"loss": 0.22459895610809327,
"step": 285
},
{
"epoch": 4.2674094707520895,
"grad_norm": 0.0191650390625,
"learning_rate": 2.8749999999999997e-05,
"loss": 0.2518251895904541,
"step": 290
},
{
"epoch": 4.341689879294336,
"grad_norm": 0.0284423828125,
"learning_rate": 2.838235294117647e-05,
"loss": 0.241434645652771,
"step": 295
},
{
"epoch": 4.415970287836583,
"grad_norm": 0.02392578125,
"learning_rate": 2.8014705882352942e-05,
"loss": 0.24431805610656737,
"step": 300
},
{
"epoch": 4.49025069637883,
"grad_norm": 0.0218505859375,
"learning_rate": 2.7647058823529416e-05,
"loss": 0.24309628009796141,
"step": 305
},
{
"epoch": 4.564531104921077,
"grad_norm": 0.03369140625,
"learning_rate": 2.727941176470588e-05,
"loss": 0.2588023662567139,
"step": 310
},
{
"epoch": 4.638811513463324,
"grad_norm": 0.031494140625,
"learning_rate": 2.6911764705882354e-05,
"loss": 0.23660171031951904,
"step": 315
},
{
"epoch": 4.713091922005571,
"grad_norm": 0.0289306640625,
"learning_rate": 2.6544117647058825e-05,
"loss": 0.2682183265686035,
"step": 320
},
{
"epoch": 4.787372330547818,
"grad_norm": 0.0284423828125,
"learning_rate": 2.6176470588235295e-05,
"loss": 0.2554553270339966,
"step": 325
},
{
"epoch": 4.861652739090065,
"grad_norm": 0.0223388671875,
"learning_rate": 2.580882352941177e-05,
"loss": 0.24070463180541993,
"step": 330
},
{
"epoch": 4.935933147632312,
"grad_norm": 0.0252685546875,
"learning_rate": 2.5441176470588236e-05,
"loss": 0.26400344371795653,
"step": 335
},
{
"epoch": 5.0,
"grad_norm": 0.047119140625,
"learning_rate": 2.5073529411764707e-05,
"loss": 0.24686508178710936,
"step": 340
},
{
"epoch": 5.074280408542247,
"grad_norm": 0.0308837890625,
"learning_rate": 2.4705882352941178e-05,
"loss": 0.21166512966156006,
"step": 345
},
{
"epoch": 5.148560817084494,
"grad_norm": 0.0281982421875,
"learning_rate": 2.433823529411765e-05,
"loss": 0.17841538190841674,
"step": 350
},
{
"epoch": 5.222841225626741,
"grad_norm": 0.05029296875,
"learning_rate": 2.397058823529412e-05,
"loss": 0.19187978506088257,
"step": 355
},
{
"epoch": 5.297121634168988,
"grad_norm": 0.02685546875,
"learning_rate": 2.360294117647059e-05,
"loss": 0.18872741460800171,
"step": 360
},
{
"epoch": 5.371402042711235,
"grad_norm": 0.021728515625,
"learning_rate": 2.323529411764706e-05,
"loss": 0.18178963661193848,
"step": 365
},
{
"epoch": 5.445682451253482,
"grad_norm": 0.0263671875,
"learning_rate": 2.286764705882353e-05,
"loss": 0.16827574968338013,
"step": 370
},
{
"epoch": 5.519962859795729,
"grad_norm": 0.0247802734375,
"learning_rate": 2.25e-05,
"loss": 0.18692827224731445,
"step": 375
},
{
"epoch": 5.5942432683379755,
"grad_norm": 0.02587890625,
"learning_rate": 2.2132352941176472e-05,
"loss": 0.1941287636756897,
"step": 380
},
{
"epoch": 5.6685236768802225,
"grad_norm": 0.017822265625,
"learning_rate": 2.1764705882352943e-05,
"loss": 0.17947893142700194,
"step": 385
},
{
"epoch": 5.74280408542247,
"grad_norm": 0.022216796875,
"learning_rate": 2.1397058823529413e-05,
"loss": 0.1924704432487488,
"step": 390
},
{
"epoch": 5.817084493964717,
"grad_norm": 0.025634765625,
"learning_rate": 2.1029411764705884e-05,
"loss": 0.1785291075706482,
"step": 395
},
{
"epoch": 5.891364902506964,
"grad_norm": 0.023681640625,
"learning_rate": 2.066176470588235e-05,
"loss": 0.17278404235839845,
"step": 400
},
{
"epoch": 5.965645311049211,
"grad_norm": 0.02099609375,
"learning_rate": 2.0294117647058825e-05,
"loss": 0.17876056432724,
"step": 405
},
{
"epoch": 6.029712163416899,
"grad_norm": 0.020751953125,
"learning_rate": 1.9926470588235296e-05,
"loss": 0.17755091190338135,
"step": 410
},
{
"epoch": 6.103992571959146,
"grad_norm": 0.0211181640625,
"learning_rate": 1.9558823529411766e-05,
"loss": 0.1487801194190979,
"step": 415
},
{
"epoch": 6.178272980501393,
"grad_norm": 0.0284423828125,
"learning_rate": 1.9191176470588237e-05,
"loss": 0.12222347259521485,
"step": 420
},
{
"epoch": 6.25255338904364,
"grad_norm": 0.02099609375,
"learning_rate": 1.8823529411764708e-05,
"loss": 0.12180306911468505,
"step": 425
},
{
"epoch": 6.326833797585887,
"grad_norm": 0.028076171875,
"learning_rate": 1.8455882352941178e-05,
"loss": 0.14487186670303345,
"step": 430
},
{
"epoch": 6.401114206128134,
"grad_norm": 0.0228271484375,
"learning_rate": 1.808823529411765e-05,
"loss": 0.14980677366256714,
"step": 435
},
{
"epoch": 6.475394614670381,
"grad_norm": 0.0272216796875,
"learning_rate": 1.772058823529412e-05,
"loss": 0.14352109432220458,
"step": 440
},
{
"epoch": 6.549675023212628,
"grad_norm": 0.027587890625,
"learning_rate": 1.735294117647059e-05,
"loss": 0.13605911731719972,
"step": 445
},
{
"epoch": 6.623955431754875,
"grad_norm": 0.020751953125,
"learning_rate": 1.698529411764706e-05,
"loss": 0.1634863495826721,
"step": 450
},
{
"epoch": 6.698235840297121,
"grad_norm": 0.024658203125,
"learning_rate": 1.6617647058823528e-05,
"loss": 0.14141926765441895,
"step": 455
},
{
"epoch": 6.772516248839368,
"grad_norm": 0.026123046875,
"learning_rate": 1.6250000000000002e-05,
"loss": 0.14137257337570192,
"step": 460
},
{
"epoch": 6.846796657381615,
"grad_norm": 0.0186767578125,
"learning_rate": 1.588235294117647e-05,
"loss": 0.11963517665863037,
"step": 465
},
{
"epoch": 6.921077065923862,
"grad_norm": 0.0216064453125,
"learning_rate": 1.5514705882352943e-05,
"loss": 0.1356942892074585,
"step": 470
},
{
"epoch": 6.995357474466109,
"grad_norm": 0.01708984375,
"learning_rate": 1.5147058823529412e-05,
"loss": 0.12711585760116578,
"step": 475
},
{
"epoch": 7.059424326833797,
"grad_norm": 0.0159912109375,
"learning_rate": 1.4779411764705883e-05,
"loss": 0.10833323001861572,
"step": 480
},
{
"epoch": 7.133704735376044,
"grad_norm": 0.0167236328125,
"learning_rate": 1.4411764705882352e-05,
"loss": 0.12604920864105223,
"step": 485
},
{
"epoch": 7.207985143918291,
"grad_norm": 0.018798828125,
"learning_rate": 1.4044117647058824e-05,
"loss": 0.10249454975128174,
"step": 490
},
{
"epoch": 7.282265552460538,
"grad_norm": 0.0166015625,
"learning_rate": 1.3676470588235296e-05,
"loss": 0.11613593101501465,
"step": 495
},
{
"epoch": 7.3565459610027855,
"grad_norm": 0.0245361328125,
"learning_rate": 1.3308823529411765e-05,
"loss": 0.13158254623413085,
"step": 500
},
{
"epoch": 7.4308263695450325,
"grad_norm": 0.02294921875,
"learning_rate": 1.2941176470588238e-05,
"loss": 0.10998619794845581,
"step": 505
},
{
"epoch": 7.5051067780872796,
"grad_norm": 0.0203857421875,
"learning_rate": 1.2573529411764706e-05,
"loss": 0.10489879846572876,
"step": 510
},
{
"epoch": 7.579387186629527,
"grad_norm": 0.0159912109375,
"learning_rate": 1.2205882352941177e-05,
"loss": 0.1057117223739624,
"step": 515
},
{
"epoch": 7.653667595171774,
"grad_norm": 0.0274658203125,
"learning_rate": 1.1838235294117648e-05,
"loss": 0.12168807983398437,
"step": 520
},
{
"epoch": 7.727948003714021,
"grad_norm": 0.017578125,
"learning_rate": 1.1470588235294118e-05,
"loss": 0.10375174283981323,
"step": 525
},
{
"epoch": 7.802228412256268,
"grad_norm": 0.0162353515625,
"learning_rate": 1.1102941176470589e-05,
"loss": 0.10978785753250123,
"step": 530
},
{
"epoch": 7.876508820798515,
"grad_norm": 0.0211181640625,
"learning_rate": 1.0735294117647058e-05,
"loss": 0.12140828371047974,
"step": 535
},
{
"epoch": 7.950789229340762,
"grad_norm": 0.0177001953125,
"learning_rate": 1.036764705882353e-05,
"loss": 0.11465342044830322,
"step": 540
},
{
"epoch": 8.01485608170845,
"grad_norm": 0.01806640625,
"learning_rate": 1e-05,
"loss": 0.13681257963180543,
"step": 545
},
{
"epoch": 8.089136490250697,
"grad_norm": 0.0140380859375,
"learning_rate": 9.632352941176471e-06,
"loss": 0.09307116866111756,
"step": 550
},
{
"epoch": 8.163416898792944,
"grad_norm": 0.0126953125,
"learning_rate": 9.264705882352942e-06,
"loss": 0.10220249891281127,
"step": 555
},
{
"epoch": 8.237697307335191,
"grad_norm": 0.01556396484375,
"learning_rate": 8.897058823529413e-06,
"loss": 0.10676058530807495,
"step": 560
},
{
"epoch": 8.311977715877438,
"grad_norm": 0.01470947265625,
"learning_rate": 8.529411764705883e-06,
"loss": 0.10347579717636109,
"step": 565
},
{
"epoch": 8.386258124419685,
"grad_norm": 0.0159912109375,
"learning_rate": 8.161764705882354e-06,
"loss": 0.1033887505531311,
"step": 570
},
{
"epoch": 8.460538532961932,
"grad_norm": 0.0166015625,
"learning_rate": 7.794117647058825e-06,
"loss": 0.10061744451522828,
"step": 575
},
{
"epoch": 8.534818941504179,
"grad_norm": 0.0152587890625,
"learning_rate": 7.426470588235294e-06,
"loss": 0.10932677984237671,
"step": 580
},
{
"epoch": 8.609099350046424,
"grad_norm": 0.017822265625,
"learning_rate": 7.058823529411765e-06,
"loss": 0.12288035154342651,
"step": 585
},
{
"epoch": 8.683379758588671,
"grad_norm": 0.01806640625,
"learning_rate": 6.6911764705882356e-06,
"loss": 0.10533527135849,
"step": 590
},
{
"epoch": 8.757660167130918,
"grad_norm": 0.01708984375,
"learning_rate": 6.323529411764706e-06,
"loss": 0.10011863708496094,
"step": 595
},
{
"epoch": 8.831940575673165,
"grad_norm": 0.019287109375,
"learning_rate": 5.955882352941177e-06,
"loss": 0.09496849179267883,
"step": 600
},
{
"epoch": 8.906220984215413,
"grad_norm": 0.026123046875,
"learning_rate": 5.588235294117647e-06,
"loss": 0.10275882482528687,
"step": 605
},
{
"epoch": 8.98050139275766,
"grad_norm": 0.015625,
"learning_rate": 5.220588235294118e-06,
"loss": 0.09559512734413148,
"step": 610
}
],
"logging_steps": 5,
"max_steps": 680,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.5742192562271683e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}