vitaleantonio's picture
Upload checkpoint DeepSeek-Coder-CONTROL-LEETCODE-1.3B-Base-9 at epoch 9
438a00c verified
Raw
History Blame Contribute Delete
22.5 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": 0.07421150278293136,
"grad_norm": 0.08251953125,
"learning_rate": 4.970588235294118e-05,
"loss": 0.7136603355407715,
"step": 5
},
{
"epoch": 0.14842300556586271,
"grad_norm": 0.07861328125,
"learning_rate": 4.933823529411765e-05,
"loss": 0.6834848880767822,
"step": 10
},
{
"epoch": 0.22263450834879406,
"grad_norm": 0.0830078125,
"learning_rate": 4.897058823529412e-05,
"loss": 0.707883644104004,
"step": 15
},
{
"epoch": 0.29684601113172543,
"grad_norm": 0.0859375,
"learning_rate": 4.860294117647059e-05,
"loss": 0.6775740623474121,
"step": 20
},
{
"epoch": 0.37105751391465674,
"grad_norm": 0.091796875,
"learning_rate": 4.823529411764706e-05,
"loss": 0.776744794845581,
"step": 25
},
{
"epoch": 0.4452690166975881,
"grad_norm": 0.0849609375,
"learning_rate": 4.7867647058823535e-05,
"loss": 0.728224515914917,
"step": 30
},
{
"epoch": 0.5194805194805194,
"grad_norm": 0.06884765625,
"learning_rate": 4.75e-05,
"loss": 0.6960197925567627,
"step": 35
},
{
"epoch": 0.5936920222634509,
"grad_norm": 0.08447265625,
"learning_rate": 4.713235294117647e-05,
"loss": 0.6611286163330078,
"step": 40
},
{
"epoch": 0.6679035250463822,
"grad_norm": 0.07666015625,
"learning_rate": 4.6764705882352944e-05,
"loss": 0.6967206954956054,
"step": 45
},
{
"epoch": 0.7421150278293135,
"grad_norm": 0.07470703125,
"learning_rate": 4.639705882352942e-05,
"loss": 0.6535059452056885,
"step": 50
},
{
"epoch": 0.8163265306122449,
"grad_norm": 0.0830078125,
"learning_rate": 4.6029411764705885e-05,
"loss": 0.70545973777771,
"step": 55
},
{
"epoch": 0.8905380333951762,
"grad_norm": 0.08740234375,
"learning_rate": 4.566176470588235e-05,
"loss": 0.6584103107452393,
"step": 60
},
{
"epoch": 0.9647495361781077,
"grad_norm": 0.0693359375,
"learning_rate": 4.5294117647058826e-05,
"loss": 0.6759594917297364,
"step": 65
},
{
"epoch": 1.0296846011131726,
"grad_norm": 0.0693359375,
"learning_rate": 4.49264705882353e-05,
"loss": 0.6613986492156982,
"step": 70
},
{
"epoch": 1.103896103896104,
"grad_norm": 0.061767578125,
"learning_rate": 4.455882352941177e-05,
"loss": 0.6283697128295899,
"step": 75
},
{
"epoch": 1.1781076066790352,
"grad_norm": 0.0751953125,
"learning_rate": 4.4191176470588235e-05,
"loss": 0.5669743061065674,
"step": 80
},
{
"epoch": 1.2523191094619666,
"grad_norm": 0.08544921875,
"learning_rate": 4.382352941176471e-05,
"loss": 0.5851097583770752,
"step": 85
},
{
"epoch": 1.3265306122448979,
"grad_norm": 0.076171875,
"learning_rate": 4.345588235294118e-05,
"loss": 0.59378023147583,
"step": 90
},
{
"epoch": 1.4007421150278292,
"grad_norm": 0.07080078125,
"learning_rate": 4.308823529411765e-05,
"loss": 0.561594820022583,
"step": 95
},
{
"epoch": 1.4749536178107607,
"grad_norm": 0.08447265625,
"learning_rate": 4.272058823529412e-05,
"loss": 0.5819839477539063,
"step": 100
},
{
"epoch": 1.549165120593692,
"grad_norm": 0.08056640625,
"learning_rate": 4.235294117647059e-05,
"loss": 0.5523958206176758,
"step": 105
},
{
"epoch": 1.6233766233766234,
"grad_norm": 0.06591796875,
"learning_rate": 4.198529411764706e-05,
"loss": 0.5537418365478516,
"step": 110
},
{
"epoch": 1.6975881261595547,
"grad_norm": 0.07470703125,
"learning_rate": 4.161764705882353e-05,
"loss": 0.551865530014038,
"step": 115
},
{
"epoch": 1.7717996289424862,
"grad_norm": 0.0703125,
"learning_rate": 4.125e-05,
"loss": 0.602507495880127,
"step": 120
},
{
"epoch": 1.8460111317254175,
"grad_norm": 0.0830078125,
"learning_rate": 4.0882352941176474e-05,
"loss": 0.5978893280029297,
"step": 125
},
{
"epoch": 1.9202226345083488,
"grad_norm": 0.08154296875,
"learning_rate": 4.051470588235294e-05,
"loss": 0.625958776473999,
"step": 130
},
{
"epoch": 1.9944341372912802,
"grad_norm": 0.0703125,
"learning_rate": 4.0147058823529415e-05,
"loss": 0.553464412689209,
"step": 135
},
{
"epoch": 2.0593692022263452,
"grad_norm": 0.07568359375,
"learning_rate": 3.977941176470588e-05,
"loss": 0.5257774353027344,
"step": 140
},
{
"epoch": 2.1335807050092765,
"grad_norm": 0.07666015625,
"learning_rate": 3.9411764705882356e-05,
"loss": 0.5616061687469482,
"step": 145
},
{
"epoch": 2.207792207792208,
"grad_norm": 0.08447265625,
"learning_rate": 3.9044117647058823e-05,
"loss": 0.486341667175293,
"step": 150
},
{
"epoch": 2.282003710575139,
"grad_norm": 0.0830078125,
"learning_rate": 3.86764705882353e-05,
"loss": 0.4711045265197754,
"step": 155
},
{
"epoch": 2.3562152133580705,
"grad_norm": 0.091796875,
"learning_rate": 3.830882352941177e-05,
"loss": 0.47898192405700685,
"step": 160
},
{
"epoch": 2.430426716141002,
"grad_norm": 0.07861328125,
"learning_rate": 3.794117647058824e-05,
"loss": 0.49690723419189453,
"step": 165
},
{
"epoch": 2.504638218923933,
"grad_norm": 0.08544921875,
"learning_rate": 3.7573529411764706e-05,
"loss": 0.5519385814666748,
"step": 170
},
{
"epoch": 2.5788497217068644,
"grad_norm": 0.08642578125,
"learning_rate": 3.720588235294118e-05,
"loss": 0.5011870384216308,
"step": 175
},
{
"epoch": 2.6530612244897958,
"grad_norm": 0.0908203125,
"learning_rate": 3.6838235294117654e-05,
"loss": 0.5261661052703858,
"step": 180
},
{
"epoch": 2.7272727272727275,
"grad_norm": 0.07373046875,
"learning_rate": 3.6470588235294114e-05,
"loss": 0.49692234992980955,
"step": 185
},
{
"epoch": 2.8014842300556584,
"grad_norm": 0.0859375,
"learning_rate": 3.610294117647059e-05,
"loss": 0.48595056533813474,
"step": 190
},
{
"epoch": 2.87569573283859,
"grad_norm": 0.07177734375,
"learning_rate": 3.573529411764706e-05,
"loss": 0.46908016204833985,
"step": 195
},
{
"epoch": 2.9499072356215215,
"grad_norm": 0.0947265625,
"learning_rate": 3.5367647058823536e-05,
"loss": 0.5229842662811279,
"step": 200
},
{
"epoch": 3.014842300556586,
"grad_norm": 0.078125,
"learning_rate": 3.5e-05,
"loss": 0.4329693794250488,
"step": 205
},
{
"epoch": 3.0890538033395174,
"grad_norm": 0.103515625,
"learning_rate": 3.463235294117647e-05,
"loss": 0.4026463508605957,
"step": 210
},
{
"epoch": 3.163265306122449,
"grad_norm": 0.1416015625,
"learning_rate": 3.4264705882352945e-05,
"loss": 0.46060619354248045,
"step": 215
},
{
"epoch": 3.2374768089053805,
"grad_norm": 0.078125,
"learning_rate": 3.389705882352941e-05,
"loss": 0.3920208215713501,
"step": 220
},
{
"epoch": 3.311688311688312,
"grad_norm": 0.08447265625,
"learning_rate": 3.352941176470588e-05,
"loss": 0.4302512645721436,
"step": 225
},
{
"epoch": 3.385899814471243,
"grad_norm": 0.10546875,
"learning_rate": 3.3161764705882353e-05,
"loss": 0.39400439262390136,
"step": 230
},
{
"epoch": 3.4601113172541744,
"grad_norm": 0.0986328125,
"learning_rate": 3.279411764705883e-05,
"loss": 0.4221585750579834,
"step": 235
},
{
"epoch": 3.5343228200371057,
"grad_norm": 0.09423828125,
"learning_rate": 3.2426470588235295e-05,
"loss": 0.4395571231842041,
"step": 240
},
{
"epoch": 3.608534322820037,
"grad_norm": 0.08349609375,
"learning_rate": 3.205882352941177e-05,
"loss": 0.4064159393310547,
"step": 245
},
{
"epoch": 3.6827458256029684,
"grad_norm": 0.1025390625,
"learning_rate": 3.1691176470588236e-05,
"loss": 0.4206245899200439,
"step": 250
},
{
"epoch": 3.7569573283858997,
"grad_norm": 0.10400390625,
"learning_rate": 3.132352941176471e-05,
"loss": 0.4488075733184814,
"step": 255
},
{
"epoch": 3.8311688311688314,
"grad_norm": 0.09375,
"learning_rate": 3.095588235294118e-05,
"loss": 0.403182315826416,
"step": 260
},
{
"epoch": 3.9053803339517623,
"grad_norm": 0.08984375,
"learning_rate": 3.058823529411765e-05,
"loss": 0.3942938566207886,
"step": 265
},
{
"epoch": 3.979591836734694,
"grad_norm": 0.11083984375,
"learning_rate": 3.022058823529412e-05,
"loss": 0.434019660949707,
"step": 270
},
{
"epoch": 4.044526901669759,
"grad_norm": 0.09765625,
"learning_rate": 2.985294117647059e-05,
"loss": 0.39630928039550783,
"step": 275
},
{
"epoch": 4.1187384044526905,
"grad_norm": 0.1611328125,
"learning_rate": 2.948529411764706e-05,
"loss": 0.358514404296875,
"step": 280
},
{
"epoch": 4.192949907235621,
"grad_norm": 0.10107421875,
"learning_rate": 2.9117647058823534e-05,
"loss": 0.30582895278930666,
"step": 285
},
{
"epoch": 4.267161410018553,
"grad_norm": 0.09521484375,
"learning_rate": 2.8749999999999997e-05,
"loss": 0.3471459627151489,
"step": 290
},
{
"epoch": 4.341372912801484,
"grad_norm": 0.1171875,
"learning_rate": 2.838235294117647e-05,
"loss": 0.33401808738708494,
"step": 295
},
{
"epoch": 4.415584415584416,
"grad_norm": 0.11328125,
"learning_rate": 2.8014705882352942e-05,
"loss": 0.3511670589447021,
"step": 300
},
{
"epoch": 4.489795918367347,
"grad_norm": 0.11865234375,
"learning_rate": 2.7647058823529416e-05,
"loss": 0.3425841093063354,
"step": 305
},
{
"epoch": 4.564007421150278,
"grad_norm": 0.1240234375,
"learning_rate": 2.727941176470588e-05,
"loss": 0.3504085302352905,
"step": 310
},
{
"epoch": 4.638218923933209,
"grad_norm": 0.10400390625,
"learning_rate": 2.6911764705882354e-05,
"loss": 0.32737371921539304,
"step": 315
},
{
"epoch": 4.712430426716141,
"grad_norm": 0.11376953125,
"learning_rate": 2.6544117647058825e-05,
"loss": 0.3573514699935913,
"step": 320
},
{
"epoch": 4.786641929499073,
"grad_norm": 0.11962890625,
"learning_rate": 2.6176470588235295e-05,
"loss": 0.35710322856903076,
"step": 325
},
{
"epoch": 4.860853432282004,
"grad_norm": 0.1103515625,
"learning_rate": 2.580882352941177e-05,
"loss": 0.35215983390808103,
"step": 330
},
{
"epoch": 4.935064935064935,
"grad_norm": 0.11865234375,
"learning_rate": 2.5441176470588236e-05,
"loss": 0.3538684844970703,
"step": 335
},
{
"epoch": 5.0,
"grad_norm": 0.244140625,
"learning_rate": 2.5073529411764707e-05,
"loss": 0.3404927015304565,
"step": 340
},
{
"epoch": 5.074211502782932,
"grad_norm": 0.1318359375,
"learning_rate": 2.4705882352941178e-05,
"loss": 0.3135892152786255,
"step": 345
},
{
"epoch": 5.148423005565863,
"grad_norm": 0.142578125,
"learning_rate": 2.433823529411765e-05,
"loss": 0.2727874994277954,
"step": 350
},
{
"epoch": 5.222634508348794,
"grad_norm": 0.1064453125,
"learning_rate": 2.397058823529412e-05,
"loss": 0.2944751262664795,
"step": 355
},
{
"epoch": 5.296846011131725,
"grad_norm": 0.1318359375,
"learning_rate": 2.360294117647059e-05,
"loss": 0.2924535036087036,
"step": 360
},
{
"epoch": 5.371057513914657,
"grad_norm": 0.1220703125,
"learning_rate": 2.323529411764706e-05,
"loss": 0.2774681568145752,
"step": 365
},
{
"epoch": 5.445269016697588,
"grad_norm": 0.1591796875,
"learning_rate": 2.286764705882353e-05,
"loss": 0.2758533239364624,
"step": 370
},
{
"epoch": 5.51948051948052,
"grad_norm": 0.11328125,
"learning_rate": 2.25e-05,
"loss": 0.28443448543548583,
"step": 375
},
{
"epoch": 5.5936920222634505,
"grad_norm": 0.12109375,
"learning_rate": 2.2132352941176472e-05,
"loss": 0.29056899547576903,
"step": 380
},
{
"epoch": 5.667903525046382,
"grad_norm": 0.1328125,
"learning_rate": 2.1764705882352943e-05,
"loss": 0.2798746585845947,
"step": 385
},
{
"epoch": 5.742115027829313,
"grad_norm": 0.11083984375,
"learning_rate": 2.1397058823529413e-05,
"loss": 0.2820063591003418,
"step": 390
},
{
"epoch": 5.816326530612245,
"grad_norm": 0.1279296875,
"learning_rate": 2.1029411764705884e-05,
"loss": 0.2856459379196167,
"step": 395
},
{
"epoch": 5.890538033395176,
"grad_norm": 0.10986328125,
"learning_rate": 2.066176470588235e-05,
"loss": 0.2717560291290283,
"step": 400
},
{
"epoch": 5.9647495361781075,
"grad_norm": 0.11474609375,
"learning_rate": 2.0294117647058825e-05,
"loss": 0.2703937292098999,
"step": 405
},
{
"epoch": 6.029684601113172,
"grad_norm": 0.11181640625,
"learning_rate": 1.9926470588235296e-05,
"loss": 0.2820188045501709,
"step": 410
},
{
"epoch": 6.103896103896104,
"grad_norm": 0.11474609375,
"learning_rate": 1.9558823529411766e-05,
"loss": 0.2424381732940674,
"step": 415
},
{
"epoch": 6.178107606679035,
"grad_norm": 0.142578125,
"learning_rate": 1.9191176470588237e-05,
"loss": 0.2197338104248047,
"step": 420
},
{
"epoch": 6.252319109461967,
"grad_norm": 0.11181640625,
"learning_rate": 1.8823529411764708e-05,
"loss": 0.2251077651977539,
"step": 425
},
{
"epoch": 6.326530612244898,
"grad_norm": 0.12890625,
"learning_rate": 1.8455882352941178e-05,
"loss": 0.23930027484893798,
"step": 430
},
{
"epoch": 6.400742115027829,
"grad_norm": 0.119140625,
"learning_rate": 1.808823529411765e-05,
"loss": 0.23911054134368898,
"step": 435
},
{
"epoch": 6.474953617810761,
"grad_norm": 0.12255859375,
"learning_rate": 1.772058823529412e-05,
"loss": 0.2539715051651001,
"step": 440
},
{
"epoch": 6.549165120593692,
"grad_norm": 0.1455078125,
"learning_rate": 1.735294117647059e-05,
"loss": 0.23563437461853026,
"step": 445
},
{
"epoch": 6.623376623376624,
"grad_norm": 0.1318359375,
"learning_rate": 1.698529411764706e-05,
"loss": 0.26609752178192136,
"step": 450
},
{
"epoch": 6.6975881261595545,
"grad_norm": 0.1474609375,
"learning_rate": 1.6617647058823528e-05,
"loss": 0.24501259326934816,
"step": 455
},
{
"epoch": 6.771799628942486,
"grad_norm": 0.1552734375,
"learning_rate": 1.6250000000000002e-05,
"loss": 0.2446495532989502,
"step": 460
},
{
"epoch": 6.846011131725417,
"grad_norm": 0.10986328125,
"learning_rate": 1.588235294117647e-05,
"loss": 0.21488475799560547,
"step": 465
},
{
"epoch": 6.920222634508349,
"grad_norm": 0.12109375,
"learning_rate": 1.5514705882352943e-05,
"loss": 0.2299583911895752,
"step": 470
},
{
"epoch": 6.994434137291281,
"grad_norm": 0.0888671875,
"learning_rate": 1.5147058823529412e-05,
"loss": 0.22204258441925048,
"step": 475
},
{
"epoch": 7.059369202226345,
"grad_norm": 0.10986328125,
"learning_rate": 1.4779411764705883e-05,
"loss": 0.1963812828063965,
"step": 480
},
{
"epoch": 7.133580705009276,
"grad_norm": 0.11083984375,
"learning_rate": 1.4411764705882352e-05,
"loss": 0.22501554489135742,
"step": 485
},
{
"epoch": 7.207792207792208,
"grad_norm": 0.1416015625,
"learning_rate": 1.4044117647058824e-05,
"loss": 0.19327964782714843,
"step": 490
},
{
"epoch": 7.282003710575139,
"grad_norm": 0.1005859375,
"learning_rate": 1.3676470588235296e-05,
"loss": 0.21416759490966797,
"step": 495
},
{
"epoch": 7.3562152133580705,
"grad_norm": 0.126953125,
"learning_rate": 1.3308823529411765e-05,
"loss": 0.2346568822860718,
"step": 500
},
{
"epoch": 7.430426716141002,
"grad_norm": 0.236328125,
"learning_rate": 1.2941176470588238e-05,
"loss": 0.20478355884552002,
"step": 505
},
{
"epoch": 7.504638218923933,
"grad_norm": 0.123046875,
"learning_rate": 1.2573529411764706e-05,
"loss": 0.19913241863250733,
"step": 510
},
{
"epoch": 7.578849721706865,
"grad_norm": 0.1005859375,
"learning_rate": 1.2205882352941177e-05,
"loss": 0.20022623538970946,
"step": 515
},
{
"epoch": 7.653061224489796,
"grad_norm": 0.115234375,
"learning_rate": 1.1838235294117648e-05,
"loss": 0.21551852226257323,
"step": 520
},
{
"epoch": 7.7272727272727275,
"grad_norm": 0.1083984375,
"learning_rate": 1.1470588235294118e-05,
"loss": 0.19650646448135375,
"step": 525
},
{
"epoch": 7.801484230055658,
"grad_norm": 0.11572265625,
"learning_rate": 1.1102941176470589e-05,
"loss": 0.20335066318511963,
"step": 530
},
{
"epoch": 7.87569573283859,
"grad_norm": 0.11328125,
"learning_rate": 1.0735294117647058e-05,
"loss": 0.21862897872924805,
"step": 535
},
{
"epoch": 7.949907235621521,
"grad_norm": 0.10595703125,
"learning_rate": 1.036764705882353e-05,
"loss": 0.2059312343597412,
"step": 540
},
{
"epoch": 8.014842300556586,
"grad_norm": 0.1142578125,
"learning_rate": 1e-05,
"loss": 0.2448486328125,
"step": 545
},
{
"epoch": 8.089053803339517,
"grad_norm": 0.296875,
"learning_rate": 9.632352941176471e-06,
"loss": 0.18099163770675658,
"step": 550
},
{
"epoch": 8.16326530612245,
"grad_norm": 0.08837890625,
"learning_rate": 9.264705882352942e-06,
"loss": 0.19377894401550294,
"step": 555
},
{
"epoch": 8.237476808905381,
"grad_norm": 0.1083984375,
"learning_rate": 8.897058823529413e-06,
"loss": 0.19930765628814698,
"step": 560
},
{
"epoch": 8.311688311688311,
"grad_norm": 0.091796875,
"learning_rate": 8.529411764705883e-06,
"loss": 0.18337740898132324,
"step": 565
},
{
"epoch": 8.385899814471243,
"grad_norm": 0.10205078125,
"learning_rate": 8.161764705882354e-06,
"loss": 0.19968538284301757,
"step": 570
},
{
"epoch": 8.460111317254174,
"grad_norm": 0.11328125,
"learning_rate": 7.794117647058825e-06,
"loss": 0.19343130588531493,
"step": 575
},
{
"epoch": 8.534322820037106,
"grad_norm": 0.103515625,
"learning_rate": 7.426470588235294e-06,
"loss": 0.20264458656311035,
"step": 580
},
{
"epoch": 8.608534322820038,
"grad_norm": 0.11865234375,
"learning_rate": 7.058823529411765e-06,
"loss": 0.2226201057434082,
"step": 585
},
{
"epoch": 8.682745825602968,
"grad_norm": 0.1142578125,
"learning_rate": 6.6911764705882356e-06,
"loss": 0.20946204662322998,
"step": 590
},
{
"epoch": 8.7569573283859,
"grad_norm": 0.115234375,
"learning_rate": 6.323529411764706e-06,
"loss": 0.1859149932861328,
"step": 595
},
{
"epoch": 8.831168831168831,
"grad_norm": 0.1220703125,
"learning_rate": 5.955882352941177e-06,
"loss": 0.18132244348526,
"step": 600
},
{
"epoch": 8.905380333951763,
"grad_norm": 0.125,
"learning_rate": 5.588235294117647e-06,
"loss": 0.19473851919174195,
"step": 605
},
{
"epoch": 8.979591836734693,
"grad_norm": 0.09765625,
"learning_rate": 5.220588235294118e-06,
"loss": 0.18387948274612426,
"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": 3.0501347583747686e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}