autoprogrammer's picture
Upload sdar_1.7b_trace_sft_math-checkpoint-716
01be64e verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 716,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006985679357317499,
"grad_norm": 9.417793273925781,
"learning_rate": 6.153846153846155e-07,
"loss": 0.4856,
"step": 5
},
{
"epoch": 0.013971358714634998,
"grad_norm": 7.6536865234375,
"learning_rate": 1.3846153846153848e-06,
"loss": 0.4457,
"step": 10
},
{
"epoch": 0.020957038071952497,
"grad_norm": 6.9425950050354,
"learning_rate": 2.153846153846154e-06,
"loss": 0.4359,
"step": 15
},
{
"epoch": 0.027942717429269997,
"grad_norm": 7.008752822875977,
"learning_rate": 2.9230769230769236e-06,
"loss": 0.4247,
"step": 20
},
{
"epoch": 0.0349283967865875,
"grad_norm": 7.943561553955078,
"learning_rate": 3.692307692307693e-06,
"loss": 0.4144,
"step": 25
},
{
"epoch": 0.041914076143904994,
"grad_norm": 8.960087776184082,
"learning_rate": 4.461538461538462e-06,
"loss": 0.4095,
"step": 30
},
{
"epoch": 0.0488997555012225,
"grad_norm": 9.126522064208984,
"learning_rate": 5.230769230769232e-06,
"loss": 0.4195,
"step": 35
},
{
"epoch": 0.055885434858539994,
"grad_norm": 6.81967306137085,
"learning_rate": 6e-06,
"loss": 0.409,
"step": 40
},
{
"epoch": 0.06287111421585749,
"grad_norm": 9.193132400512695,
"learning_rate": 6.76923076923077e-06,
"loss": 0.4256,
"step": 45
},
{
"epoch": 0.069856793573175,
"grad_norm": 7.224976062774658,
"learning_rate": 7.538461538461539e-06,
"loss": 0.41,
"step": 50
},
{
"epoch": 0.07684247293049248,
"grad_norm": 7.260319232940674,
"learning_rate": 8.307692307692309e-06,
"loss": 0.4534,
"step": 55
},
{
"epoch": 0.08382815228780999,
"grad_norm": 8.081445693969727,
"learning_rate": 9.076923076923078e-06,
"loss": 0.4435,
"step": 60
},
{
"epoch": 0.09081383164512749,
"grad_norm": 8.150150299072266,
"learning_rate": 9.846153846153848e-06,
"loss": 0.4457,
"step": 65
},
{
"epoch": 0.097799511002445,
"grad_norm": 6.927804946899414,
"learning_rate": 9.999909012888162e-06,
"loss": 0.4559,
"step": 70
},
{
"epoch": 0.10478519035976248,
"grad_norm": 7.140408039093018,
"learning_rate": 9.999539383421715e-06,
"loss": 0.4217,
"step": 75
},
{
"epoch": 0.11177086971707999,
"grad_norm": 7.418540000915527,
"learning_rate": 9.998885445909666e-06,
"loss": 0.4857,
"step": 80
},
{
"epoch": 0.11875654907439749,
"grad_norm": 8.253525733947754,
"learning_rate": 9.997947237539373e-06,
"loss": 0.4863,
"step": 85
},
{
"epoch": 0.12574222843171498,
"grad_norm": 6.550653457641602,
"learning_rate": 9.996724811663797e-06,
"loss": 0.4663,
"step": 90
},
{
"epoch": 0.13272790778903248,
"grad_norm": 6.81130313873291,
"learning_rate": 9.99521823779844e-06,
"loss": 0.4684,
"step": 95
},
{
"epoch": 0.13971358714635,
"grad_norm": 7.913576602935791,
"learning_rate": 9.99342760161741e-06,
"loss": 0.5049,
"step": 100
},
{
"epoch": 0.1466992665036675,
"grad_norm": 8.523401260375977,
"learning_rate": 9.991353004948538e-06,
"loss": 0.4635,
"step": 105
},
{
"epoch": 0.15368494586098497,
"grad_norm": 6.084781169891357,
"learning_rate": 9.988994565767604e-06,
"loss": 0.4752,
"step": 110
},
{
"epoch": 0.16067062521830247,
"grad_norm": 5.975230693817139,
"learning_rate": 9.986352418191608e-06,
"loss": 0.4722,
"step": 115
},
{
"epoch": 0.16765630457561997,
"grad_norm": 6.941432476043701,
"learning_rate": 9.983426712471151e-06,
"loss": 0.4991,
"step": 120
},
{
"epoch": 0.17464198393293748,
"grad_norm": 6.190479755401611,
"learning_rate": 9.9802176149819e-06,
"loss": 0.4821,
"step": 125
},
{
"epoch": 0.18162766329025498,
"grad_norm": 6.3899006843566895,
"learning_rate": 9.976725308215109e-06,
"loss": 0.5163,
"step": 130
},
{
"epoch": 0.18861334264757249,
"grad_norm": 5.7873430252075195,
"learning_rate": 9.97294999076726e-06,
"loss": 0.4517,
"step": 135
},
{
"epoch": 0.19559902200489,
"grad_norm": 6.523060321807861,
"learning_rate": 9.968891877328752e-06,
"loss": 0.4632,
"step": 140
},
{
"epoch": 0.20258470136220746,
"grad_norm": 7.010469436645508,
"learning_rate": 9.964551198671709e-06,
"loss": 0.4643,
"step": 145
},
{
"epoch": 0.20957038071952497,
"grad_norm": 6.9780473709106445,
"learning_rate": 9.95992820163684e-06,
"loss": 0.4737,
"step": 150
},
{
"epoch": 0.21655606007684247,
"grad_norm": 6.335629463195801,
"learning_rate": 9.955023149119413e-06,
"loss": 0.4552,
"step": 155
},
{
"epoch": 0.22354173943415998,
"grad_norm": 5.958488464355469,
"learning_rate": 9.949836320054309e-06,
"loss": 0.4553,
"step": 160
},
{
"epoch": 0.23052741879147748,
"grad_norm": 6.195608139038086,
"learning_rate": 9.944368009400145e-06,
"loss": 0.5117,
"step": 165
},
{
"epoch": 0.23751309814879498,
"grad_norm": 6.441509246826172,
"learning_rate": 9.93861852812251e-06,
"loss": 0.4652,
"step": 170
},
{
"epoch": 0.24449877750611246,
"grad_norm": 5.994947910308838,
"learning_rate": 9.932588203176281e-06,
"loss": 0.4832,
"step": 175
},
{
"epoch": 0.25148445686342996,
"grad_norm": 6.672873020172119,
"learning_rate": 9.92627737748703e-06,
"loss": 0.4827,
"step": 180
},
{
"epoch": 0.2584701362207475,
"grad_norm": 6.571279048919678,
"learning_rate": 9.919686409931523e-06,
"loss": 0.5003,
"step": 185
},
{
"epoch": 0.26545581557806497,
"grad_norm": 6.049185276031494,
"learning_rate": 9.912815675317307e-06,
"loss": 0.4905,
"step": 190
},
{
"epoch": 0.27244149493538244,
"grad_norm": 6.473181247711182,
"learning_rate": 9.905665564361403e-06,
"loss": 0.4843,
"step": 195
},
{
"epoch": 0.2794271742927,
"grad_norm": 7.581283092498779,
"learning_rate": 9.898236483668086e-06,
"loss": 0.5097,
"step": 200
},
{
"epoch": 0.28641285365001745,
"grad_norm": 7.333038806915283,
"learning_rate": 9.890528855705753e-06,
"loss": 0.4698,
"step": 205
},
{
"epoch": 0.293398533007335,
"grad_norm": 6.216223239898682,
"learning_rate": 9.882543118782913e-06,
"loss": 0.5034,
"step": 210
},
{
"epoch": 0.30038421236465246,
"grad_norm": 6.861793041229248,
"learning_rate": 9.874279727023253e-06,
"loss": 0.4756,
"step": 215
},
{
"epoch": 0.30736989172196993,
"grad_norm": 6.37476110458374,
"learning_rate": 9.865739150339815e-06,
"loss": 0.5117,
"step": 220
},
{
"epoch": 0.31435557107928747,
"grad_norm": 5.816511154174805,
"learning_rate": 9.856921874408272e-06,
"loss": 0.4925,
"step": 225
},
{
"epoch": 0.32134125043660494,
"grad_norm": 6.3242692947387695,
"learning_rate": 9.847828400639317e-06,
"loss": 0.4679,
"step": 230
},
{
"epoch": 0.3283269297939225,
"grad_norm": 6.17088508605957,
"learning_rate": 9.838459246150138e-06,
"loss": 0.4646,
"step": 235
},
{
"epoch": 0.33531260915123995,
"grad_norm": 7.1427812576293945,
"learning_rate": 9.828814943735019e-06,
"loss": 0.4633,
"step": 240
},
{
"epoch": 0.3422982885085575,
"grad_norm": 6.307351112365723,
"learning_rate": 9.818896041835036e-06,
"loss": 0.4586,
"step": 245
},
{
"epoch": 0.34928396786587496,
"grad_norm": 6.033569812774658,
"learning_rate": 9.808703104506874e-06,
"loss": 0.5144,
"step": 250
},
{
"epoch": 0.35626964722319243,
"grad_norm": 6.253153324127197,
"learning_rate": 9.798236711390754e-06,
"loss": 0.4936,
"step": 255
},
{
"epoch": 0.36325532658050996,
"grad_norm": 6.369323253631592,
"learning_rate": 9.787497457677456e-06,
"loss": 0.5142,
"step": 260
},
{
"epoch": 0.37024100593782744,
"grad_norm": 7.059694766998291,
"learning_rate": 9.776485954074492e-06,
"loss": 0.508,
"step": 265
},
{
"epoch": 0.37722668529514497,
"grad_norm": 5.437386989593506,
"learning_rate": 9.765202826771358e-06,
"loss": 0.4517,
"step": 270
},
{
"epoch": 0.38421236465246245,
"grad_norm": 6.353536605834961,
"learning_rate": 9.753648717403944e-06,
"loss": 0.5177,
"step": 275
},
{
"epoch": 0.39119804400978,
"grad_norm": 6.7363481521606445,
"learning_rate": 9.741824283018022e-06,
"loss": 0.4768,
"step": 280
},
{
"epoch": 0.39818372336709745,
"grad_norm": 6.804571151733398,
"learning_rate": 9.729730196031908e-06,
"loss": 0.5009,
"step": 285
},
{
"epoch": 0.40516940272441493,
"grad_norm": 6.188082695007324,
"learning_rate": 9.717367144198209e-06,
"loss": 0.4975,
"step": 290
},
{
"epoch": 0.41215508208173246,
"grad_norm": 6.352089881896973,
"learning_rate": 9.704735830564707e-06,
"loss": 0.458,
"step": 295
},
{
"epoch": 0.41914076143904994,
"grad_norm": 5.823917388916016,
"learning_rate": 9.6918369734344e-06,
"loss": 0.4863,
"step": 300
},
{
"epoch": 0.42612644079636747,
"grad_norm": 6.301001071929932,
"learning_rate": 9.678671306324627e-06,
"loss": 0.5175,
"step": 305
},
{
"epoch": 0.43311212015368494,
"grad_norm": 6.185693740844727,
"learning_rate": 9.665239577925384e-06,
"loss": 0.4844,
"step": 310
},
{
"epoch": 0.4400977995110024,
"grad_norm": 6.580015182495117,
"learning_rate": 9.65154255205672e-06,
"loss": 0.4907,
"step": 315
},
{
"epoch": 0.44708347886831995,
"grad_norm": 5.962856769561768,
"learning_rate": 9.637581007625328e-06,
"loss": 0.4552,
"step": 320
},
{
"epoch": 0.4540691582256374,
"grad_norm": 6.2723774909973145,
"learning_rate": 9.623355738580226e-06,
"loss": 0.4994,
"step": 325
},
{
"epoch": 0.46105483758295496,
"grad_norm": 6.140941143035889,
"learning_rate": 9.608867553867628e-06,
"loss": 0.4829,
"step": 330
},
{
"epoch": 0.46804051694027243,
"grad_norm": 6.278982639312744,
"learning_rate": 9.594117277384928e-06,
"loss": 0.5118,
"step": 335
},
{
"epoch": 0.47502619629758996,
"grad_norm": 6.221822261810303,
"learning_rate": 9.579105747933858e-06,
"loss": 0.4903,
"step": 340
},
{
"epoch": 0.48201187565490744,
"grad_norm": 6.153563976287842,
"learning_rate": 9.563833819172777e-06,
"loss": 0.4729,
"step": 345
},
{
"epoch": 0.4889975550122249,
"grad_norm": 5.723773956298828,
"learning_rate": 9.548302359568136e-06,
"loss": 0.536,
"step": 350
},
{
"epoch": 0.49598323436954245,
"grad_norm": 5.7412238121032715,
"learning_rate": 9.532512252345086e-06,
"loss": 0.4818,
"step": 355
},
{
"epoch": 0.5029689137268599,
"grad_norm": 5.776915073394775,
"learning_rate": 9.516464395437251e-06,
"loss": 0.4818,
"step": 360
},
{
"epoch": 0.5099545930841775,
"grad_norm": 6.4714741706848145,
"learning_rate": 9.50015970143567e-06,
"loss": 0.486,
"step": 365
},
{
"epoch": 0.516940272441495,
"grad_norm": 5.570414066314697,
"learning_rate": 9.483599097536895e-06,
"loss": 0.4821,
"step": 370
},
{
"epoch": 0.5239259517988124,
"grad_norm": 5.86240816116333,
"learning_rate": 9.466783525490271e-06,
"loss": 0.5014,
"step": 375
},
{
"epoch": 0.5309116311561299,
"grad_norm": 5.690156936645508,
"learning_rate": 9.449713941544375e-06,
"loss": 0.505,
"step": 380
},
{
"epoch": 0.5378973105134475,
"grad_norm": 5.273125648498535,
"learning_rate": 9.432391316392639e-06,
"loss": 0.4738,
"step": 385
},
{
"epoch": 0.5448829898707649,
"grad_norm": 6.2202887535095215,
"learning_rate": 9.414816635118154e-06,
"loss": 0.5023,
"step": 390
},
{
"epoch": 0.5518686692280824,
"grad_norm": 6.270415782928467,
"learning_rate": 9.396990897137647e-06,
"loss": 0.4772,
"step": 395
},
{
"epoch": 0.5588543485854,
"grad_norm": 5.550614356994629,
"learning_rate": 9.378915116144646e-06,
"loss": 0.4556,
"step": 400
},
{
"epoch": 0.5658400279427175,
"grad_norm": 5.853529930114746,
"learning_rate": 9.360590320051844e-06,
"loss": 0.4942,
"step": 405
},
{
"epoch": 0.5728257073000349,
"grad_norm": 5.692981243133545,
"learning_rate": 9.342017550932627e-06,
"loss": 0.4772,
"step": 410
},
{
"epoch": 0.5798113866573524,
"grad_norm": 5.6134185791015625,
"learning_rate": 9.323197864961835e-06,
"loss": 0.4245,
"step": 415
},
{
"epoch": 0.58679706601467,
"grad_norm": 6.195576190948486,
"learning_rate": 9.304132332355685e-06,
"loss": 0.5083,
"step": 420
},
{
"epoch": 0.5937827453719874,
"grad_norm": 6.21861457824707,
"learning_rate": 9.28482203731092e-06,
"loss": 0.5366,
"step": 425
},
{
"epoch": 0.6007684247293049,
"grad_norm": 5.109756946563721,
"learning_rate": 9.265268077943152e-06,
"loss": 0.4774,
"step": 430
},
{
"epoch": 0.6077541040866224,
"grad_norm": 6.137323379516602,
"learning_rate": 9.245471566224416e-06,
"loss": 0.5125,
"step": 435
},
{
"epoch": 0.6147397834439399,
"grad_norm": 5.771416187286377,
"learning_rate": 9.225433627919927e-06,
"loss": 0.5453,
"step": 440
},
{
"epoch": 0.6217254628012574,
"grad_norm": 5.52296781539917,
"learning_rate": 9.20515540252408e-06,
"loss": 0.4663,
"step": 445
},
{
"epoch": 0.6287111421585749,
"grad_norm": 6.380407333374023,
"learning_rate": 9.184638043195628e-06,
"loss": 0.4752,
"step": 450
},
{
"epoch": 0.6356968215158925,
"grad_norm": 5.940698623657227,
"learning_rate": 9.16388271669213e-06,
"loss": 0.4309,
"step": 455
},
{
"epoch": 0.6426825008732099,
"grad_norm": 6.604904651641846,
"learning_rate": 9.142890603303573e-06,
"loss": 0.5043,
"step": 460
},
{
"epoch": 0.6496681802305274,
"grad_norm": 6.345200061798096,
"learning_rate": 9.121662896785285e-06,
"loss": 0.4991,
"step": 465
},
{
"epoch": 0.656653859587845,
"grad_norm": 5.294460773468018,
"learning_rate": 9.100200804290014e-06,
"loss": 0.4788,
"step": 470
},
{
"epoch": 0.6636395389451624,
"grad_norm": 5.905223846435547,
"learning_rate": 9.078505546299317e-06,
"loss": 0.4871,
"step": 475
},
{
"epoch": 0.6706252183024799,
"grad_norm": 4.967826843261719,
"learning_rate": 9.056578356554124e-06,
"loss": 0.5174,
"step": 480
},
{
"epoch": 0.6776108976597974,
"grad_norm": 5.444486618041992,
"learning_rate": 9.034420481984604e-06,
"loss": 0.4889,
"step": 485
},
{
"epoch": 0.684596577017115,
"grad_norm": 5.278167724609375,
"learning_rate": 9.012033182639238e-06,
"loss": 0.4793,
"step": 490
},
{
"epoch": 0.6915822563744324,
"grad_norm": 6.902711391448975,
"learning_rate": 8.989417731613169e-06,
"loss": 0.5259,
"step": 495
},
{
"epoch": 0.6985679357317499,
"grad_norm": 6.086877346038818,
"learning_rate": 8.966575414975813e-06,
"loss": 0.5203,
"step": 500
},
{
"epoch": 0.7055536150890674,
"grad_norm": 6.7947564125061035,
"learning_rate": 8.943507531697715e-06,
"loss": 0.4609,
"step": 505
},
{
"epoch": 0.7125392944463849,
"grad_norm": 6.169280052185059,
"learning_rate": 8.920215393576685e-06,
"loss": 0.4799,
"step": 510
},
{
"epoch": 0.7195249738037024,
"grad_norm": 6.514042377471924,
"learning_rate": 8.8967003251632e-06,
"loss": 0.5,
"step": 515
},
{
"epoch": 0.7265106531610199,
"grad_norm": 7.015414714813232,
"learning_rate": 8.872963663685075e-06,
"loss": 0.5226,
"step": 520
},
{
"epoch": 0.7334963325183375,
"grad_norm": 4.968021869659424,
"learning_rate": 8.849006758971429e-06,
"loss": 0.4697,
"step": 525
},
{
"epoch": 0.7404820118756549,
"grad_norm": 6.74957799911499,
"learning_rate": 8.824830973375917e-06,
"loss": 0.5045,
"step": 530
},
{
"epoch": 0.7474676912329724,
"grad_norm": 5.4804816246032715,
"learning_rate": 8.800437681699264e-06,
"loss": 0.465,
"step": 535
},
{
"epoch": 0.7544533705902899,
"grad_norm": 5.658529281616211,
"learning_rate": 8.775828271111074e-06,
"loss": 0.474,
"step": 540
},
{
"epoch": 0.7614390499476074,
"grad_norm": 5.418574333190918,
"learning_rate": 8.751004141070958e-06,
"loss": 0.4904,
"step": 545
},
{
"epoch": 0.7684247293049249,
"grad_norm": 5.922712802886963,
"learning_rate": 8.72596670324894e-06,
"loss": 0.4721,
"step": 550
},
{
"epoch": 0.7754104086622424,
"grad_norm": 6.200154781341553,
"learning_rate": 8.70071738144519e-06,
"loss": 0.4902,
"step": 555
},
{
"epoch": 0.78239608801956,
"grad_norm": 5.705479145050049,
"learning_rate": 8.67525761150905e-06,
"loss": 0.4726,
"step": 560
},
{
"epoch": 0.7893817673768774,
"grad_norm": 6.879328727722168,
"learning_rate": 8.649588841257383e-06,
"loss": 0.4757,
"step": 565
},
{
"epoch": 0.7963674467341949,
"grad_norm": 7.012612819671631,
"learning_rate": 8.623712530392244e-06,
"loss": 0.4522,
"step": 570
},
{
"epoch": 0.8033531260915124,
"grad_norm": 6.293166160583496,
"learning_rate": 8.597630150417867e-06,
"loss": 0.4651,
"step": 575
},
{
"epoch": 0.8103388054488299,
"grad_norm": 5.768970012664795,
"learning_rate": 8.571343184556985e-06,
"loss": 0.4277,
"step": 580
},
{
"epoch": 0.8173244848061474,
"grad_norm": 6.452169895172119,
"learning_rate": 8.544853127666483e-06,
"loss": 0.5337,
"step": 585
},
{
"epoch": 0.8243101641634649,
"grad_norm": 5.4347615242004395,
"learning_rate": 8.518161486152406e-06,
"loss": 0.468,
"step": 590
},
{
"epoch": 0.8312958435207825,
"grad_norm": 5.982383728027344,
"learning_rate": 8.491269777884264e-06,
"loss": 0.4511,
"step": 595
},
{
"epoch": 0.8382815228780999,
"grad_norm": 5.2124457359313965,
"learning_rate": 8.464179532108742e-06,
"loss": 0.4667,
"step": 600
},
{
"epoch": 0.8452672022354174,
"grad_norm": 5.130034923553467,
"learning_rate": 8.436892289362728e-06,
"loss": 0.4551,
"step": 605
},
{
"epoch": 0.8522528815927349,
"grad_norm": 5.86264705657959,
"learning_rate": 8.409409601385702e-06,
"loss": 0.5026,
"step": 610
},
{
"epoch": 0.8592385609500524,
"grad_norm": 6.521675109863281,
"learning_rate": 8.381733031031503e-06,
"loss": 0.5017,
"step": 615
},
{
"epoch": 0.8662242403073699,
"grad_norm": 5.794342994689941,
"learning_rate": 8.353864152179445e-06,
"loss": 0.4638,
"step": 620
},
{
"epoch": 0.8732099196646874,
"grad_norm": 5.721254348754883,
"learning_rate": 8.325804549644823e-06,
"loss": 0.4652,
"step": 625
},
{
"epoch": 0.8801955990220048,
"grad_norm": 5.914518356323242,
"learning_rate": 8.297555819088787e-06,
"loss": 0.4613,
"step": 630
},
{
"epoch": 0.8871812783793224,
"grad_norm": 5.939746856689453,
"learning_rate": 8.269119566927599e-06,
"loss": 0.4599,
"step": 635
},
{
"epoch": 0.8941669577366399,
"grad_norm": 5.655862808227539,
"learning_rate": 8.240497410241286e-06,
"loss": 0.4602,
"step": 640
},
{
"epoch": 0.9011526370939574,
"grad_norm": 6.510814666748047,
"learning_rate": 8.211690976681678e-06,
"loss": 0.4582,
"step": 645
},
{
"epoch": 0.9081383164512749,
"grad_norm": 5.543778419494629,
"learning_rate": 8.18270190437985e-06,
"loss": 0.4777,
"step": 650
},
{
"epoch": 0.9151239958085924,
"grad_norm": 5.059428691864014,
"learning_rate": 8.153531841852969e-06,
"loss": 0.4756,
"step": 655
},
{
"epoch": 0.9221096751659099,
"grad_norm": 5.040985584259033,
"learning_rate": 8.12418244791054e-06,
"loss": 0.4742,
"step": 660
},
{
"epoch": 0.9290953545232273,
"grad_norm": 5.490272521972656,
"learning_rate": 8.094655391560086e-06,
"loss": 0.4614,
"step": 665
},
{
"epoch": 0.9360810338805449,
"grad_norm": 5.865604877471924,
"learning_rate": 8.064952351912227e-06,
"loss": 0.4671,
"step": 670
},
{
"epoch": 0.9430667132378624,
"grad_norm": 5.491858005523682,
"learning_rate": 8.035075018085204e-06,
"loss": 0.4624,
"step": 675
},
{
"epoch": 0.9500523925951799,
"grad_norm": 5.839197158813477,
"learning_rate": 8.005025089108812e-06,
"loss": 0.4811,
"step": 680
},
{
"epoch": 0.9570380719524973,
"grad_norm": 6.362710952758789,
"learning_rate": 7.974804273827791e-06,
"loss": 0.4829,
"step": 685
},
{
"epoch": 0.9640237513098149,
"grad_norm": 5.933167457580566,
"learning_rate": 7.944414290804647e-06,
"loss": 0.4895,
"step": 690
},
{
"epoch": 0.9710094306671324,
"grad_norm": 6.338855743408203,
"learning_rate": 7.913856868221922e-06,
"loss": 0.4729,
"step": 695
},
{
"epoch": 0.9779951100244498,
"grad_norm": 5.022581577301025,
"learning_rate": 7.883133743783918e-06,
"loss": 0.4772,
"step": 700
},
{
"epoch": 0.9849807893817674,
"grad_norm": 5.898752212524414,
"learning_rate": 7.852246664617878e-06,
"loss": 0.457,
"step": 705
},
{
"epoch": 0.9919664687390849,
"grad_norm": 4.9067864418029785,
"learning_rate": 7.821197387174638e-06,
"loss": 0.4577,
"step": 710
},
{
"epoch": 0.9989521480964024,
"grad_norm": 4.425784111022949,
"learning_rate": 7.78998767712873e-06,
"loss": 0.4683,
"step": 715
}
],
"logging_steps": 5,
"max_steps": 2148,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 9.684922567617413e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}