ayuwal12's picture
Upload LoRA fine-tuned BioMistral-7B model
6690520 verified
{
"best_global_step": 1500,
"best_metric": 0.7986094355583191,
"best_model_checkpoint": "./biomistral-lora-finetuned/checkpoint-1500",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 2772,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010832769126607989,
"grad_norm": 0.7727395296096802,
"learning_rate": 1.8e-05,
"loss": 0.889,
"step": 10
},
{
"epoch": 0.021665538253215978,
"grad_norm": 0.8008129596710205,
"learning_rate": 3.8e-05,
"loss": 0.8378,
"step": 20
},
{
"epoch": 0.03249830737982397,
"grad_norm": 0.9147247076034546,
"learning_rate": 5.8e-05,
"loss": 0.8108,
"step": 30
},
{
"epoch": 0.043331076506431955,
"grad_norm": 0.8121607303619385,
"learning_rate": 7.800000000000001e-05,
"loss": 0.8597,
"step": 40
},
{
"epoch": 0.05416384563303995,
"grad_norm": 1.0018593072891235,
"learning_rate": 9.8e-05,
"loss": 0.7486,
"step": 50
},
{
"epoch": 0.06499661475964794,
"grad_norm": 1.2048218250274658,
"learning_rate": 0.000118,
"loss": 0.6825,
"step": 60
},
{
"epoch": 0.07582938388625593,
"grad_norm": 0.9863468408584595,
"learning_rate": 0.000138,
"loss": 0.6539,
"step": 70
},
{
"epoch": 0.08666215301286391,
"grad_norm": 1.2911494970321655,
"learning_rate": 0.00015800000000000002,
"loss": 0.6198,
"step": 80
},
{
"epoch": 0.0974949221394719,
"grad_norm": 1.159672737121582,
"learning_rate": 0.00017800000000000002,
"loss": 0.6222,
"step": 90
},
{
"epoch": 0.1083276912660799,
"grad_norm": 1.0924432277679443,
"learning_rate": 0.00019800000000000002,
"loss": 0.5923,
"step": 100
},
{
"epoch": 0.11916046039268788,
"grad_norm": 1.3423463106155396,
"learning_rate": 0.00019932634730538925,
"loss": 0.5548,
"step": 110
},
{
"epoch": 0.12999322951929587,
"grad_norm": 1.4929102659225464,
"learning_rate": 0.00019857784431137723,
"loss": 0.6701,
"step": 120
},
{
"epoch": 0.14082599864590387,
"grad_norm": 0.9462954998016357,
"learning_rate": 0.00019782934131736527,
"loss": 0.8675,
"step": 130
},
{
"epoch": 0.15165876777251186,
"grad_norm": 0.9912289977073669,
"learning_rate": 0.0001970808383233533,
"loss": 0.9074,
"step": 140
},
{
"epoch": 0.16249153689911983,
"grad_norm": 1.1070538759231567,
"learning_rate": 0.00019633233532934132,
"loss": 0.8755,
"step": 150
},
{
"epoch": 0.17332430602572782,
"grad_norm": 0.9465340375900269,
"learning_rate": 0.00019558383233532936,
"loss": 0.882,
"step": 160
},
{
"epoch": 0.18415707515233581,
"grad_norm": 0.8657329678535461,
"learning_rate": 0.00019483532934131737,
"loss": 0.8737,
"step": 170
},
{
"epoch": 0.1949898442789438,
"grad_norm": 0.7293577790260315,
"learning_rate": 0.0001940868263473054,
"loss": 0.8473,
"step": 180
},
{
"epoch": 0.2058226134055518,
"grad_norm": 0.849353551864624,
"learning_rate": 0.00019333832335329343,
"loss": 0.9414,
"step": 190
},
{
"epoch": 0.2166553825321598,
"grad_norm": 0.7525314688682556,
"learning_rate": 0.00019258982035928144,
"loss": 0.8852,
"step": 200
},
{
"epoch": 0.22748815165876776,
"grad_norm": 1.0732208490371704,
"learning_rate": 0.00019184131736526948,
"loss": 0.8074,
"step": 210
},
{
"epoch": 0.23832092078537576,
"grad_norm": 0.8420374393463135,
"learning_rate": 0.0001910928143712575,
"loss": 0.9508,
"step": 220
},
{
"epoch": 0.24915368991198375,
"grad_norm": 0.8308244347572327,
"learning_rate": 0.0001903443113772455,
"loss": 0.8734,
"step": 230
},
{
"epoch": 0.25998645903859174,
"grad_norm": 0.9915153384208679,
"learning_rate": 0.00018959580838323354,
"loss": 0.8816,
"step": 240
},
{
"epoch": 0.2708192281651997,
"grad_norm": 4.8621978759765625,
"learning_rate": 0.00018884730538922158,
"loss": 0.8848,
"step": 250
},
{
"epoch": 0.28165199729180773,
"grad_norm": 0.7945590019226074,
"learning_rate": 0.0001880988023952096,
"loss": 0.8503,
"step": 260
},
{
"epoch": 0.2924847664184157,
"grad_norm": 0.7896672487258911,
"learning_rate": 0.00018735029940119763,
"loss": 0.8798,
"step": 270
},
{
"epoch": 0.3033175355450237,
"grad_norm": 0.8870701789855957,
"learning_rate": 0.00018660179640718564,
"loss": 0.9112,
"step": 280
},
{
"epoch": 0.3141503046716317,
"grad_norm": 0.9003740549087524,
"learning_rate": 0.00018585329341317365,
"loss": 0.846,
"step": 290
},
{
"epoch": 0.32498307379823965,
"grad_norm": 0.7067676186561584,
"learning_rate": 0.0001851047904191617,
"loss": 0.8588,
"step": 300
},
{
"epoch": 0.3358158429248477,
"grad_norm": 0.9696246385574341,
"learning_rate": 0.0001843562874251497,
"loss": 0.8244,
"step": 310
},
{
"epoch": 0.34664861205145564,
"grad_norm": 0.9892609715461731,
"learning_rate": 0.00018360778443113774,
"loss": 0.8214,
"step": 320
},
{
"epoch": 0.35748138117806366,
"grad_norm": 0.822260856628418,
"learning_rate": 0.00018285928143712575,
"loss": 0.7977,
"step": 330
},
{
"epoch": 0.36831415030467163,
"grad_norm": 0.7743964791297913,
"learning_rate": 0.00018211077844311376,
"loss": 0.8002,
"step": 340
},
{
"epoch": 0.3791469194312796,
"grad_norm": 0.7090775370597839,
"learning_rate": 0.0001813622754491018,
"loss": 0.8192,
"step": 350
},
{
"epoch": 0.3899796885578876,
"grad_norm": 1.0970802307128906,
"learning_rate": 0.00018061377245508984,
"loss": 0.8516,
"step": 360
},
{
"epoch": 0.4008124576844956,
"grad_norm": 0.9633163213729858,
"learning_rate": 0.00017986526946107785,
"loss": 0.8414,
"step": 370
},
{
"epoch": 0.4116452268111036,
"grad_norm": 0.6846926808357239,
"learning_rate": 0.00017911676646706587,
"loss": 0.8187,
"step": 380
},
{
"epoch": 0.42247799593771157,
"grad_norm": 0.7262110710144043,
"learning_rate": 0.0001783682634730539,
"loss": 0.8572,
"step": 390
},
{
"epoch": 0.4333107650643196,
"grad_norm": 0.8537372350692749,
"learning_rate": 0.00017761976047904192,
"loss": 0.8286,
"step": 400
},
{
"epoch": 0.44414353419092756,
"grad_norm": 0.8860271573066711,
"learning_rate": 0.00017687125748502996,
"loss": 0.8416,
"step": 410
},
{
"epoch": 0.4549763033175355,
"grad_norm": 0.7984218597412109,
"learning_rate": 0.000176122754491018,
"loss": 0.8373,
"step": 420
},
{
"epoch": 0.46580907244414355,
"grad_norm": 0.8060943484306335,
"learning_rate": 0.000175374251497006,
"loss": 0.9165,
"step": 430
},
{
"epoch": 0.4766418415707515,
"grad_norm": 0.7871391177177429,
"learning_rate": 0.00017462574850299402,
"loss": 0.8276,
"step": 440
},
{
"epoch": 0.48747461069735953,
"grad_norm": 0.7732688784599304,
"learning_rate": 0.00017387724550898203,
"loss": 0.8346,
"step": 450
},
{
"epoch": 0.4983073798239675,
"grad_norm": 0.9314000606536865,
"learning_rate": 0.00017312874251497007,
"loss": 0.8291,
"step": 460
},
{
"epoch": 0.5091401489505755,
"grad_norm": 0.6721988916397095,
"learning_rate": 0.0001723802395209581,
"loss": 0.7091,
"step": 470
},
{
"epoch": 0.5199729180771835,
"grad_norm": 0.825965940952301,
"learning_rate": 0.00017163173652694612,
"loss": 0.8934,
"step": 480
},
{
"epoch": 0.5308056872037915,
"grad_norm": 0.8427668213844299,
"learning_rate": 0.00017088323353293413,
"loss": 0.7603,
"step": 490
},
{
"epoch": 0.5416384563303994,
"grad_norm": 1.0061259269714355,
"learning_rate": 0.00017013473053892217,
"loss": 0.8277,
"step": 500
},
{
"epoch": 0.5416384563303994,
"eval_loss": 0.8331602811813354,
"eval_runtime": 355.9061,
"eval_samples_per_second": 4.614,
"eval_steps_per_second": 2.307,
"step": 500
},
{
"epoch": 0.5524712254570074,
"grad_norm": 0.8820628523826599,
"learning_rate": 0.00016938622754491018,
"loss": 0.8348,
"step": 510
},
{
"epoch": 0.5633039945836155,
"grad_norm": 0.8095284700393677,
"learning_rate": 0.00016863772455089822,
"loss": 0.9172,
"step": 520
},
{
"epoch": 0.5741367637102234,
"grad_norm": 0.6959540843963623,
"learning_rate": 0.00016788922155688623,
"loss": 0.838,
"step": 530
},
{
"epoch": 0.5849695328368314,
"grad_norm": 0.835831880569458,
"learning_rate": 0.00016714071856287424,
"loss": 0.8887,
"step": 540
},
{
"epoch": 0.5958023019634394,
"grad_norm": 0.9289611577987671,
"learning_rate": 0.00016639221556886228,
"loss": 0.8514,
"step": 550
},
{
"epoch": 0.6066350710900474,
"grad_norm": 0.6904628872871399,
"learning_rate": 0.00016564371257485032,
"loss": 0.8645,
"step": 560
},
{
"epoch": 0.6174678402166554,
"grad_norm": 0.8879178762435913,
"learning_rate": 0.00016489520958083833,
"loss": 0.8201,
"step": 570
},
{
"epoch": 0.6283006093432634,
"grad_norm": 0.8411425948143005,
"learning_rate": 0.00016414670658682637,
"loss": 0.836,
"step": 580
},
{
"epoch": 0.6391333784698714,
"grad_norm": 0.8564555644989014,
"learning_rate": 0.00016339820359281436,
"loss": 0.7724,
"step": 590
},
{
"epoch": 0.6499661475964793,
"grad_norm": 0.8382830619812012,
"learning_rate": 0.0001626497005988024,
"loss": 0.7839,
"step": 600
},
{
"epoch": 0.6607989167230873,
"grad_norm": 0.7657437920570374,
"learning_rate": 0.00016190119760479043,
"loss": 0.7973,
"step": 610
},
{
"epoch": 0.6716316858496953,
"grad_norm": 0.7758445143699646,
"learning_rate": 0.00016115269461077845,
"loss": 0.8111,
"step": 620
},
{
"epoch": 0.6824644549763034,
"grad_norm": 1.0041533708572388,
"learning_rate": 0.00016040419161676649,
"loss": 0.8359,
"step": 630
},
{
"epoch": 0.6932972241029113,
"grad_norm": 0.9679577946662903,
"learning_rate": 0.0001596556886227545,
"loss": 0.8822,
"step": 640
},
{
"epoch": 0.7041299932295193,
"grad_norm": 0.8141391277313232,
"learning_rate": 0.0001589071856287425,
"loss": 0.8714,
"step": 650
},
{
"epoch": 0.7149627623561273,
"grad_norm": 0.7982810139656067,
"learning_rate": 0.00015815868263473055,
"loss": 0.856,
"step": 660
},
{
"epoch": 0.7257955314827352,
"grad_norm": 0.7932000160217285,
"learning_rate": 0.00015741017964071859,
"loss": 0.8405,
"step": 670
},
{
"epoch": 0.7366283006093433,
"grad_norm": 0.7269508242607117,
"learning_rate": 0.0001566616766467066,
"loss": 0.8371,
"step": 680
},
{
"epoch": 0.7474610697359513,
"grad_norm": 0.9001722931861877,
"learning_rate": 0.0001559131736526946,
"loss": 0.8305,
"step": 690
},
{
"epoch": 0.7582938388625592,
"grad_norm": 0.6795508861541748,
"learning_rate": 0.00015516467065868262,
"loss": 0.8324,
"step": 700
},
{
"epoch": 0.7691266079891672,
"grad_norm": 0.8868729472160339,
"learning_rate": 0.00015441616766467066,
"loss": 0.8521,
"step": 710
},
{
"epoch": 0.7799593771157752,
"grad_norm": 0.9720478653907776,
"learning_rate": 0.0001536676646706587,
"loss": 0.7759,
"step": 720
},
{
"epoch": 0.7907921462423833,
"grad_norm": 0.8006075620651245,
"learning_rate": 0.0001529191616766467,
"loss": 0.7981,
"step": 730
},
{
"epoch": 0.8016249153689912,
"grad_norm": 0.9107721447944641,
"learning_rate": 0.00015217065868263475,
"loss": 0.7868,
"step": 740
},
{
"epoch": 0.8124576844955992,
"grad_norm": 0.7584466338157654,
"learning_rate": 0.00015142215568862276,
"loss": 0.7401,
"step": 750
},
{
"epoch": 0.8232904536222072,
"grad_norm": 1.0075221061706543,
"learning_rate": 0.00015067365269461077,
"loss": 0.8024,
"step": 760
},
{
"epoch": 0.8341232227488151,
"grad_norm": 0.8769344091415405,
"learning_rate": 0.0001499251497005988,
"loss": 0.7779,
"step": 770
},
{
"epoch": 0.8449559918754231,
"grad_norm": 0.84312903881073,
"learning_rate": 0.00014917664670658685,
"loss": 0.8314,
"step": 780
},
{
"epoch": 0.8557887610020312,
"grad_norm": 0.8116353750228882,
"learning_rate": 0.00014842814371257486,
"loss": 0.8146,
"step": 790
},
{
"epoch": 0.8666215301286392,
"grad_norm": 0.8301011919975281,
"learning_rate": 0.00014767964071856287,
"loss": 0.7422,
"step": 800
},
{
"epoch": 0.8774542992552471,
"grad_norm": 0.8579692244529724,
"learning_rate": 0.00014693113772455091,
"loss": 0.7442,
"step": 810
},
{
"epoch": 0.8882870683818551,
"grad_norm": 0.7513943910598755,
"learning_rate": 0.00014618263473053893,
"loss": 0.7671,
"step": 820
},
{
"epoch": 0.8991198375084631,
"grad_norm": 0.9639107584953308,
"learning_rate": 0.00014543413173652696,
"loss": 0.7896,
"step": 830
},
{
"epoch": 0.909952606635071,
"grad_norm": 0.8897636532783508,
"learning_rate": 0.00014468562874251498,
"loss": 0.7613,
"step": 840
},
{
"epoch": 0.9207853757616791,
"grad_norm": 0.7998213171958923,
"learning_rate": 0.000143937125748503,
"loss": 0.7647,
"step": 850
},
{
"epoch": 0.9316181448882871,
"grad_norm": 0.6916050910949707,
"learning_rate": 0.00014318862275449103,
"loss": 0.7697,
"step": 860
},
{
"epoch": 0.942450914014895,
"grad_norm": 1.0154324769973755,
"learning_rate": 0.00014244011976047904,
"loss": 0.7314,
"step": 870
},
{
"epoch": 0.953283683141503,
"grad_norm": 0.9787517786026001,
"learning_rate": 0.00014169161676646708,
"loss": 0.8047,
"step": 880
},
{
"epoch": 0.964116452268111,
"grad_norm": 0.6035457253456116,
"learning_rate": 0.00014094311377245512,
"loss": 0.783,
"step": 890
},
{
"epoch": 0.9749492213947191,
"grad_norm": 0.940951943397522,
"learning_rate": 0.0001401946107784431,
"loss": 0.7741,
"step": 900
},
{
"epoch": 0.985781990521327,
"grad_norm": 0.7785654067993164,
"learning_rate": 0.00013944610778443114,
"loss": 0.7855,
"step": 910
},
{
"epoch": 0.996614759647935,
"grad_norm": 0.8356137275695801,
"learning_rate": 0.00013869760479041918,
"loss": 0.8292,
"step": 920
},
{
"epoch": 1.0064996614759647,
"grad_norm": 0.6590499877929688,
"learning_rate": 0.0001379491017964072,
"loss": 0.6858,
"step": 930
},
{
"epoch": 1.0173324306025728,
"grad_norm": 1.0389671325683594,
"learning_rate": 0.00013720059880239523,
"loss": 0.6097,
"step": 940
},
{
"epoch": 1.0281651997291807,
"grad_norm": 0.9596243500709534,
"learning_rate": 0.00013645209580838324,
"loss": 0.5676,
"step": 950
},
{
"epoch": 1.0389979688557887,
"grad_norm": 1.0831798315048218,
"learning_rate": 0.00013570359281437125,
"loss": 0.6106,
"step": 960
},
{
"epoch": 1.0498307379823968,
"grad_norm": 0.92978835105896,
"learning_rate": 0.0001349550898203593,
"loss": 0.5924,
"step": 970
},
{
"epoch": 1.0606635071090047,
"grad_norm": 0.9672062993049622,
"learning_rate": 0.0001342065868263473,
"loss": 0.5496,
"step": 980
},
{
"epoch": 1.0714962762356128,
"grad_norm": 1.1402652263641357,
"learning_rate": 0.00013345808383233534,
"loss": 0.5871,
"step": 990
},
{
"epoch": 1.0823290453622207,
"grad_norm": 1.1109035015106201,
"learning_rate": 0.00013270958083832335,
"loss": 0.5424,
"step": 1000
},
{
"epoch": 1.0823290453622207,
"eval_loss": 0.8179630041122437,
"eval_runtime": 357.2769,
"eval_samples_per_second": 4.596,
"eval_steps_per_second": 2.298,
"step": 1000
},
{
"epoch": 1.0931618144888287,
"grad_norm": 0.8117087483406067,
"learning_rate": 0.00013196107784431137,
"loss": 0.5636,
"step": 1010
},
{
"epoch": 1.1039945836154368,
"grad_norm": 0.86320561170578,
"learning_rate": 0.0001312125748502994,
"loss": 0.5191,
"step": 1020
},
{
"epoch": 1.1148273527420447,
"grad_norm": 1.1274133920669556,
"learning_rate": 0.00013046407185628744,
"loss": 0.5891,
"step": 1030
},
{
"epoch": 1.1256601218686526,
"grad_norm": 1.0116336345672607,
"learning_rate": 0.00012971556886227546,
"loss": 0.5579,
"step": 1040
},
{
"epoch": 1.1364928909952607,
"grad_norm": 0.9277855157852173,
"learning_rate": 0.0001289670658682635,
"loss": 0.5971,
"step": 1050
},
{
"epoch": 1.1473256601218687,
"grad_norm": 1.0700503587722778,
"learning_rate": 0.0001282185628742515,
"loss": 0.5815,
"step": 1060
},
{
"epoch": 1.1581584292484766,
"grad_norm": 0.9346574544906616,
"learning_rate": 0.00012747005988023952,
"loss": 0.5472,
"step": 1070
},
{
"epoch": 1.1689911983750847,
"grad_norm": 1.047631025314331,
"learning_rate": 0.00012672155688622756,
"loss": 0.5479,
"step": 1080
},
{
"epoch": 1.1798239675016926,
"grad_norm": 0.9931487441062927,
"learning_rate": 0.00012597305389221557,
"loss": 0.5521,
"step": 1090
},
{
"epoch": 1.1906567366283005,
"grad_norm": 0.9764857292175293,
"learning_rate": 0.0001252245508982036,
"loss": 0.584,
"step": 1100
},
{
"epoch": 1.2014895057549086,
"grad_norm": 1.0661903619766235,
"learning_rate": 0.00012447604790419162,
"loss": 0.6101,
"step": 1110
},
{
"epoch": 1.2123222748815166,
"grad_norm": 1.0962295532226562,
"learning_rate": 0.00012372754491017963,
"loss": 0.6028,
"step": 1120
},
{
"epoch": 1.2231550440081245,
"grad_norm": 0.9794766306877136,
"learning_rate": 0.00012297904191616767,
"loss": 0.5813,
"step": 1130
},
{
"epoch": 1.2339878131347326,
"grad_norm": 0.9556275606155396,
"learning_rate": 0.0001222305389221557,
"loss": 0.5662,
"step": 1140
},
{
"epoch": 1.2448205822613405,
"grad_norm": 1.1200224161148071,
"learning_rate": 0.0001214820359281437,
"loss": 0.5642,
"step": 1150
},
{
"epoch": 1.2556533513879486,
"grad_norm": 1.0518434047698975,
"learning_rate": 0.00012073353293413175,
"loss": 0.6126,
"step": 1160
},
{
"epoch": 1.2664861205145566,
"grad_norm": 1.1709963083267212,
"learning_rate": 0.00011998502994011977,
"loss": 0.5189,
"step": 1170
},
{
"epoch": 1.2773188896411645,
"grad_norm": 0.8867760896682739,
"learning_rate": 0.00011923652694610778,
"loss": 0.6098,
"step": 1180
},
{
"epoch": 1.2881516587677724,
"grad_norm": 0.9317127466201782,
"learning_rate": 0.00011848802395209582,
"loss": 0.5667,
"step": 1190
},
{
"epoch": 1.2989844278943805,
"grad_norm": 1.1382100582122803,
"learning_rate": 0.00011773952095808385,
"loss": 0.5756,
"step": 1200
},
{
"epoch": 1.3098171970209884,
"grad_norm": 0.9819681644439697,
"learning_rate": 0.00011699101796407186,
"loss": 0.5922,
"step": 1210
},
{
"epoch": 1.3206499661475966,
"grad_norm": 1.0776174068450928,
"learning_rate": 0.00011624251497005988,
"loss": 0.5728,
"step": 1220
},
{
"epoch": 1.3314827352742045,
"grad_norm": 1.0137302875518799,
"learning_rate": 0.0001154940119760479,
"loss": 0.5603,
"step": 1230
},
{
"epoch": 1.3423155044008124,
"grad_norm": 1.1223585605621338,
"learning_rate": 0.00011474550898203593,
"loss": 0.5639,
"step": 1240
},
{
"epoch": 1.3531482735274205,
"grad_norm": 0.8942229747772217,
"learning_rate": 0.00011399700598802396,
"loss": 0.586,
"step": 1250
},
{
"epoch": 1.3639810426540284,
"grad_norm": 1.225698709487915,
"learning_rate": 0.00011324850299401197,
"loss": 0.563,
"step": 1260
},
{
"epoch": 1.3748138117806366,
"grad_norm": 1.159463882446289,
"learning_rate": 0.00011250000000000001,
"loss": 0.5898,
"step": 1270
},
{
"epoch": 1.3856465809072445,
"grad_norm": 1.0059807300567627,
"learning_rate": 0.00011175149700598804,
"loss": 0.6096,
"step": 1280
},
{
"epoch": 1.3964793500338524,
"grad_norm": 1.1433062553405762,
"learning_rate": 0.00011100299401197605,
"loss": 0.5411,
"step": 1290
},
{
"epoch": 1.4073121191604603,
"grad_norm": 1.0282905101776123,
"learning_rate": 0.00011025449101796407,
"loss": 0.5928,
"step": 1300
},
{
"epoch": 1.4181448882870684,
"grad_norm": 0.8389853835105896,
"learning_rate": 0.00010950598802395211,
"loss": 0.5657,
"step": 1310
},
{
"epoch": 1.4289776574136763,
"grad_norm": 1.132350206375122,
"learning_rate": 0.00010875748502994012,
"loss": 0.6196,
"step": 1320
},
{
"epoch": 1.4398104265402845,
"grad_norm": 1.1093621253967285,
"learning_rate": 0.00010800898203592815,
"loss": 0.5845,
"step": 1330
},
{
"epoch": 1.4506431956668924,
"grad_norm": 1.3198816776275635,
"learning_rate": 0.00010726047904191616,
"loss": 0.5711,
"step": 1340
},
{
"epoch": 1.4614759647935003,
"grad_norm": 0.8968690037727356,
"learning_rate": 0.0001065119760479042,
"loss": 0.6075,
"step": 1350
},
{
"epoch": 1.4723087339201082,
"grad_norm": 1.0248963832855225,
"learning_rate": 0.00010576347305389222,
"loss": 0.5869,
"step": 1360
},
{
"epoch": 1.4831415030467163,
"grad_norm": 1.2115412950515747,
"learning_rate": 0.00010501497005988024,
"loss": 0.549,
"step": 1370
},
{
"epoch": 1.4939742721733242,
"grad_norm": 1.1320476531982422,
"learning_rate": 0.00010426646706586826,
"loss": 0.5661,
"step": 1380
},
{
"epoch": 1.5048070412999324,
"grad_norm": 1.0099844932556152,
"learning_rate": 0.0001035179640718563,
"loss": 0.5953,
"step": 1390
},
{
"epoch": 1.5156398104265403,
"grad_norm": 0.9809553623199463,
"learning_rate": 0.00010276946107784431,
"loss": 0.578,
"step": 1400
},
{
"epoch": 1.5264725795531482,
"grad_norm": 1.4169446229934692,
"learning_rate": 0.00010202095808383234,
"loss": 0.6173,
"step": 1410
},
{
"epoch": 1.537305348679756,
"grad_norm": 1.1033852100372314,
"learning_rate": 0.00010127245508982038,
"loss": 0.5917,
"step": 1420
},
{
"epoch": 1.5481381178063642,
"grad_norm": 1.1163372993469238,
"learning_rate": 0.00010052395209580839,
"loss": 0.589,
"step": 1430
},
{
"epoch": 1.5589708869329724,
"grad_norm": 0.9786676168441772,
"learning_rate": 9.977544910179641e-05,
"loss": 0.5425,
"step": 1440
},
{
"epoch": 1.5698036560595803,
"grad_norm": 1.034001111984253,
"learning_rate": 9.902694610778444e-05,
"loss": 0.5467,
"step": 1450
},
{
"epoch": 1.5806364251861882,
"grad_norm": 0.8697665929794312,
"learning_rate": 9.827844311377245e-05,
"loss": 0.5882,
"step": 1460
},
{
"epoch": 1.591469194312796,
"grad_norm": 1.0091935396194458,
"learning_rate": 9.752994011976049e-05,
"loss": 0.573,
"step": 1470
},
{
"epoch": 1.6023019634394042,
"grad_norm": 1.0126501321792603,
"learning_rate": 9.678143712574852e-05,
"loss": 0.6083,
"step": 1480
},
{
"epoch": 1.6131347325660121,
"grad_norm": 0.9271785020828247,
"learning_rate": 9.603293413173653e-05,
"loss": 0.5564,
"step": 1490
},
{
"epoch": 1.6239675016926203,
"grad_norm": 1.0736253261566162,
"learning_rate": 9.528443113772455e-05,
"loss": 0.5696,
"step": 1500
},
{
"epoch": 1.6239675016926203,
"eval_loss": 0.7986094355583191,
"eval_runtime": 358.2761,
"eval_samples_per_second": 4.583,
"eval_steps_per_second": 2.292,
"step": 1500
},
{
"epoch": 1.6348002708192282,
"grad_norm": 0.9671568870544434,
"learning_rate": 9.453592814371258e-05,
"loss": 0.5994,
"step": 1510
},
{
"epoch": 1.645633039945836,
"grad_norm": 0.9636701345443726,
"learning_rate": 9.37874251497006e-05,
"loss": 0.6096,
"step": 1520
},
{
"epoch": 1.656465809072444,
"grad_norm": 1.1323844194412231,
"learning_rate": 9.303892215568863e-05,
"loss": 0.5981,
"step": 1530
},
{
"epoch": 1.6672985781990521,
"grad_norm": 1.0002387762069702,
"learning_rate": 9.229041916167665e-05,
"loss": 0.5807,
"step": 1540
},
{
"epoch": 1.6781313473256603,
"grad_norm": 1.2000038623809814,
"learning_rate": 9.154191616766468e-05,
"loss": 0.5583,
"step": 1550
},
{
"epoch": 1.6889641164522682,
"grad_norm": 1.153903841972351,
"learning_rate": 9.079341317365269e-05,
"loss": 0.6237,
"step": 1560
},
{
"epoch": 1.699796885578876,
"grad_norm": 1.0791847705841064,
"learning_rate": 9.004491017964072e-05,
"loss": 0.5457,
"step": 1570
},
{
"epoch": 1.710629654705484,
"grad_norm": 1.1212618350982666,
"learning_rate": 8.929640718562875e-05,
"loss": 0.551,
"step": 1580
},
{
"epoch": 1.721462423832092,
"grad_norm": 1.219691514968872,
"learning_rate": 8.854790419161677e-05,
"loss": 0.6027,
"step": 1590
},
{
"epoch": 1.7322951929587,
"grad_norm": 1.066247820854187,
"learning_rate": 8.779940119760479e-05,
"loss": 0.5739,
"step": 1600
},
{
"epoch": 1.7431279620853082,
"grad_norm": 1.070609450340271,
"learning_rate": 8.705089820359282e-05,
"loss": 0.6113,
"step": 1610
},
{
"epoch": 1.753960731211916,
"grad_norm": 1.377456784248352,
"learning_rate": 8.630239520958084e-05,
"loss": 0.5648,
"step": 1620
},
{
"epoch": 1.764793500338524,
"grad_norm": 1.0471181869506836,
"learning_rate": 8.555389221556887e-05,
"loss": 0.5514,
"step": 1630
},
{
"epoch": 1.775626269465132,
"grad_norm": 1.2327128648757935,
"learning_rate": 8.480538922155688e-05,
"loss": 0.6072,
"step": 1640
},
{
"epoch": 1.78645903859174,
"grad_norm": 1.004497766494751,
"learning_rate": 8.405688622754492e-05,
"loss": 0.5601,
"step": 1650
},
{
"epoch": 1.797291807718348,
"grad_norm": 1.2862775325775146,
"learning_rate": 8.330838323353294e-05,
"loss": 0.6073,
"step": 1660
},
{
"epoch": 1.808124576844956,
"grad_norm": 1.0752897262573242,
"learning_rate": 8.255988023952096e-05,
"loss": 0.6079,
"step": 1670
},
{
"epoch": 1.818957345971564,
"grad_norm": 1.031568169593811,
"learning_rate": 8.1811377245509e-05,
"loss": 0.5701,
"step": 1680
},
{
"epoch": 1.829790115098172,
"grad_norm": 1.2067883014678955,
"learning_rate": 8.1062874251497e-05,
"loss": 0.6024,
"step": 1690
},
{
"epoch": 1.8406228842247798,
"grad_norm": 1.2873584032058716,
"learning_rate": 8.031437125748503e-05,
"loss": 0.6033,
"step": 1700
},
{
"epoch": 1.851455653351388,
"grad_norm": 1.1230562925338745,
"learning_rate": 7.956586826347306e-05,
"loss": 0.5534,
"step": 1710
},
{
"epoch": 1.862288422477996,
"grad_norm": 1.275429129600525,
"learning_rate": 7.881736526946108e-05,
"loss": 0.5483,
"step": 1720
},
{
"epoch": 1.873121191604604,
"grad_norm": 1.1561681032180786,
"learning_rate": 7.806886227544911e-05,
"loss": 0.5948,
"step": 1730
},
{
"epoch": 1.883953960731212,
"grad_norm": 1.0285365581512451,
"learning_rate": 7.732035928143713e-05,
"loss": 0.5843,
"step": 1740
},
{
"epoch": 1.8947867298578198,
"grad_norm": 1.257944107055664,
"learning_rate": 7.657185628742516e-05,
"loss": 0.5672,
"step": 1750
},
{
"epoch": 1.9056194989844277,
"grad_norm": 1.2069061994552612,
"learning_rate": 7.582335329341318e-05,
"loss": 0.6312,
"step": 1760
},
{
"epoch": 1.9164522681110359,
"grad_norm": 0.946007251739502,
"learning_rate": 7.50748502994012e-05,
"loss": 0.6028,
"step": 1770
},
{
"epoch": 1.927285037237644,
"grad_norm": 1.3141242265701294,
"learning_rate": 7.432634730538922e-05,
"loss": 0.5762,
"step": 1780
},
{
"epoch": 1.938117806364252,
"grad_norm": 0.9737468957901001,
"learning_rate": 7.357784431137726e-05,
"loss": 0.5637,
"step": 1790
},
{
"epoch": 1.9489505754908598,
"grad_norm": 1.0719372034072876,
"learning_rate": 7.282934131736527e-05,
"loss": 0.5685,
"step": 1800
},
{
"epoch": 1.9597833446174677,
"grad_norm": 0.9777527451515198,
"learning_rate": 7.20808383233533e-05,
"loss": 0.5823,
"step": 1810
},
{
"epoch": 1.9706161137440759,
"grad_norm": 1.019610047340393,
"learning_rate": 7.133233532934132e-05,
"loss": 0.5342,
"step": 1820
},
{
"epoch": 1.9814488828706838,
"grad_norm": 1.2895872592926025,
"learning_rate": 7.058383233532935e-05,
"loss": 0.5625,
"step": 1830
},
{
"epoch": 1.992281651997292,
"grad_norm": 1.1473089456558228,
"learning_rate": 6.983532934131737e-05,
"loss": 0.5476,
"step": 1840
},
{
"epoch": 2.0021665538253215,
"grad_norm": 0.9660665392875671,
"learning_rate": 6.908682634730538e-05,
"loss": 0.5755,
"step": 1850
},
{
"epoch": 2.0129993229519294,
"grad_norm": 1.2142918109893799,
"learning_rate": 6.833832335329342e-05,
"loss": 0.3712,
"step": 1860
},
{
"epoch": 2.0238320920785378,
"grad_norm": 1.4106266498565674,
"learning_rate": 6.758982035928145e-05,
"loss": 0.3645,
"step": 1870
},
{
"epoch": 2.0346648612051457,
"grad_norm": 1.2526434659957886,
"learning_rate": 6.684131736526946e-05,
"loss": 0.3634,
"step": 1880
},
{
"epoch": 2.0454976303317536,
"grad_norm": 1.2345237731933594,
"learning_rate": 6.609281437125749e-05,
"loss": 0.3181,
"step": 1890
},
{
"epoch": 2.0563303994583615,
"grad_norm": 1.1664937734603882,
"learning_rate": 6.534431137724551e-05,
"loss": 0.3412,
"step": 1900
},
{
"epoch": 2.0671631685849694,
"grad_norm": 1.3861303329467773,
"learning_rate": 6.459580838323354e-05,
"loss": 0.348,
"step": 1910
},
{
"epoch": 2.0779959377115773,
"grad_norm": 1.4952672719955444,
"learning_rate": 6.384730538922156e-05,
"loss": 0.3193,
"step": 1920
},
{
"epoch": 2.0888287068381857,
"grad_norm": 1.3477551937103271,
"learning_rate": 6.309880239520959e-05,
"loss": 0.3499,
"step": 1930
},
{
"epoch": 2.0996614759647936,
"grad_norm": 1.5403518676757812,
"learning_rate": 6.235029940119761e-05,
"loss": 0.3742,
"step": 1940
},
{
"epoch": 2.1104942450914015,
"grad_norm": 1.2402806282043457,
"learning_rate": 6.160179640718562e-05,
"loss": 0.3575,
"step": 1950
},
{
"epoch": 2.1213270142180094,
"grad_norm": 1.0961482524871826,
"learning_rate": 6.085329341317365e-05,
"loss": 0.355,
"step": 1960
},
{
"epoch": 2.1321597833446173,
"grad_norm": 1.1491034030914307,
"learning_rate": 6.010479041916168e-05,
"loss": 0.3555,
"step": 1970
},
{
"epoch": 2.1429925524712257,
"grad_norm": 1.6308982372283936,
"learning_rate": 5.9356287425149706e-05,
"loss": 0.3408,
"step": 1980
},
{
"epoch": 2.1538253215978336,
"grad_norm": 1.481628656387329,
"learning_rate": 5.8607784431137725e-05,
"loss": 0.3814,
"step": 1990
},
{
"epoch": 2.1646580907244415,
"grad_norm": 1.2989139556884766,
"learning_rate": 5.785928143712576e-05,
"loss": 0.343,
"step": 2000
},
{
"epoch": 2.1646580907244415,
"eval_loss": 0.8451017141342163,
"eval_runtime": 357.77,
"eval_samples_per_second": 4.59,
"eval_steps_per_second": 2.295,
"step": 2000
},
{
"epoch": 2.1754908598510494,
"grad_norm": 1.3194793462753296,
"learning_rate": 5.7110778443113775e-05,
"loss": 0.3473,
"step": 2010
},
{
"epoch": 2.1863236289776573,
"grad_norm": 1.0370373725891113,
"learning_rate": 5.63622754491018e-05,
"loss": 0.3167,
"step": 2020
},
{
"epoch": 2.197156398104265,
"grad_norm": 1.1874184608459473,
"learning_rate": 5.561377245508982e-05,
"loss": 0.3533,
"step": 2030
},
{
"epoch": 2.2079891672308736,
"grad_norm": 1.6191632747650146,
"learning_rate": 5.486526946107785e-05,
"loss": 0.3676,
"step": 2040
},
{
"epoch": 2.2188219363574815,
"grad_norm": 1.5258554220199585,
"learning_rate": 5.411676646706587e-05,
"loss": 0.3684,
"step": 2050
},
{
"epoch": 2.2296547054840894,
"grad_norm": 1.5065487623214722,
"learning_rate": 5.3368263473053895e-05,
"loss": 0.3634,
"step": 2060
},
{
"epoch": 2.2404874746106973,
"grad_norm": 1.4091628789901733,
"learning_rate": 5.261976047904193e-05,
"loss": 0.3637,
"step": 2070
},
{
"epoch": 2.251320243737305,
"grad_norm": 1.304001808166504,
"learning_rate": 5.1871257485029946e-05,
"loss": 0.3429,
"step": 2080
},
{
"epoch": 2.262153012863913,
"grad_norm": 1.4180433750152588,
"learning_rate": 5.1122754491017964e-05,
"loss": 0.3317,
"step": 2090
},
{
"epoch": 2.2729857819905215,
"grad_norm": 1.4093214273452759,
"learning_rate": 5.037425149700599e-05,
"loss": 0.3068,
"step": 2100
},
{
"epoch": 2.2838185511171294,
"grad_norm": 1.3135852813720703,
"learning_rate": 4.9625748502994015e-05,
"loss": 0.3606,
"step": 2110
},
{
"epoch": 2.2946513202437373,
"grad_norm": 1.180317759513855,
"learning_rate": 4.887724550898204e-05,
"loss": 0.347,
"step": 2120
},
{
"epoch": 2.305484089370345,
"grad_norm": 1.3517941236495972,
"learning_rate": 4.812874251497006e-05,
"loss": 0.3263,
"step": 2130
},
{
"epoch": 2.316316858496953,
"grad_norm": 1.4726624488830566,
"learning_rate": 4.7380239520958084e-05,
"loss": 0.369,
"step": 2140
},
{
"epoch": 2.3271496276235615,
"grad_norm": 1.5008536577224731,
"learning_rate": 4.663173652694611e-05,
"loss": 0.373,
"step": 2150
},
{
"epoch": 2.3379823967501694,
"grad_norm": 1.251826524734497,
"learning_rate": 4.5883233532934135e-05,
"loss": 0.3576,
"step": 2160
},
{
"epoch": 2.3488151658767773,
"grad_norm": 1.3931865692138672,
"learning_rate": 4.513473053892216e-05,
"loss": 0.3544,
"step": 2170
},
{
"epoch": 2.359647935003385,
"grad_norm": 1.2691062688827515,
"learning_rate": 4.438622754491018e-05,
"loss": 0.3802,
"step": 2180
},
{
"epoch": 2.370480704129993,
"grad_norm": 1.1229090690612793,
"learning_rate": 4.3637724550898204e-05,
"loss": 0.3144,
"step": 2190
},
{
"epoch": 2.381313473256601,
"grad_norm": 1.153255581855774,
"learning_rate": 4.288922155688623e-05,
"loss": 0.3531,
"step": 2200
},
{
"epoch": 2.3921462423832094,
"grad_norm": 1.426155924797058,
"learning_rate": 4.2140718562874255e-05,
"loss": 0.359,
"step": 2210
},
{
"epoch": 2.4029790115098173,
"grad_norm": 1.1010292768478394,
"learning_rate": 4.139221556886227e-05,
"loss": 0.3529,
"step": 2220
},
{
"epoch": 2.413811780636425,
"grad_norm": 1.080626130104065,
"learning_rate": 4.07185628742515e-05,
"loss": 0.3312,
"step": 2230
},
{
"epoch": 2.424644549763033,
"grad_norm": 1.2923741340637207,
"learning_rate": 3.9970059880239525e-05,
"loss": 0.3347,
"step": 2240
},
{
"epoch": 2.435477318889641,
"grad_norm": 1.5063426494598389,
"learning_rate": 3.9221556886227544e-05,
"loss": 0.3455,
"step": 2250
},
{
"epoch": 2.446310088016249,
"grad_norm": 1.608620285987854,
"learning_rate": 3.847305389221557e-05,
"loss": 0.3507,
"step": 2260
},
{
"epoch": 2.4571428571428573,
"grad_norm": 1.3278478384017944,
"learning_rate": 3.7724550898203595e-05,
"loss": 0.3308,
"step": 2270
},
{
"epoch": 2.467975626269465,
"grad_norm": 0.9832974672317505,
"learning_rate": 3.697604790419162e-05,
"loss": 0.3349,
"step": 2280
},
{
"epoch": 2.478808395396073,
"grad_norm": 1.549773097038269,
"learning_rate": 3.6227544910179645e-05,
"loss": 0.3574,
"step": 2290
},
{
"epoch": 2.489641164522681,
"grad_norm": 1.3476412296295166,
"learning_rate": 3.5479041916167664e-05,
"loss": 0.3226,
"step": 2300
},
{
"epoch": 2.500473933649289,
"grad_norm": 1.3767112493515015,
"learning_rate": 3.473053892215569e-05,
"loss": 0.3651,
"step": 2310
},
{
"epoch": 2.5113067027758973,
"grad_norm": 1.1789909601211548,
"learning_rate": 3.3982035928143714e-05,
"loss": 0.3132,
"step": 2320
},
{
"epoch": 2.522139471902505,
"grad_norm": 1.262040376663208,
"learning_rate": 3.323353293413174e-05,
"loss": 0.3083,
"step": 2330
},
{
"epoch": 2.532972241029113,
"grad_norm": 1.381622552871704,
"learning_rate": 3.248502994011976e-05,
"loss": 0.3666,
"step": 2340
},
{
"epoch": 2.543805010155721,
"grad_norm": 1.4656392335891724,
"learning_rate": 3.1736526946107784e-05,
"loss": 0.3446,
"step": 2350
},
{
"epoch": 2.554637779282329,
"grad_norm": 1.1189512014389038,
"learning_rate": 3.098802395209581e-05,
"loss": 0.3318,
"step": 2360
},
{
"epoch": 2.5654705484089373,
"grad_norm": 1.595189094543457,
"learning_rate": 3.0239520958083834e-05,
"loss": 0.3481,
"step": 2370
},
{
"epoch": 2.5763033175355448,
"grad_norm": 1.0735886096954346,
"learning_rate": 2.949101796407186e-05,
"loss": 0.3698,
"step": 2380
},
{
"epoch": 2.587136086662153,
"grad_norm": 1.2776819467544556,
"learning_rate": 2.874251497005988e-05,
"loss": 0.3517,
"step": 2390
},
{
"epoch": 2.597968855788761,
"grad_norm": 1.514204740524292,
"learning_rate": 2.7994011976047907e-05,
"loss": 0.3443,
"step": 2400
},
{
"epoch": 2.608801624915369,
"grad_norm": 1.3794538974761963,
"learning_rate": 2.724550898203593e-05,
"loss": 0.3634,
"step": 2410
},
{
"epoch": 2.619634394041977,
"grad_norm": 1.6485087871551514,
"learning_rate": 2.6497005988023954e-05,
"loss": 0.3606,
"step": 2420
},
{
"epoch": 2.6304671631685848,
"grad_norm": 1.3901994228363037,
"learning_rate": 2.5748502994011976e-05,
"loss": 0.3398,
"step": 2430
},
{
"epoch": 2.641299932295193,
"grad_norm": 1.384027123451233,
"learning_rate": 2.5e-05,
"loss": 0.3635,
"step": 2440
},
{
"epoch": 2.652132701421801,
"grad_norm": 1.4652822017669678,
"learning_rate": 2.4251497005988023e-05,
"loss": 0.3739,
"step": 2450
},
{
"epoch": 2.662965470548409,
"grad_norm": 1.3109517097473145,
"learning_rate": 2.350299401197605e-05,
"loss": 0.3424,
"step": 2460
},
{
"epoch": 2.673798239675017,
"grad_norm": 1.518933892250061,
"learning_rate": 2.275449101796407e-05,
"loss": 0.3644,
"step": 2470
},
{
"epoch": 2.6846310088016248,
"grad_norm": 1.1910316944122314,
"learning_rate": 2.20059880239521e-05,
"loss": 0.3641,
"step": 2480
},
{
"epoch": 2.695463777928233,
"grad_norm": 1.5054243803024292,
"learning_rate": 2.125748502994012e-05,
"loss": 0.3235,
"step": 2490
},
{
"epoch": 2.706296547054841,
"grad_norm": 1.3502476215362549,
"learning_rate": 2.0508982035928146e-05,
"loss": 0.3184,
"step": 2500
},
{
"epoch": 2.706296547054841,
"eval_loss": 0.848840594291687,
"eval_runtime": 357.9885,
"eval_samples_per_second": 4.587,
"eval_steps_per_second": 2.293,
"step": 2500
},
{
"epoch": 2.717129316181449,
"grad_norm": 1.245007872581482,
"learning_rate": 1.9760479041916168e-05,
"loss": 0.3269,
"step": 2510
},
{
"epoch": 2.727962085308057,
"grad_norm": 1.43673574924469,
"learning_rate": 1.9011976047904194e-05,
"loss": 0.3447,
"step": 2520
},
{
"epoch": 2.7387948544346647,
"grad_norm": 1.5020848512649536,
"learning_rate": 1.8263473053892215e-05,
"loss": 0.3329,
"step": 2530
},
{
"epoch": 2.749627623561273,
"grad_norm": 1.483389139175415,
"learning_rate": 1.751497005988024e-05,
"loss": 0.3438,
"step": 2540
},
{
"epoch": 2.7604603926878806,
"grad_norm": 1.2835885286331177,
"learning_rate": 1.6766467065868263e-05,
"loss": 0.3259,
"step": 2550
},
{
"epoch": 2.771293161814489,
"grad_norm": 1.3246042728424072,
"learning_rate": 1.6017964071856288e-05,
"loss": 0.3409,
"step": 2560
},
{
"epoch": 2.782125930941097,
"grad_norm": 1.3244729042053223,
"learning_rate": 1.5269461077844313e-05,
"loss": 0.3044,
"step": 2570
},
{
"epoch": 2.7929587000677047,
"grad_norm": 1.3871108293533325,
"learning_rate": 1.4520958083832337e-05,
"loss": 0.3518,
"step": 2580
},
{
"epoch": 2.8037914691943127,
"grad_norm": 1.1578019857406616,
"learning_rate": 1.377245508982036e-05,
"loss": 0.3692,
"step": 2590
},
{
"epoch": 2.8146242383209206,
"grad_norm": 1.3286668062210083,
"learning_rate": 1.3023952095808384e-05,
"loss": 0.3326,
"step": 2600
},
{
"epoch": 2.825457007447529,
"grad_norm": 1.5447322130203247,
"learning_rate": 1.2275449101796408e-05,
"loss": 0.3555,
"step": 2610
},
{
"epoch": 2.836289776574137,
"grad_norm": 1.2768478393554688,
"learning_rate": 1.1526946107784433e-05,
"loss": 0.3502,
"step": 2620
},
{
"epoch": 2.8471225457007447,
"grad_norm": 1.2796357870101929,
"learning_rate": 1.0778443113772455e-05,
"loss": 0.3226,
"step": 2630
},
{
"epoch": 2.8579553148273527,
"grad_norm": 1.370597243309021,
"learning_rate": 1.0029940119760479e-05,
"loss": 0.3377,
"step": 2640
},
{
"epoch": 2.8687880839539606,
"grad_norm": 1.3650193214416504,
"learning_rate": 9.281437125748502e-06,
"loss": 0.3471,
"step": 2650
},
{
"epoch": 2.879620853080569,
"grad_norm": 1.3109257221221924,
"learning_rate": 8.532934131736528e-06,
"loss": 0.3133,
"step": 2660
},
{
"epoch": 2.890453622207177,
"grad_norm": 1.2204105854034424,
"learning_rate": 7.784431137724551e-06,
"loss": 0.319,
"step": 2670
},
{
"epoch": 2.9012863913337847,
"grad_norm": 1.1295379400253296,
"learning_rate": 7.035928143712575e-06,
"loss": 0.3297,
"step": 2680
},
{
"epoch": 2.9121191604603927,
"grad_norm": 1.130431890487671,
"learning_rate": 6.2874251497005985e-06,
"loss": 0.328,
"step": 2690
},
{
"epoch": 2.9229519295870006,
"grad_norm": 1.2526017427444458,
"learning_rate": 5.538922155688623e-06,
"loss": 0.3287,
"step": 2700
},
{
"epoch": 2.933784698713609,
"grad_norm": 1.4595975875854492,
"learning_rate": 4.7904191616766475e-06,
"loss": 0.3272,
"step": 2710
},
{
"epoch": 2.9446174678402164,
"grad_norm": 1.2819081544876099,
"learning_rate": 4.041916167664671e-06,
"loss": 0.3624,
"step": 2720
},
{
"epoch": 2.9554502369668247,
"grad_norm": 1.216588020324707,
"learning_rate": 3.293413173652695e-06,
"loss": 0.3416,
"step": 2730
},
{
"epoch": 2.9662830060934327,
"grad_norm": 1.3824045658111572,
"learning_rate": 2.5449101796407188e-06,
"loss": 0.3654,
"step": 2740
},
{
"epoch": 2.9771157752200406,
"grad_norm": 1.2501113414764404,
"learning_rate": 1.7964071856287426e-06,
"loss": 0.3443,
"step": 2750
},
{
"epoch": 2.9879485443466485,
"grad_norm": 1.1143591403961182,
"learning_rate": 1.0479041916167664e-06,
"loss": 0.3604,
"step": 2760
},
{
"epoch": 2.9987813134732564,
"grad_norm": 1.2795544862747192,
"learning_rate": 2.9940119760479047e-07,
"loss": 0.3251,
"step": 2770
}
],
"logging_steps": 10,
"max_steps": 2772,
"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": true
},
"attributes": {}
}
},
"total_flos": 9.746693219533455e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}