TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
smollm-350M-instruct-test2-noOH / trainer_state.json
loubnabnl's picture
loubnabnl HF staff
Model save
2b29917 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9993181043300376,
"eval_steps": 500,
"global_step": 1466,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0013637913399249914,
"grad_norm": 1.598020721574378,
"learning_rate": 6.8027210884353745e-06,
"loss": 1.3936,
"step": 1
},
{
"epoch": 0.006818956699624957,
"grad_norm": 1.582179170492486,
"learning_rate": 3.4013605442176877e-05,
"loss": 1.3732,
"step": 5
},
{
"epoch": 0.013637913399249914,
"grad_norm": 0.5247209097240487,
"learning_rate": 6.802721088435375e-05,
"loss": 1.3443,
"step": 10
},
{
"epoch": 0.020456870098874872,
"grad_norm": 0.8017522199019398,
"learning_rate": 0.00010204081632653062,
"loss": 1.2617,
"step": 15
},
{
"epoch": 0.02727582679849983,
"grad_norm": 0.4014040737926046,
"learning_rate": 0.0001360544217687075,
"loss": 1.1857,
"step": 20
},
{
"epoch": 0.03409478349812479,
"grad_norm": 0.32790437534680206,
"learning_rate": 0.00017006802721088434,
"loss": 1.1436,
"step": 25
},
{
"epoch": 0.040913740197749744,
"grad_norm": 0.2966698205141879,
"learning_rate": 0.00020408163265306123,
"loss": 1.0996,
"step": 30
},
{
"epoch": 0.0477326968973747,
"grad_norm": 0.17808447662676022,
"learning_rate": 0.0002380952380952381,
"loss": 1.0757,
"step": 35
},
{
"epoch": 0.05455165359699966,
"grad_norm": 0.14553030270593192,
"learning_rate": 0.000272108843537415,
"loss": 1.07,
"step": 40
},
{
"epoch": 0.06137061029662462,
"grad_norm": 0.12365194167763814,
"learning_rate": 0.0003061224489795919,
"loss": 1.0494,
"step": 45
},
{
"epoch": 0.06818956699624958,
"grad_norm": 0.19450168087415454,
"learning_rate": 0.0003401360544217687,
"loss": 1.0515,
"step": 50
},
{
"epoch": 0.07500852369587453,
"grad_norm": 0.1207148840427689,
"learning_rate": 0.0003741496598639456,
"loss": 1.0253,
"step": 55
},
{
"epoch": 0.08182748039549949,
"grad_norm": 0.10854420757501072,
"learning_rate": 0.00040816326530612246,
"loss": 1.0353,
"step": 60
},
{
"epoch": 0.08864643709512444,
"grad_norm": 0.16561709445658757,
"learning_rate": 0.0004421768707482993,
"loss": 1.0285,
"step": 65
},
{
"epoch": 0.0954653937947494,
"grad_norm": 0.524524123408497,
"learning_rate": 0.0004761904761904762,
"loss": 1.0379,
"step": 70
},
{
"epoch": 0.10228435049437436,
"grad_norm": 0.12853108179786138,
"learning_rate": 0.0005102040816326531,
"loss": 1.0186,
"step": 75
},
{
"epoch": 0.10910330719399931,
"grad_norm": 0.2734451972437396,
"learning_rate": 0.00054421768707483,
"loss": 1.0063,
"step": 80
},
{
"epoch": 0.11592226389362427,
"grad_norm": 0.14711225612929515,
"learning_rate": 0.0005782312925170068,
"loss": 1.0132,
"step": 85
},
{
"epoch": 0.12274122059324924,
"grad_norm": 0.11857109812836017,
"learning_rate": 0.0006122448979591838,
"loss": 1.0131,
"step": 90
},
{
"epoch": 0.1295601772928742,
"grad_norm": 0.16843211920179874,
"learning_rate": 0.0006462585034013606,
"loss": 0.9969,
"step": 95
},
{
"epoch": 0.13637913399249915,
"grad_norm": 0.15975057567245052,
"learning_rate": 0.0006802721088435374,
"loss": 0.9909,
"step": 100
},
{
"epoch": 0.1431980906921241,
"grad_norm": 0.15632985298714983,
"learning_rate": 0.0007142857142857143,
"loss": 0.9966,
"step": 105
},
{
"epoch": 0.15001704739174906,
"grad_norm": 0.1621684383980749,
"learning_rate": 0.0007482993197278912,
"loss": 0.9915,
"step": 110
},
{
"epoch": 0.15683600409137402,
"grad_norm": 0.12303095362829028,
"learning_rate": 0.000782312925170068,
"loss": 0.9787,
"step": 115
},
{
"epoch": 0.16365496079099898,
"grad_norm": 0.14599562372712946,
"learning_rate": 0.0008163265306122449,
"loss": 0.9882,
"step": 120
},
{
"epoch": 0.17047391749062393,
"grad_norm": 0.14693955034453152,
"learning_rate": 0.0008503401360544217,
"loss": 0.9801,
"step": 125
},
{
"epoch": 0.1772928741902489,
"grad_norm": 0.22554930118958344,
"learning_rate": 0.0008843537414965987,
"loss": 0.9767,
"step": 130
},
{
"epoch": 0.18411183088987385,
"grad_norm": 0.15209662483639966,
"learning_rate": 0.0009183673469387756,
"loss": 0.9827,
"step": 135
},
{
"epoch": 0.1909307875894988,
"grad_norm": 0.1338153825791751,
"learning_rate": 0.0009523809523809524,
"loss": 0.9725,
"step": 140
},
{
"epoch": 0.19774974428912376,
"grad_norm": 0.16873273473563985,
"learning_rate": 0.0009863945578231293,
"loss": 0.9747,
"step": 145
},
{
"epoch": 0.20456870098874871,
"grad_norm": 0.18631348995548455,
"learning_rate": 0.000999987235881584,
"loss": 0.9737,
"step": 150
},
{
"epoch": 0.21138765768837367,
"grad_norm": 0.1398209387998964,
"learning_rate": 0.0009999092352957284,
"loss": 0.9848,
"step": 155
},
{
"epoch": 0.21820661438799863,
"grad_norm": 0.13947559562857936,
"learning_rate": 0.0009997603363497414,
"loss": 0.9643,
"step": 160
},
{
"epoch": 0.22502557108762358,
"grad_norm": 0.14313053783616825,
"learning_rate": 0.000999540560160838,
"loss": 0.974,
"step": 165
},
{
"epoch": 0.23184452778724854,
"grad_norm": 0.13580380953886942,
"learning_rate": 0.0009992499378982194,
"loss": 0.9761,
"step": 170
},
{
"epoch": 0.2386634844868735,
"grad_norm": 0.14428497093865783,
"learning_rate": 0.0009988885107786517,
"loss": 0.9652,
"step": 175
},
{
"epoch": 0.24548244118649848,
"grad_norm": 0.12382971206501955,
"learning_rate": 0.0009984563300606192,
"loss": 0.9678,
"step": 180
},
{
"epoch": 0.25230139788612344,
"grad_norm": 0.14065780649342097,
"learning_rate": 0.0009979534570370575,
"loss": 0.969,
"step": 185
},
{
"epoch": 0.2591203545857484,
"grad_norm": 0.11357268655774008,
"learning_rate": 0.000997379963026658,
"loss": 0.9692,
"step": 190
},
{
"epoch": 0.26593931128537335,
"grad_norm": 0.1622202809625719,
"learning_rate": 0.0009967359293637553,
"loss": 0.9588,
"step": 195
},
{
"epoch": 0.2727582679849983,
"grad_norm": 0.1776637907272292,
"learning_rate": 0.0009960214473867907,
"loss": 0.9613,
"step": 200
},
{
"epoch": 0.27957722468462326,
"grad_norm": 0.1215741064620054,
"learning_rate": 0.0009952366184253602,
"loss": 0.963,
"step": 205
},
{
"epoch": 0.2863961813842482,
"grad_norm": 0.1302207261176898,
"learning_rate": 0.0009943815537858415,
"loss": 0.9551,
"step": 210
},
{
"epoch": 0.2932151380838732,
"grad_norm": 0.11682895510290592,
"learning_rate": 0.00099345637473561,
"loss": 0.9598,
"step": 215
},
{
"epoch": 0.30003409478349813,
"grad_norm": 0.15188852916347045,
"learning_rate": 0.0009924612124858389,
"loss": 0.9583,
"step": 220
},
{
"epoch": 0.3068530514831231,
"grad_norm": 0.13240495035670563,
"learning_rate": 0.0009913962081728918,
"loss": 0.9538,
"step": 225
},
{
"epoch": 0.31367200818274804,
"grad_norm": 0.16120589037533914,
"learning_rate": 0.0009902615128383062,
"loss": 0.9464,
"step": 230
},
{
"epoch": 0.320490964882373,
"grad_norm": 0.1382061477313828,
"learning_rate": 0.0009890572874073713,
"loss": 0.9434,
"step": 235
},
{
"epoch": 0.32730992158199795,
"grad_norm": 0.11549986617558586,
"learning_rate": 0.0009877837026663068,
"loss": 0.9441,
"step": 240
},
{
"epoch": 0.3341288782816229,
"grad_norm": 0.10980499757109458,
"learning_rate": 0.00098644093923804,
"loss": 0.96,
"step": 245
},
{
"epoch": 0.34094783498124787,
"grad_norm": 0.19062656435818273,
"learning_rate": 0.0009850291875565908,
"loss": 0.9577,
"step": 250
},
{
"epoch": 0.3477667916808728,
"grad_norm": 0.12141161965377588,
"learning_rate": 0.0009835486478400625,
"loss": 0.9456,
"step": 255
},
{
"epoch": 0.3545857483804978,
"grad_norm": 0.11932394138168441,
"learning_rate": 0.000981999530062248,
"loss": 0.9546,
"step": 260
},
{
"epoch": 0.36140470508012273,
"grad_norm": 0.1277558444188088,
"learning_rate": 0.0009803820539228492,
"loss": 0.9375,
"step": 265
},
{
"epoch": 0.3682236617797477,
"grad_norm": 0.11354346745136285,
"learning_rate": 0.0009786964488163194,
"loss": 0.9473,
"step": 270
},
{
"epoch": 0.37504261847937265,
"grad_norm": 0.10871503403228854,
"learning_rate": 0.000976942953799331,
"loss": 0.9321,
"step": 275
},
{
"epoch": 0.3818615751789976,
"grad_norm": 0.14107095714136358,
"learning_rate": 0.0009751218175568688,
"loss": 0.9346,
"step": 280
},
{
"epoch": 0.38868053187862256,
"grad_norm": 0.11468378232954199,
"learning_rate": 0.0009732332983669651,
"loss": 0.9333,
"step": 285
},
{
"epoch": 0.3954994885782475,
"grad_norm": 0.11614073571579422,
"learning_rate": 0.0009712776640640671,
"loss": 0.933,
"step": 290
},
{
"epoch": 0.40231844527787247,
"grad_norm": 0.14233058701254916,
"learning_rate": 0.0009692551920010519,
"loss": 0.9365,
"step": 295
},
{
"epoch": 0.40913740197749743,
"grad_norm": 0.16365059288233255,
"learning_rate": 0.0009671661690098941,
"loss": 0.9345,
"step": 300
},
{
"epoch": 0.4159563586771224,
"grad_norm": 0.2778458797011963,
"learning_rate": 0.0009650108913609837,
"loss": 0.9243,
"step": 305
},
{
"epoch": 0.42277531537674734,
"grad_norm": 0.12497969488106986,
"learning_rate": 0.0009627896647211103,
"loss": 0.915,
"step": 310
},
{
"epoch": 0.4295942720763723,
"grad_norm": 0.12132320992585822,
"learning_rate": 0.0009605028041101116,
"loss": 0.9306,
"step": 315
},
{
"epoch": 0.43641322877599725,
"grad_norm": 0.15422956629129714,
"learning_rate": 0.0009581506338561974,
"loss": 0.9229,
"step": 320
},
{
"epoch": 0.4432321854756222,
"grad_norm": 0.10857379661878619,
"learning_rate": 0.0009557334875499513,
"loss": 0.9295,
"step": 325
},
{
"epoch": 0.45005114217524717,
"grad_norm": 0.09700456702304185,
"learning_rate": 0.0009532517079970214,
"loss": 0.9144,
"step": 330
},
{
"epoch": 0.4568700988748721,
"grad_norm": 0.1574301623396698,
"learning_rate": 0.000950705647169502,
"loss": 0.9303,
"step": 335
},
{
"epoch": 0.4636890555744971,
"grad_norm": 0.12653500024100792,
"learning_rate": 0.000948095666156016,
"loss": 0.9145,
"step": 340
},
{
"epoch": 0.47050801227412203,
"grad_norm": 0.12348356194845742,
"learning_rate": 0.0009454221351105055,
"loss": 0.9115,
"step": 345
},
{
"epoch": 0.477326968973747,
"grad_norm": 0.1307740739484115,
"learning_rate": 0.0009426854331997334,
"loss": 0.9188,
"step": 350
},
{
"epoch": 0.484145925673372,
"grad_norm": 0.10835447562048035,
"learning_rate": 0.0009398859485495119,
"loss": 0.9247,
"step": 355
},
{
"epoch": 0.49096488237299696,
"grad_norm": 0.11863788647430744,
"learning_rate": 0.0009370240781896553,
"loss": 0.9102,
"step": 360
},
{
"epoch": 0.4977838390726219,
"grad_norm": 0.14783785955650325,
"learning_rate": 0.0009341002279976728,
"loss": 0.9136,
"step": 365
},
{
"epoch": 0.5046027957722469,
"grad_norm": 0.11185935178347504,
"learning_rate": 0.0009311148126412067,
"loss": 0.9108,
"step": 370
},
{
"epoch": 0.5114217524718718,
"grad_norm": 0.11360824911697796,
"learning_rate": 0.0009280682555192229,
"loss": 0.9167,
"step": 375
},
{
"epoch": 0.5182407091714968,
"grad_norm": 0.10219440421235579,
"learning_rate": 0.0009249609887019624,
"loss": 0.9125,
"step": 380
},
{
"epoch": 0.5250596658711217,
"grad_norm": 0.1063437764241102,
"learning_rate": 0.0009217934528696652,
"loss": 0.9135,
"step": 385
},
{
"epoch": 0.5318786225707467,
"grad_norm": 0.12924256438154388,
"learning_rate": 0.000918566097250072,
"loss": 0.9044,
"step": 390
},
{
"epoch": 0.5386975792703717,
"grad_norm": 0.1672822885194737,
"learning_rate": 0.0009152793795547129,
"loss": 0.905,
"step": 395
},
{
"epoch": 0.5455165359699966,
"grad_norm": 0.18170913356641202,
"learning_rate": 0.0009119337659139939,
"loss": 0.9077,
"step": 400
},
{
"epoch": 0.5523354926696216,
"grad_norm": 0.14583299571955888,
"learning_rate": 0.0009085297308110889,
"loss": 0.9013,
"step": 405
},
{
"epoch": 0.5591544493692465,
"grad_norm": 0.1328861894472585,
"learning_rate": 0.0009050677570146482,
"loss": 0.8972,
"step": 410
},
{
"epoch": 0.5659734060688715,
"grad_norm": 0.12732498687417756,
"learning_rate": 0.0009015483355103298,
"loss": 0.8948,
"step": 415
},
{
"epoch": 0.5727923627684964,
"grad_norm": 0.10225924635313659,
"learning_rate": 0.0008979719654311677,
"loss": 0.8977,
"step": 420
},
{
"epoch": 0.5796113194681214,
"grad_norm": 0.11222734733135577,
"learning_rate": 0.0008943391539867831,
"loss": 0.9086,
"step": 425
},
{
"epoch": 0.5864302761677463,
"grad_norm": 0.10007024319396716,
"learning_rate": 0.0008906504163914506,
"loss": 0.9047,
"step": 430
},
{
"epoch": 0.5932492328673713,
"grad_norm": 0.11019466700605089,
"learning_rate": 0.0008869062757910296,
"loss": 0.8998,
"step": 435
},
{
"epoch": 0.6000681895669963,
"grad_norm": 0.12131434093089721,
"learning_rate": 0.00088310726318877,
"loss": 0.9073,
"step": 440
},
{
"epoch": 0.6068871462666212,
"grad_norm": 0.09939916214847802,
"learning_rate": 0.0008792539173700046,
"loss": 0.9056,
"step": 445
},
{
"epoch": 0.6137061029662462,
"grad_norm": 0.11240353319322192,
"learning_rate": 0.0008753467848257366,
"loss": 0.9023,
"step": 450
},
{
"epoch": 0.6205250596658711,
"grad_norm": 0.12884203346821665,
"learning_rate": 0.0008713864196751353,
"loss": 0.891,
"step": 455
},
{
"epoch": 0.6273440163654961,
"grad_norm": 0.13107538778471978,
"learning_rate": 0.0008673733835869496,
"loss": 0.9053,
"step": 460
},
{
"epoch": 0.634162973065121,
"grad_norm": 0.1265128902066715,
"learning_rate": 0.0008633082456998505,
"loss": 0.8765,
"step": 465
},
{
"epoch": 0.640981929764746,
"grad_norm": 0.11168557466408092,
"learning_rate": 0.0008591915825417144,
"loss": 0.8937,
"step": 470
},
{
"epoch": 0.647800886464371,
"grad_norm": 0.10749488343940884,
"learning_rate": 0.0008550239779478592,
"loss": 0.8936,
"step": 475
},
{
"epoch": 0.6546198431639959,
"grad_norm": 0.12116636988129866,
"learning_rate": 0.0008508060229782422,
"loss": 0.8985,
"step": 480
},
{
"epoch": 0.6614387998636209,
"grad_norm": 0.11248409191993927,
"learning_rate": 0.0008465383158336352,
"loss": 0.9068,
"step": 485
},
{
"epoch": 0.6682577565632458,
"grad_norm": 0.09616110942207395,
"learning_rate": 0.0008422214617707864,
"loss": 0.893,
"step": 490
},
{
"epoch": 0.6750767132628708,
"grad_norm": 0.10944978412158525,
"learning_rate": 0.000837856073016581,
"loss": 0.9015,
"step": 495
},
{
"epoch": 0.6818956699624957,
"grad_norm": 0.12373353259009305,
"learning_rate": 0.0008334427686812137,
"loss": 0.8805,
"step": 500
},
{
"epoch": 0.6887146266621207,
"grad_norm": 0.10998182720982563,
"learning_rate": 0.000828982174670385,
"loss": 0.8764,
"step": 505
},
{
"epoch": 0.6955335833617456,
"grad_norm": 0.11981879919775634,
"learning_rate": 0.0008244749235965338,
"loss": 0.8972,
"step": 510
},
{
"epoch": 0.7023525400613706,
"grad_norm": 0.11009515701872061,
"learning_rate": 0.000819921654689119,
"loss": 0.883,
"step": 515
},
{
"epoch": 0.7091714967609956,
"grad_norm": 0.1206592530642094,
"learning_rate": 0.0008153230137039615,
"loss": 0.8887,
"step": 520
},
{
"epoch": 0.7159904534606205,
"grad_norm": 0.10679229804484212,
"learning_rate": 0.0008106796528316626,
"loss": 0.8894,
"step": 525
},
{
"epoch": 0.7228094101602455,
"grad_norm": 0.11030470444996518,
"learning_rate": 0.000805992230605108,
"loss": 0.8881,
"step": 530
},
{
"epoch": 0.7296283668598704,
"grad_norm": 0.14989020257644473,
"learning_rate": 0.0008012614118060733,
"loss": 0.8758,
"step": 535
},
{
"epoch": 0.7364473235594954,
"grad_norm": 0.19608291727965096,
"learning_rate": 0.0007964878673709432,
"loss": 0.873,
"step": 540
},
{
"epoch": 0.7432662802591203,
"grad_norm": 0.1357305661381077,
"learning_rate": 0.0007916722742955573,
"loss": 0.878,
"step": 545
},
{
"epoch": 0.7500852369587453,
"grad_norm": 0.09279906563803725,
"learning_rate": 0.0007868153155391968,
"loss": 0.8844,
"step": 550
},
{
"epoch": 0.7569041936583703,
"grad_norm": 0.1003975725083102,
"learning_rate": 0.0007819176799277262,
"loss": 0.8875,
"step": 555
},
{
"epoch": 0.7637231503579952,
"grad_norm": 0.09978871199012411,
"learning_rate": 0.0007769800620559015,
"loss": 0.8866,
"step": 560
},
{
"epoch": 0.7705421070576202,
"grad_norm": 0.13532770031312716,
"learning_rate": 0.0007720031621888615,
"loss": 0.879,
"step": 565
},
{
"epoch": 0.7773610637572451,
"grad_norm": 0.10118664495666357,
"learning_rate": 0.0007669876861628144,
"loss": 0.87,
"step": 570
},
{
"epoch": 0.7841800204568701,
"grad_norm": 0.09994831940420743,
"learning_rate": 0.0007619343452849349,
"loss": 0.8759,
"step": 575
},
{
"epoch": 0.790998977156495,
"grad_norm": 0.12994411471721243,
"learning_rate": 0.0007568438562324833,
"loss": 0.8783,
"step": 580
},
{
"epoch": 0.79781793385612,
"grad_norm": 0.1169831966799223,
"learning_rate": 0.0007517169409511664,
"loss": 0.8672,
"step": 585
},
{
"epoch": 0.8046368905557449,
"grad_norm": 0.10141671278849922,
"learning_rate": 0.0007465543265527482,
"loss": 0.8695,
"step": 590
},
{
"epoch": 0.8114558472553699,
"grad_norm": 0.11783176873723326,
"learning_rate": 0.0007413567452119298,
"loss": 0.8689,
"step": 595
},
{
"epoch": 0.8182748039549949,
"grad_norm": 0.12718960852527547,
"learning_rate": 0.00073612493406251,
"loss": 0.8708,
"step": 600
},
{
"epoch": 0.8250937606546198,
"grad_norm": 0.12649370297868867,
"learning_rate": 0.0007308596350928434,
"loss": 0.8759,
"step": 605
},
{
"epoch": 0.8319127173542448,
"grad_norm": 0.1009142565676403,
"learning_rate": 0.0007255615950406102,
"loss": 0.862,
"step": 610
},
{
"epoch": 0.8387316740538697,
"grad_norm": 0.10490423262148889,
"learning_rate": 0.0007202315652869112,
"loss": 0.87,
"step": 615
},
{
"epoch": 0.8455506307534947,
"grad_norm": 0.09903668718402683,
"learning_rate": 0.0007148703017497058,
"loss": 0.8705,
"step": 620
},
{
"epoch": 0.8523695874531196,
"grad_norm": 0.14442585966687965,
"learning_rate": 0.0007094785647766055,
"loss": 0.8681,
"step": 625
},
{
"epoch": 0.8591885441527446,
"grad_norm": 0.16498073796059864,
"learning_rate": 0.0007040571190370397,
"loss": 0.8656,
"step": 630
},
{
"epoch": 0.8660075008523695,
"grad_norm": 0.1129999366359928,
"learning_rate": 0.0006986067334138079,
"loss": 0.8686,
"step": 635
},
{
"epoch": 0.8728264575519945,
"grad_norm": 0.09929311073474267,
"learning_rate": 0.0006931281808940361,
"loss": 0.8687,
"step": 640
},
{
"epoch": 0.8796454142516195,
"grad_norm": 0.11972041401629113,
"learning_rate": 0.0006876222384595477,
"loss": 0.8652,
"step": 645
},
{
"epoch": 0.8864643709512444,
"grad_norm": 0.09934940714328987,
"learning_rate": 0.0006820896869766725,
"loss": 0.8709,
"step": 650
},
{
"epoch": 0.8932833276508694,
"grad_norm": 0.10973507676224258,
"learning_rate": 0.0006765313110855009,
"loss": 0.8652,
"step": 655
},
{
"epoch": 0.9001022843504943,
"grad_norm": 0.09165992876326395,
"learning_rate": 0.0006709478990886039,
"loss": 0.8611,
"step": 660
},
{
"epoch": 0.9069212410501193,
"grad_norm": 0.09988220618681196,
"learning_rate": 0.0006653402428392354,
"loss": 0.8556,
"step": 665
},
{
"epoch": 0.9137401977497442,
"grad_norm": 0.09446350263562757,
"learning_rate": 0.0006597091376290288,
"loss": 0.8528,
"step": 670
},
{
"epoch": 0.9205591544493692,
"grad_norm": 0.08902820350532409,
"learning_rate": 0.0006540553820752069,
"loss": 0.8609,
"step": 675
},
{
"epoch": 0.9273781111489942,
"grad_norm": 0.10011816954581992,
"learning_rate": 0.00064837977800732,
"loss": 0.8625,
"step": 680
},
{
"epoch": 0.9341970678486191,
"grad_norm": 0.08775726631732685,
"learning_rate": 0.0006426831303535284,
"loss": 0.8576,
"step": 685
},
{
"epoch": 0.9410160245482441,
"grad_norm": 0.11117730920395297,
"learning_rate": 0.0006369662470264462,
"loss": 0.8704,
"step": 690
},
{
"epoch": 0.947834981247869,
"grad_norm": 0.139154974071725,
"learning_rate": 0.0006312299388085596,
"loss": 0.8584,
"step": 695
},
{
"epoch": 0.954653937947494,
"grad_norm": 0.10346972946518294,
"learning_rate": 0.0006254750192372418,
"loss": 0.8709,
"step": 700
},
{
"epoch": 0.9614728946471189,
"grad_norm": 0.09900042387283375,
"learning_rate": 0.0006197023044893734,
"loss": 0.8482,
"step": 705
},
{
"epoch": 0.968291851346744,
"grad_norm": 0.09908280186750126,
"learning_rate": 0.0006139126132655905,
"loss": 0.8597,
"step": 710
},
{
"epoch": 0.975110808046369,
"grad_norm": 0.13127044402154367,
"learning_rate": 0.0006081067666741757,
"loss": 0.8483,
"step": 715
},
{
"epoch": 0.9819297647459939,
"grad_norm": 0.09623829465725477,
"learning_rate": 0.0006022855881146053,
"loss": 0.8589,
"step": 720
},
{
"epoch": 0.9887487214456189,
"grad_norm": 0.09762948252187646,
"learning_rate": 0.0005964499031607727,
"loss": 0.8479,
"step": 725
},
{
"epoch": 0.9955676781452438,
"grad_norm": 0.11109345413298818,
"learning_rate": 0.0005906005394439044,
"loss": 0.8625,
"step": 730
},
{
"epoch": 0.9996590521650187,
"eval_loss": 0.8650394678115845,
"eval_runtime": 60.297,
"eval_samples_per_second": 184.404,
"eval_steps_per_second": 5.771,
"step": 733
},
{
"epoch": 1.0023866348448687,
"grad_norm": 0.150003136868036,
"learning_rate": 0.0005847383265351828,
"loss": 0.8218,
"step": 735
},
{
"epoch": 1.0092055915444937,
"grad_norm": 0.1668337683466409,
"learning_rate": 0.0005788640958280941,
"loss": 0.7516,
"step": 740
},
{
"epoch": 1.0160245482441186,
"grad_norm": 0.14142825658305677,
"learning_rate": 0.0005729786804205181,
"loss": 0.7548,
"step": 745
},
{
"epoch": 1.0228435049437437,
"grad_norm": 0.12528810569521878,
"learning_rate": 0.0005670829149965773,
"loss": 0.7473,
"step": 750
},
{
"epoch": 1.0296624616433685,
"grad_norm": 0.11736651721866655,
"learning_rate": 0.0005611776357082579,
"loss": 0.747,
"step": 755
},
{
"epoch": 1.0364814183429936,
"grad_norm": 0.09403020504249461,
"learning_rate": 0.0005552636800568266,
"loss": 0.7621,
"step": 760
},
{
"epoch": 1.0433003750426184,
"grad_norm": 0.11315198038951943,
"learning_rate": 0.0005493418867740529,
"loss": 0.745,
"step": 765
},
{
"epoch": 1.0501193317422435,
"grad_norm": 0.1022560757959738,
"learning_rate": 0.0005434130957032589,
"loss": 0.7459,
"step": 770
},
{
"epoch": 1.0569382884418683,
"grad_norm": 0.10922375995449658,
"learning_rate": 0.0005374781476802096,
"loss": 0.7466,
"step": 775
},
{
"epoch": 1.0637572451414934,
"grad_norm": 0.5193070680732547,
"learning_rate": 0.0005315378844138647,
"loss": 0.7627,
"step": 780
},
{
"epoch": 1.0705762018411182,
"grad_norm": 0.12177144687559627,
"learning_rate": 0.0005255931483670049,
"loss": 0.7546,
"step": 785
},
{
"epoch": 1.0773951585407433,
"grad_norm": 0.7694014802591276,
"learning_rate": 0.000519644782636751,
"loss": 0.7528,
"step": 790
},
{
"epoch": 1.0842141152403681,
"grad_norm": 0.11357197300498553,
"learning_rate": 0.000513693630834995,
"loss": 0.7533,
"step": 795
},
{
"epoch": 1.0910330719399932,
"grad_norm": 0.09386251189985013,
"learning_rate": 0.0005077405369687564,
"loss": 0.7542,
"step": 800
},
{
"epoch": 1.097852028639618,
"grad_norm": 0.09656492984059917,
"learning_rate": 0.0005017863453204828,
"loss": 0.7453,
"step": 805
},
{
"epoch": 1.1046709853392431,
"grad_norm": 0.09988629196548339,
"learning_rate": 0.0004958319003283121,
"loss": 0.7567,
"step": 810
},
{
"epoch": 1.111489942038868,
"grad_norm": 0.1340291294865019,
"learning_rate": 0.0004898780464663119,
"loss": 0.7572,
"step": 815
},
{
"epoch": 1.118308898738493,
"grad_norm": 0.12216818040509048,
"learning_rate": 0.00048392562812471485,
"loss": 0.7386,
"step": 820
},
{
"epoch": 1.1251278554381179,
"grad_norm": 0.10511324731067179,
"learning_rate": 0.0004779754894901638,
"loss": 0.7551,
"step": 825
},
{
"epoch": 1.131946812137743,
"grad_norm": 0.08878475250721538,
"learning_rate": 0.00047202847442598845,
"loss": 0.7476,
"step": 830
},
{
"epoch": 1.1387657688373678,
"grad_norm": 0.10961153167460981,
"learning_rate": 0.0004660854263525255,
"loss": 0.7501,
"step": 835
},
{
"epoch": 1.1455847255369929,
"grad_norm": 0.11227235770228143,
"learning_rate": 0.0004601471881275041,
"loss": 0.7468,
"step": 840
},
{
"epoch": 1.1524036822366177,
"grad_norm": 0.14319195588727593,
"learning_rate": 0.00045421460192650786,
"loss": 0.7459,
"step": 845
},
{
"epoch": 1.1592226389362428,
"grad_norm": 0.12581674820255845,
"learning_rate": 0.00044828850912353703,
"loss": 0.7496,
"step": 850
},
{
"epoch": 1.1660415956358676,
"grad_norm": 0.10879564209007402,
"learning_rate": 0.0004423697501716823,
"loss": 0.7377,
"step": 855
},
{
"epoch": 1.1728605523354927,
"grad_norm": 0.10910700864864685,
"learning_rate": 0.00043645916448392885,
"loss": 0.7569,
"step": 860
},
{
"epoch": 1.1796795090351175,
"grad_norm": 0.12233584779335835,
"learning_rate": 0.00043055759031411007,
"loss": 0.7451,
"step": 865
},
{
"epoch": 1.1864984657347426,
"grad_norm": 0.09336996907684925,
"learning_rate": 0.0004246658646380229,
"loss": 0.7486,
"step": 870
},
{
"epoch": 1.1933174224343674,
"grad_norm": 0.09297895821672336,
"learning_rate": 0.00041878482303472745,
"loss": 0.7522,
"step": 875
},
{
"epoch": 1.2001363791339925,
"grad_norm": 0.09998221831882348,
"learning_rate": 0.00041291529956804195,
"loss": 0.756,
"step": 880
},
{
"epoch": 1.2069553358336174,
"grad_norm": 0.09246595578930603,
"learning_rate": 0.0004070581266682539,
"loss": 0.7564,
"step": 885
},
{
"epoch": 1.2137742925332424,
"grad_norm": 0.09888677663554202,
"learning_rate": 0.000401214135014063,
"loss": 0.7406,
"step": 890
},
{
"epoch": 1.2205932492328673,
"grad_norm": 0.09840879351277865,
"learning_rate": 0.0003953841534147725,
"loss": 0.7444,
"step": 895
},
{
"epoch": 1.2274122059324923,
"grad_norm": 0.09608186181313223,
"learning_rate": 0.000389569008692745,
"loss": 0.7434,
"step": 900
},
{
"epoch": 1.2342311626321174,
"grad_norm": 0.12027155555266326,
"learning_rate": 0.0003837695255661403,
"loss": 0.7505,
"step": 905
},
{
"epoch": 1.2410501193317423,
"grad_norm": 0.09938398385533825,
"learning_rate": 0.00037798652653195266,
"loss": 0.7524,
"step": 910
},
{
"epoch": 1.247869076031367,
"grad_norm": 0.0963922155626505,
"learning_rate": 0.00037222083174936137,
"loss": 0.7481,
"step": 915
},
{
"epoch": 1.2546880327309922,
"grad_norm": 0.0959346234671189,
"learning_rate": 0.00036647325892341393,
"loss": 0.7398,
"step": 920
},
{
"epoch": 1.2615069894306172,
"grad_norm": 0.08820345622198668,
"learning_rate": 0.0003607446231890575,
"loss": 0.7405,
"step": 925
},
{
"epoch": 1.268325946130242,
"grad_norm": 0.11589956732636802,
"learning_rate": 0.0003550357369955347,
"loss": 0.7509,
"step": 930
},
{
"epoch": 1.275144902829867,
"grad_norm": 0.10547612256066802,
"learning_rate": 0.00034934740999115866,
"loss": 0.7502,
"step": 935
},
{
"epoch": 1.281963859529492,
"grad_norm": 0.11823191257134831,
"learning_rate": 0.00034368044890848814,
"loss": 0.7661,
"step": 940
},
{
"epoch": 1.288782816229117,
"grad_norm": 0.09346920096074791,
"learning_rate": 0.0003380356574499141,
"loss": 0.7409,
"step": 945
},
{
"epoch": 1.295601772928742,
"grad_norm": 0.09247106405202875,
"learning_rate": 0.00033241383617367706,
"loss": 0.7448,
"step": 950
},
{
"epoch": 1.3024207296283667,
"grad_norm": 0.10126097744075767,
"learning_rate": 0.00032681578238032914,
"loss": 0.7455,
"step": 955
},
{
"epoch": 1.3092396863279918,
"grad_norm": 0.10957664402150283,
"learning_rate": 0.0003212422899996599,
"loss": 0.7442,
"step": 960
},
{
"epoch": 1.3160586430276169,
"grad_norm": 0.08997598908036177,
"learning_rate": 0.0003156941494780983,
"loss": 0.7399,
"step": 965
},
{
"epoch": 1.3228775997272417,
"grad_norm": 0.09339106504051306,
"learning_rate": 0.0003101721476666106,
"loss": 0.7473,
"step": 970
},
{
"epoch": 1.3296965564268666,
"grad_norm": 0.09094074237158431,
"learning_rate": 0.00030467706770910687,
"loss": 0.7349,
"step": 975
},
{
"epoch": 1.3365155131264916,
"grad_norm": 0.08949096519435662,
"learning_rate": 0.00029920968893137277,
"loss": 0.7335,
"step": 980
},
{
"epoch": 1.3433344698261167,
"grad_norm": 0.10666408169466289,
"learning_rate": 0.00029377078673054524,
"loss": 0.7431,
"step": 985
},
{
"epoch": 1.3501534265257416,
"grad_norm": 0.09360456030533196,
"learning_rate": 0.00028836113246514215,
"loss": 0.7504,
"step": 990
},
{
"epoch": 1.3569723832253664,
"grad_norm": 0.0857322076398207,
"learning_rate": 0.00028298149334566745,
"loss": 0.7461,
"step": 995
},
{
"epoch": 1.3637913399249915,
"grad_norm": 0.08664863370331233,
"learning_rate": 0.0002776326323258029,
"loss": 0.7347,
"step": 1000
},
{
"epoch": 1.3706102966246165,
"grad_norm": 0.09553160941014031,
"learning_rate": 0.0002723153079942047,
"loss": 0.7432,
"step": 1005
},
{
"epoch": 1.3774292533242414,
"grad_norm": 0.09757917450665214,
"learning_rate": 0.00026703027446691753,
"loss": 0.7319,
"step": 1010
},
{
"epoch": 1.3842482100238662,
"grad_norm": 0.13001681090880932,
"learning_rate": 0.0002617782812804252,
"loss": 0.731,
"step": 1015
},
{
"epoch": 1.3910671667234913,
"grad_norm": 0.09842205689754281,
"learning_rate": 0.00025656007328534857,
"loss": 0.7377,
"step": 1020
},
{
"epoch": 1.3978861234231164,
"grad_norm": 0.08966471368100484,
"learning_rate": 0.00025137639054080975,
"loss": 0.7393,
"step": 1025
},
{
"epoch": 1.4047050801227412,
"grad_norm": 0.09544505949561016,
"learning_rate": 0.0002462279682094742,
"loss": 0.7448,
"step": 1030
},
{
"epoch": 1.411524036822366,
"grad_norm": 0.09721892448809809,
"learning_rate": 0.00024111553645328872,
"loss": 0.7383,
"step": 1035
},
{
"epoch": 1.4183429935219911,
"grad_norm": 0.09528944859478844,
"learning_rate": 0.00023603982032992861,
"loss": 0.743,
"step": 1040
},
{
"epoch": 1.4251619502216162,
"grad_norm": 0.09295756990644403,
"learning_rate": 0.00023100153968996678,
"loss": 0.7354,
"step": 1045
},
{
"epoch": 1.431980906921241,
"grad_norm": 0.09085933894422743,
"learning_rate": 0.0002260014090747845,
"loss": 0.7363,
"step": 1050
},
{
"epoch": 1.4387998636208659,
"grad_norm": 0.09685032026741523,
"learning_rate": 0.00022104013761523156,
"loss": 0.7457,
"step": 1055
},
{
"epoch": 1.445618820320491,
"grad_norm": 0.08857516230100924,
"learning_rate": 0.00021611842893105726,
"loss": 0.742,
"step": 1060
},
{
"epoch": 1.452437777020116,
"grad_norm": 0.08773056464470375,
"learning_rate": 0.0002112369810311201,
"loss": 0.7332,
"step": 1065
},
{
"epoch": 1.4592567337197409,
"grad_norm": 0.0900763405573559,
"learning_rate": 0.00020639648621439488,
"loss": 0.7449,
"step": 1070
},
{
"epoch": 1.466075690419366,
"grad_norm": 0.09851993938416971,
"learning_rate": 0.00020159763097178952,
"loss": 0.7402,
"step": 1075
},
{
"epoch": 1.4728946471189908,
"grad_norm": 0.08759892676999576,
"learning_rate": 0.0001968410958887849,
"loss": 0.7445,
"step": 1080
},
{
"epoch": 1.4797136038186158,
"grad_norm": 0.0907347079072196,
"learning_rate": 0.0001921275555489122,
"loss": 0.7399,
"step": 1085
},
{
"epoch": 1.4865325605182407,
"grad_norm": 0.08112607532285956,
"learning_rate": 0.00018745767843808209,
"loss": 0.7304,
"step": 1090
},
{
"epoch": 1.4933515172178657,
"grad_norm": 0.09161753107862378,
"learning_rate": 0.000182832126849779,
"loss": 0.7285,
"step": 1095
},
{
"epoch": 1.5001704739174906,
"grad_norm": 0.08358605650538908,
"learning_rate": 0.00017825155679113204,
"loss": 0.7348,
"step": 1100
},
{
"epoch": 1.5069894306171157,
"grad_norm": 0.08675686822052969,
"learning_rate": 0.00017371661788987875,
"loss": 0.7409,
"step": 1105
},
{
"epoch": 1.5138083873167405,
"grad_norm": 0.08810226317282835,
"learning_rate": 0.0001692279533022339,
"loss": 0.7384,
"step": 1110
},
{
"epoch": 1.5206273440163653,
"grad_norm": 0.08950130348184156,
"learning_rate": 0.00016478619962167495,
"loss": 0.7492,
"step": 1115
},
{
"epoch": 1.5274463007159904,
"grad_norm": 0.08034358957544274,
"learning_rate": 0.00016039198678865861,
"loss": 0.7332,
"step": 1120
},
{
"epoch": 1.5342652574156155,
"grad_norm": 0.09875564116278145,
"learning_rate": 0.00015604593800128157,
"loss": 0.7245,
"step": 1125
},
{
"epoch": 1.5410842141152403,
"grad_norm": 0.08654215732134887,
"learning_rate": 0.00015174866962689655,
"loss": 0.735,
"step": 1130
},
{
"epoch": 1.5479031708148652,
"grad_norm": 0.08592984519220763,
"learning_rate": 0.00014750079111469844,
"loss": 0.7409,
"step": 1135
},
{
"epoch": 1.5547221275144902,
"grad_norm": 0.09146622488124098,
"learning_rate": 0.00014330290490928936,
"loss": 0.7307,
"step": 1140
},
{
"epoch": 1.5615410842141153,
"grad_norm": 0.09107009139517197,
"learning_rate": 0.00013915560636524005,
"loss": 0.7298,
"step": 1145
},
{
"epoch": 1.5683600409137401,
"grad_norm": 0.08290920543587224,
"learning_rate": 0.0001350594836626537,
"loss": 0.7288,
"step": 1150
},
{
"epoch": 1.575178997613365,
"grad_norm": 0.089017743866575,
"learning_rate": 0.00013101511772375002,
"loss": 0.721,
"step": 1155
},
{
"epoch": 1.58199795431299,
"grad_norm": 0.08395496088906577,
"learning_rate": 0.00012702308213047653,
"loss": 0.7369,
"step": 1160
},
{
"epoch": 1.5888169110126151,
"grad_norm": 0.09332825258379267,
"learning_rate": 0.00012308394304316224,
"loss": 0.7331,
"step": 1165
},
{
"epoch": 1.59563586771224,
"grad_norm": 0.08663551849922511,
"learning_rate": 0.00011919825912022336,
"loss": 0.7284,
"step": 1170
},
{
"epoch": 1.6024548244118648,
"grad_norm": 0.08467643435872389,
"learning_rate": 0.00011536658143893309,
"loss": 0.73,
"step": 1175
},
{
"epoch": 1.6092737811114899,
"grad_norm": 0.10792296188935317,
"learning_rate": 0.0001115894534172659,
"loss": 0.7304,
"step": 1180
},
{
"epoch": 1.616092737811115,
"grad_norm": 0.08665506882217053,
"learning_rate": 0.0001078674107368291,
"loss": 0.7365,
"step": 1185
},
{
"epoch": 1.6229116945107398,
"grad_norm": 0.0869258591144236,
"learning_rate": 0.00010420098126689159,
"loss": 0.7271,
"step": 1190
},
{
"epoch": 1.6297306512103649,
"grad_norm": 0.08082381008828005,
"learning_rate": 0.00010059068498951912,
"loss": 0.7334,
"step": 1195
},
{
"epoch": 1.63654960790999,
"grad_norm": 0.09653014658305435,
"learning_rate": 9.70370339258298e-05,
"loss": 0.733,
"step": 1200
},
{
"epoch": 1.6433685646096148,
"grad_norm": 0.08209631476731684,
"learning_rate": 9.354053206337803e-05,
"loss": 0.7295,
"step": 1205
},
{
"epoch": 1.6501875213092396,
"grad_norm": 0.08281543379309102,
"learning_rate": 9.010167528467784e-05,
"loss": 0.7282,
"step": 1210
},
{
"epoch": 1.6570064780088647,
"grad_norm": 0.09079242657548177,
"learning_rate": 8.672095129687485e-05,
"loss": 0.7332,
"step": 1215
},
{
"epoch": 1.6638254347084898,
"grad_norm": 0.08732562104521625,
"learning_rate": 8.33988395625791e-05,
"loss": 0.7196,
"step": 1220
},
{
"epoch": 1.6706443914081146,
"grad_norm": 0.09634799774642026,
"learning_rate": 8.013581123186675e-05,
"loss": 0.7243,
"step": 1225
},
{
"epoch": 1.6774633481077394,
"grad_norm": 0.0892053596550817,
"learning_rate": 7.693232907545955e-05,
"loss": 0.7284,
"step": 1230
},
{
"epoch": 1.6842823048073645,
"grad_norm": 0.08080152740232713,
"learning_rate": 7.378884741909409e-05,
"loss": 0.7226,
"step": 1235
},
{
"epoch": 1.6911012615069896,
"grad_norm": 0.08211682147824328,
"learning_rate": 7.070581207908832e-05,
"loss": 0.7293,
"step": 1240
},
{
"epoch": 1.6979202182066144,
"grad_norm": 0.08125416074026208,
"learning_rate": 6.76836602991146e-05,
"loss": 0.7241,
"step": 1245
},
{
"epoch": 1.7047391749062393,
"grad_norm": 0.08118597843483698,
"learning_rate": 6.472282068818857e-05,
"loss": 0.7176,
"step": 1250
},
{
"epoch": 1.7115581316058643,
"grad_norm": 0.08444459255476687,
"learning_rate": 6.182371315988283e-05,
"loss": 0.7345,
"step": 1255
},
{
"epoch": 1.7183770883054894,
"grad_norm": 0.08993862852560496,
"learning_rate": 5.898674887277394e-05,
"loss": 0.7287,
"step": 1260
},
{
"epoch": 1.7251960450051143,
"grad_norm": 0.09172625446804755,
"learning_rate": 5.621233017213095e-05,
"loss": 0.728,
"step": 1265
},
{
"epoch": 1.732015001704739,
"grad_norm": 0.09728192339349417,
"learning_rate": 5.3500850532853477e-05,
"loss": 0.7252,
"step": 1270
},
{
"epoch": 1.7388339584043642,
"grad_norm": 0.08183637004716483,
"learning_rate": 5.085269450366836e-05,
"loss": 0.7249,
"step": 1275
},
{
"epoch": 1.7456529151039892,
"grad_norm": 0.08417398467645139,
"learning_rate": 4.8268237652591805e-05,
"loss": 0.7263,
"step": 1280
},
{
"epoch": 1.752471871803614,
"grad_norm": 0.08559525343966955,
"learning_rate": 4.574784651366581e-05,
"loss": 0.7307,
"step": 1285
},
{
"epoch": 1.759290828503239,
"grad_norm": 0.08652462817281027,
"learning_rate": 4.329187853497491e-05,
"loss": 0.7321,
"step": 1290
},
{
"epoch": 1.766109785202864,
"grad_norm": 0.07780149732014437,
"learning_rate": 4.0900682027952274e-05,
"loss": 0.7259,
"step": 1295
},
{
"epoch": 1.772928741902489,
"grad_norm": 0.08073420987197251,
"learning_rate": 3.8574596117981367e-05,
"loss": 0.7318,
"step": 1300
},
{
"epoch": 1.779747698602114,
"grad_norm": 0.09399125884464814,
"learning_rate": 3.631395069630039e-05,
"loss": 0.7286,
"step": 1305
},
{
"epoch": 1.7865666553017387,
"grad_norm": 0.08683728371693161,
"learning_rate": 3.411906637321588e-05,
"loss": 0.7281,
"step": 1310
},
{
"epoch": 1.7933856120013638,
"grad_norm": 0.08220865889050938,
"learning_rate": 3.199025443263331e-05,
"loss": 0.7214,
"step": 1315
},
{
"epoch": 1.8002045687009889,
"grad_norm": 0.08394991114226853,
"learning_rate": 2.9927816787910233e-05,
"loss": 0.7274,
"step": 1320
},
{
"epoch": 1.8070235254006137,
"grad_norm": 0.08648979166756451,
"learning_rate": 2.79320459390377e-05,
"loss": 0.728,
"step": 1325
},
{
"epoch": 1.8138424821002386,
"grad_norm": 0.0809919030945408,
"learning_rate": 2.600322493115742e-05,
"loss": 0.7207,
"step": 1330
},
{
"epoch": 1.8206614387998636,
"grad_norm": 0.08146420956821185,
"learning_rate": 2.414162731441971e-05,
"loss": 0.7279,
"step": 1335
},
{
"epoch": 1.8274803954994887,
"grad_norm": 0.08991080627514368,
"learning_rate": 2.2347517105187952e-05,
"loss": 0.7285,
"step": 1340
},
{
"epoch": 1.8342993521991136,
"grad_norm": 0.08113174604843235,
"learning_rate": 2.062114874859483e-05,
"loss": 0.7212,
"step": 1345
},
{
"epoch": 1.8411183088987384,
"grad_norm": 0.0890991046050432,
"learning_rate": 1.8962767082456368e-05,
"loss": 0.7238,
"step": 1350
},
{
"epoch": 1.8479372655983635,
"grad_norm": 0.08194468587127682,
"learning_rate": 1.7372607302548916e-05,
"loss": 0.7278,
"step": 1355
},
{
"epoch": 1.8547562222979885,
"grad_norm": 0.0796060532873072,
"learning_rate": 1.58508949292524e-05,
"loss": 0.7303,
"step": 1360
},
{
"epoch": 1.8615751789976134,
"grad_norm": 0.08325978355636353,
"learning_rate": 1.439784577556702e-05,
"loss": 0.7259,
"step": 1365
},
{
"epoch": 1.8683941356972382,
"grad_norm": 0.08101951703165321,
"learning_rate": 1.3013665916505824e-05,
"loss": 0.7213,
"step": 1370
},
{
"epoch": 1.8752130923968633,
"grad_norm": 0.07474258489762015,
"learning_rate": 1.1698551659868716e-05,
"loss": 0.7251,
"step": 1375
},
{
"epoch": 1.8820320490964884,
"grad_norm": 0.07988354824659524,
"learning_rate": 1.0452689518401615e-05,
"loss": 0.7336,
"step": 1380
},
{
"epoch": 1.8888510057961132,
"grad_norm": 0.0869204045893242,
"learning_rate": 9.276256183344767e-06,
"loss": 0.7225,
"step": 1385
},
{
"epoch": 1.895669962495738,
"grad_norm": 0.08073129640276419,
"learning_rate": 8.169418499373749e-06,
"loss": 0.719,
"step": 1390
},
{
"epoch": 1.9024889191953631,
"grad_norm": 0.09277363778878074,
"learning_rate": 7.132333440937666e-06,
"loss": 0.7163,
"step": 1395
},
{
"epoch": 1.9093078758949882,
"grad_norm": 0.08156654600969289,
"learning_rate": 6.165148089996075e-06,
"loss": 0.7294,
"step": 1400
},
{
"epoch": 1.916126832594613,
"grad_norm": 0.07931208656000137,
"learning_rate": 5.267999615159724e-06,
"loss": 0.7188,
"step": 1405
},
{
"epoch": 1.9229457892942379,
"grad_norm": 0.08734085147118956,
"learning_rate": 4.441015252237113e-06,
"loss": 0.7239,
"step": 1410
},
{
"epoch": 1.929764745993863,
"grad_norm": 0.07927625348774799,
"learning_rate": 3.684312286189151e-06,
"loss": 0.737,
"step": 1415
},
{
"epoch": 1.936583702693488,
"grad_norm": 0.08278514720419748,
"learning_rate": 2.997998034495908e-06,
"loss": 0.7232,
"step": 1420
},
{
"epoch": 1.9434026593931129,
"grad_norm": 0.09337537685419582,
"learning_rate": 2.382169831936565e-06,
"loss": 0.7327,
"step": 1425
},
{
"epoch": 1.9502216160927377,
"grad_norm": 0.07802348568191127,
"learning_rate": 1.8369150167848459e-06,
"loss": 0.7168,
"step": 1430
},
{
"epoch": 1.9570405727923628,
"grad_norm": 0.07582457656438514,
"learning_rate": 1.3623109184228711e-06,
"loss": 0.7111,
"step": 1435
},
{
"epoch": 1.9638595294919878,
"grad_norm": 0.07999706762970123,
"learning_rate": 9.584248463739288e-07,
"loss": 0.7251,
"step": 1440
},
{
"epoch": 1.9706784861916127,
"grad_norm": 0.08421307868632791,
"learning_rate": 6.253140807562785e-07,
"loss": 0.7172,
"step": 1445
},
{
"epoch": 1.9774974428912375,
"grad_norm": 0.08148471965897129,
"learning_rate": 3.630258641600381e-07,
"loss": 0.7198,
"step": 1450
},
{
"epoch": 1.9843163995908626,
"grad_norm": 0.0748791624620726,
"learning_rate": 1.7159739494654325e-07,
"loss": 0.7267,
"step": 1455
},
{
"epoch": 1.9911353562904877,
"grad_norm": 0.08613985665976748,
"learning_rate": 5.1055821973289286e-08,
"loss": 0.7258,
"step": 1460
},
{
"epoch": 1.9979543129901125,
"grad_norm": 0.07749130518414991,
"learning_rate": 1.418240743289445e-09,
"loss": 0.7335,
"step": 1465
},
{
"epoch": 1.9993181043300376,
"eval_loss": 0.8305559158325195,
"eval_runtime": 60.2883,
"eval_samples_per_second": 184.43,
"eval_steps_per_second": 5.772,
"step": 1466
},
{
"epoch": 1.9993181043300376,
"step": 1466,
"total_flos": 143858545459200.0,
"train_loss": 0.8359313647060732,
"train_runtime": 3324.125,
"train_samples_per_second": 56.452,
"train_steps_per_second": 0.441
}
],
"logging_steps": 5,
"max_steps": 1466,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 143858545459200.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}