gemma_conversational / trainer_state.json
namuunbt02's picture
Upload folder using huggingface_hub
6283e7a verified
Raw
History Blame Contribute Delete
65.1 kB
{
"best_global_step": 1842,
"best_metric": 1.0541821718215942,
"best_model_checkpoint": "/home/astgpu3/workspace/znamuun/gemma_unsloth/output/conversational_v1_30k/checkpoint-1842",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1842,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0054333061668024995,
"grad_norm": 94.05772399902344,
"learning_rate": 0.00016,
"loss": 5.5664,
"step": 5
},
{
"epoch": 0.010866612333604999,
"grad_norm": 13.2901029586792,
"learning_rate": 0.00019970993473531544,
"loss": 2.3616,
"step": 10
},
{
"epoch": 0.016299918500407497,
"grad_norm": 7.427643775939941,
"learning_rate": 0.00019934735315445975,
"loss": 1.9261,
"step": 15
},
{
"epoch": 0.021733224667209998,
"grad_norm": 5.632727146148682,
"learning_rate": 0.00019898477157360406,
"loss": 1.7626,
"step": 20
},
{
"epoch": 0.027166530834012496,
"grad_norm": 4.494379997253418,
"learning_rate": 0.00019862218999274836,
"loss": 1.6662,
"step": 25
},
{
"epoch": 0.032599837000814993,
"grad_norm": 4.2322516441345215,
"learning_rate": 0.00019825960841189267,
"loss": 1.5438,
"step": 30
},
{
"epoch": 0.038033143167617495,
"grad_norm": 3.744213104248047,
"learning_rate": 0.00019789702683103698,
"loss": 1.5352,
"step": 35
},
{
"epoch": 0.043466449334419996,
"grad_norm": 3.162693738937378,
"learning_rate": 0.0001975344452501813,
"loss": 1.4912,
"step": 40
},
{
"epoch": 0.0488997555012225,
"grad_norm": 2.6240363121032715,
"learning_rate": 0.00019717186366932562,
"loss": 1.4284,
"step": 45
},
{
"epoch": 0.05433306166802499,
"grad_norm": 2.9256842136383057,
"learning_rate": 0.00019680928208846993,
"loss": 1.4817,
"step": 50
},
{
"epoch": 0.05976636783482749,
"grad_norm": 2.765918493270874,
"learning_rate": 0.00019644670050761423,
"loss": 1.4454,
"step": 55
},
{
"epoch": 0.06519967400162999,
"grad_norm": 2.6395816802978516,
"learning_rate": 0.00019608411892675854,
"loss": 1.3469,
"step": 60
},
{
"epoch": 0.07063298016843249,
"grad_norm": 2.685492753982544,
"learning_rate": 0.00019572153734590285,
"loss": 1.3815,
"step": 65
},
{
"epoch": 0.07606628633523499,
"grad_norm": 2.7929065227508545,
"learning_rate": 0.00019535895576504715,
"loss": 1.3455,
"step": 70
},
{
"epoch": 0.08149959250203749,
"grad_norm": 2.353255271911621,
"learning_rate": 0.00019499637418419146,
"loss": 1.3715,
"step": 75
},
{
"epoch": 0.08693289866883999,
"grad_norm": 2.219590902328491,
"learning_rate": 0.00019463379260333577,
"loss": 1.3263,
"step": 80
},
{
"epoch": 0.0923662048356425,
"grad_norm": 2.428845167160034,
"learning_rate": 0.00019427121102248007,
"loss": 1.3271,
"step": 85
},
{
"epoch": 0.097799511002445,
"grad_norm": 2.2855656147003174,
"learning_rate": 0.00019390862944162438,
"loss": 1.2585,
"step": 90
},
{
"epoch": 0.10323281716924748,
"grad_norm": 1.8471496105194092,
"learning_rate": 0.00019354604786076869,
"loss": 1.3017,
"step": 95
},
{
"epoch": 0.10866612333604998,
"grad_norm": 1.90038001537323,
"learning_rate": 0.000193183466279913,
"loss": 1.3322,
"step": 100
},
{
"epoch": 0.11409942950285248,
"grad_norm": 2.1164159774780273,
"learning_rate": 0.0001928208846990573,
"loss": 1.2592,
"step": 105
},
{
"epoch": 0.11953273566965499,
"grad_norm": 1.8444099426269531,
"learning_rate": 0.0001924583031182016,
"loss": 1.2927,
"step": 110
},
{
"epoch": 0.12496604183645749,
"grad_norm": 1.9745773077011108,
"learning_rate": 0.0001920957215373459,
"loss": 1.2741,
"step": 115
},
{
"epoch": 0.13039934800325997,
"grad_norm": 2.013883113861084,
"learning_rate": 0.00019173313995649022,
"loss": 1.3218,
"step": 120
},
{
"epoch": 0.1358326541700625,
"grad_norm": 2.1666481494903564,
"learning_rate": 0.00019137055837563453,
"loss": 1.3297,
"step": 125
},
{
"epoch": 0.14126596033686498,
"grad_norm": 2.155470371246338,
"learning_rate": 0.00019100797679477883,
"loss": 1.2874,
"step": 130
},
{
"epoch": 0.1466992665036675,
"grad_norm": 1.8312768936157227,
"learning_rate": 0.00019064539521392314,
"loss": 1.2409,
"step": 135
},
{
"epoch": 0.15213257267046998,
"grad_norm": 2.063589096069336,
"learning_rate": 0.00019028281363306745,
"loss": 1.2179,
"step": 140
},
{
"epoch": 0.1575658788372725,
"grad_norm": 1.747312068939209,
"learning_rate": 0.00018992023205221175,
"loss": 1.3022,
"step": 145
},
{
"epoch": 0.16299918500407498,
"grad_norm": 1.7806073427200317,
"learning_rate": 0.0001895576504713561,
"loss": 1.217,
"step": 150
},
{
"epoch": 0.16843249117087747,
"grad_norm": 1.837993860244751,
"learning_rate": 0.0001891950688905004,
"loss": 1.2132,
"step": 155
},
{
"epoch": 0.17386579733767998,
"grad_norm": 1.7257343530654907,
"learning_rate": 0.0001888324873096447,
"loss": 1.2665,
"step": 160
},
{
"epoch": 0.17929910350448247,
"grad_norm": 1.8893738985061646,
"learning_rate": 0.00018846990572878898,
"loss": 1.2344,
"step": 165
},
{
"epoch": 0.184732409671285,
"grad_norm": 1.6077213287353516,
"learning_rate": 0.0001881073241479333,
"loss": 1.1938,
"step": 170
},
{
"epoch": 0.19016571583808747,
"grad_norm": 1.6754542589187622,
"learning_rate": 0.0001877447425670776,
"loss": 1.1868,
"step": 175
},
{
"epoch": 0.19559902200489,
"grad_norm": 1.7836875915527344,
"learning_rate": 0.0001873821609862219,
"loss": 1.2142,
"step": 180
},
{
"epoch": 0.20103232817169248,
"grad_norm": 1.6601991653442383,
"learning_rate": 0.0001870195794053662,
"loss": 1.2607,
"step": 185
},
{
"epoch": 0.20646563433849496,
"grad_norm": 1.870048999786377,
"learning_rate": 0.00018665699782451051,
"loss": 1.2084,
"step": 190
},
{
"epoch": 0.21189894050529748,
"grad_norm": 1.7718192338943481,
"learning_rate": 0.00018629441624365482,
"loss": 1.2659,
"step": 195
},
{
"epoch": 0.21733224667209997,
"grad_norm": 1.585939645767212,
"learning_rate": 0.00018593183466279913,
"loss": 1.1891,
"step": 200
},
{
"epoch": 0.22276555283890248,
"grad_norm": 1.764376163482666,
"learning_rate": 0.00018556925308194343,
"loss": 1.1859,
"step": 205
},
{
"epoch": 0.22819885900570497,
"grad_norm": 1.412095546722412,
"learning_rate": 0.00018520667150108774,
"loss": 1.1426,
"step": 210
},
{
"epoch": 0.23363216517250748,
"grad_norm": 1.6154894828796387,
"learning_rate": 0.00018484408992023205,
"loss": 1.2003,
"step": 215
},
{
"epoch": 0.23906547133930997,
"grad_norm": 1.4826689958572388,
"learning_rate": 0.00018448150833937635,
"loss": 1.188,
"step": 220
},
{
"epoch": 0.24449877750611246,
"grad_norm": 1.6184778213500977,
"learning_rate": 0.00018411892675852066,
"loss": 1.2223,
"step": 225
},
{
"epoch": 0.24993208367291497,
"grad_norm": 1.756441593170166,
"learning_rate": 0.00018375634517766497,
"loss": 1.2589,
"step": 230
},
{
"epoch": 0.25536538983971746,
"grad_norm": 1.475306510925293,
"learning_rate": 0.00018339376359680928,
"loss": 1.1927,
"step": 235
},
{
"epoch": 0.26079869600651995,
"grad_norm": 1.4867374897003174,
"learning_rate": 0.00018303118201595358,
"loss": 1.1579,
"step": 240
},
{
"epoch": 0.2662320021733225,
"grad_norm": 1.6788930892944336,
"learning_rate": 0.00018266860043509792,
"loss": 1.1589,
"step": 245
},
{
"epoch": 0.271665308340125,
"grad_norm": 1.4673781394958496,
"learning_rate": 0.00018230601885424222,
"loss": 1.1274,
"step": 250
},
{
"epoch": 0.27709861450692747,
"grad_norm": 1.6435223817825317,
"learning_rate": 0.00018194343727338653,
"loss": 1.1959,
"step": 255
},
{
"epoch": 0.28253192067372995,
"grad_norm": 1.4649943113327026,
"learning_rate": 0.00018158085569253084,
"loss": 1.1783,
"step": 260
},
{
"epoch": 0.28796522684053244,
"grad_norm": 1.6235178709030151,
"learning_rate": 0.00018121827411167514,
"loss": 1.2556,
"step": 265
},
{
"epoch": 0.293398533007335,
"grad_norm": 1.404118537902832,
"learning_rate": 0.00018085569253081945,
"loss": 1.2253,
"step": 270
},
{
"epoch": 0.29883183917413747,
"grad_norm": 1.3945000171661377,
"learning_rate": 0.00018049311094996376,
"loss": 1.1298,
"step": 275
},
{
"epoch": 0.30426514534093996,
"grad_norm": 1.40553879737854,
"learning_rate": 0.00018013052936910806,
"loss": 1.0989,
"step": 280
},
{
"epoch": 0.30969845150774244,
"grad_norm": 1.51361882686615,
"learning_rate": 0.00017976794778825237,
"loss": 1.2315,
"step": 285
},
{
"epoch": 0.315131757674545,
"grad_norm": 1.4282881021499634,
"learning_rate": 0.00017940536620739668,
"loss": 1.1301,
"step": 290
},
{
"epoch": 0.3205650638413475,
"grad_norm": 1.3679155111312866,
"learning_rate": 0.00017904278462654098,
"loss": 1.1215,
"step": 295
},
{
"epoch": 0.32599837000814996,
"grad_norm": 1.3678269386291504,
"learning_rate": 0.0001786802030456853,
"loss": 1.0858,
"step": 300
},
{
"epoch": 0.33143167617495245,
"grad_norm": 1.320778250694275,
"learning_rate": 0.0001783176214648296,
"loss": 1.142,
"step": 305
},
{
"epoch": 0.33686498234175494,
"grad_norm": 1.4018844366073608,
"learning_rate": 0.0001779550398839739,
"loss": 1.1729,
"step": 310
},
{
"epoch": 0.3422982885085575,
"grad_norm": 1.6065289974212646,
"learning_rate": 0.0001775924583031182,
"loss": 1.1491,
"step": 315
},
{
"epoch": 0.34773159467535997,
"grad_norm": 1.463248610496521,
"learning_rate": 0.00017722987672226252,
"loss": 1.1071,
"step": 320
},
{
"epoch": 0.35316490084216245,
"grad_norm": 1.3639869689941406,
"learning_rate": 0.00017686729514140682,
"loss": 1.1745,
"step": 325
},
{
"epoch": 0.35859820700896494,
"grad_norm": 1.5606908798217773,
"learning_rate": 0.00017650471356055113,
"loss": 1.1361,
"step": 330
},
{
"epoch": 0.36403151317576743,
"grad_norm": 1.2420063018798828,
"learning_rate": 0.00017614213197969544,
"loss": 1.1144,
"step": 335
},
{
"epoch": 0.36946481934257,
"grad_norm": 1.3263566493988037,
"learning_rate": 0.00017577955039883974,
"loss": 1.0744,
"step": 340
},
{
"epoch": 0.37489812550937246,
"grad_norm": 1.4993051290512085,
"learning_rate": 0.00017541696881798405,
"loss": 1.0908,
"step": 345
},
{
"epoch": 0.38033143167617495,
"grad_norm": 1.3254144191741943,
"learning_rate": 0.00017505438723712836,
"loss": 1.1584,
"step": 350
},
{
"epoch": 0.38576473784297743,
"grad_norm": 1.3965848684310913,
"learning_rate": 0.00017469180565627266,
"loss": 1.0959,
"step": 355
},
{
"epoch": 0.39119804400978,
"grad_norm": 1.3152015209197998,
"learning_rate": 0.000174329224075417,
"loss": 1.1178,
"step": 360
},
{
"epoch": 0.39663135017658246,
"grad_norm": 1.4309927225112915,
"learning_rate": 0.0001739666424945613,
"loss": 1.1177,
"step": 365
},
{
"epoch": 0.40206465634338495,
"grad_norm": 1.3448002338409424,
"learning_rate": 0.0001736040609137056,
"loss": 1.101,
"step": 370
},
{
"epoch": 0.40749796251018744,
"grad_norm": 1.285933256149292,
"learning_rate": 0.00017324147933284992,
"loss": 1.0626,
"step": 375
},
{
"epoch": 0.4129312686769899,
"grad_norm": 1.4348984956741333,
"learning_rate": 0.00017287889775199423,
"loss": 1.1462,
"step": 380
},
{
"epoch": 0.41836457484379247,
"grad_norm": 1.3408560752868652,
"learning_rate": 0.0001725163161711385,
"loss": 1.1475,
"step": 385
},
{
"epoch": 0.42379788101059496,
"grad_norm": 1.3782771825790405,
"learning_rate": 0.0001721537345902828,
"loss": 1.0875,
"step": 390
},
{
"epoch": 0.42923118717739744,
"grad_norm": 1.3274637460708618,
"learning_rate": 0.00017179115300942712,
"loss": 1.0746,
"step": 395
},
{
"epoch": 0.43466449334419993,
"grad_norm": 1.5006779432296753,
"learning_rate": 0.00017142857142857143,
"loss": 1.1149,
"step": 400
},
{
"epoch": 0.4400977995110024,
"grad_norm": 1.3363099098205566,
"learning_rate": 0.00017106598984771573,
"loss": 1.0515,
"step": 405
},
{
"epoch": 0.44553110567780496,
"grad_norm": 1.439466953277588,
"learning_rate": 0.00017070340826686004,
"loss": 1.1296,
"step": 410
},
{
"epoch": 0.45096441184460745,
"grad_norm": 1.155349850654602,
"learning_rate": 0.00017034082668600435,
"loss": 1.1185,
"step": 415
},
{
"epoch": 0.45639771801140994,
"grad_norm": 1.1358013153076172,
"learning_rate": 0.00016997824510514865,
"loss": 1.1267,
"step": 420
},
{
"epoch": 0.4618310241782124,
"grad_norm": 1.3416662216186523,
"learning_rate": 0.00016961566352429296,
"loss": 1.1187,
"step": 425
},
{
"epoch": 0.46726433034501497,
"grad_norm": 1.2996137142181396,
"learning_rate": 0.00016925308194343727,
"loss": 1.0405,
"step": 430
},
{
"epoch": 0.47269763651181745,
"grad_norm": 1.257703185081482,
"learning_rate": 0.00016889050036258157,
"loss": 1.0456,
"step": 435
},
{
"epoch": 0.47813094267861994,
"grad_norm": 1.1873438358306885,
"learning_rate": 0.00016852791878172588,
"loss": 1.0442,
"step": 440
},
{
"epoch": 0.48356424884542243,
"grad_norm": 1.2138140201568604,
"learning_rate": 0.00016816533720087019,
"loss": 1.0797,
"step": 445
},
{
"epoch": 0.4889975550122249,
"grad_norm": 1.2529609203338623,
"learning_rate": 0.00016780275562001452,
"loss": 1.0624,
"step": 450
},
{
"epoch": 0.49443086117902746,
"grad_norm": 1.2894572019577026,
"learning_rate": 0.00016744017403915883,
"loss": 1.0507,
"step": 455
},
{
"epoch": 0.49986416734582995,
"grad_norm": 1.3366247415542603,
"learning_rate": 0.00016707759245830313,
"loss": 1.0792,
"step": 460
},
{
"epoch": 0.5052974735126324,
"grad_norm": 1.1520795822143555,
"learning_rate": 0.00016671501087744744,
"loss": 1.0353,
"step": 465
},
{
"epoch": 0.5107307796794349,
"grad_norm": 1.2416119575500488,
"learning_rate": 0.00016635242929659175,
"loss": 1.1282,
"step": 470
},
{
"epoch": 0.5161640858462374,
"grad_norm": 1.1610630750656128,
"learning_rate": 0.00016598984771573605,
"loss": 1.0581,
"step": 475
},
{
"epoch": 0.5215973920130399,
"grad_norm": 1.143537163734436,
"learning_rate": 0.00016562726613488036,
"loss": 1.0652,
"step": 480
},
{
"epoch": 0.5270306981798424,
"grad_norm": 1.0708473920822144,
"learning_rate": 0.00016526468455402467,
"loss": 1.0943,
"step": 485
},
{
"epoch": 0.532464004346645,
"grad_norm": 1.2459930181503296,
"learning_rate": 0.00016490210297316897,
"loss": 1.028,
"step": 490
},
{
"epoch": 0.5378973105134475,
"grad_norm": 1.3345253467559814,
"learning_rate": 0.00016453952139231328,
"loss": 1.1056,
"step": 495
},
{
"epoch": 0.54333061668025,
"grad_norm": 1.270090937614441,
"learning_rate": 0.0001641769398114576,
"loss": 1.0562,
"step": 500
},
{
"epoch": 0.5487639228470524,
"grad_norm": 1.1992326974868774,
"learning_rate": 0.0001638143582306019,
"loss": 1.0641,
"step": 505
},
{
"epoch": 0.5541972290138549,
"grad_norm": 1.182948350906372,
"learning_rate": 0.0001634517766497462,
"loss": 1.0496,
"step": 510
},
{
"epoch": 0.5596305351806574,
"grad_norm": 1.2159981727600098,
"learning_rate": 0.0001630891950688905,
"loss": 1.1103,
"step": 515
},
{
"epoch": 0.5650638413474599,
"grad_norm": 1.4117026329040527,
"learning_rate": 0.00016272661348803481,
"loss": 1.0865,
"step": 520
},
{
"epoch": 0.5704971475142624,
"grad_norm": 1.1276116371154785,
"learning_rate": 0.00016236403190717912,
"loss": 1.0844,
"step": 525
},
{
"epoch": 0.5759304536810649,
"grad_norm": 1.2447335720062256,
"learning_rate": 0.00016200145032632343,
"loss": 1.0771,
"step": 530
},
{
"epoch": 0.5813637598478675,
"grad_norm": 1.1846734285354614,
"learning_rate": 0.00016163886874546773,
"loss": 1.0601,
"step": 535
},
{
"epoch": 0.58679706601467,
"grad_norm": 1.0874987840652466,
"learning_rate": 0.00016127628716461204,
"loss": 1.0539,
"step": 540
},
{
"epoch": 0.5922303721814725,
"grad_norm": 1.161940574645996,
"learning_rate": 0.00016091370558375635,
"loss": 1.0732,
"step": 545
},
{
"epoch": 0.5976636783482749,
"grad_norm": 1.3249943256378174,
"learning_rate": 0.00016055112400290065,
"loss": 1.0771,
"step": 550
},
{
"epoch": 0.6030969845150774,
"grad_norm": 1.3140604496002197,
"learning_rate": 0.00016018854242204496,
"loss": 1.0611,
"step": 555
},
{
"epoch": 0.6085302906818799,
"grad_norm": 1.1174367666244507,
"learning_rate": 0.00015982596084118927,
"loss": 1.0457,
"step": 560
},
{
"epoch": 0.6139635968486824,
"grad_norm": 1.0260871648788452,
"learning_rate": 0.0001594633792603336,
"loss": 1.0164,
"step": 565
},
{
"epoch": 0.6193969030154849,
"grad_norm": 1.1550908088684082,
"learning_rate": 0.0001591007976794779,
"loss": 1.0173,
"step": 570
},
{
"epoch": 0.6248302091822874,
"grad_norm": 1.2019294500350952,
"learning_rate": 0.00015873821609862222,
"loss": 1.0284,
"step": 575
},
{
"epoch": 0.63026351534909,
"grad_norm": 1.2347038984298706,
"learning_rate": 0.00015837563451776652,
"loss": 1.0494,
"step": 580
},
{
"epoch": 0.6356968215158925,
"grad_norm": 1.06244957447052,
"learning_rate": 0.00015801305293691083,
"loss": 1.0365,
"step": 585
},
{
"epoch": 0.641130127682695,
"grad_norm": 1.0355654954910278,
"learning_rate": 0.00015765047135605514,
"loss": 1.0686,
"step": 590
},
{
"epoch": 0.6465634338494974,
"grad_norm": 1.1522706747055054,
"learning_rate": 0.00015728788977519944,
"loss": 1.0455,
"step": 595
},
{
"epoch": 0.6519967400162999,
"grad_norm": 1.0630000829696655,
"learning_rate": 0.00015692530819434375,
"loss": 1.0803,
"step": 600
},
{
"epoch": 0.6574300461831024,
"grad_norm": 1.0645341873168945,
"learning_rate": 0.00015656272661348806,
"loss": 1.0453,
"step": 605
},
{
"epoch": 0.6628633523499049,
"grad_norm": 1.113446831703186,
"learning_rate": 0.00015620014503263234,
"loss": 1.0388,
"step": 610
},
{
"epoch": 0.6682966585167074,
"grad_norm": 1.224284291267395,
"learning_rate": 0.00015583756345177664,
"loss": 1.0277,
"step": 615
},
{
"epoch": 0.6737299646835099,
"grad_norm": 1.2570809125900269,
"learning_rate": 0.00015547498187092095,
"loss": 1.0811,
"step": 620
},
{
"epoch": 0.6791632708503124,
"grad_norm": 1.097993016242981,
"learning_rate": 0.00015511240029006526,
"loss": 1.0439,
"step": 625
},
{
"epoch": 0.684596577017115,
"grad_norm": 1.1960225105285645,
"learning_rate": 0.00015474981870920956,
"loss": 1.0555,
"step": 630
},
{
"epoch": 0.6900298831839174,
"grad_norm": 1.104408860206604,
"learning_rate": 0.00015438723712835387,
"loss": 1.03,
"step": 635
},
{
"epoch": 0.6954631893507199,
"grad_norm": 1.1032377481460571,
"learning_rate": 0.00015402465554749818,
"loss": 1.0474,
"step": 640
},
{
"epoch": 0.7008964955175224,
"grad_norm": 1.2313536405563354,
"learning_rate": 0.00015366207396664248,
"loss": 1.1071,
"step": 645
},
{
"epoch": 0.7063298016843249,
"grad_norm": 1.1079504489898682,
"learning_rate": 0.0001532994923857868,
"loss": 0.991,
"step": 650
},
{
"epoch": 0.7117631078511274,
"grad_norm": 1.1161744594573975,
"learning_rate": 0.00015293691080493112,
"loss": 1.0002,
"step": 655
},
{
"epoch": 0.7171964140179299,
"grad_norm": 1.082507610321045,
"learning_rate": 0.00015257432922407543,
"loss": 1.0661,
"step": 660
},
{
"epoch": 0.7226297201847324,
"grad_norm": 1.1152865886688232,
"learning_rate": 0.00015221174764321974,
"loss": 1.0414,
"step": 665
},
{
"epoch": 0.7280630263515349,
"grad_norm": 1.1129889488220215,
"learning_rate": 0.00015184916606236404,
"loss": 1.0882,
"step": 670
},
{
"epoch": 0.7334963325183375,
"grad_norm": 1.2625923156738281,
"learning_rate": 0.00015148658448150835,
"loss": 1.054,
"step": 675
},
{
"epoch": 0.73892963868514,
"grad_norm": 1.194080114364624,
"learning_rate": 0.00015112400290065266,
"loss": 0.9775,
"step": 680
},
{
"epoch": 0.7443629448519424,
"grad_norm": 1.1932792663574219,
"learning_rate": 0.00015076142131979696,
"loss": 1.039,
"step": 685
},
{
"epoch": 0.7497962510187449,
"grad_norm": 1.2291207313537598,
"learning_rate": 0.00015039883973894127,
"loss": 0.9981,
"step": 690
},
{
"epoch": 0.7552295571855474,
"grad_norm": 1.0410774946212769,
"learning_rate": 0.00015003625815808558,
"loss": 1.0136,
"step": 695
},
{
"epoch": 0.7606628633523499,
"grad_norm": 1.3354581594467163,
"learning_rate": 0.00014967367657722988,
"loss": 1.0413,
"step": 700
},
{
"epoch": 0.7660961695191524,
"grad_norm": 1.1308538913726807,
"learning_rate": 0.0001493110949963742,
"loss": 1.062,
"step": 705
},
{
"epoch": 0.7715294756859549,
"grad_norm": 1.2079111337661743,
"learning_rate": 0.0001489485134155185,
"loss": 1.1237,
"step": 710
},
{
"epoch": 0.7769627818527574,
"grad_norm": 1.0739976167678833,
"learning_rate": 0.0001485859318346628,
"loss": 0.9859,
"step": 715
},
{
"epoch": 0.78239608801956,
"grad_norm": 0.9215412139892578,
"learning_rate": 0.0001482233502538071,
"loss": 0.9993,
"step": 720
},
{
"epoch": 0.7878293941863624,
"grad_norm": 1.1274949312210083,
"learning_rate": 0.00014786076867295142,
"loss": 1.0042,
"step": 725
},
{
"epoch": 0.7932627003531649,
"grad_norm": 1.311325192451477,
"learning_rate": 0.00014749818709209573,
"loss": 1.0855,
"step": 730
},
{
"epoch": 0.7986960065199674,
"grad_norm": 1.1324517726898193,
"learning_rate": 0.00014713560551124003,
"loss": 1.0675,
"step": 735
},
{
"epoch": 0.8041293126867699,
"grad_norm": 1.2283560037612915,
"learning_rate": 0.00014677302393038434,
"loss": 1.0262,
"step": 740
},
{
"epoch": 0.8095626188535724,
"grad_norm": 1.1866376399993896,
"learning_rate": 0.00014641044234952865,
"loss": 1.0767,
"step": 745
},
{
"epoch": 0.8149959250203749,
"grad_norm": 1.0849380493164062,
"learning_rate": 0.00014604786076867295,
"loss": 0.991,
"step": 750
},
{
"epoch": 0.8204292311871774,
"grad_norm": 1.1167508363723755,
"learning_rate": 0.00014568527918781726,
"loss": 0.9748,
"step": 755
},
{
"epoch": 0.8258625373539799,
"grad_norm": 1.0191930532455444,
"learning_rate": 0.00014532269760696157,
"loss": 0.9399,
"step": 760
},
{
"epoch": 0.8312958435207825,
"grad_norm": 1.1307344436645508,
"learning_rate": 0.00014496011602610587,
"loss": 0.9596,
"step": 765
},
{
"epoch": 0.8367291496875849,
"grad_norm": 1.0472939014434814,
"learning_rate": 0.0001445975344452502,
"loss": 1.0304,
"step": 770
},
{
"epoch": 0.8421624558543874,
"grad_norm": 1.333527684211731,
"learning_rate": 0.0001442349528643945,
"loss": 1.0326,
"step": 775
},
{
"epoch": 0.8475957620211899,
"grad_norm": 1.168447732925415,
"learning_rate": 0.00014387237128353882,
"loss": 1.0782,
"step": 780
},
{
"epoch": 0.8530290681879924,
"grad_norm": 1.1996850967407227,
"learning_rate": 0.00014350978970268313,
"loss": 1.0502,
"step": 785
},
{
"epoch": 0.8584623743547949,
"grad_norm": 1.0453308820724487,
"learning_rate": 0.00014314720812182743,
"loss": 1.0413,
"step": 790
},
{
"epoch": 0.8638956805215974,
"grad_norm": 1.0719515085220337,
"learning_rate": 0.00014278462654097174,
"loss": 1.0407,
"step": 795
},
{
"epoch": 0.8693289866883999,
"grad_norm": 1.1286976337432861,
"learning_rate": 0.00014242204496011605,
"loss": 0.9675,
"step": 800
},
{
"epoch": 0.8747622928552024,
"grad_norm": 1.1395922899246216,
"learning_rate": 0.00014205946337926035,
"loss": 1.0504,
"step": 805
},
{
"epoch": 0.8801955990220048,
"grad_norm": 1.1917579174041748,
"learning_rate": 0.00014169688179840466,
"loss": 1.0361,
"step": 810
},
{
"epoch": 0.8856289051888074,
"grad_norm": 1.1743110418319702,
"learning_rate": 0.00014133430021754897,
"loss": 0.9684,
"step": 815
},
{
"epoch": 0.8910622113556099,
"grad_norm": 1.10382080078125,
"learning_rate": 0.00014097171863669327,
"loss": 1.0359,
"step": 820
},
{
"epoch": 0.8964955175224124,
"grad_norm": 1.1514308452606201,
"learning_rate": 0.00014060913705583758,
"loss": 1.0011,
"step": 825
},
{
"epoch": 0.9019288236892149,
"grad_norm": 1.2536178827285767,
"learning_rate": 0.00014024655547498186,
"loss": 1.0913,
"step": 830
},
{
"epoch": 0.9073621298560174,
"grad_norm": 1.0985808372497559,
"learning_rate": 0.00013988397389412617,
"loss": 0.9757,
"step": 835
},
{
"epoch": 0.9127954360228199,
"grad_norm": 1.042410135269165,
"learning_rate": 0.00013952139231327047,
"loss": 1.0196,
"step": 840
},
{
"epoch": 0.9182287421896224,
"grad_norm": 1.2049064636230469,
"learning_rate": 0.00013915881073241478,
"loss": 0.9862,
"step": 845
},
{
"epoch": 0.9236620483564248,
"grad_norm": 1.169303059577942,
"learning_rate": 0.0001387962291515591,
"loss": 0.9924,
"step": 850
},
{
"epoch": 0.9290953545232273,
"grad_norm": 1.1006051301956177,
"learning_rate": 0.0001384336475707034,
"loss": 1.037,
"step": 855
},
{
"epoch": 0.9345286606900299,
"grad_norm": 1.044036626815796,
"learning_rate": 0.00013807106598984773,
"loss": 0.9422,
"step": 860
},
{
"epoch": 0.9399619668568324,
"grad_norm": 1.0203227996826172,
"learning_rate": 0.00013770848440899203,
"loss": 1.0634,
"step": 865
},
{
"epoch": 0.9453952730236349,
"grad_norm": 1.1052066087722778,
"learning_rate": 0.00013734590282813634,
"loss": 0.989,
"step": 870
},
{
"epoch": 0.9508285791904374,
"grad_norm": 1.0601762533187866,
"learning_rate": 0.00013698332124728065,
"loss": 0.97,
"step": 875
},
{
"epoch": 0.9562618853572399,
"grad_norm": 1.2294491529464722,
"learning_rate": 0.00013662073966642495,
"loss": 1.0011,
"step": 880
},
{
"epoch": 0.9616951915240424,
"grad_norm": 1.0348526239395142,
"learning_rate": 0.00013625815808556926,
"loss": 0.9967,
"step": 885
},
{
"epoch": 0.9671284976908449,
"grad_norm": 1.159955620765686,
"learning_rate": 0.00013589557650471357,
"loss": 1.0426,
"step": 890
},
{
"epoch": 0.9725618038576473,
"grad_norm": 0.9879871606826782,
"learning_rate": 0.00013553299492385788,
"loss": 0.9393,
"step": 895
},
{
"epoch": 0.9779951100244498,
"grad_norm": 1.0977790355682373,
"learning_rate": 0.00013517041334300218,
"loss": 0.9383,
"step": 900
},
{
"epoch": 0.9834284161912524,
"grad_norm": 1.0443631410598755,
"learning_rate": 0.0001348078317621465,
"loss": 1.0478,
"step": 905
},
{
"epoch": 0.9888617223580549,
"grad_norm": 1.088100790977478,
"learning_rate": 0.0001344452501812908,
"loss": 1.0814,
"step": 910
},
{
"epoch": 0.9942950285248574,
"grad_norm": 1.1516419649124146,
"learning_rate": 0.0001340826686004351,
"loss": 1.0281,
"step": 915
},
{
"epoch": 0.9997283346916599,
"grad_norm": 1.0100435018539429,
"learning_rate": 0.0001337200870195794,
"loss": 0.9778,
"step": 920
},
{
"epoch": 1.0,
"eval_loss": 1.0629626512527466,
"eval_runtime": 160.1638,
"eval_samples_per_second": 9.678,
"eval_steps_per_second": 2.423,
"step": 921
},
{
"epoch": 1.004346644933442,
"grad_norm": 1.0621072053909302,
"learning_rate": 0.00013335750543872372,
"loss": 0.9633,
"step": 925
},
{
"epoch": 1.0097799511002445,
"grad_norm": 1.2327194213867188,
"learning_rate": 0.00013299492385786802,
"loss": 0.8117,
"step": 930
},
{
"epoch": 1.015213257267047,
"grad_norm": 1.1144647598266602,
"learning_rate": 0.00013263234227701233,
"loss": 0.9238,
"step": 935
},
{
"epoch": 1.0206465634338495,
"grad_norm": 1.3408534526824951,
"learning_rate": 0.00013226976069615664,
"loss": 0.8266,
"step": 940
},
{
"epoch": 1.026079869600652,
"grad_norm": 1.3345109224319458,
"learning_rate": 0.00013190717911530094,
"loss": 0.9091,
"step": 945
},
{
"epoch": 1.0315131757674545,
"grad_norm": 1.1732280254364014,
"learning_rate": 0.00013154459753444525,
"loss": 0.876,
"step": 950
},
{
"epoch": 1.036946481934257,
"grad_norm": 1.2480390071868896,
"learning_rate": 0.00013118201595358956,
"loss": 0.9055,
"step": 955
},
{
"epoch": 1.0423797881010595,
"grad_norm": 1.0195136070251465,
"learning_rate": 0.00013081943437273386,
"loss": 0.9262,
"step": 960
},
{
"epoch": 1.047813094267862,
"grad_norm": 1.1737656593322754,
"learning_rate": 0.00013045685279187817,
"loss": 0.9174,
"step": 965
},
{
"epoch": 1.0532464004346644,
"grad_norm": 1.087819218635559,
"learning_rate": 0.00013009427121102248,
"loss": 0.8892,
"step": 970
},
{
"epoch": 1.058679706601467,
"grad_norm": 1.0774587392807007,
"learning_rate": 0.0001297316896301668,
"loss": 0.8276,
"step": 975
},
{
"epoch": 1.0641130127682694,
"grad_norm": 1.2075201272964478,
"learning_rate": 0.00012936910804931112,
"loss": 0.9004,
"step": 980
},
{
"epoch": 1.069546318935072,
"grad_norm": 1.1365958452224731,
"learning_rate": 0.00012900652646845542,
"loss": 0.8428,
"step": 985
},
{
"epoch": 1.0749796251018744,
"grad_norm": 1.032224178314209,
"learning_rate": 0.00012864394488759973,
"loss": 0.8797,
"step": 990
},
{
"epoch": 1.080412931268677,
"grad_norm": 1.1515988111495972,
"learning_rate": 0.00012828136330674404,
"loss": 0.8756,
"step": 995
},
{
"epoch": 1.0858462374354796,
"grad_norm": 1.1434125900268555,
"learning_rate": 0.00012791878172588834,
"loss": 0.9153,
"step": 1000
},
{
"epoch": 1.091279543602282,
"grad_norm": 1.4158624410629272,
"learning_rate": 0.00012755620014503265,
"loss": 0.8762,
"step": 1005
},
{
"epoch": 1.0967128497690846,
"grad_norm": 1.069629192352295,
"learning_rate": 0.00012719361856417696,
"loss": 0.8729,
"step": 1010
},
{
"epoch": 1.102146155935887,
"grad_norm": 1.1010494232177734,
"learning_rate": 0.00012683103698332126,
"loss": 0.8883,
"step": 1015
},
{
"epoch": 1.1075794621026895,
"grad_norm": 1.4307278394699097,
"learning_rate": 0.00012646845540246557,
"loss": 0.8894,
"step": 1020
},
{
"epoch": 1.113012768269492,
"grad_norm": 1.1194878816604614,
"learning_rate": 0.00012610587382160988,
"loss": 0.9064,
"step": 1025
},
{
"epoch": 1.1184460744362945,
"grad_norm": 1.1481852531433105,
"learning_rate": 0.00012574329224075418,
"loss": 0.8716,
"step": 1030
},
{
"epoch": 1.123879380603097,
"grad_norm": 1.0588971376419067,
"learning_rate": 0.0001253807106598985,
"loss": 0.92,
"step": 1035
},
{
"epoch": 1.1293126867698995,
"grad_norm": 1.1482290029525757,
"learning_rate": 0.0001250181290790428,
"loss": 0.8431,
"step": 1040
},
{
"epoch": 1.1347459929367019,
"grad_norm": 1.115369439125061,
"learning_rate": 0.0001246555474981871,
"loss": 0.8804,
"step": 1045
},
{
"epoch": 1.1401792991035045,
"grad_norm": 1.1321439743041992,
"learning_rate": 0.0001242929659173314,
"loss": 0.8311,
"step": 1050
},
{
"epoch": 1.145612605270307,
"grad_norm": 1.2138570547103882,
"learning_rate": 0.0001239303843364757,
"loss": 0.9062,
"step": 1055
},
{
"epoch": 1.1510459114371094,
"grad_norm": 1.171796441078186,
"learning_rate": 0.00012356780275562,
"loss": 0.8656,
"step": 1060
},
{
"epoch": 1.156479217603912,
"grad_norm": 1.277994990348816,
"learning_rate": 0.0001232052211747643,
"loss": 0.8735,
"step": 1065
},
{
"epoch": 1.1619125237707144,
"grad_norm": 1.0549153089523315,
"learning_rate": 0.00012284263959390864,
"loss": 0.8959,
"step": 1070
},
{
"epoch": 1.167345829937517,
"grad_norm": 0.9898720979690552,
"learning_rate": 0.00012248005801305295,
"loss": 0.8446,
"step": 1075
},
{
"epoch": 1.1727791361043194,
"grad_norm": 1.0818243026733398,
"learning_rate": 0.00012211747643219725,
"loss": 0.9452,
"step": 1080
},
{
"epoch": 1.178212442271122,
"grad_norm": 1.233089566230774,
"learning_rate": 0.00012175489485134155,
"loss": 0.8391,
"step": 1085
},
{
"epoch": 1.1836457484379244,
"grad_norm": 1.0094175338745117,
"learning_rate": 0.00012139231327048585,
"loss": 0.8363,
"step": 1090
},
{
"epoch": 1.189079054604727,
"grad_norm": 1.1545265913009644,
"learning_rate": 0.00012102973168963017,
"loss": 0.8744,
"step": 1095
},
{
"epoch": 1.1945123607715296,
"grad_norm": 1.1529176235198975,
"learning_rate": 0.00012066715010877448,
"loss": 0.8819,
"step": 1100
},
{
"epoch": 1.199945666938332,
"grad_norm": 1.1534438133239746,
"learning_rate": 0.00012030456852791879,
"loss": 0.8522,
"step": 1105
},
{
"epoch": 1.2053789731051345,
"grad_norm": 1.146657109260559,
"learning_rate": 0.00011994198694706309,
"loss": 0.8919,
"step": 1110
},
{
"epoch": 1.210812279271937,
"grad_norm": 1.2342313528060913,
"learning_rate": 0.0001195794053662074,
"loss": 0.8456,
"step": 1115
},
{
"epoch": 1.2162455854387395,
"grad_norm": 1.398826241493225,
"learning_rate": 0.0001192168237853517,
"loss": 0.8727,
"step": 1120
},
{
"epoch": 1.2216788916055419,
"grad_norm": 1.1229655742645264,
"learning_rate": 0.00011885424220449601,
"loss": 0.8537,
"step": 1125
},
{
"epoch": 1.2271121977723445,
"grad_norm": 1.1513757705688477,
"learning_rate": 0.00011849166062364032,
"loss": 0.9139,
"step": 1130
},
{
"epoch": 1.2325455039391469,
"grad_norm": 1.090980052947998,
"learning_rate": 0.00011812907904278463,
"loss": 0.884,
"step": 1135
},
{
"epoch": 1.2379788101059495,
"grad_norm": 1.2172348499298096,
"learning_rate": 0.00011776649746192893,
"loss": 0.8701,
"step": 1140
},
{
"epoch": 1.243412116272752,
"grad_norm": 1.1310840845108032,
"learning_rate": 0.00011740391588107324,
"loss": 0.8342,
"step": 1145
},
{
"epoch": 1.2488454224395544,
"grad_norm": 1.1303426027297974,
"learning_rate": 0.00011704133430021755,
"loss": 0.8672,
"step": 1150
},
{
"epoch": 1.254278728606357,
"grad_norm": 1.2884100675582886,
"learning_rate": 0.00011667875271936187,
"loss": 0.9344,
"step": 1155
},
{
"epoch": 1.2597120347731594,
"grad_norm": 1.1938570737838745,
"learning_rate": 0.00011631617113850617,
"loss": 0.8617,
"step": 1160
},
{
"epoch": 1.265145340939962,
"grad_norm": 1.1624027490615845,
"learning_rate": 0.00011595358955765048,
"loss": 0.802,
"step": 1165
},
{
"epoch": 1.2705786471067646,
"grad_norm": 1.1146856546401978,
"learning_rate": 0.00011559100797679479,
"loss": 0.8936,
"step": 1170
},
{
"epoch": 1.276011953273567,
"grad_norm": 0.9942327737808228,
"learning_rate": 0.0001152284263959391,
"loss": 0.8782,
"step": 1175
},
{
"epoch": 1.2814452594403694,
"grad_norm": 1.1722972393035889,
"learning_rate": 0.0001148658448150834,
"loss": 0.8808,
"step": 1180
},
{
"epoch": 1.286878565607172,
"grad_norm": 1.2962080240249634,
"learning_rate": 0.00011450326323422771,
"loss": 0.853,
"step": 1185
},
{
"epoch": 1.2923118717739746,
"grad_norm": 1.0645427703857422,
"learning_rate": 0.00011414068165337201,
"loss": 0.862,
"step": 1190
},
{
"epoch": 1.297745177940777,
"grad_norm": 1.3279187679290771,
"learning_rate": 0.00011377810007251632,
"loss": 0.9193,
"step": 1195
},
{
"epoch": 1.3031784841075795,
"grad_norm": 0.99788898229599,
"learning_rate": 0.00011341551849166063,
"loss": 0.848,
"step": 1200
},
{
"epoch": 1.308611790274382,
"grad_norm": 1.0723084211349487,
"learning_rate": 0.00011305293691080493,
"loss": 0.793,
"step": 1205
},
{
"epoch": 1.3140450964411845,
"grad_norm": 1.1458420753479004,
"learning_rate": 0.00011269035532994925,
"loss": 0.8531,
"step": 1210
},
{
"epoch": 1.3194784026079869,
"grad_norm": 1.1347026824951172,
"learning_rate": 0.00011232777374909356,
"loss": 0.846,
"step": 1215
},
{
"epoch": 1.3249117087747895,
"grad_norm": 1.0811132192611694,
"learning_rate": 0.00011196519216823787,
"loss": 0.8587,
"step": 1220
},
{
"epoch": 1.3303450149415919,
"grad_norm": 1.2509421110153198,
"learning_rate": 0.00011160261058738218,
"loss": 0.8441,
"step": 1225
},
{
"epoch": 1.3357783211083945,
"grad_norm": 1.0099766254425049,
"learning_rate": 0.00011124002900652648,
"loss": 0.8737,
"step": 1230
},
{
"epoch": 1.341211627275197,
"grad_norm": 1.1766360998153687,
"learning_rate": 0.00011087744742567079,
"loss": 0.9182,
"step": 1235
},
{
"epoch": 1.3466449334419994,
"grad_norm": 1.0566556453704834,
"learning_rate": 0.0001105148658448151,
"loss": 0.8829,
"step": 1240
},
{
"epoch": 1.352078239608802,
"grad_norm": 1.3091182708740234,
"learning_rate": 0.0001101522842639594,
"loss": 0.9399,
"step": 1245
},
{
"epoch": 1.3575115457756044,
"grad_norm": 1.35448157787323,
"learning_rate": 0.00010978970268310371,
"loss": 0.8651,
"step": 1250
},
{
"epoch": 1.362944851942407,
"grad_norm": 1.1222350597381592,
"learning_rate": 0.00010942712110224802,
"loss": 0.864,
"step": 1255
},
{
"epoch": 1.3683781581092094,
"grad_norm": 0.9896799921989441,
"learning_rate": 0.00010906453952139232,
"loss": 0.8638,
"step": 1260
},
{
"epoch": 1.373811464276012,
"grad_norm": 1.214143991470337,
"learning_rate": 0.00010870195794053664,
"loss": 0.8961,
"step": 1265
},
{
"epoch": 1.3792447704428143,
"grad_norm": 1.1640385389328003,
"learning_rate": 0.00010833937635968095,
"loss": 0.8818,
"step": 1270
},
{
"epoch": 1.384678076609617,
"grad_norm": 1.1086711883544922,
"learning_rate": 0.00010797679477882523,
"loss": 0.8502,
"step": 1275
},
{
"epoch": 1.3901113827764195,
"grad_norm": 1.1714527606964111,
"learning_rate": 0.00010761421319796954,
"loss": 0.8456,
"step": 1280
},
{
"epoch": 1.395544688943222,
"grad_norm": 1.0106830596923828,
"learning_rate": 0.00010725163161711384,
"loss": 0.8588,
"step": 1285
},
{
"epoch": 1.4009779951100245,
"grad_norm": 1.2438123226165771,
"learning_rate": 0.00010688905003625815,
"loss": 0.9012,
"step": 1290
},
{
"epoch": 1.406411301276827,
"grad_norm": 1.055284023284912,
"learning_rate": 0.00010652646845540246,
"loss": 0.8724,
"step": 1295
},
{
"epoch": 1.4118446074436295,
"grad_norm": 1.1548635959625244,
"learning_rate": 0.00010616388687454676,
"loss": 0.8323,
"step": 1300
},
{
"epoch": 1.4172779136104319,
"grad_norm": 1.2211989164352417,
"learning_rate": 0.00010580130529369108,
"loss": 0.8472,
"step": 1305
},
{
"epoch": 1.4227112197772345,
"grad_norm": 1.2574783563613892,
"learning_rate": 0.00010543872371283539,
"loss": 0.8812,
"step": 1310
},
{
"epoch": 1.4281445259440368,
"grad_norm": 1.1512340307235718,
"learning_rate": 0.0001050761421319797,
"loss": 0.8231,
"step": 1315
},
{
"epoch": 1.4335778321108394,
"grad_norm": 1.053491234779358,
"learning_rate": 0.000104713560551124,
"loss": 0.8484,
"step": 1320
},
{
"epoch": 1.439011138277642,
"grad_norm": 0.9974244236946106,
"learning_rate": 0.00010435097897026831,
"loss": 0.8774,
"step": 1325
},
{
"epoch": 1.4444444444444444,
"grad_norm": 1.1907140016555786,
"learning_rate": 0.00010398839738941262,
"loss": 0.8524,
"step": 1330
},
{
"epoch": 1.449877750611247,
"grad_norm": 1.0929960012435913,
"learning_rate": 0.00010362581580855692,
"loss": 0.8793,
"step": 1335
},
{
"epoch": 1.4553110567780494,
"grad_norm": 1.1883609294891357,
"learning_rate": 0.00010326323422770123,
"loss": 0.8784,
"step": 1340
},
{
"epoch": 1.460744362944852,
"grad_norm": 1.0147247314453125,
"learning_rate": 0.00010290065264684554,
"loss": 0.8559,
"step": 1345
},
{
"epoch": 1.4661776691116544,
"grad_norm": 1.0622776746749878,
"learning_rate": 0.00010253807106598984,
"loss": 0.9126,
"step": 1350
},
{
"epoch": 1.471610975278457,
"grad_norm": 1.0322296619415283,
"learning_rate": 0.00010217548948513415,
"loss": 0.8228,
"step": 1355
},
{
"epoch": 1.4770442814452593,
"grad_norm": 1.3334159851074219,
"learning_rate": 0.00010181290790427847,
"loss": 0.8945,
"step": 1360
},
{
"epoch": 1.482477587612062,
"grad_norm": 1.029920220375061,
"learning_rate": 0.00010145032632342278,
"loss": 0.8321,
"step": 1365
},
{
"epoch": 1.4879108937788645,
"grad_norm": 1.1344255208969116,
"learning_rate": 0.00010108774474256708,
"loss": 0.8733,
"step": 1370
},
{
"epoch": 1.493344199945667,
"grad_norm": 1.1062661409378052,
"learning_rate": 0.00010072516316171139,
"loss": 0.8485,
"step": 1375
},
{
"epoch": 1.4987775061124695,
"grad_norm": 0.9658976197242737,
"learning_rate": 0.0001003625815808557,
"loss": 0.9261,
"step": 1380
},
{
"epoch": 1.504210812279272,
"grad_norm": 1.2899905443191528,
"learning_rate": 0.0001,
"loss": 0.9171,
"step": 1385
},
{
"epoch": 1.5096441184460745,
"grad_norm": 1.067159652709961,
"learning_rate": 9.963741841914431e-05,
"loss": 0.8402,
"step": 1390
},
{
"epoch": 1.515077424612877,
"grad_norm": 1.211645483970642,
"learning_rate": 9.927483683828862e-05,
"loss": 0.8477,
"step": 1395
},
{
"epoch": 1.5205107307796795,
"grad_norm": 1.385699987411499,
"learning_rate": 9.891225525743293e-05,
"loss": 0.9136,
"step": 1400
},
{
"epoch": 1.5259440369464818,
"grad_norm": 1.1355695724487305,
"learning_rate": 9.854967367657723e-05,
"loss": 0.8304,
"step": 1405
},
{
"epoch": 1.5313773431132844,
"grad_norm": 1.2345882654190063,
"learning_rate": 9.818709209572154e-05,
"loss": 0.8749,
"step": 1410
},
{
"epoch": 1.536810649280087,
"grad_norm": 1.1696631908416748,
"learning_rate": 9.782451051486586e-05,
"loss": 0.8991,
"step": 1415
},
{
"epoch": 1.5422439554468894,
"grad_norm": 1.1087141036987305,
"learning_rate": 9.746192893401017e-05,
"loss": 0.8925,
"step": 1420
},
{
"epoch": 1.5476772616136918,
"grad_norm": 1.0509897470474243,
"learning_rate": 9.709934735315447e-05,
"loss": 0.8121,
"step": 1425
},
{
"epoch": 1.5531105677804944,
"grad_norm": 1.2797741889953613,
"learning_rate": 9.673676577229878e-05,
"loss": 0.8782,
"step": 1430
},
{
"epoch": 1.558543873947297,
"grad_norm": 1.1424418687820435,
"learning_rate": 9.637418419144309e-05,
"loss": 0.8634,
"step": 1435
},
{
"epoch": 1.5639771801140996,
"grad_norm": 1.1863006353378296,
"learning_rate": 9.601160261058739e-05,
"loss": 0.8899,
"step": 1440
},
{
"epoch": 1.569410486280902,
"grad_norm": 1.1050300598144531,
"learning_rate": 9.564902102973169e-05,
"loss": 0.8619,
"step": 1445
},
{
"epoch": 1.5748437924477043,
"grad_norm": 1.1671733856201172,
"learning_rate": 9.528643944887599e-05,
"loss": 0.855,
"step": 1450
},
{
"epoch": 1.580277098614507,
"grad_norm": 1.1153284311294556,
"learning_rate": 9.49238578680203e-05,
"loss": 0.8478,
"step": 1455
},
{
"epoch": 1.5857104047813095,
"grad_norm": 0.9661588668823242,
"learning_rate": 9.456127628716462e-05,
"loss": 0.8411,
"step": 1460
},
{
"epoch": 1.591143710948112,
"grad_norm": 1.2390023469924927,
"learning_rate": 9.419869470630893e-05,
"loss": 0.8836,
"step": 1465
},
{
"epoch": 1.5965770171149143,
"grad_norm": 1.0662574768066406,
"learning_rate": 9.383611312545323e-05,
"loss": 0.8696,
"step": 1470
},
{
"epoch": 1.6020103232817169,
"grad_norm": 1.2085328102111816,
"learning_rate": 9.347353154459754e-05,
"loss": 0.8032,
"step": 1475
},
{
"epoch": 1.6074436294485195,
"grad_norm": 1.1510725021362305,
"learning_rate": 9.311094996374185e-05,
"loss": 0.9099,
"step": 1480
},
{
"epoch": 1.612876935615322,
"grad_norm": 1.2687468528747559,
"learning_rate": 9.274836838288615e-05,
"loss": 0.8215,
"step": 1485
},
{
"epoch": 1.6183102417821245,
"grad_norm": 1.2436496019363403,
"learning_rate": 9.238578680203046e-05,
"loss": 0.84,
"step": 1490
},
{
"epoch": 1.6237435479489268,
"grad_norm": 1.0118858814239502,
"learning_rate": 9.202320522117477e-05,
"loss": 0.8481,
"step": 1495
},
{
"epoch": 1.6291768541157294,
"grad_norm": 1.057982087135315,
"learning_rate": 9.166062364031907e-05,
"loss": 0.853,
"step": 1500
},
{
"epoch": 1.634610160282532,
"grad_norm": 1.0575734376907349,
"learning_rate": 9.129804205946338e-05,
"loss": 0.9001,
"step": 1505
},
{
"epoch": 1.6400434664493344,
"grad_norm": 1.119564175605774,
"learning_rate": 9.093546047860769e-05,
"loss": 0.8093,
"step": 1510
},
{
"epoch": 1.6454767726161368,
"grad_norm": 1.120884895324707,
"learning_rate": 9.0572878897752e-05,
"loss": 0.8213,
"step": 1515
},
{
"epoch": 1.6509100787829394,
"grad_norm": 1.1385974884033203,
"learning_rate": 9.021029731689631e-05,
"loss": 0.8877,
"step": 1520
},
{
"epoch": 1.656343384949742,
"grad_norm": 1.1706347465515137,
"learning_rate": 8.984771573604062e-05,
"loss": 0.8279,
"step": 1525
},
{
"epoch": 1.6617766911165446,
"grad_norm": 1.2245526313781738,
"learning_rate": 8.948513415518493e-05,
"loss": 0.8668,
"step": 1530
},
{
"epoch": 1.667209997283347,
"grad_norm": 1.0326176881790161,
"learning_rate": 8.912255257432923e-05,
"loss": 0.8367,
"step": 1535
},
{
"epoch": 1.6726433034501493,
"grad_norm": 1.1200278997421265,
"learning_rate": 8.875997099347354e-05,
"loss": 0.8095,
"step": 1540
},
{
"epoch": 1.678076609616952,
"grad_norm": 1.2948065996170044,
"learning_rate": 8.839738941261785e-05,
"loss": 0.8287,
"step": 1545
},
{
"epoch": 1.6835099157837545,
"grad_norm": 1.0283042192459106,
"learning_rate": 8.803480783176215e-05,
"loss": 0.8308,
"step": 1550
},
{
"epoch": 1.688943221950557,
"grad_norm": 1.001953125,
"learning_rate": 8.767222625090645e-05,
"loss": 0.8586,
"step": 1555
},
{
"epoch": 1.6943765281173593,
"grad_norm": 1.4033405780792236,
"learning_rate": 8.730964467005075e-05,
"loss": 0.9156,
"step": 1560
},
{
"epoch": 1.6998098342841619,
"grad_norm": 1.1317863464355469,
"learning_rate": 8.694706308919508e-05,
"loss": 0.8126,
"step": 1565
},
{
"epoch": 1.7052431404509645,
"grad_norm": 1.2173607349395752,
"learning_rate": 8.658448150833938e-05,
"loss": 0.8535,
"step": 1570
},
{
"epoch": 1.710676446617767,
"grad_norm": 1.0661206245422363,
"learning_rate": 8.622189992748369e-05,
"loss": 0.8383,
"step": 1575
},
{
"epoch": 1.7161097527845695,
"grad_norm": 1.0935437679290771,
"learning_rate": 8.5859318346628e-05,
"loss": 0.8502,
"step": 1580
},
{
"epoch": 1.7215430589513718,
"grad_norm": 1.1766958236694336,
"learning_rate": 8.54967367657723e-05,
"loss": 0.8249,
"step": 1585
},
{
"epoch": 1.7269763651181744,
"grad_norm": 1.1970454454421997,
"learning_rate": 8.513415518491661e-05,
"loss": 0.8488,
"step": 1590
},
{
"epoch": 1.732409671284977,
"grad_norm": 1.0711541175842285,
"learning_rate": 8.477157360406092e-05,
"loss": 0.8612,
"step": 1595
},
{
"epoch": 1.7378429774517794,
"grad_norm": 1.142510175704956,
"learning_rate": 8.440899202320522e-05,
"loss": 0.8237,
"step": 1600
},
{
"epoch": 1.7432762836185818,
"grad_norm": 1.157728672027588,
"learning_rate": 8.404641044234953e-05,
"loss": 0.8693,
"step": 1605
},
{
"epoch": 1.7487095897853844,
"grad_norm": 1.2358007431030273,
"learning_rate": 8.368382886149384e-05,
"loss": 0.8697,
"step": 1610
},
{
"epoch": 1.754142895952187,
"grad_norm": 1.2696595191955566,
"learning_rate": 8.332124728063814e-05,
"loss": 0.8626,
"step": 1615
},
{
"epoch": 1.7595762021189894,
"grad_norm": 1.2669212818145752,
"learning_rate": 8.295866569978246e-05,
"loss": 0.8889,
"step": 1620
},
{
"epoch": 1.765009508285792,
"grad_norm": 1.071008324623108,
"learning_rate": 8.259608411892677e-05,
"loss": 0.8591,
"step": 1625
},
{
"epoch": 1.7704428144525943,
"grad_norm": 1.0619854927062988,
"learning_rate": 8.223350253807108e-05,
"loss": 0.8183,
"step": 1630
},
{
"epoch": 1.775876120619397,
"grad_norm": 1.0905566215515137,
"learning_rate": 8.187092095721538e-05,
"loss": 0.8569,
"step": 1635
},
{
"epoch": 1.7813094267861995,
"grad_norm": 1.1269817352294922,
"learning_rate": 8.150833937635969e-05,
"loss": 0.9046,
"step": 1640
},
{
"epoch": 1.786742732953002,
"grad_norm": 1.123292326927185,
"learning_rate": 8.1145757795504e-05,
"loss": 0.7951,
"step": 1645
},
{
"epoch": 1.7921760391198043,
"grad_norm": 1.0677564144134521,
"learning_rate": 8.07831762146483e-05,
"loss": 0.7568,
"step": 1650
},
{
"epoch": 1.7976093452866069,
"grad_norm": 1.3572133779525757,
"learning_rate": 8.042059463379261e-05,
"loss": 0.856,
"step": 1655
},
{
"epoch": 1.8030426514534095,
"grad_norm": 1.0941401720046997,
"learning_rate": 8.005801305293692e-05,
"loss": 0.8384,
"step": 1660
},
{
"epoch": 1.8084759576202118,
"grad_norm": 1.094785213470459,
"learning_rate": 7.969543147208121e-05,
"loss": 0.8504,
"step": 1665
},
{
"epoch": 1.8139092637870144,
"grad_norm": 1.0520368814468384,
"learning_rate": 7.933284989122553e-05,
"loss": 0.8267,
"step": 1670
},
{
"epoch": 1.8193425699538168,
"grad_norm": 1.0908136367797852,
"learning_rate": 7.897026831036984e-05,
"loss": 0.8239,
"step": 1675
},
{
"epoch": 1.8247758761206194,
"grad_norm": 1.1392829418182373,
"learning_rate": 7.860768672951414e-05,
"loss": 0.8786,
"step": 1680
},
{
"epoch": 1.830209182287422,
"grad_norm": 1.2346545457839966,
"learning_rate": 7.824510514865845e-05,
"loss": 0.8669,
"step": 1685
},
{
"epoch": 1.8356424884542244,
"grad_norm": 1.131622314453125,
"learning_rate": 7.788252356780276e-05,
"loss": 0.8707,
"step": 1690
},
{
"epoch": 1.8410757946210268,
"grad_norm": 1.2329860925674438,
"learning_rate": 7.751994198694706e-05,
"loss": 0.8205,
"step": 1695
},
{
"epoch": 1.8465091007878294,
"grad_norm": 1.0701172351837158,
"learning_rate": 7.715736040609137e-05,
"loss": 0.8733,
"step": 1700
},
{
"epoch": 1.851942406954632,
"grad_norm": 1.112290382385254,
"learning_rate": 7.679477882523568e-05,
"loss": 0.8,
"step": 1705
},
{
"epoch": 1.8573757131214343,
"grad_norm": 1.154740571975708,
"learning_rate": 7.643219724437998e-05,
"loss": 0.7865,
"step": 1710
},
{
"epoch": 1.862809019288237,
"grad_norm": 1.0539336204528809,
"learning_rate": 7.606961566352429e-05,
"loss": 0.8828,
"step": 1715
},
{
"epoch": 1.8682423254550393,
"grad_norm": 1.034320592880249,
"learning_rate": 7.57070340826686e-05,
"loss": 0.8341,
"step": 1720
},
{
"epoch": 1.873675631621842,
"grad_norm": 1.1562882661819458,
"learning_rate": 7.534445250181292e-05,
"loss": 0.7654,
"step": 1725
},
{
"epoch": 1.8791089377886445,
"grad_norm": 1.1259301900863647,
"learning_rate": 7.498187092095723e-05,
"loss": 0.8479,
"step": 1730
},
{
"epoch": 1.884542243955447,
"grad_norm": 1.0703877210617065,
"learning_rate": 7.461928934010153e-05,
"loss": 0.8129,
"step": 1735
},
{
"epoch": 1.8899755501222493,
"grad_norm": 1.2072659730911255,
"learning_rate": 7.425670775924584e-05,
"loss": 0.8493,
"step": 1740
},
{
"epoch": 1.8954088562890519,
"grad_norm": 1.0550438165664673,
"learning_rate": 7.389412617839015e-05,
"loss": 0.8305,
"step": 1745
},
{
"epoch": 1.9008421624558545,
"grad_norm": 1.2068486213684082,
"learning_rate": 7.353154459753445e-05,
"loss": 0.814,
"step": 1750
},
{
"epoch": 1.9062754686226568,
"grad_norm": 1.1273876428604126,
"learning_rate": 7.316896301667876e-05,
"loss": 0.8302,
"step": 1755
},
{
"epoch": 1.9117087747894592,
"grad_norm": 1.0691168308258057,
"learning_rate": 7.280638143582307e-05,
"loss": 0.8305,
"step": 1760
},
{
"epoch": 1.9171420809562618,
"grad_norm": 1.1833313703536987,
"learning_rate": 7.244379985496737e-05,
"loss": 0.8292,
"step": 1765
},
{
"epoch": 1.9225753871230644,
"grad_norm": 1.0391945838928223,
"learning_rate": 7.208121827411168e-05,
"loss": 0.8173,
"step": 1770
},
{
"epoch": 1.928008693289867,
"grad_norm": 1.1484371423721313,
"learning_rate": 7.171863669325599e-05,
"loss": 0.8855,
"step": 1775
},
{
"epoch": 1.9334419994566694,
"grad_norm": 1.1941226720809937,
"learning_rate": 7.135605511240029e-05,
"loss": 0.8908,
"step": 1780
},
{
"epoch": 1.9388753056234718,
"grad_norm": 1.1475844383239746,
"learning_rate": 7.09934735315446e-05,
"loss": 0.8317,
"step": 1785
},
{
"epoch": 1.9443086117902744,
"grad_norm": 1.1159197092056274,
"learning_rate": 7.06308919506889e-05,
"loss": 0.8222,
"step": 1790
},
{
"epoch": 1.949741917957077,
"grad_norm": 1.1025739908218384,
"learning_rate": 7.026831036983321e-05,
"loss": 0.824,
"step": 1795
},
{
"epoch": 1.9551752241238793,
"grad_norm": 1.1180258989334106,
"learning_rate": 6.990572878897752e-05,
"loss": 0.8362,
"step": 1800
},
{
"epoch": 1.9606085302906817,
"grad_norm": 1.2311022281646729,
"learning_rate": 6.954314720812183e-05,
"loss": 0.8303,
"step": 1805
},
{
"epoch": 1.9660418364574843,
"grad_norm": 1.0354889631271362,
"learning_rate": 6.918056562726613e-05,
"loss": 0.8128,
"step": 1810
},
{
"epoch": 1.971475142624287,
"grad_norm": 1.0918065309524536,
"learning_rate": 6.881798404641044e-05,
"loss": 0.8402,
"step": 1815
},
{
"epoch": 1.9769084487910895,
"grad_norm": 1.0534344911575317,
"learning_rate": 6.845540246555475e-05,
"loss": 0.835,
"step": 1820
},
{
"epoch": 1.9823417549578919,
"grad_norm": 1.2761425971984863,
"learning_rate": 6.809282088469905e-05,
"loss": 0.8245,
"step": 1825
},
{
"epoch": 1.9877750611246943,
"grad_norm": 1.2208045721054077,
"learning_rate": 6.773023930384337e-05,
"loss": 0.814,
"step": 1830
},
{
"epoch": 1.9932083672914969,
"grad_norm": 1.1697189807891846,
"learning_rate": 6.736765772298768e-05,
"loss": 0.7971,
"step": 1835
},
{
"epoch": 1.9986416734582995,
"grad_norm": 1.2008514404296875,
"learning_rate": 6.700507614213199e-05,
"loss": 0.8403,
"step": 1840
},
{
"epoch": 2.0,
"eval_loss": 1.0541821718215942,
"eval_runtime": 152.5101,
"eval_samples_per_second": 10.163,
"eval_steps_per_second": 2.544,
"step": 1842
}
],
"logging_steps": 5,
"max_steps": 2763,
"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": 8.490251112814382e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}