CantoneseLLMChat-v0.5 / trainer_state.json
indiejoseph's picture
Upload folder using huggingface_hub
70ff487 verified
raw
history blame
55.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9970883209317374,
"eval_steps": 500,
"global_step": 1737,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008627197239296884,
"grad_norm": 5.919341564178467,
"learning_rate": 1e-05,
"loss": 1.3814,
"step": 5
},
{
"epoch": 0.017254394478593768,
"grad_norm": 4.066539287567139,
"learning_rate": 1e-05,
"loss": 1.3848,
"step": 10
},
{
"epoch": 0.02588159171789065,
"grad_norm": 4.004323959350586,
"learning_rate": 1e-05,
"loss": 1.3517,
"step": 15
},
{
"epoch": 0.034508788957187536,
"grad_norm": 4.424528121948242,
"learning_rate": 1e-05,
"loss": 1.4088,
"step": 20
},
{
"epoch": 0.04313598619648442,
"grad_norm": 4.122994899749756,
"learning_rate": 1e-05,
"loss": 1.3542,
"step": 25
},
{
"epoch": 0.0517631834357813,
"grad_norm": 3.9815385341644287,
"learning_rate": 1e-05,
"loss": 1.3434,
"step": 30
},
{
"epoch": 0.06039038067507818,
"grad_norm": 3.663285255432129,
"learning_rate": 1e-05,
"loss": 1.3926,
"step": 35
},
{
"epoch": 0.06901757791437507,
"grad_norm": 3.6322672367095947,
"learning_rate": 1e-05,
"loss": 1.2819,
"step": 40
},
{
"epoch": 0.07764477515367195,
"grad_norm": 4.1651387214660645,
"learning_rate": 1e-05,
"loss": 1.3482,
"step": 45
},
{
"epoch": 0.08627197239296884,
"grad_norm": 3.8225786685943604,
"learning_rate": 1e-05,
"loss": 1.2621,
"step": 50
},
{
"epoch": 0.09489916963226572,
"grad_norm": 3.9319000244140625,
"learning_rate": 1e-05,
"loss": 1.2695,
"step": 55
},
{
"epoch": 0.1035263668715626,
"grad_norm": 4.2429633140563965,
"learning_rate": 1e-05,
"loss": 1.2302,
"step": 60
},
{
"epoch": 0.11215356411085949,
"grad_norm": 3.836970090866089,
"learning_rate": 1e-05,
"loss": 1.242,
"step": 65
},
{
"epoch": 0.12078076135015636,
"grad_norm": 3.622291326522827,
"learning_rate": 1e-05,
"loss": 1.2433,
"step": 70
},
{
"epoch": 0.12940795858945325,
"grad_norm": 3.876661539077759,
"learning_rate": 1e-05,
"loss": 1.3095,
"step": 75
},
{
"epoch": 0.13803515582875014,
"grad_norm": 3.3505313396453857,
"learning_rate": 1e-05,
"loss": 1.3006,
"step": 80
},
{
"epoch": 0.146662353068047,
"grad_norm": 4.024404048919678,
"learning_rate": 1e-05,
"loss": 1.2698,
"step": 85
},
{
"epoch": 0.1552895503073439,
"grad_norm": 3.4006166458129883,
"learning_rate": 1e-05,
"loss": 1.3346,
"step": 90
},
{
"epoch": 0.1639167475466408,
"grad_norm": 3.5438950061798096,
"learning_rate": 1e-05,
"loss": 1.3634,
"step": 95
},
{
"epoch": 0.17254394478593768,
"grad_norm": 4.186426162719727,
"learning_rate": 1e-05,
"loss": 1.2645,
"step": 100
},
{
"epoch": 0.18117114202523454,
"grad_norm": 3.5808355808258057,
"learning_rate": 1e-05,
"loss": 1.3625,
"step": 105
},
{
"epoch": 0.18979833926453143,
"grad_norm": 4.477747917175293,
"learning_rate": 1e-05,
"loss": 1.2592,
"step": 110
},
{
"epoch": 0.19842553650382833,
"grad_norm": 3.461580753326416,
"learning_rate": 1e-05,
"loss": 1.2872,
"step": 115
},
{
"epoch": 0.2070527337431252,
"grad_norm": 4.153059005737305,
"learning_rate": 1e-05,
"loss": 1.31,
"step": 120
},
{
"epoch": 0.21567993098242208,
"grad_norm": 4.117781639099121,
"learning_rate": 1e-05,
"loss": 1.2627,
"step": 125
},
{
"epoch": 0.22430712822171897,
"grad_norm": 4.274353504180908,
"learning_rate": 1e-05,
"loss": 1.206,
"step": 130
},
{
"epoch": 0.23293432546101586,
"grad_norm": 3.5153017044067383,
"learning_rate": 1e-05,
"loss": 1.3192,
"step": 135
},
{
"epoch": 0.24156152270031273,
"grad_norm": 3.2502472400665283,
"learning_rate": 1e-05,
"loss": 1.2825,
"step": 140
},
{
"epoch": 0.2501887199396096,
"grad_norm": 3.598522186279297,
"learning_rate": 1e-05,
"loss": 1.3421,
"step": 145
},
{
"epoch": 0.2588159171789065,
"grad_norm": 3.85213565826416,
"learning_rate": 1e-05,
"loss": 1.3141,
"step": 150
},
{
"epoch": 0.2674431144182034,
"grad_norm": 4.03485107421875,
"learning_rate": 1e-05,
"loss": 1.298,
"step": 155
},
{
"epoch": 0.2760703116575003,
"grad_norm": 3.352916717529297,
"learning_rate": 1e-05,
"loss": 1.3034,
"step": 160
},
{
"epoch": 0.2846975088967972,
"grad_norm": 3.504659652709961,
"learning_rate": 1e-05,
"loss": 1.2532,
"step": 165
},
{
"epoch": 0.293324706136094,
"grad_norm": 3.5304458141326904,
"learning_rate": 1e-05,
"loss": 1.2745,
"step": 170
},
{
"epoch": 0.3019519033753909,
"grad_norm": 3.2286152839660645,
"learning_rate": 1e-05,
"loss": 1.3067,
"step": 175
},
{
"epoch": 0.3105791006146878,
"grad_norm": 3.1940603256225586,
"learning_rate": 1e-05,
"loss": 1.2628,
"step": 180
},
{
"epoch": 0.3192062978539847,
"grad_norm": 3.7485692501068115,
"learning_rate": 1e-05,
"loss": 1.2514,
"step": 185
},
{
"epoch": 0.3278334950932816,
"grad_norm": 3.438934326171875,
"learning_rate": 1e-05,
"loss": 1.2122,
"step": 190
},
{
"epoch": 0.33646069233257847,
"grad_norm": 4.063304424285889,
"learning_rate": 1e-05,
"loss": 1.2825,
"step": 195
},
{
"epoch": 0.34508788957187536,
"grad_norm": 3.3390140533447266,
"learning_rate": 1e-05,
"loss": 1.2752,
"step": 200
},
{
"epoch": 0.3537150868111722,
"grad_norm": 3.5218873023986816,
"learning_rate": 1e-05,
"loss": 1.3145,
"step": 205
},
{
"epoch": 0.3623422840504691,
"grad_norm": 4.008931636810303,
"learning_rate": 1e-05,
"loss": 1.2694,
"step": 210
},
{
"epoch": 0.370969481289766,
"grad_norm": 3.844992160797119,
"learning_rate": 1e-05,
"loss": 1.3507,
"step": 215
},
{
"epoch": 0.37959667852906287,
"grad_norm": 3.2494778633117676,
"learning_rate": 1e-05,
"loss": 1.3843,
"step": 220
},
{
"epoch": 0.38822387576835976,
"grad_norm": 3.2193210124969482,
"learning_rate": 1e-05,
"loss": 1.2553,
"step": 225
},
{
"epoch": 0.39685107300765665,
"grad_norm": 3.6562159061431885,
"learning_rate": 1e-05,
"loss": 1.3664,
"step": 230
},
{
"epoch": 0.40547827024695354,
"grad_norm": 3.219736099243164,
"learning_rate": 1e-05,
"loss": 1.3083,
"step": 235
},
{
"epoch": 0.4141054674862504,
"grad_norm": 3.986835241317749,
"learning_rate": 1e-05,
"loss": 1.2945,
"step": 240
},
{
"epoch": 0.42273266472554727,
"grad_norm": 3.874375581741333,
"learning_rate": 1e-05,
"loss": 1.2938,
"step": 245
},
{
"epoch": 0.43135986196484416,
"grad_norm": 3.1514320373535156,
"learning_rate": 1e-05,
"loss": 1.2231,
"step": 250
},
{
"epoch": 0.43998705920414105,
"grad_norm": 3.3543567657470703,
"learning_rate": 1e-05,
"loss": 1.2237,
"step": 255
},
{
"epoch": 0.44861425644343794,
"grad_norm": 4.068399906158447,
"learning_rate": 1e-05,
"loss": 1.1541,
"step": 260
},
{
"epoch": 0.45724145368273483,
"grad_norm": 3.7400364875793457,
"learning_rate": 1e-05,
"loss": 1.2629,
"step": 265
},
{
"epoch": 0.4658686509220317,
"grad_norm": 3.091808557510376,
"learning_rate": 1e-05,
"loss": 1.1911,
"step": 270
},
{
"epoch": 0.4744958481613286,
"grad_norm": 3.622913360595703,
"learning_rate": 1e-05,
"loss": 1.4012,
"step": 275
},
{
"epoch": 0.48312304540062545,
"grad_norm": 3.368582010269165,
"learning_rate": 1e-05,
"loss": 1.2188,
"step": 280
},
{
"epoch": 0.49175024263992234,
"grad_norm": 3.4569334983825684,
"learning_rate": 1e-05,
"loss": 1.354,
"step": 285
},
{
"epoch": 0.5003774398792192,
"grad_norm": 3.7725794315338135,
"learning_rate": 1e-05,
"loss": 1.3322,
"step": 290
},
{
"epoch": 0.5090046371185161,
"grad_norm": 3.446682929992676,
"learning_rate": 1e-05,
"loss": 1.3385,
"step": 295
},
{
"epoch": 0.517631834357813,
"grad_norm": 3.31061053276062,
"learning_rate": 1e-05,
"loss": 1.2541,
"step": 300
},
{
"epoch": 0.5262590315971098,
"grad_norm": 3.3477659225463867,
"learning_rate": 1e-05,
"loss": 1.3451,
"step": 305
},
{
"epoch": 0.5348862288364068,
"grad_norm": 4.0511322021484375,
"learning_rate": 1e-05,
"loss": 1.3269,
"step": 310
},
{
"epoch": 0.5435134260757036,
"grad_norm": 3.5980873107910156,
"learning_rate": 1e-05,
"loss": 1.2654,
"step": 315
},
{
"epoch": 0.5521406233150006,
"grad_norm": 4.6503119468688965,
"learning_rate": 1e-05,
"loss": 1.3162,
"step": 320
},
{
"epoch": 0.5607678205542974,
"grad_norm": 3.890101432800293,
"learning_rate": 1e-05,
"loss": 1.2839,
"step": 325
},
{
"epoch": 0.5693950177935944,
"grad_norm": 3.019289016723633,
"learning_rate": 1e-05,
"loss": 1.3095,
"step": 330
},
{
"epoch": 0.5780222150328912,
"grad_norm": 3.544351100921631,
"learning_rate": 1e-05,
"loss": 1.285,
"step": 335
},
{
"epoch": 0.586649412272188,
"grad_norm": 4.081313133239746,
"learning_rate": 1e-05,
"loss": 1.2419,
"step": 340
},
{
"epoch": 0.595276609511485,
"grad_norm": 3.010798454284668,
"learning_rate": 1e-05,
"loss": 1.2875,
"step": 345
},
{
"epoch": 0.6039038067507818,
"grad_norm": 3.469045639038086,
"learning_rate": 1e-05,
"loss": 1.3055,
"step": 350
},
{
"epoch": 0.6125310039900788,
"grad_norm": 3.8424911499023438,
"learning_rate": 1e-05,
"loss": 1.33,
"step": 355
},
{
"epoch": 0.6211582012293756,
"grad_norm": 3.3473572731018066,
"learning_rate": 1e-05,
"loss": 1.2003,
"step": 360
},
{
"epoch": 0.6297853984686725,
"grad_norm": 3.4214556217193604,
"learning_rate": 1e-05,
"loss": 1.2385,
"step": 365
},
{
"epoch": 0.6384125957079694,
"grad_norm": 3.459791898727417,
"learning_rate": 1e-05,
"loss": 1.2198,
"step": 370
},
{
"epoch": 0.6470397929472662,
"grad_norm": 3.77476167678833,
"learning_rate": 1e-05,
"loss": 1.3135,
"step": 375
},
{
"epoch": 0.6556669901865632,
"grad_norm": 3.092871904373169,
"learning_rate": 1e-05,
"loss": 1.3234,
"step": 380
},
{
"epoch": 0.66429418742586,
"grad_norm": 3.2897961139678955,
"learning_rate": 1e-05,
"loss": 1.3376,
"step": 385
},
{
"epoch": 0.6729213846651569,
"grad_norm": 3.227506399154663,
"learning_rate": 1e-05,
"loss": 1.2237,
"step": 390
},
{
"epoch": 0.6815485819044538,
"grad_norm": 3.3434855937957764,
"learning_rate": 1e-05,
"loss": 1.2465,
"step": 395
},
{
"epoch": 0.6901757791437507,
"grad_norm": 3.5809898376464844,
"learning_rate": 1e-05,
"loss": 1.2188,
"step": 400
},
{
"epoch": 0.6988029763830476,
"grad_norm": 3.5106072425842285,
"learning_rate": 1e-05,
"loss": 1.2663,
"step": 405
},
{
"epoch": 0.7074301736223444,
"grad_norm": 3.0715136528015137,
"learning_rate": 1e-05,
"loss": 1.3354,
"step": 410
},
{
"epoch": 0.7160573708616413,
"grad_norm": 3.441499948501587,
"learning_rate": 1e-05,
"loss": 1.3112,
"step": 415
},
{
"epoch": 0.7246845681009382,
"grad_norm": 2.81852388381958,
"learning_rate": 1e-05,
"loss": 1.2335,
"step": 420
},
{
"epoch": 0.7333117653402351,
"grad_norm": 4.062169075012207,
"learning_rate": 1e-05,
"loss": 1.2291,
"step": 425
},
{
"epoch": 0.741938962579532,
"grad_norm": 3.453822612762451,
"learning_rate": 1e-05,
"loss": 1.1676,
"step": 430
},
{
"epoch": 0.7505661598188289,
"grad_norm": 3.2253923416137695,
"learning_rate": 1e-05,
"loss": 1.2539,
"step": 435
},
{
"epoch": 0.7591933570581257,
"grad_norm": 3.092754364013672,
"learning_rate": 1e-05,
"loss": 1.2994,
"step": 440
},
{
"epoch": 0.7678205542974226,
"grad_norm": 3.07718825340271,
"learning_rate": 1e-05,
"loss": 1.2304,
"step": 445
},
{
"epoch": 0.7764477515367195,
"grad_norm": 3.2939090728759766,
"learning_rate": 1e-05,
"loss": 1.2871,
"step": 450
},
{
"epoch": 0.7850749487760164,
"grad_norm": 3.8047966957092285,
"learning_rate": 1e-05,
"loss": 1.3053,
"step": 455
},
{
"epoch": 0.7937021460153133,
"grad_norm": 4.2863969802856445,
"learning_rate": 1e-05,
"loss": 1.2691,
"step": 460
},
{
"epoch": 0.8023293432546101,
"grad_norm": 3.9592127799987793,
"learning_rate": 1e-05,
"loss": 1.2744,
"step": 465
},
{
"epoch": 0.8109565404939071,
"grad_norm": 4.489944934844971,
"learning_rate": 1e-05,
"loss": 1.2016,
"step": 470
},
{
"epoch": 0.8195837377332039,
"grad_norm": 3.259884834289551,
"learning_rate": 1e-05,
"loss": 1.2787,
"step": 475
},
{
"epoch": 0.8282109349725008,
"grad_norm": 3.40492582321167,
"learning_rate": 1e-05,
"loss": 1.3095,
"step": 480
},
{
"epoch": 0.8368381322117977,
"grad_norm": 3.3192970752716064,
"learning_rate": 1e-05,
"loss": 1.2503,
"step": 485
},
{
"epoch": 0.8454653294510945,
"grad_norm": 3.331552743911743,
"learning_rate": 1e-05,
"loss": 1.2598,
"step": 490
},
{
"epoch": 0.8540925266903915,
"grad_norm": 3.073087692260742,
"learning_rate": 1e-05,
"loss": 1.2914,
"step": 495
},
{
"epoch": 0.8627197239296883,
"grad_norm": 3.344917058944702,
"learning_rate": 1e-05,
"loss": 1.2744,
"step": 500
},
{
"epoch": 0.8713469211689853,
"grad_norm": 2.9080522060394287,
"learning_rate": 1e-05,
"loss": 1.3817,
"step": 505
},
{
"epoch": 0.8799741184082821,
"grad_norm": 3.2660365104675293,
"learning_rate": 1e-05,
"loss": 1.1628,
"step": 510
},
{
"epoch": 0.8886013156475789,
"grad_norm": 3.2718842029571533,
"learning_rate": 1e-05,
"loss": 1.2602,
"step": 515
},
{
"epoch": 0.8972285128868759,
"grad_norm": 3.0166728496551514,
"learning_rate": 1e-05,
"loss": 1.2036,
"step": 520
},
{
"epoch": 0.9058557101261727,
"grad_norm": 3.566046953201294,
"learning_rate": 1e-05,
"loss": 1.2575,
"step": 525
},
{
"epoch": 0.9144829073654697,
"grad_norm": 3.3579084873199463,
"learning_rate": 1e-05,
"loss": 1.2762,
"step": 530
},
{
"epoch": 0.9231101046047665,
"grad_norm": 3.251415252685547,
"learning_rate": 1e-05,
"loss": 1.299,
"step": 535
},
{
"epoch": 0.9317373018440634,
"grad_norm": 3.4540982246398926,
"learning_rate": 1e-05,
"loss": 1.2246,
"step": 540
},
{
"epoch": 0.9403644990833603,
"grad_norm": 3.0218403339385986,
"learning_rate": 1e-05,
"loss": 1.2069,
"step": 545
},
{
"epoch": 0.9489916963226572,
"grad_norm": 3.457592248916626,
"learning_rate": 1e-05,
"loss": 1.244,
"step": 550
},
{
"epoch": 0.9576188935619541,
"grad_norm": 2.8288912773132324,
"learning_rate": 1e-05,
"loss": 1.2785,
"step": 555
},
{
"epoch": 0.9662460908012509,
"grad_norm": 3.9383344650268555,
"learning_rate": 1e-05,
"loss": 1.2542,
"step": 560
},
{
"epoch": 0.9748732880405478,
"grad_norm": 3.215847969055176,
"learning_rate": 1e-05,
"loss": 1.2649,
"step": 565
},
{
"epoch": 0.9835004852798447,
"grad_norm": 3.3479530811309814,
"learning_rate": 1e-05,
"loss": 1.2963,
"step": 570
},
{
"epoch": 0.9921276825191416,
"grad_norm": 3.1215426921844482,
"learning_rate": 1e-05,
"loss": 1.2534,
"step": 575
},
{
"epoch": 1.0007548797584385,
"grad_norm": 3.651639223098755,
"learning_rate": 1e-05,
"loss": 1.1385,
"step": 580
},
{
"epoch": 1.0093820769977353,
"grad_norm": 3.4434738159179688,
"learning_rate": 1e-05,
"loss": 0.8563,
"step": 585
},
{
"epoch": 1.0180092742370321,
"grad_norm": 4.103019714355469,
"learning_rate": 1e-05,
"loss": 0.9018,
"step": 590
},
{
"epoch": 1.0266364714763292,
"grad_norm": 3.472033977508545,
"learning_rate": 1e-05,
"loss": 0.8435,
"step": 595
},
{
"epoch": 1.035263668715626,
"grad_norm": 3.869497537612915,
"learning_rate": 1e-05,
"loss": 0.7686,
"step": 600
},
{
"epoch": 1.0438908659549229,
"grad_norm": 3.7982940673828125,
"learning_rate": 1e-05,
"loss": 0.7134,
"step": 605
},
{
"epoch": 1.0525180631942197,
"grad_norm": 3.038923978805542,
"learning_rate": 1e-05,
"loss": 0.7836,
"step": 610
},
{
"epoch": 1.0611452604335168,
"grad_norm": 3.709296464920044,
"learning_rate": 1e-05,
"loss": 0.8263,
"step": 615
},
{
"epoch": 1.0697724576728136,
"grad_norm": 3.110173225402832,
"learning_rate": 1e-05,
"loss": 0.8028,
"step": 620
},
{
"epoch": 1.0783996549121104,
"grad_norm": 4.099541187286377,
"learning_rate": 1e-05,
"loss": 0.7552,
"step": 625
},
{
"epoch": 1.0870268521514073,
"grad_norm": 3.3552350997924805,
"learning_rate": 1e-05,
"loss": 0.838,
"step": 630
},
{
"epoch": 1.095654049390704,
"grad_norm": 3.6320431232452393,
"learning_rate": 1e-05,
"loss": 0.7915,
"step": 635
},
{
"epoch": 1.1042812466300012,
"grad_norm": 3.646231174468994,
"learning_rate": 1e-05,
"loss": 0.7522,
"step": 640
},
{
"epoch": 1.112908443869298,
"grad_norm": 3.390377998352051,
"learning_rate": 1e-05,
"loss": 0.7777,
"step": 645
},
{
"epoch": 1.1215356411085948,
"grad_norm": 3.605112075805664,
"learning_rate": 1e-05,
"loss": 0.8388,
"step": 650
},
{
"epoch": 1.1301628383478917,
"grad_norm": 3.313898801803589,
"learning_rate": 1e-05,
"loss": 0.8455,
"step": 655
},
{
"epoch": 1.1387900355871885,
"grad_norm": 3.3568379878997803,
"learning_rate": 1e-05,
"loss": 0.8048,
"step": 660
},
{
"epoch": 1.1474172328264856,
"grad_norm": 3.5753304958343506,
"learning_rate": 1e-05,
"loss": 0.7762,
"step": 665
},
{
"epoch": 1.1560444300657824,
"grad_norm": 3.9311811923980713,
"learning_rate": 1e-05,
"loss": 0.7812,
"step": 670
},
{
"epoch": 1.1646716273050792,
"grad_norm": 3.399244546890259,
"learning_rate": 1e-05,
"loss": 0.8134,
"step": 675
},
{
"epoch": 1.173298824544376,
"grad_norm": 3.5281805992126465,
"learning_rate": 1e-05,
"loss": 0.7821,
"step": 680
},
{
"epoch": 1.1819260217836731,
"grad_norm": 3.510946273803711,
"learning_rate": 1e-05,
"loss": 0.8034,
"step": 685
},
{
"epoch": 1.19055321902297,
"grad_norm": 3.504866361618042,
"learning_rate": 1e-05,
"loss": 0.7592,
"step": 690
},
{
"epoch": 1.1991804162622668,
"grad_norm": 3.339489698410034,
"learning_rate": 1e-05,
"loss": 0.7738,
"step": 695
},
{
"epoch": 1.2078076135015636,
"grad_norm": 2.915128231048584,
"learning_rate": 1e-05,
"loss": 0.7043,
"step": 700
},
{
"epoch": 1.2164348107408607,
"grad_norm": 3.4995436668395996,
"learning_rate": 1e-05,
"loss": 0.7969,
"step": 705
},
{
"epoch": 1.2250620079801575,
"grad_norm": 3.3331191539764404,
"learning_rate": 1e-05,
"loss": 0.7299,
"step": 710
},
{
"epoch": 1.2336892052194544,
"grad_norm": 3.898615598678589,
"learning_rate": 1e-05,
"loss": 0.811,
"step": 715
},
{
"epoch": 1.2423164024587512,
"grad_norm": 3.1952695846557617,
"learning_rate": 1e-05,
"loss": 0.7714,
"step": 720
},
{
"epoch": 1.250943599698048,
"grad_norm": 3.310316801071167,
"learning_rate": 1e-05,
"loss": 0.8388,
"step": 725
},
{
"epoch": 1.259570796937345,
"grad_norm": 3.0263495445251465,
"learning_rate": 1e-05,
"loss": 0.8244,
"step": 730
},
{
"epoch": 1.268197994176642,
"grad_norm": 3.4661359786987305,
"learning_rate": 1e-05,
"loss": 0.8326,
"step": 735
},
{
"epoch": 1.2768251914159388,
"grad_norm": 3.4017932415008545,
"learning_rate": 1e-05,
"loss": 0.8302,
"step": 740
},
{
"epoch": 1.2854523886552356,
"grad_norm": 3.6982741355895996,
"learning_rate": 1e-05,
"loss": 0.7911,
"step": 745
},
{
"epoch": 1.2940795858945324,
"grad_norm": 3.737339973449707,
"learning_rate": 1e-05,
"loss": 0.8836,
"step": 750
},
{
"epoch": 1.3027067831338295,
"grad_norm": 3.491697311401367,
"learning_rate": 1e-05,
"loss": 0.8023,
"step": 755
},
{
"epoch": 1.3113339803731263,
"grad_norm": 3.9661755561828613,
"learning_rate": 1e-05,
"loss": 0.8338,
"step": 760
},
{
"epoch": 1.3199611776124232,
"grad_norm": 3.4925425052642822,
"learning_rate": 1e-05,
"loss": 0.8247,
"step": 765
},
{
"epoch": 1.32858837485172,
"grad_norm": 3.0747172832489014,
"learning_rate": 1e-05,
"loss": 0.8781,
"step": 770
},
{
"epoch": 1.3372155720910168,
"grad_norm": 3.2208268642425537,
"learning_rate": 1e-05,
"loss": 0.7967,
"step": 775
},
{
"epoch": 1.3458427693303139,
"grad_norm": 3.751079559326172,
"learning_rate": 1e-05,
"loss": 0.7918,
"step": 780
},
{
"epoch": 1.3544699665696107,
"grad_norm": 3.1584877967834473,
"learning_rate": 1e-05,
"loss": 0.7784,
"step": 785
},
{
"epoch": 1.3630971638089076,
"grad_norm": 3.420969009399414,
"learning_rate": 1e-05,
"loss": 0.8017,
"step": 790
},
{
"epoch": 1.3717243610482044,
"grad_norm": 3.333355188369751,
"learning_rate": 1e-05,
"loss": 0.7803,
"step": 795
},
{
"epoch": 1.3803515582875012,
"grad_norm": 3.5859718322753906,
"learning_rate": 1e-05,
"loss": 0.8341,
"step": 800
},
{
"epoch": 1.3889787555267983,
"grad_norm": 3.3463239669799805,
"learning_rate": 1e-05,
"loss": 0.7977,
"step": 805
},
{
"epoch": 1.3976059527660951,
"grad_norm": 3.34783935546875,
"learning_rate": 1e-05,
"loss": 0.778,
"step": 810
},
{
"epoch": 1.406233150005392,
"grad_norm": 4.29722261428833,
"learning_rate": 1e-05,
"loss": 0.8107,
"step": 815
},
{
"epoch": 1.414860347244689,
"grad_norm": 3.2892956733703613,
"learning_rate": 1e-05,
"loss": 0.753,
"step": 820
},
{
"epoch": 1.4234875444839858,
"grad_norm": 3.7883739471435547,
"learning_rate": 1e-05,
"loss": 0.8111,
"step": 825
},
{
"epoch": 1.4321147417232827,
"grad_norm": 3.545917510986328,
"learning_rate": 1e-05,
"loss": 0.7559,
"step": 830
},
{
"epoch": 1.4407419389625795,
"grad_norm": 3.5111639499664307,
"learning_rate": 1e-05,
"loss": 0.8213,
"step": 835
},
{
"epoch": 1.4493691362018764,
"grad_norm": 3.9835708141326904,
"learning_rate": 1e-05,
"loss": 0.9053,
"step": 840
},
{
"epoch": 1.4579963334411734,
"grad_norm": 3.5352683067321777,
"learning_rate": 1e-05,
"loss": 0.7486,
"step": 845
},
{
"epoch": 1.4666235306804702,
"grad_norm": 3.8274669647216797,
"learning_rate": 1e-05,
"loss": 0.8385,
"step": 850
},
{
"epoch": 1.475250727919767,
"grad_norm": 3.425276041030884,
"learning_rate": 1e-05,
"loss": 0.8994,
"step": 855
},
{
"epoch": 1.483877925159064,
"grad_norm": 3.498198986053467,
"learning_rate": 1e-05,
"loss": 0.7993,
"step": 860
},
{
"epoch": 1.4925051223983608,
"grad_norm": 3.5711140632629395,
"learning_rate": 1e-05,
"loss": 0.8415,
"step": 865
},
{
"epoch": 1.5011323196376578,
"grad_norm": 3.628063917160034,
"learning_rate": 1e-05,
"loss": 0.7544,
"step": 870
},
{
"epoch": 1.5097595168769546,
"grad_norm": 3.185468912124634,
"learning_rate": 1e-05,
"loss": 0.8997,
"step": 875
},
{
"epoch": 1.5183867141162515,
"grad_norm": 3.289321184158325,
"learning_rate": 1e-05,
"loss": 0.7673,
"step": 880
},
{
"epoch": 1.5270139113555483,
"grad_norm": 3.4474823474884033,
"learning_rate": 1e-05,
"loss": 0.8582,
"step": 885
},
{
"epoch": 1.5356411085948452,
"grad_norm": 4.132356643676758,
"learning_rate": 1e-05,
"loss": 0.7828,
"step": 890
},
{
"epoch": 1.5442683058341422,
"grad_norm": 3.1645920276641846,
"learning_rate": 1e-05,
"loss": 0.8359,
"step": 895
},
{
"epoch": 1.552895503073439,
"grad_norm": 4.218339443206787,
"learning_rate": 1e-05,
"loss": 0.8226,
"step": 900
},
{
"epoch": 1.5615227003127359,
"grad_norm": 3.5735368728637695,
"learning_rate": 1e-05,
"loss": 0.8219,
"step": 905
},
{
"epoch": 1.570149897552033,
"grad_norm": 3.3347320556640625,
"learning_rate": 1e-05,
"loss": 0.8212,
"step": 910
},
{
"epoch": 1.5787770947913295,
"grad_norm": 3.6230201721191406,
"learning_rate": 1e-05,
"loss": 0.8036,
"step": 915
},
{
"epoch": 1.5874042920306266,
"grad_norm": 3.4478774070739746,
"learning_rate": 1e-05,
"loss": 0.7633,
"step": 920
},
{
"epoch": 1.5960314892699234,
"grad_norm": 3.934248924255371,
"learning_rate": 1e-05,
"loss": 0.7673,
"step": 925
},
{
"epoch": 1.6046586865092203,
"grad_norm": 3.3679585456848145,
"learning_rate": 1e-05,
"loss": 0.7732,
"step": 930
},
{
"epoch": 1.6132858837485173,
"grad_norm": 3.6777756214141846,
"learning_rate": 1e-05,
"loss": 0.7941,
"step": 935
},
{
"epoch": 1.621913080987814,
"grad_norm": 3.4815165996551514,
"learning_rate": 1e-05,
"loss": 0.8184,
"step": 940
},
{
"epoch": 1.630540278227111,
"grad_norm": 3.4345767498016357,
"learning_rate": 1e-05,
"loss": 0.8496,
"step": 945
},
{
"epoch": 1.6391674754664078,
"grad_norm": 3.3284542560577393,
"learning_rate": 1e-05,
"loss": 0.888,
"step": 950
},
{
"epoch": 1.6477946727057047,
"grad_norm": 3.9973185062408447,
"learning_rate": 1e-05,
"loss": 0.8551,
"step": 955
},
{
"epoch": 1.6564218699450017,
"grad_norm": 3.136579751968384,
"learning_rate": 1e-05,
"loss": 0.8184,
"step": 960
},
{
"epoch": 1.6650490671842983,
"grad_norm": 3.745621919631958,
"learning_rate": 1e-05,
"loss": 0.8045,
"step": 965
},
{
"epoch": 1.6736762644235954,
"grad_norm": 3.2420082092285156,
"learning_rate": 1e-05,
"loss": 0.7489,
"step": 970
},
{
"epoch": 1.6823034616628922,
"grad_norm": 3.52974009513855,
"learning_rate": 1e-05,
"loss": 0.7816,
"step": 975
},
{
"epoch": 1.690930658902189,
"grad_norm": 3.9357786178588867,
"learning_rate": 1e-05,
"loss": 0.884,
"step": 980
},
{
"epoch": 1.6995578561414861,
"grad_norm": 3.807739734649658,
"learning_rate": 1e-05,
"loss": 0.9077,
"step": 985
},
{
"epoch": 1.708185053380783,
"grad_norm": 3.0585408210754395,
"learning_rate": 1e-05,
"loss": 0.8371,
"step": 990
},
{
"epoch": 1.7168122506200798,
"grad_norm": 3.0159707069396973,
"learning_rate": 1e-05,
"loss": 0.8028,
"step": 995
},
{
"epoch": 1.7254394478593766,
"grad_norm": 3.9987428188323975,
"learning_rate": 1e-05,
"loss": 0.7969,
"step": 1000
},
{
"epoch": 1.7340666450986735,
"grad_norm": 3.4167709350585938,
"learning_rate": 1e-05,
"loss": 0.8557,
"step": 1005
},
{
"epoch": 1.7426938423379705,
"grad_norm": 3.235368251800537,
"learning_rate": 1e-05,
"loss": 0.7524,
"step": 1010
},
{
"epoch": 1.7513210395772674,
"grad_norm": 3.3228580951690674,
"learning_rate": 1e-05,
"loss": 0.8103,
"step": 1015
},
{
"epoch": 1.7599482368165642,
"grad_norm": 3.2793571949005127,
"learning_rate": 1e-05,
"loss": 0.7795,
"step": 1020
},
{
"epoch": 1.7685754340558613,
"grad_norm": 3.4918506145477295,
"learning_rate": 1e-05,
"loss": 0.8534,
"step": 1025
},
{
"epoch": 1.7772026312951579,
"grad_norm": 3.5630784034729004,
"learning_rate": 1e-05,
"loss": 0.8371,
"step": 1030
},
{
"epoch": 1.785829828534455,
"grad_norm": 3.330843210220337,
"learning_rate": 1e-05,
"loss": 0.7688,
"step": 1035
},
{
"epoch": 1.7944570257737518,
"grad_norm": 3.340770721435547,
"learning_rate": 1e-05,
"loss": 0.7823,
"step": 1040
},
{
"epoch": 1.8030842230130486,
"grad_norm": 3.48885440826416,
"learning_rate": 1e-05,
"loss": 0.8135,
"step": 1045
},
{
"epoch": 1.8117114202523457,
"grad_norm": 3.783395528793335,
"learning_rate": 1e-05,
"loss": 0.8169,
"step": 1050
},
{
"epoch": 1.8203386174916423,
"grad_norm": 3.1166722774505615,
"learning_rate": 1e-05,
"loss": 0.846,
"step": 1055
},
{
"epoch": 1.8289658147309393,
"grad_norm": 3.627532720565796,
"learning_rate": 1e-05,
"loss": 0.8055,
"step": 1060
},
{
"epoch": 1.8375930119702362,
"grad_norm": 3.264894723892212,
"learning_rate": 1e-05,
"loss": 0.8216,
"step": 1065
},
{
"epoch": 1.846220209209533,
"grad_norm": 3.652085781097412,
"learning_rate": 1e-05,
"loss": 0.8663,
"step": 1070
},
{
"epoch": 1.85484740644883,
"grad_norm": 3.269554376602173,
"learning_rate": 1e-05,
"loss": 0.8332,
"step": 1075
},
{
"epoch": 1.8634746036881267,
"grad_norm": 3.3206093311309814,
"learning_rate": 1e-05,
"loss": 0.8408,
"step": 1080
},
{
"epoch": 1.8721018009274237,
"grad_norm": 4.427550792694092,
"learning_rate": 1e-05,
"loss": 0.828,
"step": 1085
},
{
"epoch": 1.8807289981667206,
"grad_norm": 3.235623359680176,
"learning_rate": 1e-05,
"loss": 0.8127,
"step": 1090
},
{
"epoch": 1.8893561954060174,
"grad_norm": 3.4541192054748535,
"learning_rate": 1e-05,
"loss": 0.8607,
"step": 1095
},
{
"epoch": 1.8979833926453145,
"grad_norm": 3.4523119926452637,
"learning_rate": 1e-05,
"loss": 0.9251,
"step": 1100
},
{
"epoch": 1.906610589884611,
"grad_norm": 3.4309825897216797,
"learning_rate": 1e-05,
"loss": 0.8388,
"step": 1105
},
{
"epoch": 1.9152377871239081,
"grad_norm": 3.8286280632019043,
"learning_rate": 1e-05,
"loss": 0.8036,
"step": 1110
},
{
"epoch": 1.923864984363205,
"grad_norm": 3.4782304763793945,
"learning_rate": 1e-05,
"loss": 0.8001,
"step": 1115
},
{
"epoch": 1.9324921816025018,
"grad_norm": 3.265873432159424,
"learning_rate": 1e-05,
"loss": 0.775,
"step": 1120
},
{
"epoch": 1.9411193788417989,
"grad_norm": 3.65558123588562,
"learning_rate": 1e-05,
"loss": 0.8639,
"step": 1125
},
{
"epoch": 1.9497465760810957,
"grad_norm": 3.7924466133117676,
"learning_rate": 1e-05,
"loss": 0.8513,
"step": 1130
},
{
"epoch": 1.9583737733203925,
"grad_norm": 3.99310564994812,
"learning_rate": 1e-05,
"loss": 0.77,
"step": 1135
},
{
"epoch": 1.9670009705596894,
"grad_norm": 3.121508836746216,
"learning_rate": 1e-05,
"loss": 0.732,
"step": 1140
},
{
"epoch": 1.9756281677989862,
"grad_norm": 3.812880277633667,
"learning_rate": 1e-05,
"loss": 0.8029,
"step": 1145
},
{
"epoch": 1.9842553650382833,
"grad_norm": 3.398724317550659,
"learning_rate": 1e-05,
"loss": 0.8205,
"step": 1150
},
{
"epoch": 1.99288256227758,
"grad_norm": 3.3330962657928467,
"learning_rate": 1e-05,
"loss": 0.7995,
"step": 1155
},
{
"epoch": 2.001509759516877,
"grad_norm": 4.028820991516113,
"learning_rate": 1e-05,
"loss": 0.7343,
"step": 1160
},
{
"epoch": 2.010136956756174,
"grad_norm": 4.329206943511963,
"learning_rate": 1e-05,
"loss": 0.4413,
"step": 1165
},
{
"epoch": 2.0187641539954706,
"grad_norm": 7.581143379211426,
"learning_rate": 1e-05,
"loss": 0.4171,
"step": 1170
},
{
"epoch": 2.0273913512347677,
"grad_norm": 3.6165997982025146,
"learning_rate": 1e-05,
"loss": 0.3829,
"step": 1175
},
{
"epoch": 2.0360185484740643,
"grad_norm": 3.6805825233459473,
"learning_rate": 1e-05,
"loss": 0.3505,
"step": 1180
},
{
"epoch": 2.0446457457133613,
"grad_norm": 3.5917325019836426,
"learning_rate": 1e-05,
"loss": 0.3448,
"step": 1185
},
{
"epoch": 2.0532729429526584,
"grad_norm": 4.101263046264648,
"learning_rate": 1e-05,
"loss": 0.3737,
"step": 1190
},
{
"epoch": 2.061900140191955,
"grad_norm": 4.450289726257324,
"learning_rate": 1e-05,
"loss": 0.3939,
"step": 1195
},
{
"epoch": 2.070527337431252,
"grad_norm": 3.6648216247558594,
"learning_rate": 1e-05,
"loss": 0.3638,
"step": 1200
},
{
"epoch": 2.079154534670549,
"grad_norm": 4.237855434417725,
"learning_rate": 1e-05,
"loss": 0.3634,
"step": 1205
},
{
"epoch": 2.0877817319098457,
"grad_norm": 4.677015781402588,
"learning_rate": 1e-05,
"loss": 0.4462,
"step": 1210
},
{
"epoch": 2.096408929149143,
"grad_norm": 3.543541431427002,
"learning_rate": 1e-05,
"loss": 0.4071,
"step": 1215
},
{
"epoch": 2.1050361263884394,
"grad_norm": 4.441009521484375,
"learning_rate": 1e-05,
"loss": 0.3735,
"step": 1220
},
{
"epoch": 2.1136633236277365,
"grad_norm": 3.5603976249694824,
"learning_rate": 1e-05,
"loss": 0.383,
"step": 1225
},
{
"epoch": 2.1222905208670335,
"grad_norm": 3.347618579864502,
"learning_rate": 1e-05,
"loss": 0.3077,
"step": 1230
},
{
"epoch": 2.13091771810633,
"grad_norm": 3.57377028465271,
"learning_rate": 1e-05,
"loss": 0.3774,
"step": 1235
},
{
"epoch": 2.139544915345627,
"grad_norm": 3.4287397861480713,
"learning_rate": 1e-05,
"loss": 0.3388,
"step": 1240
},
{
"epoch": 2.148172112584924,
"grad_norm": 3.9330341815948486,
"learning_rate": 1e-05,
"loss": 0.3848,
"step": 1245
},
{
"epoch": 2.156799309824221,
"grad_norm": 3.7925400733947754,
"learning_rate": 1e-05,
"loss": 0.4173,
"step": 1250
},
{
"epoch": 2.165426507063518,
"grad_norm": 3.818533420562744,
"learning_rate": 1e-05,
"loss": 0.3514,
"step": 1255
},
{
"epoch": 2.1740537043028145,
"grad_norm": 4.525712013244629,
"learning_rate": 1e-05,
"loss": 0.393,
"step": 1260
},
{
"epoch": 2.1826809015421116,
"grad_norm": 3.9103636741638184,
"learning_rate": 1e-05,
"loss": 0.3886,
"step": 1265
},
{
"epoch": 2.191308098781408,
"grad_norm": 4.36718225479126,
"learning_rate": 1e-05,
"loss": 0.3943,
"step": 1270
},
{
"epoch": 2.1999352960207053,
"grad_norm": 4.249504566192627,
"learning_rate": 1e-05,
"loss": 0.3562,
"step": 1275
},
{
"epoch": 2.2085624932600023,
"grad_norm": 3.6772570610046387,
"learning_rate": 1e-05,
"loss": 0.3609,
"step": 1280
},
{
"epoch": 2.217189690499299,
"grad_norm": 4.188706398010254,
"learning_rate": 1e-05,
"loss": 0.4031,
"step": 1285
},
{
"epoch": 2.225816887738596,
"grad_norm": 4.41935920715332,
"learning_rate": 1e-05,
"loss": 0.3989,
"step": 1290
},
{
"epoch": 2.234444084977893,
"grad_norm": 3.972947359085083,
"learning_rate": 1e-05,
"loss": 0.4016,
"step": 1295
},
{
"epoch": 2.2430712822171897,
"grad_norm": 3.753408193588257,
"learning_rate": 1e-05,
"loss": 0.3735,
"step": 1300
},
{
"epoch": 2.2516984794564867,
"grad_norm": 3.882584810256958,
"learning_rate": 1e-05,
"loss": 0.376,
"step": 1305
},
{
"epoch": 2.2603256766957833,
"grad_norm": 3.9297213554382324,
"learning_rate": 1e-05,
"loss": 0.4118,
"step": 1310
},
{
"epoch": 2.2689528739350804,
"grad_norm": 4.477977752685547,
"learning_rate": 1e-05,
"loss": 0.4483,
"step": 1315
},
{
"epoch": 2.277580071174377,
"grad_norm": 4.420772552490234,
"learning_rate": 1e-05,
"loss": 0.3646,
"step": 1320
},
{
"epoch": 2.286207268413674,
"grad_norm": 4.0902276039123535,
"learning_rate": 1e-05,
"loss": 0.3901,
"step": 1325
},
{
"epoch": 2.294834465652971,
"grad_norm": 3.598499298095703,
"learning_rate": 1e-05,
"loss": 0.3684,
"step": 1330
},
{
"epoch": 2.3034616628922677,
"grad_norm": 3.4670894145965576,
"learning_rate": 1e-05,
"loss": 0.3885,
"step": 1335
},
{
"epoch": 2.312088860131565,
"grad_norm": 4.802315711975098,
"learning_rate": 1e-05,
"loss": 0.424,
"step": 1340
},
{
"epoch": 2.320716057370862,
"grad_norm": 4.187905788421631,
"learning_rate": 1e-05,
"loss": 0.4194,
"step": 1345
},
{
"epoch": 2.3293432546101585,
"grad_norm": 3.7030727863311768,
"learning_rate": 1e-05,
"loss": 0.3982,
"step": 1350
},
{
"epoch": 2.3379704518494555,
"grad_norm": 4.434927463531494,
"learning_rate": 1e-05,
"loss": 0.4565,
"step": 1355
},
{
"epoch": 2.346597649088752,
"grad_norm": 4.65302038192749,
"learning_rate": 1e-05,
"loss": 0.3995,
"step": 1360
},
{
"epoch": 2.355224846328049,
"grad_norm": 4.085888862609863,
"learning_rate": 1e-05,
"loss": 0.426,
"step": 1365
},
{
"epoch": 2.3638520435673462,
"grad_norm": 4.577415466308594,
"learning_rate": 1e-05,
"loss": 0.3854,
"step": 1370
},
{
"epoch": 2.372479240806643,
"grad_norm": 4.255492210388184,
"learning_rate": 1e-05,
"loss": 0.3808,
"step": 1375
},
{
"epoch": 2.38110643804594,
"grad_norm": 3.9601423740386963,
"learning_rate": 1e-05,
"loss": 0.3598,
"step": 1380
},
{
"epoch": 2.3897336352852365,
"grad_norm": 3.984498977661133,
"learning_rate": 1e-05,
"loss": 0.4018,
"step": 1385
},
{
"epoch": 2.3983608325245336,
"grad_norm": 4.054710388183594,
"learning_rate": 1e-05,
"loss": 0.4105,
"step": 1390
},
{
"epoch": 2.4069880297638306,
"grad_norm": 3.6106574535369873,
"learning_rate": 1e-05,
"loss": 0.3832,
"step": 1395
},
{
"epoch": 2.4156152270031273,
"grad_norm": 3.7792673110961914,
"learning_rate": 1e-05,
"loss": 0.4288,
"step": 1400
},
{
"epoch": 2.4242424242424243,
"grad_norm": 4.984143257141113,
"learning_rate": 1e-05,
"loss": 0.3759,
"step": 1405
},
{
"epoch": 2.4328696214817214,
"grad_norm": 4.424108028411865,
"learning_rate": 1e-05,
"loss": 0.3981,
"step": 1410
},
{
"epoch": 2.441496818721018,
"grad_norm": 3.914560079574585,
"learning_rate": 1e-05,
"loss": 0.3461,
"step": 1415
},
{
"epoch": 2.450124015960315,
"grad_norm": 3.667935848236084,
"learning_rate": 1e-05,
"loss": 0.3898,
"step": 1420
},
{
"epoch": 2.4587512131996117,
"grad_norm": 3.2983341217041016,
"learning_rate": 1e-05,
"loss": 0.36,
"step": 1425
},
{
"epoch": 2.4673784104389087,
"grad_norm": 5.143230438232422,
"learning_rate": 1e-05,
"loss": 0.4348,
"step": 1430
},
{
"epoch": 2.4760056076782053,
"grad_norm": 3.818688154220581,
"learning_rate": 1e-05,
"loss": 0.3582,
"step": 1435
},
{
"epoch": 2.4846328049175024,
"grad_norm": 4.086068153381348,
"learning_rate": 1e-05,
"loss": 0.4337,
"step": 1440
},
{
"epoch": 2.4932600021567994,
"grad_norm": 3.717658281326294,
"learning_rate": 1e-05,
"loss": 0.4196,
"step": 1445
},
{
"epoch": 2.501887199396096,
"grad_norm": 3.619304895401001,
"learning_rate": 1e-05,
"loss": 0.3901,
"step": 1450
},
{
"epoch": 2.510514396635393,
"grad_norm": 4.011234283447266,
"learning_rate": 1e-05,
"loss": 0.3864,
"step": 1455
},
{
"epoch": 2.51914159387469,
"grad_norm": 3.993927478790283,
"learning_rate": 1e-05,
"loss": 0.3911,
"step": 1460
},
{
"epoch": 2.527768791113987,
"grad_norm": 4.390587329864502,
"learning_rate": 1e-05,
"loss": 0.4008,
"step": 1465
},
{
"epoch": 2.536395988353284,
"grad_norm": 4.767730236053467,
"learning_rate": 1e-05,
"loss": 0.3738,
"step": 1470
},
{
"epoch": 2.5450231855925805,
"grad_norm": 3.377415180206299,
"learning_rate": 1e-05,
"loss": 0.3892,
"step": 1475
},
{
"epoch": 2.5536503828318775,
"grad_norm": 3.5132322311401367,
"learning_rate": 1e-05,
"loss": 0.4022,
"step": 1480
},
{
"epoch": 2.562277580071174,
"grad_norm": 3.9030888080596924,
"learning_rate": 1e-05,
"loss": 0.436,
"step": 1485
},
{
"epoch": 2.570904777310471,
"grad_norm": 3.88025164604187,
"learning_rate": 1e-05,
"loss": 0.4164,
"step": 1490
},
{
"epoch": 2.5795319745497682,
"grad_norm": 4.036890983581543,
"learning_rate": 1e-05,
"loss": 0.3914,
"step": 1495
},
{
"epoch": 2.588159171789065,
"grad_norm": 3.56758189201355,
"learning_rate": 1e-05,
"loss": 0.3878,
"step": 1500
},
{
"epoch": 2.596786369028362,
"grad_norm": 3.9577293395996094,
"learning_rate": 1e-05,
"loss": 0.39,
"step": 1505
},
{
"epoch": 2.605413566267659,
"grad_norm": 4.392646312713623,
"learning_rate": 1e-05,
"loss": 0.3989,
"step": 1510
},
{
"epoch": 2.6140407635069556,
"grad_norm": 4.026916027069092,
"learning_rate": 1e-05,
"loss": 0.3613,
"step": 1515
},
{
"epoch": 2.6226679607462526,
"grad_norm": 4.357356548309326,
"learning_rate": 1e-05,
"loss": 0.3995,
"step": 1520
},
{
"epoch": 2.6312951579855497,
"grad_norm": 3.703214406967163,
"learning_rate": 1e-05,
"loss": 0.3376,
"step": 1525
},
{
"epoch": 2.6399223552248463,
"grad_norm": 3.8401548862457275,
"learning_rate": 1e-05,
"loss": 0.3861,
"step": 1530
},
{
"epoch": 2.6485495524641434,
"grad_norm": 3.7734174728393555,
"learning_rate": 1e-05,
"loss": 0.4193,
"step": 1535
},
{
"epoch": 2.65717674970344,
"grad_norm": 3.929262161254883,
"learning_rate": 1e-05,
"loss": 0.4235,
"step": 1540
},
{
"epoch": 2.665803946942737,
"grad_norm": 4.2804975509643555,
"learning_rate": 1e-05,
"loss": 0.39,
"step": 1545
},
{
"epoch": 2.6744311441820336,
"grad_norm": 4.476975440979004,
"learning_rate": 1e-05,
"loss": 0.4395,
"step": 1550
},
{
"epoch": 2.6830583414213307,
"grad_norm": 3.710632562637329,
"learning_rate": 1e-05,
"loss": 0.3956,
"step": 1555
},
{
"epoch": 2.6916855386606278,
"grad_norm": 5.090831756591797,
"learning_rate": 1e-05,
"loss": 0.4399,
"step": 1560
},
{
"epoch": 2.7003127358999244,
"grad_norm": 4.323583602905273,
"learning_rate": 1e-05,
"loss": 0.4161,
"step": 1565
},
{
"epoch": 2.7089399331392214,
"grad_norm": 4.236275672912598,
"learning_rate": 1e-05,
"loss": 0.4128,
"step": 1570
},
{
"epoch": 2.7175671303785185,
"grad_norm": 4.034735202789307,
"learning_rate": 1e-05,
"loss": 0.4291,
"step": 1575
},
{
"epoch": 2.726194327617815,
"grad_norm": 4.452931880950928,
"learning_rate": 1e-05,
"loss": 0.4198,
"step": 1580
},
{
"epoch": 2.734821524857112,
"grad_norm": 3.9385485649108887,
"learning_rate": 1e-05,
"loss": 0.3954,
"step": 1585
},
{
"epoch": 2.7434487220964088,
"grad_norm": 3.8436594009399414,
"learning_rate": 1e-05,
"loss": 0.3718,
"step": 1590
},
{
"epoch": 2.752075919335706,
"grad_norm": 3.962069272994995,
"learning_rate": 1e-05,
"loss": 0.3488,
"step": 1595
},
{
"epoch": 2.7607031165750024,
"grad_norm": 4.306760787963867,
"learning_rate": 1e-05,
"loss": 0.4581,
"step": 1600
},
{
"epoch": 2.7693303138142995,
"grad_norm": 4.657399654388428,
"learning_rate": 1e-05,
"loss": 0.4455,
"step": 1605
},
{
"epoch": 2.7779575110535966,
"grad_norm": 4.039801120758057,
"learning_rate": 1e-05,
"loss": 0.3918,
"step": 1610
},
{
"epoch": 2.786584708292893,
"grad_norm": 5.203350067138672,
"learning_rate": 1e-05,
"loss": 0.4067,
"step": 1615
},
{
"epoch": 2.7952119055321902,
"grad_norm": 3.9145352840423584,
"learning_rate": 1e-05,
"loss": 0.4237,
"step": 1620
},
{
"epoch": 2.8038391027714873,
"grad_norm": 3.5493838787078857,
"learning_rate": 1e-05,
"loss": 0.3939,
"step": 1625
},
{
"epoch": 2.812466300010784,
"grad_norm": 4.310389995574951,
"learning_rate": 1e-05,
"loss": 0.4385,
"step": 1630
},
{
"epoch": 2.821093497250081,
"grad_norm": 5.43610954284668,
"learning_rate": 1e-05,
"loss": 0.4109,
"step": 1635
},
{
"epoch": 2.829720694489378,
"grad_norm": 4.191155433654785,
"learning_rate": 1e-05,
"loss": 0.4402,
"step": 1640
},
{
"epoch": 2.8383478917286746,
"grad_norm": 3.9996650218963623,
"learning_rate": 1e-05,
"loss": 0.444,
"step": 1645
},
{
"epoch": 2.8469750889679717,
"grad_norm": 10.163007736206055,
"learning_rate": 1e-05,
"loss": 0.413,
"step": 1650
},
{
"epoch": 2.8556022862072683,
"grad_norm": 3.8168654441833496,
"learning_rate": 1e-05,
"loss": 0.4245,
"step": 1655
},
{
"epoch": 2.8642294834465654,
"grad_norm": 3.9268579483032227,
"learning_rate": 1e-05,
"loss": 0.4091,
"step": 1660
},
{
"epoch": 2.872856680685862,
"grad_norm": 4.146000385284424,
"learning_rate": 1e-05,
"loss": 0.4206,
"step": 1665
},
{
"epoch": 2.881483877925159,
"grad_norm": 4.102123260498047,
"learning_rate": 1e-05,
"loss": 0.3868,
"step": 1670
},
{
"epoch": 2.890111075164456,
"grad_norm": 4.318619728088379,
"learning_rate": 1e-05,
"loss": 0.4102,
"step": 1675
},
{
"epoch": 2.8987382724037527,
"grad_norm": 4.203400611877441,
"learning_rate": 1e-05,
"loss": 0.4349,
"step": 1680
},
{
"epoch": 2.9073654696430498,
"grad_norm": 4.164772987365723,
"learning_rate": 1e-05,
"loss": 0.4298,
"step": 1685
},
{
"epoch": 2.915992666882347,
"grad_norm": 4.088376998901367,
"learning_rate": 1e-05,
"loss": 0.431,
"step": 1690
},
{
"epoch": 2.9246198641216434,
"grad_norm": 4.593983173370361,
"learning_rate": 1e-05,
"loss": 0.4373,
"step": 1695
},
{
"epoch": 2.9332470613609405,
"grad_norm": 4.246501445770264,
"learning_rate": 1e-05,
"loss": 0.4239,
"step": 1700
},
{
"epoch": 2.941874258600237,
"grad_norm": 3.8412177562713623,
"learning_rate": 1e-05,
"loss": 0.4277,
"step": 1705
},
{
"epoch": 2.950501455839534,
"grad_norm": 3.7681996822357178,
"learning_rate": 1e-05,
"loss": 0.4302,
"step": 1710
},
{
"epoch": 2.9591286530788308,
"grad_norm": 4.009012699127197,
"learning_rate": 1e-05,
"loss": 0.3822,
"step": 1715
},
{
"epoch": 2.967755850318128,
"grad_norm": 4.4853434562683105,
"learning_rate": 1e-05,
"loss": 0.4402,
"step": 1720
},
{
"epoch": 2.976383047557425,
"grad_norm": 3.743802785873413,
"learning_rate": 1e-05,
"loss": 0.3803,
"step": 1725
},
{
"epoch": 2.9850102447967215,
"grad_norm": 4.453946113586426,
"learning_rate": 1e-05,
"loss": 0.4109,
"step": 1730
},
{
"epoch": 2.9936374420360186,
"grad_norm": 3.8939476013183594,
"learning_rate": 1e-05,
"loss": 0.4232,
"step": 1735
},
{
"epoch": 2.9970883209317374,
"step": 1737,
"total_flos": 2.5609799507175014e+18,
"train_loss": 0.8316220592066139,
"train_runtime": 17540.1657,
"train_samples_per_second": 6.344,
"train_steps_per_second": 0.099
}
],
"logging_steps": 5,
"max_steps": 1737,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.5609799507175014e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}