instruct_4ef6b15 / trainer_state.json
bimabk's picture
Upload task output 1
d9fcdd8 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.999277804525758,
"eval_steps": 500,
"global_step": 12459,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001203659123736158,
"grad_norm": 4.59375,
"learning_rate": 2.0735274428673248e-05,
"loss": 1.9426,
"step": 5
},
{
"epoch": 0.002407318247472316,
"grad_norm": 3.9375,
"learning_rate": 4.66543674645148e-05,
"loss": 1.8336,
"step": 10
},
{
"epoch": 0.0036109773712084737,
"grad_norm": 3.09375,
"learning_rate": 7.257346050035636e-05,
"loss": 1.716,
"step": 15
},
{
"epoch": 0.004814636494944632,
"grad_norm": 3.078125,
"learning_rate": 9.849255353619792e-05,
"loss": 1.59,
"step": 20
},
{
"epoch": 0.00601829561868079,
"grad_norm": 3.671875,
"learning_rate": 0.00012441164657203948,
"loss": 1.532,
"step": 25
},
{
"epoch": 0.007221954742416947,
"grad_norm": 3.078125,
"learning_rate": 0.00015033073960788105,
"loss": 1.4454,
"step": 30
},
{
"epoch": 0.008425613866153106,
"grad_norm": 2.6875,
"learning_rate": 0.0001762498326437226,
"loss": 1.3962,
"step": 35
},
{
"epoch": 0.009629272989889264,
"grad_norm": 3.03125,
"learning_rate": 0.0001814336164647536,
"loss": 1.3353,
"step": 40
},
{
"epoch": 0.010832932113625422,
"grad_norm": 3.265625,
"learning_rate": 0.0001814334751461317,
"loss": 1.3248,
"step": 45
},
{
"epoch": 0.01203659123736158,
"grad_norm": 2.8125,
"learning_rate": 0.00018143322512111725,
"loss": 1.2706,
"step": 50
},
{
"epoch": 0.013240250361097737,
"grad_norm": 2.96875,
"learning_rate": 0.00018143286639010973,
"loss": 1.2645,
"step": 55
},
{
"epoch": 0.014443909484833895,
"grad_norm": 2.71875,
"learning_rate": 0.00018143239895368233,
"loss": 1.2174,
"step": 60
},
{
"epoch": 0.015647568608570053,
"grad_norm": 2.734375,
"learning_rate": 0.00018143182281258187,
"loss": 1.2203,
"step": 65
},
{
"epoch": 0.016851227732306212,
"grad_norm": 2.703125,
"learning_rate": 0.00018143113796772884,
"loss": 1.1906,
"step": 70
},
{
"epoch": 0.018054886856042368,
"grad_norm": 2.53125,
"learning_rate": 0.00018143034442021747,
"loss": 1.1788,
"step": 75
},
{
"epoch": 0.019258545979778528,
"grad_norm": 2.703125,
"learning_rate": 0.00018142944217131572,
"loss": 1.1606,
"step": 80
},
{
"epoch": 0.020462205103514684,
"grad_norm": 2.421875,
"learning_rate": 0.00018142843122246502,
"loss": 1.1618,
"step": 85
},
{
"epoch": 0.021665864227250843,
"grad_norm": 2.5,
"learning_rate": 0.00018142731157528072,
"loss": 1.1545,
"step": 90
},
{
"epoch": 0.022869523350987,
"grad_norm": 2.46875,
"learning_rate": 0.00018142608323155166,
"loss": 1.129,
"step": 95
},
{
"epoch": 0.02407318247472316,
"grad_norm": 2.40625,
"learning_rate": 0.00018142474619324043,
"loss": 1.1211,
"step": 100
},
{
"epoch": 0.025276841598459315,
"grad_norm": 2.546875,
"learning_rate": 0.00018142330046248332,
"loss": 1.0903,
"step": 105
},
{
"epoch": 0.026480500722195474,
"grad_norm": 2.296875,
"learning_rate": 0.00018142174604159016,
"loss": 1.127,
"step": 110
},
{
"epoch": 0.027684159845931634,
"grad_norm": 2.78125,
"learning_rate": 0.0001814200829330446,
"loss": 1.1246,
"step": 115
},
{
"epoch": 0.02888781896966779,
"grad_norm": 2.828125,
"learning_rate": 0.00018141831113950379,
"loss": 1.0981,
"step": 120
},
{
"epoch": 0.03009147809340395,
"grad_norm": 2.359375,
"learning_rate": 0.00018141643066379865,
"loss": 1.0506,
"step": 125
},
{
"epoch": 0.031295137217140105,
"grad_norm": 2.828125,
"learning_rate": 0.00018141444150893366,
"loss": 1.1246,
"step": 130
},
{
"epoch": 0.03249879634087626,
"grad_norm": 2.515625,
"learning_rate": 0.00018141234367808704,
"loss": 1.0545,
"step": 135
},
{
"epoch": 0.033702455464612424,
"grad_norm": 2.53125,
"learning_rate": 0.0001814101371746105,
"loss": 1.0579,
"step": 140
},
{
"epoch": 0.03490611458834858,
"grad_norm": 2.6875,
"learning_rate": 0.00018140782200202953,
"loss": 1.0468,
"step": 145
},
{
"epoch": 0.036109773712084736,
"grad_norm": 2.171875,
"learning_rate": 0.00018140539816404317,
"loss": 1.0484,
"step": 150
},
{
"epoch": 0.03731343283582089,
"grad_norm": 2.4375,
"learning_rate": 0.00018140286566452408,
"loss": 1.0511,
"step": 155
},
{
"epoch": 0.038517091959557055,
"grad_norm": 2.25,
"learning_rate": 0.00018140022450751858,
"loss": 1.0796,
"step": 160
},
{
"epoch": 0.03972075108329321,
"grad_norm": 2.15625,
"learning_rate": 0.0001813974746972465,
"loss": 1.04,
"step": 165
},
{
"epoch": 0.04092441020702937,
"grad_norm": 2.5625,
"learning_rate": 0.00018139461623810138,
"loss": 1.046,
"step": 170
},
{
"epoch": 0.04212806933076553,
"grad_norm": 2.15625,
"learning_rate": 0.0001813916491346503,
"loss": 1.0332,
"step": 175
},
{
"epoch": 0.043331728454501686,
"grad_norm": 2.40625,
"learning_rate": 0.00018138857339163392,
"loss": 1.0369,
"step": 180
},
{
"epoch": 0.04453538757823784,
"grad_norm": 1.9765625,
"learning_rate": 0.00018138538901396647,
"loss": 0.9817,
"step": 185
},
{
"epoch": 0.045739046701974,
"grad_norm": 2.546875,
"learning_rate": 0.0001813820960067358,
"loss": 1.0455,
"step": 190
},
{
"epoch": 0.04694270582571016,
"grad_norm": 2.328125,
"learning_rate": 0.00018137869437520328,
"loss": 0.9987,
"step": 195
},
{
"epoch": 0.04814636494944632,
"grad_norm": 2.421875,
"learning_rate": 0.00018137518412480384,
"loss": 0.9892,
"step": 200
},
{
"epoch": 0.04935002407318247,
"grad_norm": 1.984375,
"learning_rate": 0.00018137156526114596,
"loss": 0.9887,
"step": 205
},
{
"epoch": 0.05055368319691863,
"grad_norm": 1.984375,
"learning_rate": 0.00018136783779001167,
"loss": 0.9929,
"step": 210
},
{
"epoch": 0.05175734232065479,
"grad_norm": 2.3125,
"learning_rate": 0.00018136400171735653,
"loss": 0.9929,
"step": 215
},
{
"epoch": 0.05296100144439095,
"grad_norm": 2.15625,
"learning_rate": 0.00018136005704930957,
"loss": 0.9929,
"step": 220
},
{
"epoch": 0.054164660568127104,
"grad_norm": 2.359375,
"learning_rate": 0.0001813560037921733,
"loss": 0.9898,
"step": 225
},
{
"epoch": 0.05536831969186327,
"grad_norm": 2.171875,
"learning_rate": 0.00018135184195242394,
"loss": 0.9808,
"step": 230
},
{
"epoch": 0.05657197881559942,
"grad_norm": 2.359375,
"learning_rate": 0.00018134757153671089,
"loss": 0.9605,
"step": 235
},
{
"epoch": 0.05777563793933558,
"grad_norm": 2.1875,
"learning_rate": 0.0001813431925518573,
"loss": 0.951,
"step": 240
},
{
"epoch": 0.058979297063071735,
"grad_norm": 2.078125,
"learning_rate": 0.00018133870500485955,
"loss": 0.9705,
"step": 245
},
{
"epoch": 0.0601829561868079,
"grad_norm": 2.234375,
"learning_rate": 0.00018133410890288767,
"loss": 0.964,
"step": 250
},
{
"epoch": 0.061386615310544054,
"grad_norm": 2.171875,
"learning_rate": 0.00018132940425328505,
"loss": 0.9917,
"step": 255
},
{
"epoch": 0.06259027443428021,
"grad_norm": 2.125,
"learning_rate": 0.00018132459106356846,
"loss": 0.9234,
"step": 260
},
{
"epoch": 0.06379393355801637,
"grad_norm": 2.234375,
"learning_rate": 0.0001813196693414282,
"loss": 0.9561,
"step": 265
},
{
"epoch": 0.06499759268175252,
"grad_norm": 2.015625,
"learning_rate": 0.00018131463909472792,
"loss": 0.9422,
"step": 270
},
{
"epoch": 0.06620125180548869,
"grad_norm": 2.28125,
"learning_rate": 0.00018130950033150463,
"loss": 0.9477,
"step": 275
},
{
"epoch": 0.06740491092922485,
"grad_norm": 2.359375,
"learning_rate": 0.00018130425305996873,
"loss": 0.9404,
"step": 280
},
{
"epoch": 0.068608570052961,
"grad_norm": 2.203125,
"learning_rate": 0.0001812988972885041,
"loss": 0.9246,
"step": 285
},
{
"epoch": 0.06981222917669716,
"grad_norm": 2.203125,
"learning_rate": 0.0001812934330256678,
"loss": 0.928,
"step": 290
},
{
"epoch": 0.07101588830043332,
"grad_norm": 2.25,
"learning_rate": 0.0001812878602801904,
"loss": 0.9228,
"step": 295
},
{
"epoch": 0.07221954742416947,
"grad_norm": 2.125,
"learning_rate": 0.00018128217906097569,
"loss": 0.8997,
"step": 300
},
{
"epoch": 0.07342320654790563,
"grad_norm": 2.109375,
"learning_rate": 0.0001812763893771008,
"loss": 0.9153,
"step": 305
},
{
"epoch": 0.07462686567164178,
"grad_norm": 2.015625,
"learning_rate": 0.00018127049123781614,
"loss": 0.9652,
"step": 310
},
{
"epoch": 0.07583052479537795,
"grad_norm": 2.09375,
"learning_rate": 0.00018126448465254544,
"loss": 0.8946,
"step": 315
},
{
"epoch": 0.07703418391911411,
"grad_norm": 2.15625,
"learning_rate": 0.0001812583696308857,
"loss": 0.9044,
"step": 320
},
{
"epoch": 0.07823784304285027,
"grad_norm": 2.03125,
"learning_rate": 0.0001812521461826071,
"loss": 0.9066,
"step": 325
},
{
"epoch": 0.07944150216658642,
"grad_norm": 2.09375,
"learning_rate": 0.00018124581431765317,
"loss": 0.9333,
"step": 330
},
{
"epoch": 0.08064516129032258,
"grad_norm": 2.421875,
"learning_rate": 0.00018123937404614064,
"loss": 0.9135,
"step": 335
},
{
"epoch": 0.08184882041405873,
"grad_norm": 2.0625,
"learning_rate": 0.00018123282537835933,
"loss": 0.9078,
"step": 340
},
{
"epoch": 0.08305247953779489,
"grad_norm": 2.234375,
"learning_rate": 0.00018122616832477238,
"loss": 0.8865,
"step": 345
},
{
"epoch": 0.08425613866153106,
"grad_norm": 1.90625,
"learning_rate": 0.00018121940289601602,
"loss": 0.9306,
"step": 350
},
{
"epoch": 0.08545979778526722,
"grad_norm": 2.265625,
"learning_rate": 0.00018121252910289972,
"loss": 0.9014,
"step": 355
},
{
"epoch": 0.08666345690900337,
"grad_norm": 1.78125,
"learning_rate": 0.000181205546956406,
"loss": 0.9043,
"step": 360
},
{
"epoch": 0.08786711603273953,
"grad_norm": 2.109375,
"learning_rate": 0.00018119845646769056,
"loss": 0.9037,
"step": 365
},
{
"epoch": 0.08907077515647568,
"grad_norm": 1.8984375,
"learning_rate": 0.00018119125764808218,
"loss": 0.9022,
"step": 370
},
{
"epoch": 0.09027443428021184,
"grad_norm": 2.109375,
"learning_rate": 0.00018118395050908273,
"loss": 0.913,
"step": 375
},
{
"epoch": 0.091478093403948,
"grad_norm": 1.8671875,
"learning_rate": 0.00018117653506236715,
"loss": 0.8847,
"step": 380
},
{
"epoch": 0.09268175252768417,
"grad_norm": 2.203125,
"learning_rate": 0.0001811690113197834,
"loss": 0.8985,
"step": 385
},
{
"epoch": 0.09388541165142032,
"grad_norm": 2.15625,
"learning_rate": 0.00018116137929335253,
"loss": 0.8898,
"step": 390
},
{
"epoch": 0.09508907077515648,
"grad_norm": 1.8828125,
"learning_rate": 0.0001811536389952685,
"loss": 0.8857,
"step": 395
},
{
"epoch": 0.09629272989889263,
"grad_norm": 2.1875,
"learning_rate": 0.00018114579043789836,
"loss": 0.8846,
"step": 400
},
{
"epoch": 0.09749638902262879,
"grad_norm": 1.8984375,
"learning_rate": 0.0001811378336337821,
"loss": 0.8833,
"step": 405
},
{
"epoch": 0.09870004814636495,
"grad_norm": 1.953125,
"learning_rate": 0.00018112976859563265,
"loss": 0.8956,
"step": 410
},
{
"epoch": 0.0999037072701011,
"grad_norm": 2.0,
"learning_rate": 0.00018112159533633588,
"loss": 0.8969,
"step": 415
},
{
"epoch": 0.10110736639383726,
"grad_norm": 2.0,
"learning_rate": 0.00018111331386895052,
"loss": 0.8938,
"step": 420
},
{
"epoch": 0.10231102551757343,
"grad_norm": 2.09375,
"learning_rate": 0.0001811049242067083,
"loss": 0.8883,
"step": 425
},
{
"epoch": 0.10351468464130958,
"grad_norm": 2.15625,
"learning_rate": 0.0001810964263630137,
"loss": 0.8387,
"step": 430
},
{
"epoch": 0.10471834376504574,
"grad_norm": 1.8125,
"learning_rate": 0.0001810878203514441,
"loss": 0.8824,
"step": 435
},
{
"epoch": 0.1059220028887819,
"grad_norm": 2.03125,
"learning_rate": 0.0001810791061857497,
"loss": 0.8522,
"step": 440
},
{
"epoch": 0.10712566201251805,
"grad_norm": 1.984375,
"learning_rate": 0.00018107028387985352,
"loss": 0.888,
"step": 445
},
{
"epoch": 0.10832932113625421,
"grad_norm": 1.8125,
"learning_rate": 0.00018106135344785136,
"loss": 0.8926,
"step": 450
},
{
"epoch": 0.10953298025999036,
"grad_norm": 1.6640625,
"learning_rate": 0.0001810523149040117,
"loss": 0.8939,
"step": 455
},
{
"epoch": 0.11073663938372653,
"grad_norm": 1.765625,
"learning_rate": 0.0001810431682627759,
"loss": 0.8591,
"step": 460
},
{
"epoch": 0.11194029850746269,
"grad_norm": 2.046875,
"learning_rate": 0.0001810339135387579,
"loss": 0.8527,
"step": 465
},
{
"epoch": 0.11314395763119885,
"grad_norm": 1.7421875,
"learning_rate": 0.00018102455074674433,
"loss": 0.8686,
"step": 470
},
{
"epoch": 0.114347616754935,
"grad_norm": 1.9375,
"learning_rate": 0.0001810150799016946,
"loss": 0.8991,
"step": 475
},
{
"epoch": 0.11555127587867116,
"grad_norm": 1.8203125,
"learning_rate": 0.00018100550101874066,
"loss": 0.8476,
"step": 480
},
{
"epoch": 0.11675493500240731,
"grad_norm": 1.8828125,
"learning_rate": 0.00018099581411318714,
"loss": 0.8648,
"step": 485
},
{
"epoch": 0.11795859412614347,
"grad_norm": 1.84375,
"learning_rate": 0.00018098601920051122,
"loss": 0.801,
"step": 490
},
{
"epoch": 0.11916225324987964,
"grad_norm": 1.84375,
"learning_rate": 0.00018097611629636263,
"loss": 0.8392,
"step": 495
},
{
"epoch": 0.1203659123736158,
"grad_norm": 1.953125,
"learning_rate": 0.00018096610541656368,
"loss": 0.8541,
"step": 500
},
{
"epoch": 0.1203659123736158,
"eval_loss": 0.7588192820549011,
"eval_runtime": 2.3912,
"eval_samples_per_second": 83.641,
"eval_steps_per_second": 83.641,
"step": 500
},
{
"epoch": 0.12156957149735195,
"grad_norm": 1.96875,
"learning_rate": 0.00018095598657710924,
"loss": 0.8072,
"step": 505
},
{
"epoch": 0.12277323062108811,
"grad_norm": 2.03125,
"learning_rate": 0.00018094575979416656,
"loss": 0.8412,
"step": 510
},
{
"epoch": 0.12397688974482426,
"grad_norm": 1.9765625,
"learning_rate": 0.00018093542508407543,
"loss": 0.8784,
"step": 515
},
{
"epoch": 0.12518054886856042,
"grad_norm": 1.96875,
"learning_rate": 0.00018092498246334812,
"loss": 0.8986,
"step": 520
},
{
"epoch": 0.12638420799229658,
"grad_norm": 2.03125,
"learning_rate": 0.0001809144319486692,
"loss": 0.8843,
"step": 525
},
{
"epoch": 0.12758786711603273,
"grad_norm": 2.078125,
"learning_rate": 0.0001809037735568957,
"loss": 0.8423,
"step": 530
},
{
"epoch": 0.1287915262397689,
"grad_norm": 1.921875,
"learning_rate": 0.00018089300730505704,
"loss": 0.8334,
"step": 535
},
{
"epoch": 0.12999518536350504,
"grad_norm": 1.90625,
"learning_rate": 0.00018088213321035485,
"loss": 0.8376,
"step": 540
},
{
"epoch": 0.1311988444872412,
"grad_norm": 1.9765625,
"learning_rate": 0.00018087115129016324,
"loss": 0.8541,
"step": 545
},
{
"epoch": 0.13240250361097738,
"grad_norm": 2.015625,
"learning_rate": 0.00018086006156202842,
"loss": 0.8112,
"step": 550
},
{
"epoch": 0.13360616273471354,
"grad_norm": 1.78125,
"learning_rate": 0.00018084886404366897,
"loss": 0.8491,
"step": 555
},
{
"epoch": 0.1348098218584497,
"grad_norm": 1.765625,
"learning_rate": 0.00018083755875297568,
"loss": 0.8348,
"step": 560
},
{
"epoch": 0.13601348098218585,
"grad_norm": 1.921875,
"learning_rate": 0.00018082614570801147,
"loss": 0.8148,
"step": 565
},
{
"epoch": 0.137217140105922,
"grad_norm": 1.8515625,
"learning_rate": 0.00018081462492701146,
"loss": 0.8154,
"step": 570
},
{
"epoch": 0.13842079922965816,
"grad_norm": 1.8046875,
"learning_rate": 0.0001808029964283829,
"loss": 0.7738,
"step": 575
},
{
"epoch": 0.13962445835339432,
"grad_norm": 1.9140625,
"learning_rate": 0.00018079126023070517,
"loss": 0.8301,
"step": 580
},
{
"epoch": 0.14082811747713048,
"grad_norm": 1.9296875,
"learning_rate": 0.00018077941635272972,
"loss": 0.8191,
"step": 585
},
{
"epoch": 0.14203177660086663,
"grad_norm": 1.8828125,
"learning_rate": 0.00018076746481337998,
"loss": 0.8251,
"step": 590
},
{
"epoch": 0.1432354357246028,
"grad_norm": 1.90625,
"learning_rate": 0.0001807554056317515,
"loss": 0.8273,
"step": 595
},
{
"epoch": 0.14443909484833894,
"grad_norm": 1.7109375,
"learning_rate": 0.00018074323882711173,
"loss": 0.7992,
"step": 600
},
{
"epoch": 0.1456427539720751,
"grad_norm": 1.7265625,
"learning_rate": 0.0001807309644189001,
"loss": 0.8212,
"step": 605
},
{
"epoch": 0.14684641309581126,
"grad_norm": 1.7109375,
"learning_rate": 0.000180718582426728,
"loss": 0.8157,
"step": 610
},
{
"epoch": 0.1480500722195474,
"grad_norm": 1.875,
"learning_rate": 0.00018070609287037864,
"loss": 0.8365,
"step": 615
},
{
"epoch": 0.14925373134328357,
"grad_norm": 1.8828125,
"learning_rate": 0.00018069349576980715,
"loss": 0.8554,
"step": 620
},
{
"epoch": 0.15045739046701975,
"grad_norm": 1.890625,
"learning_rate": 0.0001806807911451405,
"loss": 0.8188,
"step": 625
},
{
"epoch": 0.1516610495907559,
"grad_norm": 1.8671875,
"learning_rate": 0.00018066797901667732,
"loss": 0.8463,
"step": 630
},
{
"epoch": 0.15286470871449206,
"grad_norm": 1.828125,
"learning_rate": 0.00018065505940488823,
"loss": 0.8317,
"step": 635
},
{
"epoch": 0.15406836783822822,
"grad_norm": 1.6640625,
"learning_rate": 0.00018064203233041537,
"loss": 0.8088,
"step": 640
},
{
"epoch": 0.15527202696196438,
"grad_norm": 1.875,
"learning_rate": 0.00018062889781407274,
"loss": 0.8255,
"step": 645
},
{
"epoch": 0.15647568608570053,
"grad_norm": 1.78125,
"learning_rate": 0.00018061565587684583,
"loss": 0.8245,
"step": 650
},
{
"epoch": 0.1576793452094367,
"grad_norm": 1.8203125,
"learning_rate": 0.00018060230653989197,
"loss": 0.8574,
"step": 655
},
{
"epoch": 0.15888300433317284,
"grad_norm": 1.8828125,
"learning_rate": 0.0001805888498245399,
"loss": 0.82,
"step": 660
},
{
"epoch": 0.160086663456909,
"grad_norm": 1.7890625,
"learning_rate": 0.00018057528575229003,
"loss": 0.8405,
"step": 665
},
{
"epoch": 0.16129032258064516,
"grad_norm": 2.0,
"learning_rate": 0.00018056161434481429,
"loss": 0.8203,
"step": 670
},
{
"epoch": 0.1624939817043813,
"grad_norm": 1.703125,
"learning_rate": 0.00018054783562395605,
"loss": 0.7883,
"step": 675
},
{
"epoch": 0.16369764082811747,
"grad_norm": 1.8046875,
"learning_rate": 0.00018053394961173018,
"loss": 0.8059,
"step": 680
},
{
"epoch": 0.16490129995185362,
"grad_norm": 1.8515625,
"learning_rate": 0.000180519956330323,
"loss": 0.8,
"step": 685
},
{
"epoch": 0.16610495907558978,
"grad_norm": 1.78125,
"learning_rate": 0.00018050585580209214,
"loss": 0.8,
"step": 690
},
{
"epoch": 0.16730861819932596,
"grad_norm": 1.9375,
"learning_rate": 0.00018049164804956666,
"loss": 0.7914,
"step": 695
},
{
"epoch": 0.16851227732306212,
"grad_norm": 1.875,
"learning_rate": 0.0001804773330954469,
"loss": 0.7928,
"step": 700
},
{
"epoch": 0.16971593644679828,
"grad_norm": 2.03125,
"learning_rate": 0.00018046291096260447,
"loss": 0.8329,
"step": 705
},
{
"epoch": 0.17091959557053443,
"grad_norm": 1.9453125,
"learning_rate": 0.00018044838167408228,
"loss": 0.817,
"step": 710
},
{
"epoch": 0.1721232546942706,
"grad_norm": 1.7265625,
"learning_rate": 0.00018043374525309434,
"loss": 0.8079,
"step": 715
},
{
"epoch": 0.17332691381800674,
"grad_norm": 1.8359375,
"learning_rate": 0.00018041900172302601,
"loss": 0.7959,
"step": 720
},
{
"epoch": 0.1745305729417429,
"grad_norm": 1.765625,
"learning_rate": 0.00018040415110743356,
"loss": 0.8499,
"step": 725
},
{
"epoch": 0.17573423206547906,
"grad_norm": 1.796875,
"learning_rate": 0.00018038919343004453,
"loss": 0.8052,
"step": 730
},
{
"epoch": 0.1769378911892152,
"grad_norm": 1.875,
"learning_rate": 0.0001803741287147574,
"loss": 0.8096,
"step": 735
},
{
"epoch": 0.17814155031295137,
"grad_norm": 1.8125,
"learning_rate": 0.0001803589569856418,
"loss": 0.7846,
"step": 740
},
{
"epoch": 0.17934520943668752,
"grad_norm": 1.7578125,
"learning_rate": 0.0001803436782669382,
"loss": 0.7706,
"step": 745
},
{
"epoch": 0.18054886856042368,
"grad_norm": 1.71875,
"learning_rate": 0.00018032829258305812,
"loss": 0.7574,
"step": 750
},
{
"epoch": 0.18175252768415984,
"grad_norm": 1.625,
"learning_rate": 0.0001803127999585839,
"loss": 0.7831,
"step": 755
},
{
"epoch": 0.182956186807896,
"grad_norm": 1.703125,
"learning_rate": 0.00018029720041826878,
"loss": 0.7531,
"step": 760
},
{
"epoch": 0.18415984593163215,
"grad_norm": 1.9140625,
"learning_rate": 0.00018028149398703687,
"loss": 0.7958,
"step": 765
},
{
"epoch": 0.18536350505536833,
"grad_norm": 1.7265625,
"learning_rate": 0.000180265680689983,
"loss": 0.7503,
"step": 770
},
{
"epoch": 0.1865671641791045,
"grad_norm": 1.6484375,
"learning_rate": 0.00018024976055237276,
"loss": 0.8319,
"step": 775
},
{
"epoch": 0.18777082330284064,
"grad_norm": 1.9296875,
"learning_rate": 0.00018023373359964245,
"loss": 0.7884,
"step": 780
},
{
"epoch": 0.1889744824265768,
"grad_norm": 1.765625,
"learning_rate": 0.000180217599857399,
"loss": 0.7968,
"step": 785
},
{
"epoch": 0.19017814155031296,
"grad_norm": 1.953125,
"learning_rate": 0.00018020135935142007,
"loss": 0.7777,
"step": 790
},
{
"epoch": 0.1913818006740491,
"grad_norm": 1.6484375,
"learning_rate": 0.00018018501210765377,
"loss": 0.75,
"step": 795
},
{
"epoch": 0.19258545979778527,
"grad_norm": 1.8984375,
"learning_rate": 0.0001801685581522188,
"loss": 0.7865,
"step": 800
},
{
"epoch": 0.19378911892152142,
"grad_norm": 1.75,
"learning_rate": 0.00018015199751140437,
"loss": 0.7916,
"step": 805
},
{
"epoch": 0.19499277804525758,
"grad_norm": 1.75,
"learning_rate": 0.00018013533021167018,
"loss": 0.7863,
"step": 810
},
{
"epoch": 0.19619643716899374,
"grad_norm": 1.65625,
"learning_rate": 0.00018011855627964626,
"loss": 0.7675,
"step": 815
},
{
"epoch": 0.1974000962927299,
"grad_norm": 1.8203125,
"learning_rate": 0.00018010167574213307,
"loss": 0.7847,
"step": 820
},
{
"epoch": 0.19860375541646605,
"grad_norm": 1.7109375,
"learning_rate": 0.00018008468862610135,
"loss": 0.7765,
"step": 825
},
{
"epoch": 0.1998074145402022,
"grad_norm": 1.8671875,
"learning_rate": 0.00018006759495869219,
"loss": 0.7872,
"step": 830
},
{
"epoch": 0.20101107366393836,
"grad_norm": 1.703125,
"learning_rate": 0.0001800503947672169,
"loss": 0.7879,
"step": 835
},
{
"epoch": 0.20221473278767452,
"grad_norm": 1.6328125,
"learning_rate": 0.0001800330880791569,
"loss": 0.7615,
"step": 840
},
{
"epoch": 0.2034183919114107,
"grad_norm": 1.609375,
"learning_rate": 0.00018001567492216398,
"loss": 0.7837,
"step": 845
},
{
"epoch": 0.20462205103514686,
"grad_norm": 1.734375,
"learning_rate": 0.00017999815532405977,
"loss": 0.7927,
"step": 850
},
{
"epoch": 0.205825710158883,
"grad_norm": 1.4609375,
"learning_rate": 0.00017998052931283615,
"loss": 0.8079,
"step": 855
},
{
"epoch": 0.20702936928261917,
"grad_norm": 1.7109375,
"learning_rate": 0.000179962796916655,
"loss": 0.786,
"step": 860
},
{
"epoch": 0.20823302840635532,
"grad_norm": 1.6484375,
"learning_rate": 0.00017994495816384804,
"loss": 0.8247,
"step": 865
},
{
"epoch": 0.20943668753009148,
"grad_norm": 1.7265625,
"learning_rate": 0.0001799270130829171,
"loss": 0.7969,
"step": 870
},
{
"epoch": 0.21064034665382764,
"grad_norm": 1.890625,
"learning_rate": 0.00017990896170253385,
"loss": 0.7756,
"step": 875
},
{
"epoch": 0.2118440057775638,
"grad_norm": 1.5703125,
"learning_rate": 0.00017989080405153972,
"loss": 0.8003,
"step": 880
},
{
"epoch": 0.21304766490129995,
"grad_norm": 1.734375,
"learning_rate": 0.00017987254015894595,
"loss": 0.7765,
"step": 885
},
{
"epoch": 0.2142513240250361,
"grad_norm": 1.609375,
"learning_rate": 0.00017985417005393365,
"loss": 0.7648,
"step": 890
},
{
"epoch": 0.21545498314877226,
"grad_norm": 1.8046875,
"learning_rate": 0.00017983569376585346,
"loss": 0.7684,
"step": 895
},
{
"epoch": 0.21665864227250842,
"grad_norm": 1.5,
"learning_rate": 0.00017981711132422577,
"loss": 0.7555,
"step": 900
},
{
"epoch": 0.21786230139624457,
"grad_norm": 1.71875,
"learning_rate": 0.0001797984227587406,
"loss": 0.7881,
"step": 905
},
{
"epoch": 0.21906596051998073,
"grad_norm": 1.84375,
"learning_rate": 0.0001797796280992574,
"loss": 0.7826,
"step": 910
},
{
"epoch": 0.2202696196437169,
"grad_norm": 1.7109375,
"learning_rate": 0.00017976072737580529,
"loss": 0.7615,
"step": 915
},
{
"epoch": 0.22147327876745307,
"grad_norm": 1.734375,
"learning_rate": 0.00017974172061858276,
"loss": 0.7794,
"step": 920
},
{
"epoch": 0.22267693789118922,
"grad_norm": 1.8359375,
"learning_rate": 0.00017972260785795776,
"loss": 0.7793,
"step": 925
},
{
"epoch": 0.22388059701492538,
"grad_norm": 1.8046875,
"learning_rate": 0.00017970338912446756,
"loss": 0.7668,
"step": 930
},
{
"epoch": 0.22508425613866154,
"grad_norm": 1.609375,
"learning_rate": 0.00017968406444881873,
"loss": 0.7745,
"step": 935
},
{
"epoch": 0.2262879152623977,
"grad_norm": 1.765625,
"learning_rate": 0.00017966463386188722,
"loss": 0.7792,
"step": 940
},
{
"epoch": 0.22749157438613385,
"grad_norm": 1.765625,
"learning_rate": 0.00017964509739471806,
"loss": 0.7773,
"step": 945
},
{
"epoch": 0.22869523350987,
"grad_norm": 1.6171875,
"learning_rate": 0.0001796254550785256,
"loss": 0.7977,
"step": 950
},
{
"epoch": 0.22989889263360616,
"grad_norm": 1.6796875,
"learning_rate": 0.00017960570694469313,
"loss": 0.7452,
"step": 955
},
{
"epoch": 0.23110255175734232,
"grad_norm": 1.8359375,
"learning_rate": 0.00017958585302477317,
"loss": 0.7605,
"step": 960
},
{
"epoch": 0.23230621088107847,
"grad_norm": 1.6328125,
"learning_rate": 0.0001795658933504872,
"loss": 0.7691,
"step": 965
},
{
"epoch": 0.23350987000481463,
"grad_norm": 1.6015625,
"learning_rate": 0.00017954582795372557,
"loss": 0.7643,
"step": 970
},
{
"epoch": 0.23471352912855079,
"grad_norm": 1.6640625,
"learning_rate": 0.00017952565686654777,
"loss": 0.7389,
"step": 975
},
{
"epoch": 0.23591718825228694,
"grad_norm": 1.59375,
"learning_rate": 0.00017950538012118192,
"loss": 0.7381,
"step": 980
},
{
"epoch": 0.2371208473760231,
"grad_norm": 1.578125,
"learning_rate": 0.00017948499775002514,
"loss": 0.7427,
"step": 985
},
{
"epoch": 0.23832450649975928,
"grad_norm": 1.5859375,
"learning_rate": 0.00017946450978564317,
"loss": 0.7455,
"step": 990
},
{
"epoch": 0.23952816562349544,
"grad_norm": 1.6640625,
"learning_rate": 0.00017944391626077057,
"loss": 0.7557,
"step": 995
},
{
"epoch": 0.2407318247472316,
"grad_norm": 1.75,
"learning_rate": 0.00017942321720831048,
"loss": 0.7453,
"step": 1000
},
{
"epoch": 0.2407318247472316,
"eval_loss": 0.6591922044754028,
"eval_runtime": 2.3906,
"eval_samples_per_second": 83.662,
"eval_steps_per_second": 83.662,
"step": 1000
},
{
"epoch": 0.24193548387096775,
"grad_norm": 1.6640625,
"learning_rate": 0.00017940241266133474,
"loss": 0.7753,
"step": 1005
},
{
"epoch": 0.2431391429947039,
"grad_norm": 1.765625,
"learning_rate": 0.0001793815026530836,
"loss": 0.7529,
"step": 1010
},
{
"epoch": 0.24434280211844006,
"grad_norm": 1.5390625,
"learning_rate": 0.00017936048721696595,
"loss": 0.7543,
"step": 1015
},
{
"epoch": 0.24554646124217622,
"grad_norm": 1.6484375,
"learning_rate": 0.00017933936638655907,
"loss": 0.7304,
"step": 1020
},
{
"epoch": 0.24675012036591237,
"grad_norm": 1.4296875,
"learning_rate": 0.0001793181401956086,
"loss": 0.7233,
"step": 1025
},
{
"epoch": 0.24795377948964853,
"grad_norm": 1.5625,
"learning_rate": 0.00017929680867802855,
"loss": 0.7151,
"step": 1030
},
{
"epoch": 0.24915743861338469,
"grad_norm": 1.7890625,
"learning_rate": 0.00017927537186790125,
"loss": 0.7661,
"step": 1035
},
{
"epoch": 0.25036109773712084,
"grad_norm": 1.6171875,
"learning_rate": 0.0001792538297994772,
"loss": 0.7578,
"step": 1040
},
{
"epoch": 0.251564756860857,
"grad_norm": 1.734375,
"learning_rate": 0.00017923218250717512,
"loss": 0.7055,
"step": 1045
},
{
"epoch": 0.25276841598459315,
"grad_norm": 1.5859375,
"learning_rate": 0.0001792104300255818,
"loss": 0.7427,
"step": 1050
},
{
"epoch": 0.2539720751083293,
"grad_norm": 1.5625,
"learning_rate": 0.0001791885723894522,
"loss": 0.7011,
"step": 1055
},
{
"epoch": 0.25517573423206547,
"grad_norm": 1.7890625,
"learning_rate": 0.00017916660963370915,
"loss": 0.7699,
"step": 1060
},
{
"epoch": 0.2563793933558016,
"grad_norm": 1.5859375,
"learning_rate": 0.00017914454179344358,
"loss": 0.7615,
"step": 1065
},
{
"epoch": 0.2575830524795378,
"grad_norm": 1.6328125,
"learning_rate": 0.00017912236890391415,
"loss": 0.7437,
"step": 1070
},
{
"epoch": 0.25878671160327393,
"grad_norm": 1.65625,
"learning_rate": 0.00017910009100054747,
"loss": 0.7752,
"step": 1075
},
{
"epoch": 0.2599903707270101,
"grad_norm": 1.78125,
"learning_rate": 0.00017907770811893798,
"loss": 0.8086,
"step": 1080
},
{
"epoch": 0.26119402985074625,
"grad_norm": 1.8125,
"learning_rate": 0.00017905522029484775,
"loss": 0.713,
"step": 1085
},
{
"epoch": 0.2623976889744824,
"grad_norm": 1.53125,
"learning_rate": 0.00017903262756420652,
"loss": 0.7457,
"step": 1090
},
{
"epoch": 0.26360134809821856,
"grad_norm": 1.75,
"learning_rate": 0.00017900992996311175,
"loss": 0.7358,
"step": 1095
},
{
"epoch": 0.26480500722195477,
"grad_norm": 1.53125,
"learning_rate": 0.00017898712752782838,
"loss": 0.7431,
"step": 1100
},
{
"epoch": 0.2660086663456909,
"grad_norm": 1.6015625,
"learning_rate": 0.0001789642202947888,
"loss": 0.7242,
"step": 1105
},
{
"epoch": 0.2672123254694271,
"grad_norm": 1.4921875,
"learning_rate": 0.00017894120830059295,
"loss": 0.696,
"step": 1110
},
{
"epoch": 0.26841598459316324,
"grad_norm": 1.734375,
"learning_rate": 0.0001789180915820081,
"loss": 0.7504,
"step": 1115
},
{
"epoch": 0.2696196437168994,
"grad_norm": 1.6875,
"learning_rate": 0.00017889487017596877,
"loss": 0.7081,
"step": 1120
},
{
"epoch": 0.27082330284063555,
"grad_norm": 1.78125,
"learning_rate": 0.00017887154411957686,
"loss": 0.7614,
"step": 1125
},
{
"epoch": 0.2720269619643717,
"grad_norm": 1.7578125,
"learning_rate": 0.00017884811345010145,
"loss": 0.7445,
"step": 1130
},
{
"epoch": 0.27323062108810786,
"grad_norm": 1.8203125,
"learning_rate": 0.00017882457820497872,
"loss": 0.7695,
"step": 1135
},
{
"epoch": 0.274434280211844,
"grad_norm": 1.609375,
"learning_rate": 0.000178800938421812,
"loss": 0.7481,
"step": 1140
},
{
"epoch": 0.2756379393355802,
"grad_norm": 1.6640625,
"learning_rate": 0.00017877719413837153,
"loss": 0.7543,
"step": 1145
},
{
"epoch": 0.27684159845931633,
"grad_norm": 1.7578125,
"learning_rate": 0.00017875334539259463,
"loss": 0.7673,
"step": 1150
},
{
"epoch": 0.2780452575830525,
"grad_norm": 1.7421875,
"learning_rate": 0.00017872939222258547,
"loss": 0.7476,
"step": 1155
},
{
"epoch": 0.27924891670678864,
"grad_norm": 1.5234375,
"learning_rate": 0.0001787053346666151,
"loss": 0.7663,
"step": 1160
},
{
"epoch": 0.2804525758305248,
"grad_norm": 1.5546875,
"learning_rate": 0.00017868117276312128,
"loss": 0.7063,
"step": 1165
},
{
"epoch": 0.28165623495426095,
"grad_norm": 1.6953125,
"learning_rate": 0.00017865690655070857,
"loss": 0.7367,
"step": 1170
},
{
"epoch": 0.2828598940779971,
"grad_norm": 1.4609375,
"learning_rate": 0.00017863253606814817,
"loss": 0.7308,
"step": 1175
},
{
"epoch": 0.28406355320173327,
"grad_norm": 1.5703125,
"learning_rate": 0.00017860806135437784,
"loss": 0.7511,
"step": 1180
},
{
"epoch": 0.2852672123254694,
"grad_norm": 1.5546875,
"learning_rate": 0.0001785834824485019,
"loss": 0.7355,
"step": 1185
},
{
"epoch": 0.2864708714492056,
"grad_norm": 1.640625,
"learning_rate": 0.00017855879938979114,
"loss": 0.7639,
"step": 1190
},
{
"epoch": 0.28767453057294173,
"grad_norm": 1.5234375,
"learning_rate": 0.00017853401221768278,
"loss": 0.7357,
"step": 1195
},
{
"epoch": 0.2888781896966779,
"grad_norm": 1.5546875,
"learning_rate": 0.00017850912097178034,
"loss": 0.7448,
"step": 1200
},
{
"epoch": 0.29008184882041405,
"grad_norm": 1.5,
"learning_rate": 0.00017848412569185365,
"loss": 0.7036,
"step": 1205
},
{
"epoch": 0.2912855079441502,
"grad_norm": 1.7265625,
"learning_rate": 0.0001784590264178388,
"loss": 0.7411,
"step": 1210
},
{
"epoch": 0.29248916706788636,
"grad_norm": 1.6484375,
"learning_rate": 0.000178433823189838,
"loss": 0.7449,
"step": 1215
},
{
"epoch": 0.2936928261916225,
"grad_norm": 1.609375,
"learning_rate": 0.00017840851604811946,
"loss": 0.7431,
"step": 1220
},
{
"epoch": 0.29489648531535867,
"grad_norm": 1.5546875,
"learning_rate": 0.00017838310503311757,
"loss": 0.7291,
"step": 1225
},
{
"epoch": 0.2961001444390948,
"grad_norm": 1.5703125,
"learning_rate": 0.00017835759018543262,
"loss": 0.7442,
"step": 1230
},
{
"epoch": 0.297303803562831,
"grad_norm": 1.6640625,
"learning_rate": 0.00017833197154583076,
"loss": 0.7111,
"step": 1235
},
{
"epoch": 0.29850746268656714,
"grad_norm": 1.71875,
"learning_rate": 0.00017830624915524408,
"loss": 0.7175,
"step": 1240
},
{
"epoch": 0.29971112181030335,
"grad_norm": 1.5390625,
"learning_rate": 0.0001782804230547703,
"loss": 0.7278,
"step": 1245
},
{
"epoch": 0.3009147809340395,
"grad_norm": 1.7578125,
"learning_rate": 0.0001782544932856729,
"loss": 0.7335,
"step": 1250
},
{
"epoch": 0.30211844005777566,
"grad_norm": 1.6875,
"learning_rate": 0.00017822845988938103,
"loss": 0.7244,
"step": 1255
},
{
"epoch": 0.3033220991815118,
"grad_norm": 1.4921875,
"learning_rate": 0.0001782023229074894,
"loss": 0.7328,
"step": 1260
},
{
"epoch": 0.304525758305248,
"grad_norm": 1.59375,
"learning_rate": 0.0001781760823817582,
"loss": 0.7015,
"step": 1265
},
{
"epoch": 0.30572941742898413,
"grad_norm": 1.5546875,
"learning_rate": 0.00017814973835411304,
"loss": 0.7289,
"step": 1270
},
{
"epoch": 0.3069330765527203,
"grad_norm": 1.3828125,
"learning_rate": 0.00017812329086664495,
"loss": 0.7213,
"step": 1275
},
{
"epoch": 0.30813673567645644,
"grad_norm": 1.484375,
"learning_rate": 0.00017809673996161023,
"loss": 0.7053,
"step": 1280
},
{
"epoch": 0.3093403948001926,
"grad_norm": 1.5703125,
"learning_rate": 0.0001780700856814304,
"loss": 0.7443,
"step": 1285
},
{
"epoch": 0.31054405392392875,
"grad_norm": 1.6875,
"learning_rate": 0.00017804332806869218,
"loss": 0.7331,
"step": 1290
},
{
"epoch": 0.3117477130476649,
"grad_norm": 1.5234375,
"learning_rate": 0.0001780164671661474,
"loss": 0.7462,
"step": 1295
},
{
"epoch": 0.31295137217140107,
"grad_norm": 1.609375,
"learning_rate": 0.00017798950301671282,
"loss": 0.7001,
"step": 1300
},
{
"epoch": 0.3141550312951372,
"grad_norm": 1.7578125,
"learning_rate": 0.00017796243566347032,
"loss": 0.7057,
"step": 1305
},
{
"epoch": 0.3153586904188734,
"grad_norm": 1.8515625,
"learning_rate": 0.00017793526514966654,
"loss": 0.7206,
"step": 1310
},
{
"epoch": 0.31656234954260953,
"grad_norm": 1.7109375,
"learning_rate": 0.00017790799151871304,
"loss": 0.7501,
"step": 1315
},
{
"epoch": 0.3177660086663457,
"grad_norm": 1.6796875,
"learning_rate": 0.00017788061481418608,
"loss": 0.7305,
"step": 1320
},
{
"epoch": 0.31896966779008185,
"grad_norm": 1.5859375,
"learning_rate": 0.0001778531350798266,
"loss": 0.734,
"step": 1325
},
{
"epoch": 0.320173326913818,
"grad_norm": 1.5859375,
"learning_rate": 0.00017782555235954013,
"loss": 0.7195,
"step": 1330
},
{
"epoch": 0.32137698603755416,
"grad_norm": 1.5390625,
"learning_rate": 0.00017779786669739687,
"loss": 0.7174,
"step": 1335
},
{
"epoch": 0.3225806451612903,
"grad_norm": 1.4609375,
"learning_rate": 0.00017777007813763135,
"loss": 0.6927,
"step": 1340
},
{
"epoch": 0.32378430428502647,
"grad_norm": 1.5234375,
"learning_rate": 0.0001777421867246426,
"loss": 0.6868,
"step": 1345
},
{
"epoch": 0.3249879634087626,
"grad_norm": 1.5390625,
"learning_rate": 0.00017771419250299395,
"loss": 0.6822,
"step": 1350
},
{
"epoch": 0.3261916225324988,
"grad_norm": 1.5390625,
"learning_rate": 0.00017768609551741294,
"loss": 0.7231,
"step": 1355
},
{
"epoch": 0.32739528165623494,
"grad_norm": 1.5703125,
"learning_rate": 0.00017765789581279142,
"loss": 0.7121,
"step": 1360
},
{
"epoch": 0.3285989407799711,
"grad_norm": 1.5625,
"learning_rate": 0.00017762959343418523,
"loss": 0.7539,
"step": 1365
},
{
"epoch": 0.32980259990370725,
"grad_norm": 1.4453125,
"learning_rate": 0.00017760118842681432,
"loss": 0.6681,
"step": 1370
},
{
"epoch": 0.3310062590274434,
"grad_norm": 1.5625,
"learning_rate": 0.00017757268083606266,
"loss": 0.732,
"step": 1375
},
{
"epoch": 0.33220991815117956,
"grad_norm": 1.6328125,
"learning_rate": 0.00017754407070747803,
"loss": 0.6868,
"step": 1380
},
{
"epoch": 0.3334135772749157,
"grad_norm": 1.421875,
"learning_rate": 0.00017751535808677212,
"loss": 0.687,
"step": 1385
},
{
"epoch": 0.33461723639865193,
"grad_norm": 1.65625,
"learning_rate": 0.00017748654301982027,
"loss": 0.7162,
"step": 1390
},
{
"epoch": 0.3358208955223881,
"grad_norm": 1.453125,
"learning_rate": 0.00017745762555266162,
"loss": 0.7199,
"step": 1395
},
{
"epoch": 0.33702455464612424,
"grad_norm": 1.4375,
"learning_rate": 0.00017742860573149888,
"loss": 0.7354,
"step": 1400
},
{
"epoch": 0.3382282137698604,
"grad_norm": 1.5703125,
"learning_rate": 0.00017739948360269827,
"loss": 0.6817,
"step": 1405
},
{
"epoch": 0.33943187289359655,
"grad_norm": 1.390625,
"learning_rate": 0.00017737025921278943,
"loss": 0.7115,
"step": 1410
},
{
"epoch": 0.3406355320173327,
"grad_norm": 1.5234375,
"learning_rate": 0.00017734093260846553,
"loss": 0.7204,
"step": 1415
},
{
"epoch": 0.34183919114106887,
"grad_norm": 1.6640625,
"learning_rate": 0.00017731150383658293,
"loss": 0.7286,
"step": 1420
},
{
"epoch": 0.343042850264805,
"grad_norm": 1.5078125,
"learning_rate": 0.00017728197294416124,
"loss": 0.7304,
"step": 1425
},
{
"epoch": 0.3442465093885412,
"grad_norm": 1.6953125,
"learning_rate": 0.00017725233997838329,
"loss": 0.7101,
"step": 1430
},
{
"epoch": 0.34545016851227733,
"grad_norm": 1.46875,
"learning_rate": 0.00017722260498659496,
"loss": 0.7209,
"step": 1435
},
{
"epoch": 0.3466538276360135,
"grad_norm": 1.5546875,
"learning_rate": 0.00017719276801630515,
"loss": 0.7022,
"step": 1440
},
{
"epoch": 0.34785748675974965,
"grad_norm": 1.453125,
"learning_rate": 0.00017716282911518566,
"loss": 0.6727,
"step": 1445
},
{
"epoch": 0.3490611458834858,
"grad_norm": 1.5546875,
"learning_rate": 0.0001771327883310712,
"loss": 0.6885,
"step": 1450
},
{
"epoch": 0.35026480500722196,
"grad_norm": 1.453125,
"learning_rate": 0.00017710264571195922,
"loss": 0.6793,
"step": 1455
},
{
"epoch": 0.3514684641309581,
"grad_norm": 1.578125,
"learning_rate": 0.00017707240130600992,
"loss": 0.6901,
"step": 1460
},
{
"epoch": 0.35267212325469427,
"grad_norm": 1.4765625,
"learning_rate": 0.00017704205516154612,
"loss": 0.7077,
"step": 1465
},
{
"epoch": 0.3538757823784304,
"grad_norm": 1.53125,
"learning_rate": 0.00017701160732705313,
"loss": 0.7431,
"step": 1470
},
{
"epoch": 0.3550794415021666,
"grad_norm": 1.421875,
"learning_rate": 0.00017698105785117884,
"loss": 0.7215,
"step": 1475
},
{
"epoch": 0.35628310062590274,
"grad_norm": 1.5390625,
"learning_rate": 0.00017695040678273344,
"loss": 0.7106,
"step": 1480
},
{
"epoch": 0.3574867597496389,
"grad_norm": 1.609375,
"learning_rate": 0.0001769196541706895,
"loss": 0.6923,
"step": 1485
},
{
"epoch": 0.35869041887337505,
"grad_norm": 1.4375,
"learning_rate": 0.00017688880006418183,
"loss": 0.6773,
"step": 1490
},
{
"epoch": 0.3598940779971112,
"grad_norm": 1.4921875,
"learning_rate": 0.00017685784451250733,
"loss": 0.6892,
"step": 1495
},
{
"epoch": 0.36109773712084736,
"grad_norm": 1.640625,
"learning_rate": 0.00017682678756512509,
"loss": 0.6795,
"step": 1500
},
{
"epoch": 0.36109773712084736,
"eval_loss": 0.6025854349136353,
"eval_runtime": 2.4049,
"eval_samples_per_second": 83.162,
"eval_steps_per_second": 83.162,
"step": 1500
},
{
"epoch": 0.3623013962445835,
"grad_norm": 1.578125,
"learning_rate": 0.00017679562927165612,
"loss": 0.7128,
"step": 1505
},
{
"epoch": 0.3635050553683197,
"grad_norm": 1.5234375,
"learning_rate": 0.0001767643696818834,
"loss": 0.6946,
"step": 1510
},
{
"epoch": 0.36470871449205583,
"grad_norm": 1.59375,
"learning_rate": 0.00017673300884575173,
"loss": 0.7061,
"step": 1515
},
{
"epoch": 0.365912373615792,
"grad_norm": 1.5078125,
"learning_rate": 0.00017670154681336767,
"loss": 0.6766,
"step": 1520
},
{
"epoch": 0.36711603273952814,
"grad_norm": 1.375,
"learning_rate": 0.0001766699836349995,
"loss": 0.6685,
"step": 1525
},
{
"epoch": 0.3683196918632643,
"grad_norm": 1.5078125,
"learning_rate": 0.00017663831936107712,
"loss": 0.728,
"step": 1530
},
{
"epoch": 0.36952335098700045,
"grad_norm": 1.7109375,
"learning_rate": 0.0001766065540421919,
"loss": 0.7238,
"step": 1535
},
{
"epoch": 0.37072701011073667,
"grad_norm": 1.71875,
"learning_rate": 0.00017657468772909663,
"loss": 0.7126,
"step": 1540
},
{
"epoch": 0.3719306692344728,
"grad_norm": 1.5234375,
"learning_rate": 0.00017654272047270558,
"loss": 0.6897,
"step": 1545
},
{
"epoch": 0.373134328358209,
"grad_norm": 1.4765625,
"learning_rate": 0.00017651065232409416,
"loss": 0.6872,
"step": 1550
},
{
"epoch": 0.37433798748194513,
"grad_norm": 1.5390625,
"learning_rate": 0.0001764784833344991,
"loss": 0.7086,
"step": 1555
},
{
"epoch": 0.3755416466056813,
"grad_norm": 1.5859375,
"learning_rate": 0.00017644621355531823,
"loss": 0.7068,
"step": 1560
},
{
"epoch": 0.37674530572941745,
"grad_norm": 1.625,
"learning_rate": 0.00017641384303811032,
"loss": 0.6891,
"step": 1565
},
{
"epoch": 0.3779489648531536,
"grad_norm": 1.4296875,
"learning_rate": 0.00017638137183459516,
"loss": 0.7255,
"step": 1570
},
{
"epoch": 0.37915262397688976,
"grad_norm": 1.578125,
"learning_rate": 0.00017634879999665348,
"loss": 0.7103,
"step": 1575
},
{
"epoch": 0.3803562831006259,
"grad_norm": 1.5234375,
"learning_rate": 0.00017631612757632663,
"loss": 0.6874,
"step": 1580
},
{
"epoch": 0.38155994222436207,
"grad_norm": 1.3671875,
"learning_rate": 0.0001762833546258168,
"loss": 0.6898,
"step": 1585
},
{
"epoch": 0.3827636013480982,
"grad_norm": 1.5859375,
"learning_rate": 0.0001762504811974868,
"loss": 0.707,
"step": 1590
},
{
"epoch": 0.3839672604718344,
"grad_norm": 1.5703125,
"learning_rate": 0.00017621750734385993,
"loss": 0.6924,
"step": 1595
},
{
"epoch": 0.38517091959557054,
"grad_norm": 1.5390625,
"learning_rate": 0.0001761844331176199,
"loss": 0.7022,
"step": 1600
},
{
"epoch": 0.3863745787193067,
"grad_norm": 1.3984375,
"learning_rate": 0.00017615125857161094,
"loss": 0.6904,
"step": 1605
},
{
"epoch": 0.38757823784304285,
"grad_norm": 1.4921875,
"learning_rate": 0.00017611798375883738,
"loss": 0.6895,
"step": 1610
},
{
"epoch": 0.388781896966779,
"grad_norm": 1.6171875,
"learning_rate": 0.00017608460873246387,
"loss": 0.7075,
"step": 1615
},
{
"epoch": 0.38998555609051516,
"grad_norm": 1.4921875,
"learning_rate": 0.00017605113354581515,
"loss": 0.6792,
"step": 1620
},
{
"epoch": 0.3911892152142513,
"grad_norm": 1.5859375,
"learning_rate": 0.000176017558252376,
"loss": 0.7466,
"step": 1625
},
{
"epoch": 0.3923928743379875,
"grad_norm": 1.390625,
"learning_rate": 0.00017598388290579115,
"loss": 0.6889,
"step": 1630
},
{
"epoch": 0.39359653346172363,
"grad_norm": 1.53125,
"learning_rate": 0.0001759501075598651,
"loss": 0.7023,
"step": 1635
},
{
"epoch": 0.3948001925854598,
"grad_norm": 1.59375,
"learning_rate": 0.00017591623226856224,
"loss": 0.707,
"step": 1640
},
{
"epoch": 0.39600385170919594,
"grad_norm": 1.53125,
"learning_rate": 0.00017588225708600662,
"loss": 0.6763,
"step": 1645
},
{
"epoch": 0.3972075108329321,
"grad_norm": 1.5859375,
"learning_rate": 0.0001758481820664818,
"loss": 0.683,
"step": 1650
},
{
"epoch": 0.39841116995666825,
"grad_norm": 1.4765625,
"learning_rate": 0.00017581400726443102,
"loss": 0.7005,
"step": 1655
},
{
"epoch": 0.3996148290804044,
"grad_norm": 1.390625,
"learning_rate": 0.0001757797327344568,
"loss": 0.6983,
"step": 1660
},
{
"epoch": 0.40081848820414057,
"grad_norm": 1.5234375,
"learning_rate": 0.00017574535853132108,
"loss": 0.6762,
"step": 1665
},
{
"epoch": 0.4020221473278767,
"grad_norm": 1.6015625,
"learning_rate": 0.000175710884709945,
"loss": 0.6733,
"step": 1670
},
{
"epoch": 0.4032258064516129,
"grad_norm": 1.609375,
"learning_rate": 0.00017567631132540886,
"loss": 0.6843,
"step": 1675
},
{
"epoch": 0.40442946557534903,
"grad_norm": 1.5078125,
"learning_rate": 0.0001756416384329521,
"loss": 0.7135,
"step": 1680
},
{
"epoch": 0.40563312469908525,
"grad_norm": 1.609375,
"learning_rate": 0.00017560686608797315,
"loss": 0.6691,
"step": 1685
},
{
"epoch": 0.4068367838228214,
"grad_norm": 1.625,
"learning_rate": 0.00017557199434602925,
"loss": 0.7016,
"step": 1690
},
{
"epoch": 0.40804044294655756,
"grad_norm": 1.4609375,
"learning_rate": 0.00017553702326283653,
"loss": 0.6793,
"step": 1695
},
{
"epoch": 0.4092441020702937,
"grad_norm": 1.4921875,
"learning_rate": 0.0001755019528942698,
"loss": 0.6773,
"step": 1700
},
{
"epoch": 0.41044776119402987,
"grad_norm": 1.59375,
"learning_rate": 0.00017546678329636252,
"loss": 0.7092,
"step": 1705
},
{
"epoch": 0.411651420317766,
"grad_norm": 1.3671875,
"learning_rate": 0.00017543151452530673,
"loss": 0.6657,
"step": 1710
},
{
"epoch": 0.4128550794415022,
"grad_norm": 1.4296875,
"learning_rate": 0.0001753961466374528,
"loss": 0.6737,
"step": 1715
},
{
"epoch": 0.41405873856523834,
"grad_norm": 1.5078125,
"learning_rate": 0.00017536067968930964,
"loss": 0.693,
"step": 1720
},
{
"epoch": 0.4152623976889745,
"grad_norm": 1.4375,
"learning_rate": 0.0001753251137375443,
"loss": 0.6852,
"step": 1725
},
{
"epoch": 0.41646605681271065,
"grad_norm": 1.359375,
"learning_rate": 0.00017528944883898206,
"loss": 0.6566,
"step": 1730
},
{
"epoch": 0.4176697159364468,
"grad_norm": 1.53125,
"learning_rate": 0.00017525368505060627,
"loss": 0.6874,
"step": 1735
},
{
"epoch": 0.41887337506018296,
"grad_norm": 1.5546875,
"learning_rate": 0.00017521782242955827,
"loss": 0.6762,
"step": 1740
},
{
"epoch": 0.4200770341839191,
"grad_norm": 1.4765625,
"learning_rate": 0.00017518186103313742,
"loss": 0.6745,
"step": 1745
},
{
"epoch": 0.4212806933076553,
"grad_norm": 1.4375,
"learning_rate": 0.00017514580091880077,
"loss": 0.6853,
"step": 1750
},
{
"epoch": 0.42248435243139143,
"grad_norm": 1.390625,
"learning_rate": 0.0001751096421441631,
"loss": 0.69,
"step": 1755
},
{
"epoch": 0.4236880115551276,
"grad_norm": 1.6015625,
"learning_rate": 0.00017507338476699692,
"loss": 0.6636,
"step": 1760
},
{
"epoch": 0.42489167067886374,
"grad_norm": 1.46875,
"learning_rate": 0.00017503702884523218,
"loss": 0.6855,
"step": 1765
},
{
"epoch": 0.4260953298025999,
"grad_norm": 1.59375,
"learning_rate": 0.00017500057443695636,
"loss": 0.6725,
"step": 1770
},
{
"epoch": 0.42729898892633605,
"grad_norm": 1.5546875,
"learning_rate": 0.0001749640216004142,
"loss": 0.6449,
"step": 1775
},
{
"epoch": 0.4285026480500722,
"grad_norm": 1.390625,
"learning_rate": 0.00017492737039400785,
"loss": 0.6772,
"step": 1780
},
{
"epoch": 0.42970630717380837,
"grad_norm": 1.3828125,
"learning_rate": 0.00017489062087629648,
"loss": 0.7016,
"step": 1785
},
{
"epoch": 0.4309099662975445,
"grad_norm": 1.40625,
"learning_rate": 0.0001748537731059964,
"loss": 0.7142,
"step": 1790
},
{
"epoch": 0.4321136254212807,
"grad_norm": 1.5859375,
"learning_rate": 0.00017481682714198097,
"loss": 0.6957,
"step": 1795
},
{
"epoch": 0.43331728454501683,
"grad_norm": 1.359375,
"learning_rate": 0.00017477978304328024,
"loss": 0.6857,
"step": 1800
},
{
"epoch": 0.434520943668753,
"grad_norm": 1.5,
"learning_rate": 0.0001747426408690813,
"loss": 0.7223,
"step": 1805
},
{
"epoch": 0.43572460279248915,
"grad_norm": 1.3359375,
"learning_rate": 0.0001747054006787278,
"loss": 0.6781,
"step": 1810
},
{
"epoch": 0.4369282619162253,
"grad_norm": 1.5078125,
"learning_rate": 0.00017466806253171996,
"loss": 0.664,
"step": 1815
},
{
"epoch": 0.43813192103996146,
"grad_norm": 1.671875,
"learning_rate": 0.00017463062648771462,
"loss": 0.666,
"step": 1820
},
{
"epoch": 0.4393355801636976,
"grad_norm": 1.484375,
"learning_rate": 0.00017459309260652497,
"loss": 0.6811,
"step": 1825
},
{
"epoch": 0.4405392392874338,
"grad_norm": 1.484375,
"learning_rate": 0.0001745554609481205,
"loss": 0.6608,
"step": 1830
},
{
"epoch": 0.44174289841117,
"grad_norm": 1.4375,
"learning_rate": 0.00017451773157262703,
"loss": 0.6846,
"step": 1835
},
{
"epoch": 0.44294655753490614,
"grad_norm": 1.515625,
"learning_rate": 0.00017447990454032636,
"loss": 0.7046,
"step": 1840
},
{
"epoch": 0.4441502166586423,
"grad_norm": 1.375,
"learning_rate": 0.0001744419799116564,
"loss": 0.6599,
"step": 1845
},
{
"epoch": 0.44535387578237845,
"grad_norm": 1.4453125,
"learning_rate": 0.00017440395774721102,
"loss": 0.6928,
"step": 1850
},
{
"epoch": 0.4465575349061146,
"grad_norm": 1.40625,
"learning_rate": 0.00017436583810773987,
"loss": 0.6748,
"step": 1855
},
{
"epoch": 0.44776119402985076,
"grad_norm": 1.4375,
"learning_rate": 0.00017432762105414832,
"loss": 0.6887,
"step": 1860
},
{
"epoch": 0.4489648531535869,
"grad_norm": 1.40625,
"learning_rate": 0.00017428930664749749,
"loss": 0.6298,
"step": 1865
},
{
"epoch": 0.4501685122773231,
"grad_norm": 1.6875,
"learning_rate": 0.00017425089494900394,
"loss": 0.6894,
"step": 1870
},
{
"epoch": 0.45137217140105923,
"grad_norm": 1.4453125,
"learning_rate": 0.00017421238602003975,
"loss": 0.6788,
"step": 1875
},
{
"epoch": 0.4525758305247954,
"grad_norm": 1.3203125,
"learning_rate": 0.0001741737799221323,
"loss": 0.6706,
"step": 1880
},
{
"epoch": 0.45377948964853154,
"grad_norm": 1.53125,
"learning_rate": 0.0001741350767169642,
"loss": 0.6857,
"step": 1885
},
{
"epoch": 0.4549831487722677,
"grad_norm": 1.46875,
"learning_rate": 0.00017409627646637334,
"loss": 0.6344,
"step": 1890
},
{
"epoch": 0.45618680789600385,
"grad_norm": 1.5,
"learning_rate": 0.00017405737923235247,
"loss": 0.6424,
"step": 1895
},
{
"epoch": 0.45739046701974,
"grad_norm": 1.5859375,
"learning_rate": 0.00017401838507704947,
"loss": 0.7227,
"step": 1900
},
{
"epoch": 0.45859412614347617,
"grad_norm": 1.484375,
"learning_rate": 0.00017397929406276697,
"loss": 0.6895,
"step": 1905
},
{
"epoch": 0.4597977852672123,
"grad_norm": 1.484375,
"learning_rate": 0.00017394010625196242,
"loss": 0.6858,
"step": 1910
},
{
"epoch": 0.4610014443909485,
"grad_norm": 1.390625,
"learning_rate": 0.00017390082170724787,
"loss": 0.6728,
"step": 1915
},
{
"epoch": 0.46220510351468463,
"grad_norm": 1.515625,
"learning_rate": 0.00017386144049138995,
"loss": 0.6685,
"step": 1920
},
{
"epoch": 0.4634087626384208,
"grad_norm": 1.515625,
"learning_rate": 0.00017382196266730977,
"loss": 0.7095,
"step": 1925
},
{
"epoch": 0.46461242176215695,
"grad_norm": 1.53125,
"learning_rate": 0.00017378238829808274,
"loss": 0.6678,
"step": 1930
},
{
"epoch": 0.4658160808858931,
"grad_norm": 1.640625,
"learning_rate": 0.00017374271744693861,
"loss": 0.6634,
"step": 1935
},
{
"epoch": 0.46701974000962926,
"grad_norm": 1.359375,
"learning_rate": 0.0001737029501772612,
"loss": 0.6682,
"step": 1940
},
{
"epoch": 0.4682233991333654,
"grad_norm": 1.3671875,
"learning_rate": 0.00017366308655258837,
"loss": 0.6648,
"step": 1945
},
{
"epoch": 0.46942705825710157,
"grad_norm": 1.4921875,
"learning_rate": 0.00017362312663661203,
"loss": 0.6449,
"step": 1950
},
{
"epoch": 0.4706307173808377,
"grad_norm": 1.3984375,
"learning_rate": 0.00017358307049317786,
"loss": 0.6514,
"step": 1955
},
{
"epoch": 0.4718343765045739,
"grad_norm": 1.3671875,
"learning_rate": 0.00017354291818628533,
"loss": 0.6347,
"step": 1960
},
{
"epoch": 0.47303803562831004,
"grad_norm": 1.59375,
"learning_rate": 0.0001735026697800875,
"loss": 0.6859,
"step": 1965
},
{
"epoch": 0.4742416947520462,
"grad_norm": 1.3515625,
"learning_rate": 0.00017346232533889104,
"loss": 0.6924,
"step": 1970
},
{
"epoch": 0.4754453538757824,
"grad_norm": 1.4375,
"learning_rate": 0.00017342188492715596,
"loss": 0.6782,
"step": 1975
},
{
"epoch": 0.47664901299951856,
"grad_norm": 1.53125,
"learning_rate": 0.00017338134860949578,
"loss": 0.6753,
"step": 1980
},
{
"epoch": 0.4778526721232547,
"grad_norm": 1.4296875,
"learning_rate": 0.00017334071645067704,
"loss": 0.6419,
"step": 1985
},
{
"epoch": 0.4790563312469909,
"grad_norm": 1.4453125,
"learning_rate": 0.00017329998851561956,
"loss": 0.6609,
"step": 1990
},
{
"epoch": 0.48025999037072703,
"grad_norm": 1.5546875,
"learning_rate": 0.00017325916486939617,
"loss": 0.6492,
"step": 1995
},
{
"epoch": 0.4814636494944632,
"grad_norm": 1.3046875,
"learning_rate": 0.00017321824557723253,
"loss": 0.6382,
"step": 2000
},
{
"epoch": 0.4814636494944632,
"eval_loss": 0.5719231963157654,
"eval_runtime": 2.395,
"eval_samples_per_second": 83.506,
"eval_steps_per_second": 83.506,
"step": 2000
},
{
"epoch": 0.48266730861819934,
"grad_norm": 1.5625,
"learning_rate": 0.0001731772307045072,
"loss": 0.6636,
"step": 2005
},
{
"epoch": 0.4838709677419355,
"grad_norm": 1.421875,
"learning_rate": 0.00017313612031675144,
"loss": 0.6493,
"step": 2010
},
{
"epoch": 0.48507462686567165,
"grad_norm": 1.4453125,
"learning_rate": 0.00017309491447964912,
"loss": 0.6684,
"step": 2015
},
{
"epoch": 0.4862782859894078,
"grad_norm": 1.4765625,
"learning_rate": 0.0001730536132590366,
"loss": 0.6535,
"step": 2020
},
{
"epoch": 0.48748194511314397,
"grad_norm": 1.5390625,
"learning_rate": 0.0001730122167209026,
"loss": 0.6687,
"step": 2025
},
{
"epoch": 0.4886856042368801,
"grad_norm": 1.5078125,
"learning_rate": 0.00017297072493138824,
"loss": 0.6337,
"step": 2030
},
{
"epoch": 0.4898892633606163,
"grad_norm": 1.609375,
"learning_rate": 0.0001729291379567867,
"loss": 0.689,
"step": 2035
},
{
"epoch": 0.49109292248435243,
"grad_norm": 1.65625,
"learning_rate": 0.00017288745586354338,
"loss": 0.6611,
"step": 2040
},
{
"epoch": 0.4922965816080886,
"grad_norm": 1.4375,
"learning_rate": 0.00017284567871825554,
"loss": 0.6394,
"step": 2045
},
{
"epoch": 0.49350024073182475,
"grad_norm": 1.453125,
"learning_rate": 0.00017280380658767232,
"loss": 0.6721,
"step": 2050
},
{
"epoch": 0.4947038998555609,
"grad_norm": 1.4296875,
"learning_rate": 0.00017276183953869468,
"loss": 0.6445,
"step": 2055
},
{
"epoch": 0.49590755897929706,
"grad_norm": 1.5390625,
"learning_rate": 0.0001727197776383752,
"loss": 0.6357,
"step": 2060
},
{
"epoch": 0.4971112181030332,
"grad_norm": 1.4609375,
"learning_rate": 0.00017267762095391805,
"loss": 0.6575,
"step": 2065
},
{
"epoch": 0.49831487722676937,
"grad_norm": 1.4140625,
"learning_rate": 0.00017263536955267877,
"loss": 0.668,
"step": 2070
},
{
"epoch": 0.4995185363505055,
"grad_norm": 1.40625,
"learning_rate": 0.00017259302350216426,
"loss": 0.6321,
"step": 2075
},
{
"epoch": 0.5007221954742417,
"grad_norm": 1.703125,
"learning_rate": 0.00017255058287003267,
"loss": 0.6468,
"step": 2080
},
{
"epoch": 0.5019258545979779,
"grad_norm": 1.546875,
"learning_rate": 0.00017250804772409321,
"loss": 0.6888,
"step": 2085
},
{
"epoch": 0.503129513721714,
"grad_norm": 1.375,
"learning_rate": 0.00017246541813230621,
"loss": 0.6862,
"step": 2090
},
{
"epoch": 0.5043331728454502,
"grad_norm": 1.25,
"learning_rate": 0.00017242269416278277,
"loss": 0.6215,
"step": 2095
},
{
"epoch": 0.5055368319691863,
"grad_norm": 1.3671875,
"learning_rate": 0.0001723798758837849,
"loss": 0.6863,
"step": 2100
},
{
"epoch": 0.5067404910929225,
"grad_norm": 1.484375,
"learning_rate": 0.00017233696336372518,
"loss": 0.6396,
"step": 2105
},
{
"epoch": 0.5079441502166586,
"grad_norm": 1.46875,
"learning_rate": 0.0001722939566711668,
"loss": 0.6635,
"step": 2110
},
{
"epoch": 0.5091478093403948,
"grad_norm": 1.5078125,
"learning_rate": 0.0001722508558748235,
"loss": 0.676,
"step": 2115
},
{
"epoch": 0.5103514684641309,
"grad_norm": 1.53125,
"learning_rate": 0.0001722076610435593,
"loss": 0.6546,
"step": 2120
},
{
"epoch": 0.5115551275878671,
"grad_norm": 1.4453125,
"learning_rate": 0.00017216437224638835,
"loss": 0.6884,
"step": 2125
},
{
"epoch": 0.5127587867116032,
"grad_norm": 1.421875,
"learning_rate": 0.0001721209895524752,
"loss": 0.6016,
"step": 2130
},
{
"epoch": 0.5139624458353395,
"grad_norm": 1.5,
"learning_rate": 0.0001720775130311342,
"loss": 0.6292,
"step": 2135
},
{
"epoch": 0.5151661049590756,
"grad_norm": 1.3984375,
"learning_rate": 0.00017203394275182966,
"loss": 0.6847,
"step": 2140
},
{
"epoch": 0.5163697640828118,
"grad_norm": 1.4296875,
"learning_rate": 0.00017199027878417577,
"loss": 0.6527,
"step": 2145
},
{
"epoch": 0.5175734232065479,
"grad_norm": 1.2734375,
"learning_rate": 0.00017194652119793634,
"loss": 0.6383,
"step": 2150
},
{
"epoch": 0.5187770823302841,
"grad_norm": 1.4921875,
"learning_rate": 0.0001719026700630248,
"loss": 0.6664,
"step": 2155
},
{
"epoch": 0.5199807414540202,
"grad_norm": 1.3046875,
"learning_rate": 0.00017185872544950396,
"loss": 0.6455,
"step": 2160
},
{
"epoch": 0.5211844005777564,
"grad_norm": 1.4765625,
"learning_rate": 0.0001718146874275861,
"loss": 0.6697,
"step": 2165
},
{
"epoch": 0.5223880597014925,
"grad_norm": 1.515625,
"learning_rate": 0.00017177055606763266,
"loss": 0.6764,
"step": 2170
},
{
"epoch": 0.5235917188252287,
"grad_norm": 1.359375,
"learning_rate": 0.00017172633144015424,
"loss": 0.6458,
"step": 2175
},
{
"epoch": 0.5247953779489648,
"grad_norm": 1.328125,
"learning_rate": 0.00017168201361581053,
"loss": 0.6561,
"step": 2180
},
{
"epoch": 0.525999037072701,
"grad_norm": 1.390625,
"learning_rate": 0.00017163760266540994,
"loss": 0.6688,
"step": 2185
},
{
"epoch": 0.5272026961964371,
"grad_norm": 1.3984375,
"learning_rate": 0.00017159309865990988,
"loss": 0.652,
"step": 2190
},
{
"epoch": 0.5284063553201733,
"grad_norm": 1.3828125,
"learning_rate": 0.00017154850167041625,
"loss": 0.6565,
"step": 2195
},
{
"epoch": 0.5296100144439095,
"grad_norm": 1.3046875,
"learning_rate": 0.0001715038117681837,
"loss": 0.6544,
"step": 2200
},
{
"epoch": 0.5308136735676456,
"grad_norm": 1.4609375,
"learning_rate": 0.00017145902902461515,
"loss": 0.663,
"step": 2205
},
{
"epoch": 0.5320173326913819,
"grad_norm": 1.4140625,
"learning_rate": 0.00017141415351126202,
"loss": 0.6494,
"step": 2210
},
{
"epoch": 0.533220991815118,
"grad_norm": 1.3203125,
"learning_rate": 0.0001713691852998238,
"loss": 0.6389,
"step": 2215
},
{
"epoch": 0.5344246509388542,
"grad_norm": 1.484375,
"learning_rate": 0.00017132412446214823,
"loss": 0.6686,
"step": 2220
},
{
"epoch": 0.5356283100625903,
"grad_norm": 1.578125,
"learning_rate": 0.000171278971070231,
"loss": 0.6633,
"step": 2225
},
{
"epoch": 0.5368319691863265,
"grad_norm": 1.53125,
"learning_rate": 0.00017123372519621557,
"loss": 0.6523,
"step": 2230
},
{
"epoch": 0.5380356283100626,
"grad_norm": 1.2890625,
"learning_rate": 0.00017118838691239328,
"loss": 0.6764,
"step": 2235
},
{
"epoch": 0.5392392874337988,
"grad_norm": 1.5234375,
"learning_rate": 0.0001711429562912031,
"loss": 0.6358,
"step": 2240
},
{
"epoch": 0.5404429465575349,
"grad_norm": 1.359375,
"learning_rate": 0.00017109743340523154,
"loss": 0.6273,
"step": 2245
},
{
"epoch": 0.5416466056812711,
"grad_norm": 1.25,
"learning_rate": 0.00017105181832721244,
"loss": 0.6216,
"step": 2250
},
{
"epoch": 0.5428502648050072,
"grad_norm": 1.421875,
"learning_rate": 0.00017100611113002702,
"loss": 0.6458,
"step": 2255
},
{
"epoch": 0.5440539239287434,
"grad_norm": 1.375,
"learning_rate": 0.0001709603118867037,
"loss": 0.6651,
"step": 2260
},
{
"epoch": 0.5452575830524795,
"grad_norm": 1.4375,
"learning_rate": 0.00017091442067041792,
"loss": 0.6818,
"step": 2265
},
{
"epoch": 0.5464612421762157,
"grad_norm": 1.3203125,
"learning_rate": 0.00017086843755449203,
"loss": 0.6613,
"step": 2270
},
{
"epoch": 0.5476649012999518,
"grad_norm": 1.46875,
"learning_rate": 0.00017082236261239532,
"loss": 0.6473,
"step": 2275
},
{
"epoch": 0.548868560423688,
"grad_norm": 1.5,
"learning_rate": 0.0001707761959177437,
"loss": 0.6797,
"step": 2280
},
{
"epoch": 0.5500722195474241,
"grad_norm": 1.484375,
"learning_rate": 0.00017072993754429973,
"loss": 0.6512,
"step": 2285
},
{
"epoch": 0.5512758786711603,
"grad_norm": 1.4921875,
"learning_rate": 0.00017068358756597242,
"loss": 0.6498,
"step": 2290
},
{
"epoch": 0.5524795377948964,
"grad_norm": 1.265625,
"learning_rate": 0.00017063714605681718,
"loss": 0.6372,
"step": 2295
},
{
"epoch": 0.5536831969186327,
"grad_norm": 1.421875,
"learning_rate": 0.00017059061309103563,
"loss": 0.6486,
"step": 2300
},
{
"epoch": 0.5548868560423688,
"grad_norm": 1.453125,
"learning_rate": 0.00017054398874297548,
"loss": 0.6633,
"step": 2305
},
{
"epoch": 0.556090515166105,
"grad_norm": 1.5078125,
"learning_rate": 0.00017049727308713052,
"loss": 0.6301,
"step": 2310
},
{
"epoch": 0.5572941742898411,
"grad_norm": 1.40625,
"learning_rate": 0.00017045046619814036,
"loss": 0.6282,
"step": 2315
},
{
"epoch": 0.5584978334135773,
"grad_norm": 1.4453125,
"learning_rate": 0.00017040356815079048,
"loss": 0.6738,
"step": 2320
},
{
"epoch": 0.5597014925373134,
"grad_norm": 1.3046875,
"learning_rate": 0.00017035657902001188,
"loss": 0.6275,
"step": 2325
},
{
"epoch": 0.5609051516610496,
"grad_norm": 1.34375,
"learning_rate": 0.00017030949888088116,
"loss": 0.6388,
"step": 2330
},
{
"epoch": 0.5621088107847857,
"grad_norm": 1.2421875,
"learning_rate": 0.0001702623278086203,
"loss": 0.6096,
"step": 2335
},
{
"epoch": 0.5633124699085219,
"grad_norm": 1.375,
"learning_rate": 0.00017021506587859664,
"loss": 0.6627,
"step": 2340
},
{
"epoch": 0.5645161290322581,
"grad_norm": 1.453125,
"learning_rate": 0.00017016771316632253,
"loss": 0.6482,
"step": 2345
},
{
"epoch": 0.5657197881559942,
"grad_norm": 1.53125,
"learning_rate": 0.00017012026974745555,
"loss": 0.6469,
"step": 2350
},
{
"epoch": 0.5669234472797304,
"grad_norm": 1.5,
"learning_rate": 0.00017007273569779807,
"loss": 0.6173,
"step": 2355
},
{
"epoch": 0.5681271064034665,
"grad_norm": 1.3828125,
"learning_rate": 0.00017002511109329732,
"loss": 0.622,
"step": 2360
},
{
"epoch": 0.5693307655272027,
"grad_norm": 1.3671875,
"learning_rate": 0.00016997739601004523,
"loss": 0.6142,
"step": 2365
},
{
"epoch": 0.5705344246509388,
"grad_norm": 1.3984375,
"learning_rate": 0.0001699295905242783,
"loss": 0.6124,
"step": 2370
},
{
"epoch": 0.571738083774675,
"grad_norm": 1.53125,
"learning_rate": 0.00016988169471237737,
"loss": 0.634,
"step": 2375
},
{
"epoch": 0.5729417428984112,
"grad_norm": 1.34375,
"learning_rate": 0.00016983370865086774,
"loss": 0.6306,
"step": 2380
},
{
"epoch": 0.5741454020221474,
"grad_norm": 1.34375,
"learning_rate": 0.00016978563241641873,
"loss": 0.6354,
"step": 2385
},
{
"epoch": 0.5753490611458835,
"grad_norm": 1.375,
"learning_rate": 0.00016973746608584396,
"loss": 0.683,
"step": 2390
},
{
"epoch": 0.5765527202696197,
"grad_norm": 1.3046875,
"learning_rate": 0.00016968920973610082,
"loss": 0.635,
"step": 2395
},
{
"epoch": 0.5777563793933558,
"grad_norm": 1.4921875,
"learning_rate": 0.0001696408634442906,
"loss": 0.6502,
"step": 2400
},
{
"epoch": 0.578960038517092,
"grad_norm": 1.3203125,
"learning_rate": 0.00016959242728765828,
"loss": 0.6509,
"step": 2405
},
{
"epoch": 0.5801636976408281,
"grad_norm": 1.4453125,
"learning_rate": 0.00016954390134359237,
"loss": 0.6082,
"step": 2410
},
{
"epoch": 0.5813673567645643,
"grad_norm": 1.359375,
"learning_rate": 0.000169495285689625,
"loss": 0.6122,
"step": 2415
},
{
"epoch": 0.5825710158883004,
"grad_norm": 1.4296875,
"learning_rate": 0.00016944658040343142,
"loss": 0.6628,
"step": 2420
},
{
"epoch": 0.5837746750120366,
"grad_norm": 1.25,
"learning_rate": 0.0001693977855628302,
"loss": 0.6307,
"step": 2425
},
{
"epoch": 0.5849783341357727,
"grad_norm": 2.234375,
"learning_rate": 0.00016934890124578305,
"loss": 0.6582,
"step": 2430
},
{
"epoch": 0.5861819932595089,
"grad_norm": 1.484375,
"learning_rate": 0.00016929992753039454,
"loss": 0.6318,
"step": 2435
},
{
"epoch": 0.587385652383245,
"grad_norm": 1.3046875,
"learning_rate": 0.00016925086449491212,
"loss": 0.626,
"step": 2440
},
{
"epoch": 0.5885893115069812,
"grad_norm": 1.4609375,
"learning_rate": 0.0001692017122177259,
"loss": 0.6422,
"step": 2445
},
{
"epoch": 0.5897929706307173,
"grad_norm": 1.3671875,
"learning_rate": 0.00016915247077736872,
"loss": 0.649,
"step": 2450
},
{
"epoch": 0.5909966297544536,
"grad_norm": 1.3984375,
"learning_rate": 0.00016910314025251567,
"loss": 0.6335,
"step": 2455
},
{
"epoch": 0.5922002888781897,
"grad_norm": 1.28125,
"learning_rate": 0.00016905372072198433,
"loss": 0.6265,
"step": 2460
},
{
"epoch": 0.5934039480019259,
"grad_norm": 1.4921875,
"learning_rate": 0.00016900421226473446,
"loss": 0.6399,
"step": 2465
},
{
"epoch": 0.594607607125662,
"grad_norm": 1.5234375,
"learning_rate": 0.00016895461495986783,
"loss": 0.6459,
"step": 2470
},
{
"epoch": 0.5958112662493982,
"grad_norm": 1.421875,
"learning_rate": 0.0001689049288866283,
"loss": 0.6353,
"step": 2475
},
{
"epoch": 0.5970149253731343,
"grad_norm": 1.421875,
"learning_rate": 0.00016885515412440137,
"loss": 0.661,
"step": 2480
},
{
"epoch": 0.5982185844968705,
"grad_norm": 1.3671875,
"learning_rate": 0.00016880529075271445,
"loss": 0.7094,
"step": 2485
},
{
"epoch": 0.5994222436206067,
"grad_norm": 1.3203125,
"learning_rate": 0.00016875533885123636,
"loss": 0.6169,
"step": 2490
},
{
"epoch": 0.6006259027443428,
"grad_norm": 1.5859375,
"learning_rate": 0.00016870529849977745,
"loss": 0.6238,
"step": 2495
},
{
"epoch": 0.601829561868079,
"grad_norm": 1.421875,
"learning_rate": 0.0001686551697782894,
"loss": 0.6355,
"step": 2500
},
{
"epoch": 0.601829561868079,
"eval_loss": 0.5359562635421753,
"eval_runtime": 2.4034,
"eval_samples_per_second": 83.214,
"eval_steps_per_second": 83.214,
"step": 2500
},
{
"epoch": 0.6030332209918151,
"grad_norm": 1.4296875,
"learning_rate": 0.00016860495276686504,
"loss": 0.6152,
"step": 2505
},
{
"epoch": 0.6042368801155513,
"grad_norm": 1.2578125,
"learning_rate": 0.00016855464754573826,
"loss": 0.6355,
"step": 2510
},
{
"epoch": 0.6054405392392874,
"grad_norm": 1.3828125,
"learning_rate": 0.00016850425419528395,
"loss": 0.6177,
"step": 2515
},
{
"epoch": 0.6066441983630236,
"grad_norm": 1.3046875,
"learning_rate": 0.00016845377279601774,
"loss": 0.6431,
"step": 2520
},
{
"epoch": 0.6078478574867597,
"grad_norm": 1.421875,
"learning_rate": 0.00016840320342859593,
"loss": 0.641,
"step": 2525
},
{
"epoch": 0.609051516610496,
"grad_norm": 1.421875,
"learning_rate": 0.0001683525461738155,
"loss": 0.6243,
"step": 2530
},
{
"epoch": 0.610255175734232,
"grad_norm": 1.3984375,
"learning_rate": 0.00016830180111261362,
"loss": 0.6137,
"step": 2535
},
{
"epoch": 0.6114588348579683,
"grad_norm": 1.3828125,
"learning_rate": 0.00016825096832606806,
"loss": 0.6148,
"step": 2540
},
{
"epoch": 0.6126624939817044,
"grad_norm": 1.3203125,
"learning_rate": 0.0001682000478953964,
"loss": 0.6307,
"step": 2545
},
{
"epoch": 0.6138661531054406,
"grad_norm": 1.296875,
"learning_rate": 0.00016814903990195658,
"loss": 0.6314,
"step": 2550
},
{
"epoch": 0.6150698122291767,
"grad_norm": 1.3046875,
"learning_rate": 0.00016809794442724623,
"loss": 0.6148,
"step": 2555
},
{
"epoch": 0.6162734713529129,
"grad_norm": 1.2578125,
"learning_rate": 0.00016804676155290284,
"loss": 0.6156,
"step": 2560
},
{
"epoch": 0.617477130476649,
"grad_norm": 1.421875,
"learning_rate": 0.0001679954913607035,
"loss": 0.641,
"step": 2565
},
{
"epoch": 0.6186807896003852,
"grad_norm": 1.3984375,
"learning_rate": 0.00016794413393256486,
"loss": 0.6264,
"step": 2570
},
{
"epoch": 0.6198844487241213,
"grad_norm": 1.3515625,
"learning_rate": 0.0001678926893505429,
"loss": 0.5985,
"step": 2575
},
{
"epoch": 0.6210881078478575,
"grad_norm": 1.4140625,
"learning_rate": 0.0001678411576968329,
"loss": 0.5958,
"step": 2580
},
{
"epoch": 0.6222917669715936,
"grad_norm": 1.4140625,
"learning_rate": 0.0001677895390537692,
"loss": 0.658,
"step": 2585
},
{
"epoch": 0.6234954260953298,
"grad_norm": 1.5234375,
"learning_rate": 0.0001677378335038252,
"loss": 0.6186,
"step": 2590
},
{
"epoch": 0.6246990852190659,
"grad_norm": 1.4609375,
"learning_rate": 0.0001676860411296131,
"loss": 0.6286,
"step": 2595
},
{
"epoch": 0.6259027443428021,
"grad_norm": 1.34375,
"learning_rate": 0.0001676341620138838,
"loss": 0.6219,
"step": 2600
},
{
"epoch": 0.6271064034665382,
"grad_norm": 1.5,
"learning_rate": 0.00016758219623952688,
"loss": 0.6304,
"step": 2605
},
{
"epoch": 0.6283100625902744,
"grad_norm": 1.4921875,
"learning_rate": 0.00016753014388957028,
"loss": 0.653,
"step": 2610
},
{
"epoch": 0.6295137217140105,
"grad_norm": 1.4296875,
"learning_rate": 0.00016747800504718035,
"loss": 0.6361,
"step": 2615
},
{
"epoch": 0.6307173808377468,
"grad_norm": 1.2890625,
"learning_rate": 0.00016742577979566157,
"loss": 0.6186,
"step": 2620
},
{
"epoch": 0.6319210399614829,
"grad_norm": 1.3359375,
"learning_rate": 0.0001673734682184565,
"loss": 0.6639,
"step": 2625
},
{
"epoch": 0.6331246990852191,
"grad_norm": 1.34375,
"learning_rate": 0.0001673210703991457,
"loss": 0.6343,
"step": 2630
},
{
"epoch": 0.6343283582089553,
"grad_norm": 1.3515625,
"learning_rate": 0.00016726858642144733,
"loss": 0.6222,
"step": 2635
},
{
"epoch": 0.6355320173326914,
"grad_norm": 1.4140625,
"learning_rate": 0.00016721601636921743,
"loss": 0.6644,
"step": 2640
},
{
"epoch": 0.6367356764564276,
"grad_norm": 1.5234375,
"learning_rate": 0.00016716336032644944,
"loss": 0.6349,
"step": 2645
},
{
"epoch": 0.6379393355801637,
"grad_norm": 1.40625,
"learning_rate": 0.0001671106183772742,
"loss": 0.6215,
"step": 2650
},
{
"epoch": 0.6391429947038999,
"grad_norm": 1.4140625,
"learning_rate": 0.00016705779060595985,
"loss": 0.641,
"step": 2655
},
{
"epoch": 0.640346653827636,
"grad_norm": 1.4375,
"learning_rate": 0.0001670048770969116,
"loss": 0.6223,
"step": 2660
},
{
"epoch": 0.6415503129513722,
"grad_norm": 1.359375,
"learning_rate": 0.00016695187793467167,
"loss": 0.6244,
"step": 2665
},
{
"epoch": 0.6427539720751083,
"grad_norm": 1.3046875,
"learning_rate": 0.00016689879320391917,
"loss": 0.6003,
"step": 2670
},
{
"epoch": 0.6439576311988445,
"grad_norm": 1.1875,
"learning_rate": 0.00016684562298946987,
"loss": 0.6195,
"step": 2675
},
{
"epoch": 0.6451612903225806,
"grad_norm": 1.5703125,
"learning_rate": 0.00016679236737627613,
"loss": 0.6311,
"step": 2680
},
{
"epoch": 0.6463649494463168,
"grad_norm": 1.390625,
"learning_rate": 0.0001667390264494268,
"loss": 0.6297,
"step": 2685
},
{
"epoch": 0.6475686085700529,
"grad_norm": 1.3125,
"learning_rate": 0.00016668560029414699,
"loss": 0.6197,
"step": 2690
},
{
"epoch": 0.6487722676937892,
"grad_norm": 1.3984375,
"learning_rate": 0.00016663208899579798,
"loss": 0.6159,
"step": 2695
},
{
"epoch": 0.6499759268175253,
"grad_norm": 1.328125,
"learning_rate": 0.00016657849263987715,
"loss": 0.6258,
"step": 2700
},
{
"epoch": 0.6511795859412615,
"grad_norm": 1.25,
"learning_rate": 0.00016652481131201768,
"loss": 0.6746,
"step": 2705
},
{
"epoch": 0.6523832450649976,
"grad_norm": 1.28125,
"learning_rate": 0.00016647104509798867,
"loss": 0.6039,
"step": 2710
},
{
"epoch": 0.6535869041887338,
"grad_norm": 1.25,
"learning_rate": 0.00016641719408369462,
"loss": 0.6381,
"step": 2715
},
{
"epoch": 0.6547905633124699,
"grad_norm": 1.3359375,
"learning_rate": 0.0001663632583551757,
"loss": 0.6218,
"step": 2720
},
{
"epoch": 0.6559942224362061,
"grad_norm": 1.4296875,
"learning_rate": 0.00016630923799860743,
"loss": 0.6147,
"step": 2725
},
{
"epoch": 0.6571978815599422,
"grad_norm": 1.4375,
"learning_rate": 0.00016625513310030042,
"loss": 0.6536,
"step": 2730
},
{
"epoch": 0.6584015406836784,
"grad_norm": 1.3125,
"learning_rate": 0.00016620094374670047,
"loss": 0.6633,
"step": 2735
},
{
"epoch": 0.6596051998074145,
"grad_norm": 1.2421875,
"learning_rate": 0.00016614667002438823,
"loss": 0.6164,
"step": 2740
},
{
"epoch": 0.6608088589311507,
"grad_norm": 1.28125,
"learning_rate": 0.00016609231202007924,
"loss": 0.5894,
"step": 2745
},
{
"epoch": 0.6620125180548868,
"grad_norm": 1.34375,
"learning_rate": 0.00016603786982062363,
"loss": 0.6336,
"step": 2750
},
{
"epoch": 0.663216177178623,
"grad_norm": 1.34375,
"learning_rate": 0.00016598334351300613,
"loss": 0.6402,
"step": 2755
},
{
"epoch": 0.6644198363023591,
"grad_norm": 1.3125,
"learning_rate": 0.0001659287331843457,
"loss": 0.6195,
"step": 2760
},
{
"epoch": 0.6656234954260953,
"grad_norm": 1.34375,
"learning_rate": 0.00016587403892189575,
"loss": 0.6338,
"step": 2765
},
{
"epoch": 0.6668271545498314,
"grad_norm": 1.3046875,
"learning_rate": 0.00016581926081304365,
"loss": 0.631,
"step": 2770
},
{
"epoch": 0.6680308136735676,
"grad_norm": 1.453125,
"learning_rate": 0.00016576439894531075,
"loss": 0.6237,
"step": 2775
},
{
"epoch": 0.6692344727973039,
"grad_norm": 1.34375,
"learning_rate": 0.00016570945340635228,
"loss": 0.6423,
"step": 2780
},
{
"epoch": 0.67043813192104,
"grad_norm": 1.3359375,
"learning_rate": 0.0001656544242839571,
"loss": 0.6303,
"step": 2785
},
{
"epoch": 0.6716417910447762,
"grad_norm": 1.3828125,
"learning_rate": 0.00016559931166604768,
"loss": 0.6014,
"step": 2790
},
{
"epoch": 0.6728454501685123,
"grad_norm": 1.28125,
"learning_rate": 0.00016554411564067984,
"loss": 0.6299,
"step": 2795
},
{
"epoch": 0.6740491092922485,
"grad_norm": 1.3515625,
"learning_rate": 0.00016548883629604266,
"loss": 0.6262,
"step": 2800
},
{
"epoch": 0.6752527684159846,
"grad_norm": 1.2734375,
"learning_rate": 0.00016543347372045838,
"loss": 0.6097,
"step": 2805
},
{
"epoch": 0.6764564275397208,
"grad_norm": 1.546875,
"learning_rate": 0.0001653780280023822,
"loss": 0.6265,
"step": 2810
},
{
"epoch": 0.6776600866634569,
"grad_norm": 1.3671875,
"learning_rate": 0.00016532249923040214,
"loss": 0.6533,
"step": 2815
},
{
"epoch": 0.6788637457871931,
"grad_norm": 1.4296875,
"learning_rate": 0.00016526688749323901,
"loss": 0.6321,
"step": 2820
},
{
"epoch": 0.6800674049109292,
"grad_norm": 1.6328125,
"learning_rate": 0.00016521119287974602,
"loss": 0.6148,
"step": 2825
},
{
"epoch": 0.6812710640346654,
"grad_norm": 1.296875,
"learning_rate": 0.00016515541547890895,
"loss": 0.6007,
"step": 2830
},
{
"epoch": 0.6824747231584015,
"grad_norm": 1.2265625,
"learning_rate": 0.00016509955537984575,
"loss": 0.6219,
"step": 2835
},
{
"epoch": 0.6836783822821377,
"grad_norm": 1.359375,
"learning_rate": 0.00016504361267180657,
"loss": 0.6367,
"step": 2840
},
{
"epoch": 0.6848820414058738,
"grad_norm": 1.359375,
"learning_rate": 0.00016498758744417353,
"loss": 0.6188,
"step": 2845
},
{
"epoch": 0.68608570052961,
"grad_norm": 1.3125,
"learning_rate": 0.0001649314797864605,
"loss": 0.6162,
"step": 2850
},
{
"epoch": 0.6872893596533461,
"grad_norm": 1.8984375,
"learning_rate": 0.00016487528978831323,
"loss": 0.6024,
"step": 2855
},
{
"epoch": 0.6884930187770824,
"grad_norm": 1.4140625,
"learning_rate": 0.00016481901753950888,
"loss": 0.6152,
"step": 2860
},
{
"epoch": 0.6896966779008185,
"grad_norm": 1.3125,
"learning_rate": 0.0001647626631299561,
"loss": 0.6176,
"step": 2865
},
{
"epoch": 0.6909003370245547,
"grad_norm": 1.375,
"learning_rate": 0.00016470622664969473,
"loss": 0.6142,
"step": 2870
},
{
"epoch": 0.6921039961482908,
"grad_norm": 1.3671875,
"learning_rate": 0.00016464970818889587,
"loss": 0.6095,
"step": 2875
},
{
"epoch": 0.693307655272027,
"grad_norm": 1.265625,
"learning_rate": 0.00016459310783786154,
"loss": 0.6172,
"step": 2880
},
{
"epoch": 0.6945113143957631,
"grad_norm": 1.3203125,
"learning_rate": 0.00016453642568702454,
"loss": 0.6371,
"step": 2885
},
{
"epoch": 0.6957149735194993,
"grad_norm": 1.3515625,
"learning_rate": 0.00016447966182694842,
"loss": 0.6234,
"step": 2890
},
{
"epoch": 0.6969186326432354,
"grad_norm": 1.375,
"learning_rate": 0.0001644228163483273,
"loss": 0.6368,
"step": 2895
},
{
"epoch": 0.6981222917669716,
"grad_norm": 1.4296875,
"learning_rate": 0.0001643658893419857,
"loss": 0.5879,
"step": 2900
},
{
"epoch": 0.6993259508907077,
"grad_norm": 1.359375,
"learning_rate": 0.00016430888089887834,
"loss": 0.6275,
"step": 2905
},
{
"epoch": 0.7005296100144439,
"grad_norm": 1.21875,
"learning_rate": 0.00016425179111009009,
"loss": 0.5837,
"step": 2910
},
{
"epoch": 0.70173326913818,
"grad_norm": 1.421875,
"learning_rate": 0.00016419462006683584,
"loss": 0.6286,
"step": 2915
},
{
"epoch": 0.7029369282619162,
"grad_norm": 1.3046875,
"learning_rate": 0.00016413736786046024,
"loss": 0.5522,
"step": 2920
},
{
"epoch": 0.7041405873856523,
"grad_norm": 1.3828125,
"learning_rate": 0.00016408003458243768,
"loss": 0.6287,
"step": 2925
},
{
"epoch": 0.7053442465093885,
"grad_norm": 1.328125,
"learning_rate": 0.00016402262032437194,
"loss": 0.5847,
"step": 2930
},
{
"epoch": 0.7065479056331248,
"grad_norm": 1.4296875,
"learning_rate": 0.00016396512517799638,
"loss": 0.5989,
"step": 2935
},
{
"epoch": 0.7077515647568609,
"grad_norm": 1.3125,
"learning_rate": 0.00016390754923517348,
"loss": 0.5815,
"step": 2940
},
{
"epoch": 0.7089552238805971,
"grad_norm": 1.2578125,
"learning_rate": 0.00016384989258789483,
"loss": 0.6299,
"step": 2945
},
{
"epoch": 0.7101588830043332,
"grad_norm": 1.3828125,
"learning_rate": 0.00016379215532828098,
"loss": 0.6205,
"step": 2950
},
{
"epoch": 0.7113625421280694,
"grad_norm": 1.3203125,
"learning_rate": 0.00016373433754858128,
"loss": 0.6041,
"step": 2955
},
{
"epoch": 0.7125662012518055,
"grad_norm": 1.265625,
"learning_rate": 0.00016367643934117368,
"loss": 0.5704,
"step": 2960
},
{
"epoch": 0.7137698603755417,
"grad_norm": 1.2890625,
"learning_rate": 0.00016361846079856467,
"loss": 0.593,
"step": 2965
},
{
"epoch": 0.7149735194992778,
"grad_norm": 1.3359375,
"learning_rate": 0.00016356040201338917,
"loss": 0.6131,
"step": 2970
},
{
"epoch": 0.716177178623014,
"grad_norm": 1.4296875,
"learning_rate": 0.00016350226307841015,
"loss": 0.5934,
"step": 2975
},
{
"epoch": 0.7173808377467501,
"grad_norm": 1.21875,
"learning_rate": 0.0001634440440865188,
"loss": 0.6044,
"step": 2980
},
{
"epoch": 0.7185844968704863,
"grad_norm": 1.2421875,
"learning_rate": 0.0001633857451307341,
"loss": 0.6189,
"step": 2985
},
{
"epoch": 0.7197881559942224,
"grad_norm": 1.2734375,
"learning_rate": 0.00016332736630420282,
"loss": 0.6159,
"step": 2990
},
{
"epoch": 0.7209918151179586,
"grad_norm": 1.359375,
"learning_rate": 0.00016326890770019942,
"loss": 0.5984,
"step": 2995
},
{
"epoch": 0.7221954742416947,
"grad_norm": 1.375,
"learning_rate": 0.0001632103694121257,
"loss": 0.5956,
"step": 3000
},
{
"epoch": 0.7221954742416947,
"eval_loss": 0.5172761082649231,
"eval_runtime": 2.4017,
"eval_samples_per_second": 83.276,
"eval_steps_per_second": 83.276,
"step": 3000
},
{
"epoch": 0.7233991333654309,
"grad_norm": 1.34375,
"learning_rate": 0.0001631517515335109,
"loss": 0.6393,
"step": 3005
},
{
"epoch": 0.724602792489167,
"grad_norm": 1.390625,
"learning_rate": 0.00016309305415801128,
"loss": 0.6718,
"step": 3010
},
{
"epoch": 0.7258064516129032,
"grad_norm": 1.234375,
"learning_rate": 0.0001630342773794103,
"loss": 0.6037,
"step": 3015
},
{
"epoch": 0.7270101107366393,
"grad_norm": 1.2578125,
"learning_rate": 0.0001629754212916181,
"loss": 0.5953,
"step": 3020
},
{
"epoch": 0.7282137698603756,
"grad_norm": 1.34375,
"learning_rate": 0.00016291648598867163,
"loss": 0.5897,
"step": 3025
},
{
"epoch": 0.7294174289841117,
"grad_norm": 1.3515625,
"learning_rate": 0.00016285747156473445,
"loss": 0.6198,
"step": 3030
},
{
"epoch": 0.7306210881078479,
"grad_norm": 1.2265625,
"learning_rate": 0.00016279837811409645,
"loss": 0.5962,
"step": 3035
},
{
"epoch": 0.731824747231584,
"grad_norm": 1.3125,
"learning_rate": 0.0001627392057311738,
"loss": 0.5809,
"step": 3040
},
{
"epoch": 0.7330284063553202,
"grad_norm": 1.296875,
"learning_rate": 0.00016267995451050885,
"loss": 0.5829,
"step": 3045
},
{
"epoch": 0.7342320654790563,
"grad_norm": 1.2578125,
"learning_rate": 0.00016262062454676978,
"loss": 0.632,
"step": 3050
},
{
"epoch": 0.7354357246027925,
"grad_norm": 1.4921875,
"learning_rate": 0.00016256121593475072,
"loss": 0.5775,
"step": 3055
},
{
"epoch": 0.7366393837265286,
"grad_norm": 1.3984375,
"learning_rate": 0.0001625017287693714,
"loss": 0.623,
"step": 3060
},
{
"epoch": 0.7378430428502648,
"grad_norm": 1.375,
"learning_rate": 0.00016244216314567704,
"loss": 0.611,
"step": 3065
},
{
"epoch": 0.7390467019740009,
"grad_norm": 1.2890625,
"learning_rate": 0.00016238251915883827,
"loss": 0.6363,
"step": 3070
},
{
"epoch": 0.7402503610977371,
"grad_norm": 1.296875,
"learning_rate": 0.00016232279690415086,
"loss": 0.633,
"step": 3075
},
{
"epoch": 0.7414540202214733,
"grad_norm": 1.265625,
"learning_rate": 0.00016226299647703564,
"loss": 0.612,
"step": 3080
},
{
"epoch": 0.7426576793452094,
"grad_norm": 1.3046875,
"learning_rate": 0.0001622031179730384,
"loss": 0.5371,
"step": 3085
},
{
"epoch": 0.7438613384689456,
"grad_norm": 1.3046875,
"learning_rate": 0.00016214316148782968,
"loss": 0.6312,
"step": 3090
},
{
"epoch": 0.7450649975926817,
"grad_norm": 1.21875,
"learning_rate": 0.0001620831271172045,
"loss": 0.595,
"step": 3095
},
{
"epoch": 0.746268656716418,
"grad_norm": 1.2890625,
"learning_rate": 0.00016202301495708244,
"loss": 0.615,
"step": 3100
},
{
"epoch": 0.7474723158401541,
"grad_norm": 1.484375,
"learning_rate": 0.00016196282510350725,
"loss": 0.6047,
"step": 3105
},
{
"epoch": 0.7486759749638903,
"grad_norm": 1.3359375,
"learning_rate": 0.000161902557652647,
"loss": 0.5688,
"step": 3110
},
{
"epoch": 0.7498796340876264,
"grad_norm": 1.1328125,
"learning_rate": 0.00016184221270079352,
"loss": 0.6099,
"step": 3115
},
{
"epoch": 0.7510832932113626,
"grad_norm": 1.2734375,
"learning_rate": 0.00016178179034436263,
"loss": 0.5904,
"step": 3120
},
{
"epoch": 0.7522869523350987,
"grad_norm": 1.234375,
"learning_rate": 0.0001617212906798938,
"loss": 0.5969,
"step": 3125
},
{
"epoch": 0.7534906114588349,
"grad_norm": 1.375,
"learning_rate": 0.00016166071380404988,
"loss": 0.6169,
"step": 3130
},
{
"epoch": 0.754694270582571,
"grad_norm": 1.3828125,
"learning_rate": 0.00016160005981361727,
"loss": 0.5742,
"step": 3135
},
{
"epoch": 0.7558979297063072,
"grad_norm": 1.1953125,
"learning_rate": 0.0001615393288055055,
"loss": 0.6365,
"step": 3140
},
{
"epoch": 0.7571015888300433,
"grad_norm": 1.3359375,
"learning_rate": 0.0001614785208767471,
"loss": 0.5881,
"step": 3145
},
{
"epoch": 0.7583052479537795,
"grad_norm": 1.2890625,
"learning_rate": 0.00016141763612449758,
"loss": 0.6109,
"step": 3150
},
{
"epoch": 0.7595089070775156,
"grad_norm": 1.2421875,
"learning_rate": 0.0001613566746460352,
"loss": 0.5787,
"step": 3155
},
{
"epoch": 0.7607125662012518,
"grad_norm": 1.234375,
"learning_rate": 0.00016129563653876069,
"loss": 0.6149,
"step": 3160
},
{
"epoch": 0.7619162253249879,
"grad_norm": 1.3671875,
"learning_rate": 0.0001612345219001974,
"loss": 0.6038,
"step": 3165
},
{
"epoch": 0.7631198844487241,
"grad_norm": 1.28125,
"learning_rate": 0.0001611733308279908,
"loss": 0.5831,
"step": 3170
},
{
"epoch": 0.7643235435724602,
"grad_norm": 1.3984375,
"learning_rate": 0.00016111206341990855,
"loss": 0.6032,
"step": 3175
},
{
"epoch": 0.7655272026961965,
"grad_norm": 1.28125,
"learning_rate": 0.00016105071977384023,
"loss": 0.5921,
"step": 3180
},
{
"epoch": 0.7667308618199326,
"grad_norm": 1.3515625,
"learning_rate": 0.0001609892999877973,
"loss": 0.6032,
"step": 3185
},
{
"epoch": 0.7679345209436688,
"grad_norm": 1.234375,
"learning_rate": 0.0001609278041599128,
"loss": 0.6096,
"step": 3190
},
{
"epoch": 0.7691381800674049,
"grad_norm": 1.28125,
"learning_rate": 0.00016086623238844132,
"loss": 0.6154,
"step": 3195
},
{
"epoch": 0.7703418391911411,
"grad_norm": 1.3515625,
"learning_rate": 0.00016080458477175878,
"loss": 0.6341,
"step": 3200
},
{
"epoch": 0.7715454983148772,
"grad_norm": 1.2890625,
"learning_rate": 0.00016074286140836224,
"loss": 0.5924,
"step": 3205
},
{
"epoch": 0.7727491574386134,
"grad_norm": 1.265625,
"learning_rate": 0.00016068106239686985,
"loss": 0.619,
"step": 3210
},
{
"epoch": 0.7739528165623495,
"grad_norm": 1.203125,
"learning_rate": 0.00016061918783602056,
"loss": 0.6052,
"step": 3215
},
{
"epoch": 0.7751564756860857,
"grad_norm": 1.3125,
"learning_rate": 0.00016055723782467402,
"loss": 0.5785,
"step": 3220
},
{
"epoch": 0.7763601348098219,
"grad_norm": 1.21875,
"learning_rate": 0.00016049521246181054,
"loss": 0.6208,
"step": 3225
},
{
"epoch": 0.777563793933558,
"grad_norm": 1.21875,
"learning_rate": 0.0001604331118465307,
"loss": 0.6546,
"step": 3230
},
{
"epoch": 0.7787674530572942,
"grad_norm": 1.359375,
"learning_rate": 0.00016037093607805536,
"loss": 0.6166,
"step": 3235
},
{
"epoch": 0.7799711121810303,
"grad_norm": 1.328125,
"learning_rate": 0.00016030868525572555,
"loss": 0.5876,
"step": 3240
},
{
"epoch": 0.7811747713047665,
"grad_norm": 1.4375,
"learning_rate": 0.000160246359479002,
"loss": 0.5557,
"step": 3245
},
{
"epoch": 0.7823784304285026,
"grad_norm": 1.15625,
"learning_rate": 0.00016018395884746534,
"loss": 0.6041,
"step": 3250
},
{
"epoch": 0.7835820895522388,
"grad_norm": 1.546875,
"learning_rate": 0.0001601214834608159,
"loss": 0.5732,
"step": 3255
},
{
"epoch": 0.784785748675975,
"grad_norm": 1.2890625,
"learning_rate": 0.00016005893341887318,
"loss": 0.6156,
"step": 3260
},
{
"epoch": 0.7859894077997112,
"grad_norm": 1.1796875,
"learning_rate": 0.00015999630882157623,
"loss": 0.5772,
"step": 3265
},
{
"epoch": 0.7871930669234473,
"grad_norm": 1.28125,
"learning_rate": 0.00015993360976898304,
"loss": 0.5651,
"step": 3270
},
{
"epoch": 0.7883967260471835,
"grad_norm": 1.4453125,
"learning_rate": 0.00015987083636127066,
"loss": 0.6199,
"step": 3275
},
{
"epoch": 0.7896003851709196,
"grad_norm": 1.171875,
"learning_rate": 0.00015980798869873487,
"loss": 0.5641,
"step": 3280
},
{
"epoch": 0.7908040442946558,
"grad_norm": 1.2890625,
"learning_rate": 0.00015974506688179015,
"loss": 0.6227,
"step": 3285
},
{
"epoch": 0.7920077034183919,
"grad_norm": 1.265625,
"learning_rate": 0.0001596820710109694,
"loss": 0.5881,
"step": 3290
},
{
"epoch": 0.7932113625421281,
"grad_norm": 1.3515625,
"learning_rate": 0.00015961900118692388,
"loss": 0.5989,
"step": 3295
},
{
"epoch": 0.7944150216658642,
"grad_norm": 1.3984375,
"learning_rate": 0.00015955585751042305,
"loss": 0.5997,
"step": 3300
},
{
"epoch": 0.7956186807896004,
"grad_norm": 1.2890625,
"learning_rate": 0.00015949264008235426,
"loss": 0.598,
"step": 3305
},
{
"epoch": 0.7968223399133365,
"grad_norm": 1.4453125,
"learning_rate": 0.0001594293490037228,
"loss": 0.5824,
"step": 3310
},
{
"epoch": 0.7980259990370727,
"grad_norm": 1.3828125,
"learning_rate": 0.00015936598437565154,
"loss": 0.6047,
"step": 3315
},
{
"epoch": 0.7992296581608088,
"grad_norm": 1.21875,
"learning_rate": 0.00015930254629938095,
"loss": 0.6081,
"step": 3320
},
{
"epoch": 0.800433317284545,
"grad_norm": 1.25,
"learning_rate": 0.0001592390348762688,
"loss": 0.6084,
"step": 3325
},
{
"epoch": 0.8016369764082811,
"grad_norm": 1.2421875,
"learning_rate": 0.00015917545020779005,
"loss": 0.5911,
"step": 3330
},
{
"epoch": 0.8028406355320173,
"grad_norm": 1.2890625,
"learning_rate": 0.0001591117923955367,
"loss": 0.5856,
"step": 3335
},
{
"epoch": 0.8040442946557534,
"grad_norm": 1.421875,
"learning_rate": 0.00015904806154121766,
"loss": 0.6114,
"step": 3340
},
{
"epoch": 0.8052479537794897,
"grad_norm": 1.28125,
"learning_rate": 0.00015898425774665844,
"loss": 0.5982,
"step": 3345
},
{
"epoch": 0.8064516129032258,
"grad_norm": 1.234375,
"learning_rate": 0.00015892038111380122,
"loss": 0.5542,
"step": 3350
},
{
"epoch": 0.807655272026962,
"grad_norm": 1.375,
"learning_rate": 0.00015885643174470438,
"loss": 0.5927,
"step": 3355
},
{
"epoch": 0.8088589311506981,
"grad_norm": 1.2265625,
"learning_rate": 0.0001587924097415427,
"loss": 0.5313,
"step": 3360
},
{
"epoch": 0.8100625902744343,
"grad_norm": 1.3984375,
"learning_rate": 0.0001587283152066069,
"loss": 0.575,
"step": 3365
},
{
"epoch": 0.8112662493981705,
"grad_norm": 1.3359375,
"learning_rate": 0.00015866414824230362,
"loss": 0.5912,
"step": 3370
},
{
"epoch": 0.8124699085219066,
"grad_norm": 1.1875,
"learning_rate": 0.00015859990895115525,
"loss": 0.5957,
"step": 3375
},
{
"epoch": 0.8136735676456428,
"grad_norm": 1.3828125,
"learning_rate": 0.00015853559743579966,
"loss": 0.5992,
"step": 3380
},
{
"epoch": 0.8148772267693789,
"grad_norm": 1.2109375,
"learning_rate": 0.00015847121379899018,
"loss": 0.55,
"step": 3385
},
{
"epoch": 0.8160808858931151,
"grad_norm": 1.453125,
"learning_rate": 0.00015840675814359533,
"loss": 0.6401,
"step": 3390
},
{
"epoch": 0.8172845450168512,
"grad_norm": 1.3984375,
"learning_rate": 0.0001583422305725988,
"loss": 0.5889,
"step": 3395
},
{
"epoch": 0.8184882041405874,
"grad_norm": 1.2578125,
"learning_rate": 0.00015827763118909905,
"loss": 0.5919,
"step": 3400
},
{
"epoch": 0.8196918632643235,
"grad_norm": 1.4375,
"learning_rate": 0.00015821296009630936,
"loss": 0.633,
"step": 3405
},
{
"epoch": 0.8208955223880597,
"grad_norm": 1.234375,
"learning_rate": 0.00015814821739755752,
"loss": 0.5937,
"step": 3410
},
{
"epoch": 0.8220991815117958,
"grad_norm": 1.375,
"learning_rate": 0.00015808340319628582,
"loss": 0.5949,
"step": 3415
},
{
"epoch": 0.823302840635532,
"grad_norm": 1.390625,
"learning_rate": 0.00015801851759605069,
"loss": 0.5666,
"step": 3420
},
{
"epoch": 0.8245064997592682,
"grad_norm": 1.2421875,
"learning_rate": 0.0001579535607005227,
"loss": 0.6208,
"step": 3425
},
{
"epoch": 0.8257101588830044,
"grad_norm": 1.3046875,
"learning_rate": 0.00015788853261348635,
"loss": 0.6313,
"step": 3430
},
{
"epoch": 0.8269138180067405,
"grad_norm": 1.28125,
"learning_rate": 0.00015782343343883978,
"loss": 0.5513,
"step": 3435
},
{
"epoch": 0.8281174771304767,
"grad_norm": 1.296875,
"learning_rate": 0.00015775826328059484,
"loss": 0.5594,
"step": 3440
},
{
"epoch": 0.8293211362542128,
"grad_norm": 1.21875,
"learning_rate": 0.0001576930222428767,
"loss": 0.57,
"step": 3445
},
{
"epoch": 0.830524795377949,
"grad_norm": 1.2890625,
"learning_rate": 0.0001576277104299239,
"loss": 0.5756,
"step": 3450
},
{
"epoch": 0.8317284545016851,
"grad_norm": 1.3359375,
"learning_rate": 0.00015756232794608788,
"loss": 0.6003,
"step": 3455
},
{
"epoch": 0.8329321136254213,
"grad_norm": 1.4921875,
"learning_rate": 0.00015749687489583313,
"loss": 0.6116,
"step": 3460
},
{
"epoch": 0.8341357727491574,
"grad_norm": 1.2265625,
"learning_rate": 0.0001574313513837368,
"loss": 0.5729,
"step": 3465
},
{
"epoch": 0.8353394318728936,
"grad_norm": 1.2421875,
"learning_rate": 0.00015736575751448877,
"loss": 0.5828,
"step": 3470
},
{
"epoch": 0.8365430909966297,
"grad_norm": 1.359375,
"learning_rate": 0.0001573000933928911,
"loss": 0.5651,
"step": 3475
},
{
"epoch": 0.8377467501203659,
"grad_norm": 1.265625,
"learning_rate": 0.0001572343591238583,
"loss": 0.5863,
"step": 3480
},
{
"epoch": 0.838950409244102,
"grad_norm": 1.265625,
"learning_rate": 0.00015716855481241686,
"loss": 0.6015,
"step": 3485
},
{
"epoch": 0.8401540683678382,
"grad_norm": 1.2578125,
"learning_rate": 0.0001571026805637052,
"loss": 0.5433,
"step": 3490
},
{
"epoch": 0.8413577274915743,
"grad_norm": 1.453125,
"learning_rate": 0.00015703673648297345,
"loss": 0.613,
"step": 3495
},
{
"epoch": 0.8425613866153105,
"grad_norm": 1.234375,
"learning_rate": 0.00015697072267558345,
"loss": 0.6195,
"step": 3500
},
{
"epoch": 0.8425613866153105,
"eval_loss": 0.49514415860176086,
"eval_runtime": 2.4002,
"eval_samples_per_second": 83.326,
"eval_steps_per_second": 83.326,
"step": 3500
},
{
"epoch": 0.8437650457390466,
"grad_norm": 1.2421875,
"learning_rate": 0.00015690463924700822,
"loss": 0.5976,
"step": 3505
},
{
"epoch": 0.8449687048627829,
"grad_norm": 1.28125,
"learning_rate": 0.00015683848630283222,
"loss": 0.5928,
"step": 3510
},
{
"epoch": 0.8461723639865191,
"grad_norm": 1.359375,
"learning_rate": 0.00015677226394875086,
"loss": 0.5912,
"step": 3515
},
{
"epoch": 0.8473760231102552,
"grad_norm": 1.296875,
"learning_rate": 0.0001567059722905705,
"loss": 0.5744,
"step": 3520
},
{
"epoch": 0.8485796822339914,
"grad_norm": 1.2890625,
"learning_rate": 0.00015663961143420817,
"loss": 0.6012,
"step": 3525
},
{
"epoch": 0.8497833413577275,
"grad_norm": 1.3359375,
"learning_rate": 0.0001565731814856916,
"loss": 0.5899,
"step": 3530
},
{
"epoch": 0.8509870004814637,
"grad_norm": 1.4140625,
"learning_rate": 0.0001565066825511587,
"loss": 0.6465,
"step": 3535
},
{
"epoch": 0.8521906596051998,
"grad_norm": 1.1796875,
"learning_rate": 0.00015644011473685786,
"loss": 0.5968,
"step": 3540
},
{
"epoch": 0.853394318728936,
"grad_norm": 1.3671875,
"learning_rate": 0.00015637347814914724,
"loss": 0.588,
"step": 3545
},
{
"epoch": 0.8545979778526721,
"grad_norm": 1.265625,
"learning_rate": 0.00015630677289449514,
"loss": 0.565,
"step": 3550
},
{
"epoch": 0.8558016369764083,
"grad_norm": 1.296875,
"learning_rate": 0.00015623999907947935,
"loss": 0.6125,
"step": 3555
},
{
"epoch": 0.8570052961001444,
"grad_norm": 1.2265625,
"learning_rate": 0.0001561731568107874,
"loss": 0.5903,
"step": 3560
},
{
"epoch": 0.8582089552238806,
"grad_norm": 1.140625,
"learning_rate": 0.0001561062461952161,
"loss": 0.6142,
"step": 3565
},
{
"epoch": 0.8594126143476167,
"grad_norm": 1.3984375,
"learning_rate": 0.00015603926733967138,
"loss": 0.5918,
"step": 3570
},
{
"epoch": 0.8606162734713529,
"grad_norm": 1.21875,
"learning_rate": 0.00015597222035116835,
"loss": 0.5974,
"step": 3575
},
{
"epoch": 0.861819932595089,
"grad_norm": 1.3515625,
"learning_rate": 0.00015590510533683088,
"loss": 0.5726,
"step": 3580
},
{
"epoch": 0.8630235917188253,
"grad_norm": 1.2421875,
"learning_rate": 0.00015583792240389158,
"loss": 0.5648,
"step": 3585
},
{
"epoch": 0.8642272508425614,
"grad_norm": 1.2890625,
"learning_rate": 0.00015577067165969152,
"loss": 0.5807,
"step": 3590
},
{
"epoch": 0.8654309099662976,
"grad_norm": 1.2578125,
"learning_rate": 0.00015570335321168018,
"loss": 0.6013,
"step": 3595
},
{
"epoch": 0.8666345690900337,
"grad_norm": 1.3515625,
"learning_rate": 0.00015563596716741516,
"loss": 0.5767,
"step": 3600
},
{
"epoch": 0.8678382282137699,
"grad_norm": 1.3125,
"learning_rate": 0.00015556851363456213,
"loss": 0.5825,
"step": 3605
},
{
"epoch": 0.869041887337506,
"grad_norm": 1.328125,
"learning_rate": 0.0001555009927208945,
"loss": 0.5685,
"step": 3610
},
{
"epoch": 0.8702455464612422,
"grad_norm": 1.21875,
"learning_rate": 0.00015543340453429337,
"loss": 0.6157,
"step": 3615
},
{
"epoch": 0.8714492055849783,
"grad_norm": 1.3203125,
"learning_rate": 0.00015536574918274736,
"loss": 0.5748,
"step": 3620
},
{
"epoch": 0.8726528647087145,
"grad_norm": 1.296875,
"learning_rate": 0.0001552980267743524,
"loss": 0.5961,
"step": 3625
},
{
"epoch": 0.8738565238324506,
"grad_norm": 1.2578125,
"learning_rate": 0.0001552302374173115,
"loss": 0.6097,
"step": 3630
},
{
"epoch": 0.8750601829561868,
"grad_norm": 1.1953125,
"learning_rate": 0.00015516238121993466,
"loss": 0.5665,
"step": 3635
},
{
"epoch": 0.8762638420799229,
"grad_norm": 1.171875,
"learning_rate": 0.00015509445829063877,
"loss": 0.619,
"step": 3640
},
{
"epoch": 0.8774675012036591,
"grad_norm": 1.265625,
"learning_rate": 0.00015502646873794717,
"loss": 0.5902,
"step": 3645
},
{
"epoch": 0.8786711603273952,
"grad_norm": 1.3046875,
"learning_rate": 0.00015495841267048978,
"loss": 0.5833,
"step": 3650
},
{
"epoch": 0.8798748194511314,
"grad_norm": 1.15625,
"learning_rate": 0.00015489029019700274,
"loss": 0.5734,
"step": 3655
},
{
"epoch": 0.8810784785748677,
"grad_norm": 1.203125,
"learning_rate": 0.00015482210142632832,
"loss": 0.5526,
"step": 3660
},
{
"epoch": 0.8822821376986038,
"grad_norm": 1.2578125,
"learning_rate": 0.00015475384646741465,
"loss": 0.5419,
"step": 3665
},
{
"epoch": 0.88348579682234,
"grad_norm": 1.2578125,
"learning_rate": 0.0001546855254293157,
"loss": 0.6102,
"step": 3670
},
{
"epoch": 0.8846894559460761,
"grad_norm": 1.203125,
"learning_rate": 0.00015461713842119092,
"loss": 0.5931,
"step": 3675
},
{
"epoch": 0.8858931150698123,
"grad_norm": 1.3125,
"learning_rate": 0.00015454868555230526,
"loss": 0.5969,
"step": 3680
},
{
"epoch": 0.8870967741935484,
"grad_norm": 1.296875,
"learning_rate": 0.00015448016693202888,
"loss": 0.555,
"step": 3685
},
{
"epoch": 0.8883004333172846,
"grad_norm": 1.34375,
"learning_rate": 0.0001544115826698369,
"loss": 0.5798,
"step": 3690
},
{
"epoch": 0.8895040924410207,
"grad_norm": 1.3984375,
"learning_rate": 0.00015434293287530947,
"loss": 0.5854,
"step": 3695
},
{
"epoch": 0.8907077515647569,
"grad_norm": 1.359375,
"learning_rate": 0.00015427421765813133,
"loss": 0.6015,
"step": 3700
},
{
"epoch": 0.891911410688493,
"grad_norm": 1.125,
"learning_rate": 0.00015420543712809176,
"loss": 0.5548,
"step": 3705
},
{
"epoch": 0.8931150698122292,
"grad_norm": 1.1953125,
"learning_rate": 0.00015413659139508444,
"loss": 0.5799,
"step": 3710
},
{
"epoch": 0.8943187289359653,
"grad_norm": 1.2890625,
"learning_rate": 0.00015406768056910717,
"loss": 0.5821,
"step": 3715
},
{
"epoch": 0.8955223880597015,
"grad_norm": 1.1015625,
"learning_rate": 0.0001539987047602618,
"loss": 0.5711,
"step": 3720
},
{
"epoch": 0.8967260471834376,
"grad_norm": 1.1875,
"learning_rate": 0.00015392966407875403,
"loss": 0.5839,
"step": 3725
},
{
"epoch": 0.8979297063071738,
"grad_norm": 1.1484375,
"learning_rate": 0.0001538605586348931,
"loss": 0.5959,
"step": 3730
},
{
"epoch": 0.8991333654309099,
"grad_norm": 1.234375,
"learning_rate": 0.0001537913885390919,
"loss": 0.545,
"step": 3735
},
{
"epoch": 0.9003370245546461,
"grad_norm": 1.1953125,
"learning_rate": 0.0001537221539018664,
"loss": 0.5711,
"step": 3740
},
{
"epoch": 0.9015406836783822,
"grad_norm": 1.296875,
"learning_rate": 0.00015365285483383582,
"loss": 0.5497,
"step": 3745
},
{
"epoch": 0.9027443428021185,
"grad_norm": 1.3359375,
"learning_rate": 0.00015358349144572236,
"loss": 0.5744,
"step": 3750
},
{
"epoch": 0.9039480019258546,
"grad_norm": 1.1484375,
"learning_rate": 0.0001535140638483509,
"loss": 0.5886,
"step": 3755
},
{
"epoch": 0.9051516610495908,
"grad_norm": 1.2578125,
"learning_rate": 0.00015344457215264894,
"loss": 0.5872,
"step": 3760
},
{
"epoch": 0.9063553201733269,
"grad_norm": 1.2890625,
"learning_rate": 0.0001533750164696464,
"loss": 0.6167,
"step": 3765
},
{
"epoch": 0.9075589792970631,
"grad_norm": 1.234375,
"learning_rate": 0.00015330539691047544,
"loss": 0.5705,
"step": 3770
},
{
"epoch": 0.9087626384207992,
"grad_norm": 1.1875,
"learning_rate": 0.00015323571358637024,
"loss": 0.5854,
"step": 3775
},
{
"epoch": 0.9099662975445354,
"grad_norm": 1.28125,
"learning_rate": 0.00015316596660866694,
"loss": 0.5895,
"step": 3780
},
{
"epoch": 0.9111699566682715,
"grad_norm": 1.2265625,
"learning_rate": 0.00015309615608880329,
"loss": 0.5797,
"step": 3785
},
{
"epoch": 0.9123736157920077,
"grad_norm": 1.203125,
"learning_rate": 0.0001530262821383186,
"loss": 0.5766,
"step": 3790
},
{
"epoch": 0.9135772749157438,
"grad_norm": 1.3125,
"learning_rate": 0.00015295634486885357,
"loss": 0.5612,
"step": 3795
},
{
"epoch": 0.91478093403948,
"grad_norm": 1.296875,
"learning_rate": 0.00015288634439215,
"loss": 0.5973,
"step": 3800
},
{
"epoch": 0.9159845931632162,
"grad_norm": 1.25,
"learning_rate": 0.00015281628082005068,
"loss": 0.5812,
"step": 3805
},
{
"epoch": 0.9171882522869523,
"grad_norm": 1.2578125,
"learning_rate": 0.00015274615426449928,
"loss": 0.6128,
"step": 3810
},
{
"epoch": 0.9183919114106885,
"grad_norm": 1.234375,
"learning_rate": 0.00015267596483754006,
"loss": 0.5636,
"step": 3815
},
{
"epoch": 0.9195955705344246,
"grad_norm": 1.2734375,
"learning_rate": 0.0001526057126513177,
"loss": 0.6068,
"step": 3820
},
{
"epoch": 0.9207992296581609,
"grad_norm": 1.359375,
"learning_rate": 0.00015253539781807723,
"loss": 0.5671,
"step": 3825
},
{
"epoch": 0.922002888781897,
"grad_norm": 1.3203125,
"learning_rate": 0.00015246502045016368,
"loss": 0.5896,
"step": 3830
},
{
"epoch": 0.9232065479056332,
"grad_norm": 1.3125,
"learning_rate": 0.00015239458066002205,
"loss": 0.5953,
"step": 3835
},
{
"epoch": 0.9244102070293693,
"grad_norm": 1.25,
"learning_rate": 0.0001523240785601971,
"loss": 0.5414,
"step": 3840
},
{
"epoch": 0.9256138661531055,
"grad_norm": 1.3046875,
"learning_rate": 0.00015225351426333307,
"loss": 0.5688,
"step": 3845
},
{
"epoch": 0.9268175252768416,
"grad_norm": 1.28125,
"learning_rate": 0.00015218288788217365,
"loss": 0.5837,
"step": 3850
},
{
"epoch": 0.9280211844005778,
"grad_norm": 1.390625,
"learning_rate": 0.0001521121995295617,
"loss": 0.6235,
"step": 3855
},
{
"epoch": 0.9292248435243139,
"grad_norm": 1.28125,
"learning_rate": 0.00015204144931843907,
"loss": 0.5753,
"step": 3860
},
{
"epoch": 0.9304285026480501,
"grad_norm": 1.2734375,
"learning_rate": 0.00015197063736184638,
"loss": 0.5954,
"step": 3865
},
{
"epoch": 0.9316321617717862,
"grad_norm": 1.359375,
"learning_rate": 0.00015189976377292313,
"loss": 0.6025,
"step": 3870
},
{
"epoch": 0.9328358208955224,
"grad_norm": 1.1953125,
"learning_rate": 0.00015182882866490705,
"loss": 0.568,
"step": 3875
},
{
"epoch": 0.9340394800192585,
"grad_norm": 1.21875,
"learning_rate": 0.0001517578321511343,
"loss": 0.5858,
"step": 3880
},
{
"epoch": 0.9352431391429947,
"grad_norm": 1.2265625,
"learning_rate": 0.0001516867743450391,
"loss": 0.5447,
"step": 3885
},
{
"epoch": 0.9364467982667308,
"grad_norm": 1.3046875,
"learning_rate": 0.0001516156553601536,
"loss": 0.5706,
"step": 3890
},
{
"epoch": 0.937650457390467,
"grad_norm": 1.296875,
"learning_rate": 0.0001515444753101077,
"loss": 0.5655,
"step": 3895
},
{
"epoch": 0.9388541165142031,
"grad_norm": 1.296875,
"learning_rate": 0.00015147323430862885,
"loss": 0.5894,
"step": 3900
},
{
"epoch": 0.9400577756379394,
"grad_norm": 1.2109375,
"learning_rate": 0.000151401932469542,
"loss": 0.5615,
"step": 3905
},
{
"epoch": 0.9412614347616755,
"grad_norm": 1.203125,
"learning_rate": 0.0001513305699067691,
"loss": 0.5968,
"step": 3910
},
{
"epoch": 0.9424650938854117,
"grad_norm": 1.2265625,
"learning_rate": 0.0001512591467343293,
"loss": 0.5947,
"step": 3915
},
{
"epoch": 0.9436687530091478,
"grad_norm": 1.171875,
"learning_rate": 0.00015118766306633852,
"loss": 0.5947,
"step": 3920
},
{
"epoch": 0.944872412132884,
"grad_norm": 1.1796875,
"learning_rate": 0.0001511161190170093,
"loss": 0.5479,
"step": 3925
},
{
"epoch": 0.9460760712566201,
"grad_norm": 1.2734375,
"learning_rate": 0.00015104451470065072,
"loss": 0.5633,
"step": 3930
},
{
"epoch": 0.9472797303803563,
"grad_norm": 1.296875,
"learning_rate": 0.00015097285023166806,
"loss": 0.5664,
"step": 3935
},
{
"epoch": 0.9484833895040924,
"grad_norm": 1.1875,
"learning_rate": 0.00015090112572456287,
"loss": 0.5505,
"step": 3940
},
{
"epoch": 0.9496870486278286,
"grad_norm": 1.3203125,
"learning_rate": 0.00015082934129393246,
"loss": 0.5501,
"step": 3945
},
{
"epoch": 0.9508907077515648,
"grad_norm": 1.25,
"learning_rate": 0.00015075749705447,
"loss": 0.5473,
"step": 3950
},
{
"epoch": 0.9520943668753009,
"grad_norm": 1.21875,
"learning_rate": 0.0001506855931209641,
"loss": 0.5399,
"step": 3955
},
{
"epoch": 0.9532980259990371,
"grad_norm": 1.2578125,
"learning_rate": 0.0001506136296082988,
"loss": 0.538,
"step": 3960
},
{
"epoch": 0.9545016851227732,
"grad_norm": 1.2890625,
"learning_rate": 0.00015054160663145348,
"loss": 0.5856,
"step": 3965
},
{
"epoch": 0.9557053442465094,
"grad_norm": 1.296875,
"learning_rate": 0.00015046952430550222,
"loss": 0.5595,
"step": 3970
},
{
"epoch": 0.9569090033702455,
"grad_norm": 1.2578125,
"learning_rate": 0.00015039738274561423,
"loss": 0.5672,
"step": 3975
},
{
"epoch": 0.9581126624939817,
"grad_norm": 1.3515625,
"learning_rate": 0.00015032518206705317,
"loss": 0.5799,
"step": 3980
},
{
"epoch": 0.9593163216177178,
"grad_norm": 1.46875,
"learning_rate": 0.00015025292238517721,
"loss": 0.5946,
"step": 3985
},
{
"epoch": 0.9605199807414541,
"grad_norm": 1.25,
"learning_rate": 0.00015018060381543884,
"loss": 0.5416,
"step": 3990
},
{
"epoch": 0.9617236398651902,
"grad_norm": 1.2890625,
"learning_rate": 0.00015010822647338454,
"loss": 0.5897,
"step": 3995
},
{
"epoch": 0.9629272989889264,
"grad_norm": 1.296875,
"learning_rate": 0.0001500357904746548,
"loss": 0.5483,
"step": 4000
},
{
"epoch": 0.9629272989889264,
"eval_loss": 0.4734587073326111,
"eval_runtime": 2.3912,
"eval_samples_per_second": 83.641,
"eval_steps_per_second": 83.641,
"step": 4000
},
{
"epoch": 0.9641309581126625,
"grad_norm": 1.234375,
"learning_rate": 0.00014996329593498374,
"loss": 0.6136,
"step": 4005
},
{
"epoch": 0.9653346172363987,
"grad_norm": 1.265625,
"learning_rate": 0.00014989074297019905,
"loss": 0.57,
"step": 4010
},
{
"epoch": 0.9665382763601348,
"grad_norm": 1.3203125,
"learning_rate": 0.0001498181316962218,
"loss": 0.5694,
"step": 4015
},
{
"epoch": 0.967741935483871,
"grad_norm": 1.3359375,
"learning_rate": 0.00014974546222906615,
"loss": 0.5752,
"step": 4020
},
{
"epoch": 0.9689455946076071,
"grad_norm": 1.28125,
"learning_rate": 0.00014967273468483936,
"loss": 0.5556,
"step": 4025
},
{
"epoch": 0.9701492537313433,
"grad_norm": 1.234375,
"learning_rate": 0.00014959994917974133,
"loss": 0.5719,
"step": 4030
},
{
"epoch": 0.9713529128550794,
"grad_norm": 1.171875,
"learning_rate": 0.00014952710583006462,
"loss": 0.5756,
"step": 4035
},
{
"epoch": 0.9725565719788156,
"grad_norm": 1.28125,
"learning_rate": 0.00014945420475219427,
"loss": 0.5698,
"step": 4040
},
{
"epoch": 0.9737602311025517,
"grad_norm": 1.1953125,
"learning_rate": 0.00014938124606260752,
"loss": 0.5599,
"step": 4045
},
{
"epoch": 0.9749638902262879,
"grad_norm": 1.296875,
"learning_rate": 0.00014930822987787367,
"loss": 0.5838,
"step": 4050
},
{
"epoch": 0.976167549350024,
"grad_norm": 1.28125,
"learning_rate": 0.0001492351563146538,
"loss": 0.557,
"step": 4055
},
{
"epoch": 0.9773712084737602,
"grad_norm": 1.3203125,
"learning_rate": 0.00014916202548970076,
"loss": 0.5653,
"step": 4060
},
{
"epoch": 0.9785748675974963,
"grad_norm": 1.2734375,
"learning_rate": 0.0001490888375198589,
"loss": 0.5479,
"step": 4065
},
{
"epoch": 0.9797785267212326,
"grad_norm": 1.2265625,
"learning_rate": 0.00014901559252206373,
"loss": 0.556,
"step": 4070
},
{
"epoch": 0.9809821858449687,
"grad_norm": 1.4375,
"learning_rate": 0.00014894229061334212,
"loss": 0.617,
"step": 4075
},
{
"epoch": 0.9821858449687049,
"grad_norm": 1.171875,
"learning_rate": 0.0001488689319108117,
"loss": 0.5858,
"step": 4080
},
{
"epoch": 0.983389504092441,
"grad_norm": 1.1953125,
"learning_rate": 0.00014879551653168075,
"loss": 0.5617,
"step": 4085
},
{
"epoch": 0.9845931632161772,
"grad_norm": 1.140625,
"learning_rate": 0.00014872204459324834,
"loss": 0.5746,
"step": 4090
},
{
"epoch": 0.9857968223399133,
"grad_norm": 1.2421875,
"learning_rate": 0.00014864851621290375,
"loss": 0.5643,
"step": 4095
},
{
"epoch": 0.9870004814636495,
"grad_norm": 1.34375,
"learning_rate": 0.0001485749315081265,
"loss": 0.5819,
"step": 4100
},
{
"epoch": 0.9882041405873857,
"grad_norm": 1.2734375,
"learning_rate": 0.00014850129059648608,
"loss": 0.5738,
"step": 4105
},
{
"epoch": 0.9894077997111218,
"grad_norm": 1.328125,
"learning_rate": 0.0001484275935956418,
"loss": 0.5664,
"step": 4110
},
{
"epoch": 0.990611458834858,
"grad_norm": 1.171875,
"learning_rate": 0.00014835384062334255,
"loss": 0.5583,
"step": 4115
},
{
"epoch": 0.9918151179585941,
"grad_norm": 1.25,
"learning_rate": 0.00014828003179742665,
"loss": 0.5798,
"step": 4120
},
{
"epoch": 0.9930187770823303,
"grad_norm": 1.2890625,
"learning_rate": 0.00014820616723582175,
"loss": 0.5652,
"step": 4125
},
{
"epoch": 0.9942224362060664,
"grad_norm": 1.1875,
"learning_rate": 0.00014813224705654448,
"loss": 0.5567,
"step": 4130
},
{
"epoch": 0.9954260953298026,
"grad_norm": 1.203125,
"learning_rate": 0.00014805827137770027,
"loss": 0.5679,
"step": 4135
},
{
"epoch": 0.9966297544535387,
"grad_norm": 1.3671875,
"learning_rate": 0.00014798424031748335,
"loss": 0.5511,
"step": 4140
},
{
"epoch": 0.997833413577275,
"grad_norm": 1.34375,
"learning_rate": 0.00014791015399417634,
"loss": 0.584,
"step": 4145
},
{
"epoch": 0.999037072701011,
"grad_norm": 1.4921875,
"learning_rate": 0.00014783601252615021,
"loss": 0.5678,
"step": 4150
},
{
"epoch": 0.9997592681752527,
"eval_loss": 0.473895788192749,
"eval_runtime": 2.3815,
"eval_samples_per_second": 83.979,
"eval_steps_per_second": 83.979,
"step": 4153
},
{
"epoch": 1.0002407318247473,
"grad_norm": 1.2890625,
"learning_rate": 0.000147761816031864,
"loss": 0.5771,
"step": 4155
},
{
"epoch": 1.0014443909484834,
"grad_norm": 1.1875,
"learning_rate": 0.00014768756462986472,
"loss": 0.5225,
"step": 4160
},
{
"epoch": 1.0026480500722195,
"grad_norm": 1.15625,
"learning_rate": 0.00014761325843878708,
"loss": 0.5087,
"step": 4165
},
{
"epoch": 1.0038517091959558,
"grad_norm": 1.234375,
"learning_rate": 0.0001475388975773533,
"loss": 0.5132,
"step": 4170
},
{
"epoch": 1.0050553683196919,
"grad_norm": 1.1484375,
"learning_rate": 0.00014746448216437297,
"loss": 0.5072,
"step": 4175
},
{
"epoch": 1.006259027443428,
"grad_norm": 1.2109375,
"learning_rate": 0.00014739001231874282,
"loss": 0.5182,
"step": 4180
},
{
"epoch": 1.007462686567164,
"grad_norm": 1.28125,
"learning_rate": 0.00014731548815944667,
"loss": 0.5508,
"step": 4185
},
{
"epoch": 1.0086663456909004,
"grad_norm": 1.34375,
"learning_rate": 0.00014724090980555493,
"loss": 0.5124,
"step": 4190
},
{
"epoch": 1.0098700048146365,
"grad_norm": 1.2265625,
"learning_rate": 0.00014716627737622472,
"loss": 0.531,
"step": 4195
},
{
"epoch": 1.0110736639383726,
"grad_norm": 1.265625,
"learning_rate": 0.00014709159099069954,
"loss": 0.5358,
"step": 4200
},
{
"epoch": 1.0122773230621087,
"grad_norm": 1.3125,
"learning_rate": 0.00014701685076830905,
"loss": 0.5555,
"step": 4205
},
{
"epoch": 1.013480982185845,
"grad_norm": 1.140625,
"learning_rate": 0.00014694205682846902,
"loss": 0.5441,
"step": 4210
},
{
"epoch": 1.0146846413095811,
"grad_norm": 1.2265625,
"learning_rate": 0.00014686720929068097,
"loss": 0.4988,
"step": 4215
},
{
"epoch": 1.0158883004333172,
"grad_norm": 1.25,
"learning_rate": 0.00014679230827453201,
"loss": 0.5267,
"step": 4220
},
{
"epoch": 1.0170919595570533,
"grad_norm": 1.3515625,
"learning_rate": 0.00014671735389969488,
"loss": 0.5199,
"step": 4225
},
{
"epoch": 1.0182956186807897,
"grad_norm": 1.2890625,
"learning_rate": 0.0001466423462859274,
"loss": 0.5331,
"step": 4230
},
{
"epoch": 1.0194992778045258,
"grad_norm": 1.34375,
"learning_rate": 0.0001465672855530725,
"loss": 0.5153,
"step": 4235
},
{
"epoch": 1.0207029369282619,
"grad_norm": 1.28125,
"learning_rate": 0.000146492171821058,
"loss": 0.5189,
"step": 4240
},
{
"epoch": 1.021906596051998,
"grad_norm": 1.078125,
"learning_rate": 0.00014641700520989638,
"loss": 0.5432,
"step": 4245
},
{
"epoch": 1.0231102551757343,
"grad_norm": 1.171875,
"learning_rate": 0.0001463417858396846,
"loss": 0.5175,
"step": 4250
},
{
"epoch": 1.0243139142994704,
"grad_norm": 1.140625,
"learning_rate": 0.000146266513830604,
"loss": 0.5426,
"step": 4255
},
{
"epoch": 1.0255175734232065,
"grad_norm": 1.2890625,
"learning_rate": 0.00014619118930291993,
"loss": 0.5428,
"step": 4260
},
{
"epoch": 1.0267212325469428,
"grad_norm": 1.2578125,
"learning_rate": 0.0001461158123769816,
"loss": 0.5442,
"step": 4265
},
{
"epoch": 1.027924891670679,
"grad_norm": 1.2109375,
"learning_rate": 0.0001460403831732221,
"loss": 0.5237,
"step": 4270
},
{
"epoch": 1.029128550794415,
"grad_norm": 1.3359375,
"learning_rate": 0.0001459649018121579,
"loss": 0.5397,
"step": 4275
},
{
"epoch": 1.030332209918151,
"grad_norm": 1.1875,
"learning_rate": 0.00014588936841438893,
"loss": 0.5196,
"step": 4280
},
{
"epoch": 1.0315358690418874,
"grad_norm": 1.1484375,
"learning_rate": 0.00014581378310059813,
"loss": 0.5221,
"step": 4285
},
{
"epoch": 1.0327395281656235,
"grad_norm": 1.3203125,
"learning_rate": 0.0001457381459915515,
"loss": 0.4995,
"step": 4290
},
{
"epoch": 1.0339431872893596,
"grad_norm": 1.1875,
"learning_rate": 0.00014566245720809776,
"loss": 0.4799,
"step": 4295
},
{
"epoch": 1.0351468464130957,
"grad_norm": 1.125,
"learning_rate": 0.00014558671687116812,
"loss": 0.4823,
"step": 4300
},
{
"epoch": 1.036350505536832,
"grad_norm": 1.34375,
"learning_rate": 0.00014551092510177628,
"loss": 0.5294,
"step": 4305
},
{
"epoch": 1.0375541646605682,
"grad_norm": 1.3125,
"learning_rate": 0.00014543508202101804,
"loss": 0.5223,
"step": 4310
},
{
"epoch": 1.0387578237843043,
"grad_norm": 1.3203125,
"learning_rate": 0.0001453591877500712,
"loss": 0.5217,
"step": 4315
},
{
"epoch": 1.0399614829080404,
"grad_norm": 1.1875,
"learning_rate": 0.0001452832424101954,
"loss": 0.5155,
"step": 4320
},
{
"epoch": 1.0411651420317767,
"grad_norm": 1.1875,
"learning_rate": 0.00014520724612273169,
"loss": 0.5396,
"step": 4325
},
{
"epoch": 1.0423688011555128,
"grad_norm": 1.2265625,
"learning_rate": 0.0001451311990091028,
"loss": 0.5092,
"step": 4330
},
{
"epoch": 1.0435724602792489,
"grad_norm": 1.2890625,
"learning_rate": 0.00014505510119081237,
"loss": 0.5019,
"step": 4335
},
{
"epoch": 1.044776119402985,
"grad_norm": 1.1796875,
"learning_rate": 0.0001449789527894454,
"loss": 0.5046,
"step": 4340
},
{
"epoch": 1.0459797785267213,
"grad_norm": 1.2578125,
"learning_rate": 0.00014490275392666738,
"loss": 0.5062,
"step": 4345
},
{
"epoch": 1.0471834376504574,
"grad_norm": 1.203125,
"learning_rate": 0.0001448265047242246,
"loss": 0.5312,
"step": 4350
},
{
"epoch": 1.0483870967741935,
"grad_norm": 1.4375,
"learning_rate": 0.0001447502053039437,
"loss": 0.4988,
"step": 4355
},
{
"epoch": 1.0495907558979296,
"grad_norm": 1.2734375,
"learning_rate": 0.00014467385578773167,
"loss": 0.5001,
"step": 4360
},
{
"epoch": 1.050794415021666,
"grad_norm": 1.328125,
"learning_rate": 0.00014459745629757538,
"loss": 0.5061,
"step": 4365
},
{
"epoch": 1.051998074145402,
"grad_norm": 1.171875,
"learning_rate": 0.0001445210069555417,
"loss": 0.5037,
"step": 4370
},
{
"epoch": 1.0532017332691381,
"grad_norm": 1.1328125,
"learning_rate": 0.00014444450788377703,
"loss": 0.5185,
"step": 4375
},
{
"epoch": 1.0544053923928742,
"grad_norm": 1.265625,
"learning_rate": 0.00014436795920450734,
"loss": 0.4907,
"step": 4380
},
{
"epoch": 1.0556090515166106,
"grad_norm": 1.390625,
"learning_rate": 0.0001442913610400377,
"loss": 0.5318,
"step": 4385
},
{
"epoch": 1.0568127106403467,
"grad_norm": 1.296875,
"learning_rate": 0.0001442147135127524,
"loss": 0.5462,
"step": 4390
},
{
"epoch": 1.0580163697640828,
"grad_norm": 1.328125,
"learning_rate": 0.00014413801674511453,
"loss": 0.5337,
"step": 4395
},
{
"epoch": 1.059220028887819,
"grad_norm": 1.2578125,
"learning_rate": 0.0001440612708596659,
"loss": 0.5172,
"step": 4400
},
{
"epoch": 1.0604236880115552,
"grad_norm": 1.2578125,
"learning_rate": 0.0001439844759790267,
"loss": 0.5241,
"step": 4405
},
{
"epoch": 1.0616273471352913,
"grad_norm": 1.2734375,
"learning_rate": 0.00014390763222589547,
"loss": 0.5169,
"step": 4410
},
{
"epoch": 1.0628310062590274,
"grad_norm": 1.2421875,
"learning_rate": 0.00014383073972304888,
"loss": 0.521,
"step": 4415
},
{
"epoch": 1.0640346653827637,
"grad_norm": 1.28125,
"learning_rate": 0.0001437537985933414,
"loss": 0.524,
"step": 4420
},
{
"epoch": 1.0652383245064998,
"grad_norm": 1.3203125,
"learning_rate": 0.00014367680895970524,
"loss": 0.538,
"step": 4425
},
{
"epoch": 1.066441983630236,
"grad_norm": 1.21875,
"learning_rate": 0.0001435997709451501,
"loss": 0.5229,
"step": 4430
},
{
"epoch": 1.067645642753972,
"grad_norm": 1.2109375,
"learning_rate": 0.00014352268467276297,
"loss": 0.5578,
"step": 4435
},
{
"epoch": 1.0688493018777083,
"grad_norm": 1.3125,
"learning_rate": 0.00014344555026570794,
"loss": 0.5176,
"step": 4440
},
{
"epoch": 1.0700529610014444,
"grad_norm": 1.2265625,
"learning_rate": 0.00014336836784722601,
"loss": 0.5166,
"step": 4445
},
{
"epoch": 1.0712566201251805,
"grad_norm": 1.1640625,
"learning_rate": 0.000143291137540635,
"loss": 0.5137,
"step": 4450
},
{
"epoch": 1.0724602792489166,
"grad_norm": 1.21875,
"learning_rate": 0.00014321385946932904,
"loss": 0.5232,
"step": 4455
},
{
"epoch": 1.073663938372653,
"grad_norm": 1.1484375,
"learning_rate": 0.00014313653375677866,
"loss": 0.497,
"step": 4460
},
{
"epoch": 1.074867597496389,
"grad_norm": 1.1875,
"learning_rate": 0.00014305916052653059,
"loss": 0.5122,
"step": 4465
},
{
"epoch": 1.0760712566201251,
"grad_norm": 1.1796875,
"learning_rate": 0.0001429817399022074,
"loss": 0.5198,
"step": 4470
},
{
"epoch": 1.0772749157438612,
"grad_norm": 1.265625,
"learning_rate": 0.0001429042720075074,
"loss": 0.509,
"step": 4475
},
{
"epoch": 1.0784785748675976,
"grad_norm": 1.25,
"learning_rate": 0.00014282675696620443,
"loss": 0.4838,
"step": 4480
},
{
"epoch": 1.0796822339913337,
"grad_norm": 1.3046875,
"learning_rate": 0.00014274919490214763,
"loss": 0.5123,
"step": 4485
},
{
"epoch": 1.0808858931150698,
"grad_norm": 1.1796875,
"learning_rate": 0.0001426715859392613,
"loss": 0.5272,
"step": 4490
},
{
"epoch": 1.0820895522388059,
"grad_norm": 1.1640625,
"learning_rate": 0.00014259393020154475,
"loss": 0.5045,
"step": 4495
},
{
"epoch": 1.0832932113625422,
"grad_norm": 1.1015625,
"learning_rate": 0.0001425162278130718,
"loss": 0.5249,
"step": 4500
},
{
"epoch": 1.0832932113625422,
"eval_loss": 0.4617222547531128,
"eval_runtime": 2.4499,
"eval_samples_per_second": 81.637,
"eval_steps_per_second": 81.637,
"step": 4500
},
{
"epoch": 1.0844968704862783,
"grad_norm": 1.125,
"learning_rate": 0.00014243847889799108,
"loss": 0.5066,
"step": 4505
},
{
"epoch": 1.0857005296100144,
"grad_norm": 1.1796875,
"learning_rate": 0.00014236068358052531,
"loss": 0.5523,
"step": 4510
},
{
"epoch": 1.0869041887337505,
"grad_norm": 1.234375,
"learning_rate": 0.00014228284198497155,
"loss": 0.512,
"step": 4515
},
{
"epoch": 1.0881078478574868,
"grad_norm": 1.15625,
"learning_rate": 0.00014220495423570068,
"loss": 0.5772,
"step": 4520
},
{
"epoch": 1.089311506981223,
"grad_norm": 1.265625,
"learning_rate": 0.00014212702045715735,
"loss": 0.5035,
"step": 4525
},
{
"epoch": 1.090515166104959,
"grad_norm": 1.265625,
"learning_rate": 0.0001420490407738598,
"loss": 0.5199,
"step": 4530
},
{
"epoch": 1.0917188252286953,
"grad_norm": 1.265625,
"learning_rate": 0.0001419710153103995,
"loss": 0.5553,
"step": 4535
},
{
"epoch": 1.0929224843524314,
"grad_norm": 1.28125,
"learning_rate": 0.0001418929441914412,
"loss": 0.4998,
"step": 4540
},
{
"epoch": 1.0941261434761675,
"grad_norm": 1.1875,
"learning_rate": 0.00014181482754172252,
"loss": 0.5263,
"step": 4545
},
{
"epoch": 1.0953298025999036,
"grad_norm": 1.34375,
"learning_rate": 0.00014173666548605385,
"loss": 0.498,
"step": 4550
},
{
"epoch": 1.09653346172364,
"grad_norm": 1.21875,
"learning_rate": 0.0001416584581493181,
"loss": 0.5324,
"step": 4555
},
{
"epoch": 1.097737120847376,
"grad_norm": 1.4296875,
"learning_rate": 0.00014158020565647057,
"loss": 0.5463,
"step": 4560
},
{
"epoch": 1.0989407799711122,
"grad_norm": 1.1875,
"learning_rate": 0.00014150190813253864,
"loss": 0.5182,
"step": 4565
},
{
"epoch": 1.1001444390948483,
"grad_norm": 1.1796875,
"learning_rate": 0.0001414235657026217,
"loss": 0.5274,
"step": 4570
},
{
"epoch": 1.1013480982185846,
"grad_norm": 1.21875,
"learning_rate": 0.0001413451784918909,
"loss": 0.4993,
"step": 4575
},
{
"epoch": 1.1025517573423207,
"grad_norm": 1.3125,
"learning_rate": 0.00014126674662558885,
"loss": 0.4948,
"step": 4580
},
{
"epoch": 1.1037554164660568,
"grad_norm": 1.28125,
"learning_rate": 0.00014118827022902963,
"loss": 0.5347,
"step": 4585
},
{
"epoch": 1.104959075589793,
"grad_norm": 1.328125,
"learning_rate": 0.0001411097494275984,
"loss": 0.523,
"step": 4590
},
{
"epoch": 1.1061627347135292,
"grad_norm": 1.2109375,
"learning_rate": 0.00014103118434675117,
"loss": 0.4897,
"step": 4595
},
{
"epoch": 1.1073663938372653,
"grad_norm": 1.296875,
"learning_rate": 0.00014095257511201494,
"loss": 0.5214,
"step": 4600
},
{
"epoch": 1.1085700529610014,
"grad_norm": 1.2265625,
"learning_rate": 0.000140873921848987,
"loss": 0.4806,
"step": 4605
},
{
"epoch": 1.1097737120847375,
"grad_norm": 1.1796875,
"learning_rate": 0.00014079522468333518,
"loss": 0.5315,
"step": 4610
},
{
"epoch": 1.1109773712084738,
"grad_norm": 1.28125,
"learning_rate": 0.00014071648374079738,
"loss": 0.5276,
"step": 4615
},
{
"epoch": 1.11218103033221,
"grad_norm": 1.28125,
"learning_rate": 0.00014063769914718135,
"loss": 0.4961,
"step": 4620
},
{
"epoch": 1.113384689455946,
"grad_norm": 1.2890625,
"learning_rate": 0.00014055887102836477,
"loss": 0.5384,
"step": 4625
},
{
"epoch": 1.1145883485796821,
"grad_norm": 1.265625,
"learning_rate": 0.0001404799995102947,
"loss": 0.5496,
"step": 4630
},
{
"epoch": 1.1157920077034185,
"grad_norm": 1.375,
"learning_rate": 0.00014040108471898767,
"loss": 0.5306,
"step": 4635
},
{
"epoch": 1.1169956668271546,
"grad_norm": 1.25,
"learning_rate": 0.00014032212678052923,
"loss": 0.511,
"step": 4640
},
{
"epoch": 1.1181993259508907,
"grad_norm": 1.2578125,
"learning_rate": 0.00014024312582107396,
"loss": 0.5264,
"step": 4645
},
{
"epoch": 1.1194029850746268,
"grad_norm": 1.3125,
"learning_rate": 0.00014016408196684512,
"loss": 0.4961,
"step": 4650
},
{
"epoch": 1.120606644198363,
"grad_norm": 1.2734375,
"learning_rate": 0.00014008499534413454,
"loss": 0.5045,
"step": 4655
},
{
"epoch": 1.1218103033220992,
"grad_norm": 1.2109375,
"learning_rate": 0.00014000586607930236,
"loss": 0.506,
"step": 4660
},
{
"epoch": 1.1230139624458353,
"grad_norm": 1.2734375,
"learning_rate": 0.0001399266942987769,
"loss": 0.5392,
"step": 4665
},
{
"epoch": 1.1242176215695716,
"grad_norm": 1.2109375,
"learning_rate": 0.0001398474801290543,
"loss": 0.4822,
"step": 4670
},
{
"epoch": 1.1254212806933077,
"grad_norm": 1.140625,
"learning_rate": 0.00013976822369669847,
"loss": 0.5352,
"step": 4675
},
{
"epoch": 1.1266249398170438,
"grad_norm": 1.296875,
"learning_rate": 0.00013968892512834102,
"loss": 0.5048,
"step": 4680
},
{
"epoch": 1.12782859894078,
"grad_norm": 1.2734375,
"learning_rate": 0.0001396095845506806,
"loss": 0.5026,
"step": 4685
},
{
"epoch": 1.129032258064516,
"grad_norm": 1.21875,
"learning_rate": 0.0001395302020904832,
"loss": 0.5228,
"step": 4690
},
{
"epoch": 1.1302359171882523,
"grad_norm": 1.1796875,
"learning_rate": 0.0001394507778745816,
"loss": 0.5086,
"step": 4695
},
{
"epoch": 1.1314395763119884,
"grad_norm": 1.1171875,
"learning_rate": 0.00013937131202987528,
"loss": 0.5125,
"step": 4700
},
{
"epoch": 1.1326432354357245,
"grad_norm": 1.234375,
"learning_rate": 0.00013929180468333038,
"loss": 0.4953,
"step": 4705
},
{
"epoch": 1.1338468945594609,
"grad_norm": 1.2421875,
"learning_rate": 0.0001392122559619792,
"loss": 0.5134,
"step": 4710
},
{
"epoch": 1.135050553683197,
"grad_norm": 1.28125,
"learning_rate": 0.00013913266599292025,
"loss": 0.5201,
"step": 4715
},
{
"epoch": 1.136254212806933,
"grad_norm": 1.21875,
"learning_rate": 0.0001390530349033179,
"loss": 0.5389,
"step": 4720
},
{
"epoch": 1.1374578719306692,
"grad_norm": 1.234375,
"learning_rate": 0.00013897336282040214,
"loss": 0.5209,
"step": 4725
},
{
"epoch": 1.1386615310544055,
"grad_norm": 1.4296875,
"learning_rate": 0.0001388936498714686,
"loss": 0.5175,
"step": 4730
},
{
"epoch": 1.1398651901781416,
"grad_norm": 1.140625,
"learning_rate": 0.00013881389618387814,
"loss": 0.5347,
"step": 4735
},
{
"epoch": 1.1410688493018777,
"grad_norm": 1.1640625,
"learning_rate": 0.00013873410188505668,
"loss": 0.4957,
"step": 4740
},
{
"epoch": 1.1422725084256138,
"grad_norm": 1.2109375,
"learning_rate": 0.00013865426710249511,
"loss": 0.5297,
"step": 4745
},
{
"epoch": 1.14347616754935,
"grad_norm": 1.2265625,
"learning_rate": 0.00013857439196374884,
"loss": 0.523,
"step": 4750
},
{
"epoch": 1.1446798266730862,
"grad_norm": 1.2265625,
"learning_rate": 0.00013849447659643798,
"loss": 0.5046,
"step": 4755
},
{
"epoch": 1.1458834857968223,
"grad_norm": 1.1796875,
"learning_rate": 0.0001384145211282467,
"loss": 0.5278,
"step": 4760
},
{
"epoch": 1.1470871449205584,
"grad_norm": 1.28125,
"learning_rate": 0.00013833452568692343,
"loss": 0.5012,
"step": 4765
},
{
"epoch": 1.1482908040442947,
"grad_norm": 1.3125,
"learning_rate": 0.00013825449040028034,
"loss": 0.5116,
"step": 4770
},
{
"epoch": 1.1494944631680308,
"grad_norm": 1.1953125,
"learning_rate": 0.0001381744153961933,
"loss": 0.4871,
"step": 4775
},
{
"epoch": 1.150698122291767,
"grad_norm": 1.3515625,
"learning_rate": 0.0001380943008026016,
"loss": 0.5277,
"step": 4780
},
{
"epoch": 1.151901781415503,
"grad_norm": 1.3671875,
"learning_rate": 0.0001380141467475079,
"loss": 0.5294,
"step": 4785
},
{
"epoch": 1.1531054405392394,
"grad_norm": 1.15625,
"learning_rate": 0.00013793395335897778,
"loss": 0.5147,
"step": 4790
},
{
"epoch": 1.1543090996629755,
"grad_norm": 1.1875,
"learning_rate": 0.00013785372076513972,
"loss": 0.5138,
"step": 4795
},
{
"epoch": 1.1555127587867116,
"grad_norm": 1.2421875,
"learning_rate": 0.00013777344909418488,
"loss": 0.4957,
"step": 4800
},
{
"epoch": 1.1567164179104479,
"grad_norm": 1.15625,
"learning_rate": 0.00013769313847436675,
"loss": 0.5136,
"step": 4805
},
{
"epoch": 1.157920077034184,
"grad_norm": 1.21875,
"learning_rate": 0.00013761278903400115,
"loss": 0.5179,
"step": 4810
},
{
"epoch": 1.15912373615792,
"grad_norm": 1.2890625,
"learning_rate": 0.00013753240090146588,
"loss": 0.5299,
"step": 4815
},
{
"epoch": 1.1603273952816562,
"grad_norm": 1.3046875,
"learning_rate": 0.00013745197420520058,
"loss": 0.5254,
"step": 4820
},
{
"epoch": 1.1615310544053923,
"grad_norm": 1.234375,
"learning_rate": 0.00013737150907370646,
"loss": 0.5321,
"step": 4825
},
{
"epoch": 1.1627347135291286,
"grad_norm": 1.1640625,
"learning_rate": 0.00013729100563554623,
"loss": 0.4723,
"step": 4830
},
{
"epoch": 1.1639383726528647,
"grad_norm": 1.28125,
"learning_rate": 0.00013721046401934367,
"loss": 0.5046,
"step": 4835
},
{
"epoch": 1.1651420317766008,
"grad_norm": 1.171875,
"learning_rate": 0.00013712988435378372,
"loss": 0.5246,
"step": 4840
},
{
"epoch": 1.1663456909003371,
"grad_norm": 1.1875,
"learning_rate": 0.00013704926676761197,
"loss": 0.5104,
"step": 4845
},
{
"epoch": 1.1675493500240732,
"grad_norm": 1.1875,
"learning_rate": 0.00013696861138963467,
"loss": 0.5346,
"step": 4850
},
{
"epoch": 1.1687530091478093,
"grad_norm": 1.265625,
"learning_rate": 0.00013688791834871845,
"loss": 0.4683,
"step": 4855
},
{
"epoch": 1.1699566682715454,
"grad_norm": 1.3046875,
"learning_rate": 0.00013680718777379008,
"loss": 0.5208,
"step": 4860
},
{
"epoch": 1.1711603273952818,
"grad_norm": 1.1796875,
"learning_rate": 0.00013672641979383635,
"loss": 0.4973,
"step": 4865
},
{
"epoch": 1.1723639865190179,
"grad_norm": 1.2734375,
"learning_rate": 0.00013664561453790376,
"loss": 0.4948,
"step": 4870
},
{
"epoch": 1.173567645642754,
"grad_norm": 1.2421875,
"learning_rate": 0.00013656477213509844,
"loss": 0.5358,
"step": 4875
},
{
"epoch": 1.17477130476649,
"grad_norm": 1.2734375,
"learning_rate": 0.00013648389271458575,
"loss": 0.5246,
"step": 4880
},
{
"epoch": 1.1759749638902264,
"grad_norm": 1.2578125,
"learning_rate": 0.00013640297640559035,
"loss": 0.5285,
"step": 4885
},
{
"epoch": 1.1771786230139625,
"grad_norm": 1.265625,
"learning_rate": 0.0001363220233373957,
"loss": 0.4932,
"step": 4890
},
{
"epoch": 1.1783822821376986,
"grad_norm": 1.1484375,
"learning_rate": 0.0001362410336393441,
"loss": 0.4945,
"step": 4895
},
{
"epoch": 1.1795859412614347,
"grad_norm": 1.2578125,
"learning_rate": 0.00013616000744083627,
"loss": 0.4816,
"step": 4900
},
{
"epoch": 1.180789600385171,
"grad_norm": 1.1015625,
"learning_rate": 0.00013607894487133133,
"loss": 0.5009,
"step": 4905
},
{
"epoch": 1.181993259508907,
"grad_norm": 1.28125,
"learning_rate": 0.00013599784606034652,
"loss": 0.557,
"step": 4910
},
{
"epoch": 1.1831969186326432,
"grad_norm": 1.296875,
"learning_rate": 0.00013591671113745692,
"loss": 0.4899,
"step": 4915
},
{
"epoch": 1.1844005777563793,
"grad_norm": 1.15625,
"learning_rate": 0.0001358355402322953,
"loss": 0.5142,
"step": 4920
},
{
"epoch": 1.1856042368801156,
"grad_norm": 1.265625,
"learning_rate": 0.000135754333474552,
"loss": 0.4999,
"step": 4925
},
{
"epoch": 1.1868078960038517,
"grad_norm": 1.1875,
"learning_rate": 0.00013567309099397464,
"loss": 0.5319,
"step": 4930
},
{
"epoch": 1.1880115551275878,
"grad_norm": 1.2578125,
"learning_rate": 0.0001355918129203678,
"loss": 0.5222,
"step": 4935
},
{
"epoch": 1.1892152142513241,
"grad_norm": 1.1875,
"learning_rate": 0.00013551049938359305,
"loss": 0.4894,
"step": 4940
},
{
"epoch": 1.1904188733750602,
"grad_norm": 1.1953125,
"learning_rate": 0.00013542915051356855,
"loss": 0.5252,
"step": 4945
},
{
"epoch": 1.1916225324987963,
"grad_norm": 1.171875,
"learning_rate": 0.00013534776644026896,
"loss": 0.5026,
"step": 4950
},
{
"epoch": 1.1928261916225325,
"grad_norm": 1.1796875,
"learning_rate": 0.00013526634729372518,
"loss": 0.4818,
"step": 4955
},
{
"epoch": 1.1940298507462686,
"grad_norm": 1.296875,
"learning_rate": 0.00013518489320402412,
"loss": 0.5361,
"step": 4960
},
{
"epoch": 1.1952335098700049,
"grad_norm": 1.28125,
"learning_rate": 0.0001351034043013085,
"loss": 0.5016,
"step": 4965
},
{
"epoch": 1.196437168993741,
"grad_norm": 1.2421875,
"learning_rate": 0.00013502188071577676,
"loss": 0.481,
"step": 4970
},
{
"epoch": 1.197640828117477,
"grad_norm": 1.2890625,
"learning_rate": 0.00013494032257768264,
"loss": 0.5144,
"step": 4975
},
{
"epoch": 1.1988444872412134,
"grad_norm": 1.21875,
"learning_rate": 0.00013485873001733514,
"loss": 0.4989,
"step": 4980
},
{
"epoch": 1.2000481463649495,
"grad_norm": 1.296875,
"learning_rate": 0.0001347771031650983,
"loss": 0.5184,
"step": 4985
},
{
"epoch": 1.2012518054886856,
"grad_norm": 1.1796875,
"learning_rate": 0.00013469544215139086,
"loss": 0.5012,
"step": 4990
},
{
"epoch": 1.2024554646124217,
"grad_norm": 1.359375,
"learning_rate": 0.0001346137471066862,
"loss": 0.5221,
"step": 4995
},
{
"epoch": 1.2036591237361578,
"grad_norm": 1.3125,
"learning_rate": 0.0001345320181615121,
"loss": 0.5348,
"step": 5000
},
{
"epoch": 1.2036591237361578,
"eval_loss": 0.4517897665500641,
"eval_runtime": 2.4035,
"eval_samples_per_second": 83.211,
"eval_steps_per_second": 83.211,
"step": 5000
},
{
"epoch": 1.2048627828598941,
"grad_norm": 1.21875,
"learning_rate": 0.00013445025544645036,
"loss": 0.4839,
"step": 5005
},
{
"epoch": 1.2060664419836302,
"grad_norm": 1.2109375,
"learning_rate": 0.00013436845909213694,
"loss": 0.4808,
"step": 5010
},
{
"epoch": 1.2072701011073663,
"grad_norm": 1.203125,
"learning_rate": 0.0001342866292292614,
"loss": 0.5058,
"step": 5015
},
{
"epoch": 1.2084737602311026,
"grad_norm": 1.1875,
"learning_rate": 0.0001342047659885669,
"loss": 0.505,
"step": 5020
},
{
"epoch": 1.2096774193548387,
"grad_norm": 1.078125,
"learning_rate": 0.00013412286950084988,
"loss": 0.5294,
"step": 5025
},
{
"epoch": 1.2108810784785748,
"grad_norm": 1.3203125,
"learning_rate": 0.00013404093989695997,
"loss": 0.5163,
"step": 5030
},
{
"epoch": 1.212084737602311,
"grad_norm": 1.1875,
"learning_rate": 0.00013395897730779965,
"loss": 0.5139,
"step": 5035
},
{
"epoch": 1.2132883967260473,
"grad_norm": 1.25,
"learning_rate": 0.00013387698186432417,
"loss": 0.528,
"step": 5040
},
{
"epoch": 1.2144920558497834,
"grad_norm": 1.2265625,
"learning_rate": 0.00013379495369754115,
"loss": 0.5191,
"step": 5045
},
{
"epoch": 1.2156957149735195,
"grad_norm": 1.1484375,
"learning_rate": 0.00013371289293851065,
"loss": 0.5063,
"step": 5050
},
{
"epoch": 1.2168993740972556,
"grad_norm": 1.234375,
"learning_rate": 0.00013363079971834467,
"loss": 0.5163,
"step": 5055
},
{
"epoch": 1.218103033220992,
"grad_norm": 1.0546875,
"learning_rate": 0.00013354867416820717,
"loss": 0.5024,
"step": 5060
},
{
"epoch": 1.219306692344728,
"grad_norm": 1.125,
"learning_rate": 0.00013346651641931372,
"loss": 0.4864,
"step": 5065
},
{
"epoch": 1.220510351468464,
"grad_norm": 1.3046875,
"learning_rate": 0.00013338432660293134,
"loss": 0.5081,
"step": 5070
},
{
"epoch": 1.2217140105922002,
"grad_norm": 1.1796875,
"learning_rate": 0.00013330210485037826,
"loss": 0.5035,
"step": 5075
},
{
"epoch": 1.2229176697159365,
"grad_norm": 1.2578125,
"learning_rate": 0.0001332198512930238,
"loss": 0.5395,
"step": 5080
},
{
"epoch": 1.2241213288396726,
"grad_norm": 1.109375,
"learning_rate": 0.00013313756606228802,
"loss": 0.4689,
"step": 5085
},
{
"epoch": 1.2253249879634087,
"grad_norm": 1.2734375,
"learning_rate": 0.00013305524928964164,
"loss": 0.5177,
"step": 5090
},
{
"epoch": 1.2265286470871448,
"grad_norm": 1.1875,
"learning_rate": 0.00013297290110660578,
"loss": 0.5019,
"step": 5095
},
{
"epoch": 1.2277323062108811,
"grad_norm": 1.1875,
"learning_rate": 0.00013289052164475174,
"loss": 0.5231,
"step": 5100
},
{
"epoch": 1.2289359653346172,
"grad_norm": 1.3046875,
"learning_rate": 0.00013280811103570073,
"loss": 0.4896,
"step": 5105
},
{
"epoch": 1.2301396244583533,
"grad_norm": 1.25,
"learning_rate": 0.00013272566941112382,
"loss": 0.4972,
"step": 5110
},
{
"epoch": 1.2313432835820897,
"grad_norm": 1.1328125,
"learning_rate": 0.00013264319690274153,
"loss": 0.5249,
"step": 5115
},
{
"epoch": 1.2325469427058258,
"grad_norm": 1.171875,
"learning_rate": 0.00013256069364232388,
"loss": 0.5052,
"step": 5120
},
{
"epoch": 1.2337506018295619,
"grad_norm": 1.34375,
"learning_rate": 0.00013247815976168985,
"loss": 0.4939,
"step": 5125
},
{
"epoch": 1.234954260953298,
"grad_norm": 1.25,
"learning_rate": 0.00013239559539270746,
"loss": 0.4873,
"step": 5130
},
{
"epoch": 1.236157920077034,
"grad_norm": 1.046875,
"learning_rate": 0.00013231300066729343,
"loss": 0.4558,
"step": 5135
},
{
"epoch": 1.2373615792007704,
"grad_norm": 1.1796875,
"learning_rate": 0.0001322303757174129,
"loss": 0.5328,
"step": 5140
},
{
"epoch": 1.2385652383245065,
"grad_norm": 1.171875,
"learning_rate": 0.0001321477206750794,
"loss": 0.5181,
"step": 5145
},
{
"epoch": 1.2397688974482426,
"grad_norm": 1.2109375,
"learning_rate": 0.00013206503567235448,
"loss": 0.4987,
"step": 5150
},
{
"epoch": 1.240972556571979,
"grad_norm": 1.296875,
"learning_rate": 0.00013198232084134757,
"loss": 0.4767,
"step": 5155
},
{
"epoch": 1.242176215695715,
"grad_norm": 1.1953125,
"learning_rate": 0.0001318995763142158,
"loss": 0.5226,
"step": 5160
},
{
"epoch": 1.2433798748194511,
"grad_norm": 1.3359375,
"learning_rate": 0.0001318168022231637,
"loss": 0.4951,
"step": 5165
},
{
"epoch": 1.2445835339431872,
"grad_norm": 1.1796875,
"learning_rate": 0.00013173399870044302,
"loss": 0.5172,
"step": 5170
},
{
"epoch": 1.2457871930669235,
"grad_norm": 1.265625,
"learning_rate": 0.00013165116587835258,
"loss": 0.4999,
"step": 5175
},
{
"epoch": 1.2469908521906596,
"grad_norm": 1.2578125,
"learning_rate": 0.000131568303889238,
"loss": 0.5176,
"step": 5180
},
{
"epoch": 1.2481945113143957,
"grad_norm": 1.25,
"learning_rate": 0.00013148541286549153,
"loss": 0.4963,
"step": 5185
},
{
"epoch": 1.2493981704381318,
"grad_norm": 1.1796875,
"learning_rate": 0.00013140249293955173,
"loss": 0.4923,
"step": 5190
},
{
"epoch": 1.2506018295618682,
"grad_norm": 1.21875,
"learning_rate": 0.00013131954424390338,
"loss": 0.5051,
"step": 5195
},
{
"epoch": 1.2518054886856043,
"grad_norm": 1.1484375,
"learning_rate": 0.00013123656691107723,
"loss": 0.5134,
"step": 5200
},
{
"epoch": 1.2530091478093404,
"grad_norm": 1.1953125,
"learning_rate": 0.00013115356107364982,
"loss": 0.503,
"step": 5205
},
{
"epoch": 1.2542128069330767,
"grad_norm": 1.1640625,
"learning_rate": 0.0001310705268642432,
"loss": 0.5029,
"step": 5210
},
{
"epoch": 1.2554164660568128,
"grad_norm": 1.234375,
"learning_rate": 0.00013098746441552473,
"loss": 0.4801,
"step": 5215
},
{
"epoch": 1.2566201251805489,
"grad_norm": 1.234375,
"learning_rate": 0.0001309043738602069,
"loss": 0.5105,
"step": 5220
},
{
"epoch": 1.257823784304285,
"grad_norm": 1.2109375,
"learning_rate": 0.00013082125533104714,
"loss": 0.4996,
"step": 5225
},
{
"epoch": 1.259027443428021,
"grad_norm": 1.2109375,
"learning_rate": 0.00013073810896084757,
"loss": 0.4947,
"step": 5230
},
{
"epoch": 1.2602311025517574,
"grad_norm": 1.1953125,
"learning_rate": 0.0001306549348824547,
"loss": 0.5176,
"step": 5235
},
{
"epoch": 1.2614347616754935,
"grad_norm": 1.3125,
"learning_rate": 0.00013057173322875945,
"loss": 0.513,
"step": 5240
},
{
"epoch": 1.2626384207992296,
"grad_norm": 1.2109375,
"learning_rate": 0.00013048850413269672,
"loss": 0.4998,
"step": 5245
},
{
"epoch": 1.263842079922966,
"grad_norm": 1.203125,
"learning_rate": 0.00013040524772724526,
"loss": 0.5221,
"step": 5250
},
{
"epoch": 1.265045739046702,
"grad_norm": 1.1796875,
"learning_rate": 0.00013032196414542748,
"loss": 0.4986,
"step": 5255
},
{
"epoch": 1.2662493981704381,
"grad_norm": 1.3046875,
"learning_rate": 0.0001302386535203092,
"loss": 0.5107,
"step": 5260
},
{
"epoch": 1.2674530572941742,
"grad_norm": 1.2265625,
"learning_rate": 0.0001301553159849994,
"loss": 0.5451,
"step": 5265
},
{
"epoch": 1.2686567164179103,
"grad_norm": 1.234375,
"learning_rate": 0.00013007195167265016,
"loss": 0.5035,
"step": 5270
},
{
"epoch": 1.2698603755416467,
"grad_norm": 1.1640625,
"learning_rate": 0.0001299885607164562,
"loss": 0.4897,
"step": 5275
},
{
"epoch": 1.2710640346653828,
"grad_norm": 1.296875,
"learning_rate": 0.00012990514324965496,
"loss": 0.5223,
"step": 5280
},
{
"epoch": 1.2722676937891189,
"grad_norm": 1.2109375,
"learning_rate": 0.00012982169940552613,
"loss": 0.523,
"step": 5285
},
{
"epoch": 1.2734713529128552,
"grad_norm": 1.1875,
"learning_rate": 0.0001297382293173916,
"loss": 0.4896,
"step": 5290
},
{
"epoch": 1.2746750120365913,
"grad_norm": 1.125,
"learning_rate": 0.00012965473311861517,
"loss": 0.5007,
"step": 5295
},
{
"epoch": 1.2758786711603274,
"grad_norm": 1.125,
"learning_rate": 0.00012957121094260234,
"loss": 0.5159,
"step": 5300
},
{
"epoch": 1.2770823302840635,
"grad_norm": 1.1953125,
"learning_rate": 0.00012948766292280017,
"loss": 0.4975,
"step": 5305
},
{
"epoch": 1.2782859894077996,
"grad_norm": 1.2421875,
"learning_rate": 0.00012940408919269697,
"loss": 0.5584,
"step": 5310
},
{
"epoch": 1.279489648531536,
"grad_norm": 1.2265625,
"learning_rate": 0.0001293204898858221,
"loss": 0.4937,
"step": 5315
},
{
"epoch": 1.280693307655272,
"grad_norm": 1.125,
"learning_rate": 0.0001292368651357459,
"loss": 0.5058,
"step": 5320
},
{
"epoch": 1.281896966779008,
"grad_norm": 1.2265625,
"learning_rate": 0.00012915321507607917,
"loss": 0.5049,
"step": 5325
},
{
"epoch": 1.2831006259027444,
"grad_norm": 1.2265625,
"learning_rate": 0.0001290695398404734,
"loss": 0.5174,
"step": 5330
},
{
"epoch": 1.2843042850264805,
"grad_norm": 1.28125,
"learning_rate": 0.00012898583956262003,
"loss": 0.522,
"step": 5335
},
{
"epoch": 1.2855079441502166,
"grad_norm": 1.328125,
"learning_rate": 0.0001289021143762507,
"loss": 0.5216,
"step": 5340
},
{
"epoch": 1.286711603273953,
"grad_norm": 1.2421875,
"learning_rate": 0.00012881836441513687,
"loss": 0.4868,
"step": 5345
},
{
"epoch": 1.287915262397689,
"grad_norm": 1.1640625,
"learning_rate": 0.0001287345898130894,
"loss": 0.4973,
"step": 5350
},
{
"epoch": 1.2891189215214252,
"grad_norm": 1.171875,
"learning_rate": 0.00012865079070395867,
"loss": 0.5306,
"step": 5355
},
{
"epoch": 1.2903225806451613,
"grad_norm": 1.328125,
"learning_rate": 0.00012856696722163418,
"loss": 0.5288,
"step": 5360
},
{
"epoch": 1.2915262397688974,
"grad_norm": 1.1171875,
"learning_rate": 0.00012848311950004436,
"loss": 0.5023,
"step": 5365
},
{
"epoch": 1.2927298988926337,
"grad_norm": 1.03125,
"learning_rate": 0.00012839924767315636,
"loss": 0.4719,
"step": 5370
},
{
"epoch": 1.2939335580163698,
"grad_norm": 1.3125,
"learning_rate": 0.0001283153518749759,
"loss": 0.4913,
"step": 5375
},
{
"epoch": 1.2951372171401059,
"grad_norm": 1.203125,
"learning_rate": 0.0001282314322395469,
"loss": 0.5153,
"step": 5380
},
{
"epoch": 1.2963408762638422,
"grad_norm": 1.1640625,
"learning_rate": 0.0001281474889009515,
"loss": 0.5297,
"step": 5385
},
{
"epoch": 1.2975445353875783,
"grad_norm": 1.1875,
"learning_rate": 0.00012806352199330954,
"loss": 0.516,
"step": 5390
},
{
"epoch": 1.2987481945113144,
"grad_norm": 1.34375,
"learning_rate": 0.0001279795316507787,
"loss": 0.5134,
"step": 5395
},
{
"epoch": 1.2999518536350505,
"grad_norm": 1.140625,
"learning_rate": 0.00012789551800755397,
"loss": 0.4592,
"step": 5400
},
{
"epoch": 1.3011555127587866,
"grad_norm": 1.1875,
"learning_rate": 0.00012781148119786763,
"loss": 0.5122,
"step": 5405
},
{
"epoch": 1.302359171882523,
"grad_norm": 1.203125,
"learning_rate": 0.000127727421355989,
"loss": 0.5261,
"step": 5410
},
{
"epoch": 1.303562831006259,
"grad_norm": 1.109375,
"learning_rate": 0.00012764333861622405,
"loss": 0.4806,
"step": 5415
},
{
"epoch": 1.3047664901299951,
"grad_norm": 1.203125,
"learning_rate": 0.00012755923311291554,
"loss": 0.4957,
"step": 5420
},
{
"epoch": 1.3059701492537314,
"grad_norm": 1.2421875,
"learning_rate": 0.00012747510498044247,
"loss": 0.4763,
"step": 5425
},
{
"epoch": 1.3071738083774675,
"grad_norm": 1.21875,
"learning_rate": 0.00012739095435322,
"loss": 0.4947,
"step": 5430
},
{
"epoch": 1.3083774675012037,
"grad_norm": 1.1640625,
"learning_rate": 0.00012730678136569935,
"loss": 0.5029,
"step": 5435
},
{
"epoch": 1.3095811266249398,
"grad_norm": 1.171875,
"learning_rate": 0.00012722258615236725,
"loss": 0.509,
"step": 5440
},
{
"epoch": 1.3107847857486759,
"grad_norm": 1.2578125,
"learning_rate": 0.00012713836884774618,
"loss": 0.5267,
"step": 5445
},
{
"epoch": 1.3119884448724122,
"grad_norm": 1.2109375,
"learning_rate": 0.00012705412958639373,
"loss": 0.4885,
"step": 5450
},
{
"epoch": 1.3131921039961483,
"grad_norm": 1.1796875,
"learning_rate": 0.00012696986850290268,
"loss": 0.4938,
"step": 5455
},
{
"epoch": 1.3143957631198844,
"grad_norm": 1.1640625,
"learning_rate": 0.00012688558573190062,
"loss": 0.5027,
"step": 5460
},
{
"epoch": 1.3155994222436207,
"grad_norm": 1.2109375,
"learning_rate": 0.00012680128140804987,
"loss": 0.5026,
"step": 5465
},
{
"epoch": 1.3168030813673568,
"grad_norm": 1.21875,
"learning_rate": 0.00012671695566604706,
"loss": 0.4694,
"step": 5470
},
{
"epoch": 1.318006740491093,
"grad_norm": 1.1328125,
"learning_rate": 0.00012663260864062312,
"loss": 0.4949,
"step": 5475
},
{
"epoch": 1.319210399614829,
"grad_norm": 1.1484375,
"learning_rate": 0.000126548240466543,
"loss": 0.493,
"step": 5480
},
{
"epoch": 1.320414058738565,
"grad_norm": 1.265625,
"learning_rate": 0.00012646385127860536,
"loss": 0.4796,
"step": 5485
},
{
"epoch": 1.3216177178623014,
"grad_norm": 1.171875,
"learning_rate": 0.00012637944121164258,
"loss": 0.511,
"step": 5490
},
{
"epoch": 1.3228213769860375,
"grad_norm": 1.125,
"learning_rate": 0.00012629501040052024,
"loss": 0.4867,
"step": 5495
},
{
"epoch": 1.3240250361097736,
"grad_norm": 1.125,
"learning_rate": 0.00012621055898013713,
"loss": 0.5021,
"step": 5500
},
{
"epoch": 1.3240250361097736,
"eval_loss": 0.4372206926345825,
"eval_runtime": 2.3993,
"eval_samples_per_second": 83.357,
"eval_steps_per_second": 83.357,
"step": 5500
},
{
"epoch": 1.32522869523351,
"grad_norm": 1.2578125,
"learning_rate": 0.00012612608708542503,
"loss": 0.5143,
"step": 5505
},
{
"epoch": 1.326432354357246,
"grad_norm": 1.25,
"learning_rate": 0.0001260415948513483,
"loss": 0.522,
"step": 5510
},
{
"epoch": 1.3276360134809821,
"grad_norm": 1.2109375,
"learning_rate": 0.00012595708241290392,
"loss": 0.4713,
"step": 5515
},
{
"epoch": 1.3288396726047185,
"grad_norm": 1.3203125,
"learning_rate": 0.0001258725499051211,
"loss": 0.4949,
"step": 5520
},
{
"epoch": 1.3300433317284546,
"grad_norm": 1.28125,
"learning_rate": 0.00012578799746306108,
"loss": 0.5109,
"step": 5525
},
{
"epoch": 1.3312469908521907,
"grad_norm": 1.171875,
"learning_rate": 0.000125703425221817,
"loss": 0.4836,
"step": 5530
},
{
"epoch": 1.3324506499759268,
"grad_norm": 1.2890625,
"learning_rate": 0.00012561883331651364,
"loss": 0.497,
"step": 5535
},
{
"epoch": 1.3336543090996629,
"grad_norm": 1.25,
"learning_rate": 0.00012553422188230716,
"loss": 0.4835,
"step": 5540
},
{
"epoch": 1.3348579682233992,
"grad_norm": 0.99609375,
"learning_rate": 0.00012544959105438498,
"loss": 0.5083,
"step": 5545
},
{
"epoch": 1.3360616273471353,
"grad_norm": 1.25,
"learning_rate": 0.00012536494096796543,
"loss": 0.5072,
"step": 5550
},
{
"epoch": 1.3372652864708714,
"grad_norm": 1.2734375,
"learning_rate": 0.00012528027175829763,
"loss": 0.4937,
"step": 5555
},
{
"epoch": 1.3384689455946077,
"grad_norm": 1.328125,
"learning_rate": 0.0001251955835606613,
"loss": 0.5118,
"step": 5560
},
{
"epoch": 1.3396726047183438,
"grad_norm": 1.3515625,
"learning_rate": 0.00012511087651036648,
"loss": 0.525,
"step": 5565
},
{
"epoch": 1.34087626384208,
"grad_norm": 1.1875,
"learning_rate": 0.00012502615074275335,
"loss": 0.4801,
"step": 5570
},
{
"epoch": 1.342079922965816,
"grad_norm": 1.15625,
"learning_rate": 0.0001249414063931919,
"loss": 0.5221,
"step": 5575
},
{
"epoch": 1.3432835820895521,
"grad_norm": 1.0859375,
"learning_rate": 0.0001248566435970819,
"loss": 0.4969,
"step": 5580
},
{
"epoch": 1.3444872412132884,
"grad_norm": 1.1875,
"learning_rate": 0.00012477186248985257,
"loss": 0.4779,
"step": 5585
},
{
"epoch": 1.3456909003370245,
"grad_norm": 1.25,
"learning_rate": 0.00012468706320696238,
"loss": 0.4816,
"step": 5590
},
{
"epoch": 1.3468945594607606,
"grad_norm": 1.1640625,
"learning_rate": 0.00012460224588389885,
"loss": 0.5386,
"step": 5595
},
{
"epoch": 1.348098218584497,
"grad_norm": 1.328125,
"learning_rate": 0.00012451741065617835,
"loss": 0.5128,
"step": 5600
},
{
"epoch": 1.349301877708233,
"grad_norm": 1.2265625,
"learning_rate": 0.0001244325576593458,
"loss": 0.4803,
"step": 5605
},
{
"epoch": 1.3505055368319692,
"grad_norm": 1.328125,
"learning_rate": 0.0001243476870289745,
"loss": 0.4959,
"step": 5610
},
{
"epoch": 1.3517091959557053,
"grad_norm": 1.171875,
"learning_rate": 0.000124262798900666,
"loss": 0.4922,
"step": 5615
},
{
"epoch": 1.3529128550794414,
"grad_norm": 1.2578125,
"learning_rate": 0.0001241778934100498,
"loss": 0.4875,
"step": 5620
},
{
"epoch": 1.3541165142031777,
"grad_norm": 1.21875,
"learning_rate": 0.00012409297069278306,
"loss": 0.5178,
"step": 5625
},
{
"epoch": 1.3553201733269138,
"grad_norm": 1.203125,
"learning_rate": 0.00012400803088455053,
"loss": 0.4882,
"step": 5630
},
{
"epoch": 1.35652383245065,
"grad_norm": 1.2265625,
"learning_rate": 0.00012392307412106423,
"loss": 0.4877,
"step": 5635
},
{
"epoch": 1.3577274915743862,
"grad_norm": 1.203125,
"learning_rate": 0.00012383810053806328,
"loss": 0.5071,
"step": 5640
},
{
"epoch": 1.3589311506981223,
"grad_norm": 1.2265625,
"learning_rate": 0.00012375311027131372,
"loss": 0.5296,
"step": 5645
},
{
"epoch": 1.3601348098218584,
"grad_norm": 1.21875,
"learning_rate": 0.00012366810345660823,
"loss": 0.5262,
"step": 5650
},
{
"epoch": 1.3613384689455947,
"grad_norm": 1.2890625,
"learning_rate": 0.00012358308022976584,
"loss": 0.4921,
"step": 5655
},
{
"epoch": 1.3625421280693308,
"grad_norm": 1.171875,
"learning_rate": 0.0001234980407266319,
"loss": 0.4937,
"step": 5660
},
{
"epoch": 1.363745787193067,
"grad_norm": 1.2265625,
"learning_rate": 0.00012341298508307773,
"loss": 0.4961,
"step": 5665
},
{
"epoch": 1.364949446316803,
"grad_norm": 1.25,
"learning_rate": 0.00012332791343500047,
"loss": 0.4887,
"step": 5670
},
{
"epoch": 1.3661531054405391,
"grad_norm": 1.2109375,
"learning_rate": 0.0001232428259183228,
"loss": 0.4992,
"step": 5675
},
{
"epoch": 1.3673567645642755,
"grad_norm": 1.015625,
"learning_rate": 0.00012315772266899275,
"loss": 0.4733,
"step": 5680
},
{
"epoch": 1.3685604236880116,
"grad_norm": 1.140625,
"learning_rate": 0.00012307260382298345,
"loss": 0.5134,
"step": 5685
},
{
"epoch": 1.3697640828117477,
"grad_norm": 1.2578125,
"learning_rate": 0.00012298746951629308,
"loss": 0.4616,
"step": 5690
},
{
"epoch": 1.370967741935484,
"grad_norm": 1.25,
"learning_rate": 0.0001229023198849444,
"loss": 0.5291,
"step": 5695
},
{
"epoch": 1.37217140105922,
"grad_norm": 1.265625,
"learning_rate": 0.00012281715506498464,
"loss": 0.5034,
"step": 5700
},
{
"epoch": 1.3733750601829562,
"grad_norm": 1.1796875,
"learning_rate": 0.00012273197519248547,
"loss": 0.4917,
"step": 5705
},
{
"epoch": 1.3745787193066923,
"grad_norm": 1.1796875,
"learning_rate": 0.00012264678040354237,
"loss": 0.4709,
"step": 5710
},
{
"epoch": 1.3757823784304284,
"grad_norm": 1.28125,
"learning_rate": 0.00012256157083427482,
"loss": 0.5178,
"step": 5715
},
{
"epoch": 1.3769860375541647,
"grad_norm": 1.1640625,
"learning_rate": 0.00012247634662082587,
"loss": 0.4827,
"step": 5720
},
{
"epoch": 1.3781896966779008,
"grad_norm": 1.125,
"learning_rate": 0.00012239110789936199,
"loss": 0.4989,
"step": 5725
},
{
"epoch": 1.379393355801637,
"grad_norm": 1.2890625,
"learning_rate": 0.0001223058548060728,
"loss": 0.4845,
"step": 5730
},
{
"epoch": 1.3805970149253732,
"grad_norm": 1.1953125,
"learning_rate": 0.00012222058747717084,
"loss": 0.5135,
"step": 5735
},
{
"epoch": 1.3818006740491093,
"grad_norm": 1.15625,
"learning_rate": 0.00012213530604889147,
"loss": 0.5021,
"step": 5740
},
{
"epoch": 1.3830043331728454,
"grad_norm": 1.1171875,
"learning_rate": 0.00012205001065749255,
"loss": 0.4686,
"step": 5745
},
{
"epoch": 1.3842079922965815,
"grad_norm": 1.2109375,
"learning_rate": 0.00012196470143925426,
"loss": 0.5039,
"step": 5750
},
{
"epoch": 1.3854116514203176,
"grad_norm": 1.0703125,
"learning_rate": 0.00012187937853047884,
"loss": 0.505,
"step": 5755
},
{
"epoch": 1.386615310544054,
"grad_norm": 1.171875,
"learning_rate": 0.00012179404206749049,
"loss": 0.5195,
"step": 5760
},
{
"epoch": 1.38781896966779,
"grad_norm": 1.1328125,
"learning_rate": 0.00012170869218663492,
"loss": 0.4773,
"step": 5765
},
{
"epoch": 1.3890226287915262,
"grad_norm": 1.2265625,
"learning_rate": 0.00012162332902427938,
"loss": 0.4814,
"step": 5770
},
{
"epoch": 1.3902262879152625,
"grad_norm": 1.1953125,
"learning_rate": 0.00012153795271681234,
"loss": 0.5127,
"step": 5775
},
{
"epoch": 1.3914299470389986,
"grad_norm": 1.2265625,
"learning_rate": 0.00012145256340064325,
"loss": 0.4639,
"step": 5780
},
{
"epoch": 1.3926336061627347,
"grad_norm": 1.21875,
"learning_rate": 0.00012136716121220235,
"loss": 0.5135,
"step": 5785
},
{
"epoch": 1.393837265286471,
"grad_norm": 1.203125,
"learning_rate": 0.00012128174628794044,
"loss": 0.4896,
"step": 5790
},
{
"epoch": 1.395040924410207,
"grad_norm": 1.125,
"learning_rate": 0.00012119631876432865,
"loss": 0.4836,
"step": 5795
},
{
"epoch": 1.3962445835339432,
"grad_norm": 1.1328125,
"learning_rate": 0.00012111087877785829,
"loss": 0.4916,
"step": 5800
},
{
"epoch": 1.3974482426576793,
"grad_norm": 1.1328125,
"learning_rate": 0.00012102542646504054,
"loss": 0.5167,
"step": 5805
},
{
"epoch": 1.3986519017814154,
"grad_norm": 1.2734375,
"learning_rate": 0.00012093996196240631,
"loss": 0.5174,
"step": 5810
},
{
"epoch": 1.3998555609051517,
"grad_norm": 1.1328125,
"learning_rate": 0.00012085448540650597,
"loss": 0.4978,
"step": 5815
},
{
"epoch": 1.4010592200288878,
"grad_norm": 1.203125,
"learning_rate": 0.0001207689969339091,
"loss": 0.4887,
"step": 5820
},
{
"epoch": 1.402262879152624,
"grad_norm": 1.1953125,
"learning_rate": 0.00012068349668120441,
"loss": 0.4983,
"step": 5825
},
{
"epoch": 1.4034665382763603,
"grad_norm": 1.140625,
"learning_rate": 0.00012059798478499935,
"loss": 0.5057,
"step": 5830
},
{
"epoch": 1.4046701974000964,
"grad_norm": 1.21875,
"learning_rate": 0.00012051246138192003,
"loss": 0.5114,
"step": 5835
},
{
"epoch": 1.4058738565238325,
"grad_norm": 1.21875,
"learning_rate": 0.00012042692660861097,
"loss": 0.4961,
"step": 5840
},
{
"epoch": 1.4070775156475686,
"grad_norm": 1.328125,
"learning_rate": 0.00012034138060173472,
"loss": 0.4637,
"step": 5845
},
{
"epoch": 1.4082811747713047,
"grad_norm": 1.078125,
"learning_rate": 0.00012025582349797189,
"loss": 0.464,
"step": 5850
},
{
"epoch": 1.409484833895041,
"grad_norm": 1.1640625,
"learning_rate": 0.00012017025543402084,
"loss": 0.474,
"step": 5855
},
{
"epoch": 1.410688493018777,
"grad_norm": 1.1484375,
"learning_rate": 0.00012008467654659739,
"loss": 0.467,
"step": 5860
},
{
"epoch": 1.4118921521425132,
"grad_norm": 1.1875,
"learning_rate": 0.00011999908697243468,
"loss": 0.4678,
"step": 5865
},
{
"epoch": 1.4130958112662495,
"grad_norm": 1.25,
"learning_rate": 0.00011991348684828284,
"loss": 0.4767,
"step": 5870
},
{
"epoch": 1.4142994703899856,
"grad_norm": 1.1484375,
"learning_rate": 0.00011982787631090896,
"loss": 0.4711,
"step": 5875
},
{
"epoch": 1.4155031295137217,
"grad_norm": 1.234375,
"learning_rate": 0.00011974225549709677,
"loss": 0.4824,
"step": 5880
},
{
"epoch": 1.4167067886374578,
"grad_norm": 1.1796875,
"learning_rate": 0.00011965662454364634,
"loss": 0.4644,
"step": 5885
},
{
"epoch": 1.417910447761194,
"grad_norm": 1.1875,
"learning_rate": 0.00011957098358737399,
"loss": 0.4832,
"step": 5890
},
{
"epoch": 1.4191141068849302,
"grad_norm": 1.171875,
"learning_rate": 0.00011948533276511205,
"loss": 0.4851,
"step": 5895
},
{
"epoch": 1.4203177660086663,
"grad_norm": 1.125,
"learning_rate": 0.00011939967221370848,
"loss": 0.4649,
"step": 5900
},
{
"epoch": 1.4215214251324024,
"grad_norm": 1.1953125,
"learning_rate": 0.000119314002070027,
"loss": 0.4774,
"step": 5905
},
{
"epoch": 1.4227250842561388,
"grad_norm": 1.140625,
"learning_rate": 0.00011922832247094646,
"loss": 0.4969,
"step": 5910
},
{
"epoch": 1.4239287433798749,
"grad_norm": 1.0859375,
"learning_rate": 0.00011914263355336094,
"loss": 0.5128,
"step": 5915
},
{
"epoch": 1.425132402503611,
"grad_norm": 1.1953125,
"learning_rate": 0.00011905693545417933,
"loss": 0.4906,
"step": 5920
},
{
"epoch": 1.4263360616273473,
"grad_norm": 1.1953125,
"learning_rate": 0.00011897122831032525,
"loss": 0.4675,
"step": 5925
},
{
"epoch": 1.4275397207510834,
"grad_norm": 1.1640625,
"learning_rate": 0.0001188855122587367,
"loss": 0.4809,
"step": 5930
},
{
"epoch": 1.4287433798748195,
"grad_norm": 1.1328125,
"learning_rate": 0.000118799787436366,
"loss": 0.4919,
"step": 5935
},
{
"epoch": 1.4299470389985556,
"grad_norm": 1.1484375,
"learning_rate": 0.00011871405398017943,
"loss": 0.4994,
"step": 5940
},
{
"epoch": 1.4311506981222917,
"grad_norm": 1.203125,
"learning_rate": 0.0001186283120271571,
"loss": 0.4926,
"step": 5945
},
{
"epoch": 1.432354357246028,
"grad_norm": 1.203125,
"learning_rate": 0.00011854256171429261,
"loss": 0.4811,
"step": 5950
},
{
"epoch": 1.433558016369764,
"grad_norm": 1.125,
"learning_rate": 0.00011845680317859303,
"loss": 0.514,
"step": 5955
},
{
"epoch": 1.4347616754935002,
"grad_norm": 1.234375,
"learning_rate": 0.00011837103655707849,
"loss": 0.4987,
"step": 5960
},
{
"epoch": 1.4359653346172365,
"grad_norm": 1.1640625,
"learning_rate": 0.00011828526198678208,
"loss": 0.4906,
"step": 5965
},
{
"epoch": 1.4371689937409726,
"grad_norm": 1.171875,
"learning_rate": 0.00011819947960474954,
"loss": 0.4696,
"step": 5970
},
{
"epoch": 1.4383726528647087,
"grad_norm": 1.3046875,
"learning_rate": 0.0001181136895480392,
"loss": 0.4913,
"step": 5975
},
{
"epoch": 1.4395763119884448,
"grad_norm": 1.21875,
"learning_rate": 0.0001180278919537215,
"loss": 0.5125,
"step": 5980
},
{
"epoch": 1.440779971112181,
"grad_norm": 1.234375,
"learning_rate": 0.00011794208695887903,
"loss": 0.4988,
"step": 5985
},
{
"epoch": 1.4419836302359172,
"grad_norm": 1.0859375,
"learning_rate": 0.00011785627470060619,
"loss": 0.4803,
"step": 5990
},
{
"epoch": 1.4431872893596533,
"grad_norm": 1.2734375,
"learning_rate": 0.00011777045531600896,
"loss": 0.5158,
"step": 5995
},
{
"epoch": 1.4443909484833894,
"grad_norm": 1.15625,
"learning_rate": 0.00011768462894220472,
"loss": 0.4966,
"step": 6000
},
{
"epoch": 1.4443909484833894,
"eval_loss": 0.4236730933189392,
"eval_runtime": 2.3901,
"eval_samples_per_second": 83.68,
"eval_steps_per_second": 83.68,
"step": 6000
},
{
"epoch": 1.4455946076071258,
"grad_norm": 1.1796875,
"learning_rate": 0.00011759879571632197,
"loss": 0.4952,
"step": 6005
},
{
"epoch": 1.4467982667308619,
"grad_norm": 1.1640625,
"learning_rate": 0.00011751295577550028,
"loss": 0.477,
"step": 6010
},
{
"epoch": 1.448001925854598,
"grad_norm": 1.234375,
"learning_rate": 0.00011742710925688983,
"loss": 0.4742,
"step": 6015
},
{
"epoch": 1.449205584978334,
"grad_norm": 1.21875,
"learning_rate": 0.00011734125629765133,
"loss": 0.4721,
"step": 6020
},
{
"epoch": 1.4504092441020702,
"grad_norm": 1.1015625,
"learning_rate": 0.00011725539703495584,
"loss": 0.5081,
"step": 6025
},
{
"epoch": 1.4516129032258065,
"grad_norm": 1.1484375,
"learning_rate": 0.00011716953160598443,
"loss": 0.4644,
"step": 6030
},
{
"epoch": 1.4528165623495426,
"grad_norm": 1.0859375,
"learning_rate": 0.00011708366014792801,
"loss": 0.4901,
"step": 6035
},
{
"epoch": 1.4540202214732787,
"grad_norm": 1.171875,
"learning_rate": 0.00011699778279798723,
"loss": 0.4536,
"step": 6040
},
{
"epoch": 1.455223880597015,
"grad_norm": 1.0859375,
"learning_rate": 0.00011691189969337203,
"loss": 0.4701,
"step": 6045
},
{
"epoch": 1.4564275397207511,
"grad_norm": 1.28125,
"learning_rate": 0.00011682601097130162,
"loss": 0.4936,
"step": 6050
},
{
"epoch": 1.4576311988444872,
"grad_norm": 1.125,
"learning_rate": 0.00011674011676900414,
"loss": 0.5204,
"step": 6055
},
{
"epoch": 1.4588348579682233,
"grad_norm": 1.265625,
"learning_rate": 0.0001166542172237165,
"loss": 0.4949,
"step": 6060
},
{
"epoch": 1.4600385170919594,
"grad_norm": 1.203125,
"learning_rate": 0.00011656831247268417,
"loss": 0.4835,
"step": 6065
},
{
"epoch": 1.4612421762156957,
"grad_norm": 1.203125,
"learning_rate": 0.00011648240265316094,
"loss": 0.4727,
"step": 6070
},
{
"epoch": 1.4624458353394318,
"grad_norm": 1.1328125,
"learning_rate": 0.00011639648790240863,
"loss": 0.4894,
"step": 6075
},
{
"epoch": 1.463649494463168,
"grad_norm": 1.1640625,
"learning_rate": 0.00011631056835769706,
"loss": 0.5233,
"step": 6080
},
{
"epoch": 1.4648531535869043,
"grad_norm": 1.1640625,
"learning_rate": 0.00011622464415630352,
"loss": 0.4761,
"step": 6085
},
{
"epoch": 1.4660568127106404,
"grad_norm": 1.0625,
"learning_rate": 0.00011613871543551298,
"loss": 0.4713,
"step": 6090
},
{
"epoch": 1.4672604718343765,
"grad_norm": 1.1328125,
"learning_rate": 0.00011605278233261741,
"loss": 0.4944,
"step": 6095
},
{
"epoch": 1.4684641309581128,
"grad_norm": 1.1484375,
"learning_rate": 0.00011596684498491593,
"loss": 0.4928,
"step": 6100
},
{
"epoch": 1.469667790081849,
"grad_norm": 1.296875,
"learning_rate": 0.00011588090352971445,
"loss": 0.4932,
"step": 6105
},
{
"epoch": 1.470871449205585,
"grad_norm": 1.140625,
"learning_rate": 0.00011579495810432523,
"loss": 0.4658,
"step": 6110
},
{
"epoch": 1.472075108329321,
"grad_norm": 1.140625,
"learning_rate": 0.00011570900884606716,
"loss": 0.5048,
"step": 6115
},
{
"epoch": 1.4732787674530572,
"grad_norm": 1.1953125,
"learning_rate": 0.00011562305589226506,
"loss": 0.5027,
"step": 6120
},
{
"epoch": 1.4744824265767935,
"grad_norm": 1.171875,
"learning_rate": 0.00011553709938024977,
"loss": 0.4814,
"step": 6125
},
{
"epoch": 1.4756860857005296,
"grad_norm": 1.2109375,
"learning_rate": 0.00011545113944735769,
"loss": 0.4922,
"step": 6130
},
{
"epoch": 1.4768897448242657,
"grad_norm": 1.328125,
"learning_rate": 0.0001153651762309308,
"loss": 0.5091,
"step": 6135
},
{
"epoch": 1.478093403948002,
"grad_norm": 1.2734375,
"learning_rate": 0.00011527920986831631,
"loss": 0.5113,
"step": 6140
},
{
"epoch": 1.4792970630717381,
"grad_norm": 1.1328125,
"learning_rate": 0.00011519324049686634,
"loss": 0.5091,
"step": 6145
},
{
"epoch": 1.4805007221954742,
"grad_norm": 1.3515625,
"learning_rate": 0.00011510726825393796,
"loss": 0.5244,
"step": 6150
},
{
"epoch": 1.4817043813192103,
"grad_norm": 1.0859375,
"learning_rate": 0.00011502129327689282,
"loss": 0.4535,
"step": 6155
},
{
"epoch": 1.4829080404429464,
"grad_norm": 1.078125,
"learning_rate": 0.00011493531570309687,
"loss": 0.4736,
"step": 6160
},
{
"epoch": 1.4841116995666828,
"grad_norm": 1.2890625,
"learning_rate": 0.00011484933566992013,
"loss": 0.4997,
"step": 6165
},
{
"epoch": 1.4853153586904189,
"grad_norm": 1.1875,
"learning_rate": 0.00011476335331473677,
"loss": 0.5114,
"step": 6170
},
{
"epoch": 1.486519017814155,
"grad_norm": 1.234375,
"learning_rate": 0.00011467736877492454,
"loss": 0.4885,
"step": 6175
},
{
"epoch": 1.4877226769378913,
"grad_norm": 1.1875,
"learning_rate": 0.00011459138218786465,
"loss": 0.4865,
"step": 6180
},
{
"epoch": 1.4889263360616274,
"grad_norm": 1.1796875,
"learning_rate": 0.00011450539369094162,
"loss": 0.488,
"step": 6185
},
{
"epoch": 1.4901299951853635,
"grad_norm": 1.1953125,
"learning_rate": 0.00011441940342154308,
"loss": 0.4846,
"step": 6190
},
{
"epoch": 1.4913336543090996,
"grad_norm": 1.25,
"learning_rate": 0.00011433341151705937,
"loss": 0.4878,
"step": 6195
},
{
"epoch": 1.4925373134328357,
"grad_norm": 1.2421875,
"learning_rate": 0.00011424741811488358,
"loss": 0.5122,
"step": 6200
},
{
"epoch": 1.493740972556572,
"grad_norm": 1.265625,
"learning_rate": 0.00011416142335241106,
"loss": 0.4755,
"step": 6205
},
{
"epoch": 1.4949446316803081,
"grad_norm": 1.2109375,
"learning_rate": 0.00011407542736703943,
"loss": 0.5136,
"step": 6210
},
{
"epoch": 1.4961482908040442,
"grad_norm": 1.1328125,
"learning_rate": 0.00011398943029616821,
"loss": 0.4667,
"step": 6215
},
{
"epoch": 1.4973519499277805,
"grad_norm": 1.1796875,
"learning_rate": 0.00011390343227719868,
"loss": 0.4883,
"step": 6220
},
{
"epoch": 1.4985556090515166,
"grad_norm": 1.3515625,
"learning_rate": 0.00011381743344753364,
"loss": 0.4689,
"step": 6225
},
{
"epoch": 1.4997592681752527,
"grad_norm": 1.1484375,
"learning_rate": 0.00011373143394457716,
"loss": 0.4806,
"step": 6230
},
{
"epoch": 1.500962927298989,
"grad_norm": 1.125,
"learning_rate": 0.00011364543390573441,
"loss": 0.471,
"step": 6235
},
{
"epoch": 1.502166586422725,
"grad_norm": 1.3046875,
"learning_rate": 0.0001135594334684114,
"loss": 0.4961,
"step": 6240
},
{
"epoch": 1.5033702455464613,
"grad_norm": 1.1953125,
"learning_rate": 0.0001134734327700148,
"loss": 0.4623,
"step": 6245
},
{
"epoch": 1.5045739046701974,
"grad_norm": 1.2109375,
"learning_rate": 0.00011338743194795163,
"loss": 0.4349,
"step": 6250
},
{
"epoch": 1.5057775637939335,
"grad_norm": 1.234375,
"learning_rate": 0.00011330143113962918,
"loss": 0.4838,
"step": 6255
},
{
"epoch": 1.5069812229176698,
"grad_norm": 1.140625,
"learning_rate": 0.00011321543048245474,
"loss": 0.4885,
"step": 6260
},
{
"epoch": 1.5081848820414059,
"grad_norm": 1.25,
"learning_rate": 0.00011312943011383526,
"loss": 0.4958,
"step": 6265
},
{
"epoch": 1.509388541165142,
"grad_norm": 1.1875,
"learning_rate": 0.0001130434301711773,
"loss": 0.5054,
"step": 6270
},
{
"epoch": 1.5105922002888783,
"grad_norm": 1.0859375,
"learning_rate": 0.00011295743079188675,
"loss": 0.4916,
"step": 6275
},
{
"epoch": 1.5117958594126142,
"grad_norm": 1.28125,
"learning_rate": 0.0001128714321133685,
"loss": 0.4826,
"step": 6280
},
{
"epoch": 1.5129995185363505,
"grad_norm": 1.234375,
"learning_rate": 0.00011278543427302645,
"loss": 0.5122,
"step": 6285
},
{
"epoch": 1.5142031776600868,
"grad_norm": 1.1640625,
"learning_rate": 0.0001126994374082631,
"loss": 0.4941,
"step": 6290
},
{
"epoch": 1.5154068367838227,
"grad_norm": 1.1875,
"learning_rate": 0.0001126134416564794,
"loss": 0.4636,
"step": 6295
},
{
"epoch": 1.516610495907559,
"grad_norm": 1.15625,
"learning_rate": 0.0001125274471550745,
"loss": 0.4767,
"step": 6300
},
{
"epoch": 1.5178141550312951,
"grad_norm": 1.2734375,
"learning_rate": 0.00011244145404144554,
"loss": 0.4698,
"step": 6305
},
{
"epoch": 1.5190178141550312,
"grad_norm": 1.1328125,
"learning_rate": 0.0001123554624529875,
"loss": 0.4936,
"step": 6310
},
{
"epoch": 1.5202214732787676,
"grad_norm": 1.0859375,
"learning_rate": 0.00011226947252709293,
"loss": 0.5105,
"step": 6315
},
{
"epoch": 1.5214251324025037,
"grad_norm": 1.3125,
"learning_rate": 0.00011218348440115162,
"loss": 0.5167,
"step": 6320
},
{
"epoch": 1.5226287915262398,
"grad_norm": 1.0859375,
"learning_rate": 0.00011209749821255062,
"loss": 0.4814,
"step": 6325
},
{
"epoch": 1.523832450649976,
"grad_norm": 1.1875,
"learning_rate": 0.00011201151409867374,
"loss": 0.4943,
"step": 6330
},
{
"epoch": 1.525036109773712,
"grad_norm": 1.3203125,
"learning_rate": 0.0001119255321969016,
"loss": 0.4951,
"step": 6335
},
{
"epoch": 1.5262397688974483,
"grad_norm": 1.1640625,
"learning_rate": 0.00011183955264461125,
"loss": 0.4885,
"step": 6340
},
{
"epoch": 1.5274434280211844,
"grad_norm": 1.1640625,
"learning_rate": 0.00011175357557917597,
"loss": 0.4522,
"step": 6345
},
{
"epoch": 1.5286470871449205,
"grad_norm": 1.1171875,
"learning_rate": 0.00011166760113796501,
"loss": 0.4875,
"step": 6350
},
{
"epoch": 1.5298507462686568,
"grad_norm": 1.234375,
"learning_rate": 0.00011158162945834355,
"loss": 0.4492,
"step": 6355
},
{
"epoch": 1.531054405392393,
"grad_norm": 1.1484375,
"learning_rate": 0.00011149566067767227,
"loss": 0.48,
"step": 6360
},
{
"epoch": 1.532258064516129,
"grad_norm": 1.2109375,
"learning_rate": 0.00011140969493330727,
"loss": 0.4518,
"step": 6365
},
{
"epoch": 1.5334617236398653,
"grad_norm": 1.234375,
"learning_rate": 0.00011132373236259974,
"loss": 0.435,
"step": 6370
},
{
"epoch": 1.5346653827636012,
"grad_norm": 1.1484375,
"learning_rate": 0.00011123777310289585,
"loss": 0.5019,
"step": 6375
},
{
"epoch": 1.5358690418873375,
"grad_norm": 1.109375,
"learning_rate": 0.00011115181729153642,
"loss": 0.4437,
"step": 6380
},
{
"epoch": 1.5370727010110736,
"grad_norm": 1.2734375,
"learning_rate": 0.00011106586506585685,
"loss": 0.4861,
"step": 6385
},
{
"epoch": 1.5382763601348097,
"grad_norm": 1.1328125,
"learning_rate": 0.00011097991656318678,
"loss": 0.4799,
"step": 6390
},
{
"epoch": 1.539480019258546,
"grad_norm": 1.1640625,
"learning_rate": 0.00011089397192084982,
"loss": 0.5087,
"step": 6395
},
{
"epoch": 1.5406836783822822,
"grad_norm": 1.1796875,
"learning_rate": 0.00011080803127616352,
"loss": 0.4612,
"step": 6400
},
{
"epoch": 1.5418873375060183,
"grad_norm": 1.15625,
"learning_rate": 0.00011072209476643897,
"loss": 0.4816,
"step": 6405
},
{
"epoch": 1.5430909966297546,
"grad_norm": 1.1640625,
"learning_rate": 0.00011063616252898071,
"loss": 0.5003,
"step": 6410
},
{
"epoch": 1.5442946557534905,
"grad_norm": 1.2578125,
"learning_rate": 0.00011055023470108644,
"loss": 0.4642,
"step": 6415
},
{
"epoch": 1.5454983148772268,
"grad_norm": 1.109375,
"learning_rate": 0.00011046431142004676,
"loss": 0.5087,
"step": 6420
},
{
"epoch": 1.5467019740009629,
"grad_norm": 1.1953125,
"learning_rate": 0.00011037839282314504,
"loss": 0.4676,
"step": 6425
},
{
"epoch": 1.547905633124699,
"grad_norm": 1.25,
"learning_rate": 0.00011029247904765724,
"loss": 0.5149,
"step": 6430
},
{
"epoch": 1.5491092922484353,
"grad_norm": 1.1953125,
"learning_rate": 0.00011020657023085149,
"loss": 0.4821,
"step": 6435
},
{
"epoch": 1.5503129513721714,
"grad_norm": 1.1328125,
"learning_rate": 0.00011012066650998805,
"loss": 0.4744,
"step": 6440
},
{
"epoch": 1.5515166104959075,
"grad_norm": 1.140625,
"learning_rate": 0.00011003476802231909,
"loss": 0.4787,
"step": 6445
},
{
"epoch": 1.5527202696196438,
"grad_norm": 1.21875,
"learning_rate": 0.00010994887490508834,
"loss": 0.4899,
"step": 6450
},
{
"epoch": 1.55392392874338,
"grad_norm": 1.1953125,
"learning_rate": 0.000109862987295531,
"loss": 0.4836,
"step": 6455
},
{
"epoch": 1.555127587867116,
"grad_norm": 1.2109375,
"learning_rate": 0.00010977710533087346,
"loss": 0.4532,
"step": 6460
},
{
"epoch": 1.5563312469908523,
"grad_norm": 1.3046875,
"learning_rate": 0.00010969122914833304,
"loss": 0.4874,
"step": 6465
},
{
"epoch": 1.5575349061145882,
"grad_norm": 1.1484375,
"learning_rate": 0.00010960535888511789,
"loss": 0.4735,
"step": 6470
},
{
"epoch": 1.5587385652383245,
"grad_norm": 1.1015625,
"learning_rate": 0.00010951949467842669,
"loss": 0.4959,
"step": 6475
},
{
"epoch": 1.5599422243620606,
"grad_norm": 1.1953125,
"learning_rate": 0.00010943363666544845,
"loss": 0.4706,
"step": 6480
},
{
"epoch": 1.5611458834857967,
"grad_norm": 1.0625,
"learning_rate": 0.00010934778498336222,
"loss": 0.4864,
"step": 6485
},
{
"epoch": 1.562349542609533,
"grad_norm": 1.1640625,
"learning_rate": 0.00010926193976933696,
"loss": 0.5178,
"step": 6490
},
{
"epoch": 1.5635532017332692,
"grad_norm": 1.15625,
"learning_rate": 0.00010917610116053135,
"loss": 0.4709,
"step": 6495
},
{
"epoch": 1.5647568608570053,
"grad_norm": 1.203125,
"learning_rate": 0.00010909026929409354,
"loss": 0.5032,
"step": 6500
},
{
"epoch": 1.5647568608570053,
"eval_loss": 0.41056159138679504,
"eval_runtime": 2.398,
"eval_samples_per_second": 83.402,
"eval_steps_per_second": 83.402,
"step": 6500
},
{
"epoch": 1.5659605199807416,
"grad_norm": 1.2578125,
"learning_rate": 0.00010900444430716075,
"loss": 0.495,
"step": 6505
},
{
"epoch": 1.5671641791044775,
"grad_norm": 1.203125,
"learning_rate": 0.00010891862633685939,
"loss": 0.4829,
"step": 6510
},
{
"epoch": 1.5683678382282138,
"grad_norm": 1.203125,
"learning_rate": 0.0001088328155203045,
"loss": 0.4818,
"step": 6515
},
{
"epoch": 1.56957149735195,
"grad_norm": 1.0859375,
"learning_rate": 0.0001087470119945998,
"loss": 0.476,
"step": 6520
},
{
"epoch": 1.570775156475686,
"grad_norm": 1.109375,
"learning_rate": 0.00010866121589683738,
"loss": 0.4425,
"step": 6525
},
{
"epoch": 1.5719788155994223,
"grad_norm": 1.1171875,
"learning_rate": 0.00010857542736409733,
"loss": 0.5139,
"step": 6530
},
{
"epoch": 1.5731824747231584,
"grad_norm": 1.15625,
"learning_rate": 0.00010848964653344778,
"loss": 0.4963,
"step": 6535
},
{
"epoch": 1.5743861338468945,
"grad_norm": 1.1171875,
"learning_rate": 0.00010840387354194445,
"loss": 0.4689,
"step": 6540
},
{
"epoch": 1.5755897929706308,
"grad_norm": 1.203125,
"learning_rate": 0.00010831810852663065,
"loss": 0.4876,
"step": 6545
},
{
"epoch": 1.5767934520943667,
"grad_norm": 1.1640625,
"learning_rate": 0.0001082323516245369,
"loss": 0.4751,
"step": 6550
},
{
"epoch": 1.577997111218103,
"grad_norm": 1.21875,
"learning_rate": 0.00010814660297268071,
"loss": 0.4719,
"step": 6555
},
{
"epoch": 1.5792007703418391,
"grad_norm": 1.2578125,
"learning_rate": 0.00010806086270806646,
"loss": 0.4712,
"step": 6560
},
{
"epoch": 1.5804044294655752,
"grad_norm": 1.203125,
"learning_rate": 0.0001079751309676851,
"loss": 0.4717,
"step": 6565
},
{
"epoch": 1.5816080885893116,
"grad_norm": 1.1328125,
"learning_rate": 0.00010788940788851398,
"loss": 0.4869,
"step": 6570
},
{
"epoch": 1.5828117477130477,
"grad_norm": 1.1328125,
"learning_rate": 0.00010780369360751663,
"loss": 0.504,
"step": 6575
},
{
"epoch": 1.5840154068367838,
"grad_norm": 1.0546875,
"learning_rate": 0.00010771798826164241,
"loss": 0.4856,
"step": 6580
},
{
"epoch": 1.58521906596052,
"grad_norm": 1.2109375,
"learning_rate": 0.00010763229198782662,
"loss": 0.4648,
"step": 6585
},
{
"epoch": 1.5864227250842562,
"grad_norm": 1.1953125,
"learning_rate": 0.00010754660492298984,
"loss": 0.4842,
"step": 6590
},
{
"epoch": 1.5876263842079923,
"grad_norm": 1.2109375,
"learning_rate": 0.00010746092720403805,
"loss": 0.4613,
"step": 6595
},
{
"epoch": 1.5888300433317286,
"grad_norm": 1.3359375,
"learning_rate": 0.00010737525896786234,
"loss": 0.4635,
"step": 6600
},
{
"epoch": 1.5900337024554645,
"grad_norm": 1.1171875,
"learning_rate": 0.00010728960035133852,
"loss": 0.4909,
"step": 6605
},
{
"epoch": 1.5912373615792008,
"grad_norm": 1.171875,
"learning_rate": 0.00010720395149132714,
"loss": 0.4731,
"step": 6610
},
{
"epoch": 1.592441020702937,
"grad_norm": 1.203125,
"learning_rate": 0.0001071183125246731,
"loss": 0.5077,
"step": 6615
},
{
"epoch": 1.593644679826673,
"grad_norm": 1.2265625,
"learning_rate": 0.00010703268358820552,
"loss": 0.472,
"step": 6620
},
{
"epoch": 1.5948483389504093,
"grad_norm": 1.2578125,
"learning_rate": 0.00010694706481873753,
"loss": 0.4272,
"step": 6625
},
{
"epoch": 1.5960519980741454,
"grad_norm": 1.1015625,
"learning_rate": 0.00010686145635306588,
"loss": 0.4776,
"step": 6630
},
{
"epoch": 1.5972556571978815,
"grad_norm": 1.125,
"learning_rate": 0.00010677585832797107,
"loss": 0.4335,
"step": 6635
},
{
"epoch": 1.5984593163216179,
"grad_norm": 1.1171875,
"learning_rate": 0.0001066902708802167,
"loss": 0.4629,
"step": 6640
},
{
"epoch": 1.5996629754453537,
"grad_norm": 1.1875,
"learning_rate": 0.00010660469414654962,
"loss": 0.492,
"step": 6645
},
{
"epoch": 1.60086663456909,
"grad_norm": 1.21875,
"learning_rate": 0.00010651912826369955,
"loss": 0.477,
"step": 6650
},
{
"epoch": 1.6020702936928262,
"grad_norm": 1.1484375,
"learning_rate": 0.00010643357336837872,
"loss": 0.4892,
"step": 6655
},
{
"epoch": 1.6032739528165623,
"grad_norm": 1.171875,
"learning_rate": 0.00010634802959728206,
"loss": 0.5039,
"step": 6660
},
{
"epoch": 1.6044776119402986,
"grad_norm": 1.0546875,
"learning_rate": 0.00010626249708708647,
"loss": 0.5071,
"step": 6665
},
{
"epoch": 1.6056812710640347,
"grad_norm": 1.21875,
"learning_rate": 0.00010617697597445104,
"loss": 0.5055,
"step": 6670
},
{
"epoch": 1.6068849301877708,
"grad_norm": 1.09375,
"learning_rate": 0.00010609146639601659,
"loss": 0.489,
"step": 6675
},
{
"epoch": 1.608088589311507,
"grad_norm": 1.1796875,
"learning_rate": 0.00010600596848840544,
"loss": 0.5205,
"step": 6680
},
{
"epoch": 1.609292248435243,
"grad_norm": 1.1953125,
"learning_rate": 0.0001059204823882214,
"loss": 0.495,
"step": 6685
},
{
"epoch": 1.6104959075589793,
"grad_norm": 1.15625,
"learning_rate": 0.00010583500823204933,
"loss": 0.4569,
"step": 6690
},
{
"epoch": 1.6116995666827154,
"grad_norm": 1.1484375,
"learning_rate": 0.00010574954615645499,
"loss": 0.4698,
"step": 6695
},
{
"epoch": 1.6129032258064515,
"grad_norm": 1.1796875,
"learning_rate": 0.00010566409629798486,
"loss": 0.4777,
"step": 6700
},
{
"epoch": 1.6141068849301878,
"grad_norm": 1.078125,
"learning_rate": 0.00010557865879316595,
"loss": 0.4874,
"step": 6705
},
{
"epoch": 1.615310544053924,
"grad_norm": 1.140625,
"learning_rate": 0.0001054932337785055,
"loss": 0.4672,
"step": 6710
},
{
"epoch": 1.61651420317766,
"grad_norm": 1.0859375,
"learning_rate": 0.00010540782139049073,
"loss": 0.427,
"step": 6715
},
{
"epoch": 1.6177178623013964,
"grad_norm": 1.203125,
"learning_rate": 0.00010532242176558877,
"loss": 0.4983,
"step": 6720
},
{
"epoch": 1.6189215214251322,
"grad_norm": 1.15625,
"learning_rate": 0.00010523703504024633,
"loss": 0.4716,
"step": 6725
},
{
"epoch": 1.6201251805488686,
"grad_norm": 1.2421875,
"learning_rate": 0.0001051516613508895,
"loss": 0.4437,
"step": 6730
},
{
"epoch": 1.6213288396726049,
"grad_norm": 1.15625,
"learning_rate": 0.00010506630083392358,
"loss": 0.49,
"step": 6735
},
{
"epoch": 1.6225324987963408,
"grad_norm": 1.1328125,
"learning_rate": 0.00010498095362573273,
"loss": 0.4688,
"step": 6740
},
{
"epoch": 1.623736157920077,
"grad_norm": 1.1640625,
"learning_rate": 0.00010489561986267997,
"loss": 0.482,
"step": 6745
},
{
"epoch": 1.6249398170438132,
"grad_norm": 1.1640625,
"learning_rate": 0.00010481029968110677,
"loss": 0.4841,
"step": 6750
},
{
"epoch": 1.6261434761675493,
"grad_norm": 1.109375,
"learning_rate": 0.00010472499321733286,
"loss": 0.5009,
"step": 6755
},
{
"epoch": 1.6273471352912856,
"grad_norm": 1.1015625,
"learning_rate": 0.00010463970060765619,
"loss": 0.4861,
"step": 6760
},
{
"epoch": 1.6285507944150217,
"grad_norm": 1.234375,
"learning_rate": 0.00010455442198835239,
"loss": 0.4887,
"step": 6765
},
{
"epoch": 1.6297544535387578,
"grad_norm": 1.25,
"learning_rate": 0.00010446915749567487,
"loss": 0.4773,
"step": 6770
},
{
"epoch": 1.6309581126624941,
"grad_norm": 1.171875,
"learning_rate": 0.00010438390726585444,
"loss": 0.4515,
"step": 6775
},
{
"epoch": 1.63216177178623,
"grad_norm": 1.328125,
"learning_rate": 0.00010429867143509911,
"loss": 0.4575,
"step": 6780
},
{
"epoch": 1.6333654309099663,
"grad_norm": 1.1484375,
"learning_rate": 0.0001042134501395939,
"loss": 0.4457,
"step": 6785
},
{
"epoch": 1.6345690900337024,
"grad_norm": 1.203125,
"learning_rate": 0.00010412824351550055,
"loss": 0.4922,
"step": 6790
},
{
"epoch": 1.6357727491574385,
"grad_norm": 1.2734375,
"learning_rate": 0.00010404305169895746,
"loss": 0.4796,
"step": 6795
},
{
"epoch": 1.6369764082811749,
"grad_norm": 1.171875,
"learning_rate": 0.00010395787482607926,
"loss": 0.4898,
"step": 6800
},
{
"epoch": 1.638180067404911,
"grad_norm": 1.234375,
"learning_rate": 0.00010387271303295677,
"loss": 0.4823,
"step": 6805
},
{
"epoch": 1.639383726528647,
"grad_norm": 1.21875,
"learning_rate": 0.00010378756645565674,
"loss": 0.4629,
"step": 6810
},
{
"epoch": 1.6405873856523834,
"grad_norm": 1.234375,
"learning_rate": 0.00010370243523022154,
"loss": 0.4652,
"step": 6815
},
{
"epoch": 1.6417910447761193,
"grad_norm": 1.21875,
"learning_rate": 0.00010361731949266905,
"loss": 0.4604,
"step": 6820
},
{
"epoch": 1.6429947038998556,
"grad_norm": 1.1484375,
"learning_rate": 0.00010353221937899241,
"loss": 0.4678,
"step": 6825
},
{
"epoch": 1.6441983630235917,
"grad_norm": 1.1484375,
"learning_rate": 0.00010344713502515978,
"loss": 0.4846,
"step": 6830
},
{
"epoch": 1.6454020221473278,
"grad_norm": 1.203125,
"learning_rate": 0.00010336206656711416,
"loss": 0.4587,
"step": 6835
},
{
"epoch": 1.646605681271064,
"grad_norm": 1.0546875,
"learning_rate": 0.00010327701414077307,
"loss": 0.4833,
"step": 6840
},
{
"epoch": 1.6478093403948002,
"grad_norm": 1.0859375,
"learning_rate": 0.00010319197788202859,
"loss": 0.4579,
"step": 6845
},
{
"epoch": 1.6490129995185363,
"grad_norm": 1.1796875,
"learning_rate": 0.00010310695792674681,
"loss": 0.4999,
"step": 6850
},
{
"epoch": 1.6502166586422726,
"grad_norm": 1.1796875,
"learning_rate": 0.00010302195441076776,
"loss": 0.4468,
"step": 6855
},
{
"epoch": 1.6514203177660085,
"grad_norm": 1.1953125,
"learning_rate": 0.0001029369674699054,
"loss": 0.4587,
"step": 6860
},
{
"epoch": 1.6526239768897448,
"grad_norm": 1.1640625,
"learning_rate": 0.00010285199723994696,
"loss": 0.4643,
"step": 6865
},
{
"epoch": 1.653827636013481,
"grad_norm": 1.140625,
"learning_rate": 0.00010276704385665316,
"loss": 0.5027,
"step": 6870
},
{
"epoch": 1.655031295137217,
"grad_norm": 1.109375,
"learning_rate": 0.00010268210745575766,
"loss": 0.4241,
"step": 6875
},
{
"epoch": 1.6562349542609534,
"grad_norm": 1.2109375,
"learning_rate": 0.00010259718817296711,
"loss": 0.4809,
"step": 6880
},
{
"epoch": 1.6574386133846895,
"grad_norm": 1.1015625,
"learning_rate": 0.00010251228614396078,
"loss": 0.5063,
"step": 6885
},
{
"epoch": 1.6586422725084256,
"grad_norm": 1.203125,
"learning_rate": 0.00010242740150439024,
"loss": 0.4927,
"step": 6890
},
{
"epoch": 1.6598459316321619,
"grad_norm": 1.15625,
"learning_rate": 0.0001023425343898795,
"loss": 0.4651,
"step": 6895
},
{
"epoch": 1.661049590755898,
"grad_norm": 1.1953125,
"learning_rate": 0.00010225768493602437,
"loss": 0.4627,
"step": 6900
},
{
"epoch": 1.662253249879634,
"grad_norm": 1.1640625,
"learning_rate": 0.0001021728532783926,
"loss": 0.4753,
"step": 6905
},
{
"epoch": 1.6634569090033704,
"grad_norm": 1.1875,
"learning_rate": 0.00010208803955252335,
"loss": 0.4603,
"step": 6910
},
{
"epoch": 1.6646605681271063,
"grad_norm": 1.1796875,
"learning_rate": 0.00010200324389392724,
"loss": 0.4871,
"step": 6915
},
{
"epoch": 1.6658642272508426,
"grad_norm": 1.140625,
"learning_rate": 0.00010191846643808607,
"loss": 0.4724,
"step": 6920
},
{
"epoch": 1.6670678863745787,
"grad_norm": 1.1328125,
"learning_rate": 0.00010183370732045236,
"loss": 0.473,
"step": 6925
},
{
"epoch": 1.6682715454983148,
"grad_norm": 1.296875,
"learning_rate": 0.00010174896667644954,
"loss": 0.5103,
"step": 6930
},
{
"epoch": 1.6694752046220511,
"grad_norm": 1.125,
"learning_rate": 0.0001016642446414714,
"loss": 0.4525,
"step": 6935
},
{
"epoch": 1.6706788637457872,
"grad_norm": 1.21875,
"learning_rate": 0.00010157954135088202,
"loss": 0.4582,
"step": 6940
},
{
"epoch": 1.6718825228695233,
"grad_norm": 1.3125,
"learning_rate": 0.0001014948569400156,
"loss": 0.4983,
"step": 6945
},
{
"epoch": 1.6730861819932596,
"grad_norm": 1.171875,
"learning_rate": 0.00010141019154417605,
"loss": 0.4344,
"step": 6950
},
{
"epoch": 1.6742898411169955,
"grad_norm": 1.1796875,
"learning_rate": 0.00010132554529863701,
"loss": 0.4866,
"step": 6955
},
{
"epoch": 1.6754935002407318,
"grad_norm": 1.234375,
"learning_rate": 0.00010124091833864149,
"loss": 0.445,
"step": 6960
},
{
"epoch": 1.676697159364468,
"grad_norm": 1.21875,
"learning_rate": 0.00010115631079940164,
"loss": 0.4949,
"step": 6965
},
{
"epoch": 1.677900818488204,
"grad_norm": 1.1171875,
"learning_rate": 0.00010107172281609865,
"loss": 0.4533,
"step": 6970
},
{
"epoch": 1.6791044776119404,
"grad_norm": 1.234375,
"learning_rate": 0.0001009871545238824,
"loss": 0.4666,
"step": 6975
},
{
"epoch": 1.6803081367356765,
"grad_norm": 1.171875,
"learning_rate": 0.0001009026060578714,
"loss": 0.4385,
"step": 6980
},
{
"epoch": 1.6815117958594126,
"grad_norm": 1.09375,
"learning_rate": 0.00010081807755315239,
"loss": 0.4661,
"step": 6985
},
{
"epoch": 1.682715454983149,
"grad_norm": 1.2890625,
"learning_rate": 0.00010073356914478021,
"loss": 0.4982,
"step": 6990
},
{
"epoch": 1.6839191141068848,
"grad_norm": 1.1953125,
"learning_rate": 0.00010064908096777771,
"loss": 0.4564,
"step": 6995
},
{
"epoch": 1.685122773230621,
"grad_norm": 1.1640625,
"learning_rate": 0.00010056461315713526,
"loss": 0.4728,
"step": 7000
},
{
"epoch": 1.685122773230621,
"eval_loss": 0.4017234146595001,
"eval_runtime": 2.4276,
"eval_samples_per_second": 82.387,
"eval_steps_per_second": 82.387,
"step": 7000
},
{
"epoch": 1.6863264323543572,
"grad_norm": 1.21875,
"learning_rate": 0.00010048016584781085,
"loss": 0.4775,
"step": 7005
},
{
"epoch": 1.6875300914780933,
"grad_norm": 1.1953125,
"learning_rate": 0.00010039573917472955,
"loss": 0.4673,
"step": 7010
},
{
"epoch": 1.6887337506018296,
"grad_norm": 1.1796875,
"learning_rate": 0.0001003113332727836,
"loss": 0.4877,
"step": 7015
},
{
"epoch": 1.6899374097255657,
"grad_norm": 1.109375,
"learning_rate": 0.000100226948276832,
"loss": 0.4254,
"step": 7020
},
{
"epoch": 1.6911410688493018,
"grad_norm": 1.078125,
"learning_rate": 0.00010014258432170028,
"loss": 0.4543,
"step": 7025
},
{
"epoch": 1.6923447279730381,
"grad_norm": 1.1484375,
"learning_rate": 0.00010005824154218047,
"loss": 0.4555,
"step": 7030
},
{
"epoch": 1.6935483870967742,
"grad_norm": 1.234375,
"learning_rate": 9.997392007303066e-05,
"loss": 0.4845,
"step": 7035
},
{
"epoch": 1.6947520462205103,
"grad_norm": 1.0546875,
"learning_rate": 9.9889620048975e-05,
"loss": 0.4641,
"step": 7040
},
{
"epoch": 1.6959557053442467,
"grad_norm": 1.2265625,
"learning_rate": 9.98053416047033e-05,
"loss": 0.4804,
"step": 7045
},
{
"epoch": 1.6971593644679825,
"grad_norm": 1.203125,
"learning_rate": 9.972108487487087e-05,
"loss": 0.4517,
"step": 7050
},
{
"epoch": 1.6983630235917189,
"grad_norm": 1.15625,
"learning_rate": 9.963684999409843e-05,
"loss": 0.4462,
"step": 7055
},
{
"epoch": 1.699566682715455,
"grad_norm": 1.2109375,
"learning_rate": 9.955263709697163e-05,
"loss": 0.4604,
"step": 7060
},
{
"epoch": 1.700770341839191,
"grad_norm": 1.125,
"learning_rate": 9.946844631804118e-05,
"loss": 0.44,
"step": 7065
},
{
"epoch": 1.7019740009629274,
"grad_norm": 1.2109375,
"learning_rate": 9.938427779182235e-05,
"loss": 0.4756,
"step": 7070
},
{
"epoch": 1.7031776600866635,
"grad_norm": 1.21875,
"learning_rate": 9.930013165279483e-05,
"loss": 0.4968,
"step": 7075
},
{
"epoch": 1.7043813192103996,
"grad_norm": 1.1171875,
"learning_rate": 9.92160080354026e-05,
"loss": 0.4313,
"step": 7080
},
{
"epoch": 1.705584978334136,
"grad_norm": 1.15625,
"learning_rate": 9.913190707405364e-05,
"loss": 0.453,
"step": 7085
},
{
"epoch": 1.7067886374578718,
"grad_norm": 1.1875,
"learning_rate": 9.90478289031197e-05,
"loss": 0.4536,
"step": 7090
},
{
"epoch": 1.7079922965816081,
"grad_norm": 1.09375,
"learning_rate": 9.89637736569362e-05,
"loss": 0.4394,
"step": 7095
},
{
"epoch": 1.7091959557053442,
"grad_norm": 1.0703125,
"learning_rate": 9.887974146980183e-05,
"loss": 0.4743,
"step": 7100
},
{
"epoch": 1.7103996148290803,
"grad_norm": 1.1953125,
"learning_rate": 9.879573247597849e-05,
"loss": 0.4516,
"step": 7105
},
{
"epoch": 1.7116032739528166,
"grad_norm": 1.1796875,
"learning_rate": 9.8711746809691e-05,
"loss": 0.4844,
"step": 7110
},
{
"epoch": 1.7128069330765527,
"grad_norm": 1.140625,
"learning_rate": 9.862778460512697e-05,
"loss": 0.4653,
"step": 7115
},
{
"epoch": 1.7140105922002888,
"grad_norm": 1.109375,
"learning_rate": 9.854384599643646e-05,
"loss": 0.4733,
"step": 7120
},
{
"epoch": 1.7152142513240252,
"grad_norm": 1.15625,
"learning_rate": 9.845993111773181e-05,
"loss": 0.4359,
"step": 7125
},
{
"epoch": 1.716417910447761,
"grad_norm": 1.3359375,
"learning_rate": 9.837604010308757e-05,
"loss": 0.5006,
"step": 7130
},
{
"epoch": 1.7176215695714974,
"grad_norm": 1.2109375,
"learning_rate": 9.829217308653996e-05,
"loss": 0.4801,
"step": 7135
},
{
"epoch": 1.7188252286952335,
"grad_norm": 1.1328125,
"learning_rate": 9.820833020208709e-05,
"loss": 0.4744,
"step": 7140
},
{
"epoch": 1.7200288878189696,
"grad_norm": 1.203125,
"learning_rate": 9.81245115836883e-05,
"loss": 0.4371,
"step": 7145
},
{
"epoch": 1.7212325469427059,
"grad_norm": 1.046875,
"learning_rate": 9.804071736526432e-05,
"loss": 0.4655,
"step": 7150
},
{
"epoch": 1.722436206066442,
"grad_norm": 1.078125,
"learning_rate": 9.795694768069681e-05,
"loss": 0.4688,
"step": 7155
},
{
"epoch": 1.723639865190178,
"grad_norm": 1.28125,
"learning_rate": 9.787320266382821e-05,
"loss": 0.4847,
"step": 7160
},
{
"epoch": 1.7248435243139144,
"grad_norm": 1.125,
"learning_rate": 9.778948244846171e-05,
"loss": 0.436,
"step": 7165
},
{
"epoch": 1.7260471834376505,
"grad_norm": 1.1484375,
"learning_rate": 9.770578716836058e-05,
"loss": 0.4586,
"step": 7170
},
{
"epoch": 1.7272508425613866,
"grad_norm": 1.2109375,
"learning_rate": 9.762211695724857e-05,
"loss": 0.508,
"step": 7175
},
{
"epoch": 1.728454501685123,
"grad_norm": 1.265625,
"learning_rate": 9.753847194880916e-05,
"loss": 0.4431,
"step": 7180
},
{
"epoch": 1.7296581608088588,
"grad_norm": 1.21875,
"learning_rate": 9.745485227668559e-05,
"loss": 0.4897,
"step": 7185
},
{
"epoch": 1.7308618199325951,
"grad_norm": 1.203125,
"learning_rate": 9.73712580744808e-05,
"loss": 0.5014,
"step": 7190
},
{
"epoch": 1.7320654790563312,
"grad_norm": 1.1796875,
"learning_rate": 9.728768947575673e-05,
"loss": 0.4469,
"step": 7195
},
{
"epoch": 1.7332691381800673,
"grad_norm": 1.1328125,
"learning_rate": 9.720414661403469e-05,
"loss": 0.4667,
"step": 7200
},
{
"epoch": 1.7344727973038037,
"grad_norm": 1.125,
"learning_rate": 9.712062962279472e-05,
"loss": 0.4498,
"step": 7205
},
{
"epoch": 1.7356764564275398,
"grad_norm": 1.1875,
"learning_rate": 9.703713863547554e-05,
"loss": 0.4739,
"step": 7210
},
{
"epoch": 1.7368801155512759,
"grad_norm": 1.265625,
"learning_rate": 9.69536737854744e-05,
"loss": 0.4298,
"step": 7215
},
{
"epoch": 1.7380837746750122,
"grad_norm": 1.21875,
"learning_rate": 9.687023520614666e-05,
"loss": 0.4709,
"step": 7220
},
{
"epoch": 1.739287433798748,
"grad_norm": 1.1875,
"learning_rate": 9.678682303080585e-05,
"loss": 0.4882,
"step": 7225
},
{
"epoch": 1.7404910929224844,
"grad_norm": 1.15625,
"learning_rate": 9.670343739272324e-05,
"loss": 0.4488,
"step": 7230
},
{
"epoch": 1.7416947520462205,
"grad_norm": 1.21875,
"learning_rate": 9.662007842512765e-05,
"loss": 0.4741,
"step": 7235
},
{
"epoch": 1.7428984111699566,
"grad_norm": 1.15625,
"learning_rate": 9.653674626120536e-05,
"loss": 0.4721,
"step": 7240
},
{
"epoch": 1.744102070293693,
"grad_norm": 1.078125,
"learning_rate": 9.645344103409982e-05,
"loss": 0.4671,
"step": 7245
},
{
"epoch": 1.745305729417429,
"grad_norm": 1.640625,
"learning_rate": 9.637016287691144e-05,
"loss": 0.4693,
"step": 7250
},
{
"epoch": 1.746509388541165,
"grad_norm": 1.1015625,
"learning_rate": 9.628691192269735e-05,
"loss": 0.4494,
"step": 7255
},
{
"epoch": 1.7477130476649014,
"grad_norm": 1.140625,
"learning_rate": 9.62036883044712e-05,
"loss": 0.464,
"step": 7260
},
{
"epoch": 1.7489167067886373,
"grad_norm": 1.21875,
"learning_rate": 9.612049215520306e-05,
"loss": 0.4814,
"step": 7265
},
{
"epoch": 1.7501203659123736,
"grad_norm": 1.1328125,
"learning_rate": 9.603732360781898e-05,
"loss": 0.4608,
"step": 7270
},
{
"epoch": 1.7513240250361097,
"grad_norm": 1.09375,
"learning_rate": 9.595418279520106e-05,
"loss": 0.445,
"step": 7275
},
{
"epoch": 1.7525276841598458,
"grad_norm": 1.140625,
"learning_rate": 9.587106985018696e-05,
"loss": 0.4452,
"step": 7280
},
{
"epoch": 1.7537313432835822,
"grad_norm": 1.09375,
"learning_rate": 9.578798490556983e-05,
"loss": 0.4525,
"step": 7285
},
{
"epoch": 1.7549350024073183,
"grad_norm": 1.15625,
"learning_rate": 9.570492809409817e-05,
"loss": 0.4515,
"step": 7290
},
{
"epoch": 1.7561386615310544,
"grad_norm": 1.0859375,
"learning_rate": 9.562189954847543e-05,
"loss": 0.4457,
"step": 7295
},
{
"epoch": 1.7573423206547907,
"grad_norm": 1.1484375,
"learning_rate": 9.553889940135997e-05,
"loss": 0.4403,
"step": 7300
},
{
"epoch": 1.7585459797785266,
"grad_norm": 1.078125,
"learning_rate": 9.545592778536476e-05,
"loss": 0.458,
"step": 7305
},
{
"epoch": 1.7597496389022629,
"grad_norm": 1.1875,
"learning_rate": 9.537298483305711e-05,
"loss": 0.4915,
"step": 7310
},
{
"epoch": 1.7609532980259992,
"grad_norm": 1.0703125,
"learning_rate": 9.529007067695869e-05,
"loss": 0.4384,
"step": 7315
},
{
"epoch": 1.762156957149735,
"grad_norm": 1.1484375,
"learning_rate": 9.520718544954493e-05,
"loss": 0.4502,
"step": 7320
},
{
"epoch": 1.7633606162734714,
"grad_norm": 1.125,
"learning_rate": 9.51243292832453e-05,
"loss": 0.4817,
"step": 7325
},
{
"epoch": 1.7645642753972075,
"grad_norm": 1.1015625,
"learning_rate": 9.504150231044268e-05,
"loss": 0.4458,
"step": 7330
},
{
"epoch": 1.7657679345209436,
"grad_norm": 1.140625,
"learning_rate": 9.495870466347332e-05,
"loss": 0.4879,
"step": 7335
},
{
"epoch": 1.76697159364468,
"grad_norm": 1.1640625,
"learning_rate": 9.487593647462665e-05,
"loss": 0.4667,
"step": 7340
},
{
"epoch": 1.768175252768416,
"grad_norm": 1.2109375,
"learning_rate": 9.479319787614498e-05,
"loss": 0.4865,
"step": 7345
},
{
"epoch": 1.7693789118921521,
"grad_norm": 1.1875,
"learning_rate": 9.471048900022342e-05,
"loss": 0.4443,
"step": 7350
},
{
"epoch": 1.7705825710158885,
"grad_norm": 1.0703125,
"learning_rate": 9.462780997900958e-05,
"loss": 0.4703,
"step": 7355
},
{
"epoch": 1.7717862301396243,
"grad_norm": 1.125,
"learning_rate": 9.454516094460328e-05,
"loss": 0.4557,
"step": 7360
},
{
"epoch": 1.7729898892633607,
"grad_norm": 1.234375,
"learning_rate": 9.446254202905652e-05,
"loss": 0.4903,
"step": 7365
},
{
"epoch": 1.7741935483870968,
"grad_norm": 1.078125,
"learning_rate": 9.437995336437311e-05,
"loss": 0.4427,
"step": 7370
},
{
"epoch": 1.7753972075108329,
"grad_norm": 1.203125,
"learning_rate": 9.429739508250864e-05,
"loss": 0.4733,
"step": 7375
},
{
"epoch": 1.7766008666345692,
"grad_norm": 1.21875,
"learning_rate": 9.421486731537e-05,
"loss": 0.4731,
"step": 7380
},
{
"epoch": 1.7778045257583053,
"grad_norm": 1.15625,
"learning_rate": 9.413237019481546e-05,
"loss": 0.4572,
"step": 7385
},
{
"epoch": 1.7790081848820414,
"grad_norm": 1.1171875,
"learning_rate": 9.404990385265427e-05,
"loss": 0.4595,
"step": 7390
},
{
"epoch": 1.7802118440057777,
"grad_norm": 1.1015625,
"learning_rate": 9.396746842064645e-05,
"loss": 0.4541,
"step": 7395
},
{
"epoch": 1.7814155031295136,
"grad_norm": 1.0625,
"learning_rate": 9.388506403050277e-05,
"loss": 0.4592,
"step": 7400
},
{
"epoch": 1.78261916225325,
"grad_norm": 1.28125,
"learning_rate": 9.380269081388421e-05,
"loss": 0.4734,
"step": 7405
},
{
"epoch": 1.783822821376986,
"grad_norm": 1.125,
"learning_rate": 9.372034890240215e-05,
"loss": 0.4551,
"step": 7410
},
{
"epoch": 1.785026480500722,
"grad_norm": 1.0625,
"learning_rate": 9.363803842761786e-05,
"loss": 0.4583,
"step": 7415
},
{
"epoch": 1.7862301396244584,
"grad_norm": 1.140625,
"learning_rate": 9.35557595210423e-05,
"loss": 0.473,
"step": 7420
},
{
"epoch": 1.7874337987481945,
"grad_norm": 1.0859375,
"learning_rate": 9.347351231413613e-05,
"loss": 0.441,
"step": 7425
},
{
"epoch": 1.7886374578719306,
"grad_norm": 1.0859375,
"learning_rate": 9.339129693830927e-05,
"loss": 0.4616,
"step": 7430
},
{
"epoch": 1.789841116995667,
"grad_norm": 1.1796875,
"learning_rate": 9.330911352492083e-05,
"loss": 0.4818,
"step": 7435
},
{
"epoch": 1.7910447761194028,
"grad_norm": 1.15625,
"learning_rate": 9.322696220527885e-05,
"loss": 0.4542,
"step": 7440
},
{
"epoch": 1.7922484352431391,
"grad_norm": 1.140625,
"learning_rate": 9.314484311064006e-05,
"loss": 0.4578,
"step": 7445
},
{
"epoch": 1.7934520943668752,
"grad_norm": 1.25,
"learning_rate": 9.306275637220975e-05,
"loss": 0.4762,
"step": 7450
},
{
"epoch": 1.7946557534906113,
"grad_norm": 1.109375,
"learning_rate": 9.298070212114141e-05,
"loss": 0.4547,
"step": 7455
},
{
"epoch": 1.7958594126143477,
"grad_norm": 1.203125,
"learning_rate": 9.28986804885368e-05,
"loss": 0.4402,
"step": 7460
},
{
"epoch": 1.7970630717380838,
"grad_norm": 1.0625,
"learning_rate": 9.281669160544539e-05,
"loss": 0.4647,
"step": 7465
},
{
"epoch": 1.7982667308618199,
"grad_norm": 1.1875,
"learning_rate": 9.273473560286441e-05,
"loss": 0.4407,
"step": 7470
},
{
"epoch": 1.7994703899855562,
"grad_norm": 1.2265625,
"learning_rate": 9.26528126117386e-05,
"loss": 0.4796,
"step": 7475
},
{
"epoch": 1.8006740491092923,
"grad_norm": 1.0546875,
"learning_rate": 9.257092276295981e-05,
"loss": 0.446,
"step": 7480
},
{
"epoch": 1.8018777082330284,
"grad_norm": 1.140625,
"learning_rate": 9.248906618736706e-05,
"loss": 0.4775,
"step": 7485
},
{
"epoch": 1.8030813673567647,
"grad_norm": 1.1484375,
"learning_rate": 9.240724301574621e-05,
"loss": 0.4508,
"step": 7490
},
{
"epoch": 1.8042850264805006,
"grad_norm": 1.21875,
"learning_rate": 9.232545337882966e-05,
"loss": 0.4432,
"step": 7495
},
{
"epoch": 1.805488685604237,
"grad_norm": 1.0078125,
"learning_rate": 9.224369740729636e-05,
"loss": 0.437,
"step": 7500
},
{
"epoch": 1.805488685604237,
"eval_loss": 0.3923625946044922,
"eval_runtime": 2.4326,
"eval_samples_per_second": 82.217,
"eval_steps_per_second": 82.217,
"step": 7500
},
{
"epoch": 1.806692344727973,
"grad_norm": 1.1796875,
"learning_rate": 9.216197523177126e-05,
"loss": 0.4852,
"step": 7505
},
{
"epoch": 1.8078960038517091,
"grad_norm": 1.171875,
"learning_rate": 9.208028698282558e-05,
"loss": 0.4466,
"step": 7510
},
{
"epoch": 1.8090996629754454,
"grad_norm": 1.171875,
"learning_rate": 9.199863279097612e-05,
"loss": 0.4602,
"step": 7515
},
{
"epoch": 1.8103033220991815,
"grad_norm": 1.1328125,
"learning_rate": 9.19170127866854e-05,
"loss": 0.4465,
"step": 7520
},
{
"epoch": 1.8115069812229176,
"grad_norm": 1.1640625,
"learning_rate": 9.183542710036125e-05,
"loss": 0.4367,
"step": 7525
},
{
"epoch": 1.812710640346654,
"grad_norm": 1.109375,
"learning_rate": 9.175387586235664e-05,
"loss": 0.4722,
"step": 7530
},
{
"epoch": 1.8139142994703898,
"grad_norm": 1.203125,
"learning_rate": 9.167235920296956e-05,
"loss": 0.4959,
"step": 7535
},
{
"epoch": 1.8151179585941262,
"grad_norm": 1.234375,
"learning_rate": 9.159087725244279e-05,
"loss": 0.4682,
"step": 7540
},
{
"epoch": 1.8163216177178623,
"grad_norm": 1.1171875,
"learning_rate": 9.150943014096355e-05,
"loss": 0.4735,
"step": 7545
},
{
"epoch": 1.8175252768415984,
"grad_norm": 1.0625,
"learning_rate": 9.142801799866344e-05,
"loss": 0.4483,
"step": 7550
},
{
"epoch": 1.8187289359653347,
"grad_norm": 1.265625,
"learning_rate": 9.134664095561819e-05,
"loss": 0.4961,
"step": 7555
},
{
"epoch": 1.8199325950890708,
"grad_norm": 1.21875,
"learning_rate": 9.126529914184744e-05,
"loss": 0.4515,
"step": 7560
},
{
"epoch": 1.821136254212807,
"grad_norm": 1.171875,
"learning_rate": 9.118399268731464e-05,
"loss": 0.461,
"step": 7565
},
{
"epoch": 1.8223399133365432,
"grad_norm": 1.1015625,
"learning_rate": 9.11027217219266e-05,
"loss": 0.446,
"step": 7570
},
{
"epoch": 1.823543572460279,
"grad_norm": 1.2421875,
"learning_rate": 9.10214863755335e-05,
"loss": 0.4625,
"step": 7575
},
{
"epoch": 1.8247472315840154,
"grad_norm": 1.1953125,
"learning_rate": 9.094028677792856e-05,
"loss": 0.4575,
"step": 7580
},
{
"epoch": 1.8259508907077515,
"grad_norm": 1.1015625,
"learning_rate": 9.085912305884799e-05,
"loss": 0.4514,
"step": 7585
},
{
"epoch": 1.8271545498314876,
"grad_norm": 1.25,
"learning_rate": 9.077799534797055e-05,
"loss": 0.4618,
"step": 7590
},
{
"epoch": 1.828358208955224,
"grad_norm": 1.0625,
"learning_rate": 9.069690377491755e-05,
"loss": 0.4788,
"step": 7595
},
{
"epoch": 1.82956186807896,
"grad_norm": 1.265625,
"learning_rate": 9.061584846925254e-05,
"loss": 0.4367,
"step": 7600
},
{
"epoch": 1.8307655272026961,
"grad_norm": 1.2265625,
"learning_rate": 9.053482956048107e-05,
"loss": 0.4539,
"step": 7605
},
{
"epoch": 1.8319691863264325,
"grad_norm": 1.0859375,
"learning_rate": 9.045384717805068e-05,
"loss": 0.4725,
"step": 7610
},
{
"epoch": 1.8331728454501686,
"grad_norm": 1.046875,
"learning_rate": 9.037290145135037e-05,
"loss": 0.4512,
"step": 7615
},
{
"epoch": 1.8343765045739047,
"grad_norm": 1.265625,
"learning_rate": 9.02919925097107e-05,
"loss": 0.4691,
"step": 7620
},
{
"epoch": 1.835580163697641,
"grad_norm": 1.2578125,
"learning_rate": 9.021112048240343e-05,
"loss": 0.439,
"step": 7625
},
{
"epoch": 1.8367838228213769,
"grad_norm": 1.2109375,
"learning_rate": 9.01302854986413e-05,
"loss": 0.4738,
"step": 7630
},
{
"epoch": 1.8379874819451132,
"grad_norm": 1.296875,
"learning_rate": 9.004948768757791e-05,
"loss": 0.4421,
"step": 7635
},
{
"epoch": 1.8391911410688493,
"grad_norm": 1.0859375,
"learning_rate": 8.996872717830741e-05,
"loss": 0.4801,
"step": 7640
},
{
"epoch": 1.8403948001925854,
"grad_norm": 1.1328125,
"learning_rate": 8.988800409986444e-05,
"loss": 0.4642,
"step": 7645
},
{
"epoch": 1.8415984593163217,
"grad_norm": 1.1484375,
"learning_rate": 8.980731858122381e-05,
"loss": 0.4792,
"step": 7650
},
{
"epoch": 1.8428021184400578,
"grad_norm": 1.171875,
"learning_rate": 8.97266707513002e-05,
"loss": 0.4573,
"step": 7655
},
{
"epoch": 1.844005777563794,
"grad_norm": 1.234375,
"learning_rate": 8.964606073894827e-05,
"loss": 0.4592,
"step": 7660
},
{
"epoch": 1.8452094366875302,
"grad_norm": 1.1953125,
"learning_rate": 8.956548867296207e-05,
"loss": 0.4835,
"step": 7665
},
{
"epoch": 1.8464130958112661,
"grad_norm": 1.1640625,
"learning_rate": 8.948495468207513e-05,
"loss": 0.4719,
"step": 7670
},
{
"epoch": 1.8476167549350024,
"grad_norm": 1.0546875,
"learning_rate": 8.940445889496017e-05,
"loss": 0.4719,
"step": 7675
},
{
"epoch": 1.8488204140587385,
"grad_norm": 1.0703125,
"learning_rate": 8.932400144022878e-05,
"loss": 0.4302,
"step": 7680
},
{
"epoch": 1.8500240731824746,
"grad_norm": 1.140625,
"learning_rate": 8.924358244643136e-05,
"loss": 0.4676,
"step": 7685
},
{
"epoch": 1.851227732306211,
"grad_norm": 1.265625,
"learning_rate": 8.916320204205683e-05,
"loss": 0.4808,
"step": 7690
},
{
"epoch": 1.852431391429947,
"grad_norm": 1.09375,
"learning_rate": 8.908286035553246e-05,
"loss": 0.4307,
"step": 7695
},
{
"epoch": 1.8536350505536832,
"grad_norm": 1.2109375,
"learning_rate": 8.900255751522374e-05,
"loss": 0.4679,
"step": 7700
},
{
"epoch": 1.8548387096774195,
"grad_norm": 1.1796875,
"learning_rate": 8.892229364943395e-05,
"loss": 0.4465,
"step": 7705
},
{
"epoch": 1.8560423688011554,
"grad_norm": 1.0546875,
"learning_rate": 8.884206888640423e-05,
"loss": 0.4463,
"step": 7710
},
{
"epoch": 1.8572460279248917,
"grad_norm": 1.1796875,
"learning_rate": 8.876188335431309e-05,
"loss": 0.4698,
"step": 7715
},
{
"epoch": 1.8584496870486278,
"grad_norm": 1.125,
"learning_rate": 8.868173718127654e-05,
"loss": 0.4684,
"step": 7720
},
{
"epoch": 1.8596533461723639,
"grad_norm": 1.140625,
"learning_rate": 8.860163049534762e-05,
"loss": 0.4427,
"step": 7725
},
{
"epoch": 1.8608570052961002,
"grad_norm": 1.265625,
"learning_rate": 8.852156342451623e-05,
"loss": 0.4535,
"step": 7730
},
{
"epoch": 1.8620606644198363,
"grad_norm": 1.140625,
"learning_rate": 8.844153609670907e-05,
"loss": 0.476,
"step": 7735
},
{
"epoch": 1.8632643235435724,
"grad_norm": 1.0703125,
"learning_rate": 8.836154863978926e-05,
"loss": 0.4558,
"step": 7740
},
{
"epoch": 1.8644679826673087,
"grad_norm": 1.0625,
"learning_rate": 8.828160118155623e-05,
"loss": 0.4243,
"step": 7745
},
{
"epoch": 1.8656716417910446,
"grad_norm": 1.1875,
"learning_rate": 8.82016938497456e-05,
"loss": 0.4738,
"step": 7750
},
{
"epoch": 1.866875300914781,
"grad_norm": 1.234375,
"learning_rate": 8.812182677202875e-05,
"loss": 0.4459,
"step": 7755
},
{
"epoch": 1.8680789600385173,
"grad_norm": 1.375,
"learning_rate": 8.80420000760128e-05,
"loss": 0.4569,
"step": 7760
},
{
"epoch": 1.8692826191622531,
"grad_norm": 1.1953125,
"learning_rate": 8.796221388924035e-05,
"loss": 0.4515,
"step": 7765
},
{
"epoch": 1.8704862782859895,
"grad_norm": 1.140625,
"learning_rate": 8.788246833918926e-05,
"loss": 0.4504,
"step": 7770
},
{
"epoch": 1.8716899374097256,
"grad_norm": 1.0703125,
"learning_rate": 8.780276355327253e-05,
"loss": 0.4491,
"step": 7775
},
{
"epoch": 1.8728935965334617,
"grad_norm": 1.25,
"learning_rate": 8.772309965883792e-05,
"loss": 0.4417,
"step": 7780
},
{
"epoch": 1.874097255657198,
"grad_norm": 1.125,
"learning_rate": 8.764347678316792e-05,
"loss": 0.4526,
"step": 7785
},
{
"epoch": 1.875300914780934,
"grad_norm": 1.203125,
"learning_rate": 8.756389505347948e-05,
"loss": 0.4433,
"step": 7790
},
{
"epoch": 1.8765045739046702,
"grad_norm": 1.1640625,
"learning_rate": 8.748435459692378e-05,
"loss": 0.4938,
"step": 7795
},
{
"epoch": 1.8777082330284065,
"grad_norm": 1.2578125,
"learning_rate": 8.740485554058615e-05,
"loss": 0.4613,
"step": 7800
},
{
"epoch": 1.8789118921521424,
"grad_norm": 1.125,
"learning_rate": 8.732539801148562e-05,
"loss": 0.4855,
"step": 7805
},
{
"epoch": 1.8801155512758787,
"grad_norm": 1.125,
"learning_rate": 8.724598213657503e-05,
"loss": 0.4591,
"step": 7810
},
{
"epoch": 1.8813192103996148,
"grad_norm": 1.140625,
"learning_rate": 8.716660804274052e-05,
"loss": 0.436,
"step": 7815
},
{
"epoch": 1.882522869523351,
"grad_norm": 1.25,
"learning_rate": 8.708727585680157e-05,
"loss": 0.4879,
"step": 7820
},
{
"epoch": 1.8837265286470872,
"grad_norm": 1.171875,
"learning_rate": 8.700798570551068e-05,
"loss": 0.4676,
"step": 7825
},
{
"epoch": 1.8849301877708233,
"grad_norm": 1.109375,
"learning_rate": 8.692873771555317e-05,
"loss": 0.4801,
"step": 7830
},
{
"epoch": 1.8861338468945594,
"grad_norm": 1.3046875,
"learning_rate": 8.684953201354705e-05,
"loss": 0.4642,
"step": 7835
},
{
"epoch": 1.8873375060182958,
"grad_norm": 1.125,
"learning_rate": 8.677036872604268e-05,
"loss": 0.4721,
"step": 7840
},
{
"epoch": 1.8885411651420316,
"grad_norm": 1.171875,
"learning_rate": 8.669124797952277e-05,
"loss": 0.462,
"step": 7845
},
{
"epoch": 1.889744824265768,
"grad_norm": 1.2890625,
"learning_rate": 8.661216990040188e-05,
"loss": 0.4289,
"step": 7850
},
{
"epoch": 1.890948483389504,
"grad_norm": 1.1796875,
"learning_rate": 8.65331346150266e-05,
"loss": 0.4524,
"step": 7855
},
{
"epoch": 1.8921521425132402,
"grad_norm": 1.1875,
"learning_rate": 8.645414224967503e-05,
"loss": 0.4301,
"step": 7860
},
{
"epoch": 1.8933558016369765,
"grad_norm": 1.109375,
"learning_rate": 8.637519293055672e-05,
"loss": 0.4577,
"step": 7865
},
{
"epoch": 1.8945594607607126,
"grad_norm": 1.1171875,
"learning_rate": 8.629628678381245e-05,
"loss": 0.435,
"step": 7870
},
{
"epoch": 1.8957631198844487,
"grad_norm": 1.140625,
"learning_rate": 8.621742393551398e-05,
"loss": 0.4733,
"step": 7875
},
{
"epoch": 1.896966779008185,
"grad_norm": 1.0703125,
"learning_rate": 8.613860451166396e-05,
"loss": 0.4073,
"step": 7880
},
{
"epoch": 1.8981704381319209,
"grad_norm": 1.171875,
"learning_rate": 8.605982863819561e-05,
"loss": 0.4518,
"step": 7885
},
{
"epoch": 1.8993740972556572,
"grad_norm": 1.1328125,
"learning_rate": 8.598109644097259e-05,
"loss": 0.4688,
"step": 7890
},
{
"epoch": 1.9005777563793933,
"grad_norm": 1.0859375,
"learning_rate": 8.590240804578877e-05,
"loss": 0.4641,
"step": 7895
},
{
"epoch": 1.9017814155031294,
"grad_norm": 1.0234375,
"learning_rate": 8.582376357836801e-05,
"loss": 0.4241,
"step": 7900
},
{
"epoch": 1.9029850746268657,
"grad_norm": 1.2421875,
"learning_rate": 8.574516316436402e-05,
"loss": 0.4692,
"step": 7905
},
{
"epoch": 1.9041887337506018,
"grad_norm": 1.171875,
"learning_rate": 8.566660692936014e-05,
"loss": 0.4423,
"step": 7910
},
{
"epoch": 1.905392392874338,
"grad_norm": 1.1015625,
"learning_rate": 8.558809499886906e-05,
"loss": 0.4413,
"step": 7915
},
{
"epoch": 1.9065960519980742,
"grad_norm": 1.1875,
"learning_rate": 8.550962749833274e-05,
"loss": 0.4658,
"step": 7920
},
{
"epoch": 1.9077997111218103,
"grad_norm": 1.2734375,
"learning_rate": 8.543120455312211e-05,
"loss": 0.4967,
"step": 7925
},
{
"epoch": 1.9090033702455464,
"grad_norm": 1.1640625,
"learning_rate": 8.535282628853693e-05,
"loss": 0.4573,
"step": 7930
},
{
"epoch": 1.9102070293692828,
"grad_norm": 1.15625,
"learning_rate": 8.527449282980564e-05,
"loss": 0.4532,
"step": 7935
},
{
"epoch": 1.9114106884930187,
"grad_norm": 1.0625,
"learning_rate": 8.519620430208491e-05,
"loss": 0.4343,
"step": 7940
},
{
"epoch": 1.912614347616755,
"grad_norm": 1.1953125,
"learning_rate": 8.511796083045985e-05,
"loss": 0.4682,
"step": 7945
},
{
"epoch": 1.913818006740491,
"grad_norm": 1.0859375,
"learning_rate": 8.503976253994338e-05,
"loss": 0.4351,
"step": 7950
},
{
"epoch": 1.9150216658642272,
"grad_norm": 1.2421875,
"learning_rate": 8.496160955547641e-05,
"loss": 0.4599,
"step": 7955
},
{
"epoch": 1.9162253249879635,
"grad_norm": 1.15625,
"learning_rate": 8.488350200192731e-05,
"loss": 0.4671,
"step": 7960
},
{
"epoch": 1.9174289841116996,
"grad_norm": 1.1328125,
"learning_rate": 8.480544000409193e-05,
"loss": 0.4484,
"step": 7965
},
{
"epoch": 1.9186326432354357,
"grad_norm": 1.0078125,
"learning_rate": 8.472742368669337e-05,
"loss": 0.4137,
"step": 7970
},
{
"epoch": 1.919836302359172,
"grad_norm": 1.046875,
"learning_rate": 8.464945317438164e-05,
"loss": 0.4392,
"step": 7975
},
{
"epoch": 1.921039961482908,
"grad_norm": 1.296875,
"learning_rate": 8.457152859173371e-05,
"loss": 0.4482,
"step": 7980
},
{
"epoch": 1.9222436206066442,
"grad_norm": 1.1171875,
"learning_rate": 8.449365006325304e-05,
"loss": 0.4845,
"step": 7985
},
{
"epoch": 1.9234472797303803,
"grad_norm": 1.1015625,
"learning_rate": 8.441581771336956e-05,
"loss": 0.4533,
"step": 7990
},
{
"epoch": 1.9246509388541164,
"grad_norm": 1.1328125,
"learning_rate": 8.433803166643944e-05,
"loss": 0.4669,
"step": 7995
},
{
"epoch": 1.9258545979778527,
"grad_norm": 1.0703125,
"learning_rate": 8.426029204674479e-05,
"loss": 0.4378,
"step": 8000
},
{
"epoch": 1.9258545979778527,
"eval_loss": 0.38515639305114746,
"eval_runtime": 2.416,
"eval_samples_per_second": 82.78,
"eval_steps_per_second": 82.78,
"step": 8000
},
{
"epoch": 1.9270582571015888,
"grad_norm": 1.1796875,
"learning_rate": 8.418259897849365e-05,
"loss": 0.4709,
"step": 8005
},
{
"epoch": 1.928261916225325,
"grad_norm": 1.140625,
"learning_rate": 8.410495258581957e-05,
"loss": 0.432,
"step": 8010
},
{
"epoch": 1.9294655753490613,
"grad_norm": 1.2265625,
"learning_rate": 8.402735299278164e-05,
"loss": 0.4623,
"step": 8015
},
{
"epoch": 1.9306692344727971,
"grad_norm": 1.3046875,
"learning_rate": 8.394980032336409e-05,
"loss": 0.4701,
"step": 8020
},
{
"epoch": 1.9318728935965335,
"grad_norm": 1.1171875,
"learning_rate": 8.387229470147617e-05,
"loss": 0.4867,
"step": 8025
},
{
"epoch": 1.9330765527202696,
"grad_norm": 1.203125,
"learning_rate": 8.379483625095202e-05,
"loss": 0.4878,
"step": 8030
},
{
"epoch": 1.9342802118440057,
"grad_norm": 1.1328125,
"learning_rate": 8.371742509555042e-05,
"loss": 0.4176,
"step": 8035
},
{
"epoch": 1.935483870967742,
"grad_norm": 1.1796875,
"learning_rate": 8.36400613589545e-05,
"loss": 0.482,
"step": 8040
},
{
"epoch": 1.936687530091478,
"grad_norm": 1.2265625,
"learning_rate": 8.356274516477175e-05,
"loss": 0.4373,
"step": 8045
},
{
"epoch": 1.9378911892152142,
"grad_norm": 1.140625,
"learning_rate": 8.348547663653352e-05,
"loss": 0.4531,
"step": 8050
},
{
"epoch": 1.9390948483389505,
"grad_norm": 1.1328125,
"learning_rate": 8.340825589769523e-05,
"loss": 0.4447,
"step": 8055
},
{
"epoch": 1.9402985074626866,
"grad_norm": 1.0859375,
"learning_rate": 8.333108307163573e-05,
"loss": 0.4565,
"step": 8060
},
{
"epoch": 1.9415021665864227,
"grad_norm": 1.1875,
"learning_rate": 8.325395828165749e-05,
"loss": 0.4464,
"step": 8065
},
{
"epoch": 1.942705825710159,
"grad_norm": 1.0859375,
"learning_rate": 8.31768816509861e-05,
"loss": 0.4316,
"step": 8070
},
{
"epoch": 1.943909484833895,
"grad_norm": 1.15625,
"learning_rate": 8.309985330277024e-05,
"loss": 0.443,
"step": 8075
},
{
"epoch": 1.9451131439576312,
"grad_norm": 1.234375,
"learning_rate": 8.302287336008153e-05,
"loss": 0.4285,
"step": 8080
},
{
"epoch": 1.9463168030813673,
"grad_norm": 1.1328125,
"learning_rate": 8.294594194591412e-05,
"loss": 0.4081,
"step": 8085
},
{
"epoch": 1.9475204622051034,
"grad_norm": 1.0546875,
"learning_rate": 8.286905918318472e-05,
"loss": 0.4254,
"step": 8090
},
{
"epoch": 1.9487241213288398,
"grad_norm": 1.0234375,
"learning_rate": 8.279222519473229e-05,
"loss": 0.4297,
"step": 8095
},
{
"epoch": 1.9499277804525759,
"grad_norm": 1.3515625,
"learning_rate": 8.27154401033178e-05,
"loss": 0.462,
"step": 8100
},
{
"epoch": 1.951131439576312,
"grad_norm": 1.0390625,
"learning_rate": 8.263870403162422e-05,
"loss": 0.4902,
"step": 8105
},
{
"epoch": 1.9523350987000483,
"grad_norm": 1.1640625,
"learning_rate": 8.256201710225603e-05,
"loss": 0.4382,
"step": 8110
},
{
"epoch": 1.9535387578237842,
"grad_norm": 1.109375,
"learning_rate": 8.248537943773936e-05,
"loss": 0.4516,
"step": 8115
},
{
"epoch": 1.9547424169475205,
"grad_norm": 1.03125,
"learning_rate": 8.240879116052151e-05,
"loss": 0.4287,
"step": 8120
},
{
"epoch": 1.9559460760712566,
"grad_norm": 1.234375,
"learning_rate": 8.23322523929709e-05,
"loss": 0.4558,
"step": 8125
},
{
"epoch": 1.9571497351949927,
"grad_norm": 1.296875,
"learning_rate": 8.225576325737692e-05,
"loss": 0.4495,
"step": 8130
},
{
"epoch": 1.958353394318729,
"grad_norm": 1.21875,
"learning_rate": 8.217932387594952e-05,
"loss": 0.4783,
"step": 8135
},
{
"epoch": 1.9595570534424651,
"grad_norm": 1.0390625,
"learning_rate": 8.210293437081929e-05,
"loss": 0.447,
"step": 8140
},
{
"epoch": 1.9607607125662012,
"grad_norm": 1.1640625,
"learning_rate": 8.202659486403709e-05,
"loss": 0.4473,
"step": 8145
},
{
"epoch": 1.9619643716899375,
"grad_norm": 1.2109375,
"learning_rate": 8.195030547757383e-05,
"loss": 0.4188,
"step": 8150
},
{
"epoch": 1.9631680308136734,
"grad_norm": 1.1875,
"learning_rate": 8.187406633332045e-05,
"loss": 0.463,
"step": 8155
},
{
"epoch": 1.9643716899374097,
"grad_norm": 1.1796875,
"learning_rate": 8.179787755308749e-05,
"loss": 0.4376,
"step": 8160
},
{
"epoch": 1.9655753490611458,
"grad_norm": 1.15625,
"learning_rate": 8.172173925860515e-05,
"loss": 0.4411,
"step": 8165
},
{
"epoch": 1.966779008184882,
"grad_norm": 1.125,
"learning_rate": 8.164565157152289e-05,
"loss": 0.4409,
"step": 8170
},
{
"epoch": 1.9679826673086183,
"grad_norm": 1.1953125,
"learning_rate": 8.156961461340931e-05,
"loss": 0.4583,
"step": 8175
},
{
"epoch": 1.9691863264323544,
"grad_norm": 1.0390625,
"learning_rate": 8.149362850575201e-05,
"loss": 0.4748,
"step": 8180
},
{
"epoch": 1.9703899855560905,
"grad_norm": 1.1796875,
"learning_rate": 8.141769336995727e-05,
"loss": 0.4574,
"step": 8185
},
{
"epoch": 1.9715936446798268,
"grad_norm": 1.1796875,
"learning_rate": 8.134180932734998e-05,
"loss": 0.4537,
"step": 8190
},
{
"epoch": 1.9727973038035629,
"grad_norm": 1.1015625,
"learning_rate": 8.126597649917345e-05,
"loss": 0.4421,
"step": 8195
},
{
"epoch": 1.974000962927299,
"grad_norm": 1.125,
"learning_rate": 8.1190195006589e-05,
"loss": 0.4426,
"step": 8200
},
{
"epoch": 1.9752046220510353,
"grad_norm": 1.15625,
"learning_rate": 8.11144649706761e-05,
"loss": 0.4775,
"step": 8205
},
{
"epoch": 1.9764082811747712,
"grad_norm": 1.234375,
"learning_rate": 8.103878651243189e-05,
"loss": 0.4769,
"step": 8210
},
{
"epoch": 1.9776119402985075,
"grad_norm": 1.0703125,
"learning_rate": 8.096315975277116e-05,
"loss": 0.4242,
"step": 8215
},
{
"epoch": 1.9788155994222436,
"grad_norm": 1.1328125,
"learning_rate": 8.088758481252612e-05,
"loss": 0.4515,
"step": 8220
},
{
"epoch": 1.9800192585459797,
"grad_norm": 1.0390625,
"learning_rate": 8.081206181244612e-05,
"loss": 0.4238,
"step": 8225
},
{
"epoch": 1.981222917669716,
"grad_norm": 1.15625,
"learning_rate": 8.073659087319757e-05,
"loss": 0.447,
"step": 8230
},
{
"epoch": 1.9824265767934521,
"grad_norm": 1.125,
"learning_rate": 8.066117211536362e-05,
"loss": 0.438,
"step": 8235
},
{
"epoch": 1.9836302359171882,
"grad_norm": 1.046875,
"learning_rate": 8.058580565944419e-05,
"loss": 0.4456,
"step": 8240
},
{
"epoch": 1.9848338950409246,
"grad_norm": 1.109375,
"learning_rate": 8.051049162585553e-05,
"loss": 0.4426,
"step": 8245
},
{
"epoch": 1.9860375541646604,
"grad_norm": 1.2109375,
"learning_rate": 8.043523013493014e-05,
"loss": 0.4746,
"step": 8250
},
{
"epoch": 1.9872412132883968,
"grad_norm": 0.99609375,
"learning_rate": 8.036002130691662e-05,
"loss": 0.4391,
"step": 8255
},
{
"epoch": 1.9884448724121329,
"grad_norm": 1.1328125,
"learning_rate": 8.028486526197935e-05,
"loss": 0.4454,
"step": 8260
},
{
"epoch": 1.989648531535869,
"grad_norm": 1.0859375,
"learning_rate": 8.020976212019847e-05,
"loss": 0.4457,
"step": 8265
},
{
"epoch": 1.9908521906596053,
"grad_norm": 1.1015625,
"learning_rate": 8.013471200156956e-05,
"loss": 0.4616,
"step": 8270
},
{
"epoch": 1.9920558497833414,
"grad_norm": 1.140625,
"learning_rate": 8.005971502600344e-05,
"loss": 0.4433,
"step": 8275
},
{
"epoch": 1.9932595089070775,
"grad_norm": 1.203125,
"learning_rate": 7.998477131332605e-05,
"loss": 0.4558,
"step": 8280
},
{
"epoch": 1.9944631680308138,
"grad_norm": 1.140625,
"learning_rate": 7.990988098327821e-05,
"loss": 0.4677,
"step": 8285
},
{
"epoch": 1.9956668271545497,
"grad_norm": 1.140625,
"learning_rate": 7.983504415551553e-05,
"loss": 0.4546,
"step": 8290
},
{
"epoch": 1.996870486278286,
"grad_norm": 1.1171875,
"learning_rate": 7.9760260949608e-05,
"loss": 0.4472,
"step": 8295
},
{
"epoch": 1.998074145402022,
"grad_norm": 1.1171875,
"learning_rate": 7.968553148504007e-05,
"loss": 0.4175,
"step": 8300
},
{
"epoch": 1.9992778045257582,
"grad_norm": 1.140625,
"learning_rate": 7.961085588121026e-05,
"loss": 0.4297,
"step": 8305
},
{
"epoch": 1.9995185363505055,
"eval_loss": 0.37979966402053833,
"eval_runtime": 2.3917,
"eval_samples_per_second": 83.624,
"eval_steps_per_second": 83.624,
"step": 8306
},
{
"epoch": 2.0004814636494945,
"grad_norm": 1.1328125,
"learning_rate": 7.9536234257431e-05,
"loss": 0.4353,
"step": 8310
},
{
"epoch": 2.0016851227732304,
"grad_norm": 1.109375,
"learning_rate": 7.946166673292858e-05,
"loss": 0.3902,
"step": 8315
},
{
"epoch": 2.0028887818969667,
"grad_norm": 1.0390625,
"learning_rate": 7.938715342684274e-05,
"loss": 0.4374,
"step": 8320
},
{
"epoch": 2.004092441020703,
"grad_norm": 1.1484375,
"learning_rate": 7.931269445822666e-05,
"loss": 0.4068,
"step": 8325
},
{
"epoch": 2.005296100144439,
"grad_norm": 1.078125,
"learning_rate": 7.923828994604671e-05,
"loss": 0.3911,
"step": 8330
},
{
"epoch": 2.0064997592681753,
"grad_norm": 1.078125,
"learning_rate": 7.916394000918217e-05,
"loss": 0.4198,
"step": 8335
},
{
"epoch": 2.0077034183919116,
"grad_norm": 1.140625,
"learning_rate": 7.908964476642523e-05,
"loss": 0.4418,
"step": 8340
},
{
"epoch": 2.0089070775156475,
"grad_norm": 1.046875,
"learning_rate": 7.901540433648059e-05,
"loss": 0.4011,
"step": 8345
},
{
"epoch": 2.0101107366393838,
"grad_norm": 1.078125,
"learning_rate": 7.894121883796545e-05,
"loss": 0.399,
"step": 8350
},
{
"epoch": 2.01131439576312,
"grad_norm": 1.0859375,
"learning_rate": 7.886708838940925e-05,
"loss": 0.4171,
"step": 8355
},
{
"epoch": 2.012518054886856,
"grad_norm": 1.09375,
"learning_rate": 7.879301310925339e-05,
"loss": 0.3966,
"step": 8360
},
{
"epoch": 2.0137217140105923,
"grad_norm": 1.0703125,
"learning_rate": 7.871899311585123e-05,
"loss": 0.4054,
"step": 8365
},
{
"epoch": 2.014925373134328,
"grad_norm": 1.09375,
"learning_rate": 7.86450285274677e-05,
"loss": 0.393,
"step": 8370
},
{
"epoch": 2.0161290322580645,
"grad_norm": 1.1484375,
"learning_rate": 7.857111946227928e-05,
"loss": 0.421,
"step": 8375
},
{
"epoch": 2.017332691381801,
"grad_norm": 1.0546875,
"learning_rate": 7.849726603837372e-05,
"loss": 0.3687,
"step": 8380
},
{
"epoch": 2.0185363505055367,
"grad_norm": 1.1484375,
"learning_rate": 7.842346837374982e-05,
"loss": 0.4218,
"step": 8385
},
{
"epoch": 2.019740009629273,
"grad_norm": 1.09375,
"learning_rate": 7.834972658631736e-05,
"loss": 0.3992,
"step": 8390
},
{
"epoch": 2.0209436687530093,
"grad_norm": 1.171875,
"learning_rate": 7.827604079389679e-05,
"loss": 0.3854,
"step": 8395
},
{
"epoch": 2.0221473278767452,
"grad_norm": 1.1640625,
"learning_rate": 7.82024111142191e-05,
"loss": 0.4073,
"step": 8400
},
{
"epoch": 2.0233509870004815,
"grad_norm": 1.125,
"learning_rate": 7.812883766492573e-05,
"loss": 0.4257,
"step": 8405
},
{
"epoch": 2.0245546461242174,
"grad_norm": 1.0546875,
"learning_rate": 7.805532056356809e-05,
"loss": 0.3998,
"step": 8410
},
{
"epoch": 2.0257583052479537,
"grad_norm": 1.1171875,
"learning_rate": 7.798185992760773e-05,
"loss": 0.3866,
"step": 8415
},
{
"epoch": 2.02696196437169,
"grad_norm": 1.0546875,
"learning_rate": 7.790845587441587e-05,
"loss": 0.3957,
"step": 8420
},
{
"epoch": 2.028165623495426,
"grad_norm": 1.125,
"learning_rate": 7.783510852127338e-05,
"loss": 0.4383,
"step": 8425
},
{
"epoch": 2.0293692826191623,
"grad_norm": 1.0390625,
"learning_rate": 7.776181798537056e-05,
"loss": 0.3989,
"step": 8430
},
{
"epoch": 2.0305729417428986,
"grad_norm": 1.078125,
"learning_rate": 7.768858438380688e-05,
"loss": 0.4121,
"step": 8435
},
{
"epoch": 2.0317766008666345,
"grad_norm": 1.2421875,
"learning_rate": 7.761540783359083e-05,
"loss": 0.4311,
"step": 8440
},
{
"epoch": 2.032980259990371,
"grad_norm": 1.1015625,
"learning_rate": 7.754228845163984e-05,
"loss": 0.4227,
"step": 8445
},
{
"epoch": 2.0341839191141067,
"grad_norm": 1.21875,
"learning_rate": 7.746922635477986e-05,
"loss": 0.4153,
"step": 8450
},
{
"epoch": 2.035387578237843,
"grad_norm": 1.0546875,
"learning_rate": 7.739622165974547e-05,
"loss": 0.4029,
"step": 8455
},
{
"epoch": 2.0365912373615793,
"grad_norm": 1.21875,
"learning_rate": 7.732327448317938e-05,
"loss": 0.4005,
"step": 8460
},
{
"epoch": 2.037794896485315,
"grad_norm": 1.0703125,
"learning_rate": 7.725038494163256e-05,
"loss": 0.4064,
"step": 8465
},
{
"epoch": 2.0389985556090515,
"grad_norm": 1.15625,
"learning_rate": 7.717755315156373e-05,
"loss": 0.4134,
"step": 8470
},
{
"epoch": 2.040202214732788,
"grad_norm": 1.1875,
"learning_rate": 7.710477922933947e-05,
"loss": 0.3978,
"step": 8475
},
{
"epoch": 2.0414058738565237,
"grad_norm": 1.15625,
"learning_rate": 7.703206329123387e-05,
"loss": 0.3932,
"step": 8480
},
{
"epoch": 2.04260953298026,
"grad_norm": 1.1328125,
"learning_rate": 7.69594054534283e-05,
"loss": 0.4132,
"step": 8485
},
{
"epoch": 2.043813192103996,
"grad_norm": 1.0703125,
"learning_rate": 7.688680583201143e-05,
"loss": 0.4215,
"step": 8490
},
{
"epoch": 2.0450168512277322,
"grad_norm": 1.1328125,
"learning_rate": 7.68142645429788e-05,
"loss": 0.3968,
"step": 8495
},
{
"epoch": 2.0462205103514686,
"grad_norm": 1.203125,
"learning_rate": 7.674178170223279e-05,
"loss": 0.418,
"step": 8500
},
{
"epoch": 2.0462205103514686,
"eval_loss": 0.3806837499141693,
"eval_runtime": 2.3897,
"eval_samples_per_second": 83.691,
"eval_steps_per_second": 83.691,
"step": 8500
},
{
"epoch": 2.0474241694752044,
"grad_norm": 1.1015625,
"learning_rate": 7.666935742558238e-05,
"loss": 0.3989,
"step": 8505
},
{
"epoch": 2.0486278285989408,
"grad_norm": 1.2109375,
"learning_rate": 7.659699182874302e-05,
"loss": 0.4223,
"step": 8510
},
{
"epoch": 2.049831487722677,
"grad_norm": 1.0625,
"learning_rate": 7.652468502733641e-05,
"loss": 0.4093,
"step": 8515
},
{
"epoch": 2.051035146846413,
"grad_norm": 1.03125,
"learning_rate": 7.645243713689025e-05,
"loss": 0.4229,
"step": 8520
},
{
"epoch": 2.0522388059701493,
"grad_norm": 1.171875,
"learning_rate": 7.638024827283818e-05,
"loss": 0.385,
"step": 8525
},
{
"epoch": 2.0534424650938856,
"grad_norm": 1.046875,
"learning_rate": 7.630811855051943e-05,
"loss": 0.3694,
"step": 8530
},
{
"epoch": 2.0546461242176215,
"grad_norm": 1.109375,
"learning_rate": 7.623604808517888e-05,
"loss": 0.4145,
"step": 8535
},
{
"epoch": 2.055849783341358,
"grad_norm": 1.0390625,
"learning_rate": 7.616403699196664e-05,
"loss": 0.3964,
"step": 8540
},
{
"epoch": 2.0570534424650937,
"grad_norm": 1.25,
"learning_rate": 7.609208538593797e-05,
"loss": 0.3957,
"step": 8545
},
{
"epoch": 2.05825710158883,
"grad_norm": 1.078125,
"learning_rate": 7.602019338205308e-05,
"loss": 0.3741,
"step": 8550
},
{
"epoch": 2.0594607607125663,
"grad_norm": 1.1484375,
"learning_rate": 7.594836109517698e-05,
"loss": 0.4318,
"step": 8555
},
{
"epoch": 2.060664419836302,
"grad_norm": 1.171875,
"learning_rate": 7.58765886400792e-05,
"loss": 0.4193,
"step": 8560
},
{
"epoch": 2.0618680789600385,
"grad_norm": 1.1328125,
"learning_rate": 7.580487613143381e-05,
"loss": 0.4035,
"step": 8565
},
{
"epoch": 2.063071738083775,
"grad_norm": 1.125,
"learning_rate": 7.573322368381895e-05,
"loss": 0.4023,
"step": 8570
},
{
"epoch": 2.0642753972075107,
"grad_norm": 1.09375,
"learning_rate": 7.566163141171689e-05,
"loss": 0.3735,
"step": 8575
},
{
"epoch": 2.065479056331247,
"grad_norm": 1.171875,
"learning_rate": 7.559009942951371e-05,
"loss": 0.4156,
"step": 8580
},
{
"epoch": 2.066682715454983,
"grad_norm": 1.109375,
"learning_rate": 7.551862785149918e-05,
"loss": 0.4007,
"step": 8585
},
{
"epoch": 2.0678863745787193,
"grad_norm": 1.1171875,
"learning_rate": 7.544721679186659e-05,
"loss": 0.4138,
"step": 8590
},
{
"epoch": 2.0690900337024556,
"grad_norm": 1.078125,
"learning_rate": 7.53758663647125e-05,
"loss": 0.39,
"step": 8595
},
{
"epoch": 2.0702936928261915,
"grad_norm": 1.109375,
"learning_rate": 7.530457668403657e-05,
"loss": 0.4167,
"step": 8600
},
{
"epoch": 2.071497351949928,
"grad_norm": 1.0859375,
"learning_rate": 7.523334786374148e-05,
"loss": 0.417,
"step": 8605
},
{
"epoch": 2.072701011073664,
"grad_norm": 1.203125,
"learning_rate": 7.516218001763256e-05,
"loss": 0.4115,
"step": 8610
},
{
"epoch": 2.0739046701974,
"grad_norm": 1.1015625,
"learning_rate": 7.509107325941786e-05,
"loss": 0.4022,
"step": 8615
},
{
"epoch": 2.0751083293211363,
"grad_norm": 1.125,
"learning_rate": 7.502002770270769e-05,
"loss": 0.3862,
"step": 8620
},
{
"epoch": 2.076311988444872,
"grad_norm": 1.2890625,
"learning_rate": 7.494904346101468e-05,
"loss": 0.4426,
"step": 8625
},
{
"epoch": 2.0775156475686085,
"grad_norm": 1.125,
"learning_rate": 7.487812064775342e-05,
"loss": 0.3998,
"step": 8630
},
{
"epoch": 2.078719306692345,
"grad_norm": 1.1953125,
"learning_rate": 7.480725937624039e-05,
"loss": 0.415,
"step": 8635
},
{
"epoch": 2.0799229658160807,
"grad_norm": 1.0625,
"learning_rate": 7.473645975969376e-05,
"loss": 0.4114,
"step": 8640
},
{
"epoch": 2.081126624939817,
"grad_norm": 1.0546875,
"learning_rate": 7.466572191123314e-05,
"loss": 0.3811,
"step": 8645
},
{
"epoch": 2.0823302840635534,
"grad_norm": 1.1171875,
"learning_rate": 7.45950459438795e-05,
"loss": 0.3939,
"step": 8650
},
{
"epoch": 2.0835339431872892,
"grad_norm": 1.109375,
"learning_rate": 7.452443197055491e-05,
"loss": 0.3883,
"step": 8655
},
{
"epoch": 2.0847376023110256,
"grad_norm": 1.1015625,
"learning_rate": 7.445388010408239e-05,
"loss": 0.4078,
"step": 8660
},
{
"epoch": 2.085941261434762,
"grad_norm": 1.21875,
"learning_rate": 7.438339045718574e-05,
"loss": 0.3887,
"step": 8665
},
{
"epoch": 2.0871449205584978,
"grad_norm": 1.1953125,
"learning_rate": 7.431296314248934e-05,
"loss": 0.4039,
"step": 8670
},
{
"epoch": 2.088348579682234,
"grad_norm": 1.1015625,
"learning_rate": 7.4242598272518e-05,
"loss": 0.4015,
"step": 8675
},
{
"epoch": 2.08955223880597,
"grad_norm": 1.109375,
"learning_rate": 7.417229595969673e-05,
"loss": 0.394,
"step": 8680
},
{
"epoch": 2.0907558979297063,
"grad_norm": 1.078125,
"learning_rate": 7.410205631635059e-05,
"loss": 0.3929,
"step": 8685
},
{
"epoch": 2.0919595570534426,
"grad_norm": 1.15625,
"learning_rate": 7.403187945470457e-05,
"loss": 0.4202,
"step": 8690
},
{
"epoch": 2.0931632161771785,
"grad_norm": 1.2109375,
"learning_rate": 7.396176548688328e-05,
"loss": 0.397,
"step": 8695
},
{
"epoch": 2.094366875300915,
"grad_norm": 1.171875,
"learning_rate": 7.389171452491087e-05,
"loss": 0.3991,
"step": 8700
},
{
"epoch": 2.095570534424651,
"grad_norm": 1.078125,
"learning_rate": 7.382172668071079e-05,
"loss": 0.3698,
"step": 8705
},
{
"epoch": 2.096774193548387,
"grad_norm": 1.09375,
"learning_rate": 7.375180206610572e-05,
"loss": 0.3854,
"step": 8710
},
{
"epoch": 2.0979778526721233,
"grad_norm": 1.2265625,
"learning_rate": 7.368194079281723e-05,
"loss": 0.4216,
"step": 8715
},
{
"epoch": 2.099181511795859,
"grad_norm": 1.1328125,
"learning_rate": 7.361214297246573e-05,
"loss": 0.4296,
"step": 8720
},
{
"epoch": 2.1003851709195955,
"grad_norm": 1.09375,
"learning_rate": 7.354240871657028e-05,
"loss": 0.4315,
"step": 8725
},
{
"epoch": 2.101588830043332,
"grad_norm": 1.140625,
"learning_rate": 7.347273813654831e-05,
"loss": 0.4026,
"step": 8730
},
{
"epoch": 2.1027924891670677,
"grad_norm": 1.1875,
"learning_rate": 7.340313134371558e-05,
"loss": 0.4065,
"step": 8735
},
{
"epoch": 2.103996148290804,
"grad_norm": 1.1796875,
"learning_rate": 7.333358844928584e-05,
"loss": 0.4018,
"step": 8740
},
{
"epoch": 2.1051998074145404,
"grad_norm": 1.046875,
"learning_rate": 7.326410956437086e-05,
"loss": 0.3906,
"step": 8745
},
{
"epoch": 2.1064034665382763,
"grad_norm": 1.109375,
"learning_rate": 7.319469479998007e-05,
"loss": 0.3965,
"step": 8750
},
{
"epoch": 2.1076071256620126,
"grad_norm": 1.1875,
"learning_rate": 7.31253442670205e-05,
"loss": 0.3783,
"step": 8755
},
{
"epoch": 2.1088107847857485,
"grad_norm": 1.1328125,
"learning_rate": 7.305605807629646e-05,
"loss": 0.3664,
"step": 8760
},
{
"epoch": 2.110014443909485,
"grad_norm": 1.1953125,
"learning_rate": 7.298683633850958e-05,
"loss": 0.3972,
"step": 8765
},
{
"epoch": 2.111218103033221,
"grad_norm": 1.21875,
"learning_rate": 7.291767916425842e-05,
"loss": 0.4058,
"step": 8770
},
{
"epoch": 2.112421762156957,
"grad_norm": 1.2734375,
"learning_rate": 7.284858666403843e-05,
"loss": 0.4173,
"step": 8775
},
{
"epoch": 2.1136254212806933,
"grad_norm": 1.1171875,
"learning_rate": 7.27795589482417e-05,
"loss": 0.4106,
"step": 8780
},
{
"epoch": 2.1148290804044296,
"grad_norm": 1.140625,
"learning_rate": 7.271059612715683e-05,
"loss": 0.4197,
"step": 8785
},
{
"epoch": 2.1160327395281655,
"grad_norm": 1.1640625,
"learning_rate": 7.264169831096873e-05,
"loss": 0.4326,
"step": 8790
},
{
"epoch": 2.117236398651902,
"grad_norm": 1.15625,
"learning_rate": 7.257286560975844e-05,
"loss": 0.4073,
"step": 8795
},
{
"epoch": 2.118440057775638,
"grad_norm": 1.078125,
"learning_rate": 7.250409813350301e-05,
"loss": 0.3785,
"step": 8800
},
{
"epoch": 2.119643716899374,
"grad_norm": 1.125,
"learning_rate": 7.243539599207518e-05,
"loss": 0.3959,
"step": 8805
},
{
"epoch": 2.1208473760231104,
"grad_norm": 1.125,
"learning_rate": 7.236675929524341e-05,
"loss": 0.4263,
"step": 8810
},
{
"epoch": 2.1220510351468462,
"grad_norm": 1.2578125,
"learning_rate": 7.229818815267155e-05,
"loss": 0.4307,
"step": 8815
},
{
"epoch": 2.1232546942705826,
"grad_norm": 1.1796875,
"learning_rate": 7.222968267391863e-05,
"loss": 0.4089,
"step": 8820
},
{
"epoch": 2.124458353394319,
"grad_norm": 1.109375,
"learning_rate": 7.216124296843894e-05,
"loss": 0.4076,
"step": 8825
},
{
"epoch": 2.1256620125180548,
"grad_norm": 1.1640625,
"learning_rate": 7.20928691455815e-05,
"loss": 0.4176,
"step": 8830
},
{
"epoch": 2.126865671641791,
"grad_norm": 1.09375,
"learning_rate": 7.202456131459023e-05,
"loss": 0.3637,
"step": 8835
},
{
"epoch": 2.1280693307655274,
"grad_norm": 1.390625,
"learning_rate": 7.195631958460345e-05,
"loss": 0.4148,
"step": 8840
},
{
"epoch": 2.1292729898892633,
"grad_norm": 1.0625,
"learning_rate": 7.188814406465402e-05,
"loss": 0.4053,
"step": 8845
},
{
"epoch": 2.1304766490129996,
"grad_norm": 1.2265625,
"learning_rate": 7.182003486366893e-05,
"loss": 0.3777,
"step": 8850
},
{
"epoch": 2.1316803081367355,
"grad_norm": 1.1640625,
"learning_rate": 7.17519920904692e-05,
"loss": 0.3965,
"step": 8855
},
{
"epoch": 2.132883967260472,
"grad_norm": 1.125,
"learning_rate": 7.168401585376977e-05,
"loss": 0.391,
"step": 8860
},
{
"epoch": 2.134087626384208,
"grad_norm": 1.078125,
"learning_rate": 7.16161062621792e-05,
"loss": 0.4147,
"step": 8865
},
{
"epoch": 2.135291285507944,
"grad_norm": 1.0703125,
"learning_rate": 7.154826342419964e-05,
"loss": 0.3957,
"step": 8870
},
{
"epoch": 2.1364949446316803,
"grad_norm": 1.015625,
"learning_rate": 7.148048744822656e-05,
"loss": 0.3883,
"step": 8875
},
{
"epoch": 2.1376986037554166,
"grad_norm": 1.09375,
"learning_rate": 7.141277844254854e-05,
"loss": 0.387,
"step": 8880
},
{
"epoch": 2.1389022628791525,
"grad_norm": 1.109375,
"learning_rate": 7.134513651534729e-05,
"loss": 0.4049,
"step": 8885
},
{
"epoch": 2.140105922002889,
"grad_norm": 1.0625,
"learning_rate": 7.127756177469721e-05,
"loss": 0.3873,
"step": 8890
},
{
"epoch": 2.1413095811266247,
"grad_norm": 1.234375,
"learning_rate": 7.121005432856543e-05,
"loss": 0.3964,
"step": 8895
},
{
"epoch": 2.142513240250361,
"grad_norm": 1.1171875,
"learning_rate": 7.114261428481157e-05,
"loss": 0.4228,
"step": 8900
},
{
"epoch": 2.1437168993740974,
"grad_norm": 1.203125,
"learning_rate": 7.107524175118749e-05,
"loss": 0.3901,
"step": 8905
},
{
"epoch": 2.1449205584978333,
"grad_norm": 1.2734375,
"learning_rate": 7.100793683533727e-05,
"loss": 0.4142,
"step": 8910
},
{
"epoch": 2.1461242176215696,
"grad_norm": 1.1796875,
"learning_rate": 7.094069964479686e-05,
"loss": 0.4214,
"step": 8915
},
{
"epoch": 2.147327876745306,
"grad_norm": 1.1640625,
"learning_rate": 7.087353028699411e-05,
"loss": 0.3911,
"step": 8920
},
{
"epoch": 2.1485315358690418,
"grad_norm": 1.171875,
"learning_rate": 7.080642886924841e-05,
"loss": 0.3991,
"step": 8925
},
{
"epoch": 2.149735194992778,
"grad_norm": 1.2578125,
"learning_rate": 7.07393954987706e-05,
"loss": 0.3907,
"step": 8930
},
{
"epoch": 2.1509388541165144,
"grad_norm": 1.140625,
"learning_rate": 7.067243028266287e-05,
"loss": 0.3983,
"step": 8935
},
{
"epoch": 2.1521425132402503,
"grad_norm": 1.203125,
"learning_rate": 7.06055333279184e-05,
"loss": 0.4067,
"step": 8940
},
{
"epoch": 2.1533461723639866,
"grad_norm": 1.1484375,
"learning_rate": 7.053870474142144e-05,
"loss": 0.4131,
"step": 8945
},
{
"epoch": 2.1545498314877225,
"grad_norm": 1.0859375,
"learning_rate": 7.047194462994693e-05,
"loss": 0.3966,
"step": 8950
},
{
"epoch": 2.155753490611459,
"grad_norm": 1.2109375,
"learning_rate": 7.040525310016038e-05,
"loss": 0.377,
"step": 8955
},
{
"epoch": 2.156957149735195,
"grad_norm": 1.1953125,
"learning_rate": 7.03386302586178e-05,
"loss": 0.4072,
"step": 8960
},
{
"epoch": 2.158160808858931,
"grad_norm": 1.21875,
"learning_rate": 7.027207621176537e-05,
"loss": 0.3732,
"step": 8965
},
{
"epoch": 2.1593644679826673,
"grad_norm": 1.046875,
"learning_rate": 7.020559106593943e-05,
"loss": 0.4195,
"step": 8970
},
{
"epoch": 2.1605681271064037,
"grad_norm": 1.2578125,
"learning_rate": 7.01391749273662e-05,
"loss": 0.3931,
"step": 8975
},
{
"epoch": 2.1617717862301395,
"grad_norm": 1.1171875,
"learning_rate": 7.007282790216158e-05,
"loss": 0.3809,
"step": 8980
},
{
"epoch": 2.162975445353876,
"grad_norm": 1.1015625,
"learning_rate": 7.00065500963312e-05,
"loss": 0.3792,
"step": 8985
},
{
"epoch": 2.1641791044776117,
"grad_norm": 1.3359375,
"learning_rate": 6.994034161576994e-05,
"loss": 0.421,
"step": 8990
},
{
"epoch": 2.165382763601348,
"grad_norm": 1.1328125,
"learning_rate": 6.987420256626201e-05,
"loss": 0.3905,
"step": 8995
},
{
"epoch": 2.1665864227250844,
"grad_norm": 1.0546875,
"learning_rate": 6.980813305348063e-05,
"loss": 0.4093,
"step": 9000
},
{
"epoch": 2.1665864227250844,
"eval_loss": 0.37502264976501465,
"eval_runtime": 2.3896,
"eval_samples_per_second": 83.696,
"eval_steps_per_second": 83.696,
"step": 9000
},
{
"epoch": 2.1677900818488203,
"grad_norm": 1.0546875,
"learning_rate": 6.974213318298798e-05,
"loss": 0.3898,
"step": 9005
},
{
"epoch": 2.1689937409725566,
"grad_norm": 1.1953125,
"learning_rate": 6.96762030602349e-05,
"loss": 0.4196,
"step": 9010
},
{
"epoch": 2.170197400096293,
"grad_norm": 1.1796875,
"learning_rate": 6.961034279056084e-05,
"loss": 0.3951,
"step": 9015
},
{
"epoch": 2.171401059220029,
"grad_norm": 1.140625,
"learning_rate": 6.954455247919364e-05,
"loss": 0.3994,
"step": 9020
},
{
"epoch": 2.172604718343765,
"grad_norm": 1.1953125,
"learning_rate": 6.947883223124934e-05,
"loss": 0.3945,
"step": 9025
},
{
"epoch": 2.173808377467501,
"grad_norm": 1.0078125,
"learning_rate": 6.941318215173203e-05,
"loss": 0.42,
"step": 9030
},
{
"epoch": 2.1750120365912373,
"grad_norm": 1.1953125,
"learning_rate": 6.934760234553373e-05,
"loss": 0.4054,
"step": 9035
},
{
"epoch": 2.1762156957149736,
"grad_norm": 1.1171875,
"learning_rate": 6.928209291743416e-05,
"loss": 0.4085,
"step": 9040
},
{
"epoch": 2.1774193548387095,
"grad_norm": 1.0625,
"learning_rate": 6.921665397210058e-05,
"loss": 0.404,
"step": 9045
},
{
"epoch": 2.178623013962446,
"grad_norm": 1.1796875,
"learning_rate": 6.915128561408764e-05,
"loss": 0.4078,
"step": 9050
},
{
"epoch": 2.179826673086182,
"grad_norm": 1.1953125,
"learning_rate": 6.908598794783725e-05,
"loss": 0.387,
"step": 9055
},
{
"epoch": 2.181030332209918,
"grad_norm": 1.1640625,
"learning_rate": 6.902076107767832e-05,
"loss": 0.3812,
"step": 9060
},
{
"epoch": 2.1822339913336544,
"grad_norm": 1.1484375,
"learning_rate": 6.895560510782667e-05,
"loss": 0.4122,
"step": 9065
},
{
"epoch": 2.1834376504573907,
"grad_norm": 1.1796875,
"learning_rate": 6.889052014238485e-05,
"loss": 0.397,
"step": 9070
},
{
"epoch": 2.1846413095811266,
"grad_norm": 1.125,
"learning_rate": 6.882550628534193e-05,
"loss": 0.402,
"step": 9075
},
{
"epoch": 2.185844968704863,
"grad_norm": 1.1171875,
"learning_rate": 6.876056364057341e-05,
"loss": 0.416,
"step": 9080
},
{
"epoch": 2.1870486278285988,
"grad_norm": 1.0,
"learning_rate": 6.869569231184099e-05,
"loss": 0.3931,
"step": 9085
},
{
"epoch": 2.188252286952335,
"grad_norm": 1.15625,
"learning_rate": 6.863089240279237e-05,
"loss": 0.4056,
"step": 9090
},
{
"epoch": 2.1894559460760714,
"grad_norm": 1.1171875,
"learning_rate": 6.856616401696126e-05,
"loss": 0.4032,
"step": 9095
},
{
"epoch": 2.1906596051998073,
"grad_norm": 1.2421875,
"learning_rate": 6.850150725776697e-05,
"loss": 0.4192,
"step": 9100
},
{
"epoch": 2.1918632643235436,
"grad_norm": 1.2890625,
"learning_rate": 6.843692222851447e-05,
"loss": 0.4087,
"step": 9105
},
{
"epoch": 2.19306692344728,
"grad_norm": 1.078125,
"learning_rate": 6.837240903239406e-05,
"loss": 0.3928,
"step": 9110
},
{
"epoch": 2.194270582571016,
"grad_norm": 1.1015625,
"learning_rate": 6.83079677724813e-05,
"loss": 0.411,
"step": 9115
},
{
"epoch": 2.195474241694752,
"grad_norm": 1.21875,
"learning_rate": 6.824359855173681e-05,
"loss": 0.4334,
"step": 9120
},
{
"epoch": 2.196677900818488,
"grad_norm": 1.0625,
"learning_rate": 6.817930147300608e-05,
"loss": 0.4062,
"step": 9125
},
{
"epoch": 2.1978815599422243,
"grad_norm": 1.1640625,
"learning_rate": 6.811507663901937e-05,
"loss": 0.4079,
"step": 9130
},
{
"epoch": 2.1990852190659607,
"grad_norm": 1.0546875,
"learning_rate": 6.805092415239152e-05,
"loss": 0.4133,
"step": 9135
},
{
"epoch": 2.2002888781896965,
"grad_norm": 1.125,
"learning_rate": 6.798684411562172e-05,
"loss": 0.4149,
"step": 9140
},
{
"epoch": 2.201492537313433,
"grad_norm": 1.1953125,
"learning_rate": 6.792283663109347e-05,
"loss": 0.4132,
"step": 9145
},
{
"epoch": 2.202696196437169,
"grad_norm": 1.21875,
"learning_rate": 6.785890180107429e-05,
"loss": 0.4258,
"step": 9150
},
{
"epoch": 2.203899855560905,
"grad_norm": 1.0703125,
"learning_rate": 6.779503972771568e-05,
"loss": 0.4073,
"step": 9155
},
{
"epoch": 2.2051035146846414,
"grad_norm": 1.21875,
"learning_rate": 6.773125051305288e-05,
"loss": 0.4025,
"step": 9160
},
{
"epoch": 2.2063071738083773,
"grad_norm": 1.140625,
"learning_rate": 6.766753425900465e-05,
"loss": 0.3807,
"step": 9165
},
{
"epoch": 2.2075108329321136,
"grad_norm": 1.015625,
"learning_rate": 6.760389106737327e-05,
"loss": 0.3883,
"step": 9170
},
{
"epoch": 2.20871449205585,
"grad_norm": 1.171875,
"learning_rate": 6.754032103984421e-05,
"loss": 0.3972,
"step": 9175
},
{
"epoch": 2.209918151179586,
"grad_norm": 1.078125,
"learning_rate": 6.747682427798612e-05,
"loss": 0.3811,
"step": 9180
},
{
"epoch": 2.211121810303322,
"grad_norm": 1.296875,
"learning_rate": 6.741340088325055e-05,
"loss": 0.4075,
"step": 9185
},
{
"epoch": 2.2123254694270584,
"grad_norm": 1.1953125,
"learning_rate": 6.735005095697175e-05,
"loss": 0.3911,
"step": 9190
},
{
"epoch": 2.2135291285507943,
"grad_norm": 1.0859375,
"learning_rate": 6.728677460036675e-05,
"loss": 0.3871,
"step": 9195
},
{
"epoch": 2.2147327876745306,
"grad_norm": 1.234375,
"learning_rate": 6.72235719145349e-05,
"loss": 0.412,
"step": 9200
},
{
"epoch": 2.215936446798267,
"grad_norm": 1.2578125,
"learning_rate": 6.716044300045792e-05,
"loss": 0.3858,
"step": 9205
},
{
"epoch": 2.217140105922003,
"grad_norm": 1.109375,
"learning_rate": 6.709738795899959e-05,
"loss": 0.3828,
"step": 9210
},
{
"epoch": 2.218343765045739,
"grad_norm": 1.3046875,
"learning_rate": 6.703440689090572e-05,
"loss": 0.4583,
"step": 9215
},
{
"epoch": 2.219547424169475,
"grad_norm": 1.0859375,
"learning_rate": 6.697149989680394e-05,
"loss": 0.3934,
"step": 9220
},
{
"epoch": 2.2207510832932114,
"grad_norm": 1.109375,
"learning_rate": 6.690866707720346e-05,
"loss": 0.4065,
"step": 9225
},
{
"epoch": 2.2219547424169477,
"grad_norm": 1.2890625,
"learning_rate": 6.684590853249505e-05,
"loss": 0.4261,
"step": 9230
},
{
"epoch": 2.2231584015406836,
"grad_norm": 1.0859375,
"learning_rate": 6.678322436295073e-05,
"loss": 0.4086,
"step": 9235
},
{
"epoch": 2.22436206066442,
"grad_norm": 1.140625,
"learning_rate": 6.672061466872381e-05,
"loss": 0.3873,
"step": 9240
},
{
"epoch": 2.2255657197881558,
"grad_norm": 1.1015625,
"learning_rate": 6.665807954984848e-05,
"loss": 0.3935,
"step": 9245
},
{
"epoch": 2.226769378911892,
"grad_norm": 1.2265625,
"learning_rate": 6.659561910623981e-05,
"loss": 0.3903,
"step": 9250
},
{
"epoch": 2.2279730380356284,
"grad_norm": 1.0625,
"learning_rate": 6.653323343769362e-05,
"loss": 0.3877,
"step": 9255
},
{
"epoch": 2.2291766971593643,
"grad_norm": 1.21875,
"learning_rate": 6.647092264388618e-05,
"loss": 0.4119,
"step": 9260
},
{
"epoch": 2.2303803562831006,
"grad_norm": 1.1875,
"learning_rate": 6.64086868243742e-05,
"loss": 0.3823,
"step": 9265
},
{
"epoch": 2.231584015406837,
"grad_norm": 1.078125,
"learning_rate": 6.634652607859455e-05,
"loss": 0.3907,
"step": 9270
},
{
"epoch": 2.232787674530573,
"grad_norm": 1.0390625,
"learning_rate": 6.628444050586414e-05,
"loss": 0.3758,
"step": 9275
},
{
"epoch": 2.233991333654309,
"grad_norm": 1.0625,
"learning_rate": 6.622243020537987e-05,
"loss": 0.4156,
"step": 9280
},
{
"epoch": 2.2351949927780455,
"grad_norm": 1.078125,
"learning_rate": 6.616049527621821e-05,
"loss": 0.3866,
"step": 9285
},
{
"epoch": 2.2363986519017813,
"grad_norm": 1.28125,
"learning_rate": 6.609863581733538e-05,
"loss": 0.4107,
"step": 9290
},
{
"epoch": 2.2376023110255177,
"grad_norm": 1.125,
"learning_rate": 6.60368519275669e-05,
"loss": 0.4376,
"step": 9295
},
{
"epoch": 2.2388059701492535,
"grad_norm": 1.078125,
"learning_rate": 6.597514370562758e-05,
"loss": 0.4332,
"step": 9300
},
{
"epoch": 2.24000962927299,
"grad_norm": 1.0859375,
"learning_rate": 6.591351125011137e-05,
"loss": 0.3892,
"step": 9305
},
{
"epoch": 2.241213288396726,
"grad_norm": 1.0703125,
"learning_rate": 6.58519546594911e-05,
"loss": 0.3966,
"step": 9310
},
{
"epoch": 2.242416947520462,
"grad_norm": 1.1171875,
"learning_rate": 6.579047403211843e-05,
"loss": 0.3974,
"step": 9315
},
{
"epoch": 2.2436206066441984,
"grad_norm": 1.1875,
"learning_rate": 6.572906946622367e-05,
"loss": 0.4176,
"step": 9320
},
{
"epoch": 2.2448242657679347,
"grad_norm": 1.1953125,
"learning_rate": 6.566774105991555e-05,
"loss": 0.4012,
"step": 9325
},
{
"epoch": 2.2460279248916706,
"grad_norm": 1.203125,
"learning_rate": 6.560648891118115e-05,
"loss": 0.4174,
"step": 9330
},
{
"epoch": 2.247231584015407,
"grad_norm": 1.15625,
"learning_rate": 6.554531311788569e-05,
"loss": 0.3792,
"step": 9335
},
{
"epoch": 2.2484352431391432,
"grad_norm": 1.140625,
"learning_rate": 6.548421377777243e-05,
"loss": 0.4256,
"step": 9340
},
{
"epoch": 2.249638902262879,
"grad_norm": 1.125,
"learning_rate": 6.542319098846242e-05,
"loss": 0.4099,
"step": 9345
},
{
"epoch": 2.2508425613866154,
"grad_norm": 1.2734375,
"learning_rate": 6.536224484745446e-05,
"loss": 0.4194,
"step": 9350
},
{
"epoch": 2.2520462205103513,
"grad_norm": 1.109375,
"learning_rate": 6.530137545212485e-05,
"loss": 0.3866,
"step": 9355
},
{
"epoch": 2.2532498796340876,
"grad_norm": 1.1171875,
"learning_rate": 6.524058289972727e-05,
"loss": 0.4307,
"step": 9360
},
{
"epoch": 2.254453538757824,
"grad_norm": 1.125,
"learning_rate": 6.517986728739263e-05,
"loss": 0.3917,
"step": 9365
},
{
"epoch": 2.25565719788156,
"grad_norm": 1.0859375,
"learning_rate": 6.511922871212896e-05,
"loss": 0.3917,
"step": 9370
},
{
"epoch": 2.256860857005296,
"grad_norm": 1.046875,
"learning_rate": 6.50586672708211e-05,
"loss": 0.3924,
"step": 9375
},
{
"epoch": 2.258064516129032,
"grad_norm": 1.1875,
"learning_rate": 6.499818306023076e-05,
"loss": 0.4108,
"step": 9380
},
{
"epoch": 2.2592681752527684,
"grad_norm": 1.109375,
"learning_rate": 6.493777617699615e-05,
"loss": 0.4137,
"step": 9385
},
{
"epoch": 2.2604718343765047,
"grad_norm": 1.1953125,
"learning_rate": 6.487744671763201e-05,
"loss": 0.3925,
"step": 9390
},
{
"epoch": 2.2616754935002406,
"grad_norm": 1.2265625,
"learning_rate": 6.481719477852939e-05,
"loss": 0.3929,
"step": 9395
},
{
"epoch": 2.262879152623977,
"grad_norm": 1.1171875,
"learning_rate": 6.475702045595539e-05,
"loss": 0.3885,
"step": 9400
},
{
"epoch": 2.264082811747713,
"grad_norm": 1.1640625,
"learning_rate": 6.469692384605316e-05,
"loss": 0.3875,
"step": 9405
},
{
"epoch": 2.265286470871449,
"grad_norm": 1.1328125,
"learning_rate": 6.463690504484168e-05,
"loss": 0.3813,
"step": 9410
},
{
"epoch": 2.2664901299951854,
"grad_norm": 1.234375,
"learning_rate": 6.457696414821561e-05,
"loss": 0.4028,
"step": 9415
},
{
"epoch": 2.2676937891189217,
"grad_norm": 1.1875,
"learning_rate": 6.451710125194513e-05,
"loss": 0.407,
"step": 9420
},
{
"epoch": 2.2688974482426576,
"grad_norm": 1.140625,
"learning_rate": 6.445731645167583e-05,
"loss": 0.408,
"step": 9425
},
{
"epoch": 2.270101107366394,
"grad_norm": 1.15625,
"learning_rate": 6.439760984292848e-05,
"loss": 0.3812,
"step": 9430
},
{
"epoch": 2.27130476649013,
"grad_norm": 1.2265625,
"learning_rate": 6.43379815210989e-05,
"loss": 0.4072,
"step": 9435
},
{
"epoch": 2.272508425613866,
"grad_norm": 1.171875,
"learning_rate": 6.427843158145793e-05,
"loss": 0.3998,
"step": 9440
},
{
"epoch": 2.2737120847376024,
"grad_norm": 1.078125,
"learning_rate": 6.421896011915104e-05,
"loss": 0.3917,
"step": 9445
},
{
"epoch": 2.2749157438613383,
"grad_norm": 1.2734375,
"learning_rate": 6.415956722919843e-05,
"loss": 0.4218,
"step": 9450
},
{
"epoch": 2.2761194029850746,
"grad_norm": 1.1015625,
"learning_rate": 6.410025300649471e-05,
"loss": 0.3923,
"step": 9455
},
{
"epoch": 2.277323062108811,
"grad_norm": 1.0625,
"learning_rate": 6.404101754580875e-05,
"loss": 0.3824,
"step": 9460
},
{
"epoch": 2.278526721232547,
"grad_norm": 1.171875,
"learning_rate": 6.39818609417837e-05,
"loss": 0.3949,
"step": 9465
},
{
"epoch": 2.279730380356283,
"grad_norm": 1.1484375,
"learning_rate": 6.392278328893659e-05,
"loss": 0.4075,
"step": 9470
},
{
"epoch": 2.2809340394800195,
"grad_norm": 1.0859375,
"learning_rate": 6.386378468165839e-05,
"loss": 0.4196,
"step": 9475
},
{
"epoch": 2.2821376986037554,
"grad_norm": 1.4375,
"learning_rate": 6.380486521421378e-05,
"loss": 0.4198,
"step": 9480
},
{
"epoch": 2.2833413577274917,
"grad_norm": 1.234375,
"learning_rate": 6.37460249807409e-05,
"loss": 0.3953,
"step": 9485
},
{
"epoch": 2.2845450168512276,
"grad_norm": 1.1328125,
"learning_rate": 6.368726407525143e-05,
"loss": 0.4056,
"step": 9490
},
{
"epoch": 2.285748675974964,
"grad_norm": 1.21875,
"learning_rate": 6.362858259163018e-05,
"loss": 0.4337,
"step": 9495
},
{
"epoch": 2.2869523350987,
"grad_norm": 1.2421875,
"learning_rate": 6.356998062363514e-05,
"loss": 0.421,
"step": 9500
},
{
"epoch": 2.2869523350987,
"eval_loss": 0.3711702227592468,
"eval_runtime": 2.3967,
"eval_samples_per_second": 83.447,
"eval_steps_per_second": 83.447,
"step": 9500
},
{
"epoch": 2.288155994222436,
"grad_norm": 1.171875,
"learning_rate": 6.351145826489722e-05,
"loss": 0.3913,
"step": 9505
},
{
"epoch": 2.2893596533461724,
"grad_norm": 1.03125,
"learning_rate": 6.345301560892017e-05,
"loss": 0.3862,
"step": 9510
},
{
"epoch": 2.2905633124699083,
"grad_norm": 1.21875,
"learning_rate": 6.339465274908037e-05,
"loss": 0.3951,
"step": 9515
},
{
"epoch": 2.2917669715936446,
"grad_norm": 1.078125,
"learning_rate": 6.333636977862667e-05,
"loss": 0.4166,
"step": 9520
},
{
"epoch": 2.292970630717381,
"grad_norm": 1.0703125,
"learning_rate": 6.327816679068032e-05,
"loss": 0.3928,
"step": 9525
},
{
"epoch": 2.294174289841117,
"grad_norm": 1.1171875,
"learning_rate": 6.322004387823483e-05,
"loss": 0.4188,
"step": 9530
},
{
"epoch": 2.295377948964853,
"grad_norm": 1.171875,
"learning_rate": 6.316200113415568e-05,
"loss": 0.4166,
"step": 9535
},
{
"epoch": 2.2965816080885895,
"grad_norm": 1.1171875,
"learning_rate": 6.31040386511803e-05,
"loss": 0.4072,
"step": 9540
},
{
"epoch": 2.2977852672123253,
"grad_norm": 1.0546875,
"learning_rate": 6.304615652191786e-05,
"loss": 0.4007,
"step": 9545
},
{
"epoch": 2.2989889263360617,
"grad_norm": 1.2421875,
"learning_rate": 6.298835483884917e-05,
"loss": 0.4006,
"step": 9550
},
{
"epoch": 2.300192585459798,
"grad_norm": 1.046875,
"learning_rate": 6.293063369432653e-05,
"loss": 0.3938,
"step": 9555
},
{
"epoch": 2.301396244583534,
"grad_norm": 1.140625,
"learning_rate": 6.287299318057353e-05,
"loss": 0.4106,
"step": 9560
},
{
"epoch": 2.30259990370727,
"grad_norm": 1.21875,
"learning_rate": 6.28154333896849e-05,
"loss": 0.3769,
"step": 9565
},
{
"epoch": 2.303803562831006,
"grad_norm": 1.171875,
"learning_rate": 6.275795441362644e-05,
"loss": 0.424,
"step": 9570
},
{
"epoch": 2.3050072219547424,
"grad_norm": 1.109375,
"learning_rate": 6.270055634423482e-05,
"loss": 0.3756,
"step": 9575
},
{
"epoch": 2.3062108810784787,
"grad_norm": 1.1171875,
"learning_rate": 6.264323927321748e-05,
"loss": 0.4229,
"step": 9580
},
{
"epoch": 2.3074145402022146,
"grad_norm": 1.1015625,
"learning_rate": 6.258600329215234e-05,
"loss": 0.3925,
"step": 9585
},
{
"epoch": 2.308618199325951,
"grad_norm": 1.125,
"learning_rate": 6.25288484924879e-05,
"loss": 0.4099,
"step": 9590
},
{
"epoch": 2.3098218584496872,
"grad_norm": 1.125,
"learning_rate": 6.24717749655428e-05,
"loss": 0.4305,
"step": 9595
},
{
"epoch": 2.311025517573423,
"grad_norm": 1.109375,
"learning_rate": 6.241478280250594e-05,
"loss": 0.4097,
"step": 9600
},
{
"epoch": 2.3122291766971594,
"grad_norm": 1.1875,
"learning_rate": 6.23578720944362e-05,
"loss": 0.3966,
"step": 9605
},
{
"epoch": 2.3134328358208958,
"grad_norm": 1.1484375,
"learning_rate": 6.23010429322623e-05,
"loss": 0.3747,
"step": 9610
},
{
"epoch": 2.3146364949446316,
"grad_norm": 1.1796875,
"learning_rate": 6.224429540678268e-05,
"loss": 0.3955,
"step": 9615
},
{
"epoch": 2.315840154068368,
"grad_norm": 1.140625,
"learning_rate": 6.218762960866529e-05,
"loss": 0.4318,
"step": 9620
},
{
"epoch": 2.317043813192104,
"grad_norm": 1.140625,
"learning_rate": 6.213104562844759e-05,
"loss": 0.3901,
"step": 9625
},
{
"epoch": 2.31824747231584,
"grad_norm": 1.0703125,
"learning_rate": 6.207454355653628e-05,
"loss": 0.4159,
"step": 9630
},
{
"epoch": 2.3194511314395765,
"grad_norm": 1.109375,
"learning_rate": 6.201812348320715e-05,
"loss": 0.3858,
"step": 9635
},
{
"epoch": 2.3206547905633124,
"grad_norm": 1.1328125,
"learning_rate": 6.196178549860506e-05,
"loss": 0.3864,
"step": 9640
},
{
"epoch": 2.3218584496870487,
"grad_norm": 1.0390625,
"learning_rate": 6.190552969274362e-05,
"loss": 0.3958,
"step": 9645
},
{
"epoch": 2.3230621088107846,
"grad_norm": 1.2109375,
"learning_rate": 6.184935615550523e-05,
"loss": 0.4007,
"step": 9650
},
{
"epoch": 2.324265767934521,
"grad_norm": 1.1015625,
"learning_rate": 6.179326497664076e-05,
"loss": 0.3984,
"step": 9655
},
{
"epoch": 2.325469427058257,
"grad_norm": 1.2109375,
"learning_rate": 6.173725624576958e-05,
"loss": 0.3919,
"step": 9660
},
{
"epoch": 2.326673086181993,
"grad_norm": 1.125,
"learning_rate": 6.168133005237925e-05,
"loss": 0.3825,
"step": 9665
},
{
"epoch": 2.3278767453057294,
"grad_norm": 1.234375,
"learning_rate": 6.162548648582552e-05,
"loss": 0.4195,
"step": 9670
},
{
"epoch": 2.3290804044294657,
"grad_norm": 1.125,
"learning_rate": 6.156972563533207e-05,
"loss": 0.4048,
"step": 9675
},
{
"epoch": 2.3302840635532016,
"grad_norm": 1.1328125,
"learning_rate": 6.151404758999041e-05,
"loss": 0.3994,
"step": 9680
},
{
"epoch": 2.331487722676938,
"grad_norm": 1.125,
"learning_rate": 6.145845243875986e-05,
"loss": 0.4194,
"step": 9685
},
{
"epoch": 2.3326913818006743,
"grad_norm": 1.0859375,
"learning_rate": 6.140294027046718e-05,
"loss": 0.3838,
"step": 9690
},
{
"epoch": 2.33389504092441,
"grad_norm": 1.171875,
"learning_rate": 6.134751117380658e-05,
"loss": 0.3954,
"step": 9695
},
{
"epoch": 2.3350987000481465,
"grad_norm": 1.0859375,
"learning_rate": 6.129216523733955e-05,
"loss": 0.4078,
"step": 9700
},
{
"epoch": 2.3363023591718823,
"grad_norm": 1.1328125,
"learning_rate": 6.123690254949472e-05,
"loss": 0.3872,
"step": 9705
},
{
"epoch": 2.3375060182956187,
"grad_norm": 1.1953125,
"learning_rate": 6.118172319856768e-05,
"loss": 0.3944,
"step": 9710
},
{
"epoch": 2.338709677419355,
"grad_norm": 1.140625,
"learning_rate": 6.112662727272092e-05,
"loss": 0.3888,
"step": 9715
},
{
"epoch": 2.339913336543091,
"grad_norm": 1.1015625,
"learning_rate": 6.107161485998356e-05,
"loss": 0.3875,
"step": 9720
},
{
"epoch": 2.341116995666827,
"grad_norm": 1.1796875,
"learning_rate": 6.10166860482514e-05,
"loss": 0.3993,
"step": 9725
},
{
"epoch": 2.3423206547905635,
"grad_norm": 1.1328125,
"learning_rate": 6.0961840925286505e-05,
"loss": 0.4037,
"step": 9730
},
{
"epoch": 2.3435243139142994,
"grad_norm": 1.1015625,
"learning_rate": 6.090707957871739e-05,
"loss": 0.4084,
"step": 9735
},
{
"epoch": 2.3447279730380357,
"grad_norm": 1.125,
"learning_rate": 6.085240209603864e-05,
"loss": 0.3996,
"step": 9740
},
{
"epoch": 2.345931632161772,
"grad_norm": 1.125,
"learning_rate": 6.0797808564610835e-05,
"loss": 0.3843,
"step": 9745
},
{
"epoch": 2.347135291285508,
"grad_norm": 1.21875,
"learning_rate": 6.074329907166048e-05,
"loss": 0.4346,
"step": 9750
},
{
"epoch": 2.3483389504092442,
"grad_norm": 1.1328125,
"learning_rate": 6.068887370427973e-05,
"loss": 0.3709,
"step": 9755
},
{
"epoch": 2.34954260953298,
"grad_norm": 1.109375,
"learning_rate": 6.0634532549426374e-05,
"loss": 0.3787,
"step": 9760
},
{
"epoch": 2.3507462686567164,
"grad_norm": 1.2578125,
"learning_rate": 6.058027569392368e-05,
"loss": 0.397,
"step": 9765
},
{
"epoch": 2.3519499277804528,
"grad_norm": 1.0625,
"learning_rate": 6.052610322446018e-05,
"loss": 0.3798,
"step": 9770
},
{
"epoch": 2.3531535869041886,
"grad_norm": 1.2890625,
"learning_rate": 6.047201522758959e-05,
"loss": 0.3975,
"step": 9775
},
{
"epoch": 2.354357246027925,
"grad_norm": 1.171875,
"learning_rate": 6.041801178973063e-05,
"loss": 0.3933,
"step": 9780
},
{
"epoch": 2.355560905151661,
"grad_norm": 1.09375,
"learning_rate": 6.0364092997167e-05,
"loss": 0.4018,
"step": 9785
},
{
"epoch": 2.356764564275397,
"grad_norm": 1.2109375,
"learning_rate": 6.0310258936047094e-05,
"loss": 0.4337,
"step": 9790
},
{
"epoch": 2.3579682233991335,
"grad_norm": 1.1015625,
"learning_rate": 6.0256509692383914e-05,
"loss": 0.3952,
"step": 9795
},
{
"epoch": 2.3591718825228694,
"grad_norm": 1.1640625,
"learning_rate": 6.020284535205502e-05,
"loss": 0.3888,
"step": 9800
},
{
"epoch": 2.3603755416466057,
"grad_norm": 1.0703125,
"learning_rate": 6.014926600080223e-05,
"loss": 0.3849,
"step": 9805
},
{
"epoch": 2.361579200770342,
"grad_norm": 1.2265625,
"learning_rate": 6.0095771724231624e-05,
"loss": 0.3895,
"step": 9810
},
{
"epoch": 2.362782859894078,
"grad_norm": 1.078125,
"learning_rate": 6.004236260781337e-05,
"loss": 0.4174,
"step": 9815
},
{
"epoch": 2.363986519017814,
"grad_norm": 1.1171875,
"learning_rate": 5.998903873688149e-05,
"loss": 0.4015,
"step": 9820
},
{
"epoch": 2.3651901781415505,
"grad_norm": 1.109375,
"learning_rate": 5.993580019663392e-05,
"loss": 0.4158,
"step": 9825
},
{
"epoch": 2.3663938372652864,
"grad_norm": 1.0390625,
"learning_rate": 5.988264707213218e-05,
"loss": 0.3738,
"step": 9830
},
{
"epoch": 2.3675974963890227,
"grad_norm": 1.109375,
"learning_rate": 5.9829579448301284e-05,
"loss": 0.4382,
"step": 9835
},
{
"epoch": 2.3688011555127586,
"grad_norm": 1.09375,
"learning_rate": 5.9776597409929765e-05,
"loss": 0.401,
"step": 9840
},
{
"epoch": 2.370004814636495,
"grad_norm": 1.1875,
"learning_rate": 5.9723701041669286e-05,
"loss": 0.3907,
"step": 9845
},
{
"epoch": 2.3712084737602313,
"grad_norm": 1.234375,
"learning_rate": 5.967089042803473e-05,
"loss": 0.4297,
"step": 9850
},
{
"epoch": 2.372412132883967,
"grad_norm": 1.0390625,
"learning_rate": 5.961816565340387e-05,
"loss": 0.3821,
"step": 9855
},
{
"epoch": 2.3736157920077035,
"grad_norm": 1.078125,
"learning_rate": 5.956552680201741e-05,
"loss": 0.3814,
"step": 9860
},
{
"epoch": 2.3748194511314393,
"grad_norm": 1.140625,
"learning_rate": 5.9512973957978736e-05,
"loss": 0.395,
"step": 9865
},
{
"epoch": 2.3760231102551757,
"grad_norm": 1.234375,
"learning_rate": 5.946050720525381e-05,
"loss": 0.3967,
"step": 9870
},
{
"epoch": 2.377226769378912,
"grad_norm": 1.28125,
"learning_rate": 5.940812662767108e-05,
"loss": 0.3961,
"step": 9875
},
{
"epoch": 2.3784304285026483,
"grad_norm": 1.15625,
"learning_rate": 5.935583230892127e-05,
"loss": 0.4415,
"step": 9880
},
{
"epoch": 2.379634087626384,
"grad_norm": 1.171875,
"learning_rate": 5.930362433255728e-05,
"loss": 0.3949,
"step": 9885
},
{
"epoch": 2.3808377467501205,
"grad_norm": 1.234375,
"learning_rate": 5.925150278199407e-05,
"loss": 0.3874,
"step": 9890
},
{
"epoch": 2.3820414058738564,
"grad_norm": 1.125,
"learning_rate": 5.9199467740508536e-05,
"loss": 0.428,
"step": 9895
},
{
"epoch": 2.3832450649975927,
"grad_norm": 1.1796875,
"learning_rate": 5.914751929123933e-05,
"loss": 0.3851,
"step": 9900
},
{
"epoch": 2.384448724121329,
"grad_norm": 1.1875,
"learning_rate": 5.9095657517186743e-05,
"loss": 0.3884,
"step": 9905
},
{
"epoch": 2.385652383245065,
"grad_norm": 1.2265625,
"learning_rate": 5.9043882501212613e-05,
"loss": 0.392,
"step": 9910
},
{
"epoch": 2.3868560423688012,
"grad_norm": 1.125,
"learning_rate": 5.899219432604012e-05,
"loss": 0.4125,
"step": 9915
},
{
"epoch": 2.388059701492537,
"grad_norm": 1.1171875,
"learning_rate": 5.8940593074253744e-05,
"loss": 0.3937,
"step": 9920
},
{
"epoch": 2.3892633606162734,
"grad_norm": 1.15625,
"learning_rate": 5.888907882829906e-05,
"loss": 0.3936,
"step": 9925
},
{
"epoch": 2.3904670197400097,
"grad_norm": 1.1796875,
"learning_rate": 5.8837651670482604e-05,
"loss": 0.3803,
"step": 9930
},
{
"epoch": 2.3916706788637456,
"grad_norm": 1.078125,
"learning_rate": 5.878631168297181e-05,
"loss": 0.3818,
"step": 9935
},
{
"epoch": 2.392874337987482,
"grad_norm": 1.2890625,
"learning_rate": 5.873505894779479e-05,
"loss": 0.383,
"step": 9940
},
{
"epoch": 2.3940779971112183,
"grad_norm": 1.203125,
"learning_rate": 5.8683893546840286e-05,
"loss": 0.3882,
"step": 9945
},
{
"epoch": 2.395281656234954,
"grad_norm": 1.125,
"learning_rate": 5.863281556185752e-05,
"loss": 0.4125,
"step": 9950
},
{
"epoch": 2.3964853153586905,
"grad_norm": 1.1953125,
"learning_rate": 5.858182507445598e-05,
"loss": 0.3848,
"step": 9955
},
{
"epoch": 2.397688974482427,
"grad_norm": 1.109375,
"learning_rate": 5.853092216610542e-05,
"loss": 0.4149,
"step": 9960
},
{
"epoch": 2.3988926336061627,
"grad_norm": 1.1796875,
"learning_rate": 5.8480106918135636e-05,
"loss": 0.4103,
"step": 9965
},
{
"epoch": 2.400096292729899,
"grad_norm": 1.203125,
"learning_rate": 5.842937941173635e-05,
"loss": 0.3975,
"step": 9970
},
{
"epoch": 2.401299951853635,
"grad_norm": 1.171875,
"learning_rate": 5.837873972795713e-05,
"loss": 0.4351,
"step": 9975
},
{
"epoch": 2.402503610977371,
"grad_norm": 1.125,
"learning_rate": 5.832818794770718e-05,
"loss": 0.3843,
"step": 9980
},
{
"epoch": 2.4037072701011075,
"grad_norm": 1.1953125,
"learning_rate": 5.8277724151755356e-05,
"loss": 0.4056,
"step": 9985
},
{
"epoch": 2.4049109292248434,
"grad_norm": 1.0390625,
"learning_rate": 5.8227348420729805e-05,
"loss": 0.3652,
"step": 9990
},
{
"epoch": 2.4061145883485797,
"grad_norm": 1.1875,
"learning_rate": 5.8177060835118026e-05,
"loss": 0.3646,
"step": 9995
},
{
"epoch": 2.4073182474723156,
"grad_norm": 1.1640625,
"learning_rate": 5.812686147526673e-05,
"loss": 0.4058,
"step": 10000
},
{
"epoch": 2.4073182474723156,
"eval_loss": 0.36641818284988403,
"eval_runtime": 2.3939,
"eval_samples_per_second": 83.545,
"eval_steps_per_second": 83.545,
"step": 10000
},
{
"epoch": 2.408521906596052,
"grad_norm": 1.109375,
"learning_rate": 5.8076750421381594e-05,
"loss": 0.3825,
"step": 10005
},
{
"epoch": 2.4097255657197882,
"grad_norm": 1.109375,
"learning_rate": 5.802672775352725e-05,
"loss": 0.3807,
"step": 10010
},
{
"epoch": 2.410929224843524,
"grad_norm": 1.0625,
"learning_rate": 5.7976793551627094e-05,
"loss": 0.392,
"step": 10015
},
{
"epoch": 2.4121328839672604,
"grad_norm": 1.1796875,
"learning_rate": 5.7926947895463165e-05,
"loss": 0.392,
"step": 10020
},
{
"epoch": 2.4133365430909968,
"grad_norm": 1.2421875,
"learning_rate": 5.787719086467608e-05,
"loss": 0.3858,
"step": 10025
},
{
"epoch": 2.4145402022147326,
"grad_norm": 1.09375,
"learning_rate": 5.782752253876479e-05,
"loss": 0.4164,
"step": 10030
},
{
"epoch": 2.415743861338469,
"grad_norm": 1.0859375,
"learning_rate": 5.777794299708658e-05,
"loss": 0.3956,
"step": 10035
},
{
"epoch": 2.4169475204622053,
"grad_norm": 1.203125,
"learning_rate": 5.772845231885681e-05,
"loss": 0.3958,
"step": 10040
},
{
"epoch": 2.418151179585941,
"grad_norm": 1.2265625,
"learning_rate": 5.767905058314889e-05,
"loss": 0.424,
"step": 10045
},
{
"epoch": 2.4193548387096775,
"grad_norm": 1.3046875,
"learning_rate": 5.762973786889418e-05,
"loss": 0.4156,
"step": 10050
},
{
"epoch": 2.4205584978334134,
"grad_norm": 1.171875,
"learning_rate": 5.75805142548817e-05,
"loss": 0.39,
"step": 10055
},
{
"epoch": 2.4217621569571497,
"grad_norm": 1.203125,
"learning_rate": 5.7531379819758214e-05,
"loss": 0.4127,
"step": 10060
},
{
"epoch": 2.422965816080886,
"grad_norm": 1.140625,
"learning_rate": 5.748233464202791e-05,
"loss": 0.3849,
"step": 10065
},
{
"epoch": 2.424169475204622,
"grad_norm": 1.171875,
"learning_rate": 5.743337880005243e-05,
"loss": 0.3841,
"step": 10070
},
{
"epoch": 2.425373134328358,
"grad_norm": 1.1640625,
"learning_rate": 5.738451237205068e-05,
"loss": 0.3903,
"step": 10075
},
{
"epoch": 2.4265767934520945,
"grad_norm": 1.203125,
"learning_rate": 5.7335735436098656e-05,
"loss": 0.3989,
"step": 10080
},
{
"epoch": 2.4277804525758304,
"grad_norm": 1.203125,
"learning_rate": 5.72870480701294e-05,
"loss": 0.3997,
"step": 10085
},
{
"epoch": 2.4289841116995667,
"grad_norm": 1.0703125,
"learning_rate": 5.723845035193287e-05,
"loss": 0.3758,
"step": 10090
},
{
"epoch": 2.430187770823303,
"grad_norm": 1.171875,
"learning_rate": 5.718994235915571e-05,
"loss": 0.3731,
"step": 10095
},
{
"epoch": 2.431391429947039,
"grad_norm": 1.1640625,
"learning_rate": 5.714152416930132e-05,
"loss": 0.4003,
"step": 10100
},
{
"epoch": 2.4325950890707753,
"grad_norm": 1.1328125,
"learning_rate": 5.709319585972951e-05,
"loss": 0.4216,
"step": 10105
},
{
"epoch": 2.433798748194511,
"grad_norm": 1.0234375,
"learning_rate": 5.704495750765654e-05,
"loss": 0.382,
"step": 10110
},
{
"epoch": 2.4350024073182475,
"grad_norm": 1.2265625,
"learning_rate": 5.6996809190154927e-05,
"loss": 0.4103,
"step": 10115
},
{
"epoch": 2.436206066441984,
"grad_norm": 1.1875,
"learning_rate": 5.694875098415336e-05,
"loss": 0.3976,
"step": 10120
},
{
"epoch": 2.4374097255657197,
"grad_norm": 1.125,
"learning_rate": 5.6900782966436505e-05,
"loss": 0.3941,
"step": 10125
},
{
"epoch": 2.438613384689456,
"grad_norm": 1.109375,
"learning_rate": 5.685290521364497e-05,
"loss": 0.3954,
"step": 10130
},
{
"epoch": 2.439817043813192,
"grad_norm": 1.28125,
"learning_rate": 5.6805117802275146e-05,
"loss": 0.3974,
"step": 10135
},
{
"epoch": 2.441020702936928,
"grad_norm": 1.203125,
"learning_rate": 5.675742080867903e-05,
"loss": 0.3952,
"step": 10140
},
{
"epoch": 2.4422243620606645,
"grad_norm": 1.171875,
"learning_rate": 5.670981430906424e-05,
"loss": 0.4087,
"step": 10145
},
{
"epoch": 2.4434280211844004,
"grad_norm": 1.1015625,
"learning_rate": 5.666229837949371e-05,
"loss": 0.4009,
"step": 10150
},
{
"epoch": 2.4446316803081367,
"grad_norm": 1.1171875,
"learning_rate": 5.6614873095885734e-05,
"loss": 0.3799,
"step": 10155
},
{
"epoch": 2.445835339431873,
"grad_norm": 1.21875,
"learning_rate": 5.6567538534013765e-05,
"loss": 0.418,
"step": 10160
},
{
"epoch": 2.447038998555609,
"grad_norm": 1.1875,
"learning_rate": 5.652029476950628e-05,
"loss": 0.3949,
"step": 10165
},
{
"epoch": 2.4482426576793452,
"grad_norm": 1.1328125,
"learning_rate": 5.6473141877846724e-05,
"loss": 0.4035,
"step": 10170
},
{
"epoch": 2.4494463168030816,
"grad_norm": 1.1796875,
"learning_rate": 5.642607993437333e-05,
"loss": 0.4067,
"step": 10175
},
{
"epoch": 2.4506499759268174,
"grad_norm": 1.1875,
"learning_rate": 5.6379109014278985e-05,
"loss": 0.4057,
"step": 10180
},
{
"epoch": 2.4518536350505538,
"grad_norm": 1.1328125,
"learning_rate": 5.633222919261122e-05,
"loss": 0.3889,
"step": 10185
},
{
"epoch": 2.4530572941742896,
"grad_norm": 1.0859375,
"learning_rate": 5.6285440544271955e-05,
"loss": 0.3872,
"step": 10190
},
{
"epoch": 2.454260953298026,
"grad_norm": 1.0703125,
"learning_rate": 5.623874314401746e-05,
"loss": 0.4022,
"step": 10195
},
{
"epoch": 2.4554646124217623,
"grad_norm": 1.1171875,
"learning_rate": 5.619213706645821e-05,
"loss": 0.3894,
"step": 10200
},
{
"epoch": 2.456668271545498,
"grad_norm": 1.2265625,
"learning_rate": 5.614562238605875e-05,
"loss": 0.3941,
"step": 10205
},
{
"epoch": 2.4578719306692345,
"grad_norm": 1.1484375,
"learning_rate": 5.609919917713765e-05,
"loss": 0.3998,
"step": 10210
},
{
"epoch": 2.459075589792971,
"grad_norm": 1.203125,
"learning_rate": 5.605286751386726e-05,
"loss": 0.424,
"step": 10215
},
{
"epoch": 2.4602792489167067,
"grad_norm": 1.1015625,
"learning_rate": 5.600662747027373e-05,
"loss": 0.4156,
"step": 10220
},
{
"epoch": 2.461482908040443,
"grad_norm": 1.1640625,
"learning_rate": 5.596047912023678e-05,
"loss": 0.3905,
"step": 10225
},
{
"epoch": 2.4626865671641793,
"grad_norm": 1.1875,
"learning_rate": 5.591442253748964e-05,
"loss": 0.3959,
"step": 10230
},
{
"epoch": 2.463890226287915,
"grad_norm": 1.203125,
"learning_rate": 5.5868457795618946e-05,
"loss": 0.3953,
"step": 10235
},
{
"epoch": 2.4650938854116515,
"grad_norm": 1.1328125,
"learning_rate": 5.582258496806455e-05,
"loss": 0.3779,
"step": 10240
},
{
"epoch": 2.4662975445353874,
"grad_norm": 1.1328125,
"learning_rate": 5.5776804128119475e-05,
"loss": 0.4194,
"step": 10245
},
{
"epoch": 2.4675012036591237,
"grad_norm": 1.15625,
"learning_rate": 5.573111534892978e-05,
"loss": 0.3878,
"step": 10250
},
{
"epoch": 2.46870486278286,
"grad_norm": 1.1875,
"learning_rate": 5.5685518703494395e-05,
"loss": 0.4049,
"step": 10255
},
{
"epoch": 2.469908521906596,
"grad_norm": 1.09375,
"learning_rate": 5.564001426466511e-05,
"loss": 0.4012,
"step": 10260
},
{
"epoch": 2.4711121810303323,
"grad_norm": 1.1328125,
"learning_rate": 5.5594602105146296e-05,
"loss": 0.4015,
"step": 10265
},
{
"epoch": 2.472315840154068,
"grad_norm": 1.203125,
"learning_rate": 5.5549282297495004e-05,
"loss": 0.4032,
"step": 10270
},
{
"epoch": 2.4735194992778045,
"grad_norm": 1.203125,
"learning_rate": 5.550405491412062e-05,
"loss": 0.4149,
"step": 10275
},
{
"epoch": 2.474723158401541,
"grad_norm": 1.109375,
"learning_rate": 5.5458920027284944e-05,
"loss": 0.3948,
"step": 10280
},
{
"epoch": 2.4759268175252767,
"grad_norm": 1.1953125,
"learning_rate": 5.541387770910194e-05,
"loss": 0.3952,
"step": 10285
},
{
"epoch": 2.477130476649013,
"grad_norm": 1.21875,
"learning_rate": 5.536892803153768e-05,
"loss": 0.3861,
"step": 10290
},
{
"epoch": 2.4783341357727493,
"grad_norm": 1.2109375,
"learning_rate": 5.5324071066410244e-05,
"loss": 0.3851,
"step": 10295
},
{
"epoch": 2.479537794896485,
"grad_norm": 1.046875,
"learning_rate": 5.527930688538955e-05,
"loss": 0.39,
"step": 10300
},
{
"epoch": 2.4807414540202215,
"grad_norm": 1.21875,
"learning_rate": 5.523463555999728e-05,
"loss": 0.4146,
"step": 10305
},
{
"epoch": 2.481945113143958,
"grad_norm": 1.15625,
"learning_rate": 5.519005716160677e-05,
"loss": 0.374,
"step": 10310
},
{
"epoch": 2.4831487722676937,
"grad_norm": 1.2109375,
"learning_rate": 5.514557176144285e-05,
"loss": 0.4023,
"step": 10315
},
{
"epoch": 2.48435243139143,
"grad_norm": 1.1640625,
"learning_rate": 5.510117943058183e-05,
"loss": 0.3898,
"step": 10320
},
{
"epoch": 2.485556090515166,
"grad_norm": 1.15625,
"learning_rate": 5.505688023995122e-05,
"loss": 0.4129,
"step": 10325
},
{
"epoch": 2.4867597496389022,
"grad_norm": 1.109375,
"learning_rate": 5.50126742603298e-05,
"loss": 0.3818,
"step": 10330
},
{
"epoch": 2.4879634087626386,
"grad_norm": 1.140625,
"learning_rate": 5.496856156234742e-05,
"loss": 0.3979,
"step": 10335
},
{
"epoch": 2.4891670678863744,
"grad_norm": 1.2578125,
"learning_rate": 5.492454221648481e-05,
"loss": 0.3965,
"step": 10340
},
{
"epoch": 2.4903707270101108,
"grad_norm": 1.1328125,
"learning_rate": 5.488061629307364e-05,
"loss": 0.4336,
"step": 10345
},
{
"epoch": 2.491574386133847,
"grad_norm": 1.1171875,
"learning_rate": 5.483678386229625e-05,
"loss": 0.3737,
"step": 10350
},
{
"epoch": 2.492778045257583,
"grad_norm": 1.2265625,
"learning_rate": 5.4793044994185646e-05,
"loss": 0.391,
"step": 10355
},
{
"epoch": 2.4939817043813193,
"grad_norm": 1.0859375,
"learning_rate": 5.474939975862532e-05,
"loss": 0.4015,
"step": 10360
},
{
"epoch": 2.4951853635050556,
"grad_norm": 1.1953125,
"learning_rate": 5.470584822534917e-05,
"loss": 0.4185,
"step": 10365
},
{
"epoch": 2.4963890226287915,
"grad_norm": 1.1796875,
"learning_rate": 5.466239046394138e-05,
"loss": 0.4132,
"step": 10370
},
{
"epoch": 2.497592681752528,
"grad_norm": 1.15625,
"learning_rate": 5.461902654383629e-05,
"loss": 0.4081,
"step": 10375
},
{
"epoch": 2.4987963408762637,
"grad_norm": 1.3359375,
"learning_rate": 5.4575756534318385e-05,
"loss": 0.3876,
"step": 10380
},
{
"epoch": 2.5,
"grad_norm": 1.1875,
"learning_rate": 5.453258050452198e-05,
"loss": 0.4256,
"step": 10385
},
{
"epoch": 2.5012036591237363,
"grad_norm": 1.125,
"learning_rate": 5.4489498523431344e-05,
"loss": 0.3719,
"step": 10390
},
{
"epoch": 2.502407318247472,
"grad_norm": 1.203125,
"learning_rate": 5.444651065988045e-05,
"loss": 0.4402,
"step": 10395
},
{
"epoch": 2.5036109773712085,
"grad_norm": 1.078125,
"learning_rate": 5.4403616982552844e-05,
"loss": 0.3807,
"step": 10400
},
{
"epoch": 2.5048146364949444,
"grad_norm": 1.140625,
"learning_rate": 5.436081755998166e-05,
"loss": 0.3837,
"step": 10405
},
{
"epoch": 2.5060182956186807,
"grad_norm": 1.078125,
"learning_rate": 5.431811246054939e-05,
"loss": 0.3918,
"step": 10410
},
{
"epoch": 2.507221954742417,
"grad_norm": 1.1484375,
"learning_rate": 5.427550175248782e-05,
"loss": 0.3935,
"step": 10415
},
{
"epoch": 2.5084256138661534,
"grad_norm": 1.1171875,
"learning_rate": 5.423298550387798e-05,
"loss": 0.3998,
"step": 10420
},
{
"epoch": 2.5096292729898892,
"grad_norm": 1.21875,
"learning_rate": 5.419056378264988e-05,
"loss": 0.4105,
"step": 10425
},
{
"epoch": 2.5108329321136256,
"grad_norm": 1.203125,
"learning_rate": 5.4148236656582606e-05,
"loss": 0.4108,
"step": 10430
},
{
"epoch": 2.5120365912373614,
"grad_norm": 1.1328125,
"learning_rate": 5.4106004193304016e-05,
"loss": 0.3828,
"step": 10435
},
{
"epoch": 2.5132402503610978,
"grad_norm": 1.203125,
"learning_rate": 5.406386646029078e-05,
"loss": 0.3813,
"step": 10440
},
{
"epoch": 2.514443909484834,
"grad_norm": 1.21875,
"learning_rate": 5.4021823524868216e-05,
"loss": 0.4137,
"step": 10445
},
{
"epoch": 2.51564756860857,
"grad_norm": 1.125,
"learning_rate": 5.397987545421011e-05,
"loss": 0.3782,
"step": 10450
},
{
"epoch": 2.5168512277323063,
"grad_norm": 1.2265625,
"learning_rate": 5.393802231533876e-05,
"loss": 0.3988,
"step": 10455
},
{
"epoch": 2.518054886856042,
"grad_norm": 1.203125,
"learning_rate": 5.389626417512473e-05,
"loss": 0.3872,
"step": 10460
},
{
"epoch": 2.5192585459797785,
"grad_norm": 1.25,
"learning_rate": 5.3854601100286845e-05,
"loss": 0.3967,
"step": 10465
},
{
"epoch": 2.520462205103515,
"grad_norm": 1.0625,
"learning_rate": 5.3813033157391994e-05,
"loss": 0.3891,
"step": 10470
},
{
"epoch": 2.5216658642272507,
"grad_norm": 1.21875,
"learning_rate": 5.3771560412855116e-05,
"loss": 0.4044,
"step": 10475
},
{
"epoch": 2.522869523350987,
"grad_norm": 1.1875,
"learning_rate": 5.373018293293902e-05,
"loss": 0.3816,
"step": 10480
},
{
"epoch": 2.524073182474723,
"grad_norm": 1.1796875,
"learning_rate": 5.368890078375429e-05,
"loss": 0.3851,
"step": 10485
},
{
"epoch": 2.525276841598459,
"grad_norm": 1.2265625,
"learning_rate": 5.364771403125924e-05,
"loss": 0.3807,
"step": 10490
},
{
"epoch": 2.5264805007221955,
"grad_norm": 1.0859375,
"learning_rate": 5.3606622741259745e-05,
"loss": 0.3809,
"step": 10495
},
{
"epoch": 2.527684159845932,
"grad_norm": 1.046875,
"learning_rate": 5.356562697940913e-05,
"loss": 0.384,
"step": 10500
},
{
"epoch": 2.527684159845932,
"eval_loss": 0.363790363073349,
"eval_runtime": 2.4019,
"eval_samples_per_second": 83.267,
"eval_steps_per_second": 83.267,
"step": 10500
},
{
"epoch": 2.5288878189696677,
"grad_norm": 1.203125,
"learning_rate": 5.3524726811208153e-05,
"loss": 0.3944,
"step": 10505
},
{
"epoch": 2.530091478093404,
"grad_norm": 1.171875,
"learning_rate": 5.348392230200476e-05,
"loss": 0.4003,
"step": 10510
},
{
"epoch": 2.53129513721714,
"grad_norm": 1.15625,
"learning_rate": 5.344321351699411e-05,
"loss": 0.3861,
"step": 10515
},
{
"epoch": 2.5324987963408763,
"grad_norm": 1.2421875,
"learning_rate": 5.340260052121841e-05,
"loss": 0.3834,
"step": 10520
},
{
"epoch": 2.5337024554646126,
"grad_norm": 1.1015625,
"learning_rate": 5.3362083379566796e-05,
"loss": 0.3901,
"step": 10525
},
{
"epoch": 2.5349061145883485,
"grad_norm": 1.1953125,
"learning_rate": 5.3321662156775306e-05,
"loss": 0.367,
"step": 10530
},
{
"epoch": 2.536109773712085,
"grad_norm": 1.0859375,
"learning_rate": 5.3281336917426657e-05,
"loss": 0.3956,
"step": 10535
},
{
"epoch": 2.5373134328358207,
"grad_norm": 1.15625,
"learning_rate": 5.324110772595028e-05,
"loss": 0.3953,
"step": 10540
},
{
"epoch": 2.538517091959557,
"grad_norm": 1.1484375,
"learning_rate": 5.320097464662208e-05,
"loss": 0.3922,
"step": 10545
},
{
"epoch": 2.5397207510832933,
"grad_norm": 1.2109375,
"learning_rate": 5.316093774356444e-05,
"loss": 0.3925,
"step": 10550
},
{
"epoch": 2.5409244102070296,
"grad_norm": 1.2265625,
"learning_rate": 5.3120997080746086e-05,
"loss": 0.4013,
"step": 10555
},
{
"epoch": 2.5421280693307655,
"grad_norm": 1.265625,
"learning_rate": 5.3081152721981914e-05,
"loss": 0.3857,
"step": 10560
},
{
"epoch": 2.543331728454502,
"grad_norm": 1.1328125,
"learning_rate": 5.304140473093304e-05,
"loss": 0.3848,
"step": 10565
},
{
"epoch": 2.5445353875782377,
"grad_norm": 1.296875,
"learning_rate": 5.3001753171106526e-05,
"loss": 0.3886,
"step": 10570
},
{
"epoch": 2.545739046701974,
"grad_norm": 1.109375,
"learning_rate": 5.2962198105855456e-05,
"loss": 0.3627,
"step": 10575
},
{
"epoch": 2.5469427058257104,
"grad_norm": 1.0703125,
"learning_rate": 5.2922739598378634e-05,
"loss": 0.4065,
"step": 10580
},
{
"epoch": 2.5481463649494462,
"grad_norm": 1.140625,
"learning_rate": 5.288337771172064e-05,
"loss": 0.4338,
"step": 10585
},
{
"epoch": 2.5493500240731826,
"grad_norm": 1.2265625,
"learning_rate": 5.2844112508771706e-05,
"loss": 0.4,
"step": 10590
},
{
"epoch": 2.5505536831969184,
"grad_norm": 1.078125,
"learning_rate": 5.280494405226753e-05,
"loss": 0.4274,
"step": 10595
},
{
"epoch": 2.5517573423206548,
"grad_norm": 1.125,
"learning_rate": 5.27658724047893e-05,
"loss": 0.3895,
"step": 10600
},
{
"epoch": 2.552961001444391,
"grad_norm": 1.4140625,
"learning_rate": 5.2726897628763484e-05,
"loss": 0.4171,
"step": 10605
},
{
"epoch": 2.554164660568127,
"grad_norm": 1.2109375,
"learning_rate": 5.268801978646174e-05,
"loss": 0.379,
"step": 10610
},
{
"epoch": 2.5553683196918633,
"grad_norm": 1.21875,
"learning_rate": 5.264923894000096e-05,
"loss": 0.3883,
"step": 10615
},
{
"epoch": 2.556571978815599,
"grad_norm": 1.125,
"learning_rate": 5.261055515134293e-05,
"loss": 0.377,
"step": 10620
},
{
"epoch": 2.5577756379393355,
"grad_norm": 1.140625,
"learning_rate": 5.257196848229449e-05,
"loss": 0.3833,
"step": 10625
},
{
"epoch": 2.558979297063072,
"grad_norm": 1.125,
"learning_rate": 5.25334789945072e-05,
"loss": 0.4117,
"step": 10630
},
{
"epoch": 2.560182956186808,
"grad_norm": 1.125,
"learning_rate": 5.2495086749477405e-05,
"loss": 0.403,
"step": 10635
},
{
"epoch": 2.561386615310544,
"grad_norm": 1.125,
"learning_rate": 5.245679180854609e-05,
"loss": 0.3941,
"step": 10640
},
{
"epoch": 2.5625902744342803,
"grad_norm": 1.0078125,
"learning_rate": 5.2418594232898726e-05,
"loss": 0.4176,
"step": 10645
},
{
"epoch": 2.563793933558016,
"grad_norm": 1.09375,
"learning_rate": 5.238049408356525e-05,
"loss": 0.385,
"step": 10650
},
{
"epoch": 2.5649975926817525,
"grad_norm": 1.109375,
"learning_rate": 5.2342491421419956e-05,
"loss": 0.3962,
"step": 10655
},
{
"epoch": 2.566201251805489,
"grad_norm": 1.0625,
"learning_rate": 5.230458630718134e-05,
"loss": 0.3933,
"step": 10660
},
{
"epoch": 2.5674049109292247,
"grad_norm": 1.2421875,
"learning_rate": 5.226677880141207e-05,
"loss": 0.4155,
"step": 10665
},
{
"epoch": 2.568608570052961,
"grad_norm": 1.1171875,
"learning_rate": 5.2229068964518826e-05,
"loss": 0.4007,
"step": 10670
},
{
"epoch": 2.569812229176697,
"grad_norm": 1.1328125,
"learning_rate": 5.219145685675229e-05,
"loss": 0.3848,
"step": 10675
},
{
"epoch": 2.5710158883004333,
"grad_norm": 1.140625,
"learning_rate": 5.2153942538206934e-05,
"loss": 0.3625,
"step": 10680
},
{
"epoch": 2.5722195474241696,
"grad_norm": 1.1640625,
"learning_rate": 5.211652606882104e-05,
"loss": 0.3854,
"step": 10685
},
{
"epoch": 2.573423206547906,
"grad_norm": 1.2109375,
"learning_rate": 5.2079207508376544e-05,
"loss": 0.4038,
"step": 10690
},
{
"epoch": 2.574626865671642,
"grad_norm": 1.1171875,
"learning_rate": 5.2041986916498915e-05,
"loss": 0.4136,
"step": 10695
},
{
"epoch": 2.575830524795378,
"grad_norm": 1.15625,
"learning_rate": 5.200486435265714e-05,
"loss": 0.3833,
"step": 10700
},
{
"epoch": 2.577034183919114,
"grad_norm": 1.1875,
"learning_rate": 5.1967839876163556e-05,
"loss": 0.3981,
"step": 10705
},
{
"epoch": 2.5782378430428503,
"grad_norm": 1.2890625,
"learning_rate": 5.1930913546173766e-05,
"loss": 0.4059,
"step": 10710
},
{
"epoch": 2.5794415021665866,
"grad_norm": 1.1875,
"learning_rate": 5.1894085421686605e-05,
"loss": 0.399,
"step": 10715
},
{
"epoch": 2.5806451612903225,
"grad_norm": 1.1484375,
"learning_rate": 5.185735556154395e-05,
"loss": 0.4223,
"step": 10720
},
{
"epoch": 2.581848820414059,
"grad_norm": 1.171875,
"learning_rate": 5.1820724024430737e-05,
"loss": 0.3819,
"step": 10725
},
{
"epoch": 2.5830524795377947,
"grad_norm": 1.0625,
"learning_rate": 5.178419086887472e-05,
"loss": 0.4061,
"step": 10730
},
{
"epoch": 2.584256138661531,
"grad_norm": 1.1875,
"learning_rate": 5.174775615324656e-05,
"loss": 0.4162,
"step": 10735
},
{
"epoch": 2.5854597977852674,
"grad_norm": 1.15625,
"learning_rate": 5.1711419935759594e-05,
"loss": 0.3761,
"step": 10740
},
{
"epoch": 2.5866634569090032,
"grad_norm": 1.1953125,
"learning_rate": 5.1675182274469744e-05,
"loss": 0.4141,
"step": 10745
},
{
"epoch": 2.5878671160327396,
"grad_norm": 1.1171875,
"learning_rate": 5.163904322727552e-05,
"loss": 0.3762,
"step": 10750
},
{
"epoch": 2.5890707751564754,
"grad_norm": 1.0546875,
"learning_rate": 5.160300285191788e-05,
"loss": 0.3992,
"step": 10755
},
{
"epoch": 2.5902744342802118,
"grad_norm": 1.1953125,
"learning_rate": 5.156706120598007e-05,
"loss": 0.3924,
"step": 10760
},
{
"epoch": 2.591478093403948,
"grad_norm": 1.21875,
"learning_rate": 5.153121834688766e-05,
"loss": 0.3643,
"step": 10765
},
{
"epoch": 2.5926817525276844,
"grad_norm": 1.2734375,
"learning_rate": 5.1495474331908306e-05,
"loss": 0.3923,
"step": 10770
},
{
"epoch": 2.5938854116514203,
"grad_norm": 1.1484375,
"learning_rate": 5.145982921815182e-05,
"loss": 0.3632,
"step": 10775
},
{
"epoch": 2.5950890707751566,
"grad_norm": 1.25,
"learning_rate": 5.142428306256995e-05,
"loss": 0.4253,
"step": 10780
},
{
"epoch": 2.5962927298988925,
"grad_norm": 1.1171875,
"learning_rate": 5.138883592195634e-05,
"loss": 0.3692,
"step": 10785
},
{
"epoch": 2.597496389022629,
"grad_norm": 1.1796875,
"learning_rate": 5.135348785294642e-05,
"loss": 0.4008,
"step": 10790
},
{
"epoch": 2.598700048146365,
"grad_norm": 1.0546875,
"learning_rate": 5.1318238912017345e-05,
"loss": 0.395,
"step": 10795
},
{
"epoch": 2.599903707270101,
"grad_norm": 1.046875,
"learning_rate": 5.12830891554879e-05,
"loss": 0.3927,
"step": 10800
},
{
"epoch": 2.6011073663938373,
"grad_norm": 1.1015625,
"learning_rate": 5.124803863951837e-05,
"loss": 0.374,
"step": 10805
},
{
"epoch": 2.602311025517573,
"grad_norm": 1.2265625,
"learning_rate": 5.12130874201105e-05,
"loss": 0.4077,
"step": 10810
},
{
"epoch": 2.6035146846413095,
"grad_norm": 1.15625,
"learning_rate": 5.117823555310738e-05,
"loss": 0.3914,
"step": 10815
},
{
"epoch": 2.604718343765046,
"grad_norm": 1.1171875,
"learning_rate": 5.1143483094193366e-05,
"loss": 0.3755,
"step": 10820
},
{
"epoch": 2.605922002888782,
"grad_norm": 1.0390625,
"learning_rate": 5.110883009889396e-05,
"loss": 0.4147,
"step": 10825
},
{
"epoch": 2.607125662012518,
"grad_norm": 1.1484375,
"learning_rate": 5.107427662257577e-05,
"loss": 0.4125,
"step": 10830
},
{
"epoch": 2.6083293211362544,
"grad_norm": 1.234375,
"learning_rate": 5.103982272044643e-05,
"loss": 0.4214,
"step": 10835
},
{
"epoch": 2.6095329802599903,
"grad_norm": 1.1171875,
"learning_rate": 5.10054684475544e-05,
"loss": 0.3757,
"step": 10840
},
{
"epoch": 2.6107366393837266,
"grad_norm": 1.1796875,
"learning_rate": 5.0971213858789e-05,
"loss": 0.4079,
"step": 10845
},
{
"epoch": 2.611940298507463,
"grad_norm": 1.2109375,
"learning_rate": 5.093705900888031e-05,
"loss": 0.4148,
"step": 10850
},
{
"epoch": 2.6131439576311988,
"grad_norm": 1.171875,
"learning_rate": 5.090300395239901e-05,
"loss": 0.3974,
"step": 10855
},
{
"epoch": 2.614347616754935,
"grad_norm": 1.125,
"learning_rate": 5.0869048743756336e-05,
"loss": 0.4012,
"step": 10860
},
{
"epoch": 2.615551275878671,
"grad_norm": 1.109375,
"learning_rate": 5.083519343720404e-05,
"loss": 0.3988,
"step": 10865
},
{
"epoch": 2.6167549350024073,
"grad_norm": 1.171875,
"learning_rate": 5.080143808683419e-05,
"loss": 0.3792,
"step": 10870
},
{
"epoch": 2.6179585941261436,
"grad_norm": 1.1640625,
"learning_rate": 5.0767782746579206e-05,
"loss": 0.411,
"step": 10875
},
{
"epoch": 2.6191622532498795,
"grad_norm": 1.234375,
"learning_rate": 5.073422747021168e-05,
"loss": 0.4114,
"step": 10880
},
{
"epoch": 2.620365912373616,
"grad_norm": 1.25,
"learning_rate": 5.0700772311344345e-05,
"loss": 0.4095,
"step": 10885
},
{
"epoch": 2.6215695714973517,
"grad_norm": 1.125,
"learning_rate": 5.066741732342999e-05,
"loss": 0.3815,
"step": 10890
},
{
"epoch": 2.622773230621088,
"grad_norm": 1.2265625,
"learning_rate": 5.063416255976131e-05,
"loss": 0.3941,
"step": 10895
},
{
"epoch": 2.6239768897448243,
"grad_norm": 1.078125,
"learning_rate": 5.0601008073470886e-05,
"loss": 0.3619,
"step": 10900
},
{
"epoch": 2.6251805488685607,
"grad_norm": 1.1171875,
"learning_rate": 5.0567953917531106e-05,
"loss": 0.3967,
"step": 10905
},
{
"epoch": 2.6263842079922965,
"grad_norm": 1.09375,
"learning_rate": 5.053500014475402e-05,
"loss": 0.4058,
"step": 10910
},
{
"epoch": 2.627587867116033,
"grad_norm": 1.15625,
"learning_rate": 5.0502146807791325e-05,
"loss": 0.3839,
"step": 10915
},
{
"epoch": 2.6287915262397687,
"grad_norm": 1.28125,
"learning_rate": 5.046939395913423e-05,
"loss": 0.3853,
"step": 10920
},
{
"epoch": 2.629995185363505,
"grad_norm": 1.203125,
"learning_rate": 5.0436741651113396e-05,
"loss": 0.3941,
"step": 10925
},
{
"epoch": 2.6311988444872414,
"grad_norm": 1.1171875,
"learning_rate": 5.0404189935898824e-05,
"loss": 0.3901,
"step": 10930
},
{
"epoch": 2.6324025036109773,
"grad_norm": 1.1328125,
"learning_rate": 5.037173886549981e-05,
"loss": 0.3999,
"step": 10935
},
{
"epoch": 2.6336061627347136,
"grad_norm": 1.09375,
"learning_rate": 5.033938849176487e-05,
"loss": 0.4189,
"step": 10940
},
{
"epoch": 2.6348098218584495,
"grad_norm": 1.15625,
"learning_rate": 5.0307138866381594e-05,
"loss": 0.398,
"step": 10945
},
{
"epoch": 2.636013480982186,
"grad_norm": 1.1796875,
"learning_rate": 5.027499004087661e-05,
"loss": 0.4178,
"step": 10950
},
{
"epoch": 2.637217140105922,
"grad_norm": 1.1328125,
"learning_rate": 5.02429420666155e-05,
"loss": 0.3906,
"step": 10955
},
{
"epoch": 2.638420799229658,
"grad_norm": 1.1015625,
"learning_rate": 5.021099499480272e-05,
"loss": 0.3867,
"step": 10960
},
{
"epoch": 2.6396244583533943,
"grad_norm": 1.2265625,
"learning_rate": 5.01791488764815e-05,
"loss": 0.411,
"step": 10965
},
{
"epoch": 2.64082811747713,
"grad_norm": 1.2265625,
"learning_rate": 5.0147403762533755e-05,
"loss": 0.4381,
"step": 10970
},
{
"epoch": 2.6420317766008665,
"grad_norm": 1.09375,
"learning_rate": 5.011575970368007e-05,
"loss": 0.3743,
"step": 10975
},
{
"epoch": 2.643235435724603,
"grad_norm": 1.078125,
"learning_rate": 5.0084216750479514e-05,
"loss": 0.3951,
"step": 10980
},
{
"epoch": 2.644439094848339,
"grad_norm": 1.078125,
"learning_rate": 5.005277495332965e-05,
"loss": 0.3753,
"step": 10985
},
{
"epoch": 2.645642753972075,
"grad_norm": 1.1640625,
"learning_rate": 5.002143436246642e-05,
"loss": 0.4305,
"step": 10990
},
{
"epoch": 2.6468464130958114,
"grad_norm": 1.1796875,
"learning_rate": 4.9990195027964035e-05,
"loss": 0.4126,
"step": 10995
},
{
"epoch": 2.6480500722195472,
"grad_norm": 1.1640625,
"learning_rate": 4.9959056999734956e-05,
"loss": 0.405,
"step": 11000
},
{
"epoch": 2.6480500722195472,
"eval_loss": 0.35999855399131775,
"eval_runtime": 2.3992,
"eval_samples_per_second": 83.362,
"eval_steps_per_second": 83.362,
"step": 11000
},
{
"epoch": 2.6492537313432836,
"grad_norm": 1.2109375,
"learning_rate": 4.992802032752976e-05,
"loss": 0.3871,
"step": 11005
},
{
"epoch": 2.65045739046702,
"grad_norm": 1.125,
"learning_rate": 4.989708506093709e-05,
"loss": 0.3773,
"step": 11010
},
{
"epoch": 2.6516610495907558,
"grad_norm": 1.1875,
"learning_rate": 4.9866251249383596e-05,
"loss": 0.3991,
"step": 11015
},
{
"epoch": 2.652864708714492,
"grad_norm": 1.0625,
"learning_rate": 4.983551894213378e-05,
"loss": 0.4101,
"step": 11020
},
{
"epoch": 2.654068367838228,
"grad_norm": 1.1875,
"learning_rate": 4.980488818829e-05,
"loss": 0.4147,
"step": 11025
},
{
"epoch": 2.6552720269619643,
"grad_norm": 1.1640625,
"learning_rate": 4.977435903679234e-05,
"loss": 0.3749,
"step": 11030
},
{
"epoch": 2.6564756860857006,
"grad_norm": 1.1484375,
"learning_rate": 4.9743931536418574e-05,
"loss": 0.3976,
"step": 11035
},
{
"epoch": 2.657679345209437,
"grad_norm": 1.2421875,
"learning_rate": 4.971360573578403e-05,
"loss": 0.3958,
"step": 11040
},
{
"epoch": 2.658883004333173,
"grad_norm": 1.0546875,
"learning_rate": 4.968338168334157e-05,
"loss": 0.3748,
"step": 11045
},
{
"epoch": 2.660086663456909,
"grad_norm": 1.1015625,
"learning_rate": 4.96532594273815e-05,
"loss": 0.3949,
"step": 11050
},
{
"epoch": 2.661290322580645,
"grad_norm": 1.109375,
"learning_rate": 4.962323901603145e-05,
"loss": 0.3771,
"step": 11055
},
{
"epoch": 2.6624939817043813,
"grad_norm": 1.21875,
"learning_rate": 4.959332049725632e-05,
"loss": 0.4241,
"step": 11060
},
{
"epoch": 2.6636976408281177,
"grad_norm": 1.0390625,
"learning_rate": 4.9563503918858254e-05,
"loss": 0.3762,
"step": 11065
},
{
"epoch": 2.6649012999518535,
"grad_norm": 1.265625,
"learning_rate": 4.9533789328476504e-05,
"loss": 0.4294,
"step": 11070
},
{
"epoch": 2.66610495907559,
"grad_norm": 1.109375,
"learning_rate": 4.9504176773587365e-05,
"loss": 0.39,
"step": 11075
},
{
"epoch": 2.6673086181993257,
"grad_norm": 1.109375,
"learning_rate": 4.947466630150409e-05,
"loss": 0.4092,
"step": 11080
},
{
"epoch": 2.668512277323062,
"grad_norm": 1.1484375,
"learning_rate": 4.944525795937689e-05,
"loss": 0.4245,
"step": 11085
},
{
"epoch": 2.6697159364467984,
"grad_norm": 1.2421875,
"learning_rate": 4.94159517941927e-05,
"loss": 0.446,
"step": 11090
},
{
"epoch": 2.6709195955705343,
"grad_norm": 1.109375,
"learning_rate": 4.93867478527753e-05,
"loss": 0.382,
"step": 11095
},
{
"epoch": 2.6721232546942706,
"grad_norm": 1.125,
"learning_rate": 4.935764618178511e-05,
"loss": 0.3752,
"step": 11100
},
{
"epoch": 2.6733269138180065,
"grad_norm": 1.078125,
"learning_rate": 4.932864682771912e-05,
"loss": 0.3823,
"step": 11105
},
{
"epoch": 2.674530572941743,
"grad_norm": 1.234375,
"learning_rate": 4.9299749836910855e-05,
"loss": 0.3903,
"step": 11110
},
{
"epoch": 2.675734232065479,
"grad_norm": 1.2109375,
"learning_rate": 4.9270955255530304e-05,
"loss": 0.4138,
"step": 11115
},
{
"epoch": 2.6769378911892154,
"grad_norm": 1.0625,
"learning_rate": 4.924226312958383e-05,
"loss": 0.4069,
"step": 11120
},
{
"epoch": 2.6781415503129513,
"grad_norm": 1.0546875,
"learning_rate": 4.9213673504914116e-05,
"loss": 0.3896,
"step": 11125
},
{
"epoch": 2.6793452094366876,
"grad_norm": 1.078125,
"learning_rate": 4.918518642720002e-05,
"loss": 0.3947,
"step": 11130
},
{
"epoch": 2.6805488685604235,
"grad_norm": 1.1171875,
"learning_rate": 4.9156801941956615e-05,
"loss": 0.3621,
"step": 11135
},
{
"epoch": 2.68175252768416,
"grad_norm": 1.046875,
"learning_rate": 4.9128520094535e-05,
"loss": 0.3774,
"step": 11140
},
{
"epoch": 2.682956186807896,
"grad_norm": 1.140625,
"learning_rate": 4.910034093012235e-05,
"loss": 0.4004,
"step": 11145
},
{
"epoch": 2.684159845931632,
"grad_norm": 2.46875,
"learning_rate": 4.907226449374173e-05,
"loss": 0.3884,
"step": 11150
},
{
"epoch": 2.6853635050553684,
"grad_norm": 1.0546875,
"learning_rate": 4.9044290830252106e-05,
"loss": 0.3853,
"step": 11155
},
{
"epoch": 2.6865671641791042,
"grad_norm": 1.0703125,
"learning_rate": 4.901641998434819e-05,
"loss": 0.3866,
"step": 11160
},
{
"epoch": 2.6877708233028406,
"grad_norm": 1.140625,
"learning_rate": 4.8988652000560474e-05,
"loss": 0.3965,
"step": 11165
},
{
"epoch": 2.688974482426577,
"grad_norm": 1.0703125,
"learning_rate": 4.8960986923255066e-05,
"loss": 0.4114,
"step": 11170
},
{
"epoch": 2.690178141550313,
"grad_norm": 1.0859375,
"learning_rate": 4.893342479663367e-05,
"loss": 0.3998,
"step": 11175
},
{
"epoch": 2.691381800674049,
"grad_norm": 1.15625,
"learning_rate": 4.890596566473349e-05,
"loss": 0.3753,
"step": 11180
},
{
"epoch": 2.6925854597977854,
"grad_norm": 1.0859375,
"learning_rate": 4.8878609571427204e-05,
"loss": 0.3839,
"step": 11185
},
{
"epoch": 2.6937891189215213,
"grad_norm": 1.03125,
"learning_rate": 4.885135656042281e-05,
"loss": 0.3886,
"step": 11190
},
{
"epoch": 2.6949927780452576,
"grad_norm": 1.15625,
"learning_rate": 4.8824206675263646e-05,
"loss": 0.4186,
"step": 11195
},
{
"epoch": 2.696196437168994,
"grad_norm": 1.1484375,
"learning_rate": 4.879715995932828e-05,
"loss": 0.3876,
"step": 11200
},
{
"epoch": 2.69740009629273,
"grad_norm": 1.1171875,
"learning_rate": 4.877021645583041e-05,
"loss": 0.3745,
"step": 11205
},
{
"epoch": 2.698603755416466,
"grad_norm": 1.1796875,
"learning_rate": 4.8743376207818855e-05,
"loss": 0.399,
"step": 11210
},
{
"epoch": 2.699807414540202,
"grad_norm": 1.1640625,
"learning_rate": 4.871663925817746e-05,
"loss": 0.3409,
"step": 11215
},
{
"epoch": 2.7010110736639383,
"grad_norm": 1.1328125,
"learning_rate": 4.869000564962499e-05,
"loss": 0.3794,
"step": 11220
},
{
"epoch": 2.7022147327876747,
"grad_norm": 1.1796875,
"learning_rate": 4.866347542471515e-05,
"loss": 0.3588,
"step": 11225
},
{
"epoch": 2.7034183919114105,
"grad_norm": 1.171875,
"learning_rate": 4.8637048625836426e-05,
"loss": 0.3864,
"step": 11230
},
{
"epoch": 2.704622051035147,
"grad_norm": 1.1640625,
"learning_rate": 4.8610725295212084e-05,
"loss": 0.386,
"step": 11235
},
{
"epoch": 2.7058257101588827,
"grad_norm": 1.203125,
"learning_rate": 4.858450547490003e-05,
"loss": 0.409,
"step": 11240
},
{
"epoch": 2.707029369282619,
"grad_norm": 1.1171875,
"learning_rate": 4.855838920679282e-05,
"loss": 0.3893,
"step": 11245
},
{
"epoch": 2.7082330284063554,
"grad_norm": 1.1796875,
"learning_rate": 4.85323765326176e-05,
"loss": 0.4206,
"step": 11250
},
{
"epoch": 2.7094366875300917,
"grad_norm": 1.0546875,
"learning_rate": 4.8506467493935896e-05,
"loss": 0.382,
"step": 11255
},
{
"epoch": 2.7106403466538276,
"grad_norm": 1.0546875,
"learning_rate": 4.8480662132143754e-05,
"loss": 0.3788,
"step": 11260
},
{
"epoch": 2.711844005777564,
"grad_norm": 1.109375,
"learning_rate": 4.84549604884715e-05,
"loss": 0.3799,
"step": 11265
},
{
"epoch": 2.7130476649013,
"grad_norm": 1.1640625,
"learning_rate": 4.8429362603983786e-05,
"loss": 0.3809,
"step": 11270
},
{
"epoch": 2.714251324025036,
"grad_norm": 1.15625,
"learning_rate": 4.840386851957946e-05,
"loss": 0.4125,
"step": 11275
},
{
"epoch": 2.7154549831487724,
"grad_norm": 1.171875,
"learning_rate": 4.837847827599152e-05,
"loss": 0.3811,
"step": 11280
},
{
"epoch": 2.7166586422725083,
"grad_norm": 1.1015625,
"learning_rate": 4.8353191913787104e-05,
"loss": 0.3844,
"step": 11285
},
{
"epoch": 2.7178623013962446,
"grad_norm": 1.0703125,
"learning_rate": 4.832800947336731e-05,
"loss": 0.3761,
"step": 11290
},
{
"epoch": 2.7190659605199805,
"grad_norm": 1.140625,
"learning_rate": 4.830293099496724e-05,
"loss": 0.4067,
"step": 11295
},
{
"epoch": 2.720269619643717,
"grad_norm": 1.2265625,
"learning_rate": 4.827795651865584e-05,
"loss": 0.3837,
"step": 11300
},
{
"epoch": 2.721473278767453,
"grad_norm": 1.1640625,
"learning_rate": 4.825308608433596e-05,
"loss": 0.4123,
"step": 11305
},
{
"epoch": 2.7226769378911895,
"grad_norm": 1.203125,
"learning_rate": 4.822831973174415e-05,
"loss": 0.3933,
"step": 11310
},
{
"epoch": 2.7238805970149254,
"grad_norm": 1.1328125,
"learning_rate": 4.820365750045072e-05,
"loss": 0.3705,
"step": 11315
},
{
"epoch": 2.7250842561386617,
"grad_norm": 1.21875,
"learning_rate": 4.817909942985956e-05,
"loss": 0.396,
"step": 11320
},
{
"epoch": 2.7262879152623976,
"grad_norm": 1.1796875,
"learning_rate": 4.81546455592082e-05,
"loss": 0.3852,
"step": 11325
},
{
"epoch": 2.727491574386134,
"grad_norm": 1.109375,
"learning_rate": 4.813029592756763e-05,
"loss": 0.3748,
"step": 11330
},
{
"epoch": 2.72869523350987,
"grad_norm": 1.2109375,
"learning_rate": 4.810605057384235e-05,
"loss": 0.4004,
"step": 11335
},
{
"epoch": 2.729898892633606,
"grad_norm": 1.1171875,
"learning_rate": 4.8081909536770195e-05,
"loss": 0.3843,
"step": 11340
},
{
"epoch": 2.7311025517573424,
"grad_norm": 1.1015625,
"learning_rate": 4.805787285492237e-05,
"loss": 0.3786,
"step": 11345
},
{
"epoch": 2.7323062108810783,
"grad_norm": 1.0703125,
"learning_rate": 4.803394056670332e-05,
"loss": 0.368,
"step": 11350
},
{
"epoch": 2.7335098700048146,
"grad_norm": 1.1484375,
"learning_rate": 4.80101127103507e-05,
"loss": 0.3719,
"step": 11355
},
{
"epoch": 2.734713529128551,
"grad_norm": 1.1328125,
"learning_rate": 4.7986389323935345e-05,
"loss": 0.3925,
"step": 11360
},
{
"epoch": 2.735917188252287,
"grad_norm": 1.1015625,
"learning_rate": 4.796277044536111e-05,
"loss": 0.4133,
"step": 11365
},
{
"epoch": 2.737120847376023,
"grad_norm": 1.1015625,
"learning_rate": 4.793925611236494e-05,
"loss": 0.3963,
"step": 11370
},
{
"epoch": 2.738324506499759,
"grad_norm": 1.21875,
"learning_rate": 4.791584636251668e-05,
"loss": 0.4214,
"step": 11375
},
{
"epoch": 2.7395281656234953,
"grad_norm": 1.0390625,
"learning_rate": 4.789254123321914e-05,
"loss": 0.3743,
"step": 11380
},
{
"epoch": 2.7407318247472316,
"grad_norm": 1.0859375,
"learning_rate": 4.7869340761707926e-05,
"loss": 0.3723,
"step": 11385
},
{
"epoch": 2.741935483870968,
"grad_norm": 1.171875,
"learning_rate": 4.7846244985051426e-05,
"loss": 0.4027,
"step": 11390
},
{
"epoch": 2.743139142994704,
"grad_norm": 1.1796875,
"learning_rate": 4.7823253940150814e-05,
"loss": 0.3928,
"step": 11395
},
{
"epoch": 2.74434280211844,
"grad_norm": 1.0625,
"learning_rate": 4.7800367663739836e-05,
"loss": 0.3909,
"step": 11400
},
{
"epoch": 2.745546461242176,
"grad_norm": 1.140625,
"learning_rate": 4.777758619238492e-05,
"loss": 0.4082,
"step": 11405
},
{
"epoch": 2.7467501203659124,
"grad_norm": 1.28125,
"learning_rate": 4.775490956248504e-05,
"loss": 0.4194,
"step": 11410
},
{
"epoch": 2.7479537794896487,
"grad_norm": 1.1328125,
"learning_rate": 4.77323378102716e-05,
"loss": 0.3857,
"step": 11415
},
{
"epoch": 2.7491574386133846,
"grad_norm": 1.171875,
"learning_rate": 4.7709870971808497e-05,
"loss": 0.4026,
"step": 11420
},
{
"epoch": 2.750361097737121,
"grad_norm": 1.203125,
"learning_rate": 4.768750908299197e-05,
"loss": 0.3793,
"step": 11425
},
{
"epoch": 2.7515647568608568,
"grad_norm": 1.15625,
"learning_rate": 4.7665252179550576e-05,
"loss": 0.4044,
"step": 11430
},
{
"epoch": 2.752768415984593,
"grad_norm": 1.2109375,
"learning_rate": 4.7643100297045155e-05,
"loss": 0.4044,
"step": 11435
},
{
"epoch": 2.7539720751083294,
"grad_norm": 1.125,
"learning_rate": 4.7621053470868734e-05,
"loss": 0.3788,
"step": 11440
},
{
"epoch": 2.7551757342320657,
"grad_norm": 1.1953125,
"learning_rate": 4.759911173624649e-05,
"loss": 0.3904,
"step": 11445
},
{
"epoch": 2.7563793933558016,
"grad_norm": 1.1484375,
"learning_rate": 4.757727512823569e-05,
"loss": 0.4006,
"step": 11450
},
{
"epoch": 2.757583052479538,
"grad_norm": 1.15625,
"learning_rate": 4.7555543681725604e-05,
"loss": 0.3898,
"step": 11455
},
{
"epoch": 2.758786711603274,
"grad_norm": 1.09375,
"learning_rate": 4.7533917431437576e-05,
"loss": 0.3678,
"step": 11460
},
{
"epoch": 2.75999037072701,
"grad_norm": 1.171875,
"learning_rate": 4.751239641192476e-05,
"loss": 0.3722,
"step": 11465
},
{
"epoch": 2.7611940298507465,
"grad_norm": 1.1640625,
"learning_rate": 4.749098065757225e-05,
"loss": 0.3969,
"step": 11470
},
{
"epoch": 2.7623976889744823,
"grad_norm": 1.1015625,
"learning_rate": 4.746967020259693e-05,
"loss": 0.394,
"step": 11475
},
{
"epoch": 2.7636013480982187,
"grad_norm": 1.046875,
"learning_rate": 4.744846508104744e-05,
"loss": 0.3847,
"step": 11480
},
{
"epoch": 2.7648050072219545,
"grad_norm": 1.125,
"learning_rate": 4.7427365326804126e-05,
"loss": 0.3887,
"step": 11485
},
{
"epoch": 2.766008666345691,
"grad_norm": 1.203125,
"learning_rate": 4.740637097357898e-05,
"loss": 0.4225,
"step": 11490
},
{
"epoch": 2.767212325469427,
"grad_norm": 1.1171875,
"learning_rate": 4.738548205491562e-05,
"loss": 0.3742,
"step": 11495
},
{
"epoch": 2.768415984593163,
"grad_norm": 1.078125,
"learning_rate": 4.7364698604189155e-05,
"loss": 0.3791,
"step": 11500
},
{
"epoch": 2.768415984593163,
"eval_loss": 0.3576022684574127,
"eval_runtime": 2.3931,
"eval_samples_per_second": 83.574,
"eval_steps_per_second": 83.574,
"step": 11500
},
{
"epoch": 2.7696196437168994,
"grad_norm": 1.1875,
"learning_rate": 4.7344020654606226e-05,
"loss": 0.3636,
"step": 11505
},
{
"epoch": 2.7708233028406353,
"grad_norm": 1.1953125,
"learning_rate": 4.7323448239204896e-05,
"loss": 0.3912,
"step": 11510
},
{
"epoch": 2.7720269619643716,
"grad_norm": 1.1953125,
"learning_rate": 4.7302981390854604e-05,
"loss": 0.3732,
"step": 11515
},
{
"epoch": 2.773230621088108,
"grad_norm": 1.0703125,
"learning_rate": 4.728262014225614e-05,
"loss": 0.3888,
"step": 11520
},
{
"epoch": 2.7744342802118442,
"grad_norm": 1.0625,
"learning_rate": 4.726236452594155e-05,
"loss": 0.3842,
"step": 11525
},
{
"epoch": 2.77563793933558,
"grad_norm": 1.046875,
"learning_rate": 4.724221457427411e-05,
"loss": 0.382,
"step": 11530
},
{
"epoch": 2.7768415984593164,
"grad_norm": 1.1328125,
"learning_rate": 4.7222170319448306e-05,
"loss": 0.3981,
"step": 11535
},
{
"epoch": 2.7780452575830523,
"grad_norm": 1.078125,
"learning_rate": 4.720223179348968e-05,
"loss": 0.3983,
"step": 11540
},
{
"epoch": 2.7792489167067886,
"grad_norm": 1.1875,
"learning_rate": 4.718239902825491e-05,
"loss": 0.3847,
"step": 11545
},
{
"epoch": 2.780452575830525,
"grad_norm": 1.1015625,
"learning_rate": 4.716267205543166e-05,
"loss": 0.4063,
"step": 11550
},
{
"epoch": 2.781656234954261,
"grad_norm": 1.3515625,
"learning_rate": 4.714305090653857e-05,
"loss": 0.3949,
"step": 11555
},
{
"epoch": 2.782859894077997,
"grad_norm": 1.1484375,
"learning_rate": 4.712353561292523e-05,
"loss": 0.4026,
"step": 11560
},
{
"epoch": 2.784063553201733,
"grad_norm": 1.015625,
"learning_rate": 4.710412620577205e-05,
"loss": 0.3894,
"step": 11565
},
{
"epoch": 2.7852672123254694,
"grad_norm": 1.109375,
"learning_rate": 4.708482271609032e-05,
"loss": 0.382,
"step": 11570
},
{
"epoch": 2.7864708714492057,
"grad_norm": 1.21875,
"learning_rate": 4.706562517472203e-05,
"loss": 0.3983,
"step": 11575
},
{
"epoch": 2.787674530572942,
"grad_norm": 1.1640625,
"learning_rate": 4.704653361233995e-05,
"loss": 0.3772,
"step": 11580
},
{
"epoch": 2.788878189696678,
"grad_norm": 1.1953125,
"learning_rate": 4.70275480594475e-05,
"loss": 0.4026,
"step": 11585
},
{
"epoch": 2.790081848820414,
"grad_norm": 1.1015625,
"learning_rate": 4.7008668546378726e-05,
"loss": 0.3918,
"step": 11590
},
{
"epoch": 2.79128550794415,
"grad_norm": 1.3046875,
"learning_rate": 4.6989895103298245e-05,
"loss": 0.404,
"step": 11595
},
{
"epoch": 2.7924891670678864,
"grad_norm": 1.0234375,
"learning_rate": 4.697122776020121e-05,
"loss": 0.3989,
"step": 11600
},
{
"epoch": 2.7936928261916227,
"grad_norm": 1.265625,
"learning_rate": 4.695266654691326e-05,
"loss": 0.3904,
"step": 11605
},
{
"epoch": 2.7948964853153586,
"grad_norm": 1.1796875,
"learning_rate": 4.693421149309044e-05,
"loss": 0.3853,
"step": 11610
},
{
"epoch": 2.796100144439095,
"grad_norm": 1.0703125,
"learning_rate": 4.6915862628219196e-05,
"loss": 0.3757,
"step": 11615
},
{
"epoch": 2.797303803562831,
"grad_norm": 1.078125,
"learning_rate": 4.689761998161634e-05,
"loss": 0.3983,
"step": 11620
},
{
"epoch": 2.798507462686567,
"grad_norm": 1.25,
"learning_rate": 4.6879483582428885e-05,
"loss": 0.4047,
"step": 11625
},
{
"epoch": 2.7997111218103035,
"grad_norm": 1.2109375,
"learning_rate": 4.6861453459634206e-05,
"loss": 0.3826,
"step": 11630
},
{
"epoch": 2.8009147809340393,
"grad_norm": 1.1171875,
"learning_rate": 4.684352964203979e-05,
"loss": 0.3798,
"step": 11635
},
{
"epoch": 2.8021184400577757,
"grad_norm": 1.1640625,
"learning_rate": 4.682571215828331e-05,
"loss": 0.3932,
"step": 11640
},
{
"epoch": 2.8033220991815115,
"grad_norm": 1.1484375,
"learning_rate": 4.680800103683254e-05,
"loss": 0.3664,
"step": 11645
},
{
"epoch": 2.804525758305248,
"grad_norm": 1.09375,
"learning_rate": 4.679039630598529e-05,
"loss": 0.3953,
"step": 11650
},
{
"epoch": 2.805729417428984,
"grad_norm": 1.1484375,
"learning_rate": 4.6772897993869435e-05,
"loss": 0.3942,
"step": 11655
},
{
"epoch": 2.8069330765527205,
"grad_norm": 1.1796875,
"learning_rate": 4.6755506128442775e-05,
"loss": 0.383,
"step": 11660
},
{
"epoch": 2.8081367356764564,
"grad_norm": 1.125,
"learning_rate": 4.673822073749306e-05,
"loss": 0.3847,
"step": 11665
},
{
"epoch": 2.8093403948001927,
"grad_norm": 1.0703125,
"learning_rate": 4.672104184863791e-05,
"loss": 0.411,
"step": 11670
},
{
"epoch": 2.8105440539239286,
"grad_norm": 1.125,
"learning_rate": 4.670396948932479e-05,
"loss": 0.4019,
"step": 11675
},
{
"epoch": 2.811747713047665,
"grad_norm": 1.1171875,
"learning_rate": 4.6687003686830947e-05,
"loss": 0.395,
"step": 11680
},
{
"epoch": 2.8129513721714012,
"grad_norm": 1.0390625,
"learning_rate": 4.667014446826338e-05,
"loss": 0.4029,
"step": 11685
},
{
"epoch": 2.814155031295137,
"grad_norm": 1.1640625,
"learning_rate": 4.6653391860558815e-05,
"loss": 0.4214,
"step": 11690
},
{
"epoch": 2.8153586904188734,
"grad_norm": 1.1484375,
"learning_rate": 4.6636745890483633e-05,
"loss": 0.3709,
"step": 11695
},
{
"epoch": 2.8165623495426093,
"grad_norm": 1.1796875,
"learning_rate": 4.662020658463378e-05,
"loss": 0.4045,
"step": 11700
},
{
"epoch": 2.8177660086663456,
"grad_norm": 1.046875,
"learning_rate": 4.6603773969434875e-05,
"loss": 0.3849,
"step": 11705
},
{
"epoch": 2.818969667790082,
"grad_norm": 1.109375,
"learning_rate": 4.6587448071142e-05,
"loss": 0.4063,
"step": 11710
},
{
"epoch": 2.8201733269138183,
"grad_norm": 1.1640625,
"learning_rate": 4.657122891583977e-05,
"loss": 0.3738,
"step": 11715
},
{
"epoch": 2.821376986037554,
"grad_norm": 1.109375,
"learning_rate": 4.655511652944221e-05,
"loss": 0.3776,
"step": 11720
},
{
"epoch": 2.8225806451612905,
"grad_norm": 1.1640625,
"learning_rate": 4.65391109376928e-05,
"loss": 0.3899,
"step": 11725
},
{
"epoch": 2.8237843042850264,
"grad_norm": 1.09375,
"learning_rate": 4.65232121661644e-05,
"loss": 0.3891,
"step": 11730
},
{
"epoch": 2.8249879634087627,
"grad_norm": 1.109375,
"learning_rate": 4.650742024025912e-05,
"loss": 0.4112,
"step": 11735
},
{
"epoch": 2.826191622532499,
"grad_norm": 1.1953125,
"learning_rate": 4.649173518520845e-05,
"loss": 0.3939,
"step": 11740
},
{
"epoch": 2.827395281656235,
"grad_norm": 1.1015625,
"learning_rate": 4.647615702607307e-05,
"loss": 0.3799,
"step": 11745
},
{
"epoch": 2.828598940779971,
"grad_norm": 1.1328125,
"learning_rate": 4.646068578774288e-05,
"loss": 0.3861,
"step": 11750
},
{
"epoch": 2.829802599903707,
"grad_norm": 1.15625,
"learning_rate": 4.644532149493697e-05,
"loss": 0.3719,
"step": 11755
},
{
"epoch": 2.8310062590274434,
"grad_norm": 1.1171875,
"learning_rate": 4.6430064172203515e-05,
"loss": 0.3909,
"step": 11760
},
{
"epoch": 2.8322099181511797,
"grad_norm": 1.203125,
"learning_rate": 4.6414913843919834e-05,
"loss": 0.405,
"step": 11765
},
{
"epoch": 2.8334135772749156,
"grad_norm": 1.140625,
"learning_rate": 4.639987053429225e-05,
"loss": 0.4022,
"step": 11770
},
{
"epoch": 2.834617236398652,
"grad_norm": 1.203125,
"learning_rate": 4.638493426735612e-05,
"loss": 0.3874,
"step": 11775
},
{
"epoch": 2.835820895522388,
"grad_norm": 1.0859375,
"learning_rate": 4.6370105066975775e-05,
"loss": 0.3734,
"step": 11780
},
{
"epoch": 2.837024554646124,
"grad_norm": 1.125,
"learning_rate": 4.635538295684446e-05,
"loss": 0.3928,
"step": 11785
},
{
"epoch": 2.8382282137698605,
"grad_norm": 1.1875,
"learning_rate": 4.634076796048435e-05,
"loss": 0.394,
"step": 11790
},
{
"epoch": 2.8394318728935968,
"grad_norm": 1.1953125,
"learning_rate": 4.632626010124645e-05,
"loss": 0.406,
"step": 11795
},
{
"epoch": 2.8406355320173327,
"grad_norm": 1.1875,
"learning_rate": 4.631185940231062e-05,
"loss": 0.3848,
"step": 11800
},
{
"epoch": 2.841839191141069,
"grad_norm": 1.046875,
"learning_rate": 4.6297565886685466e-05,
"loss": 0.3838,
"step": 11805
},
{
"epoch": 2.843042850264805,
"grad_norm": 1.140625,
"learning_rate": 4.628337957720835e-05,
"loss": 0.3926,
"step": 11810
},
{
"epoch": 2.844246509388541,
"grad_norm": 1.1171875,
"learning_rate": 4.62693004965454e-05,
"loss": 0.3827,
"step": 11815
},
{
"epoch": 2.8454501685122775,
"grad_norm": 1.1640625,
"learning_rate": 4.6255328667191346e-05,
"loss": 0.4085,
"step": 11820
},
{
"epoch": 2.8466538276360134,
"grad_norm": 1.171875,
"learning_rate": 4.6241464111469586e-05,
"loss": 0.4502,
"step": 11825
},
{
"epoch": 2.8478574867597497,
"grad_norm": 1.140625,
"learning_rate": 4.622770685153214e-05,
"loss": 0.3902,
"step": 11830
},
{
"epoch": 2.8490611458834856,
"grad_norm": 1.1953125,
"learning_rate": 4.6214056909359585e-05,
"loss": 0.3776,
"step": 11835
},
{
"epoch": 2.850264805007222,
"grad_norm": 1.1796875,
"learning_rate": 4.6200514306761016e-05,
"loss": 0.3854,
"step": 11840
},
{
"epoch": 2.8514684641309582,
"grad_norm": 1.0859375,
"learning_rate": 4.618707906537404e-05,
"loss": 0.3774,
"step": 11845
},
{
"epoch": 2.8526721232546945,
"grad_norm": 1.296875,
"learning_rate": 4.6173751206664764e-05,
"loss": 0.3915,
"step": 11850
},
{
"epoch": 2.8538757823784304,
"grad_norm": 1.2578125,
"learning_rate": 4.616053075192764e-05,
"loss": 0.4132,
"step": 11855
},
{
"epoch": 2.8550794415021667,
"grad_norm": 1.15625,
"learning_rate": 4.61474177222856e-05,
"loss": 0.3768,
"step": 11860
},
{
"epoch": 2.8562831006259026,
"grad_norm": 1.1015625,
"learning_rate": 4.613441213868988e-05,
"loss": 0.3863,
"step": 11865
},
{
"epoch": 2.857486759749639,
"grad_norm": 1.1953125,
"learning_rate": 4.6121514021920075e-05,
"loss": 0.3987,
"step": 11870
},
{
"epoch": 2.8586904188733753,
"grad_norm": 1.1484375,
"learning_rate": 4.6108723392584075e-05,
"loss": 0.3995,
"step": 11875
},
{
"epoch": 2.859894077997111,
"grad_norm": 1.0859375,
"learning_rate": 4.609604027111803e-05,
"loss": 0.4005,
"step": 11880
},
{
"epoch": 2.8610977371208475,
"grad_norm": 1.234375,
"learning_rate": 4.608346467778631e-05,
"loss": 0.4342,
"step": 11885
},
{
"epoch": 2.8623013962445834,
"grad_norm": 1.1015625,
"learning_rate": 4.60709966326815e-05,
"loss": 0.405,
"step": 11890
},
{
"epoch": 2.8635050553683197,
"grad_norm": 1.234375,
"learning_rate": 4.605863615572432e-05,
"loss": 0.3938,
"step": 11895
},
{
"epoch": 2.864708714492056,
"grad_norm": 1.1640625,
"learning_rate": 4.6046383266663665e-05,
"loss": 0.4093,
"step": 11900
},
{
"epoch": 2.865912373615792,
"grad_norm": 1.0859375,
"learning_rate": 4.6034237985076504e-05,
"loss": 0.3839,
"step": 11905
},
{
"epoch": 2.867116032739528,
"grad_norm": 1.09375,
"learning_rate": 4.602220033036787e-05,
"loss": 0.3766,
"step": 11910
},
{
"epoch": 2.868319691863264,
"grad_norm": 1.109375,
"learning_rate": 4.601027032177086e-05,
"loss": 0.3646,
"step": 11915
},
{
"epoch": 2.8695233509870004,
"grad_norm": 1.265625,
"learning_rate": 4.5998447978346566e-05,
"loss": 0.3933,
"step": 11920
},
{
"epoch": 2.8707270101107367,
"grad_norm": 1.140625,
"learning_rate": 4.598673331898408e-05,
"loss": 0.3661,
"step": 11925
},
{
"epoch": 2.871930669234473,
"grad_norm": 1.203125,
"learning_rate": 4.59751263624004e-05,
"loss": 0.3885,
"step": 11930
},
{
"epoch": 2.873134328358209,
"grad_norm": 1.1796875,
"learning_rate": 4.596362712714046e-05,
"loss": 0.3985,
"step": 11935
},
{
"epoch": 2.8743379874819452,
"grad_norm": 1.0546875,
"learning_rate": 4.595223563157714e-05,
"loss": 0.3615,
"step": 11940
},
{
"epoch": 2.875541646605681,
"grad_norm": 1.125,
"learning_rate": 4.5940951893911076e-05,
"loss": 0.3869,
"step": 11945
},
{
"epoch": 2.8767453057294174,
"grad_norm": 1.1015625,
"learning_rate": 4.592977593217082e-05,
"loss": 0.3752,
"step": 11950
},
{
"epoch": 2.8779489648531538,
"grad_norm": 1.171875,
"learning_rate": 4.5918707764212665e-05,
"loss": 0.3578,
"step": 11955
},
{
"epoch": 2.8791526239768896,
"grad_norm": 1.234375,
"learning_rate": 4.590774740772073e-05,
"loss": 0.4142,
"step": 11960
},
{
"epoch": 2.880356283100626,
"grad_norm": 1.15625,
"learning_rate": 4.5896894880206865e-05,
"loss": 0.3769,
"step": 11965
},
{
"epoch": 2.881559942224362,
"grad_norm": 1.203125,
"learning_rate": 4.5886150199010585e-05,
"loss": 0.4187,
"step": 11970
},
{
"epoch": 2.882763601348098,
"grad_norm": 1.1953125,
"learning_rate": 4.587551338129918e-05,
"loss": 0.3809,
"step": 11975
},
{
"epoch": 2.8839672604718345,
"grad_norm": 1.203125,
"learning_rate": 4.586498444406754e-05,
"loss": 0.4233,
"step": 11980
},
{
"epoch": 2.8851709195955704,
"grad_norm": 1.0546875,
"learning_rate": 4.5854563404138195e-05,
"loss": 0.3566,
"step": 11985
},
{
"epoch": 2.8863745787193067,
"grad_norm": 1.1484375,
"learning_rate": 4.584425027816132e-05,
"loss": 0.3931,
"step": 11990
},
{
"epoch": 2.887578237843043,
"grad_norm": 1.21875,
"learning_rate": 4.583404508261461e-05,
"loss": 0.3689,
"step": 11995
},
{
"epoch": 2.888781896966779,
"grad_norm": 1.1796875,
"learning_rate": 4.58239478338034e-05,
"loss": 0.369,
"step": 12000
},
{
"epoch": 2.888781896966779,
"eval_loss": 0.3563074767589569,
"eval_runtime": 2.4086,
"eval_samples_per_second": 83.036,
"eval_steps_per_second": 83.036,
"step": 12000
},
{
"epoch": 2.889985556090515,
"grad_norm": 1.078125,
"learning_rate": 4.5813958547860474e-05,
"loss": 0.3634,
"step": 12005
},
{
"epoch": 2.8911892152142515,
"grad_norm": 1.1953125,
"learning_rate": 4.580407724074616e-05,
"loss": 0.4074,
"step": 12010
},
{
"epoch": 2.8923928743379874,
"grad_norm": 1.125,
"learning_rate": 4.5794303928248246e-05,
"loss": 0.395,
"step": 12015
},
{
"epoch": 2.8935965334617237,
"grad_norm": 1.1640625,
"learning_rate": 4.578463862598198e-05,
"loss": 0.3752,
"step": 12020
},
{
"epoch": 2.8948001925854596,
"grad_norm": 1.1484375,
"learning_rate": 4.577508134939005e-05,
"loss": 0.3828,
"step": 12025
},
{
"epoch": 2.896003851709196,
"grad_norm": 1.1484375,
"learning_rate": 4.576563211374252e-05,
"loss": 0.4007,
"step": 12030
},
{
"epoch": 2.8972075108329323,
"grad_norm": 1.0703125,
"learning_rate": 4.5756290934136856e-05,
"loss": 0.3892,
"step": 12035
},
{
"epoch": 2.898411169956668,
"grad_norm": 1.1015625,
"learning_rate": 4.574705782549786e-05,
"loss": 0.3934,
"step": 12040
},
{
"epoch": 2.8996148290804045,
"grad_norm": 1.234375,
"learning_rate": 4.573793280257768e-05,
"loss": 0.3848,
"step": 12045
},
{
"epoch": 2.9008184882041403,
"grad_norm": 1.109375,
"learning_rate": 4.572891587995576e-05,
"loss": 0.4045,
"step": 12050
},
{
"epoch": 2.9020221473278767,
"grad_norm": 1.171875,
"learning_rate": 4.572000707203883e-05,
"loss": 0.4103,
"step": 12055
},
{
"epoch": 2.903225806451613,
"grad_norm": 1.1171875,
"learning_rate": 4.5711206393060876e-05,
"loss": 0.3755,
"step": 12060
},
{
"epoch": 2.9044294655753493,
"grad_norm": 1.2734375,
"learning_rate": 4.570251385708314e-05,
"loss": 0.3847,
"step": 12065
},
{
"epoch": 2.905633124699085,
"grad_norm": 1.1484375,
"learning_rate": 4.569392947799406e-05,
"loss": 0.3923,
"step": 12070
},
{
"epoch": 2.9068367838228215,
"grad_norm": 1.171875,
"learning_rate": 4.568545326950928e-05,
"loss": 0.3719,
"step": 12075
},
{
"epoch": 2.9080404429465574,
"grad_norm": 1.203125,
"learning_rate": 4.567708524517159e-05,
"loss": 0.3855,
"step": 12080
},
{
"epoch": 2.9092441020702937,
"grad_norm": 1.28125,
"learning_rate": 4.566882541835097e-05,
"loss": 0.371,
"step": 12085
},
{
"epoch": 2.91044776119403,
"grad_norm": 1.203125,
"learning_rate": 4.566067380224448e-05,
"loss": 0.413,
"step": 12090
},
{
"epoch": 2.911651420317766,
"grad_norm": 1.21875,
"learning_rate": 4.565263040987633e-05,
"loss": 0.3755,
"step": 12095
},
{
"epoch": 2.9128550794415022,
"grad_norm": 1.1953125,
"learning_rate": 4.56446952540978e-05,
"loss": 0.3831,
"step": 12100
},
{
"epoch": 2.914058738565238,
"grad_norm": 1.1640625,
"learning_rate": 4.563686834758722e-05,
"loss": 0.4041,
"step": 12105
},
{
"epoch": 2.9152623976889744,
"grad_norm": 1.0859375,
"learning_rate": 4.5629149702850003e-05,
"loss": 0.3839,
"step": 12110
},
{
"epoch": 2.9164660568127108,
"grad_norm": 1.1015625,
"learning_rate": 4.5621539332218563e-05,
"loss": 0.3736,
"step": 12115
},
{
"epoch": 2.9176697159364466,
"grad_norm": 1.1796875,
"learning_rate": 4.56140372478523e-05,
"loss": 0.4246,
"step": 12120
},
{
"epoch": 2.918873375060183,
"grad_norm": 1.203125,
"learning_rate": 4.560664346173763e-05,
"loss": 0.3869,
"step": 12125
},
{
"epoch": 2.920077034183919,
"grad_norm": 1.3125,
"learning_rate": 4.5599357985687936e-05,
"loss": 0.4291,
"step": 12130
},
{
"epoch": 2.921280693307655,
"grad_norm": 1.171875,
"learning_rate": 4.559218083134353e-05,
"loss": 0.3501,
"step": 12135
},
{
"epoch": 2.9224843524313915,
"grad_norm": 1.2578125,
"learning_rate": 4.558511201017168e-05,
"loss": 0.4301,
"step": 12140
},
{
"epoch": 2.923688011555128,
"grad_norm": 1.1015625,
"learning_rate": 4.557815153346653e-05,
"loss": 0.388,
"step": 12145
},
{
"epoch": 2.9248916706788637,
"grad_norm": 1.2890625,
"learning_rate": 4.557129941234914e-05,
"loss": 0.4119,
"step": 12150
},
{
"epoch": 2.9260953298026,
"grad_norm": 1.15625,
"learning_rate": 4.5564555657767465e-05,
"loss": 0.3856,
"step": 12155
},
{
"epoch": 2.927298988926336,
"grad_norm": 1.25,
"learning_rate": 4.555792028049628e-05,
"loss": 0.3855,
"step": 12160
},
{
"epoch": 2.928502648050072,
"grad_norm": 1.203125,
"learning_rate": 4.555139329113723e-05,
"loss": 0.3782,
"step": 12165
},
{
"epoch": 2.9297063071738085,
"grad_norm": 1.1171875,
"learning_rate": 4.554497470011874e-05,
"loss": 0.3901,
"step": 12170
},
{
"epoch": 2.9309099662975444,
"grad_norm": 1.15625,
"learning_rate": 4.55386645176961e-05,
"loss": 0.4041,
"step": 12175
},
{
"epoch": 2.9321136254212807,
"grad_norm": 1.15625,
"learning_rate": 4.5532462753951366e-05,
"loss": 0.4107,
"step": 12180
},
{
"epoch": 2.9333172845450166,
"grad_norm": 1.171875,
"learning_rate": 4.552636941879335e-05,
"loss": 0.3928,
"step": 12185
},
{
"epoch": 2.934520943668753,
"grad_norm": 1.0546875,
"learning_rate": 4.552038452195764e-05,
"loss": 0.4072,
"step": 12190
},
{
"epoch": 2.9357246027924893,
"grad_norm": 1.046875,
"learning_rate": 4.551450807300657e-05,
"loss": 0.3735,
"step": 12195
},
{
"epoch": 2.9369282619162256,
"grad_norm": 1.2265625,
"learning_rate": 4.550874008132922e-05,
"loss": 0.3951,
"step": 12200
},
{
"epoch": 2.9381319210399615,
"grad_norm": 1.2734375,
"learning_rate": 4.550308055614134e-05,
"loss": 0.3922,
"step": 12205
},
{
"epoch": 2.939335580163698,
"grad_norm": 1.2109375,
"learning_rate": 4.54975295064854e-05,
"loss": 0.4063,
"step": 12210
},
{
"epoch": 2.9405392392874337,
"grad_norm": 1.125,
"learning_rate": 4.5492086941230566e-05,
"loss": 0.3764,
"step": 12215
},
{
"epoch": 2.94174289841117,
"grad_norm": 1.046875,
"learning_rate": 4.548675286907265e-05,
"loss": 0.3877,
"step": 12220
},
{
"epoch": 2.9429465575349063,
"grad_norm": 1.078125,
"learning_rate": 4.5481527298534135e-05,
"loss": 0.4026,
"step": 12225
},
{
"epoch": 2.944150216658642,
"grad_norm": 1.1171875,
"learning_rate": 4.547641023796415e-05,
"loss": 0.3824,
"step": 12230
},
{
"epoch": 2.9453538757823785,
"grad_norm": 1.0546875,
"learning_rate": 4.547140169553844e-05,
"loss": 0.4216,
"step": 12235
},
{
"epoch": 2.9465575349061144,
"grad_norm": 1.1953125,
"learning_rate": 4.546650167925937e-05,
"loss": 0.3813,
"step": 12240
},
{
"epoch": 2.9477611940298507,
"grad_norm": 1.125,
"learning_rate": 4.546171019695592e-05,
"loss": 0.3591,
"step": 12245
},
{
"epoch": 2.948964853153587,
"grad_norm": 1.09375,
"learning_rate": 4.5457027256283644e-05,
"loss": 0.3884,
"step": 12250
},
{
"epoch": 2.950168512277323,
"grad_norm": 1.0625,
"learning_rate": 4.545245286472468e-05,
"loss": 0.3715,
"step": 12255
},
{
"epoch": 2.9513721714010592,
"grad_norm": 1.2421875,
"learning_rate": 4.544798702958773e-05,
"loss": 0.4098,
"step": 12260
},
{
"epoch": 2.952575830524795,
"grad_norm": 1.125,
"learning_rate": 4.5443629758008056e-05,
"loss": 0.38,
"step": 12265
},
{
"epoch": 2.9537794896485314,
"grad_norm": 1.15625,
"learning_rate": 4.543938105694746e-05,
"loss": 0.3903,
"step": 12270
},
{
"epoch": 2.9549831487722678,
"grad_norm": 1.2578125,
"learning_rate": 4.543524093319429e-05,
"loss": 0.3801,
"step": 12275
},
{
"epoch": 2.956186807896004,
"grad_norm": 1.1875,
"learning_rate": 4.5431209393363386e-05,
"loss": 0.4105,
"step": 12280
},
{
"epoch": 2.95739046701974,
"grad_norm": 1.2265625,
"learning_rate": 4.542728644389611e-05,
"loss": 0.3941,
"step": 12285
},
{
"epoch": 2.9585941261434763,
"grad_norm": 1.125,
"learning_rate": 4.542347209106036e-05,
"loss": 0.3654,
"step": 12290
},
{
"epoch": 2.959797785267212,
"grad_norm": 1.2734375,
"learning_rate": 4.541976634095046e-05,
"loss": 0.3835,
"step": 12295
},
{
"epoch": 2.9610014443909485,
"grad_norm": 1.09375,
"learning_rate": 4.541616919948728e-05,
"loss": 0.3821,
"step": 12300
},
{
"epoch": 2.962205103514685,
"grad_norm": 1.203125,
"learning_rate": 4.54126806724181e-05,
"loss": 0.3633,
"step": 12305
},
{
"epoch": 2.9634087626384207,
"grad_norm": 1.0546875,
"learning_rate": 4.54093007653167e-05,
"loss": 0.3833,
"step": 12310
},
{
"epoch": 2.964612421762157,
"grad_norm": 1.109375,
"learning_rate": 4.5406029483583325e-05,
"loss": 0.3849,
"step": 12315
},
{
"epoch": 2.965816080885893,
"grad_norm": 1.046875,
"learning_rate": 4.540286683244462e-05,
"loss": 0.4046,
"step": 12320
},
{
"epoch": 2.967019740009629,
"grad_norm": 1.15625,
"learning_rate": 4.53998128169537e-05,
"loss": 0.367,
"step": 12325
},
{
"epoch": 2.9682233991333655,
"grad_norm": 1.140625,
"learning_rate": 4.539686744199011e-05,
"loss": 0.3825,
"step": 12330
},
{
"epoch": 2.969427058257102,
"grad_norm": 1.0,
"learning_rate": 4.5394030712259775e-05,
"loss": 0.399,
"step": 12335
},
{
"epoch": 2.9706307173808377,
"grad_norm": 1.1875,
"learning_rate": 4.53913026322951e-05,
"loss": 0.4124,
"step": 12340
},
{
"epoch": 2.971834376504574,
"grad_norm": 1.171875,
"learning_rate": 4.538868320645483e-05,
"loss": 0.3857,
"step": 12345
},
{
"epoch": 2.97303803562831,
"grad_norm": 1.0703125,
"learning_rate": 4.538617243892414e-05,
"loss": 0.3928,
"step": 12350
},
{
"epoch": 2.9742416947520463,
"grad_norm": 1.15625,
"learning_rate": 4.5383770333714605e-05,
"loss": 0.3823,
"step": 12355
},
{
"epoch": 2.9754453538757826,
"grad_norm": 1.1796875,
"learning_rate": 4.538147689466415e-05,
"loss": 0.4059,
"step": 12360
},
{
"epoch": 2.9766490129995185,
"grad_norm": 1.1640625,
"learning_rate": 4.537929212543713e-05,
"loss": 0.3888,
"step": 12365
},
{
"epoch": 2.9778526721232548,
"grad_norm": 1.0546875,
"learning_rate": 4.5377216029524235e-05,
"loss": 0.3633,
"step": 12370
},
{
"epoch": 2.9790563312469907,
"grad_norm": 1.3515625,
"learning_rate": 4.5375248610242525e-05,
"loss": 0.3799,
"step": 12375
},
{
"epoch": 2.980259990370727,
"grad_norm": 1.25,
"learning_rate": 4.537338987073546e-05,
"loss": 0.3851,
"step": 12380
},
{
"epoch": 2.9814636494944633,
"grad_norm": 1.1328125,
"learning_rate": 4.537163981397279e-05,
"loss": 0.3979,
"step": 12385
},
{
"epoch": 2.982667308618199,
"grad_norm": 0.9921875,
"learning_rate": 4.5369998442750676e-05,
"loss": 0.3847,
"step": 12390
},
{
"epoch": 2.9838709677419355,
"grad_norm": 1.1171875,
"learning_rate": 4.5368465759691614e-05,
"loss": 0.4103,
"step": 12395
},
{
"epoch": 2.9850746268656714,
"grad_norm": 1.1171875,
"learning_rate": 4.536704176724443e-05,
"loss": 0.4009,
"step": 12400
},
{
"epoch": 2.9862782859894077,
"grad_norm": 1.1328125,
"learning_rate": 4.5365726467684305e-05,
"loss": 0.3771,
"step": 12405
},
{
"epoch": 2.987481945113144,
"grad_norm": 1.1640625,
"learning_rate": 4.536451986311275e-05,
"loss": 0.4039,
"step": 12410
},
{
"epoch": 2.9886856042368803,
"grad_norm": 1.1171875,
"learning_rate": 4.5363421955457594e-05,
"loss": 0.3889,
"step": 12415
},
{
"epoch": 2.9898892633606162,
"grad_norm": 1.1484375,
"learning_rate": 4.536243274647304e-05,
"loss": 0.3977,
"step": 12420
},
{
"epoch": 2.9910929224843525,
"grad_norm": 1.1328125,
"learning_rate": 4.536155223773957e-05,
"loss": 0.4013,
"step": 12425
},
{
"epoch": 2.9922965816080884,
"grad_norm": 1.0703125,
"learning_rate": 4.5360780430664015e-05,
"loss": 0.3995,
"step": 12430
},
{
"epoch": 2.9935002407318247,
"grad_norm": 1.078125,
"learning_rate": 4.536011732647953e-05,
"loss": 0.3835,
"step": 12435
},
{
"epoch": 2.994703899855561,
"grad_norm": 1.1640625,
"learning_rate": 4.535956292624558e-05,
"loss": 0.4118,
"step": 12440
},
{
"epoch": 2.995907558979297,
"grad_norm": 1.140625,
"learning_rate": 4.535911723084795e-05,
"loss": 0.39,
"step": 12445
},
{
"epoch": 2.9971112181030333,
"grad_norm": 1.296875,
"learning_rate": 4.535878024099877e-05,
"loss": 0.4116,
"step": 12450
},
{
"epoch": 2.998314877226769,
"grad_norm": 1.078125,
"learning_rate": 4.5358551957236436e-05,
"loss": 0.3725,
"step": 12455
},
{
"epoch": 2.999277804525758,
"eval_loss": 0.35562843084335327,
"eval_runtime": 2.3589,
"eval_samples_per_second": 84.786,
"eval_steps_per_second": 84.786,
"step": 12459
}
],
"logging_steps": 5,
"max_steps": 12462,
"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": 3.12509450944512e+17,
"train_batch_size": 48,
"trial_name": null,
"trial_params": null
}