hexuan21's picture
Upload folder using huggingface_hub
79d7c40 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.557374764857521,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0027868738242876052,
"grad_norm": 3.5925259590148926,
"learning_rate": 2.2222222222222225e-06,
"loss": 2.5484,
"step": 5
},
{
"epoch": 0.0055737476485752105,
"grad_norm": 3.7384228706359863,
"learning_rate": 5e-06,
"loss": 2.5036,
"step": 10
},
{
"epoch": 0.008360621472862817,
"grad_norm": 3.7028982639312744,
"learning_rate": 7.777777777777777e-06,
"loss": 2.5177,
"step": 15
},
{
"epoch": 0.011147495297150421,
"grad_norm": 3.1780974864959717,
"learning_rate": 1.0555555555555555e-05,
"loss": 2.4746,
"step": 20
},
{
"epoch": 0.013934369121438027,
"grad_norm": 2.8278558254241943,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.5083,
"step": 25
},
{
"epoch": 0.016721242945725634,
"grad_norm": 2.5323452949523926,
"learning_rate": 1.6111111111111115e-05,
"loss": 2.4383,
"step": 30
},
{
"epoch": 0.019508116770013236,
"grad_norm": 1.2514830827713013,
"learning_rate": 1.888888888888889e-05,
"loss": 2.1978,
"step": 35
},
{
"epoch": 0.022294990594300842,
"grad_norm": 1.1612293720245361,
"learning_rate": 2.1666666666666667e-05,
"loss": 2.0549,
"step": 40
},
{
"epoch": 0.025081864418588447,
"grad_norm": 0.9937079548835754,
"learning_rate": 2.4444444444444445e-05,
"loss": 2.1649,
"step": 45
},
{
"epoch": 0.027868738242876053,
"grad_norm": 1.056492567062378,
"learning_rate": 2.7222222222222223e-05,
"loss": 2.0852,
"step": 50
},
{
"epoch": 0.03065561206716366,
"grad_norm": 0.9864413142204285,
"learning_rate": 3e-05,
"loss": 1.934,
"step": 55
},
{
"epoch": 0.03344248589145127,
"grad_norm": 0.9184162616729736,
"learning_rate": 3.277777777777778e-05,
"loss": 2.0746,
"step": 60
},
{
"epoch": 0.03622935971573887,
"grad_norm": 1.044710397720337,
"learning_rate": 3.555555555555556e-05,
"loss": 1.9812,
"step": 65
},
{
"epoch": 0.03901623354002647,
"grad_norm": 0.9160545468330383,
"learning_rate": 3.8333333333333334e-05,
"loss": 1.8794,
"step": 70
},
{
"epoch": 0.04180310736431408,
"grad_norm": 0.9865038990974426,
"learning_rate": 4.111111111111111e-05,
"loss": 1.9266,
"step": 75
},
{
"epoch": 0.044589981188601684,
"grad_norm": 0.9860550165176392,
"learning_rate": 4.388888888888889e-05,
"loss": 1.8417,
"step": 80
},
{
"epoch": 0.04737685501288929,
"grad_norm": 0.9826656579971313,
"learning_rate": 4.666666666666667e-05,
"loss": 1.9756,
"step": 85
},
{
"epoch": 0.050163728837176895,
"grad_norm": 0.9479106664657593,
"learning_rate": 4.9444444444444446e-05,
"loss": 1.8803,
"step": 90
},
{
"epoch": 0.0529506026614645,
"grad_norm": 1.005937933921814,
"learning_rate": 5.222222222222223e-05,
"loss": 1.8677,
"step": 95
},
{
"epoch": 0.055737476485752106,
"grad_norm": 1.1173028945922852,
"learning_rate": 5.500000000000001e-05,
"loss": 1.8416,
"step": 100
},
{
"epoch": 0.05852435031003971,
"grad_norm": 1.0000165700912476,
"learning_rate": 5.7777777777777776e-05,
"loss": 1.8607,
"step": 105
},
{
"epoch": 0.06131122413432732,
"grad_norm": 1.3015921115875244,
"learning_rate": 6.055555555555555e-05,
"loss": 1.9752,
"step": 110
},
{
"epoch": 0.06409809795861493,
"grad_norm": 1.0431042909622192,
"learning_rate": 6.333333333333333e-05,
"loss": 1.8514,
"step": 115
},
{
"epoch": 0.06688497178290254,
"grad_norm": 1.0463422536849976,
"learning_rate": 6.611111111111111e-05,
"loss": 1.8656,
"step": 120
},
{
"epoch": 0.06967184560719013,
"grad_norm": 1.0947015285491943,
"learning_rate": 6.88888888888889e-05,
"loss": 1.9479,
"step": 125
},
{
"epoch": 0.07245871943147773,
"grad_norm": 0.9953688979148865,
"learning_rate": 7.166666666666667e-05,
"loss": 1.8627,
"step": 130
},
{
"epoch": 0.07524559325576534,
"grad_norm": 1.0779668092727661,
"learning_rate": 7.444444444444444e-05,
"loss": 1.8262,
"step": 135
},
{
"epoch": 0.07803246708005294,
"grad_norm": 1.2166972160339355,
"learning_rate": 7.722222222222223e-05,
"loss": 1.8461,
"step": 140
},
{
"epoch": 0.08081934090434055,
"grad_norm": 1.055553674697876,
"learning_rate": 8e-05,
"loss": 1.9684,
"step": 145
},
{
"epoch": 0.08360621472862816,
"grad_norm": 1.0838943719863892,
"learning_rate": 8.277777777777778e-05,
"loss": 1.8891,
"step": 150
},
{
"epoch": 0.08639308855291576,
"grad_norm": 0.9238198399543762,
"learning_rate": 8.555555555555556e-05,
"loss": 1.8507,
"step": 155
},
{
"epoch": 0.08917996237720337,
"grad_norm": 1.186009168624878,
"learning_rate": 8.833333333333333e-05,
"loss": 1.8269,
"step": 160
},
{
"epoch": 0.09196683620149097,
"grad_norm": 1.122663140296936,
"learning_rate": 9.111111111111112e-05,
"loss": 1.7877,
"step": 165
},
{
"epoch": 0.09475371002577858,
"grad_norm": 1.176620364189148,
"learning_rate": 9.388888888888889e-05,
"loss": 1.8373,
"step": 170
},
{
"epoch": 0.09754058385006618,
"grad_norm": 1.0495474338531494,
"learning_rate": 9.666666666666667e-05,
"loss": 1.838,
"step": 175
},
{
"epoch": 0.10032745767435379,
"grad_norm": 1.0859992504119873,
"learning_rate": 9.944444444444446e-05,
"loss": 1.845,
"step": 180
},
{
"epoch": 0.1031143314986414,
"grad_norm": 1.1708000898361206,
"learning_rate": 9.999848639521432e-05,
"loss": 1.8148,
"step": 185
},
{
"epoch": 0.105901205322929,
"grad_norm": 1.0338629484176636,
"learning_rate": 9.999233753283091e-05,
"loss": 1.7982,
"step": 190
},
{
"epoch": 0.1086880791472166,
"grad_norm": 1.2173702716827393,
"learning_rate": 9.998145939378577e-05,
"loss": 1.792,
"step": 195
},
{
"epoch": 0.11147495297150421,
"grad_norm": 1.1683762073516846,
"learning_rate": 9.996585300715116e-05,
"loss": 1.8381,
"step": 200
},
{
"epoch": 0.11426182679579182,
"grad_norm": 1.0897382497787476,
"learning_rate": 9.994551984929175e-05,
"loss": 1.8142,
"step": 205
},
{
"epoch": 0.11704870062007942,
"grad_norm": 0.9195744395256042,
"learning_rate": 9.992046184372492e-05,
"loss": 1.8362,
"step": 210
},
{
"epoch": 0.11983557444436703,
"grad_norm": 1.039374589920044,
"learning_rate": 9.989068136093873e-05,
"loss": 1.7565,
"step": 215
},
{
"epoch": 0.12262244826865464,
"grad_norm": 1.0218507051467896,
"learning_rate": 9.985618121816779e-05,
"loss": 1.8728,
"step": 220
},
{
"epoch": 0.12540932209294225,
"grad_norm": 1.0597004890441895,
"learning_rate": 9.981696467912664e-05,
"loss": 1.7938,
"step": 225
},
{
"epoch": 0.12819619591722986,
"grad_norm": 1.1160184144973755,
"learning_rate": 9.97730354537011e-05,
"loss": 1.8156,
"step": 230
},
{
"epoch": 0.13098306974151747,
"grad_norm": 0.99184250831604,
"learning_rate": 9.972439769759722e-05,
"loss": 1.7255,
"step": 235
},
{
"epoch": 0.13376994356580507,
"grad_norm": 1.0527223348617554,
"learning_rate": 9.967105601194823e-05,
"loss": 1.8942,
"step": 240
},
{
"epoch": 0.13655681739009268,
"grad_norm": 1.0618565082550049,
"learning_rate": 9.961301544287922e-05,
"loss": 1.7666,
"step": 245
},
{
"epoch": 0.13934369121438026,
"grad_norm": 1.1174343824386597,
"learning_rate": 9.955028148102979e-05,
"loss": 1.7274,
"step": 250
},
{
"epoch": 0.14213056503866786,
"grad_norm": 1.045905351638794,
"learning_rate": 9.948286006103466e-05,
"loss": 1.9156,
"step": 255
},
{
"epoch": 0.14491743886295547,
"grad_norm": 1.1782068014144897,
"learning_rate": 9.941075756096226e-05,
"loss": 1.8142,
"step": 260
},
{
"epoch": 0.14770431268724307,
"grad_norm": 1.0786527395248413,
"learning_rate": 9.933398080171123e-05,
"loss": 1.8206,
"step": 265
},
{
"epoch": 0.15049118651153068,
"grad_norm": 1.0150487422943115,
"learning_rate": 9.925253704636543e-05,
"loss": 1.7779,
"step": 270
},
{
"epoch": 0.15327806033581828,
"grad_norm": 1.0553853511810303,
"learning_rate": 9.916643399950656e-05,
"loss": 1.8223,
"step": 275
},
{
"epoch": 0.1560649341601059,
"grad_norm": 1.0968186855316162,
"learning_rate": 9.907567980648549e-05,
"loss": 1.7834,
"step": 280
},
{
"epoch": 0.1588518079843935,
"grad_norm": 0.9188632369041443,
"learning_rate": 9.898028305265169e-05,
"loss": 1.8808,
"step": 285
},
{
"epoch": 0.1616386818086811,
"grad_norm": 0.9829431772232056,
"learning_rate": 9.888025276254096e-05,
"loss": 1.8455,
"step": 290
},
{
"epoch": 0.1644255556329687,
"grad_norm": 1.034116268157959,
"learning_rate": 9.877559839902184e-05,
"loss": 1.8042,
"step": 295
},
{
"epoch": 0.1672124294572563,
"grad_norm": 1.0451691150665283,
"learning_rate": 9.86663298624003e-05,
"loss": 1.7696,
"step": 300
},
{
"epoch": 0.16999930328154392,
"grad_norm": 1.064620852470398,
"learning_rate": 9.855245748948326e-05,
"loss": 1.8668,
"step": 305
},
{
"epoch": 0.17278617710583152,
"grad_norm": 1.0409430265426636,
"learning_rate": 9.843399205260068e-05,
"loss": 1.8274,
"step": 310
},
{
"epoch": 0.17557305093011913,
"grad_norm": 1.0153954029083252,
"learning_rate": 9.831094475858652e-05,
"loss": 1.8084,
"step": 315
},
{
"epoch": 0.17835992475440673,
"grad_norm": 0.9218955039978027,
"learning_rate": 9.818332724771857e-05,
"loss": 1.8457,
"step": 320
},
{
"epoch": 0.18114679857869434,
"grad_norm": 0.9664631485939026,
"learning_rate": 9.805115159261726e-05,
"loss": 1.772,
"step": 325
},
{
"epoch": 0.18393367240298195,
"grad_norm": 1.0060662031173706,
"learning_rate": 9.791443029710361e-05,
"loss": 1.727,
"step": 330
},
{
"epoch": 0.18672054622726955,
"grad_norm": 1.0184046030044556,
"learning_rate": 9.777317629501636e-05,
"loss": 1.7638,
"step": 335
},
{
"epoch": 0.18950742005155716,
"grad_norm": 0.9374409317970276,
"learning_rate": 9.762740294898846e-05,
"loss": 1.7323,
"step": 340
},
{
"epoch": 0.19229429387584476,
"grad_norm": 0.9715288877487183,
"learning_rate": 9.747712404918286e-05,
"loss": 1.7169,
"step": 345
},
{
"epoch": 0.19508116770013237,
"grad_norm": 1.088680624961853,
"learning_rate": 9.732235381198813e-05,
"loss": 1.8065,
"step": 350
},
{
"epoch": 0.19786804152441997,
"grad_norm": 0.9513164758682251,
"learning_rate": 9.716310687867342e-05,
"loss": 1.6545,
"step": 355
},
{
"epoch": 0.20065491534870758,
"grad_norm": 0.9501610398292542,
"learning_rate": 9.699939831400351e-05,
"loss": 1.8605,
"step": 360
},
{
"epoch": 0.20344178917299519,
"grad_norm": 0.9788233041763306,
"learning_rate": 9.683124360481364e-05,
"loss": 1.7838,
"step": 365
},
{
"epoch": 0.2062286629972828,
"grad_norm": 1.0686471462249756,
"learning_rate": 9.665865865854445e-05,
"loss": 1.7832,
"step": 370
},
{
"epoch": 0.2090155368215704,
"grad_norm": 0.9658113121986389,
"learning_rate": 9.648165980173712e-05,
"loss": 1.7721,
"step": 375
},
{
"epoch": 0.211802410645858,
"grad_norm": 1.0429141521453857,
"learning_rate": 9.630026377848892e-05,
"loss": 1.7741,
"step": 380
},
{
"epoch": 0.2145892844701456,
"grad_norm": 0.9593327641487122,
"learning_rate": 9.611448774886924e-05,
"loss": 1.7534,
"step": 385
},
{
"epoch": 0.2173761582944332,
"grad_norm": 0.9077600240707397,
"learning_rate": 9.592434928729616e-05,
"loss": 1.8398,
"step": 390
},
{
"epoch": 0.22016303211872082,
"grad_norm": 1.048581600189209,
"learning_rate": 9.572986638087396e-05,
"loss": 1.8134,
"step": 395
},
{
"epoch": 0.22294990594300843,
"grad_norm": 0.9498254060745239,
"learning_rate": 9.553105742769154e-05,
"loss": 1.7497,
"step": 400
},
{
"epoch": 0.22573677976729603,
"grad_norm": 1.0249079465866089,
"learning_rate": 9.532794123508197e-05,
"loss": 1.6412,
"step": 405
},
{
"epoch": 0.22852365359158364,
"grad_norm": 0.9723719358444214,
"learning_rate": 9.512053701784329e-05,
"loss": 1.7741,
"step": 410
},
{
"epoch": 0.23131052741587124,
"grad_norm": 0.954607367515564,
"learning_rate": 9.490886439642081e-05,
"loss": 1.7865,
"step": 415
},
{
"epoch": 0.23409740124015885,
"grad_norm": 0.9485211372375488,
"learning_rate": 9.469294339505098e-05,
"loss": 1.813,
"step": 420
},
{
"epoch": 0.23688427506444645,
"grad_norm": 0.9606624841690063,
"learning_rate": 9.447279443986716e-05,
"loss": 1.7426,
"step": 425
},
{
"epoch": 0.23967114888873406,
"grad_norm": 0.9899424910545349,
"learning_rate": 9.424843835696724e-05,
"loss": 1.7802,
"step": 430
},
{
"epoch": 0.24245802271302166,
"grad_norm": 1.0416887998580933,
"learning_rate": 9.401989637044355e-05,
"loss": 1.7418,
"step": 435
},
{
"epoch": 0.24524489653730927,
"grad_norm": 0.958951473236084,
"learning_rate": 9.3787190100375e-05,
"loss": 1.7791,
"step": 440
},
{
"epoch": 0.24803177036159688,
"grad_norm": 0.993934154510498,
"learning_rate": 9.355034156078188e-05,
"loss": 1.739,
"step": 445
},
{
"epoch": 0.2508186441858845,
"grad_norm": 0.9372468590736389,
"learning_rate": 9.330937315754329e-05,
"loss": 1.7406,
"step": 450
},
{
"epoch": 0.2536055180101721,
"grad_norm": 0.9601876735687256,
"learning_rate": 9.306430768627753e-05,
"loss": 1.7357,
"step": 455
},
{
"epoch": 0.2563923918344597,
"grad_norm": 0.9922548532485962,
"learning_rate": 9.281516833018571e-05,
"loss": 1.7677,
"step": 460
},
{
"epoch": 0.2591792656587473,
"grad_norm": 0.9353616833686829,
"learning_rate": 9.256197865785854e-05,
"loss": 1.8202,
"step": 465
},
{
"epoch": 0.26196613948303493,
"grad_norm": 0.8890717625617981,
"learning_rate": 9.230476262104677e-05,
"loss": 1.7473,
"step": 470
},
{
"epoch": 0.26475301330732254,
"grad_norm": 1.0059962272644043,
"learning_rate": 9.204354455239539e-05,
"loss": 1.7978,
"step": 475
},
{
"epoch": 0.26753988713161014,
"grad_norm": 0.9888349771499634,
"learning_rate": 9.177834916314165e-05,
"loss": 1.7481,
"step": 480
},
{
"epoch": 0.27032676095589775,
"grad_norm": 0.9407850503921509,
"learning_rate": 9.150920154077754e-05,
"loss": 1.7667,
"step": 485
},
{
"epoch": 0.27311363478018535,
"grad_norm": 1.0001949071884155,
"learning_rate": 9.123612714667634e-05,
"loss": 1.7742,
"step": 490
},
{
"epoch": 0.2759005086044729,
"grad_norm": 0.9057056307792664,
"learning_rate": 9.095915181368412e-05,
"loss": 1.816,
"step": 495
},
{
"epoch": 0.2786873824287605,
"grad_norm": 1.0183491706848145,
"learning_rate": 9.067830174367586e-05,
"loss": 1.8137,
"step": 500
},
{
"epoch": 0.2814742562530481,
"grad_norm": 0.9340478777885437,
"learning_rate": 9.039360350507679e-05,
"loss": 1.7735,
"step": 505
},
{
"epoch": 0.2842611300773357,
"grad_norm": 0.9671086668968201,
"learning_rate": 9.010508403034898e-05,
"loss": 1.7204,
"step": 510
},
{
"epoch": 0.2870480039016233,
"grad_norm": 0.9643672704696655,
"learning_rate": 8.98127706134436e-05,
"loss": 1.748,
"step": 515
},
{
"epoch": 0.28983487772591093,
"grad_norm": 0.9929302334785461,
"learning_rate": 8.951669090721881e-05,
"loss": 1.7682,
"step": 520
},
{
"epoch": 0.29262175155019854,
"grad_norm": 1.0192108154296875,
"learning_rate": 8.921687292082393e-05,
"loss": 1.6811,
"step": 525
},
{
"epoch": 0.29540862537448614,
"grad_norm": 0.9536918997764587,
"learning_rate": 8.891334501704962e-05,
"loss": 1.7562,
"step": 530
},
{
"epoch": 0.29819549919877375,
"grad_norm": 0.9654401540756226,
"learning_rate": 8.86061359096449e-05,
"loss": 1.7098,
"step": 535
},
{
"epoch": 0.30098237302306136,
"grad_norm": 0.9755784869194031,
"learning_rate": 8.829527466060072e-05,
"loss": 1.5997,
"step": 540
},
{
"epoch": 0.30376924684734896,
"grad_norm": 0.920735776424408,
"learning_rate": 8.798079067740077e-05,
"loss": 1.8432,
"step": 545
},
{
"epoch": 0.30655612067163657,
"grad_norm": 0.9787949323654175,
"learning_rate": 8.766271371023948e-05,
"loss": 1.7575,
"step": 550
},
{
"epoch": 0.3093429944959242,
"grad_norm": 0.9688432812690735,
"learning_rate": 8.73410738492077e-05,
"loss": 1.6978,
"step": 555
},
{
"epoch": 0.3121298683202118,
"grad_norm": 0.9125113487243652,
"learning_rate": 8.701590152144612e-05,
"loss": 1.7075,
"step": 560
},
{
"epoch": 0.3149167421444994,
"grad_norm": 0.954394519329071,
"learning_rate": 8.668722748826693e-05,
"loss": 1.7341,
"step": 565
},
{
"epoch": 0.317703615968787,
"grad_norm": 0.9641663432121277,
"learning_rate": 8.635508284224371e-05,
"loss": 1.84,
"step": 570
},
{
"epoch": 0.3204904897930746,
"grad_norm": 0.974785327911377,
"learning_rate": 8.601949900427016e-05,
"loss": 1.717,
"step": 575
},
{
"epoch": 0.3232773636173622,
"grad_norm": 1.0628243684768677,
"learning_rate": 8.568050772058762e-05,
"loss": 1.7745,
"step": 580
},
{
"epoch": 0.3260642374416498,
"grad_norm": 0.9969517588615417,
"learning_rate": 8.533814105978191e-05,
"loss": 1.7366,
"step": 585
},
{
"epoch": 0.3288511112659374,
"grad_norm": 0.9360251426696777,
"learning_rate": 8.499243140974966e-05,
"loss": 1.7395,
"step": 590
},
{
"epoch": 0.331637985090225,
"grad_norm": 0.9315335154533386,
"learning_rate": 8.464341147463431e-05,
"loss": 1.7478,
"step": 595
},
{
"epoch": 0.3344248589145126,
"grad_norm": 1.008952260017395,
"learning_rate": 8.429111427173241e-05,
"loss": 1.6532,
"step": 600
},
{
"epoch": 0.33721173273880023,
"grad_norm": 0.9224027395248413,
"learning_rate": 8.393557312837018e-05,
"loss": 1.6901,
"step": 605
},
{
"epoch": 0.33999860656308784,
"grad_norm": 1.0089499950408936,
"learning_rate": 8.357682167875062e-05,
"loss": 1.7778,
"step": 610
},
{
"epoch": 0.34278548038737544,
"grad_norm": 1.0609345436096191,
"learning_rate": 8.321489386077192e-05,
"loss": 1.7429,
"step": 615
},
{
"epoch": 0.34557235421166305,
"grad_norm": 0.9656564593315125,
"learning_rate": 8.28498239128167e-05,
"loss": 1.7799,
"step": 620
},
{
"epoch": 0.34835922803595065,
"grad_norm": 0.9876144528388977,
"learning_rate": 8.248164637051321e-05,
"loss": 1.7204,
"step": 625
},
{
"epoch": 0.35114610186023826,
"grad_norm": 0.9239578247070312,
"learning_rate": 8.211039606346826e-05,
"loss": 1.7871,
"step": 630
},
{
"epoch": 0.35393297568452586,
"grad_norm": 0.9991699457168579,
"learning_rate": 8.173610811197226e-05,
"loss": 1.7259,
"step": 635
},
{
"epoch": 0.35671984950881347,
"grad_norm": 0.9193426370620728,
"learning_rate": 8.135881792367686e-05,
"loss": 1.7508,
"step": 640
},
{
"epoch": 0.3595067233331011,
"grad_norm": 0.9434049129486084,
"learning_rate": 8.097856119024545e-05,
"loss": 1.8071,
"step": 645
},
{
"epoch": 0.3622935971573887,
"grad_norm": 0.9454895257949829,
"learning_rate": 8.059537388397665e-05,
"loss": 1.7493,
"step": 650
},
{
"epoch": 0.3650804709816763,
"grad_norm": 0.9811017513275146,
"learning_rate": 8.020929225440137e-05,
"loss": 1.7469,
"step": 655
},
{
"epoch": 0.3678673448059639,
"grad_norm": 0.9470755457878113,
"learning_rate": 7.98203528248536e-05,
"loss": 1.7392,
"step": 660
},
{
"epoch": 0.3706542186302515,
"grad_norm": 1.0244383811950684,
"learning_rate": 7.942859238901528e-05,
"loss": 1.7735,
"step": 665
},
{
"epoch": 0.3734410924545391,
"grad_norm": 1.1164230108261108,
"learning_rate": 7.903404800743564e-05,
"loss": 1.7982,
"step": 670
},
{
"epoch": 0.3762279662788267,
"grad_norm": 1.0754444599151611,
"learning_rate": 7.863675700402526e-05,
"loss": 1.7041,
"step": 675
},
{
"epoch": 0.3790148401031143,
"grad_norm": 0.9588093757629395,
"learning_rate": 7.823675696252524e-05,
"loss": 1.8321,
"step": 680
},
{
"epoch": 0.3818017139274019,
"grad_norm": 0.9360554218292236,
"learning_rate": 7.783408572295174e-05,
"loss": 1.7865,
"step": 685
},
{
"epoch": 0.3845885877516895,
"grad_norm": 0.9670904278755188,
"learning_rate": 7.742878137801639e-05,
"loss": 1.7208,
"step": 690
},
{
"epoch": 0.38737546157597713,
"grad_norm": 0.9358083605766296,
"learning_rate": 7.702088226952258e-05,
"loss": 1.6911,
"step": 695
},
{
"epoch": 0.39016233540026474,
"grad_norm": 1.0316359996795654,
"learning_rate": 7.661042698473853e-05,
"loss": 1.6729,
"step": 700
},
{
"epoch": 0.39294920922455234,
"grad_norm": 0.9509869813919067,
"learning_rate": 7.619745435274667e-05,
"loss": 1.7395,
"step": 705
},
{
"epoch": 0.39573608304883995,
"grad_norm": 0.9687904119491577,
"learning_rate": 7.578200344077073e-05,
"loss": 1.7688,
"step": 710
},
{
"epoch": 0.39852295687312755,
"grad_norm": 0.8772656917572021,
"learning_rate": 7.536411355047964e-05,
"loss": 1.7311,
"step": 715
},
{
"epoch": 0.40130983069741516,
"grad_norm": 0.9465420842170715,
"learning_rate": 7.494382421426984e-05,
"loss": 1.7634,
"step": 720
},
{
"epoch": 0.40409670452170277,
"grad_norm": 0.9126701354980469,
"learning_rate": 7.452117519152542e-05,
"loss": 1.6924,
"step": 725
},
{
"epoch": 0.40688357834599037,
"grad_norm": 1.070681095123291,
"learning_rate": 7.409620646485685e-05,
"loss": 1.6977,
"step": 730
},
{
"epoch": 0.409670452170278,
"grad_norm": 0.9621564149856567,
"learning_rate": 7.36689582363187e-05,
"loss": 1.7579,
"step": 735
},
{
"epoch": 0.4124573259945656,
"grad_norm": 1.0299642086029053,
"learning_rate": 7.323947092360649e-05,
"loss": 1.6608,
"step": 740
},
{
"epoch": 0.4152441998188532,
"grad_norm": 1.0028384923934937,
"learning_rate": 7.280778515623314e-05,
"loss": 1.8124,
"step": 745
},
{
"epoch": 0.4180310736431408,
"grad_norm": 0.9672207832336426,
"learning_rate": 7.237394177168548e-05,
"loss": 1.7581,
"step": 750
},
{
"epoch": 0.4208179474674284,
"grad_norm": 1.0683056116104126,
"learning_rate": 7.193798181156095e-05,
"loss": 1.7852,
"step": 755
},
{
"epoch": 0.423604821291716,
"grad_norm": 1.023703694343567,
"learning_rate": 7.149994651768514e-05,
"loss": 1.6159,
"step": 760
},
{
"epoch": 0.4263916951160036,
"grad_norm": 1.0113016366958618,
"learning_rate": 7.10598773282103e-05,
"loss": 1.7385,
"step": 765
},
{
"epoch": 0.4291785689402912,
"grad_norm": 1.0289918184280396,
"learning_rate": 7.061781587369519e-05,
"loss": 1.8094,
"step": 770
},
{
"epoch": 0.4319654427645788,
"grad_norm": 0.9700524806976318,
"learning_rate": 7.017380397316695e-05,
"loss": 1.6953,
"step": 775
},
{
"epoch": 0.4347523165888664,
"grad_norm": 0.9488673806190491,
"learning_rate": 6.972788363016497e-05,
"loss": 1.6345,
"step": 780
},
{
"epoch": 0.43753919041315403,
"grad_norm": 0.99649977684021,
"learning_rate": 6.92800970287674e-05,
"loss": 1.7524,
"step": 785
},
{
"epoch": 0.44032606423744164,
"grad_norm": 0.9158934354782104,
"learning_rate": 6.883048652960038e-05,
"loss": 1.7326,
"step": 790
},
{
"epoch": 0.44311293806172924,
"grad_norm": 0.9467411637306213,
"learning_rate": 6.837909466583095e-05,
"loss": 1.7519,
"step": 795
},
{
"epoch": 0.44589981188601685,
"grad_norm": 0.8946711421012878,
"learning_rate": 6.792596413914324e-05,
"loss": 1.6291,
"step": 800
},
{
"epoch": 0.44868668571030446,
"grad_norm": 0.9915565848350525,
"learning_rate": 6.747113781569892e-05,
"loss": 1.757,
"step": 805
},
{
"epoch": 0.45147355953459206,
"grad_norm": 0.9836114645004272,
"learning_rate": 6.701465872208216e-05,
"loss": 1.8026,
"step": 810
},
{
"epoch": 0.45426043335887967,
"grad_norm": 0.9982685446739197,
"learning_rate": 6.655657004122916e-05,
"loss": 1.7819,
"step": 815
},
{
"epoch": 0.4570473071831673,
"grad_norm": 1.0257214307785034,
"learning_rate": 6.60969151083432e-05,
"loss": 1.719,
"step": 820
},
{
"epoch": 0.4598341810074549,
"grad_norm": 0.9735772013664246,
"learning_rate": 6.563573740679496e-05,
"loss": 1.7153,
"step": 825
},
{
"epoch": 0.4626210548317425,
"grad_norm": 0.9777944684028625,
"learning_rate": 6.517308056400917e-05,
"loss": 1.7256,
"step": 830
},
{
"epoch": 0.4654079286560301,
"grad_norm": 0.9858867526054382,
"learning_rate": 6.470898834733731e-05,
"loss": 1.7,
"step": 835
},
{
"epoch": 0.4681948024803177,
"grad_norm": 0.9058387875556946,
"learning_rate": 6.42435046599173e-05,
"loss": 1.7095,
"step": 840
},
{
"epoch": 0.4709816763046053,
"grad_norm": 1.0151069164276123,
"learning_rate": 6.377667353652022e-05,
"loss": 1.7606,
"step": 845
},
{
"epoch": 0.4737685501288929,
"grad_norm": 0.9841256141662598,
"learning_rate": 6.330853913938466e-05,
"loss": 1.7015,
"step": 850
},
{
"epoch": 0.4765554239531805,
"grad_norm": 0.9631791710853577,
"learning_rate": 6.283914575403888e-05,
"loss": 1.7847,
"step": 855
},
{
"epoch": 0.4793422977774681,
"grad_norm": 1.1236021518707275,
"learning_rate": 6.236853778511156e-05,
"loss": 1.7388,
"step": 860
},
{
"epoch": 0.4821291716017557,
"grad_norm": 1.0226027965545654,
"learning_rate": 6.189675975213094e-05,
"loss": 1.6993,
"step": 865
},
{
"epoch": 0.48491604542604333,
"grad_norm": 1.0021902322769165,
"learning_rate": 6.142385628531342e-05,
"loss": 1.753,
"step": 870
},
{
"epoch": 0.48770291925033094,
"grad_norm": 0.9932888746261597,
"learning_rate": 6.09498721213414e-05,
"loss": 1.6798,
"step": 875
},
{
"epoch": 0.49048979307461854,
"grad_norm": 1.007003664970398,
"learning_rate": 6.047485209913137e-05,
"loss": 1.8083,
"step": 880
},
{
"epoch": 0.49327666689890615,
"grad_norm": 0.9325096011161804,
"learning_rate": 5.999884115559192e-05,
"loss": 1.7057,
"step": 885
},
{
"epoch": 0.49606354072319375,
"grad_norm": 0.9602507948875427,
"learning_rate": 5.952188432137293e-05,
"loss": 1.7063,
"step": 890
},
{
"epoch": 0.49885041454748136,
"grad_norm": 0.814627468585968,
"learning_rate": 5.90440267166055e-05,
"loss": 1.6748,
"step": 895
},
{
"epoch": 0.501637288371769,
"grad_norm": 1.0444878339767456,
"learning_rate": 5.8565313546633684e-05,
"loss": 1.7389,
"step": 900
},
{
"epoch": 0.5044241621960566,
"grad_norm": 0.8829376101493835,
"learning_rate": 5.8085790097738025e-05,
"loss": 1.7323,
"step": 905
},
{
"epoch": 0.5072110360203442,
"grad_norm": 0.9832122325897217,
"learning_rate": 5.7605501732851475e-05,
"loss": 1.7698,
"step": 910
},
{
"epoch": 0.5099979098446318,
"grad_norm": 0.8969665169715881,
"learning_rate": 5.712449388726807e-05,
"loss": 1.7473,
"step": 915
},
{
"epoch": 0.5127847836689194,
"grad_norm": 0.9865416884422302,
"learning_rate": 5.664281206434472e-05,
"loss": 1.6655,
"step": 920
},
{
"epoch": 0.515571657493207,
"grad_norm": 0.9947900176048279,
"learning_rate": 5.616050183119663e-05,
"loss": 1.7719,
"step": 925
},
{
"epoch": 0.5183585313174947,
"grad_norm": 0.9595984816551208,
"learning_rate": 5.5677608814386616e-05,
"loss": 1.6078,
"step": 930
},
{
"epoch": 0.5211454051417822,
"grad_norm": 1.0105018615722656,
"learning_rate": 5.519417869560889e-05,
"loss": 1.7251,
"step": 935
},
{
"epoch": 0.5239322789660699,
"grad_norm": 1.039826512336731,
"learning_rate": 5.471025720736747e-05,
"loss": 1.7688,
"step": 940
},
{
"epoch": 0.5267191527903574,
"grad_norm": 0.9929054379463196,
"learning_rate": 5.422589012864996e-05,
"loss": 1.7562,
"step": 945
},
{
"epoch": 0.5295060266146451,
"grad_norm": 1.084277629852295,
"learning_rate": 5.3741123280596864e-05,
"loss": 1.6752,
"step": 950
},
{
"epoch": 0.5322929004389326,
"grad_norm": 1.0061899423599243,
"learning_rate": 5.325600252216685e-05,
"loss": 1.7075,
"step": 955
},
{
"epoch": 0.5350797742632203,
"grad_norm": 0.9747031927108765,
"learning_rate": 5.27705737457985e-05,
"loss": 1.6154,
"step": 960
},
{
"epoch": 0.5378666480875078,
"grad_norm": 1.0520727634429932,
"learning_rate": 5.228488287306896e-05,
"loss": 1.6982,
"step": 965
},
{
"epoch": 0.5406535219117955,
"grad_norm": 0.9064339995384216,
"learning_rate": 5.179897585034963e-05,
"loss": 1.7331,
"step": 970
},
{
"epoch": 0.543440395736083,
"grad_norm": 0.9782255291938782,
"learning_rate": 5.1312898644459776e-05,
"loss": 1.6223,
"step": 975
},
{
"epoch": 0.5462272695603707,
"grad_norm": 0.9979589581489563,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.7069,
"step": 980
},
{
"epoch": 0.5490141433846583,
"grad_norm": 0.9500666260719299,
"learning_rate": 5.0340417626592016e-05,
"loss": 1.6931,
"step": 985
},
{
"epoch": 0.5518010172089458,
"grad_norm": 1.0122525691986084,
"learning_rate": 4.9854105811348216e-05,
"loss": 1.745,
"step": 990
},
{
"epoch": 0.5545878910332335,
"grad_norm": 1.0289945602416992,
"learning_rate": 4.936780779769913e-05,
"loss": 1.729,
"step": 995
},
{
"epoch": 0.557374764857521,
"grad_norm": 1.014304280281067,
"learning_rate": 4.888156958945174e-05,
"loss": 1.7108,
"step": 1000
}
],
"logging_steps": 5,
"max_steps": 1795,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 4.492061751902208e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}