dpsk-r1-dis-llama-8b_eqa_lora_sft / trainer_state.json
hexuan21's picture
Upload folder using huggingface_hub
d4dc4b2 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1795,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0027868738242876052,
"grad_norm": 1.3125083446502686,
"learning_rate": 2.2222222222222225e-06,
"loss": 2.2127,
"step": 5
},
{
"epoch": 0.0055737476485752105,
"grad_norm": 1.2902835607528687,
"learning_rate": 5e-06,
"loss": 2.1685,
"step": 10
},
{
"epoch": 0.008360621472862817,
"grad_norm": 1.260772466659546,
"learning_rate": 7.777777777777777e-06,
"loss": 2.1734,
"step": 15
},
{
"epoch": 0.011147495297150421,
"grad_norm": 1.2492824792861938,
"learning_rate": 1.0555555555555555e-05,
"loss": 2.1881,
"step": 20
},
{
"epoch": 0.013934369121438027,
"grad_norm": 1.8405438661575317,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.1732,
"step": 25
},
{
"epoch": 0.016721242945725634,
"grad_norm": 2.053272247314453,
"learning_rate": 1.6111111111111115e-05,
"loss": 2.1535,
"step": 30
},
{
"epoch": 0.019508116770013236,
"grad_norm": 1.6805298328399658,
"learning_rate": 1.888888888888889e-05,
"loss": 1.9838,
"step": 35
},
{
"epoch": 0.022294990594300842,
"grad_norm": 1.5838550329208374,
"learning_rate": 2.1666666666666667e-05,
"loss": 1.7728,
"step": 40
},
{
"epoch": 0.025081864418588447,
"grad_norm": 1.1088097095489502,
"learning_rate": 2.4444444444444445e-05,
"loss": 1.7897,
"step": 45
},
{
"epoch": 0.027868738242876053,
"grad_norm": 1.060654878616333,
"learning_rate": 2.7222222222222223e-05,
"loss": 1.6669,
"step": 50
},
{
"epoch": 0.03065561206716366,
"grad_norm": 0.9146080017089844,
"learning_rate": 3e-05,
"loss": 1.5346,
"step": 55
},
{
"epoch": 0.03344248589145127,
"grad_norm": 0.811827540397644,
"learning_rate": 3.277777777777778e-05,
"loss": 1.6357,
"step": 60
},
{
"epoch": 0.03622935971573887,
"grad_norm": 1.025479793548584,
"learning_rate": 3.555555555555556e-05,
"loss": 1.5798,
"step": 65
},
{
"epoch": 0.03901623354002647,
"grad_norm": 0.8861313462257385,
"learning_rate": 3.8333333333333334e-05,
"loss": 1.4825,
"step": 70
},
{
"epoch": 0.04180310736431408,
"grad_norm": 1.0417464971542358,
"learning_rate": 4.111111111111111e-05,
"loss": 1.5584,
"step": 75
},
{
"epoch": 0.044589981188601684,
"grad_norm": 0.9840788245201111,
"learning_rate": 4.388888888888889e-05,
"loss": 1.4355,
"step": 80
},
{
"epoch": 0.04737685501288929,
"grad_norm": 0.9761689901351929,
"learning_rate": 4.666666666666667e-05,
"loss": 1.5785,
"step": 85
},
{
"epoch": 0.050163728837176895,
"grad_norm": 1.0217355489730835,
"learning_rate": 4.9444444444444446e-05,
"loss": 1.477,
"step": 90
},
{
"epoch": 0.0529506026614645,
"grad_norm": 1.0723602771759033,
"learning_rate": 5.222222222222223e-05,
"loss": 1.4874,
"step": 95
},
{
"epoch": 0.055737476485752106,
"grad_norm": 1.0415840148925781,
"learning_rate": 5.500000000000001e-05,
"loss": 1.3867,
"step": 100
},
{
"epoch": 0.05852435031003971,
"grad_norm": 0.9482999444007874,
"learning_rate": 5.7777777777777776e-05,
"loss": 1.4529,
"step": 105
},
{
"epoch": 0.06131122413432732,
"grad_norm": 1.2104490995407104,
"learning_rate": 6.055555555555555e-05,
"loss": 1.5199,
"step": 110
},
{
"epoch": 0.06409809795861493,
"grad_norm": 1.095499873161316,
"learning_rate": 6.333333333333333e-05,
"loss": 1.4173,
"step": 115
},
{
"epoch": 0.06688497178290254,
"grad_norm": 1.0751917362213135,
"learning_rate": 6.611111111111111e-05,
"loss": 1.4632,
"step": 120
},
{
"epoch": 0.06967184560719013,
"grad_norm": 1.1421129703521729,
"learning_rate": 6.88888888888889e-05,
"loss": 1.4691,
"step": 125
},
{
"epoch": 0.07245871943147773,
"grad_norm": 1.0927807092666626,
"learning_rate": 7.166666666666667e-05,
"loss": 1.4509,
"step": 130
},
{
"epoch": 0.07524559325576534,
"grad_norm": 1.067568302154541,
"learning_rate": 7.444444444444444e-05,
"loss": 1.4235,
"step": 135
},
{
"epoch": 0.07803246708005294,
"grad_norm": 1.159364104270935,
"learning_rate": 7.722222222222223e-05,
"loss": 1.4362,
"step": 140
},
{
"epoch": 0.08081934090434055,
"grad_norm": 1.0486923456192017,
"learning_rate": 8e-05,
"loss": 1.503,
"step": 145
},
{
"epoch": 0.08360621472862816,
"grad_norm": 1.1524556875228882,
"learning_rate": 8.277777777777778e-05,
"loss": 1.4556,
"step": 150
},
{
"epoch": 0.08639308855291576,
"grad_norm": 1.0299068689346313,
"learning_rate": 8.555555555555556e-05,
"loss": 1.3988,
"step": 155
},
{
"epoch": 0.08917996237720337,
"grad_norm": 1.0863871574401855,
"learning_rate": 8.833333333333333e-05,
"loss": 1.37,
"step": 160
},
{
"epoch": 0.09196683620149097,
"grad_norm": 1.1330057382583618,
"learning_rate": 9.111111111111112e-05,
"loss": 1.3879,
"step": 165
},
{
"epoch": 0.09475371002577858,
"grad_norm": 1.0953528881072998,
"learning_rate": 9.388888888888889e-05,
"loss": 1.415,
"step": 170
},
{
"epoch": 0.09754058385006618,
"grad_norm": 1.0204545259475708,
"learning_rate": 9.666666666666667e-05,
"loss": 1.4199,
"step": 175
},
{
"epoch": 0.10032745767435379,
"grad_norm": 1.0416138172149658,
"learning_rate": 9.944444444444446e-05,
"loss": 1.3911,
"step": 180
},
{
"epoch": 0.1031143314986414,
"grad_norm": 1.0255354642868042,
"learning_rate": 9.999848639521432e-05,
"loss": 1.382,
"step": 185
},
{
"epoch": 0.105901205322929,
"grad_norm": 1.0507235527038574,
"learning_rate": 9.999233753283091e-05,
"loss": 1.3531,
"step": 190
},
{
"epoch": 0.1086880791472166,
"grad_norm": 1.1468594074249268,
"learning_rate": 9.998145939378577e-05,
"loss": 1.3873,
"step": 195
},
{
"epoch": 0.11147495297150421,
"grad_norm": 1.1430379152297974,
"learning_rate": 9.996585300715116e-05,
"loss": 1.4215,
"step": 200
},
{
"epoch": 0.11426182679579182,
"grad_norm": 1.029249668121338,
"learning_rate": 9.994551984929175e-05,
"loss": 1.3678,
"step": 205
},
{
"epoch": 0.11704870062007942,
"grad_norm": 0.9233781099319458,
"learning_rate": 9.992046184372492e-05,
"loss": 1.403,
"step": 210
},
{
"epoch": 0.11983557444436703,
"grad_norm": 0.9915686845779419,
"learning_rate": 9.989068136093873e-05,
"loss": 1.3518,
"step": 215
},
{
"epoch": 0.12262244826865464,
"grad_norm": 0.9875094294548035,
"learning_rate": 9.985618121816779e-05,
"loss": 1.4272,
"step": 220
},
{
"epoch": 0.12540932209294225,
"grad_norm": 0.9711189866065979,
"learning_rate": 9.981696467912664e-05,
"loss": 1.3453,
"step": 225
},
{
"epoch": 0.12819619591722986,
"grad_norm": 1.0352520942687988,
"learning_rate": 9.97730354537011e-05,
"loss": 1.3668,
"step": 230
},
{
"epoch": 0.13098306974151747,
"grad_norm": 0.957478940486908,
"learning_rate": 9.972439769759722e-05,
"loss": 1.3027,
"step": 235
},
{
"epoch": 0.13376994356580507,
"grad_norm": 1.0086779594421387,
"learning_rate": 9.967105601194823e-05,
"loss": 1.4556,
"step": 240
},
{
"epoch": 0.13655681739009268,
"grad_norm": 0.9436930418014526,
"learning_rate": 9.961301544287922e-05,
"loss": 1.3322,
"step": 245
},
{
"epoch": 0.13934369121438026,
"grad_norm": 1.000581979751587,
"learning_rate": 9.955028148102979e-05,
"loss": 1.303,
"step": 250
},
{
"epoch": 0.14213056503866786,
"grad_norm": 0.9896969795227051,
"learning_rate": 9.948286006103466e-05,
"loss": 1.4694,
"step": 255
},
{
"epoch": 0.14491743886295547,
"grad_norm": 1.0205310583114624,
"learning_rate": 9.941075756096226e-05,
"loss": 1.36,
"step": 260
},
{
"epoch": 0.14770431268724307,
"grad_norm": 1.0231329202651978,
"learning_rate": 9.933398080171123e-05,
"loss": 1.3808,
"step": 265
},
{
"epoch": 0.15049118651153068,
"grad_norm": 0.9146262407302856,
"learning_rate": 9.925253704636543e-05,
"loss": 1.3177,
"step": 270
},
{
"epoch": 0.15327806033581828,
"grad_norm": 0.9757639765739441,
"learning_rate": 9.916643399950656e-05,
"loss": 1.3462,
"step": 275
},
{
"epoch": 0.1560649341601059,
"grad_norm": 0.9955347180366516,
"learning_rate": 9.907567980648549e-05,
"loss": 1.3365,
"step": 280
},
{
"epoch": 0.1588518079843935,
"grad_norm": 0.9526458978652954,
"learning_rate": 9.898028305265169e-05,
"loss": 1.4223,
"step": 285
},
{
"epoch": 0.1616386818086811,
"grad_norm": 0.8748807907104492,
"learning_rate": 9.888025276254096e-05,
"loss": 1.3659,
"step": 290
},
{
"epoch": 0.1644255556329687,
"grad_norm": 0.9113283157348633,
"learning_rate": 9.877559839902184e-05,
"loss": 1.3677,
"step": 295
},
{
"epoch": 0.1672124294572563,
"grad_norm": 0.9735001921653748,
"learning_rate": 9.86663298624003e-05,
"loss": 1.3083,
"step": 300
},
{
"epoch": 0.16999930328154392,
"grad_norm": 0.9326124787330627,
"learning_rate": 9.855245748948326e-05,
"loss": 1.3757,
"step": 305
},
{
"epoch": 0.17278617710583152,
"grad_norm": 0.8787973523139954,
"learning_rate": 9.843399205260068e-05,
"loss": 1.36,
"step": 310
},
{
"epoch": 0.17557305093011913,
"grad_norm": 1.017393708229065,
"learning_rate": 9.831094475858652e-05,
"loss": 1.3754,
"step": 315
},
{
"epoch": 0.17835992475440673,
"grad_norm": 0.8852056264877319,
"learning_rate": 9.818332724771857e-05,
"loss": 1.4008,
"step": 320
},
{
"epoch": 0.18114679857869434,
"grad_norm": 0.9435309171676636,
"learning_rate": 9.805115159261726e-05,
"loss": 1.3145,
"step": 325
},
{
"epoch": 0.18393367240298195,
"grad_norm": 0.9178583025932312,
"learning_rate": 9.791443029710361e-05,
"loss": 1.3052,
"step": 330
},
{
"epoch": 0.18672054622726955,
"grad_norm": 0.9663990139961243,
"learning_rate": 9.777317629501636e-05,
"loss": 1.3237,
"step": 335
},
{
"epoch": 0.18950742005155716,
"grad_norm": 0.8486679792404175,
"learning_rate": 9.762740294898846e-05,
"loss": 1.2913,
"step": 340
},
{
"epoch": 0.19229429387584476,
"grad_norm": 0.960027277469635,
"learning_rate": 9.747712404918286e-05,
"loss": 1.2583,
"step": 345
},
{
"epoch": 0.19508116770013237,
"grad_norm": 1.0241199731826782,
"learning_rate": 9.732235381198813e-05,
"loss": 1.3535,
"step": 350
},
{
"epoch": 0.19786804152441997,
"grad_norm": 0.8933882713317871,
"learning_rate": 9.716310687867342e-05,
"loss": 1.2532,
"step": 355
},
{
"epoch": 0.20065491534870758,
"grad_norm": 0.917148232460022,
"learning_rate": 9.699939831400351e-05,
"loss": 1.4276,
"step": 360
},
{
"epoch": 0.20344178917299519,
"grad_norm": 0.9412631392478943,
"learning_rate": 9.683124360481364e-05,
"loss": 1.3184,
"step": 365
},
{
"epoch": 0.2062286629972828,
"grad_norm": 0.9783531427383423,
"learning_rate": 9.665865865854445e-05,
"loss": 1.3137,
"step": 370
},
{
"epoch": 0.2090155368215704,
"grad_norm": 0.933350682258606,
"learning_rate": 9.648165980173712e-05,
"loss": 1.3405,
"step": 375
},
{
"epoch": 0.211802410645858,
"grad_norm": 0.9554056525230408,
"learning_rate": 9.630026377848892e-05,
"loss": 1.3246,
"step": 380
},
{
"epoch": 0.2145892844701456,
"grad_norm": 0.8970703482627869,
"learning_rate": 9.611448774886924e-05,
"loss": 1.325,
"step": 385
},
{
"epoch": 0.2173761582944332,
"grad_norm": 0.9755475521087646,
"learning_rate": 9.592434928729616e-05,
"loss": 1.3922,
"step": 390
},
{
"epoch": 0.22016303211872082,
"grad_norm": 0.9652612805366516,
"learning_rate": 9.572986638087396e-05,
"loss": 1.3513,
"step": 395
},
{
"epoch": 0.22294990594300843,
"grad_norm": 0.9211638569831848,
"learning_rate": 9.553105742769154e-05,
"loss": 1.3104,
"step": 400
},
{
"epoch": 0.22573677976729603,
"grad_norm": 0.9684194326400757,
"learning_rate": 9.532794123508197e-05,
"loss": 1.23,
"step": 405
},
{
"epoch": 0.22852365359158364,
"grad_norm": 0.9077541828155518,
"learning_rate": 9.512053701784329e-05,
"loss": 1.3236,
"step": 410
},
{
"epoch": 0.23131052741587124,
"grad_norm": 0.9119937419891357,
"learning_rate": 9.490886439642081e-05,
"loss": 1.3159,
"step": 415
},
{
"epoch": 0.23409740124015885,
"grad_norm": 0.9030479192733765,
"learning_rate": 9.469294339505098e-05,
"loss": 1.3789,
"step": 420
},
{
"epoch": 0.23688427506444645,
"grad_norm": 0.9020025134086609,
"learning_rate": 9.447279443986716e-05,
"loss": 1.2921,
"step": 425
},
{
"epoch": 0.23967114888873406,
"grad_norm": 0.980591356754303,
"learning_rate": 9.424843835696724e-05,
"loss": 1.3361,
"step": 430
},
{
"epoch": 0.24245802271302166,
"grad_norm": 1.0082863569259644,
"learning_rate": 9.401989637044355e-05,
"loss": 1.2721,
"step": 435
},
{
"epoch": 0.24524489653730927,
"grad_norm": 0.9218441843986511,
"learning_rate": 9.3787190100375e-05,
"loss": 1.3214,
"step": 440
},
{
"epoch": 0.24803177036159688,
"grad_norm": 0.8562553524971008,
"learning_rate": 9.355034156078188e-05,
"loss": 1.2835,
"step": 445
},
{
"epoch": 0.2508186441858845,
"grad_norm": 0.8887034058570862,
"learning_rate": 9.330937315754329e-05,
"loss": 1.2917,
"step": 450
},
{
"epoch": 0.2536055180101721,
"grad_norm": 0.944468080997467,
"learning_rate": 9.306430768627753e-05,
"loss": 1.2844,
"step": 455
},
{
"epoch": 0.2563923918344597,
"grad_norm": 0.9446823000907898,
"learning_rate": 9.281516833018571e-05,
"loss": 1.2999,
"step": 460
},
{
"epoch": 0.2591792656587473,
"grad_norm": 0.9115864634513855,
"learning_rate": 9.256197865785854e-05,
"loss": 1.3846,
"step": 465
},
{
"epoch": 0.26196613948303493,
"grad_norm": 0.8051035404205322,
"learning_rate": 9.230476262104677e-05,
"loss": 1.3087,
"step": 470
},
{
"epoch": 0.26475301330732254,
"grad_norm": 0.9236623048782349,
"learning_rate": 9.204354455239539e-05,
"loss": 1.337,
"step": 475
},
{
"epoch": 0.26753988713161014,
"grad_norm": 0.9063863754272461,
"learning_rate": 9.177834916314165e-05,
"loss": 1.327,
"step": 480
},
{
"epoch": 0.27032676095589775,
"grad_norm": 0.8260522484779358,
"learning_rate": 9.150920154077754e-05,
"loss": 1.2957,
"step": 485
},
{
"epoch": 0.27311363478018535,
"grad_norm": 0.903109610080719,
"learning_rate": 9.123612714667634e-05,
"loss": 1.3345,
"step": 490
},
{
"epoch": 0.2759005086044729,
"grad_norm": 0.8636733293533325,
"learning_rate": 9.095915181368412e-05,
"loss": 1.3918,
"step": 495
},
{
"epoch": 0.2786873824287605,
"grad_norm": 0.9395173788070679,
"learning_rate": 9.067830174367586e-05,
"loss": 1.3573,
"step": 500
},
{
"epoch": 0.2814742562530481,
"grad_norm": 0.8924953937530518,
"learning_rate": 9.039360350507679e-05,
"loss": 1.3344,
"step": 505
},
{
"epoch": 0.2842611300773357,
"grad_norm": 0.8831427097320557,
"learning_rate": 9.010508403034898e-05,
"loss": 1.3086,
"step": 510
},
{
"epoch": 0.2870480039016233,
"grad_norm": 0.8781440854072571,
"learning_rate": 8.98127706134436e-05,
"loss": 1.3186,
"step": 515
},
{
"epoch": 0.28983487772591093,
"grad_norm": 0.9398754835128784,
"learning_rate": 8.951669090721881e-05,
"loss": 1.308,
"step": 520
},
{
"epoch": 0.29262175155019854,
"grad_norm": 0.9422699213027954,
"learning_rate": 8.921687292082393e-05,
"loss": 1.2642,
"step": 525
},
{
"epoch": 0.29540862537448614,
"grad_norm": 0.8490906357765198,
"learning_rate": 8.891334501704962e-05,
"loss": 1.3098,
"step": 530
},
{
"epoch": 0.29819549919877375,
"grad_norm": 0.9390639662742615,
"learning_rate": 8.86061359096449e-05,
"loss": 1.2832,
"step": 535
},
{
"epoch": 0.30098237302306136,
"grad_norm": 0.9434688687324524,
"learning_rate": 8.829527466060072e-05,
"loss": 1.1985,
"step": 540
},
{
"epoch": 0.30376924684734896,
"grad_norm": 0.8724851608276367,
"learning_rate": 8.798079067740077e-05,
"loss": 1.3901,
"step": 545
},
{
"epoch": 0.30655612067163657,
"grad_norm": 0.9250208139419556,
"learning_rate": 8.766271371023948e-05,
"loss": 1.2924,
"step": 550
},
{
"epoch": 0.3093429944959242,
"grad_norm": 0.9672542810440063,
"learning_rate": 8.73410738492077e-05,
"loss": 1.2702,
"step": 555
},
{
"epoch": 0.3121298683202118,
"grad_norm": 0.90570467710495,
"learning_rate": 8.701590152144612e-05,
"loss": 1.2631,
"step": 560
},
{
"epoch": 0.3149167421444994,
"grad_norm": 0.8750013113021851,
"learning_rate": 8.668722748826693e-05,
"loss": 1.2645,
"step": 565
},
{
"epoch": 0.317703615968787,
"grad_norm": 0.903086245059967,
"learning_rate": 8.635508284224371e-05,
"loss": 1.38,
"step": 570
},
{
"epoch": 0.3204904897930746,
"grad_norm": 0.8661080598831177,
"learning_rate": 8.601949900427016e-05,
"loss": 1.2704,
"step": 575
},
{
"epoch": 0.3232773636173622,
"grad_norm": 0.9066647887229919,
"learning_rate": 8.568050772058762e-05,
"loss": 1.2938,
"step": 580
},
{
"epoch": 0.3260642374416498,
"grad_norm": 0.8687067627906799,
"learning_rate": 8.533814105978191e-05,
"loss": 1.2757,
"step": 585
},
{
"epoch": 0.3288511112659374,
"grad_norm": 0.8991963863372803,
"learning_rate": 8.499243140974966e-05,
"loss": 1.2832,
"step": 590
},
{
"epoch": 0.331637985090225,
"grad_norm": 0.8930802345275879,
"learning_rate": 8.464341147463431e-05,
"loss": 1.2754,
"step": 595
},
{
"epoch": 0.3344248589145126,
"grad_norm": 0.9218065738677979,
"learning_rate": 8.429111427173241e-05,
"loss": 1.2417,
"step": 600
},
{
"epoch": 0.33721173273880023,
"grad_norm": 0.851839542388916,
"learning_rate": 8.393557312837018e-05,
"loss": 1.2424,
"step": 605
},
{
"epoch": 0.33999860656308784,
"grad_norm": 0.8438836336135864,
"learning_rate": 8.357682167875062e-05,
"loss": 1.3203,
"step": 610
},
{
"epoch": 0.34278548038737544,
"grad_norm": 0.926641047000885,
"learning_rate": 8.321489386077192e-05,
"loss": 1.2793,
"step": 615
},
{
"epoch": 0.34557235421166305,
"grad_norm": 0.8907529711723328,
"learning_rate": 8.28498239128167e-05,
"loss": 1.2911,
"step": 620
},
{
"epoch": 0.34835922803595065,
"grad_norm": 0.9093756675720215,
"learning_rate": 8.248164637051321e-05,
"loss": 1.2544,
"step": 625
},
{
"epoch": 0.35114610186023826,
"grad_norm": 0.8902727961540222,
"learning_rate": 8.211039606346826e-05,
"loss": 1.3249,
"step": 630
},
{
"epoch": 0.35393297568452586,
"grad_norm": 0.8554810285568237,
"learning_rate": 8.173610811197226e-05,
"loss": 1.2805,
"step": 635
},
{
"epoch": 0.35671984950881347,
"grad_norm": 0.864427387714386,
"learning_rate": 8.135881792367686e-05,
"loss": 1.3051,
"step": 640
},
{
"epoch": 0.3595067233331011,
"grad_norm": 0.925584077835083,
"learning_rate": 8.097856119024545e-05,
"loss": 1.3623,
"step": 645
},
{
"epoch": 0.3622935971573887,
"grad_norm": 0.8400620222091675,
"learning_rate": 8.059537388397665e-05,
"loss": 1.2708,
"step": 650
},
{
"epoch": 0.3650804709816763,
"grad_norm": 0.9252070784568787,
"learning_rate": 8.020929225440137e-05,
"loss": 1.3025,
"step": 655
},
{
"epoch": 0.3678673448059639,
"grad_norm": 0.8931984305381775,
"learning_rate": 7.98203528248536e-05,
"loss": 1.2877,
"step": 660
},
{
"epoch": 0.3706542186302515,
"grad_norm": 0.888062059879303,
"learning_rate": 7.942859238901528e-05,
"loss": 1.3231,
"step": 665
},
{
"epoch": 0.3734410924545391,
"grad_norm": 1.0426568984985352,
"learning_rate": 7.903404800743564e-05,
"loss": 1.3333,
"step": 670
},
{
"epoch": 0.3762279662788267,
"grad_norm": 0.994853138923645,
"learning_rate": 7.863675700402526e-05,
"loss": 1.2642,
"step": 675
},
{
"epoch": 0.3790148401031143,
"grad_norm": 0.9480583667755127,
"learning_rate": 7.823675696252524e-05,
"loss": 1.3738,
"step": 680
},
{
"epoch": 0.3818017139274019,
"grad_norm": 0.8688267469406128,
"learning_rate": 7.783408572295174e-05,
"loss": 1.3444,
"step": 685
},
{
"epoch": 0.3845885877516895,
"grad_norm": 0.8878870010375977,
"learning_rate": 7.742878137801639e-05,
"loss": 1.2826,
"step": 690
},
{
"epoch": 0.38737546157597713,
"grad_norm": 0.9165365099906921,
"learning_rate": 7.702088226952258e-05,
"loss": 1.282,
"step": 695
},
{
"epoch": 0.39016233540026474,
"grad_norm": 0.9026569724082947,
"learning_rate": 7.661042698473853e-05,
"loss": 1.2294,
"step": 700
},
{
"epoch": 0.39294920922455234,
"grad_norm": 0.8386527299880981,
"learning_rate": 7.619745435274667e-05,
"loss": 1.2249,
"step": 705
},
{
"epoch": 0.39573608304883995,
"grad_norm": 0.8767593502998352,
"learning_rate": 7.578200344077073e-05,
"loss": 1.2863,
"step": 710
},
{
"epoch": 0.39852295687312755,
"grad_norm": 0.8485695719718933,
"learning_rate": 7.536411355047964e-05,
"loss": 1.2873,
"step": 715
},
{
"epoch": 0.40130983069741516,
"grad_norm": 0.8822951912879944,
"learning_rate": 7.494382421426984e-05,
"loss": 1.3214,
"step": 720
},
{
"epoch": 0.40409670452170277,
"grad_norm": 0.8770014643669128,
"learning_rate": 7.452117519152542e-05,
"loss": 1.2389,
"step": 725
},
{
"epoch": 0.40688357834599037,
"grad_norm": 0.9898686408996582,
"learning_rate": 7.409620646485685e-05,
"loss": 1.2573,
"step": 730
},
{
"epoch": 0.409670452170278,
"grad_norm": 0.8657426834106445,
"learning_rate": 7.36689582363187e-05,
"loss": 1.2907,
"step": 735
},
{
"epoch": 0.4124573259945656,
"grad_norm": 0.8856871128082275,
"learning_rate": 7.323947092360649e-05,
"loss": 1.2291,
"step": 740
},
{
"epoch": 0.4152441998188532,
"grad_norm": 0.9170464277267456,
"learning_rate": 7.280778515623314e-05,
"loss": 1.3413,
"step": 745
},
{
"epoch": 0.4180310736431408,
"grad_norm": 1.0060070753097534,
"learning_rate": 7.237394177168548e-05,
"loss": 1.3131,
"step": 750
},
{
"epoch": 0.4208179474674284,
"grad_norm": 0.9314805269241333,
"learning_rate": 7.193798181156095e-05,
"loss": 1.3345,
"step": 755
},
{
"epoch": 0.423604821291716,
"grad_norm": 0.8973556160926819,
"learning_rate": 7.149994651768514e-05,
"loss": 1.165,
"step": 760
},
{
"epoch": 0.4263916951160036,
"grad_norm": 0.961757481098175,
"learning_rate": 7.10598773282103e-05,
"loss": 1.2835,
"step": 765
},
{
"epoch": 0.4291785689402912,
"grad_norm": 0.9814241528511047,
"learning_rate": 7.061781587369519e-05,
"loss": 1.3459,
"step": 770
},
{
"epoch": 0.4319654427645788,
"grad_norm": 0.906623363494873,
"learning_rate": 7.017380397316695e-05,
"loss": 1.2327,
"step": 775
},
{
"epoch": 0.4347523165888664,
"grad_norm": 0.855728268623352,
"learning_rate": 6.972788363016497e-05,
"loss": 1.1951,
"step": 780
},
{
"epoch": 0.43753919041315403,
"grad_norm": 0.8998392820358276,
"learning_rate": 6.92800970287674e-05,
"loss": 1.2595,
"step": 785
},
{
"epoch": 0.44032606423744164,
"grad_norm": 0.8634393215179443,
"learning_rate": 6.883048652960038e-05,
"loss": 1.261,
"step": 790
},
{
"epoch": 0.44311293806172924,
"grad_norm": 0.9386719465255737,
"learning_rate": 6.837909466583095e-05,
"loss": 1.3039,
"step": 795
},
{
"epoch": 0.44589981188601685,
"grad_norm": 0.8203379511833191,
"learning_rate": 6.792596413914324e-05,
"loss": 1.1734,
"step": 800
},
{
"epoch": 0.44868668571030446,
"grad_norm": 0.9148008823394775,
"learning_rate": 6.747113781569892e-05,
"loss": 1.3215,
"step": 805
},
{
"epoch": 0.45147355953459206,
"grad_norm": 0.9338198304176331,
"learning_rate": 6.701465872208216e-05,
"loss": 1.3128,
"step": 810
},
{
"epoch": 0.45426043335887967,
"grad_norm": 0.9510387778282166,
"learning_rate": 6.655657004122916e-05,
"loss": 1.3056,
"step": 815
},
{
"epoch": 0.4570473071831673,
"grad_norm": 0.9619747996330261,
"learning_rate": 6.60969151083432e-05,
"loss": 1.2678,
"step": 820
},
{
"epoch": 0.4598341810074549,
"grad_norm": 0.8645920753479004,
"learning_rate": 6.563573740679496e-05,
"loss": 1.2585,
"step": 825
},
{
"epoch": 0.4626210548317425,
"grad_norm": 0.9401421546936035,
"learning_rate": 6.517308056400917e-05,
"loss": 1.2844,
"step": 830
},
{
"epoch": 0.4654079286560301,
"grad_norm": 0.8988810181617737,
"learning_rate": 6.470898834733731e-05,
"loss": 1.2556,
"step": 835
},
{
"epoch": 0.4681948024803177,
"grad_norm": 0.9045888781547546,
"learning_rate": 6.42435046599173e-05,
"loss": 1.2669,
"step": 840
},
{
"epoch": 0.4709816763046053,
"grad_norm": 0.9363210797309875,
"learning_rate": 6.377667353652022e-05,
"loss": 1.3025,
"step": 845
},
{
"epoch": 0.4737685501288929,
"grad_norm": 0.8949057459831238,
"learning_rate": 6.330853913938466e-05,
"loss": 1.2632,
"step": 850
},
{
"epoch": 0.4765554239531805,
"grad_norm": 0.8873914480209351,
"learning_rate": 6.283914575403888e-05,
"loss": 1.322,
"step": 855
},
{
"epoch": 0.4793422977774681,
"grad_norm": 0.9296184778213501,
"learning_rate": 6.236853778511156e-05,
"loss": 1.2484,
"step": 860
},
{
"epoch": 0.4821291716017557,
"grad_norm": 0.9600350260734558,
"learning_rate": 6.189675975213094e-05,
"loss": 1.2925,
"step": 865
},
{
"epoch": 0.48491604542604333,
"grad_norm": 0.9283687472343445,
"learning_rate": 6.142385628531342e-05,
"loss": 1.2948,
"step": 870
},
{
"epoch": 0.48770291925033094,
"grad_norm": 0.9505272507667542,
"learning_rate": 6.09498721213414e-05,
"loss": 1.2185,
"step": 875
},
{
"epoch": 0.49048979307461854,
"grad_norm": 0.9199963808059692,
"learning_rate": 6.047485209913137e-05,
"loss": 1.3212,
"step": 880
},
{
"epoch": 0.49327666689890615,
"grad_norm": 0.8689345717430115,
"learning_rate": 5.999884115559192e-05,
"loss": 1.2593,
"step": 885
},
{
"epoch": 0.49606354072319375,
"grad_norm": 0.8260021805763245,
"learning_rate": 5.952188432137293e-05,
"loss": 1.2825,
"step": 890
},
{
"epoch": 0.49885041454748136,
"grad_norm": 0.7934656143188477,
"learning_rate": 5.90440267166055e-05,
"loss": 1.2512,
"step": 895
},
{
"epoch": 0.501637288371769,
"grad_norm": 0.9623500108718872,
"learning_rate": 5.8565313546633684e-05,
"loss": 1.2891,
"step": 900
},
{
"epoch": 0.5044241621960566,
"grad_norm": 0.8901398777961731,
"learning_rate": 5.8085790097738025e-05,
"loss": 1.273,
"step": 905
},
{
"epoch": 0.5072110360203442,
"grad_norm": 0.9480902552604675,
"learning_rate": 5.7605501732851475e-05,
"loss": 1.3143,
"step": 910
},
{
"epoch": 0.5099979098446318,
"grad_norm": 0.8739180564880371,
"learning_rate": 5.712449388726807e-05,
"loss": 1.3233,
"step": 915
},
{
"epoch": 0.5127847836689194,
"grad_norm": 0.8921142220497131,
"learning_rate": 5.664281206434472e-05,
"loss": 1.2178,
"step": 920
},
{
"epoch": 0.515571657493207,
"grad_norm": 0.8952714204788208,
"learning_rate": 5.616050183119663e-05,
"loss": 1.3035,
"step": 925
},
{
"epoch": 0.5183585313174947,
"grad_norm": 0.8778610825538635,
"learning_rate": 5.5677608814386616e-05,
"loss": 1.1698,
"step": 930
},
{
"epoch": 0.5211454051417822,
"grad_norm": 0.9074441194534302,
"learning_rate": 5.519417869560889e-05,
"loss": 1.2659,
"step": 935
},
{
"epoch": 0.5239322789660699,
"grad_norm": 1.0030386447906494,
"learning_rate": 5.471025720736747e-05,
"loss": 1.3052,
"step": 940
},
{
"epoch": 0.5267191527903574,
"grad_norm": 0.8883451223373413,
"learning_rate": 5.422589012864996e-05,
"loss": 1.2955,
"step": 945
},
{
"epoch": 0.5295060266146451,
"grad_norm": 0.9527599215507507,
"learning_rate": 5.3741123280596864e-05,
"loss": 1.2489,
"step": 950
},
{
"epoch": 0.5322929004389326,
"grad_norm": 0.9727275967597961,
"learning_rate": 5.325600252216685e-05,
"loss": 1.2669,
"step": 955
},
{
"epoch": 0.5350797742632203,
"grad_norm": 0.9047435522079468,
"learning_rate": 5.27705737457985e-05,
"loss": 1.1822,
"step": 960
},
{
"epoch": 0.5378666480875078,
"grad_norm": 0.929094135761261,
"learning_rate": 5.228488287306896e-05,
"loss": 1.2304,
"step": 965
},
{
"epoch": 0.5406535219117955,
"grad_norm": 0.8297614455223083,
"learning_rate": 5.179897585034963e-05,
"loss": 1.2458,
"step": 970
},
{
"epoch": 0.543440395736083,
"grad_norm": 0.8769505023956299,
"learning_rate": 5.1312898644459776e-05,
"loss": 1.1869,
"step": 975
},
{
"epoch": 0.5462272695603707,
"grad_norm": 0.9683988690376282,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.2764,
"step": 980
},
{
"epoch": 0.5490141433846583,
"grad_norm": 0.886499285697937,
"learning_rate": 5.0340417626592016e-05,
"loss": 1.2708,
"step": 985
},
{
"epoch": 0.5518010172089458,
"grad_norm": 0.9555862545967102,
"learning_rate": 4.9854105811348216e-05,
"loss": 1.2959,
"step": 990
},
{
"epoch": 0.5545878910332335,
"grad_norm": 0.9976694583892822,
"learning_rate": 4.936780779769913e-05,
"loss": 1.2704,
"step": 995
},
{
"epoch": 0.557374764857521,
"grad_norm": 0.9540396928787231,
"learning_rate": 4.888156958945174e-05,
"loss": 1.2399,
"step": 1000
},
{
"epoch": 0.5601616386818087,
"grad_norm": 0.9087413549423218,
"learning_rate": 4.839543718475543e-05,
"loss": 1.2465,
"step": 1005
},
{
"epoch": 0.5629485125060962,
"grad_norm": 0.8988016247749329,
"learning_rate": 4.790945657175061e-05,
"loss": 1.2452,
"step": 1010
},
{
"epoch": 0.5657353863303839,
"grad_norm": 0.9223970174789429,
"learning_rate": 4.742367372421811e-05,
"loss": 1.2782,
"step": 1015
},
{
"epoch": 0.5685222601546714,
"grad_norm": 0.9696489572525024,
"learning_rate": 4.69381345972302e-05,
"loss": 1.217,
"step": 1020
},
{
"epoch": 0.5713091339789591,
"grad_norm": 0.8725862503051758,
"learning_rate": 4.6452885122803205e-05,
"loss": 1.2164,
"step": 1025
},
{
"epoch": 0.5740960078032467,
"grad_norm": 0.9017091989517212,
"learning_rate": 4.5967971205552194e-05,
"loss": 1.262,
"step": 1030
},
{
"epoch": 0.5768828816275343,
"grad_norm": 0.8934043049812317,
"learning_rate": 4.548343871834864e-05,
"loss": 1.2592,
"step": 1035
},
{
"epoch": 0.5796697554518219,
"grad_norm": 0.962250292301178,
"learning_rate": 4.499933349798067e-05,
"loss": 1.2987,
"step": 1040
},
{
"epoch": 0.5824566292761095,
"grad_norm": 0.9082201719284058,
"learning_rate": 4.451570134081694e-05,
"loss": 1.3104,
"step": 1045
},
{
"epoch": 0.5852435031003971,
"grad_norm": 0.8380867838859558,
"learning_rate": 4.403258799847433e-05,
"loss": 1.2397,
"step": 1050
},
{
"epoch": 0.5880303769246847,
"grad_norm": 1.0069491863250732,
"learning_rate": 4.3550039173489845e-05,
"loss": 1.2416,
"step": 1055
},
{
"epoch": 0.5908172507489723,
"grad_norm": 0.901740550994873,
"learning_rate": 4.306810051499708e-05,
"loss": 1.2247,
"step": 1060
},
{
"epoch": 0.59360412457326,
"grad_norm": 1.0371346473693848,
"learning_rate": 4.2586817614407895e-05,
"loss": 1.2432,
"step": 1065
},
{
"epoch": 0.5963909983975475,
"grad_norm": 0.8401350975036621,
"learning_rate": 4.210623600109946e-05,
"loss": 1.1691,
"step": 1070
},
{
"epoch": 0.5991778722218352,
"grad_norm": 0.924321711063385,
"learning_rate": 4.162640113810706e-05,
"loss": 1.2647,
"step": 1075
},
{
"epoch": 0.6019647460461227,
"grad_norm": 0.9289098381996155,
"learning_rate": 4.114735841782347e-05,
"loss": 1.2958,
"step": 1080
},
{
"epoch": 0.6047516198704104,
"grad_norm": 0.9739760756492615,
"learning_rate": 4.06691531577047e-05,
"loss": 1.2703,
"step": 1085
},
{
"epoch": 0.6075384936946979,
"grad_norm": 0.8968196511268616,
"learning_rate": 4.019183059598296e-05,
"loss": 1.2312,
"step": 1090
},
{
"epoch": 0.6103253675189856,
"grad_norm": 0.8930853605270386,
"learning_rate": 3.971543588738724e-05,
"loss": 1.2612,
"step": 1095
},
{
"epoch": 0.6131122413432731,
"grad_norm": 0.8859248757362366,
"learning_rate": 3.924001409887158e-05,
"loss": 1.1742,
"step": 1100
},
{
"epoch": 0.6158991151675608,
"grad_norm": 0.9286195635795593,
"learning_rate": 3.87656102053517e-05,
"loss": 1.2483,
"step": 1105
},
{
"epoch": 0.6186859889918483,
"grad_norm": 0.895728349685669,
"learning_rate": 3.8292269085450474e-05,
"loss": 1.2157,
"step": 1110
},
{
"epoch": 0.621472862816136,
"grad_norm": 0.879304826259613,
"learning_rate": 3.782003551725236e-05,
"loss": 1.3032,
"step": 1115
},
{
"epoch": 0.6242597366404236,
"grad_norm": 0.893455982208252,
"learning_rate": 3.734895417406734e-05,
"loss": 1.2443,
"step": 1120
},
{
"epoch": 0.6270466104647112,
"grad_norm": 0.924315869808197,
"learning_rate": 3.687906962020491e-05,
"loss": 1.2759,
"step": 1125
},
{
"epoch": 0.6298334842889988,
"grad_norm": 1.0192773342132568,
"learning_rate": 3.641042630675829e-05,
"loss": 1.2816,
"step": 1130
},
{
"epoch": 0.6326203581132864,
"grad_norm": 0.9503198266029358,
"learning_rate": 3.594306856739924e-05,
"loss": 1.2173,
"step": 1135
},
{
"epoch": 0.635407231937574,
"grad_norm": 0.9149984121322632,
"learning_rate": 3.547704061418424e-05,
"loss": 1.2245,
"step": 1140
},
{
"epoch": 0.6381941057618616,
"grad_norm": 0.9525075554847717,
"learning_rate": 3.501238653337194e-05,
"loss": 1.2298,
"step": 1145
},
{
"epoch": 0.6409809795861492,
"grad_norm": 0.9972552061080933,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.3021,
"step": 1150
},
{
"epoch": 0.6437678534104369,
"grad_norm": 0.8908212184906006,
"learning_rate": 3.408737567998993e-05,
"loss": 1.191,
"step": 1155
},
{
"epoch": 0.6465547272347244,
"grad_norm": 0.9422298669815063,
"learning_rate": 3.362710641347524e-05,
"loss": 1.2812,
"step": 1160
},
{
"epoch": 0.6493416010590121,
"grad_norm": 0.8892982006072998,
"learning_rate": 3.316838602319532e-05,
"loss": 1.2787,
"step": 1165
},
{
"epoch": 0.6521284748832996,
"grad_norm": 0.9730682373046875,
"learning_rate": 3.271125790411309e-05,
"loss": 1.1704,
"step": 1170
},
{
"epoch": 0.6549153487075873,
"grad_norm": 1.0745271444320679,
"learning_rate": 3.225576530056264e-05,
"loss": 1.3028,
"step": 1175
},
{
"epoch": 0.6577022225318748,
"grad_norm": 0.9123522043228149,
"learning_rate": 3.180195130215824e-05,
"loss": 1.262,
"step": 1180
},
{
"epoch": 0.6604890963561625,
"grad_norm": 0.9651986360549927,
"learning_rate": 3.1349858839717986e-05,
"loss": 1.1867,
"step": 1185
},
{
"epoch": 0.66327597018045,
"grad_norm": 0.9499524831771851,
"learning_rate": 3.089953068120271e-05,
"loss": 1.1766,
"step": 1190
},
{
"epoch": 0.6660628440047377,
"grad_norm": 0.9542708396911621,
"learning_rate": 3.0451009427669986e-05,
"loss": 1.2212,
"step": 1195
},
{
"epoch": 0.6688497178290252,
"grad_norm": 0.9473170042037964,
"learning_rate": 3.000433750924414e-05,
"loss": 1.2332,
"step": 1200
},
{
"epoch": 0.6716365916533129,
"grad_norm": 0.8507165312767029,
"learning_rate": 2.9559557181102315e-05,
"loss": 1.245,
"step": 1205
},
{
"epoch": 0.6744234654776005,
"grad_norm": 0.9855820536613464,
"learning_rate": 2.911671051947722e-05,
"loss": 1.1962,
"step": 1210
},
{
"epoch": 0.6772103393018881,
"grad_norm": 0.970454752445221,
"learning_rate": 2.867583941767657e-05,
"loss": 1.1937,
"step": 1215
},
{
"epoch": 0.6799972131261757,
"grad_norm": 0.9287285804748535,
"learning_rate": 2.823698558212009e-05,
"loss": 1.2562,
"step": 1220
},
{
"epoch": 0.6827840869504633,
"grad_norm": 0.9838190078735352,
"learning_rate": 2.7800190528394122e-05,
"loss": 1.2125,
"step": 1225
},
{
"epoch": 0.6855709607747509,
"grad_norm": 0.8512199521064758,
"learning_rate": 2.736549557732405e-05,
"loss": 1.1991,
"step": 1230
},
{
"epoch": 0.6883578345990385,
"grad_norm": 0.8986166715621948,
"learning_rate": 2.693294185106562e-05,
"loss": 1.3633,
"step": 1235
},
{
"epoch": 0.6911447084233261,
"grad_norm": 0.9696632027626038,
"learning_rate": 2.650257026921455e-05,
"loss": 1.2675,
"step": 1240
},
{
"epoch": 0.6939315822476138,
"grad_norm": 1.0738840103149414,
"learning_rate": 2.607442154493568e-05,
"loss": 1.2917,
"step": 1245
},
{
"epoch": 0.6967184560719013,
"grad_norm": 0.9573596715927124,
"learning_rate": 2.5648536181111438e-05,
"loss": 1.2427,
"step": 1250
},
{
"epoch": 0.699505329896189,
"grad_norm": 0.9653842449188232,
"learning_rate": 2.5224954466510274e-05,
"loss": 1.2188,
"step": 1255
},
{
"epoch": 0.7022922037204765,
"grad_norm": 0.9326026439666748,
"learning_rate": 2.480371647197538e-05,
"loss": 1.2812,
"step": 1260
},
{
"epoch": 0.7050790775447642,
"grad_norm": 0.9213048219680786,
"learning_rate": 2.438486204663391e-05,
"loss": 1.2512,
"step": 1265
},
{
"epoch": 0.7078659513690517,
"grad_norm": 0.9547055959701538,
"learning_rate": 2.3968430814127385e-05,
"loss": 1.2657,
"step": 1270
},
{
"epoch": 0.7106528251933394,
"grad_norm": 0.9416990280151367,
"learning_rate": 2.3554462168863085e-05,
"loss": 1.2631,
"step": 1275
},
{
"epoch": 0.7134396990176269,
"grad_norm": 0.9471155405044556,
"learning_rate": 2.314299527228759e-05,
"loss": 1.2631,
"step": 1280
},
{
"epoch": 0.7162265728419146,
"grad_norm": 0.9220243096351624,
"learning_rate": 2.2734069049181882e-05,
"loss": 1.2288,
"step": 1285
},
{
"epoch": 0.7190134466662021,
"grad_norm": 0.9854679107666016,
"learning_rate": 2.2327722183979212e-05,
"loss": 1.261,
"step": 1290
},
{
"epoch": 0.7218003204904898,
"grad_norm": 0.898456335067749,
"learning_rate": 2.1923993117105462e-05,
"loss": 1.2037,
"step": 1295
},
{
"epoch": 0.7245871943147774,
"grad_norm": 1.0650768280029297,
"learning_rate": 2.1522920041342704e-05,
"loss": 1.214,
"step": 1300
},
{
"epoch": 0.727374068139065,
"grad_norm": 1.02187979221344,
"learning_rate": 2.1124540898216248e-05,
"loss": 1.2634,
"step": 1305
},
{
"epoch": 0.7301609419633526,
"grad_norm": 0.9087027311325073,
"learning_rate": 2.0728893374405166e-05,
"loss": 1.1596,
"step": 1310
},
{
"epoch": 0.7329478157876402,
"grad_norm": 1.0457086563110352,
"learning_rate": 2.033601489817738e-05,
"loss": 1.3245,
"step": 1315
},
{
"epoch": 0.7357346896119278,
"grad_norm": 1.012440800666809,
"learning_rate": 1.9945942635848748e-05,
"loss": 1.2658,
"step": 1320
},
{
"epoch": 0.7385215634362154,
"grad_norm": 0.9544854164123535,
"learning_rate": 1.9558713488267238e-05,
"loss": 1.2584,
"step": 1325
},
{
"epoch": 0.741308437260503,
"grad_norm": 0.9268321394920349,
"learning_rate": 1.917436408732208e-05,
"loss": 1.2337,
"step": 1330
},
{
"epoch": 0.7440953110847907,
"grad_norm": 1.108223557472229,
"learning_rate": 1.8792930792478357e-05,
"loss": 1.2228,
"step": 1335
},
{
"epoch": 0.7468821849090782,
"grad_norm": 1.0709432363510132,
"learning_rate": 1.8414449687337464e-05,
"loss": 1.183,
"step": 1340
},
{
"epoch": 0.7496690587333659,
"grad_norm": 0.9613754153251648,
"learning_rate": 1.8038956576223504e-05,
"loss": 1.1697,
"step": 1345
},
{
"epoch": 0.7524559325576534,
"grad_norm": 0.865163266658783,
"learning_rate": 1.766648698079635e-05,
"loss": 1.2347,
"step": 1350
},
{
"epoch": 0.7552428063819411,
"grad_norm": 0.9915691614151001,
"learning_rate": 1.7297076136691072e-05,
"loss": 1.3237,
"step": 1355
},
{
"epoch": 0.7580296802062286,
"grad_norm": 1.0180468559265137,
"learning_rate": 1.6930758990184875e-05,
"loss": 1.2416,
"step": 1360
},
{
"epoch": 0.7608165540305163,
"grad_norm": 1.0427292585372925,
"learning_rate": 1.6567570194891024e-05,
"loss": 1.225,
"step": 1365
},
{
"epoch": 0.7636034278548038,
"grad_norm": 1.0692229270935059,
"learning_rate": 1.620754410848069e-05,
"loss": 1.2287,
"step": 1370
},
{
"epoch": 0.7663903016790915,
"grad_norm": 0.9599437713623047,
"learning_rate": 1.5850714789432663e-05,
"loss": 1.2652,
"step": 1375
},
{
"epoch": 0.769177175503379,
"grad_norm": 0.9924296140670776,
"learning_rate": 1.549711599381145e-05,
"loss": 1.2543,
"step": 1380
},
{
"epoch": 0.7719640493276667,
"grad_norm": 0.8805568218231201,
"learning_rate": 1.5146781172073959e-05,
"loss": 1.2086,
"step": 1385
},
{
"epoch": 0.7747509231519543,
"grad_norm": 0.9607245922088623,
"learning_rate": 1.479974346590503e-05,
"loss": 1.2543,
"step": 1390
},
{
"epoch": 0.7775377969762419,
"grad_norm": 0.9395803213119507,
"learning_rate": 1.4456035705082349e-05,
"loss": 1.2146,
"step": 1395
},
{
"epoch": 0.7803246708005295,
"grad_norm": 0.9911707043647766,
"learning_rate": 1.4115690404370551e-05,
"loss": 1.2256,
"step": 1400
},
{
"epoch": 0.7831115446248171,
"grad_norm": 0.9199152588844299,
"learning_rate": 1.3778739760445552e-05,
"loss": 1.2138,
"step": 1405
},
{
"epoch": 0.7858984184491047,
"grad_norm": 0.9677468538284302,
"learning_rate": 1.344521564884858e-05,
"loss": 1.2739,
"step": 1410
},
{
"epoch": 0.7886852922733923,
"grad_norm": 0.9051083326339722,
"learning_rate": 1.3115149620970795e-05,
"loss": 1.278,
"step": 1415
},
{
"epoch": 0.7914721660976799,
"grad_norm": 1.0139137506484985,
"learning_rate": 1.2788572901068552e-05,
"loss": 1.2309,
"step": 1420
},
{
"epoch": 0.7942590399219676,
"grad_norm": 1.022859811782837,
"learning_rate": 1.2465516383309551e-05,
"loss": 1.2423,
"step": 1425
},
{
"epoch": 0.7970459137462551,
"grad_norm": 0.9269377589225769,
"learning_rate": 1.2146010628850268e-05,
"loss": 1.2685,
"step": 1430
},
{
"epoch": 0.7998327875705428,
"grad_norm": 0.9552863836288452,
"learning_rate": 1.183008586294485e-05,
"loss": 1.2021,
"step": 1435
},
{
"epoch": 0.8026196613948303,
"grad_norm": 0.9597859382629395,
"learning_rate": 1.151777197208585e-05,
"loss": 1.215,
"step": 1440
},
{
"epoch": 0.805406535219118,
"grad_norm": 0.9569510817527771,
"learning_rate": 1.1209098501176896e-05,
"loss": 1.2153,
"step": 1445
},
{
"epoch": 0.8081934090434055,
"grad_norm": 0.9744769334793091,
"learning_rate": 1.0904094650737795e-05,
"loss": 1.2153,
"step": 1450
},
{
"epoch": 0.8109802828676932,
"grad_norm": 1.118589997291565,
"learning_rate": 1.0602789274142133e-05,
"loss": 1.2763,
"step": 1455
},
{
"epoch": 0.8137671566919807,
"grad_norm": 0.9778153300285339,
"learning_rate": 1.0305210874887766e-05,
"loss": 1.1713,
"step": 1460
},
{
"epoch": 0.8165540305162684,
"grad_norm": 0.9907205700874329,
"learning_rate": 1.0011387603900385e-05,
"loss": 1.2282,
"step": 1465
},
{
"epoch": 0.819340904340556,
"grad_norm": 0.9918599128723145,
"learning_rate": 9.7213472568704e-06,
"loss": 1.2396,
"step": 1470
},
{
"epoch": 0.8221277781648436,
"grad_norm": 0.9913582801818848,
"learning_rate": 9.435117271623566e-06,
"loss": 1.1384,
"step": 1475
},
{
"epoch": 0.8249146519891312,
"grad_norm": 0.9848992228507996,
"learning_rate": 9.152724725525202e-06,
"loss": 1.2261,
"step": 1480
},
{
"epoch": 0.8277015258134188,
"grad_norm": 0.8803195953369141,
"learning_rate": 8.87419633291886e-06,
"loss": 1.265,
"step": 1485
},
{
"epoch": 0.8304883996377064,
"grad_norm": 1.0013386011123657,
"learning_rate": 8.599558442598998e-06,
"loss": 1.1752,
"step": 1490
},
{
"epoch": 0.833275273461994,
"grad_norm": 1.0229575634002686,
"learning_rate": 8.328837035318448e-06,
"loss": 1.2616,
"step": 1495
},
{
"epoch": 0.8360621472862816,
"grad_norm": 0.93488609790802,
"learning_rate": 8.06205772133063e-06,
"loss": 1.1683,
"step": 1500
},
{
"epoch": 0.8388490211105692,
"grad_norm": 1.0417516231536865,
"learning_rate": 7.799245737966821e-06,
"loss": 1.218,
"step": 1505
},
{
"epoch": 0.8416358949348568,
"grad_norm": 0.9976839423179626,
"learning_rate": 7.540425947248697e-06,
"loss": 1.2297,
"step": 1510
},
{
"epoch": 0.8444227687591445,
"grad_norm": 0.9360842108726501,
"learning_rate": 7.28562283353637e-06,
"loss": 1.2272,
"step": 1515
},
{
"epoch": 0.847209642583432,
"grad_norm": 0.9308948516845703,
"learning_rate": 7.034860501212243e-06,
"loss": 1.228,
"step": 1520
},
{
"epoch": 0.8499965164077197,
"grad_norm": 0.9917842149734497,
"learning_rate": 6.788162672400583e-06,
"loss": 1.307,
"step": 1525
},
{
"epoch": 0.8527833902320072,
"grad_norm": 0.9004817605018616,
"learning_rate": 6.5455526847235825e-06,
"loss": 1.236,
"step": 1530
},
{
"epoch": 0.8555702640562949,
"grad_norm": 0.9853699803352356,
"learning_rate": 6.307053489093506e-06,
"loss": 1.2217,
"step": 1535
},
{
"epoch": 0.8583571378805824,
"grad_norm": 0.9549526572227478,
"learning_rate": 6.072687647541553e-06,
"loss": 1.2435,
"step": 1540
},
{
"epoch": 0.8611440117048701,
"grad_norm": 0.9663627743721008,
"learning_rate": 5.842477331083518e-06,
"loss": 1.2514,
"step": 1545
},
{
"epoch": 0.8639308855291576,
"grad_norm": 0.9174144864082336,
"learning_rate": 5.616444317622388e-06,
"loss": 1.1749,
"step": 1550
},
{
"epoch": 0.8667177593534453,
"grad_norm": 0.9564938545227051,
"learning_rate": 5.394609989888161e-06,
"loss": 1.2476,
"step": 1555
},
{
"epoch": 0.8695046331777329,
"grad_norm": 1.1256656646728516,
"learning_rate": 5.176995333415019e-06,
"loss": 1.2506,
"step": 1560
},
{
"epoch": 0.8722915070020205,
"grad_norm": 1.0491883754730225,
"learning_rate": 4.963620934556168e-06,
"loss": 1.2388,
"step": 1565
},
{
"epoch": 0.8750783808263081,
"grad_norm": 0.9458408951759338,
"learning_rate": 4.754506978536227e-06,
"loss": 1.2388,
"step": 1570
},
{
"epoch": 0.8778652546505957,
"grad_norm": 0.932964563369751,
"learning_rate": 4.549673247541875e-06,
"loss": 1.2333,
"step": 1575
},
{
"epoch": 0.8806521284748833,
"grad_norm": 0.8364896178245544,
"learning_rate": 4.3491391188503264e-06,
"loss": 1.2139,
"step": 1580
},
{
"epoch": 0.8834390022991709,
"grad_norm": 1.0495798587799072,
"learning_rate": 4.152923562996297e-06,
"loss": 1.1667,
"step": 1585
},
{
"epoch": 0.8862258761234585,
"grad_norm": 0.9140335321426392,
"learning_rate": 3.961045141977376e-06,
"loss": 1.2402,
"step": 1590
},
{
"epoch": 0.8890127499477462,
"grad_norm": 0.9842175245285034,
"learning_rate": 3.773522007498065e-06,
"loss": 1.2425,
"step": 1595
},
{
"epoch": 0.8917996237720337,
"grad_norm": 0.9036964178085327,
"learning_rate": 3.590371899252659e-06,
"loss": 1.2087,
"step": 1600
},
{
"epoch": 0.8945864975963214,
"grad_norm": 0.9229257106781006,
"learning_rate": 3.4116121432469615e-06,
"loss": 1.2167,
"step": 1605
},
{
"epoch": 0.8973733714206089,
"grad_norm": 0.9462814331054688,
"learning_rate": 3.237259650159402e-06,
"loss": 1.2211,
"step": 1610
},
{
"epoch": 0.9001602452448966,
"grad_norm": 0.9471161961555481,
"learning_rate": 3.0673309137411564e-06,
"loss": 1.2463,
"step": 1615
},
{
"epoch": 0.9029471190691841,
"grad_norm": 0.9873669147491455,
"learning_rate": 2.9018420092558786e-06,
"loss": 1.207,
"step": 1620
},
{
"epoch": 0.9057339928934718,
"grad_norm": 1.0254420042037964,
"learning_rate": 2.7408085919590264e-06,
"loss": 1.2891,
"step": 1625
},
{
"epoch": 0.9085208667177593,
"grad_norm": 0.9538567662239075,
"learning_rate": 2.584245895616788e-06,
"loss": 1.2533,
"step": 1630
},
{
"epoch": 0.911307740542047,
"grad_norm": 1.055637240409851,
"learning_rate": 2.4321687310650487e-06,
"loss": 1.2598,
"step": 1635
},
{
"epoch": 0.9140946143663345,
"grad_norm": 0.9872303009033203,
"learning_rate": 2.2845914848082127e-06,
"loss": 1.2765,
"step": 1640
},
{
"epoch": 0.9168814881906222,
"grad_norm": 1.0598726272583008,
"learning_rate": 2.1415281176583203e-06,
"loss": 1.2305,
"step": 1645
},
{
"epoch": 0.9196683620149098,
"grad_norm": 0.9400553703308105,
"learning_rate": 2.0029921634142632e-06,
"loss": 1.3019,
"step": 1650
},
{
"epoch": 0.9224552358391974,
"grad_norm": 0.9695894122123718,
"learning_rate": 1.8689967275815679e-06,
"loss": 1.2685,
"step": 1655
},
{
"epoch": 0.925242109663485,
"grad_norm": 0.9889479875564575,
"learning_rate": 1.7395544861325718e-06,
"loss": 1.2702,
"step": 1660
},
{
"epoch": 0.9280289834877726,
"grad_norm": 0.9385488033294678,
"learning_rate": 1.614677684307264e-06,
"loss": 1.2255,
"step": 1665
},
{
"epoch": 0.9308158573120602,
"grad_norm": 0.9816272258758545,
"learning_rate": 1.494378135454938e-06,
"loss": 1.2531,
"step": 1670
},
{
"epoch": 0.9336027311363478,
"grad_norm": 0.9538016319274902,
"learning_rate": 1.3786672199165962e-06,
"loss": 1.2487,
"step": 1675
},
{
"epoch": 0.9363896049606354,
"grad_norm": 0.95050448179245,
"learning_rate": 1.2675558839483848e-06,
"loss": 1.1962,
"step": 1680
},
{
"epoch": 0.939176478784923,
"grad_norm": 0.98070228099823,
"learning_rate": 1.1610546386860988e-06,
"loss": 1.2306,
"step": 1685
},
{
"epoch": 0.9419633526092106,
"grad_norm": 1.0162360668182373,
"learning_rate": 1.0591735591507946e-06,
"loss": 1.2259,
"step": 1690
},
{
"epoch": 0.9447502264334983,
"grad_norm": 0.997144341468811,
"learning_rate": 9.619222832957243e-07,
"loss": 1.2142,
"step": 1695
},
{
"epoch": 0.9475371002577858,
"grad_norm": 0.9727258086204529,
"learning_rate": 8.693100110945484e-07,
"loss": 1.2123,
"step": 1700
},
{
"epoch": 0.9503239740820735,
"grad_norm": 0.8900772929191589,
"learning_rate": 7.813455036710715e-07,
"loss": 1.1853,
"step": 1705
},
{
"epoch": 0.953110847906361,
"grad_norm": 0.9536607265472412,
"learning_rate": 6.980370824703763e-07,
"loss": 1.2617,
"step": 1710
},
{
"epoch": 0.9558977217306487,
"grad_norm": 1.0575697422027588,
"learning_rate": 6.193926284716711e-07,
"loss": 1.1969,
"step": 1715
},
{
"epoch": 0.9586845955549362,
"grad_norm": 0.9426103234291077,
"learning_rate": 5.454195814427021e-07,
"loss": 1.3009,
"step": 1720
},
{
"epoch": 0.9614714693792239,
"grad_norm": 1.020992636680603,
"learning_rate": 4.76124939235989e-07,
"loss": 1.2011,
"step": 1725
},
{
"epoch": 0.9642583432035114,
"grad_norm": 0.9522945284843445,
"learning_rate": 4.1151525712680996e-07,
"loss": 1.1584,
"step": 1730
},
{
"epoch": 0.9670452170277991,
"grad_norm": 1.105689525604248,
"learning_rate": 3.515966471930643e-07,
"loss": 1.2898,
"step": 1735
},
{
"epoch": 0.9698320908520867,
"grad_norm": 1.0255939960479736,
"learning_rate": 2.963747777370907e-07,
"loss": 1.2634,
"step": 1740
},
{
"epoch": 0.9726189646763743,
"grad_norm": 1.0123835802078247,
"learning_rate": 2.458548727494292e-07,
"loss": 1.1778,
"step": 1745
},
{
"epoch": 0.9754058385006619,
"grad_norm": 0.9710216522216797,
"learning_rate": 2.0004171141464467e-07,
"loss": 1.2408,
"step": 1750
},
{
"epoch": 0.9781927123249495,
"grad_norm": 1.0030288696289062,
"learning_rate": 1.589396276591937e-07,
"loss": 1.2336,
"step": 1755
},
{
"epoch": 0.9809795861492371,
"grad_norm": 0.9503644108772278,
"learning_rate": 1.225525097414637e-07,
"loss": 1.1797,
"step": 1760
},
{
"epoch": 0.9837664599735247,
"grad_norm": 1.007887840270996,
"learning_rate": 9.088379988392848e-08,
"loss": 1.2185,
"step": 1765
},
{
"epoch": 0.9865533337978123,
"grad_norm": 1.062198281288147,
"learning_rate": 6.393649394749734e-08,
"loss": 1.2139,
"step": 1770
},
{
"epoch": 0.9893402076221,
"grad_norm": 1.0820635557174683,
"learning_rate": 4.171314114815306e-08,
"loss": 1.2726,
"step": 1775
},
{
"epoch": 0.9921270814463875,
"grad_norm": 0.97090744972229,
"learning_rate": 2.4215843815733607e-08,
"loss": 1.1734,
"step": 1780
},
{
"epoch": 0.9949139552706752,
"grad_norm": 0.9105931520462036,
"learning_rate": 1.1446257195119048e-08,
"loss": 1.2729,
"step": 1785
},
{
"epoch": 0.9977008290949627,
"grad_norm": 0.9542015790939331,
"learning_rate": 3.4055892895901167e-09,
"loss": 1.2552,
"step": 1790
},
{
"epoch": 1.0,
"grad_norm": 3.9945850372314453,
"learning_rate": 9.460074656963969e-11,
"loss": 1.3228,
"step": 1795
},
{
"epoch": 1.0,
"step": 1795,
"total_flos": 1.3861725429517517e+17,
"train_loss": 0.0,
"train_runtime": 0.8982,
"train_samples_per_second": 15978.88,
"train_steps_per_second": 1998.334
}
],
"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": true
},
"attributes": {}
}
},
"total_flos": 1.3861725429517517e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}