yi-1-5-9b_eqa_lora_sft / trainer_state.json
hexuan21's picture
Upload folder using huggingface_hub
a08f139 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": 1.9115384817123413,
"learning_rate": 2.2222222222222225e-06,
"loss": 2.4654,
"step": 5
},
{
"epoch": 0.0055737476485752105,
"grad_norm": 1.947817087173462,
"learning_rate": 5e-06,
"loss": 2.3751,
"step": 10
},
{
"epoch": 0.008360621472862817,
"grad_norm": 2.6451737880706787,
"learning_rate": 7.777777777777777e-06,
"loss": 2.3938,
"step": 15
},
{
"epoch": 0.011147495297150421,
"grad_norm": 1.6687722206115723,
"learning_rate": 1.0555555555555555e-05,
"loss": 2.3997,
"step": 20
},
{
"epoch": 0.013934369121438027,
"grad_norm": 2.434365749359131,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.421,
"step": 25
},
{
"epoch": 0.016721242945725634,
"grad_norm": 1.834489107131958,
"learning_rate": 1.6111111111111115e-05,
"loss": 2.3451,
"step": 30
},
{
"epoch": 0.019508116770013236,
"grad_norm": 1.1199796199798584,
"learning_rate": 1.888888888888889e-05,
"loss": 2.1472,
"step": 35
},
{
"epoch": 0.022294990594300842,
"grad_norm": 0.8856447339057922,
"learning_rate": 2.1666666666666667e-05,
"loss": 2.0011,
"step": 40
},
{
"epoch": 0.025081864418588447,
"grad_norm": 0.7832725048065186,
"learning_rate": 2.4444444444444445e-05,
"loss": 2.1246,
"step": 45
},
{
"epoch": 0.027868738242876053,
"grad_norm": 0.891650378704071,
"learning_rate": 2.7222222222222223e-05,
"loss": 2.0452,
"step": 50
},
{
"epoch": 0.03065561206716366,
"grad_norm": 0.8371910452842712,
"learning_rate": 3e-05,
"loss": 1.8973,
"step": 55
},
{
"epoch": 0.03344248589145127,
"grad_norm": 0.7994418144226074,
"learning_rate": 3.277777777777778e-05,
"loss": 2.021,
"step": 60
},
{
"epoch": 0.03622935971573887,
"grad_norm": 0.9120875000953674,
"learning_rate": 3.555555555555556e-05,
"loss": 1.9413,
"step": 65
},
{
"epoch": 0.03901623354002647,
"grad_norm": 0.8946442604064941,
"learning_rate": 3.8333333333333334e-05,
"loss": 1.8503,
"step": 70
},
{
"epoch": 0.04180310736431408,
"grad_norm": 0.9378814101219177,
"learning_rate": 4.111111111111111e-05,
"loss": 1.8974,
"step": 75
},
{
"epoch": 0.044589981188601684,
"grad_norm": 0.8701204657554626,
"learning_rate": 4.388888888888889e-05,
"loss": 1.8111,
"step": 80
},
{
"epoch": 0.04737685501288929,
"grad_norm": 0.8670846223831177,
"learning_rate": 4.666666666666667e-05,
"loss": 1.931,
"step": 85
},
{
"epoch": 0.050163728837176895,
"grad_norm": 0.9741831421852112,
"learning_rate": 4.9444444444444446e-05,
"loss": 1.8414,
"step": 90
},
{
"epoch": 0.0529506026614645,
"grad_norm": 0.9725918769836426,
"learning_rate": 5.222222222222223e-05,
"loss": 1.8312,
"step": 95
},
{
"epoch": 0.055737476485752106,
"grad_norm": 1.0660992860794067,
"learning_rate": 5.500000000000001e-05,
"loss": 1.8016,
"step": 100
},
{
"epoch": 0.05852435031003971,
"grad_norm": 0.8871088027954102,
"learning_rate": 5.7777777777777776e-05,
"loss": 1.8186,
"step": 105
},
{
"epoch": 0.06131122413432732,
"grad_norm": 1.19992196559906,
"learning_rate": 6.055555555555555e-05,
"loss": 1.9371,
"step": 110
},
{
"epoch": 0.06409809795861493,
"grad_norm": 0.9831395149230957,
"learning_rate": 6.333333333333333e-05,
"loss": 1.8183,
"step": 115
},
{
"epoch": 0.06688497178290254,
"grad_norm": 0.9600491523742676,
"learning_rate": 6.611111111111111e-05,
"loss": 1.8421,
"step": 120
},
{
"epoch": 0.06967184560719013,
"grad_norm": 1.0193743705749512,
"learning_rate": 6.88888888888889e-05,
"loss": 1.8991,
"step": 125
},
{
"epoch": 0.07245871943147773,
"grad_norm": 0.9411584138870239,
"learning_rate": 7.166666666666667e-05,
"loss": 1.8344,
"step": 130
},
{
"epoch": 0.07524559325576534,
"grad_norm": 0.9847779273986816,
"learning_rate": 7.444444444444444e-05,
"loss": 1.7882,
"step": 135
},
{
"epoch": 0.07803246708005294,
"grad_norm": 1.1100168228149414,
"learning_rate": 7.722222222222223e-05,
"loss": 1.8198,
"step": 140
},
{
"epoch": 0.08081934090434055,
"grad_norm": 0.9738144278526306,
"learning_rate": 8e-05,
"loss": 1.9388,
"step": 145
},
{
"epoch": 0.08360621472862816,
"grad_norm": 1.0248855352401733,
"learning_rate": 8.277777777777778e-05,
"loss": 1.8594,
"step": 150
},
{
"epoch": 0.08639308855291576,
"grad_norm": 0.8680633306503296,
"learning_rate": 8.555555555555556e-05,
"loss": 1.8297,
"step": 155
},
{
"epoch": 0.08917996237720337,
"grad_norm": 1.159138560295105,
"learning_rate": 8.833333333333333e-05,
"loss": 1.7893,
"step": 160
},
{
"epoch": 0.09196683620149097,
"grad_norm": 1.0572437047958374,
"learning_rate": 9.111111111111112e-05,
"loss": 1.7589,
"step": 165
},
{
"epoch": 0.09475371002577858,
"grad_norm": 1.0529230833053589,
"learning_rate": 9.388888888888889e-05,
"loss": 1.8112,
"step": 170
},
{
"epoch": 0.09754058385006618,
"grad_norm": 0.9541242122650146,
"learning_rate": 9.666666666666667e-05,
"loss": 1.819,
"step": 175
},
{
"epoch": 0.10032745767435379,
"grad_norm": 0.994308352470398,
"learning_rate": 9.944444444444446e-05,
"loss": 1.819,
"step": 180
},
{
"epoch": 0.1031143314986414,
"grad_norm": 1.0918625593185425,
"learning_rate": 9.999848639521432e-05,
"loss": 1.7897,
"step": 185
},
{
"epoch": 0.105901205322929,
"grad_norm": 0.9328644871711731,
"learning_rate": 9.999233753283091e-05,
"loss": 1.7692,
"step": 190
},
{
"epoch": 0.1086880791472166,
"grad_norm": 1.1488420963287354,
"learning_rate": 9.998145939378577e-05,
"loss": 1.7654,
"step": 195
},
{
"epoch": 0.11147495297150421,
"grad_norm": 1.0845956802368164,
"learning_rate": 9.996585300715116e-05,
"loss": 1.8189,
"step": 200
},
{
"epoch": 0.11426182679579182,
"grad_norm": 1.0153155326843262,
"learning_rate": 9.994551984929175e-05,
"loss": 1.7755,
"step": 205
},
{
"epoch": 0.11704870062007942,
"grad_norm": 0.8213108777999878,
"learning_rate": 9.992046184372492e-05,
"loss": 1.8018,
"step": 210
},
{
"epoch": 0.11983557444436703,
"grad_norm": 0.947027325630188,
"learning_rate": 9.989068136093873e-05,
"loss": 1.7387,
"step": 215
},
{
"epoch": 0.12262244826865464,
"grad_norm": 0.9216685891151428,
"learning_rate": 9.985618121816779e-05,
"loss": 1.8351,
"step": 220
},
{
"epoch": 0.12540932209294225,
"grad_norm": 0.9680148363113403,
"learning_rate": 9.981696467912664e-05,
"loss": 1.7574,
"step": 225
},
{
"epoch": 0.12819619591722986,
"grad_norm": 1.006169319152832,
"learning_rate": 9.97730354537011e-05,
"loss": 1.8028,
"step": 230
},
{
"epoch": 0.13098306974151747,
"grad_norm": 0.8808375597000122,
"learning_rate": 9.972439769759722e-05,
"loss": 1.7,
"step": 235
},
{
"epoch": 0.13376994356580507,
"grad_norm": 0.9949018955230713,
"learning_rate": 9.967105601194823e-05,
"loss": 1.8723,
"step": 240
},
{
"epoch": 0.13655681739009268,
"grad_norm": 0.9065477848052979,
"learning_rate": 9.961301544287922e-05,
"loss": 1.7349,
"step": 245
},
{
"epoch": 0.13934369121438026,
"grad_norm": 0.9984349012374878,
"learning_rate": 9.955028148102979e-05,
"loss": 1.6986,
"step": 250
},
{
"epoch": 0.14213056503866786,
"grad_norm": 0.9238440990447998,
"learning_rate": 9.948286006103466e-05,
"loss": 1.8907,
"step": 255
},
{
"epoch": 0.14491743886295547,
"grad_norm": 1.0889593362808228,
"learning_rate": 9.941075756096226e-05,
"loss": 1.7998,
"step": 260
},
{
"epoch": 0.14770431268724307,
"grad_norm": 0.9553403854370117,
"learning_rate": 9.933398080171123e-05,
"loss": 1.7892,
"step": 265
},
{
"epoch": 0.15049118651153068,
"grad_norm": 0.9401119351387024,
"learning_rate": 9.925253704636543e-05,
"loss": 1.7535,
"step": 270
},
{
"epoch": 0.15327806033581828,
"grad_norm": 0.9185569882392883,
"learning_rate": 9.916643399950656e-05,
"loss": 1.78,
"step": 275
},
{
"epoch": 0.1560649341601059,
"grad_norm": 1.001341462135315,
"learning_rate": 9.907567980648549e-05,
"loss": 1.7572,
"step": 280
},
{
"epoch": 0.1588518079843935,
"grad_norm": 0.8067627549171448,
"learning_rate": 9.898028305265169e-05,
"loss": 1.8483,
"step": 285
},
{
"epoch": 0.1616386818086811,
"grad_norm": 0.9016091227531433,
"learning_rate": 9.888025276254096e-05,
"loss": 1.8052,
"step": 290
},
{
"epoch": 0.1644255556329687,
"grad_norm": 0.8889392614364624,
"learning_rate": 9.877559839902184e-05,
"loss": 1.7675,
"step": 295
},
{
"epoch": 0.1672124294572563,
"grad_norm": 0.9415964484214783,
"learning_rate": 9.86663298624003e-05,
"loss": 1.7407,
"step": 300
},
{
"epoch": 0.16999930328154392,
"grad_norm": 0.9528254866600037,
"learning_rate": 9.855245748948326e-05,
"loss": 1.8361,
"step": 305
},
{
"epoch": 0.17278617710583152,
"grad_norm": 0.9676885604858398,
"learning_rate": 9.843399205260068e-05,
"loss": 1.8083,
"step": 310
},
{
"epoch": 0.17557305093011913,
"grad_norm": 0.9517872929573059,
"learning_rate": 9.831094475858652e-05,
"loss": 1.7797,
"step": 315
},
{
"epoch": 0.17835992475440673,
"grad_norm": 0.857660710811615,
"learning_rate": 9.818332724771857e-05,
"loss": 1.8284,
"step": 320
},
{
"epoch": 0.18114679857869434,
"grad_norm": 0.8926770091056824,
"learning_rate": 9.805115159261726e-05,
"loss": 1.7447,
"step": 325
},
{
"epoch": 0.18393367240298195,
"grad_norm": 0.9329388737678528,
"learning_rate": 9.791443029710361e-05,
"loss": 1.7078,
"step": 330
},
{
"epoch": 0.18672054622726955,
"grad_norm": 0.918548047542572,
"learning_rate": 9.777317629501636e-05,
"loss": 1.7399,
"step": 335
},
{
"epoch": 0.18950742005155716,
"grad_norm": 0.8394548892974854,
"learning_rate": 9.762740294898846e-05,
"loss": 1.7007,
"step": 340
},
{
"epoch": 0.19229429387584476,
"grad_norm": 0.8728898763656616,
"learning_rate": 9.747712404918286e-05,
"loss": 1.6901,
"step": 345
},
{
"epoch": 0.19508116770013237,
"grad_norm": 0.9779082536697388,
"learning_rate": 9.732235381198813e-05,
"loss": 1.7845,
"step": 350
},
{
"epoch": 0.19786804152441997,
"grad_norm": 0.8378227353096008,
"learning_rate": 9.716310687867342e-05,
"loss": 1.635,
"step": 355
},
{
"epoch": 0.20065491534870758,
"grad_norm": 0.8649258613586426,
"learning_rate": 9.699939831400351e-05,
"loss": 1.8253,
"step": 360
},
{
"epoch": 0.20344178917299519,
"grad_norm": 0.8968847393989563,
"learning_rate": 9.683124360481364e-05,
"loss": 1.7642,
"step": 365
},
{
"epoch": 0.2062286629972828,
"grad_norm": 0.9765416383743286,
"learning_rate": 9.665865865854445e-05,
"loss": 1.7616,
"step": 370
},
{
"epoch": 0.2090155368215704,
"grad_norm": 0.8812718391418457,
"learning_rate": 9.648165980173712e-05,
"loss": 1.7531,
"step": 375
},
{
"epoch": 0.211802410645858,
"grad_norm": 0.9416605830192566,
"learning_rate": 9.630026377848892e-05,
"loss": 1.7552,
"step": 380
},
{
"epoch": 0.2145892844701456,
"grad_norm": 0.8550388813018799,
"learning_rate": 9.611448774886924e-05,
"loss": 1.7298,
"step": 385
},
{
"epoch": 0.2173761582944332,
"grad_norm": 0.8427929878234863,
"learning_rate": 9.592434928729616e-05,
"loss": 1.8126,
"step": 390
},
{
"epoch": 0.22016303211872082,
"grad_norm": 0.931085467338562,
"learning_rate": 9.572986638087396e-05,
"loss": 1.7887,
"step": 395
},
{
"epoch": 0.22294990594300843,
"grad_norm": 0.8902835249900818,
"learning_rate": 9.553105742769154e-05,
"loss": 1.7183,
"step": 400
},
{
"epoch": 0.22573677976729603,
"grad_norm": 0.9223161935806274,
"learning_rate": 9.532794123508197e-05,
"loss": 1.6089,
"step": 405
},
{
"epoch": 0.22852365359158364,
"grad_norm": 0.891255795955658,
"learning_rate": 9.512053701784329e-05,
"loss": 1.7492,
"step": 410
},
{
"epoch": 0.23131052741587124,
"grad_norm": 0.8654237985610962,
"learning_rate": 9.490886439642081e-05,
"loss": 1.7518,
"step": 415
},
{
"epoch": 0.23409740124015885,
"grad_norm": 0.8336911797523499,
"learning_rate": 9.469294339505098e-05,
"loss": 1.7774,
"step": 420
},
{
"epoch": 0.23688427506444645,
"grad_norm": 0.8676822781562805,
"learning_rate": 9.447279443986716e-05,
"loss": 1.729,
"step": 425
},
{
"epoch": 0.23967114888873406,
"grad_norm": 0.8923869729042053,
"learning_rate": 9.424843835696724e-05,
"loss": 1.755,
"step": 430
},
{
"epoch": 0.24245802271302166,
"grad_norm": 0.9599496126174927,
"learning_rate": 9.401989637044355e-05,
"loss": 1.713,
"step": 435
},
{
"epoch": 0.24524489653730927,
"grad_norm": 0.9062650203704834,
"learning_rate": 9.3787190100375e-05,
"loss": 1.761,
"step": 440
},
{
"epoch": 0.24803177036159688,
"grad_norm": 0.8786470293998718,
"learning_rate": 9.355034156078188e-05,
"loss": 1.7075,
"step": 445
},
{
"epoch": 0.2508186441858845,
"grad_norm": 0.8370506763458252,
"learning_rate": 9.330937315754329e-05,
"loss": 1.7274,
"step": 450
},
{
"epoch": 0.2536055180101721,
"grad_norm": 0.8878483772277832,
"learning_rate": 9.306430768627753e-05,
"loss": 1.7198,
"step": 455
},
{
"epoch": 0.2563923918344597,
"grad_norm": 0.8782411813735962,
"learning_rate": 9.281516833018571e-05,
"loss": 1.7402,
"step": 460
},
{
"epoch": 0.2591792656587473,
"grad_norm": 0.809499979019165,
"learning_rate": 9.256197865785854e-05,
"loss": 1.7894,
"step": 465
},
{
"epoch": 0.26196613948303493,
"grad_norm": 0.802325963973999,
"learning_rate": 9.230476262104677e-05,
"loss": 1.7194,
"step": 470
},
{
"epoch": 0.26475301330732254,
"grad_norm": 0.9014655947685242,
"learning_rate": 9.204354455239539e-05,
"loss": 1.7598,
"step": 475
},
{
"epoch": 0.26753988713161014,
"grad_norm": 0.8868433833122253,
"learning_rate": 9.177834916314165e-05,
"loss": 1.7375,
"step": 480
},
{
"epoch": 0.27032676095589775,
"grad_norm": 0.834866464138031,
"learning_rate": 9.150920154077754e-05,
"loss": 1.7407,
"step": 485
},
{
"epoch": 0.27311363478018535,
"grad_norm": 0.8939329385757446,
"learning_rate": 9.123612714667634e-05,
"loss": 1.7474,
"step": 490
},
{
"epoch": 0.2759005086044729,
"grad_norm": 0.8077359199523926,
"learning_rate": 9.095915181368412e-05,
"loss": 1.7889,
"step": 495
},
{
"epoch": 0.2786873824287605,
"grad_norm": 0.9387168884277344,
"learning_rate": 9.067830174367586e-05,
"loss": 1.7851,
"step": 500
},
{
"epoch": 0.2814742562530481,
"grad_norm": 0.8156746029853821,
"learning_rate": 9.039360350507679e-05,
"loss": 1.7452,
"step": 505
},
{
"epoch": 0.2842611300773357,
"grad_norm": 0.8565810918807983,
"learning_rate": 9.010508403034898e-05,
"loss": 1.7009,
"step": 510
},
{
"epoch": 0.2870480039016233,
"grad_norm": 0.8893343210220337,
"learning_rate": 8.98127706134436e-05,
"loss": 1.7087,
"step": 515
},
{
"epoch": 0.28983487772591093,
"grad_norm": 0.9117178916931152,
"learning_rate": 8.951669090721881e-05,
"loss": 1.7378,
"step": 520
},
{
"epoch": 0.29262175155019854,
"grad_norm": 0.9399023056030273,
"learning_rate": 8.921687292082393e-05,
"loss": 1.6617,
"step": 525
},
{
"epoch": 0.29540862537448614,
"grad_norm": 0.8288427591323853,
"learning_rate": 8.891334501704962e-05,
"loss": 1.7308,
"step": 530
},
{
"epoch": 0.29819549919877375,
"grad_norm": 0.8749653100967407,
"learning_rate": 8.86061359096449e-05,
"loss": 1.6901,
"step": 535
},
{
"epoch": 0.30098237302306136,
"grad_norm": 0.8881510496139526,
"learning_rate": 8.829527466060072e-05,
"loss": 1.5869,
"step": 540
},
{
"epoch": 0.30376924684734896,
"grad_norm": 0.8279595375061035,
"learning_rate": 8.798079067740077e-05,
"loss": 1.8123,
"step": 545
},
{
"epoch": 0.30655612067163657,
"grad_norm": 0.9029069542884827,
"learning_rate": 8.766271371023948e-05,
"loss": 1.7349,
"step": 550
},
{
"epoch": 0.3093429944959242,
"grad_norm": 0.8651466369628906,
"learning_rate": 8.73410738492077e-05,
"loss": 1.682,
"step": 555
},
{
"epoch": 0.3121298683202118,
"grad_norm": 0.8340917229652405,
"learning_rate": 8.701590152144612e-05,
"loss": 1.6731,
"step": 560
},
{
"epoch": 0.3149167421444994,
"grad_norm": 0.8674319982528687,
"learning_rate": 8.668722748826693e-05,
"loss": 1.7077,
"step": 565
},
{
"epoch": 0.317703615968787,
"grad_norm": 0.8814576864242554,
"learning_rate": 8.635508284224371e-05,
"loss": 1.8157,
"step": 570
},
{
"epoch": 0.3204904897930746,
"grad_norm": 0.8834437131881714,
"learning_rate": 8.601949900427016e-05,
"loss": 1.694,
"step": 575
},
{
"epoch": 0.3232773636173622,
"grad_norm": 0.9366668462753296,
"learning_rate": 8.568050772058762e-05,
"loss": 1.7509,
"step": 580
},
{
"epoch": 0.3260642374416498,
"grad_norm": 0.8931873440742493,
"learning_rate": 8.533814105978191e-05,
"loss": 1.7052,
"step": 585
},
{
"epoch": 0.3288511112659374,
"grad_norm": 0.8785414099693298,
"learning_rate": 8.499243140974966e-05,
"loss": 1.7102,
"step": 590
},
{
"epoch": 0.331637985090225,
"grad_norm": 0.8543146252632141,
"learning_rate": 8.464341147463431e-05,
"loss": 1.7142,
"step": 595
},
{
"epoch": 0.3344248589145126,
"grad_norm": 0.9020870327949524,
"learning_rate": 8.429111427173241e-05,
"loss": 1.6234,
"step": 600
},
{
"epoch": 0.33721173273880023,
"grad_norm": 0.8740977644920349,
"learning_rate": 8.393557312837018e-05,
"loss": 1.6647,
"step": 605
},
{
"epoch": 0.33999860656308784,
"grad_norm": 0.8990283012390137,
"learning_rate": 8.357682167875062e-05,
"loss": 1.7637,
"step": 610
},
{
"epoch": 0.34278548038737544,
"grad_norm": 0.9558935165405273,
"learning_rate": 8.321489386077192e-05,
"loss": 1.7098,
"step": 615
},
{
"epoch": 0.34557235421166305,
"grad_norm": 0.840876042842865,
"learning_rate": 8.28498239128167e-05,
"loss": 1.7591,
"step": 620
},
{
"epoch": 0.34835922803595065,
"grad_norm": 0.9125795364379883,
"learning_rate": 8.248164637051321e-05,
"loss": 1.7025,
"step": 625
},
{
"epoch": 0.35114610186023826,
"grad_norm": 0.8371095657348633,
"learning_rate": 8.211039606346826e-05,
"loss": 1.7466,
"step": 630
},
{
"epoch": 0.35393297568452586,
"grad_norm": 0.9032928347587585,
"learning_rate": 8.173610811197226e-05,
"loss": 1.7037,
"step": 635
},
{
"epoch": 0.35671984950881347,
"grad_norm": 0.8027083277702332,
"learning_rate": 8.135881792367686e-05,
"loss": 1.7173,
"step": 640
},
{
"epoch": 0.3595067233331011,
"grad_norm": 0.832089364528656,
"learning_rate": 8.097856119024545e-05,
"loss": 1.7864,
"step": 645
},
{
"epoch": 0.3622935971573887,
"grad_norm": 0.8472860455513,
"learning_rate": 8.059537388397665e-05,
"loss": 1.7247,
"step": 650
},
{
"epoch": 0.3650804709816763,
"grad_norm": 0.879154622554779,
"learning_rate": 8.020929225440137e-05,
"loss": 1.725,
"step": 655
},
{
"epoch": 0.3678673448059639,
"grad_norm": 0.8750869035720825,
"learning_rate": 7.98203528248536e-05,
"loss": 1.7209,
"step": 660
},
{
"epoch": 0.3706542186302515,
"grad_norm": 0.8920248746871948,
"learning_rate": 7.942859238901528e-05,
"loss": 1.7535,
"step": 665
},
{
"epoch": 0.3734410924545391,
"grad_norm": 0.9911733269691467,
"learning_rate": 7.903404800743564e-05,
"loss": 1.7775,
"step": 670
},
{
"epoch": 0.3762279662788267,
"grad_norm": 0.9664769768714905,
"learning_rate": 7.863675700402526e-05,
"loss": 1.6848,
"step": 675
},
{
"epoch": 0.3790148401031143,
"grad_norm": 0.9310293197631836,
"learning_rate": 7.823675696252524e-05,
"loss": 1.7937,
"step": 680
},
{
"epoch": 0.3818017139274019,
"grad_norm": 0.9020529389381409,
"learning_rate": 7.783408572295174e-05,
"loss": 1.7545,
"step": 685
},
{
"epoch": 0.3845885877516895,
"grad_norm": 0.9094440937042236,
"learning_rate": 7.742878137801639e-05,
"loss": 1.7,
"step": 690
},
{
"epoch": 0.38737546157597713,
"grad_norm": 0.8321011662483215,
"learning_rate": 7.702088226952258e-05,
"loss": 1.6553,
"step": 695
},
{
"epoch": 0.39016233540026474,
"grad_norm": 0.9105309844017029,
"learning_rate": 7.661042698473853e-05,
"loss": 1.6446,
"step": 700
},
{
"epoch": 0.39294920922455234,
"grad_norm": 0.8597806096076965,
"learning_rate": 7.619745435274667e-05,
"loss": 1.7055,
"step": 705
},
{
"epoch": 0.39573608304883995,
"grad_norm": 0.8919932842254639,
"learning_rate": 7.578200344077073e-05,
"loss": 1.7395,
"step": 710
},
{
"epoch": 0.39852295687312755,
"grad_norm": 0.8174524307250977,
"learning_rate": 7.536411355047964e-05,
"loss": 1.7054,
"step": 715
},
{
"epoch": 0.40130983069741516,
"grad_norm": 0.9026328921318054,
"learning_rate": 7.494382421426984e-05,
"loss": 1.7485,
"step": 720
},
{
"epoch": 0.40409670452170277,
"grad_norm": 0.851669192314148,
"learning_rate": 7.452117519152542e-05,
"loss": 1.6561,
"step": 725
},
{
"epoch": 0.40688357834599037,
"grad_norm": 0.9910186529159546,
"learning_rate": 7.409620646485685e-05,
"loss": 1.6739,
"step": 730
},
{
"epoch": 0.409670452170278,
"grad_norm": 0.8900603652000427,
"learning_rate": 7.36689582363187e-05,
"loss": 1.7451,
"step": 735
},
{
"epoch": 0.4124573259945656,
"grad_norm": 0.9462478756904602,
"learning_rate": 7.323947092360649e-05,
"loss": 1.6377,
"step": 740
},
{
"epoch": 0.4152441998188532,
"grad_norm": 0.8992497324943542,
"learning_rate": 7.280778515623314e-05,
"loss": 1.7855,
"step": 745
},
{
"epoch": 0.4180310736431408,
"grad_norm": 0.9079445004463196,
"learning_rate": 7.237394177168548e-05,
"loss": 1.7371,
"step": 750
},
{
"epoch": 0.4208179474674284,
"grad_norm": 0.965009331703186,
"learning_rate": 7.193798181156095e-05,
"loss": 1.7658,
"step": 755
},
{
"epoch": 0.423604821291716,
"grad_norm": 0.9303287267684937,
"learning_rate": 7.149994651768514e-05,
"loss": 1.5907,
"step": 760
},
{
"epoch": 0.4263916951160036,
"grad_norm": 0.9236851930618286,
"learning_rate": 7.10598773282103e-05,
"loss": 1.7138,
"step": 765
},
{
"epoch": 0.4291785689402912,
"grad_norm": 0.9575843811035156,
"learning_rate": 7.061781587369519e-05,
"loss": 1.7821,
"step": 770
},
{
"epoch": 0.4319654427645788,
"grad_norm": 0.8724859356880188,
"learning_rate": 7.017380397316695e-05,
"loss": 1.6573,
"step": 775
},
{
"epoch": 0.4347523165888664,
"grad_norm": 0.8420785069465637,
"learning_rate": 6.972788363016497e-05,
"loss": 1.6137,
"step": 780
},
{
"epoch": 0.43753919041315403,
"grad_norm": 0.8934415578842163,
"learning_rate": 6.92800970287674e-05,
"loss": 1.7319,
"step": 785
},
{
"epoch": 0.44032606423744164,
"grad_norm": 0.8006248474121094,
"learning_rate": 6.883048652960038e-05,
"loss": 1.7072,
"step": 790
},
{
"epoch": 0.44311293806172924,
"grad_norm": 0.9047636985778809,
"learning_rate": 6.837909466583095e-05,
"loss": 1.7261,
"step": 795
},
{
"epoch": 0.44589981188601685,
"grad_norm": 0.779268741607666,
"learning_rate": 6.792596413914324e-05,
"loss": 1.6165,
"step": 800
},
{
"epoch": 0.44868668571030446,
"grad_norm": 0.9055292010307312,
"learning_rate": 6.747113781569892e-05,
"loss": 1.7387,
"step": 805
},
{
"epoch": 0.45147355953459206,
"grad_norm": 0.9208706021308899,
"learning_rate": 6.701465872208216e-05,
"loss": 1.7796,
"step": 810
},
{
"epoch": 0.45426043335887967,
"grad_norm": 0.9025313854217529,
"learning_rate": 6.655657004122916e-05,
"loss": 1.7529,
"step": 815
},
{
"epoch": 0.4570473071831673,
"grad_norm": 0.9193456768989563,
"learning_rate": 6.60969151083432e-05,
"loss": 1.6877,
"step": 820
},
{
"epoch": 0.4598341810074549,
"grad_norm": 0.8689644932746887,
"learning_rate": 6.563573740679496e-05,
"loss": 1.6914,
"step": 825
},
{
"epoch": 0.4626210548317425,
"grad_norm": 0.8842869997024536,
"learning_rate": 6.517308056400917e-05,
"loss": 1.7067,
"step": 830
},
{
"epoch": 0.4654079286560301,
"grad_norm": 0.8941370844841003,
"learning_rate": 6.470898834733731e-05,
"loss": 1.6821,
"step": 835
},
{
"epoch": 0.4681948024803177,
"grad_norm": 0.8482221961021423,
"learning_rate": 6.42435046599173e-05,
"loss": 1.6795,
"step": 840
},
{
"epoch": 0.4709816763046053,
"grad_norm": 0.9269408583641052,
"learning_rate": 6.377667353652022e-05,
"loss": 1.7339,
"step": 845
},
{
"epoch": 0.4737685501288929,
"grad_norm": 0.8573038578033447,
"learning_rate": 6.330853913938466e-05,
"loss": 1.6697,
"step": 850
},
{
"epoch": 0.4765554239531805,
"grad_norm": 0.9166283011436462,
"learning_rate": 6.283914575403888e-05,
"loss": 1.762,
"step": 855
},
{
"epoch": 0.4793422977774681,
"grad_norm": 0.9675526022911072,
"learning_rate": 6.236853778511156e-05,
"loss": 1.7138,
"step": 860
},
{
"epoch": 0.4821291716017557,
"grad_norm": 0.9200772643089294,
"learning_rate": 6.189675975213094e-05,
"loss": 1.687,
"step": 865
},
{
"epoch": 0.48491604542604333,
"grad_norm": 0.9093224406242371,
"learning_rate": 6.142385628531342e-05,
"loss": 1.7252,
"step": 870
},
{
"epoch": 0.48770291925033094,
"grad_norm": 0.936658501625061,
"learning_rate": 6.09498721213414e-05,
"loss": 1.6559,
"step": 875
},
{
"epoch": 0.49048979307461854,
"grad_norm": 0.9464199542999268,
"learning_rate": 6.047485209913137e-05,
"loss": 1.7701,
"step": 880
},
{
"epoch": 0.49327666689890615,
"grad_norm": 0.8395586609840393,
"learning_rate": 5.999884115559192e-05,
"loss": 1.6787,
"step": 885
},
{
"epoch": 0.49606354072319375,
"grad_norm": 0.8512603044509888,
"learning_rate": 5.952188432137293e-05,
"loss": 1.6798,
"step": 890
},
{
"epoch": 0.49885041454748136,
"grad_norm": 0.7427195310592651,
"learning_rate": 5.90440267166055e-05,
"loss": 1.6409,
"step": 895
},
{
"epoch": 0.501637288371769,
"grad_norm": 0.9125031232833862,
"learning_rate": 5.8565313546633684e-05,
"loss": 1.7183,
"step": 900
},
{
"epoch": 0.5044241621960566,
"grad_norm": 0.8311697244644165,
"learning_rate": 5.8085790097738025e-05,
"loss": 1.6997,
"step": 905
},
{
"epoch": 0.5072110360203442,
"grad_norm": 0.8667879700660706,
"learning_rate": 5.7605501732851475e-05,
"loss": 1.7496,
"step": 910
},
{
"epoch": 0.5099979098446318,
"grad_norm": 0.8262993693351746,
"learning_rate": 5.712449388726807e-05,
"loss": 1.7133,
"step": 915
},
{
"epoch": 0.5127847836689194,
"grad_norm": 0.8778572678565979,
"learning_rate": 5.664281206434472e-05,
"loss": 1.6403,
"step": 920
},
{
"epoch": 0.515571657493207,
"grad_norm": 0.879878044128418,
"learning_rate": 5.616050183119663e-05,
"loss": 1.7529,
"step": 925
},
{
"epoch": 0.5183585313174947,
"grad_norm": 0.8514410257339478,
"learning_rate": 5.5677608814386616e-05,
"loss": 1.5793,
"step": 930
},
{
"epoch": 0.5211454051417822,
"grad_norm": 0.9288901686668396,
"learning_rate": 5.519417869560889e-05,
"loss": 1.6991,
"step": 935
},
{
"epoch": 0.5239322789660699,
"grad_norm": 0.9093351364135742,
"learning_rate": 5.471025720736747e-05,
"loss": 1.7363,
"step": 940
},
{
"epoch": 0.5267191527903574,
"grad_norm": 0.893335223197937,
"learning_rate": 5.422589012864996e-05,
"loss": 1.7376,
"step": 945
},
{
"epoch": 0.5295060266146451,
"grad_norm": 0.9974896311759949,
"learning_rate": 5.3741123280596864e-05,
"loss": 1.6616,
"step": 950
},
{
"epoch": 0.5322929004389326,
"grad_norm": 0.8804664015769958,
"learning_rate": 5.325600252216685e-05,
"loss": 1.6733,
"step": 955
},
{
"epoch": 0.5350797742632203,
"grad_norm": 0.8462238311767578,
"learning_rate": 5.27705737457985e-05,
"loss": 1.6006,
"step": 960
},
{
"epoch": 0.5378666480875078,
"grad_norm": 0.9450251460075378,
"learning_rate": 5.228488287306896e-05,
"loss": 1.6687,
"step": 965
},
{
"epoch": 0.5406535219117955,
"grad_norm": 0.8269532322883606,
"learning_rate": 5.179897585034963e-05,
"loss": 1.7119,
"step": 970
},
{
"epoch": 0.543440395736083,
"grad_norm": 0.884152889251709,
"learning_rate": 5.1312898644459776e-05,
"loss": 1.5961,
"step": 975
},
{
"epoch": 0.5462272695603707,
"grad_norm": 0.9271142482757568,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.6841,
"step": 980
},
{
"epoch": 0.5490141433846583,
"grad_norm": 0.8629387021064758,
"learning_rate": 5.0340417626592016e-05,
"loss": 1.6719,
"step": 985
},
{
"epoch": 0.5518010172089458,
"grad_norm": 0.9146392345428467,
"learning_rate": 4.9854105811348216e-05,
"loss": 1.7152,
"step": 990
},
{
"epoch": 0.5545878910332335,
"grad_norm": 0.9807288646697998,
"learning_rate": 4.936780779769913e-05,
"loss": 1.7132,
"step": 995
},
{
"epoch": 0.557374764857521,
"grad_norm": 0.8988499045372009,
"learning_rate": 4.888156958945174e-05,
"loss": 1.6832,
"step": 1000
},
{
"epoch": 0.5601616386818087,
"grad_norm": 0.9300522804260254,
"learning_rate": 4.839543718475543e-05,
"loss": 1.6807,
"step": 1005
},
{
"epoch": 0.5629485125060962,
"grad_norm": 0.9890733361244202,
"learning_rate": 4.790945657175061e-05,
"loss": 1.7154,
"step": 1010
},
{
"epoch": 0.5657353863303839,
"grad_norm": 0.945864737033844,
"learning_rate": 4.742367372421811e-05,
"loss": 1.7254,
"step": 1015
},
{
"epoch": 0.5685222601546714,
"grad_norm": 0.9854418635368347,
"learning_rate": 4.69381345972302e-05,
"loss": 1.6697,
"step": 1020
},
{
"epoch": 0.5713091339789591,
"grad_norm": 0.8477269411087036,
"learning_rate": 4.6452885122803205e-05,
"loss": 1.6416,
"step": 1025
},
{
"epoch": 0.5740960078032467,
"grad_norm": 0.8343554735183716,
"learning_rate": 4.5967971205552194e-05,
"loss": 1.7028,
"step": 1030
},
{
"epoch": 0.5768828816275343,
"grad_norm": 0.8979123830795288,
"learning_rate": 4.548343871834864e-05,
"loss": 1.6813,
"step": 1035
},
{
"epoch": 0.5796697554518219,
"grad_norm": 0.8494421243667603,
"learning_rate": 4.499933349798067e-05,
"loss": 1.7468,
"step": 1040
},
{
"epoch": 0.5824566292761095,
"grad_norm": 0.9138739109039307,
"learning_rate": 4.451570134081694e-05,
"loss": 1.7778,
"step": 1045
},
{
"epoch": 0.5852435031003971,
"grad_norm": 0.878416895866394,
"learning_rate": 4.403258799847433e-05,
"loss": 1.6617,
"step": 1050
},
{
"epoch": 0.5880303769246847,
"grad_norm": 0.9622417092323303,
"learning_rate": 4.3550039173489845e-05,
"loss": 1.6687,
"step": 1055
},
{
"epoch": 0.5908172507489723,
"grad_norm": 0.9560658931732178,
"learning_rate": 4.306810051499708e-05,
"loss": 1.599,
"step": 1060
},
{
"epoch": 0.59360412457326,
"grad_norm": 0.9835667014122009,
"learning_rate": 4.2586817614407895e-05,
"loss": 1.7027,
"step": 1065
},
{
"epoch": 0.5963909983975475,
"grad_norm": 0.8164546489715576,
"learning_rate": 4.210623600109946e-05,
"loss": 1.5703,
"step": 1070
},
{
"epoch": 0.5991778722218352,
"grad_norm": 0.9227034449577332,
"learning_rate": 4.162640113810706e-05,
"loss": 1.7212,
"step": 1075
},
{
"epoch": 0.6019647460461227,
"grad_norm": 0.9340742826461792,
"learning_rate": 4.114735841782347e-05,
"loss": 1.7766,
"step": 1080
},
{
"epoch": 0.6047516198704104,
"grad_norm": 0.8985697627067566,
"learning_rate": 4.06691531577047e-05,
"loss": 1.6734,
"step": 1085
},
{
"epoch": 0.6075384936946979,
"grad_norm": 0.8550668954849243,
"learning_rate": 4.019183059598296e-05,
"loss": 1.6567,
"step": 1090
},
{
"epoch": 0.6103253675189856,
"grad_norm": 0.8353204131126404,
"learning_rate": 3.971543588738724e-05,
"loss": 1.6697,
"step": 1095
},
{
"epoch": 0.6131122413432731,
"grad_norm": 0.9074715971946716,
"learning_rate": 3.924001409887158e-05,
"loss": 1.6269,
"step": 1100
},
{
"epoch": 0.6158991151675608,
"grad_norm": 0.967217743396759,
"learning_rate": 3.87656102053517e-05,
"loss": 1.7003,
"step": 1105
},
{
"epoch": 0.6186859889918483,
"grad_norm": 0.9192699790000916,
"learning_rate": 3.8292269085450474e-05,
"loss": 1.6595,
"step": 1110
},
{
"epoch": 0.621472862816136,
"grad_norm": 0.8587005734443665,
"learning_rate": 3.782003551725236e-05,
"loss": 1.7265,
"step": 1115
},
{
"epoch": 0.6242597366404236,
"grad_norm": 0.8794726729393005,
"learning_rate": 3.734895417406734e-05,
"loss": 1.6934,
"step": 1120
},
{
"epoch": 0.6270466104647112,
"grad_norm": 0.885074257850647,
"learning_rate": 3.687906962020491e-05,
"loss": 1.715,
"step": 1125
},
{
"epoch": 0.6298334842889988,
"grad_norm": 0.9730757474899292,
"learning_rate": 3.641042630675829e-05,
"loss": 1.7218,
"step": 1130
},
{
"epoch": 0.6326203581132864,
"grad_norm": 0.9168181419372559,
"learning_rate": 3.594306856739924e-05,
"loss": 1.6495,
"step": 1135
},
{
"epoch": 0.635407231937574,
"grad_norm": 0.8995612263679504,
"learning_rate": 3.547704061418424e-05,
"loss": 1.646,
"step": 1140
},
{
"epoch": 0.6381941057618616,
"grad_norm": 0.9839945435523987,
"learning_rate": 3.501238653337194e-05,
"loss": 1.6917,
"step": 1145
},
{
"epoch": 0.6409809795861492,
"grad_norm": 0.9783616065979004,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.735,
"step": 1150
},
{
"epoch": 0.6437678534104369,
"grad_norm": 0.9493193626403809,
"learning_rate": 3.408737567998993e-05,
"loss": 1.6089,
"step": 1155
},
{
"epoch": 0.6465547272347244,
"grad_norm": 0.9332829117774963,
"learning_rate": 3.362710641347524e-05,
"loss": 1.7385,
"step": 1160
},
{
"epoch": 0.6493416010590121,
"grad_norm": 0.8816719651222229,
"learning_rate": 3.316838602319532e-05,
"loss": 1.7287,
"step": 1165
},
{
"epoch": 0.6521284748832996,
"grad_norm": 0.9816229343414307,
"learning_rate": 3.271125790411309e-05,
"loss": 1.567,
"step": 1170
},
{
"epoch": 0.6549153487075873,
"grad_norm": 0.9800401329994202,
"learning_rate": 3.225576530056264e-05,
"loss": 1.7358,
"step": 1175
},
{
"epoch": 0.6577022225318748,
"grad_norm": 0.8312817215919495,
"learning_rate": 3.180195130215824e-05,
"loss": 1.6703,
"step": 1180
},
{
"epoch": 0.6604890963561625,
"grad_norm": 1.055208683013916,
"learning_rate": 3.1349858839717986e-05,
"loss": 1.6207,
"step": 1185
},
{
"epoch": 0.66327597018045,
"grad_norm": 0.8680506944656372,
"learning_rate": 3.089953068120271e-05,
"loss": 1.5938,
"step": 1190
},
{
"epoch": 0.6660628440047377,
"grad_norm": 0.939007580280304,
"learning_rate": 3.0451009427669986e-05,
"loss": 1.6168,
"step": 1195
},
{
"epoch": 0.6688497178290252,
"grad_norm": 0.8930026888847351,
"learning_rate": 3.000433750924414e-05,
"loss": 1.6622,
"step": 1200
},
{
"epoch": 0.6716365916533129,
"grad_norm": 0.8716943264007568,
"learning_rate": 2.9559557181102315e-05,
"loss": 1.6795,
"step": 1205
},
{
"epoch": 0.6744234654776005,
"grad_norm": 1.015537977218628,
"learning_rate": 2.911671051947722e-05,
"loss": 1.6185,
"step": 1210
},
{
"epoch": 0.6772103393018881,
"grad_norm": 0.9457005858421326,
"learning_rate": 2.867583941767657e-05,
"loss": 1.5931,
"step": 1215
},
{
"epoch": 0.6799972131261757,
"grad_norm": 0.9158906936645508,
"learning_rate": 2.823698558212009e-05,
"loss": 1.6798,
"step": 1220
},
{
"epoch": 0.6827840869504633,
"grad_norm": 0.9375888705253601,
"learning_rate": 2.7800190528394122e-05,
"loss": 1.6461,
"step": 1225
},
{
"epoch": 0.6855709607747509,
"grad_norm": 0.8816511631011963,
"learning_rate": 2.736549557732405e-05,
"loss": 1.5936,
"step": 1230
},
{
"epoch": 0.6883578345990385,
"grad_norm": 0.9316837191581726,
"learning_rate": 2.693294185106562e-05,
"loss": 1.8401,
"step": 1235
},
{
"epoch": 0.6911447084233261,
"grad_norm": 0.963299036026001,
"learning_rate": 2.650257026921455e-05,
"loss": 1.7008,
"step": 1240
},
{
"epoch": 0.6939315822476138,
"grad_norm": 0.9570043683052063,
"learning_rate": 2.607442154493568e-05,
"loss": 1.7346,
"step": 1245
},
{
"epoch": 0.6967184560719013,
"grad_norm": 0.9720516204833984,
"learning_rate": 2.5648536181111438e-05,
"loss": 1.663,
"step": 1250
},
{
"epoch": 0.699505329896189,
"grad_norm": 0.9745333194732666,
"learning_rate": 2.5224954466510274e-05,
"loss": 1.6699,
"step": 1255
},
{
"epoch": 0.7022922037204765,
"grad_norm": 0.9541195631027222,
"learning_rate": 2.480371647197538e-05,
"loss": 1.7154,
"step": 1260
},
{
"epoch": 0.7050790775447642,
"grad_norm": 0.9474685192108154,
"learning_rate": 2.438486204663391e-05,
"loss": 1.6968,
"step": 1265
},
{
"epoch": 0.7078659513690517,
"grad_norm": 0.9263185262680054,
"learning_rate": 2.3968430814127385e-05,
"loss": 1.7174,
"step": 1270
},
{
"epoch": 0.7106528251933394,
"grad_norm": 0.9373622536659241,
"learning_rate": 2.3554462168863085e-05,
"loss": 1.6966,
"step": 1275
},
{
"epoch": 0.7134396990176269,
"grad_norm": 0.9273148775100708,
"learning_rate": 2.314299527228759e-05,
"loss": 1.6983,
"step": 1280
},
{
"epoch": 0.7162265728419146,
"grad_norm": 0.8732434511184692,
"learning_rate": 2.2734069049181882e-05,
"loss": 1.6655,
"step": 1285
},
{
"epoch": 0.7190134466662021,
"grad_norm": 0.9144579768180847,
"learning_rate": 2.2327722183979212e-05,
"loss": 1.6758,
"step": 1290
},
{
"epoch": 0.7218003204904898,
"grad_norm": 0.953395426273346,
"learning_rate": 2.1923993117105462e-05,
"loss": 1.6318,
"step": 1295
},
{
"epoch": 0.7245871943147774,
"grad_norm": 1.013447642326355,
"learning_rate": 2.1522920041342704e-05,
"loss": 1.6395,
"step": 1300
},
{
"epoch": 0.727374068139065,
"grad_norm": 1.0013914108276367,
"learning_rate": 2.1124540898216248e-05,
"loss": 1.6846,
"step": 1305
},
{
"epoch": 0.7301609419633526,
"grad_norm": 0.926443338394165,
"learning_rate": 2.0728893374405166e-05,
"loss": 1.589,
"step": 1310
},
{
"epoch": 0.7329478157876402,
"grad_norm": 1.0215915441513062,
"learning_rate": 2.033601489817738e-05,
"loss": 1.7825,
"step": 1315
},
{
"epoch": 0.7357346896119278,
"grad_norm": 0.9812716245651245,
"learning_rate": 1.9945942635848748e-05,
"loss": 1.7248,
"step": 1320
},
{
"epoch": 0.7385215634362154,
"grad_norm": 0.9645503163337708,
"learning_rate": 1.9558713488267238e-05,
"loss": 1.7045,
"step": 1325
},
{
"epoch": 0.741308437260503,
"grad_norm": 0.9337260127067566,
"learning_rate": 1.917436408732208e-05,
"loss": 1.6771,
"step": 1330
},
{
"epoch": 0.7440953110847907,
"grad_norm": 1.025767207145691,
"learning_rate": 1.8792930792478357e-05,
"loss": 1.6882,
"step": 1335
},
{
"epoch": 0.7468821849090782,
"grad_norm": 1.0005974769592285,
"learning_rate": 1.8414449687337464e-05,
"loss": 1.6064,
"step": 1340
},
{
"epoch": 0.7496690587333659,
"grad_norm": 0.9299675226211548,
"learning_rate": 1.8038956576223504e-05,
"loss": 1.6102,
"step": 1345
},
{
"epoch": 0.7524559325576534,
"grad_norm": 0.892132580280304,
"learning_rate": 1.766648698079635e-05,
"loss": 1.6886,
"step": 1350
},
{
"epoch": 0.7552428063819411,
"grad_norm": 0.9691934585571289,
"learning_rate": 1.7297076136691072e-05,
"loss": 1.7681,
"step": 1355
},
{
"epoch": 0.7580296802062286,
"grad_norm": 1.028360366821289,
"learning_rate": 1.6930758990184875e-05,
"loss": 1.682,
"step": 1360
},
{
"epoch": 0.7608165540305163,
"grad_norm": 1.0175402164459229,
"learning_rate": 1.6567570194891024e-05,
"loss": 1.6757,
"step": 1365
},
{
"epoch": 0.7636034278548038,
"grad_norm": 1.078320860862732,
"learning_rate": 1.620754410848069e-05,
"loss": 1.6719,
"step": 1370
},
{
"epoch": 0.7663903016790915,
"grad_norm": 0.908394992351532,
"learning_rate": 1.5850714789432663e-05,
"loss": 1.7082,
"step": 1375
},
{
"epoch": 0.769177175503379,
"grad_norm": 1.0041537284851074,
"learning_rate": 1.549711599381145e-05,
"loss": 1.7048,
"step": 1380
},
{
"epoch": 0.7719640493276667,
"grad_norm": 0.8650834560394287,
"learning_rate": 1.5146781172073959e-05,
"loss": 1.6771,
"step": 1385
},
{
"epoch": 0.7747509231519543,
"grad_norm": 0.9237532019615173,
"learning_rate": 1.479974346590503e-05,
"loss": 1.662,
"step": 1390
},
{
"epoch": 0.7775377969762419,
"grad_norm": 0.9722338318824768,
"learning_rate": 1.4456035705082349e-05,
"loss": 1.6298,
"step": 1395
},
{
"epoch": 0.7803246708005295,
"grad_norm": 0.9912248253822327,
"learning_rate": 1.4115690404370551e-05,
"loss": 1.6453,
"step": 1400
},
{
"epoch": 0.7831115446248171,
"grad_norm": 0.94923996925354,
"learning_rate": 1.3778739760445552e-05,
"loss": 1.6674,
"step": 1405
},
{
"epoch": 0.7858984184491047,
"grad_norm": 0.9095314741134644,
"learning_rate": 1.344521564884858e-05,
"loss": 1.73,
"step": 1410
},
{
"epoch": 0.7886852922733923,
"grad_norm": 0.9120241403579712,
"learning_rate": 1.3115149620970795e-05,
"loss": 1.6997,
"step": 1415
},
{
"epoch": 0.7914721660976799,
"grad_norm": 1.0032527446746826,
"learning_rate": 1.2788572901068552e-05,
"loss": 1.6553,
"step": 1420
},
{
"epoch": 0.7942590399219676,
"grad_norm": 1.0266504287719727,
"learning_rate": 1.2465516383309551e-05,
"loss": 1.6935,
"step": 1425
},
{
"epoch": 0.7970459137462551,
"grad_norm": 0.9933115243911743,
"learning_rate": 1.2146010628850268e-05,
"loss": 1.7382,
"step": 1430
},
{
"epoch": 0.7998327875705428,
"grad_norm": 0.9467635154724121,
"learning_rate": 1.183008586294485e-05,
"loss": 1.6005,
"step": 1435
},
{
"epoch": 0.8026196613948303,
"grad_norm": 0.9834449887275696,
"learning_rate": 1.151777197208585e-05,
"loss": 1.6238,
"step": 1440
},
{
"epoch": 0.805406535219118,
"grad_norm": 1.0462511777877808,
"learning_rate": 1.1209098501176896e-05,
"loss": 1.645,
"step": 1445
},
{
"epoch": 0.8081934090434055,
"grad_norm": 0.9458158016204834,
"learning_rate": 1.0904094650737795e-05,
"loss": 1.6394,
"step": 1450
},
{
"epoch": 0.8109802828676932,
"grad_norm": 1.178835153579712,
"learning_rate": 1.0602789274142133e-05,
"loss": 1.741,
"step": 1455
},
{
"epoch": 0.8137671566919807,
"grad_norm": 0.9792527556419373,
"learning_rate": 1.0305210874887766e-05,
"loss": 1.6032,
"step": 1460
},
{
"epoch": 0.8165540305162684,
"grad_norm": 0.9719909429550171,
"learning_rate": 1.0011387603900385e-05,
"loss": 1.6489,
"step": 1465
},
{
"epoch": 0.819340904340556,
"grad_norm": 0.9889870285987854,
"learning_rate": 9.7213472568704e-06,
"loss": 1.6819,
"step": 1470
},
{
"epoch": 0.8221277781648436,
"grad_norm": 0.9469426870346069,
"learning_rate": 9.435117271623566e-06,
"loss": 1.53,
"step": 1475
},
{
"epoch": 0.8249146519891312,
"grad_norm": 1.0353251695632935,
"learning_rate": 9.152724725525202e-06,
"loss": 1.6802,
"step": 1480
},
{
"epoch": 0.8277015258134188,
"grad_norm": 0.947878360748291,
"learning_rate": 8.87419633291886e-06,
"loss": 1.6877,
"step": 1485
},
{
"epoch": 0.8304883996377064,
"grad_norm": 1.02825129032135,
"learning_rate": 8.599558442598998e-06,
"loss": 1.6157,
"step": 1490
},
{
"epoch": 0.833275273461994,
"grad_norm": 0.9771981835365295,
"learning_rate": 8.328837035318448e-06,
"loss": 1.7158,
"step": 1495
},
{
"epoch": 0.8360621472862816,
"grad_norm": 0.9021709561347961,
"learning_rate": 8.06205772133063e-06,
"loss": 1.5565,
"step": 1500
},
{
"epoch": 0.8388490211105692,
"grad_norm": 1.0542882680892944,
"learning_rate": 7.799245737966821e-06,
"loss": 1.6085,
"step": 1505
},
{
"epoch": 0.8416358949348568,
"grad_norm": 1.0131638050079346,
"learning_rate": 7.540425947248697e-06,
"loss": 1.6971,
"step": 1510
},
{
"epoch": 0.8444227687591445,
"grad_norm": 0.9090427756309509,
"learning_rate": 7.28562283353637e-06,
"loss": 1.6479,
"step": 1515
},
{
"epoch": 0.847209642583432,
"grad_norm": 0.9409263730049133,
"learning_rate": 7.034860501212243e-06,
"loss": 1.6755,
"step": 1520
},
{
"epoch": 0.8499965164077197,
"grad_norm": 1.0106266736984253,
"learning_rate": 6.788162672400583e-06,
"loss": 1.7402,
"step": 1525
},
{
"epoch": 0.8527833902320072,
"grad_norm": 0.8963887691497803,
"learning_rate": 6.5455526847235825e-06,
"loss": 1.6715,
"step": 1530
},
{
"epoch": 0.8555702640562949,
"grad_norm": 0.9685778021812439,
"learning_rate": 6.307053489093506e-06,
"loss": 1.6622,
"step": 1535
},
{
"epoch": 0.8583571378805824,
"grad_norm": 0.9954646229743958,
"learning_rate": 6.072687647541553e-06,
"loss": 1.6801,
"step": 1540
},
{
"epoch": 0.8611440117048701,
"grad_norm": 0.9309166669845581,
"learning_rate": 5.842477331083518e-06,
"loss": 1.6783,
"step": 1545
},
{
"epoch": 0.8639308855291576,
"grad_norm": 0.9113895297050476,
"learning_rate": 5.616444317622388e-06,
"loss": 1.6001,
"step": 1550
},
{
"epoch": 0.8667177593534453,
"grad_norm": 0.931918203830719,
"learning_rate": 5.394609989888161e-06,
"loss": 1.6932,
"step": 1555
},
{
"epoch": 0.8695046331777329,
"grad_norm": 1.0742195844650269,
"learning_rate": 5.176995333415019e-06,
"loss": 1.6936,
"step": 1560
},
{
"epoch": 0.8722915070020205,
"grad_norm": 1.033225178718567,
"learning_rate": 4.963620934556168e-06,
"loss": 1.6939,
"step": 1565
},
{
"epoch": 0.8750783808263081,
"grad_norm": 0.9259639978408813,
"learning_rate": 4.754506978536227e-06,
"loss": 1.6573,
"step": 1570
},
{
"epoch": 0.8778652546505957,
"grad_norm": 0.8736875653266907,
"learning_rate": 4.549673247541875e-06,
"loss": 1.6819,
"step": 1575
},
{
"epoch": 0.8806521284748833,
"grad_norm": 0.8159767985343933,
"learning_rate": 4.3491391188503264e-06,
"loss": 1.6268,
"step": 1580
},
{
"epoch": 0.8834390022991709,
"grad_norm": 1.0910223722457886,
"learning_rate": 4.152923562996297e-06,
"loss": 1.5947,
"step": 1585
},
{
"epoch": 0.8862258761234585,
"grad_norm": 0.9220096468925476,
"learning_rate": 3.961045141977376e-06,
"loss": 1.6867,
"step": 1590
},
{
"epoch": 0.8890127499477462,
"grad_norm": 1.007515549659729,
"learning_rate": 3.773522007498065e-06,
"loss": 1.6802,
"step": 1595
},
{
"epoch": 0.8917996237720337,
"grad_norm": 0.9113195538520813,
"learning_rate": 3.590371899252659e-06,
"loss": 1.6263,
"step": 1600
},
{
"epoch": 0.8945864975963214,
"grad_norm": 0.8850412964820862,
"learning_rate": 3.4116121432469615e-06,
"loss": 1.6062,
"step": 1605
},
{
"epoch": 0.8973733714206089,
"grad_norm": 0.8960441946983337,
"learning_rate": 3.237259650159402e-06,
"loss": 1.6416,
"step": 1610
},
{
"epoch": 0.9001602452448966,
"grad_norm": 0.9448742866516113,
"learning_rate": 3.0673309137411564e-06,
"loss": 1.6766,
"step": 1615
},
{
"epoch": 0.9029471190691841,
"grad_norm": 1.0214436054229736,
"learning_rate": 2.9018420092558786e-06,
"loss": 1.6145,
"step": 1620
},
{
"epoch": 0.9057339928934718,
"grad_norm": 1.0080410242080688,
"learning_rate": 2.7408085919590264e-06,
"loss": 1.743,
"step": 1625
},
{
"epoch": 0.9085208667177593,
"grad_norm": 0.9665448069572449,
"learning_rate": 2.584245895616788e-06,
"loss": 1.689,
"step": 1630
},
{
"epoch": 0.911307740542047,
"grad_norm": 1.0166733264923096,
"learning_rate": 2.4321687310650487e-06,
"loss": 1.6924,
"step": 1635
},
{
"epoch": 0.9140946143663345,
"grad_norm": 0.9739769101142883,
"learning_rate": 2.2845914848082127e-06,
"loss": 1.7103,
"step": 1640
},
{
"epoch": 0.9168814881906222,
"grad_norm": 1.0058280229568481,
"learning_rate": 2.1415281176583203e-06,
"loss": 1.6628,
"step": 1645
},
{
"epoch": 0.9196683620149098,
"grad_norm": 1.0530660152435303,
"learning_rate": 2.0029921634142632e-06,
"loss": 1.7553,
"step": 1650
},
{
"epoch": 0.9224552358391974,
"grad_norm": 1.0165364742279053,
"learning_rate": 1.8689967275815679e-06,
"loss": 1.6909,
"step": 1655
},
{
"epoch": 0.925242109663485,
"grad_norm": 0.9941847324371338,
"learning_rate": 1.7395544861325718e-06,
"loss": 1.7238,
"step": 1660
},
{
"epoch": 0.9280289834877726,
"grad_norm": 0.9358205795288086,
"learning_rate": 1.614677684307264e-06,
"loss": 1.6756,
"step": 1665
},
{
"epoch": 0.9308158573120602,
"grad_norm": 0.9930801391601562,
"learning_rate": 1.494378135454938e-06,
"loss": 1.6863,
"step": 1670
},
{
"epoch": 0.9336027311363478,
"grad_norm": 0.9550195336341858,
"learning_rate": 1.3786672199165962e-06,
"loss": 1.6767,
"step": 1675
},
{
"epoch": 0.9363896049606354,
"grad_norm": 0.9359130859375,
"learning_rate": 1.2675558839483848e-06,
"loss": 1.6513,
"step": 1680
},
{
"epoch": 0.939176478784923,
"grad_norm": 1.0080687999725342,
"learning_rate": 1.1610546386860988e-06,
"loss": 1.6449,
"step": 1685
},
{
"epoch": 0.9419633526092106,
"grad_norm": 1.0161943435668945,
"learning_rate": 1.0591735591507946e-06,
"loss": 1.6439,
"step": 1690
},
{
"epoch": 0.9447502264334983,
"grad_norm": 1.0032378435134888,
"learning_rate": 9.619222832957243e-07,
"loss": 1.6592,
"step": 1695
},
{
"epoch": 0.9475371002577858,
"grad_norm": 0.9738765358924866,
"learning_rate": 8.693100110945484e-07,
"loss": 1.6532,
"step": 1700
},
{
"epoch": 0.9503239740820735,
"grad_norm": 0.8982930779457092,
"learning_rate": 7.813455036710715e-07,
"loss": 1.623,
"step": 1705
},
{
"epoch": 0.953110847906361,
"grad_norm": 0.9727730751037598,
"learning_rate": 6.980370824703763e-07,
"loss": 1.7,
"step": 1710
},
{
"epoch": 0.9558977217306487,
"grad_norm": 1.0639742612838745,
"learning_rate": 6.193926284716711e-07,
"loss": 1.6124,
"step": 1715
},
{
"epoch": 0.9586845955549362,
"grad_norm": 0.9579203724861145,
"learning_rate": 5.454195814427021e-07,
"loss": 1.7375,
"step": 1720
},
{
"epoch": 0.9614714693792239,
"grad_norm": 0.9791174530982971,
"learning_rate": 4.76124939235989e-07,
"loss": 1.6487,
"step": 1725
},
{
"epoch": 0.9642583432035114,
"grad_norm": 0.972382128238678,
"learning_rate": 4.1151525712680996e-07,
"loss": 1.5941,
"step": 1730
},
{
"epoch": 0.9670452170277991,
"grad_norm": 1.0629900693893433,
"learning_rate": 3.515966471930643e-07,
"loss": 1.7549,
"step": 1735
},
{
"epoch": 0.9698320908520867,
"grad_norm": 0.9898622035980225,
"learning_rate": 2.963747777370907e-07,
"loss": 1.7203,
"step": 1740
},
{
"epoch": 0.9726189646763743,
"grad_norm": 1.0101189613342285,
"learning_rate": 2.458548727494292e-07,
"loss": 1.5727,
"step": 1745
},
{
"epoch": 0.9754058385006619,
"grad_norm": 0.9302470088005066,
"learning_rate": 2.0004171141464467e-07,
"loss": 1.6881,
"step": 1750
},
{
"epoch": 0.9781927123249495,
"grad_norm": 0.9457775950431824,
"learning_rate": 1.589396276591937e-07,
"loss": 1.6543,
"step": 1755
},
{
"epoch": 0.9809795861492371,
"grad_norm": 1.007979154586792,
"learning_rate": 1.225525097414637e-07,
"loss": 1.6081,
"step": 1760
},
{
"epoch": 0.9837664599735247,
"grad_norm": 1.0765361785888672,
"learning_rate": 9.088379988392848e-08,
"loss": 1.6653,
"step": 1765
},
{
"epoch": 0.9865533337978123,
"grad_norm": 1.0036550760269165,
"learning_rate": 6.393649394749734e-08,
"loss": 1.6413,
"step": 1770
},
{
"epoch": 0.9893402076221,
"grad_norm": 1.0382869243621826,
"learning_rate": 4.171314114815306e-08,
"loss": 1.7355,
"step": 1775
},
{
"epoch": 0.9921270814463875,
"grad_norm": 1.0127909183502197,
"learning_rate": 2.4215843815733607e-08,
"loss": 1.5928,
"step": 1780
},
{
"epoch": 0.9949139552706752,
"grad_norm": 0.9076675176620483,
"learning_rate": 1.1446257195119048e-08,
"loss": 1.687,
"step": 1785
},
{
"epoch": 0.9977008290949627,
"grad_norm": 0.9625926613807678,
"learning_rate": 3.4055892895901167e-09,
"loss": 1.6857,
"step": 1790
},
{
"epoch": 1.0,
"grad_norm": 3.522580623626709,
"learning_rate": 9.460074656963969e-11,
"loss": 1.7532,
"step": 1795
},
{
"epoch": 1.0,
"step": 1795,
"total_flos": 1.1921126200049664e+17,
"train_loss": 1.7274433938241602,
"train_runtime": 6288.7205,
"train_samples_per_second": 2.282,
"train_steps_per_second": 0.285
}
],
"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": 1.1921126200049664e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}