newsLLM / checkpoint-1935 /trainer_state.json
ig16's picture
Add files using upload-large-folder tool
c7fef32 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9961270333075136,
"eval_steps": 500,
"global_step": 1935,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015491866769945779,
"grad_norm": 0.40339195728302,
"learning_rate": 9.278350515463919e-07,
"loss": 1.8526,
"step": 10
},
{
"epoch": 0.030983733539891558,
"grad_norm": 0.3715074062347412,
"learning_rate": 1.9587628865979384e-06,
"loss": 1.8835,
"step": 20
},
{
"epoch": 0.046475600309837335,
"grad_norm": 0.3445941209793091,
"learning_rate": 2.9896907216494846e-06,
"loss": 1.8733,
"step": 30
},
{
"epoch": 0.061967467079783116,
"grad_norm": 0.3444959223270416,
"learning_rate": 4.020618556701032e-06,
"loss": 1.8952,
"step": 40
},
{
"epoch": 0.07745933384972889,
"grad_norm": 0.3230769634246826,
"learning_rate": 5.051546391752578e-06,
"loss": 1.8588,
"step": 50
},
{
"epoch": 0.09295120061967467,
"grad_norm": 0.33751699328422546,
"learning_rate": 6.082474226804124e-06,
"loss": 1.8307,
"step": 60
},
{
"epoch": 0.10844306738962045,
"grad_norm": 0.2963869869709015,
"learning_rate": 7.113402061855671e-06,
"loss": 1.8419,
"step": 70
},
{
"epoch": 0.12393493415956623,
"grad_norm": 0.2550879716873169,
"learning_rate": 8.144329896907216e-06,
"loss": 1.8281,
"step": 80
},
{
"epoch": 0.139426800929512,
"grad_norm": 0.22610870003700256,
"learning_rate": 9.175257731958764e-06,
"loss": 1.8005,
"step": 90
},
{
"epoch": 0.15491866769945778,
"grad_norm": 0.1930716335773468,
"learning_rate": 1.0206185567010309e-05,
"loss": 1.7897,
"step": 100
},
{
"epoch": 0.17041053446940357,
"grad_norm": 0.18139410018920898,
"learning_rate": 1.1237113402061856e-05,
"loss": 1.7181,
"step": 110
},
{
"epoch": 0.18590240123934934,
"grad_norm": 0.1586223542690277,
"learning_rate": 1.2268041237113405e-05,
"loss": 1.7328,
"step": 120
},
{
"epoch": 0.2013942680092951,
"grad_norm": 0.2047862708568573,
"learning_rate": 1.3298969072164948e-05,
"loss": 1.7268,
"step": 130
},
{
"epoch": 0.2168861347792409,
"grad_norm": 0.16858699917793274,
"learning_rate": 1.4329896907216495e-05,
"loss": 1.7029,
"step": 140
},
{
"epoch": 0.23237800154918667,
"grad_norm": 0.15446807444095612,
"learning_rate": 1.5360824742268042e-05,
"loss": 1.7114,
"step": 150
},
{
"epoch": 0.24786986831913246,
"grad_norm": 0.1550971418619156,
"learning_rate": 1.6391752577319588e-05,
"loss": 1.7054,
"step": 160
},
{
"epoch": 0.26336173508907823,
"grad_norm": 0.13774091005325317,
"learning_rate": 1.7422680412371137e-05,
"loss": 1.685,
"step": 170
},
{
"epoch": 0.278853601859024,
"grad_norm": 0.13972033560276031,
"learning_rate": 1.8453608247422682e-05,
"loss": 1.6774,
"step": 180
},
{
"epoch": 0.29434546862896976,
"grad_norm": 0.14723576605319977,
"learning_rate": 1.9484536082474227e-05,
"loss": 1.63,
"step": 190
},
{
"epoch": 0.30983733539891556,
"grad_norm": 0.1486756056547165,
"learning_rate": 1.9999592986072886e-05,
"loss": 1.6429,
"step": 200
},
{
"epoch": 0.32532920216886135,
"grad_norm": 0.1460903435945511,
"learning_rate": 1.9996337073445673e-05,
"loss": 1.669,
"step": 210
},
{
"epoch": 0.34082106893880715,
"grad_norm": 0.16247884929180145,
"learning_rate": 1.9989826308331103e-05,
"loss": 1.6572,
"step": 220
},
{
"epoch": 0.3563129357087529,
"grad_norm": 0.16369281709194183,
"learning_rate": 1.998006281066369e-05,
"loss": 1.6545,
"step": 230
},
{
"epoch": 0.3718048024786987,
"grad_norm": 0.1450214833021164,
"learning_rate": 1.996704975948236e-05,
"loss": 1.6762,
"step": 240
},
{
"epoch": 0.3872966692486445,
"grad_norm": 0.17881567776203156,
"learning_rate": 1.9950791391895335e-05,
"loss": 1.6397,
"step": 250
},
{
"epoch": 0.4027885360185902,
"grad_norm": 0.15863952040672302,
"learning_rate": 1.9931293001700518e-05,
"loss": 1.6597,
"step": 260
},
{
"epoch": 0.418280402788536,
"grad_norm": 0.1730642467737198,
"learning_rate": 1.990856093766179e-05,
"loss": 1.6586,
"step": 270
},
{
"epoch": 0.4337722695584818,
"grad_norm": 0.14790953695774078,
"learning_rate": 1.988260260144185e-05,
"loss": 1.6416,
"step": 280
},
{
"epoch": 0.4492641363284276,
"grad_norm": 0.14577385783195496,
"learning_rate": 1.9853426445192175e-05,
"loss": 1.659,
"step": 290
},
{
"epoch": 0.46475600309837334,
"grad_norm": 0.13978034257888794,
"learning_rate": 1.9821041968800982e-05,
"loss": 1.6362,
"step": 300
},
{
"epoch": 0.48024786986831913,
"grad_norm": 0.17719446122646332,
"learning_rate": 1.9785459716800005e-05,
"loss": 1.6648,
"step": 310
},
{
"epoch": 0.4957397366382649,
"grad_norm": 0.1415952891111374,
"learning_rate": 1.9746691274931168e-05,
"loss": 1.6518,
"step": 320
},
{
"epoch": 0.5112316034082107,
"grad_norm": 0.1455707997083664,
"learning_rate": 1.970474926637418e-05,
"loss": 1.6445,
"step": 330
},
{
"epoch": 0.5267234701781565,
"grad_norm": 0.19560855627059937,
"learning_rate": 1.9659647347636422e-05,
"loss": 1.6557,
"step": 340
},
{
"epoch": 0.5422153369481022,
"grad_norm": 0.15447896718978882,
"learning_rate": 1.961140020410627e-05,
"loss": 1.6361,
"step": 350
},
{
"epoch": 0.557707203718048,
"grad_norm": 0.17043063044548035,
"learning_rate": 1.9560023545271512e-05,
"loss": 1.6289,
"step": 360
},
{
"epoch": 0.5731990704879938,
"grad_norm": 0.16939246654510498,
"learning_rate": 1.9505534099604245e-05,
"loss": 1.6318,
"step": 370
},
{
"epoch": 0.5886909372579395,
"grad_norm": 0.1785915642976761,
"learning_rate": 1.9447949609114018e-05,
"loss": 1.6321,
"step": 380
},
{
"epoch": 0.6041828040278854,
"grad_norm": 0.16734299063682556,
"learning_rate": 1.938728882357093e-05,
"loss": 1.6443,
"step": 390
},
{
"epoch": 0.6196746707978311,
"grad_norm": 0.18670211732387543,
"learning_rate": 1.932357149440067e-05,
"loss": 1.6683,
"step": 400
},
{
"epoch": 0.635166537567777,
"grad_norm": 0.15596874058246613,
"learning_rate": 1.925681836825331e-05,
"loss": 1.6336,
"step": 410
},
{
"epoch": 0.6506584043377227,
"grad_norm": 0.18547730147838593,
"learning_rate": 1.9187051180248134e-05,
"loss": 1.6374,
"step": 420
},
{
"epoch": 0.6661502711076684,
"grad_norm": 0.15439730882644653,
"learning_rate": 1.9114292646896574e-05,
"loss": 1.6298,
"step": 430
},
{
"epoch": 0.6816421378776143,
"grad_norm": 0.15702180564403534,
"learning_rate": 1.9038566458705615e-05,
"loss": 1.6235,
"step": 440
},
{
"epoch": 0.69713400464756,
"grad_norm": 0.20213943719863892,
"learning_rate": 1.895989727246405e-05,
"loss": 1.6511,
"step": 450
},
{
"epoch": 0.7126258714175058,
"grad_norm": 0.17505770921707153,
"learning_rate": 1.8878310703214148e-05,
"loss": 1.6385,
"step": 460
},
{
"epoch": 0.7281177381874516,
"grad_norm": 0.29876482486724854,
"learning_rate": 1.879383331591123e-05,
"loss": 1.6508,
"step": 470
},
{
"epoch": 0.7436096049573974,
"grad_norm": 0.16168834269046783,
"learning_rate": 1.8706492616774043e-05,
"loss": 1.6424,
"step": 480
},
{
"epoch": 0.7591014717273431,
"grad_norm": 0.1786322444677353,
"learning_rate": 1.86163170443286e-05,
"loss": 1.6699,
"step": 490
},
{
"epoch": 0.774593338497289,
"grad_norm": 0.16993215680122375,
"learning_rate": 1.8523335960148446e-05,
"loss": 1.6499,
"step": 500
},
{
"epoch": 0.7900852052672347,
"grad_norm": 0.15823154151439667,
"learning_rate": 1.8427579639294436e-05,
"loss": 1.6227,
"step": 510
},
{
"epoch": 0.8055770720371804,
"grad_norm": 0.1717902421951294,
"learning_rate": 1.8329079260457e-05,
"loss": 1.6216,
"step": 520
},
{
"epoch": 0.8210689388071263,
"grad_norm": 0.17375893890857697,
"learning_rate": 1.822786689580425e-05,
"loss": 1.6264,
"step": 530
},
{
"epoch": 0.836560805577072,
"grad_norm": 0.18277738988399506,
"learning_rate": 1.8123975500539114e-05,
"loss": 1.6314,
"step": 540
},
{
"epoch": 0.8520526723470179,
"grad_norm": 0.16117972135543823,
"learning_rate": 1.8017438902168987e-05,
"loss": 1.6274,
"step": 550
},
{
"epoch": 0.8675445391169636,
"grad_norm": 0.1836647391319275,
"learning_rate": 1.7908291789491348e-05,
"loss": 1.6163,
"step": 560
},
{
"epoch": 0.8830364058869093,
"grad_norm": 0.1835409700870514,
"learning_rate": 1.7796569701298906e-05,
"loss": 1.624,
"step": 570
},
{
"epoch": 0.8985282726568552,
"grad_norm": 0.20427103340625763,
"learning_rate": 1.7682309014808043e-05,
"loss": 1.6575,
"step": 580
},
{
"epoch": 0.9140201394268009,
"grad_norm": 0.18505772948265076,
"learning_rate": 1.756554693381419e-05,
"loss": 1.6478,
"step": 590
},
{
"epoch": 0.9295120061967467,
"grad_norm": 0.16430599987506866,
"learning_rate": 1.7446321476578138e-05,
"loss": 1.6358,
"step": 600
},
{
"epoch": 0.9450038729666925,
"grad_norm": 0.1757052093744278,
"learning_rate": 1.7324671463447092e-05,
"loss": 1.6383,
"step": 610
},
{
"epoch": 0.9604957397366383,
"grad_norm": 0.1813608705997467,
"learning_rate": 1.7200636504214618e-05,
"loss": 1.6394,
"step": 620
},
{
"epoch": 0.975987606506584,
"grad_norm": 0.16642023622989655,
"learning_rate": 1.7074256985223496e-05,
"loss": 1.6293,
"step": 630
},
{
"epoch": 0.9914794732765299,
"grad_norm": 0.16024267673492432,
"learning_rate": 1.6945574056215742e-05,
"loss": 1.6186,
"step": 640
},
{
"epoch": 1.0061967467079782,
"grad_norm": 0.1785087138414383,
"learning_rate": 1.6814629616934078e-05,
"loss": 1.6575,
"step": 650
},
{
"epoch": 1.0216886134779242,
"grad_norm": 0.15702630579471588,
"learning_rate": 1.6681466303479196e-05,
"loss": 1.6431,
"step": 660
},
{
"epoch": 1.03718048024787,
"grad_norm": 0.18289993703365326,
"learning_rate": 1.6546127474427217e-05,
"loss": 1.6231,
"step": 670
},
{
"epoch": 1.0526723470178156,
"grad_norm": 0.18264566361904144,
"learning_rate": 1.6408657196711977e-05,
"loss": 1.6293,
"step": 680
},
{
"epoch": 1.0681642137877614,
"grad_norm": 0.1770721971988678,
"learning_rate": 1.6269100231276617e-05,
"loss": 1.6123,
"step": 690
},
{
"epoch": 1.0836560805577071,
"grad_norm": 0.18177859485149384,
"learning_rate": 1.6127502018499216e-05,
"loss": 1.6367,
"step": 700
},
{
"epoch": 1.099147947327653,
"grad_norm": 0.17744611203670502,
"learning_rate": 1.598390866339721e-05,
"loss": 1.6037,
"step": 710
},
{
"epoch": 1.1146398140975988,
"grad_norm": 0.17207013070583344,
"learning_rate": 1.5838366920615395e-05,
"loss": 1.6184,
"step": 720
},
{
"epoch": 1.1301316808675446,
"grad_norm": 0.19843930006027222,
"learning_rate": 1.5690924179202375e-05,
"loss": 1.649,
"step": 730
},
{
"epoch": 1.1456235476374903,
"grad_norm": 0.1967499703168869,
"learning_rate": 1.5541628447180494e-05,
"loss": 1.644,
"step": 740
},
{
"epoch": 1.161115414407436,
"grad_norm": 0.2497672736644745,
"learning_rate": 1.5390528335914216e-05,
"loss": 1.6452,
"step": 750
},
{
"epoch": 1.1766072811773818,
"grad_norm": 0.22346507012844086,
"learning_rate": 1.5237673044282028e-05,
"loss": 1.5909,
"step": 760
},
{
"epoch": 1.1920991479473277,
"grad_norm": 0.1980983465909958,
"learning_rate": 1.5083112342657071e-05,
"loss": 1.6415,
"step": 770
},
{
"epoch": 1.2075910147172735,
"grad_norm": 0.22096283733844757,
"learning_rate": 1.4926896556701676e-05,
"loss": 1.6281,
"step": 780
},
{
"epoch": 1.2230828814872192,
"grad_norm": 0.20375041663646698,
"learning_rate": 1.4769076550981107e-05,
"loss": 1.6327,
"step": 790
},
{
"epoch": 1.238574748257165,
"grad_norm": 0.1991424262523651,
"learning_rate": 1.4609703712401832e-05,
"loss": 1.628,
"step": 800
},
{
"epoch": 1.2540666150271107,
"grad_norm": 0.1924315243959427,
"learning_rate": 1.44488299334797e-05,
"loss": 1.6228,
"step": 810
},
{
"epoch": 1.2695584817970564,
"grad_norm": 0.200628861784935,
"learning_rate": 1.4286507595443527e-05,
"loss": 1.6252,
"step": 820
},
{
"epoch": 1.2850503485670024,
"grad_norm": 0.18464049696922302,
"learning_rate": 1.4122789551179495e-05,
"loss": 1.6521,
"step": 830
},
{
"epoch": 1.3005422153369481,
"grad_norm": 0.19593623280525208,
"learning_rate": 1.3957729108022057e-05,
"loss": 1.6357,
"step": 840
},
{
"epoch": 1.3160340821068939,
"grad_norm": 0.1850130409002304,
"learning_rate": 1.37913800103968e-05,
"loss": 1.6214,
"step": 850
},
{
"epoch": 1.3315259488768396,
"grad_norm": 0.19042982161045074,
"learning_rate": 1.3623796422321018e-05,
"loss": 1.6258,
"step": 860
},
{
"epoch": 1.3470178156467854,
"grad_norm": 0.16621778905391693,
"learning_rate": 1.345503290976768e-05,
"loss": 1.5954,
"step": 870
},
{
"epoch": 1.3625096824167313,
"grad_norm": 0.22534021735191345,
"learning_rate": 1.3285144422898486e-05,
"loss": 1.63,
"step": 880
},
{
"epoch": 1.378001549186677,
"grad_norm": 0.20389960706233978,
"learning_rate": 1.3114186278171855e-05,
"loss": 1.6105,
"step": 890
},
{
"epoch": 1.3934934159566228,
"grad_norm": 0.19341149926185608,
"learning_rate": 1.294221414033163e-05,
"loss": 1.6311,
"step": 900
},
{
"epoch": 1.4089852827265685,
"grad_norm": 0.18202827870845795,
"learning_rate": 1.2769284004282398e-05,
"loss": 1.6071,
"step": 910
},
{
"epoch": 1.4244771494965143,
"grad_norm": 0.24331383407115936,
"learning_rate": 1.2595452176857283e-05,
"loss": 1.6308,
"step": 920
},
{
"epoch": 1.4399690162664602,
"grad_norm": 0.19823439419269562,
"learning_rate": 1.2420775258484194e-05,
"loss": 1.6338,
"step": 930
},
{
"epoch": 1.4554608830364058,
"grad_norm": 0.20651289820671082,
"learning_rate": 1.224531012475647e-05,
"loss": 1.6289,
"step": 940
},
{
"epoch": 1.4709527498063517,
"grad_norm": 0.19937390089035034,
"learning_rate": 1.2069113907913921e-05,
"loss": 1.6251,
"step": 950
},
{
"epoch": 1.4864446165762975,
"grad_norm": 0.2028992474079132,
"learning_rate": 1.1892243978240332e-05,
"loss": 1.6032,
"step": 960
},
{
"epoch": 1.5019364833462432,
"grad_norm": 0.19516679644584656,
"learning_rate": 1.1714757925383418e-05,
"loss": 1.658,
"step": 970
},
{
"epoch": 1.5174283501161892,
"grad_norm": 0.19880403578281403,
"learning_rate": 1.1536713539603392e-05,
"loss": 1.6286,
"step": 980
},
{
"epoch": 1.5329202168861347,
"grad_norm": 0.20677272975444794,
"learning_rate": 1.1358168792956178e-05,
"loss": 1.6366,
"step": 990
},
{
"epoch": 1.5484120836560806,
"grad_norm": 0.19314983487129211,
"learning_rate": 1.1179181820417469e-05,
"loss": 1.6277,
"step": 1000
},
{
"epoch": 1.5639039504260264,
"grad_norm": 0.22714097797870636,
"learning_rate": 1.0999810900953701e-05,
"loss": 1.604,
"step": 1010
},
{
"epoch": 1.579395817195972,
"grad_norm": 0.19973160326480865,
"learning_rate": 1.0820114438546152e-05,
"loss": 1.6419,
"step": 1020
},
{
"epoch": 1.5948876839659178,
"grad_norm": 0.19317737221717834,
"learning_rate": 1.0640150943174368e-05,
"loss": 1.6208,
"step": 1030
},
{
"epoch": 1.6103795507358636,
"grad_norm": 0.19110378623008728,
"learning_rate": 1.045997901176503e-05,
"loss": 1.6419,
"step": 1040
},
{
"epoch": 1.6258714175058095,
"grad_norm": 0.19884715974330902,
"learning_rate": 1.0279657309112526e-05,
"loss": 1.6374,
"step": 1050
},
{
"epoch": 1.641363284275755,
"grad_norm": 0.2037876695394516,
"learning_rate": 1.0099244548777444e-05,
"loss": 1.6226,
"step": 1060
},
{
"epoch": 1.656855151045701,
"grad_norm": 0.19929030537605286,
"learning_rate": 9.918799473969162e-06,
"loss": 1.6246,
"step": 1070
},
{
"epoch": 1.6723470178156468,
"grad_norm": 0.2003982663154602,
"learning_rate": 9.738380838418804e-06,
"loss": 1.6284,
"step": 1080
},
{
"epoch": 1.6878388845855925,
"grad_norm": 0.19803060591220856,
"learning_rate": 9.558047387248736e-06,
"loss": 1.6735,
"step": 1090
},
{
"epoch": 1.7033307513555385,
"grad_norm": 0.1816408932209015,
"learning_rate": 9.37785783784492e-06,
"loss": 1.6476,
"step": 1100
},
{
"epoch": 1.718822618125484,
"grad_norm": 0.2075837105512619,
"learning_rate": 9.197870860738245e-06,
"loss": 1.6332,
"step": 1110
},
{
"epoch": 1.73431448489543,
"grad_norm": 0.18789494037628174,
"learning_rate": 9.018145060501152e-06,
"loss": 1.6261,
"step": 1120
},
{
"epoch": 1.7498063516653757,
"grad_norm": 0.2126590460538864,
"learning_rate": 8.838738956665709e-06,
"loss": 1.638,
"step": 1130
},
{
"epoch": 1.7652982184353214,
"grad_norm": 0.19256949424743652,
"learning_rate": 8.65971096466939e-06,
"loss": 1.633,
"step": 1140
},
{
"epoch": 1.7807900852052674,
"grad_norm": 0.22011205554008484,
"learning_rate": 8.481119376834753e-06,
"loss": 1.6397,
"step": 1150
},
{
"epoch": 1.796281951975213,
"grad_norm": 0.2018994390964508,
"learning_rate": 8.303022343389188e-06,
"loss": 1.6424,
"step": 1160
},
{
"epoch": 1.8117738187451589,
"grad_norm": 0.22901326417922974,
"learning_rate": 8.125477853530944e-06,
"loss": 1.594,
"step": 1170
},
{
"epoch": 1.8272656855151046,
"grad_norm": 0.20335343480110168,
"learning_rate": 7.948543716547584e-06,
"loss": 1.6246,
"step": 1180
},
{
"epoch": 1.8427575522850503,
"grad_norm": 0.19213028252124786,
"learning_rate": 7.772277542993006e-06,
"loss": 1.6424,
"step": 1190
},
{
"epoch": 1.858249419054996,
"grad_norm": 0.5027441382408142,
"learning_rate": 7.596736725929218e-06,
"loss": 1.618,
"step": 1200
},
{
"epoch": 1.8737412858249418,
"grad_norm": 0.19005711376667023,
"learning_rate": 7.421978422238871e-06,
"loss": 1.6082,
"step": 1210
},
{
"epoch": 1.8892331525948878,
"grad_norm": 0.21805432438850403,
"learning_rate": 7.248059534014728e-06,
"loss": 1.6259,
"step": 1220
},
{
"epoch": 1.9047250193648335,
"grad_norm": 0.21786893904209137,
"learning_rate": 7.075036690032088e-06,
"loss": 1.6041,
"step": 1230
},
{
"epoch": 1.9202168861347793,
"grad_norm": 0.20781753957271576,
"learning_rate": 6.9029662273102015e-06,
"loss": 1.6276,
"step": 1240
},
{
"epoch": 1.935708752904725,
"grad_norm": 0.20254895091056824,
"learning_rate": 6.731904172768668e-06,
"loss": 1.6146,
"step": 1250
},
{
"epoch": 1.9512006196746707,
"grad_norm": 0.17970645427703857,
"learning_rate": 6.561906224984844e-06,
"loss": 1.6505,
"step": 1260
},
{
"epoch": 1.9666924864446167,
"grad_norm": 0.19660718739032745,
"learning_rate": 6.393027736058117e-06,
"loss": 1.6383,
"step": 1270
},
{
"epoch": 1.9821843532145622,
"grad_norm": 0.21242186427116394,
"learning_rate": 6.225323693587014e-06,
"loss": 1.6003,
"step": 1280
},
{
"epoch": 1.9976762199845082,
"grad_norm": 0.20118798315525055,
"learning_rate": 6.0588487027649954e-06,
"loss": 1.671,
"step": 1290
},
{
"epoch": 2.0123934934159564,
"grad_norm": 0.19734402000904083,
"learning_rate": 5.89365696860075e-06,
"loss": 1.6098,
"step": 1300
},
{
"epoch": 2.0278853601859024,
"grad_norm": 0.2078474462032318,
"learning_rate": 5.729802278268813e-06,
"loss": 1.6456,
"step": 1310
},
{
"epoch": 2.0433772269558483,
"grad_norm": 0.1926499605178833,
"learning_rate": 5.567337983596201e-06,
"loss": 1.5858,
"step": 1320
},
{
"epoch": 2.058869093725794,
"grad_norm": 0.1910993903875351,
"learning_rate": 5.4063169836908355e-06,
"loss": 1.6251,
"step": 1330
},
{
"epoch": 2.07436096049574,
"grad_norm": 0.1886081099510193,
"learning_rate": 5.246791707717343e-06,
"loss": 1.6366,
"step": 1340
},
{
"epoch": 2.0898528272656853,
"grad_norm": 0.20095673203468323,
"learning_rate": 5.088814097825871e-06,
"loss": 1.6346,
"step": 1350
},
{
"epoch": 2.1053446940356313,
"grad_norm": 0.22384069859981537,
"learning_rate": 4.93243559223952e-06,
"loss": 1.6186,
"step": 1360
},
{
"epoch": 2.1208365608055773,
"grad_norm": 0.19841165840625763,
"learning_rate": 4.777707108505801e-06,
"loss": 1.6127,
"step": 1370
},
{
"epoch": 2.1363284275755228,
"grad_norm": 0.2496616691350937,
"learning_rate": 4.624679026917658e-06,
"loss": 1.6116,
"step": 1380
},
{
"epoch": 2.1518202943454687,
"grad_norm": 0.1951538771390915,
"learning_rate": 4.473401174109423e-06,
"loss": 1.6312,
"step": 1390
},
{
"epoch": 2.1673121611154142,
"grad_norm": 0.21068304777145386,
"learning_rate": 4.323922806833031e-06,
"loss": 1.6177,
"step": 1400
},
{
"epoch": 2.18280402788536,
"grad_norm": 0.20252861082553864,
"learning_rate": 4.176292595919803e-06,
"loss": 1.6402,
"step": 1410
},
{
"epoch": 2.198295894655306,
"grad_norm": 0.18212322890758514,
"learning_rate": 4.030558610433005e-06,
"loss": 1.6559,
"step": 1420
},
{
"epoch": 2.2137877614252517,
"grad_norm": 0.4208082854747772,
"learning_rate": 3.8867683020163446e-06,
"loss": 1.6085,
"step": 1430
},
{
"epoch": 2.2292796281951976,
"grad_norm": 0.21806304156780243,
"learning_rate": 3.744968489443488e-06,
"loss": 1.6341,
"step": 1440
},
{
"epoch": 2.244771494965143,
"grad_norm": 0.2629954516887665,
"learning_rate": 3.6052053433736777e-06,
"loss": 1.6332,
"step": 1450
},
{
"epoch": 2.260263361735089,
"grad_norm": 0.21003496646881104,
"learning_rate": 3.4675243713183436e-06,
"loss": 1.641,
"step": 1460
},
{
"epoch": 2.2757552285050346,
"grad_norm": 0.20624355971813202,
"learning_rate": 3.3319704028236553e-06,
"loss": 1.6215,
"step": 1470
},
{
"epoch": 2.2912470952749806,
"grad_norm": 0.20449386537075043,
"learning_rate": 3.1985875748738193e-06,
"loss": 1.6289,
"step": 1480
},
{
"epoch": 2.3067389620449266,
"grad_norm": 0.2125074714422226,
"learning_rate": 3.067419317519875e-06,
"loss": 1.6083,
"step": 1490
},
{
"epoch": 2.322230828814872,
"grad_norm": 0.22426113486289978,
"learning_rate": 2.938508339738683e-06,
"loss": 1.6209,
"step": 1500
},
{
"epoch": 2.337722695584818,
"grad_norm": 0.20228077471256256,
"learning_rate": 2.81189661552667e-06,
"loss": 1.6317,
"step": 1510
},
{
"epoch": 2.3532145623547636,
"grad_norm": 0.21674266457557678,
"learning_rate": 2.68762537023293e-06,
"loss": 1.6008,
"step": 1520
},
{
"epoch": 2.3687064291247095,
"grad_norm": 0.20280566811561584,
"learning_rate": 2.5657350671360514e-06,
"loss": 1.6458,
"step": 1530
},
{
"epoch": 2.3841982958946555,
"grad_norm": 0.19379937648773193,
"learning_rate": 2.4462653942690895e-06,
"loss": 1.6324,
"step": 1540
},
{
"epoch": 2.399690162664601,
"grad_norm": 0.19534389674663544,
"learning_rate": 2.3292552514969723e-06,
"loss": 1.6027,
"step": 1550
},
{
"epoch": 2.415182029434547,
"grad_norm": 0.19875919818878174,
"learning_rate": 2.214742737850514e-06,
"loss": 1.6078,
"step": 1560
},
{
"epoch": 2.4306738962044925,
"grad_norm": 0.2097163200378418,
"learning_rate": 2.1027651391212158e-06,
"loss": 1.6286,
"step": 1570
},
{
"epoch": 2.4461657629744384,
"grad_norm": 0.2157508283853531,
"learning_rate": 1.9933589157208356e-06,
"loss": 1.6266,
"step": 1580
},
{
"epoch": 2.4616576297443844,
"grad_norm": 0.2269178032875061,
"learning_rate": 1.8865596908097105e-06,
"loss": 1.6323,
"step": 1590
},
{
"epoch": 2.47714949651433,
"grad_norm": 0.19033896923065186,
"learning_rate": 1.7824022386977014e-06,
"loss": 1.6399,
"step": 1600
},
{
"epoch": 2.492641363284276,
"grad_norm": 0.19749732315540314,
"learning_rate": 1.6809204735215179e-06,
"loss": 1.6319,
"step": 1610
},
{
"epoch": 2.5081332300542214,
"grad_norm": 0.20683521032333374,
"learning_rate": 1.5821474382021128e-06,
"loss": 1.6358,
"step": 1620
},
{
"epoch": 2.5236250968241674,
"grad_norm": 0.20513305068016052,
"learning_rate": 1.4861152936857792e-06,
"loss": 1.6265,
"step": 1630
},
{
"epoch": 2.539116963594113,
"grad_norm": 0.209518700838089,
"learning_rate": 1.3928553084723828e-06,
"loss": 1.6172,
"step": 1640
},
{
"epoch": 2.554608830364059,
"grad_norm": 0.1861906498670578,
"learning_rate": 1.3023978484342027e-06,
"loss": 1.6316,
"step": 1650
},
{
"epoch": 2.570100697134005,
"grad_norm": 0.2016245722770691,
"learning_rate": 1.2147723669286703e-06,
"loss": 1.5947,
"step": 1660
},
{
"epoch": 2.5855925639039503,
"grad_norm": 0.213214710354805,
"learning_rate": 1.1300073952082147e-06,
"loss": 1.5899,
"step": 1670
},
{
"epoch": 2.6010844306738963,
"grad_norm": 0.20174169540405273,
"learning_rate": 1.0481305331303659e-06,
"loss": 1.6347,
"step": 1680
},
{
"epoch": 2.6165762974438422,
"grad_norm": 0.21556764841079712,
"learning_rate": 9.691684401711143e-07,
"loss": 1.641,
"step": 1690
},
{
"epoch": 2.6320681642137878,
"grad_norm": 0.21022352576255798,
"learning_rate": 8.93146826744462e-07,
"loss": 1.609,
"step": 1700
},
{
"epoch": 2.6475600309837333,
"grad_norm": 0.22143913805484772,
"learning_rate": 8.200904458310022e-07,
"loss": 1.6119,
"step": 1710
},
{
"epoch": 2.6630518977536792,
"grad_norm": 0.20341992378234863,
"learning_rate": 7.500230849182278e-07,
"loss": 1.5872,
"step": 1720
},
{
"epoch": 2.678543764523625,
"grad_norm": 0.20610594749450684,
"learning_rate": 6.829675582552253e-07,
"loss": 1.6578,
"step": 1730
},
{
"epoch": 2.6940356312935707,
"grad_norm": 0.2443259358406067,
"learning_rate": 6.189456994242516e-07,
"loss": 1.6138,
"step": 1740
},
{
"epoch": 2.7095274980635167,
"grad_norm": 0.1948014199733734,
"learning_rate": 5.579783542316175e-07,
"loss": 1.6071,
"step": 1750
},
{
"epoch": 2.7250193648334626,
"grad_norm": 0.21449612081050873,
"learning_rate": 5.000853739202039e-07,
"loss": 1.628,
"step": 1760
},
{
"epoch": 2.740511231603408,
"grad_norm": 0.21719783544540405,
"learning_rate": 4.452856087058044e-07,
"loss": 1.6278,
"step": 1770
},
{
"epoch": 2.756003098373354,
"grad_norm": 0.20155809819698334,
"learning_rate": 3.935969016394048e-07,
"loss": 1.6397,
"step": 1780
},
{
"epoch": 2.7714949651432996,
"grad_norm": 0.23018154501914978,
"learning_rate": 3.450360827974175e-07,
"loss": 1.6381,
"step": 1790
},
{
"epoch": 2.7869868319132456,
"grad_norm": 0.21632038056850433,
"learning_rate": 2.996189638017233e-07,
"loss": 1.6044,
"step": 1800
},
{
"epoch": 2.802478698683191,
"grad_norm": 0.22561421990394592,
"learning_rate": 2.57360332671337e-07,
"loss": 1.6358,
"step": 1810
},
{
"epoch": 2.817970565453137,
"grad_norm": 0.21071907877922058,
"learning_rate": 2.1827394900736377e-07,
"loss": 1.6223,
"step": 1820
},
{
"epoch": 2.833462432223083,
"grad_norm": 0.2211053967475891,
"learning_rate": 1.8237253951281287e-07,
"loss": 1.6293,
"step": 1830
},
{
"epoch": 2.8489542989930285,
"grad_norm": 0.21328748762607574,
"learning_rate": 1.4966779384871789e-07,
"loss": 1.602,
"step": 1840
},
{
"epoch": 2.8644461657629745,
"grad_norm": 0.23242874443531036,
"learning_rate": 1.2017036082793922e-07,
"loss": 1.6249,
"step": 1850
},
{
"epoch": 2.8799380325329205,
"grad_norm": 0.20212414860725403,
"learning_rate": 9.388984494785869e-08,
"loss": 1.6401,
"step": 1860
},
{
"epoch": 2.895429899302866,
"grad_norm": 0.21839973330497742,
"learning_rate": 7.08348032631101e-08,
"loss": 1.6185,
"step": 1870
},
{
"epoch": 2.9109217660728115,
"grad_norm": 0.2018660604953766,
"learning_rate": 5.101274259936451e-08,
"loss": 1.6284,
"step": 1880
},
{
"epoch": 2.9264136328427575,
"grad_norm": 0.2246350198984146,
"learning_rate": 3.443011710907662e-08,
"loss": 1.6129,
"step": 1890
},
{
"epoch": 2.9419054996127034,
"grad_norm": 0.2279912680387497,
"learning_rate": 2.109232616998247e-08,
"loss": 1.6084,
"step": 1900
},
{
"epoch": 2.957397366382649,
"grad_norm": 0.22195599973201752,
"learning_rate": 1.100371262703459e-08,
"loss": 1.6222,
"step": 1910
},
{
"epoch": 2.972889233152595,
"grad_norm": 0.20175737142562866,
"learning_rate": 4.1675613783565e-09,
"loss": 1.6109,
"step": 1920
},
{
"epoch": 2.988381099922541,
"grad_norm": 0.23770569264888763,
"learning_rate": 5.860983056604763e-10,
"loss": 1.629,
"step": 1930
}
],
"logging_steps": 10,
"max_steps": 1935,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.3807044630404874e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}