qwen2-0.5b-sft / trainer_state.json
yangzhao02's picture
Model save
61c5698 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9998676022772408,
"eval_steps": 500,
"global_step": 1888,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005295908910366742,
"grad_norm": 11.06487524439423,
"learning_rate": 1.0582010582010582e-07,
"loss": 1.8074,
"step": 1
},
{
"epoch": 0.0026479544551833707,
"grad_norm": 10.35297291588404,
"learning_rate": 5.291005291005291e-07,
"loss": 1.7698,
"step": 5
},
{
"epoch": 0.005295908910366741,
"grad_norm": 4.410422081469438,
"learning_rate": 1.0582010582010582e-06,
"loss": 1.7238,
"step": 10
},
{
"epoch": 0.007943863365550112,
"grad_norm": 2.369320008302558,
"learning_rate": 1.5873015873015873e-06,
"loss": 1.686,
"step": 15
},
{
"epoch": 0.010591817820733483,
"grad_norm": 1.8383527182275317,
"learning_rate": 2.1164021164021164e-06,
"loss": 1.6501,
"step": 20
},
{
"epoch": 0.013239772275916854,
"grad_norm": 1.2958509244773313,
"learning_rate": 2.6455026455026455e-06,
"loss": 1.6124,
"step": 25
},
{
"epoch": 0.015887726731100223,
"grad_norm": 1.174964641661081,
"learning_rate": 3.1746031746031746e-06,
"loss": 1.6416,
"step": 30
},
{
"epoch": 0.018535681186283594,
"grad_norm": 1.1099336321706879,
"learning_rate": 3.7037037037037037e-06,
"loss": 1.6185,
"step": 35
},
{
"epoch": 0.021183635641466966,
"grad_norm": 1.0938179405927853,
"learning_rate": 4.232804232804233e-06,
"loss": 1.6105,
"step": 40
},
{
"epoch": 0.023831590096650337,
"grad_norm": 1.1671668437307012,
"learning_rate": 4.761904761904762e-06,
"loss": 1.6252,
"step": 45
},
{
"epoch": 0.026479544551833708,
"grad_norm": 1.1541560199576304,
"learning_rate": 5.291005291005291e-06,
"loss": 1.5897,
"step": 50
},
{
"epoch": 0.02912749900701708,
"grad_norm": 1.143774194892201,
"learning_rate": 5.820105820105821e-06,
"loss": 1.6112,
"step": 55
},
{
"epoch": 0.03177545346220045,
"grad_norm": 1.1206001249958375,
"learning_rate": 6.349206349206349e-06,
"loss": 1.5747,
"step": 60
},
{
"epoch": 0.03442340791738382,
"grad_norm": 1.0737292608277489,
"learning_rate": 6.878306878306879e-06,
"loss": 1.596,
"step": 65
},
{
"epoch": 0.03707136237256719,
"grad_norm": 1.1075534221517305,
"learning_rate": 7.4074074074074075e-06,
"loss": 1.5953,
"step": 70
},
{
"epoch": 0.03971931682775056,
"grad_norm": 1.1099499955003087,
"learning_rate": 7.936507936507936e-06,
"loss": 1.6047,
"step": 75
},
{
"epoch": 0.04236727128293393,
"grad_norm": 1.123069012889379,
"learning_rate": 8.465608465608466e-06,
"loss": 1.5838,
"step": 80
},
{
"epoch": 0.0450152257381173,
"grad_norm": 1.090428544643004,
"learning_rate": 8.994708994708995e-06,
"loss": 1.5758,
"step": 85
},
{
"epoch": 0.047663180193300674,
"grad_norm": 1.0534191502769323,
"learning_rate": 9.523809523809525e-06,
"loss": 1.6057,
"step": 90
},
{
"epoch": 0.050311134648484045,
"grad_norm": 1.137231525194321,
"learning_rate": 1.0052910052910054e-05,
"loss": 1.5962,
"step": 95
},
{
"epoch": 0.052959089103667416,
"grad_norm": 1.0968326074569497,
"learning_rate": 1.0582010582010582e-05,
"loss": 1.5966,
"step": 100
},
{
"epoch": 0.05560704355885079,
"grad_norm": 1.1309290184481768,
"learning_rate": 1.1111111111111113e-05,
"loss": 1.5828,
"step": 105
},
{
"epoch": 0.05825499801403416,
"grad_norm": 1.10504410469273,
"learning_rate": 1.1640211640211641e-05,
"loss": 1.5675,
"step": 110
},
{
"epoch": 0.06090295246921753,
"grad_norm": 1.0798493680750558,
"learning_rate": 1.216931216931217e-05,
"loss": 1.6153,
"step": 115
},
{
"epoch": 0.0635509069244009,
"grad_norm": 1.1570911354201185,
"learning_rate": 1.2698412698412699e-05,
"loss": 1.6054,
"step": 120
},
{
"epoch": 0.06619886137958426,
"grad_norm": 1.0753506577133993,
"learning_rate": 1.322751322751323e-05,
"loss": 1.5781,
"step": 125
},
{
"epoch": 0.06884681583476764,
"grad_norm": 1.0993021833530066,
"learning_rate": 1.3756613756613758e-05,
"loss": 1.5899,
"step": 130
},
{
"epoch": 0.071494770289951,
"grad_norm": 1.1542372309330358,
"learning_rate": 1.4285714285714287e-05,
"loss": 1.5751,
"step": 135
},
{
"epoch": 0.07414272474513438,
"grad_norm": 1.1332353266729192,
"learning_rate": 1.4814814814814815e-05,
"loss": 1.5921,
"step": 140
},
{
"epoch": 0.07679067920031775,
"grad_norm": 1.1191457024952258,
"learning_rate": 1.5343915343915344e-05,
"loss": 1.5918,
"step": 145
},
{
"epoch": 0.07943863365550112,
"grad_norm": 1.2189932458288275,
"learning_rate": 1.5873015873015872e-05,
"loss": 1.5967,
"step": 150
},
{
"epoch": 0.08208658811068449,
"grad_norm": 1.1599874502262428,
"learning_rate": 1.6402116402116404e-05,
"loss": 1.5997,
"step": 155
},
{
"epoch": 0.08473454256586786,
"grad_norm": 1.1115171747004207,
"learning_rate": 1.693121693121693e-05,
"loss": 1.5613,
"step": 160
},
{
"epoch": 0.08738249702105123,
"grad_norm": 1.0864466240123662,
"learning_rate": 1.7460317460317463e-05,
"loss": 1.5883,
"step": 165
},
{
"epoch": 0.0900304514762346,
"grad_norm": 1.1860151614783536,
"learning_rate": 1.798941798941799e-05,
"loss": 1.5764,
"step": 170
},
{
"epoch": 0.09267840593141798,
"grad_norm": 1.1010264235042715,
"learning_rate": 1.851851851851852e-05,
"loss": 1.5785,
"step": 175
},
{
"epoch": 0.09532636038660135,
"grad_norm": 1.1498652209509064,
"learning_rate": 1.904761904761905e-05,
"loss": 1.5779,
"step": 180
},
{
"epoch": 0.09797431484178472,
"grad_norm": 1.121779220254807,
"learning_rate": 1.9576719576719577e-05,
"loss": 1.5774,
"step": 185
},
{
"epoch": 0.10062226929696809,
"grad_norm": 1.0944181878692356,
"learning_rate": 1.999998290445824e-05,
"loss": 1.5871,
"step": 190
},
{
"epoch": 0.10327022375215146,
"grad_norm": 1.0838843974621926,
"learning_rate": 1.9999384566633966e-05,
"loss": 1.5812,
"step": 195
},
{
"epoch": 0.10591817820733483,
"grad_norm": 1.1397215331428574,
"learning_rate": 1.999793151017222e-05,
"loss": 1.6098,
"step": 200
},
{
"epoch": 0.1085661326625182,
"grad_norm": 1.2295255721168679,
"learning_rate": 1.9995623859276082e-05,
"loss": 1.5554,
"step": 205
},
{
"epoch": 0.11121408711770157,
"grad_norm": 1.1311330807062197,
"learning_rate": 1.999246181119692e-05,
"loss": 1.5841,
"step": 210
},
{
"epoch": 0.11386204157288494,
"grad_norm": 1.189685647731816,
"learning_rate": 1.9988445636217512e-05,
"loss": 1.5959,
"step": 215
},
{
"epoch": 0.11650999602806832,
"grad_norm": 1.0965577845127703,
"learning_rate": 1.9983575677628944e-05,
"loss": 1.5535,
"step": 220
},
{
"epoch": 0.11915795048325169,
"grad_norm": 1.1449588639602188,
"learning_rate": 1.9977852351701272e-05,
"loss": 1.5942,
"step": 225
},
{
"epoch": 0.12180590493843506,
"grad_norm": 1.0900575902349108,
"learning_rate": 1.9971276147647937e-05,
"loss": 1.5776,
"step": 230
},
{
"epoch": 0.12445385939361843,
"grad_norm": 1.1000072950998065,
"learning_rate": 1.9965401487447783e-05,
"loss": 1.5687,
"step": 235
},
{
"epoch": 0.1271018138488018,
"grad_norm": 1.1195092642070894,
"learning_rate": 1.9957291568257425e-05,
"loss": 1.5822,
"step": 240
},
{
"epoch": 0.12974976830398516,
"grad_norm": 1.1252728597253978,
"learning_rate": 1.9948330528418044e-05,
"loss": 1.5561,
"step": 245
},
{
"epoch": 0.13239772275916853,
"grad_norm": 1.1266747688901304,
"learning_rate": 1.9938519133893562e-05,
"loss": 1.562,
"step": 250
},
{
"epoch": 0.1350456772143519,
"grad_norm": 1.1086910563981198,
"learning_rate": 1.992785822333376e-05,
"loss": 1.5904,
"step": 255
},
{
"epoch": 0.13769363166953527,
"grad_norm": 1.0777260472777783,
"learning_rate": 1.9916348708002622e-05,
"loss": 1.5831,
"step": 260
},
{
"epoch": 0.14034158612471864,
"grad_norm": 1.1550395863394685,
"learning_rate": 1.9903991571700422e-05,
"loss": 1.5581,
"step": 265
},
{
"epoch": 0.142989540579902,
"grad_norm": 1.0664620318538827,
"learning_rate": 1.9890787870679628e-05,
"loss": 1.5744,
"step": 270
},
{
"epoch": 0.14563749503508538,
"grad_norm": 1.14251257482884,
"learning_rate": 1.987673873355464e-05,
"loss": 1.5714,
"step": 275
},
{
"epoch": 0.14828544949026876,
"grad_norm": 1.197497783667311,
"learning_rate": 1.986184536120529e-05,
"loss": 1.5816,
"step": 280
},
{
"epoch": 0.15093340394545213,
"grad_norm": 1.0819442869899158,
"learning_rate": 1.984610902667423e-05,
"loss": 1.5708,
"step": 285
},
{
"epoch": 0.1535813584006355,
"grad_norm": 1.1346045409466028,
"learning_rate": 1.982953107505807e-05,
"loss": 1.5658,
"step": 290
},
{
"epoch": 0.15622931285581887,
"grad_norm": 1.2009442681600062,
"learning_rate": 1.981211292339245e-05,
"loss": 1.5715,
"step": 295
},
{
"epoch": 0.15887726731100224,
"grad_norm": 1.0818769850873184,
"learning_rate": 1.9793856060530882e-05,
"loss": 1.5685,
"step": 300
},
{
"epoch": 0.1615252217661856,
"grad_norm": 1.098824738778624,
"learning_rate": 1.9774762047017503e-05,
"loss": 1.5531,
"step": 305
},
{
"epoch": 0.16417317622136898,
"grad_norm": 1.1351699166294587,
"learning_rate": 1.9754832514953674e-05,
"loss": 1.6106,
"step": 310
},
{
"epoch": 0.16682113067655235,
"grad_norm": 1.1817572262803626,
"learning_rate": 1.973406916785849e-05,
"loss": 1.5738,
"step": 315
},
{
"epoch": 0.16946908513173572,
"grad_norm": 1.122480345238289,
"learning_rate": 1.971247378052315e-05,
"loss": 1.5614,
"step": 320
},
{
"epoch": 0.1721170395869191,
"grad_norm": 1.1372734218681475,
"learning_rate": 1.969004819885926e-05,
"loss": 1.5674,
"step": 325
},
{
"epoch": 0.17476499404210247,
"grad_norm": 1.107310816365505,
"learning_rate": 1.9666794339741052e-05,
"loss": 1.551,
"step": 330
},
{
"epoch": 0.17741294849728584,
"grad_norm": 1.1272731404259275,
"learning_rate": 1.9642714190841537e-05,
"loss": 1.5304,
"step": 335
},
{
"epoch": 0.1800609029524692,
"grad_norm": 1.0831491448717634,
"learning_rate": 1.9617809810462586e-05,
"loss": 1.5858,
"step": 340
},
{
"epoch": 0.18270885740765258,
"grad_norm": 1.114095409388134,
"learning_rate": 1.9592083327359025e-05,
"loss": 1.5858,
"step": 345
},
{
"epoch": 0.18535681186283595,
"grad_norm": 1.1045780203627584,
"learning_rate": 1.9565536940556643e-05,
"loss": 1.602,
"step": 350
},
{
"epoch": 0.18800476631801932,
"grad_norm": 1.064137031483729,
"learning_rate": 1.9538172919164246e-05,
"loss": 1.567,
"step": 355
},
{
"epoch": 0.1906527207732027,
"grad_norm": 1.1404216929199258,
"learning_rate": 1.950999360217969e-05,
"loss": 1.5767,
"step": 360
},
{
"epoch": 0.19330067522838607,
"grad_norm": 1.0729534295841254,
"learning_rate": 1.9481001398289957e-05,
"loss": 1.5748,
"step": 365
},
{
"epoch": 0.19594862968356944,
"grad_norm": 1.0356756901012456,
"learning_rate": 1.9451198785665263e-05,
"loss": 1.5623,
"step": 370
},
{
"epoch": 0.1985965841387528,
"grad_norm": 1.0650197367365721,
"learning_rate": 1.942058831174723e-05,
"loss": 1.5758,
"step": 375
},
{
"epoch": 0.20124453859393618,
"grad_norm": 1.0856587790066892,
"learning_rate": 1.9389172593031142e-05,
"loss": 1.5499,
"step": 380
},
{
"epoch": 0.20389249304911955,
"grad_norm": 1.1164198411812878,
"learning_rate": 1.9356954314842294e-05,
"loss": 1.5774,
"step": 385
},
{
"epoch": 0.20654044750430292,
"grad_norm": 1.1319738961510737,
"learning_rate": 1.9323936231106456e-05,
"loss": 1.5735,
"step": 390
},
{
"epoch": 0.2091884019594863,
"grad_norm": 1.1255967891893999,
"learning_rate": 1.929012116411447e-05,
"loss": 1.5632,
"step": 395
},
{
"epoch": 0.21183635641466966,
"grad_norm": 1.108494426707579,
"learning_rate": 1.9255512004281028e-05,
"loss": 1.5783,
"step": 400
},
{
"epoch": 0.21448431086985303,
"grad_norm": 1.0770535769415948,
"learning_rate": 1.9220111709897584e-05,
"loss": 1.5678,
"step": 405
},
{
"epoch": 0.2171322653250364,
"grad_norm": 1.0415829053423116,
"learning_rate": 1.9183923306879495e-05,
"loss": 1.5816,
"step": 410
},
{
"epoch": 0.21978021978021978,
"grad_norm": 1.087188068573505,
"learning_rate": 1.9146949888507392e-05,
"loss": 1.5638,
"step": 415
},
{
"epoch": 0.22242817423540315,
"grad_norm": 1.1116864961195356,
"learning_rate": 1.910919461516275e-05,
"loss": 1.5658,
"step": 420
},
{
"epoch": 0.22507612869058652,
"grad_norm": 1.1417370823215336,
"learning_rate": 1.9070660714057764e-05,
"loss": 1.5425,
"step": 425
},
{
"epoch": 0.2277240831457699,
"grad_norm": 1.117200915498827,
"learning_rate": 1.903135147895948e-05,
"loss": 1.5714,
"step": 430
},
{
"epoch": 0.23037203760095326,
"grad_norm": 1.246338337601015,
"learning_rate": 1.899127026990828e-05,
"loss": 1.5646,
"step": 435
},
{
"epoch": 0.23301999205613663,
"grad_norm": 1.1173376295296633,
"learning_rate": 1.8950420512930653e-05,
"loss": 1.5556,
"step": 440
},
{
"epoch": 0.23566794651132,
"grad_norm": 1.1002049060932855,
"learning_rate": 1.8908805699746347e-05,
"loss": 1.5534,
"step": 445
},
{
"epoch": 0.23831590096650337,
"grad_norm": 1.1410000128349649,
"learning_rate": 1.8866429387469925e-05,
"loss": 1.5602,
"step": 450
},
{
"epoch": 0.24096385542168675,
"grad_norm": 1.2018225004111127,
"learning_rate": 1.883198249024526e-05,
"loss": 1.5863,
"step": 455
},
{
"epoch": 0.24361180987687012,
"grad_norm": 1.0679808550327838,
"learning_rate": 1.8788244651103884e-05,
"loss": 1.5676,
"step": 460
},
{
"epoch": 0.2462597643320535,
"grad_norm": 1.1076122026749544,
"learning_rate": 1.8743755618082132e-05,
"loss": 1.5561,
"step": 465
},
{
"epoch": 0.24890771878723686,
"grad_norm": 1.0702127304936218,
"learning_rate": 1.8698519193974607e-05,
"loss": 1.5647,
"step": 470
},
{
"epoch": 0.25155567324242023,
"grad_norm": 1.1039374045842976,
"learning_rate": 1.8652539245460758e-05,
"loss": 1.5669,
"step": 475
},
{
"epoch": 0.2542036276976036,
"grad_norm": 1.066323478050412,
"learning_rate": 1.8605819702774355e-05,
"loss": 1.5789,
"step": 480
},
{
"epoch": 0.256851582152787,
"grad_norm": 1.0544943779687024,
"learning_rate": 1.8558364559367565e-05,
"loss": 1.5836,
"step": 485
},
{
"epoch": 0.2594995366079703,
"grad_norm": 1.1202578955380416,
"learning_rate": 1.851017787156957e-05,
"loss": 1.5519,
"step": 490
},
{
"epoch": 0.2621474910631537,
"grad_norm": 1.10948092278241,
"learning_rate": 1.846126375823987e-05,
"loss": 1.5645,
"step": 495
},
{
"epoch": 0.26479544551833706,
"grad_norm": 1.0939909602427282,
"learning_rate": 1.841162640041622e-05,
"loss": 1.5553,
"step": 500
},
{
"epoch": 0.26744339997352046,
"grad_norm": 1.0748182421005708,
"learning_rate": 1.836127004095722e-05,
"loss": 1.552,
"step": 505
},
{
"epoch": 0.2700913544287038,
"grad_norm": 1.0428546609239973,
"learning_rate": 1.8310198984179664e-05,
"loss": 1.5798,
"step": 510
},
{
"epoch": 0.2727393088838872,
"grad_norm": 1.116361248332442,
"learning_rate": 1.825841759549062e-05,
"loss": 1.5906,
"step": 515
},
{
"epoch": 0.27538726333907054,
"grad_norm": 1.1910997615260301,
"learning_rate": 1.820593030101429e-05,
"loss": 1.5497,
"step": 520
},
{
"epoch": 0.27803521779425394,
"grad_norm": 1.1198458554793917,
"learning_rate": 1.8152741587213663e-05,
"loss": 1.5698,
"step": 525
},
{
"epoch": 0.2806831722494373,
"grad_norm": 1.0441545797715532,
"learning_rate": 1.8098856000507044e-05,
"loss": 1.5629,
"step": 530
},
{
"epoch": 0.2833311267046207,
"grad_norm": 1.078958367326335,
"learning_rate": 1.804427814687942e-05,
"loss": 1.563,
"step": 535
},
{
"epoch": 0.285979081159804,
"grad_norm": 1.049511571157811,
"learning_rate": 1.7989012691488773e-05,
"loss": 1.5546,
"step": 540
},
{
"epoch": 0.2886270356149874,
"grad_norm": 1.0830947470396424,
"learning_rate": 1.7933064358267304e-05,
"loss": 1.5591,
"step": 545
},
{
"epoch": 0.29127499007017077,
"grad_norm": 1.1188147326045856,
"learning_rate": 1.787643792951764e-05,
"loss": 1.5987,
"step": 550
},
{
"epoch": 0.29392294452535417,
"grad_norm": 1.1323146467371565,
"learning_rate": 1.781913824550408e-05,
"loss": 1.5372,
"step": 555
},
{
"epoch": 0.2965708989805375,
"grad_norm": 1.126908360081288,
"learning_rate": 1.7761170204038826e-05,
"loss": 1.5776,
"step": 560
},
{
"epoch": 0.2992188534357209,
"grad_norm": 1.080368974521426,
"learning_rate": 1.7702538760063364e-05,
"loss": 1.5402,
"step": 565
},
{
"epoch": 0.30186680789090425,
"grad_norm": 1.0596514703800766,
"learning_rate": 1.7643248925224926e-05,
"loss": 1.554,
"step": 570
},
{
"epoch": 0.30451476234608765,
"grad_norm": 1.0465918096539288,
"learning_rate": 1.7583305767448088e-05,
"loss": 1.5687,
"step": 575
},
{
"epoch": 0.307162716801271,
"grad_norm": 1.0376883938486323,
"learning_rate": 1.75227144105016e-05,
"loss": 1.5305,
"step": 580
},
{
"epoch": 0.3098106712564544,
"grad_norm": 1.074362321961027,
"learning_rate": 1.7461480033560415e-05,
"loss": 1.563,
"step": 585
},
{
"epoch": 0.31245862571163774,
"grad_norm": 1.07766817131444,
"learning_rate": 1.7399607870762973e-05,
"loss": 1.5599,
"step": 590
},
{
"epoch": 0.31510658016682114,
"grad_norm": 1.192806036017365,
"learning_rate": 1.733710321076383e-05,
"loss": 1.5761,
"step": 595
},
{
"epoch": 0.3177545346220045,
"grad_norm": 1.0556632469495062,
"learning_rate": 1.727397139628157e-05,
"loss": 1.5472,
"step": 600
},
{
"epoch": 0.3204024890771879,
"grad_norm": 1.1350269437645966,
"learning_rate": 1.721021782364216e-05,
"loss": 1.5819,
"step": 605
},
{
"epoch": 0.3230504435323712,
"grad_norm": 1.0604476544784243,
"learning_rate": 1.714584794231764e-05,
"loss": 1.5391,
"step": 610
},
{
"epoch": 0.3256983979875546,
"grad_norm": 1.118350982024723,
"learning_rate": 1.7080867254460363e-05,
"loss": 1.5588,
"step": 615
},
{
"epoch": 0.32834635244273797,
"grad_norm": 1.0677975558889676,
"learning_rate": 1.7015281314432665e-05,
"loss": 1.5933,
"step": 620
},
{
"epoch": 0.33099430689792136,
"grad_norm": 1.089736574490509,
"learning_rate": 1.6949095728332084e-05,
"loss": 1.5816,
"step": 625
},
{
"epoch": 0.3336422613531047,
"grad_norm": 1.0447343101414006,
"learning_rate": 1.68823161535122e-05,
"loss": 1.5483,
"step": 630
},
{
"epoch": 0.3362902158082881,
"grad_norm": 1.0665843264776165,
"learning_rate": 1.6814948298099024e-05,
"loss": 1.5767,
"step": 635
},
{
"epoch": 0.33893817026347145,
"grad_norm": 1.0351650120702554,
"learning_rate": 1.6746997920503104e-05,
"loss": 1.5795,
"step": 640
},
{
"epoch": 0.34158612471865485,
"grad_norm": 1.0484644916794084,
"learning_rate": 1.667847082892732e-05,
"loss": 1.5537,
"step": 645
},
{
"epoch": 0.3442340791738382,
"grad_norm": 1.197623024306328,
"learning_rate": 1.6609372880870393e-05,
"loss": 1.5694,
"step": 650
},
{
"epoch": 0.3468820336290216,
"grad_norm": 1.0442156663539222,
"learning_rate": 1.6539709982626213e-05,
"loss": 1.5609,
"step": 655
},
{
"epoch": 0.34952998808420493,
"grad_norm": 1.1123431780366937,
"learning_rate": 1.6469488088778996e-05,
"loss": 1.5387,
"step": 660
},
{
"epoch": 0.35217794253938833,
"grad_norm": 1.0433338753312666,
"learning_rate": 1.639871320169429e-05,
"loss": 1.569,
"step": 665
},
{
"epoch": 0.3548258969945717,
"grad_norm": 1.0849577930136236,
"learning_rate": 1.6327391371005917e-05,
"loss": 1.5727,
"step": 670
},
{
"epoch": 0.3574738514497551,
"grad_norm": 1.046861580099341,
"learning_rate": 1.625552869309886e-05,
"loss": 1.5343,
"step": 675
},
{
"epoch": 0.3601218059049384,
"grad_norm": 1.0715008652245688,
"learning_rate": 1.6183131310588173e-05,
"loss": 1.5458,
"step": 680
},
{
"epoch": 0.3627697603601218,
"grad_norm": 1.0874487989288704,
"learning_rate": 1.611020541179392e-05,
"loss": 1.5776,
"step": 685
},
{
"epoch": 0.36541771481530516,
"grad_norm": 1.056395887760786,
"learning_rate": 1.6036757230212216e-05,
"loss": 1.5423,
"step": 690
},
{
"epoch": 0.36806566927048856,
"grad_norm": 1.0608701846522224,
"learning_rate": 1.5962793043982406e-05,
"loss": 1.5409,
"step": 695
},
{
"epoch": 0.3707136237256719,
"grad_norm": 1.0362877764811316,
"learning_rate": 1.588831917535043e-05,
"loss": 1.5468,
"step": 700
},
{
"epoch": 0.3733615781808553,
"grad_norm": 1.027124601973276,
"learning_rate": 1.5813341990128415e-05,
"loss": 1.5512,
"step": 705
},
{
"epoch": 0.37600953263603865,
"grad_norm": 1.0312792307083625,
"learning_rate": 1.5737867897150542e-05,
"loss": 1.5415,
"step": 710
},
{
"epoch": 0.37865748709122204,
"grad_norm": 1.0808334145657998,
"learning_rate": 1.5661903347725238e-05,
"loss": 1.5719,
"step": 715
},
{
"epoch": 0.3813054415464054,
"grad_norm": 1.0223414325603908,
"learning_rate": 1.558545483508373e-05,
"loss": 1.5578,
"step": 720
},
{
"epoch": 0.3839533960015888,
"grad_norm": 1.0603081644668413,
"learning_rate": 1.5508528893825045e-05,
"loss": 1.5396,
"step": 725
},
{
"epoch": 0.38660135045677213,
"grad_norm": 1.0770479780831002,
"learning_rate": 1.5431132099357418e-05,
"loss": 1.5593,
"step": 730
},
{
"epoch": 0.38924930491195553,
"grad_norm": 0.9919011715354272,
"learning_rate": 1.535327106733627e-05,
"loss": 1.5289,
"step": 735
},
{
"epoch": 0.3918972593671389,
"grad_norm": 1.1157987761320602,
"learning_rate": 1.527495245309872e-05,
"loss": 1.5404,
"step": 740
},
{
"epoch": 0.39454521382232227,
"grad_norm": 1.024198117077415,
"learning_rate": 1.5196182951094685e-05,
"loss": 1.5328,
"step": 745
},
{
"epoch": 0.3971931682775056,
"grad_norm": 0.9977432943925557,
"learning_rate": 1.5116969294314679e-05,
"loss": 1.5444,
"step": 750
},
{
"epoch": 0.399841122732689,
"grad_norm": 1.0236719689047817,
"learning_rate": 1.5037318253714288e-05,
"loss": 1.5359,
"step": 755
},
{
"epoch": 0.40248907718787236,
"grad_norm": 1.0162827582624117,
"learning_rate": 1.4957236637635415e-05,
"loss": 1.5531,
"step": 760
},
{
"epoch": 0.40513703164305576,
"grad_norm": 1.0188868081662166,
"learning_rate": 1.4876731291224304e-05,
"loss": 1.5521,
"step": 765
},
{
"epoch": 0.4077849860982391,
"grad_norm": 1.0217286340114786,
"learning_rate": 1.4795809095846463e-05,
"loss": 1.5549,
"step": 770
},
{
"epoch": 0.4104329405534225,
"grad_norm": 1.028917956544073,
"learning_rate": 1.471447696849844e-05,
"loss": 1.5334,
"step": 775
},
{
"epoch": 0.41308089500860584,
"grad_norm": 1.0500908897714312,
"learning_rate": 1.4632741861216597e-05,
"loss": 1.5266,
"step": 780
},
{
"epoch": 0.41572884946378924,
"grad_norm": 1.005286165371403,
"learning_rate": 1.4550610760482853e-05,
"loss": 1.5434,
"step": 785
},
{
"epoch": 0.4183768039189726,
"grad_norm": 1.0814951413359943,
"learning_rate": 1.446809068662752e-05,
"loss": 1.5444,
"step": 790
},
{
"epoch": 0.421024758374156,
"grad_norm": 1.1011439679669661,
"learning_rate": 1.4385188693229204e-05,
"loss": 1.5569,
"step": 795
},
{
"epoch": 0.4236727128293393,
"grad_norm": 1.016923604209529,
"learning_rate": 1.4301911866511904e-05,
"loss": 1.5557,
"step": 800
},
{
"epoch": 0.4263206672845227,
"grad_norm": 0.9901274231469388,
"learning_rate": 1.4218267324739281e-05,
"loss": 1.5157,
"step": 805
},
{
"epoch": 0.42896862173970607,
"grad_norm": 1.1652933991218297,
"learning_rate": 1.4134262217606232e-05,
"loss": 1.5573,
"step": 810
},
{
"epoch": 0.43161657619488947,
"grad_norm": 1.0773884902263529,
"learning_rate": 1.4049903725627743e-05,
"loss": 1.552,
"step": 815
},
{
"epoch": 0.4342645306500728,
"grad_norm": 1.0333923700883418,
"learning_rate": 1.3965199059525114e-05,
"loss": 1.5354,
"step": 820
},
{
"epoch": 0.4369124851052562,
"grad_norm": 0.9949649082088061,
"learning_rate": 1.3880155459609621e-05,
"loss": 1.5532,
"step": 825
},
{
"epoch": 0.43956043956043955,
"grad_norm": 1.0750837236994202,
"learning_rate": 1.3794780195163622e-05,
"loss": 1.5455,
"step": 830
},
{
"epoch": 0.44220839401562295,
"grad_norm": 1.0045353502512582,
"learning_rate": 1.370908056381921e-05,
"loss": 1.5479,
"step": 835
},
{
"epoch": 0.4448563484708063,
"grad_norm": 1.0458832746708828,
"learning_rate": 1.3623063890934427e-05,
"loss": 1.5456,
"step": 840
},
{
"epoch": 0.4475043029259897,
"grad_norm": 0.976728693908767,
"learning_rate": 1.3536737528967108e-05,
"loss": 1.5607,
"step": 845
},
{
"epoch": 0.45015225738117304,
"grad_norm": 1.0311218737493033,
"learning_rate": 1.3450108856846427e-05,
"loss": 1.525,
"step": 850
},
{
"epoch": 0.45280021183635644,
"grad_norm": 0.9872604341886291,
"learning_rate": 1.3363185279342157e-05,
"loss": 1.5195,
"step": 855
},
{
"epoch": 0.4554481662915398,
"grad_norm": 1.0149041346987562,
"learning_rate": 1.3275974226431741e-05,
"loss": 1.5246,
"step": 860
},
{
"epoch": 0.4580961207467232,
"grad_norm": 0.9934776810831784,
"learning_rate": 1.3188483152665184e-05,
"loss": 1.5558,
"step": 865
},
{
"epoch": 0.4607440752019065,
"grad_norm": 1.0720157680198927,
"learning_rate": 1.3100719536527872e-05,
"loss": 1.5596,
"step": 870
},
{
"epoch": 0.4633920296570899,
"grad_norm": 1.0084638038262754,
"learning_rate": 1.3012690879801336e-05,
"loss": 1.552,
"step": 875
},
{
"epoch": 0.46603998411227326,
"grad_norm": 1.0656341079347242,
"learning_rate": 1.2924404706922004e-05,
"loss": 1.5671,
"step": 880
},
{
"epoch": 0.46868793856745666,
"grad_norm": 1.001854533922662,
"learning_rate": 1.283586856433805e-05,
"loss": 1.5455,
"step": 885
},
{
"epoch": 0.47133589302264,
"grad_norm": 1.112510941323857,
"learning_rate": 1.2747090019864337e-05,
"loss": 1.5575,
"step": 890
},
{
"epoch": 0.4739838474778234,
"grad_norm": 1.040754615982929,
"learning_rate": 1.2658076662035549e-05,
"loss": 1.5545,
"step": 895
},
{
"epoch": 0.47663180193300675,
"grad_norm": 1.0210395751767485,
"learning_rate": 1.256883609945753e-05,
"loss": 1.5364,
"step": 900
},
{
"epoch": 0.47927975638819015,
"grad_norm": 1.0275079409852799,
"learning_rate": 1.247937596015695e-05,
"loss": 1.5183,
"step": 905
},
{
"epoch": 0.4819277108433735,
"grad_norm": 1.0640533107131247,
"learning_rate": 1.2389703890929245e-05,
"loss": 1.5597,
"step": 910
},
{
"epoch": 0.4845756652985569,
"grad_norm": 1.0119600619480633,
"learning_rate": 1.2299827556685031e-05,
"loss": 1.5154,
"step": 915
},
{
"epoch": 0.48722361975374023,
"grad_norm": 1.020830011977681,
"learning_rate": 1.2209754639794897e-05,
"loss": 1.5034,
"step": 920
},
{
"epoch": 0.48987157420892363,
"grad_norm": 1.053661577221828,
"learning_rate": 1.2119492839432754e-05,
"loss": 1.535,
"step": 925
},
{
"epoch": 0.492519528664107,
"grad_norm": 1.0735392400040396,
"learning_rate": 1.2029049870917735e-05,
"loss": 1.5392,
"step": 930
},
{
"epoch": 0.4951674831192904,
"grad_norm": 1.040125386980757,
"learning_rate": 1.1938433465054698e-05,
"loss": 1.5088,
"step": 935
},
{
"epoch": 0.4978154375744737,
"grad_norm": 1.0748654533713191,
"learning_rate": 1.1847651367473429e-05,
"loss": 1.5291,
"step": 940
},
{
"epoch": 0.5004633920296571,
"grad_norm": 1.070960019314352,
"learning_rate": 1.1756711337966572e-05,
"loss": 1.5408,
"step": 945
},
{
"epoch": 0.5031113464848405,
"grad_norm": 1.0678876377133644,
"learning_rate": 1.1665621149826327e-05,
"loss": 1.522,
"step": 950
},
{
"epoch": 0.5057593009400239,
"grad_norm": 1.0532185752896248,
"learning_rate": 1.1574388589180032e-05,
"loss": 1.5436,
"step": 955
},
{
"epoch": 0.5084072553952071,
"grad_norm": 1.0851511914260046,
"learning_rate": 1.148302145432461e-05,
"loss": 1.5522,
"step": 960
},
{
"epoch": 0.5110552098503905,
"grad_norm": 1.02938231795702,
"learning_rate": 1.1391527555060002e-05,
"loss": 1.5231,
"step": 965
},
{
"epoch": 0.513703164305574,
"grad_norm": 1.0668601829517106,
"learning_rate": 1.1299914712021616e-05,
"loss": 1.5545,
"step": 970
},
{
"epoch": 0.5163511187607573,
"grad_norm": 1.0106858243798442,
"learning_rate": 1.1208190756011815e-05,
"loss": 1.5279,
"step": 975
},
{
"epoch": 0.5189990732159406,
"grad_norm": 1.0566089105177372,
"learning_rate": 1.111636352733059e-05,
"loss": 1.5619,
"step": 980
},
{
"epoch": 0.521647027671124,
"grad_norm": 1.0229597172767808,
"learning_rate": 1.1024440875105383e-05,
"loss": 1.5288,
"step": 985
},
{
"epoch": 0.5242949821263074,
"grad_norm": 1.0470712970731715,
"learning_rate": 1.0932430656620159e-05,
"loss": 1.536,
"step": 990
},
{
"epoch": 0.5269429365814908,
"grad_norm": 1.0663817640403133,
"learning_rate": 1.0840340736643803e-05,
"loss": 1.5583,
"step": 995
},
{
"epoch": 0.5295908910366741,
"grad_norm": 1.0439017159315356,
"learning_rate": 1.0748178986757852e-05,
"loss": 1.5304,
"step": 1000
},
{
"epoch": 0.5322388454918575,
"grad_norm": 1.0790858663927478,
"learning_rate": 1.0655953284683656e-05,
"loss": 1.5127,
"step": 1005
},
{
"epoch": 0.5348867999470409,
"grad_norm": 1.0536530566954696,
"learning_rate": 1.0563671513609013e-05,
"loss": 1.543,
"step": 1010
},
{
"epoch": 0.5375347544022243,
"grad_norm": 1.0170237895907281,
"learning_rate": 1.0471341561514337e-05,
"loss": 1.5194,
"step": 1015
},
{
"epoch": 0.5401827088574076,
"grad_norm": 1.0473205826242136,
"learning_rate": 1.0378971320498425e-05,
"loss": 1.5136,
"step": 1020
},
{
"epoch": 0.542830663312591,
"grad_norm": 1.0567217848188775,
"learning_rate": 1.0286568686103846e-05,
"loss": 1.5226,
"step": 1025
},
{
"epoch": 0.5454786177677744,
"grad_norm": 1.0208955618061542,
"learning_rate": 1.0194141556642065e-05,
"loss": 1.5499,
"step": 1030
},
{
"epoch": 0.5481265722229578,
"grad_norm": 1.014238754109568,
"learning_rate": 1.0101697832518316e-05,
"loss": 1.5291,
"step": 1035
},
{
"epoch": 0.5507745266781411,
"grad_norm": 1.0293706768418351,
"learning_rate": 1.0009245415556297e-05,
"loss": 1.5252,
"step": 1040
},
{
"epoch": 0.5534224811333245,
"grad_norm": 1.0505758556707483,
"learning_rate": 9.916792208322743e-06,
"loss": 1.5266,
"step": 1045
},
{
"epoch": 0.5560704355885079,
"grad_norm": 1.0130623575273145,
"learning_rate": 9.824346113451943e-06,
"loss": 1.5228,
"step": 1050
},
{
"epoch": 0.5587183900436913,
"grad_norm": 1.0351862096161806,
"learning_rate": 9.73191503297023e-06,
"loss": 1.5258,
"step": 1055
},
{
"epoch": 0.5613663444988746,
"grad_norm": 1.04995407064205,
"learning_rate": 9.639506867620574e-06,
"loss": 1.5231,
"step": 1060
},
{
"epoch": 0.564014298954058,
"grad_norm": 1.0436659926908782,
"learning_rate": 9.547129516187197e-06,
"loss": 1.518,
"step": 1065
},
{
"epoch": 0.5666622534092414,
"grad_norm": 1.046638110053409,
"learning_rate": 9.454790874820452e-06,
"loss": 1.5098,
"step": 1070
},
{
"epoch": 0.5693102078644248,
"grad_norm": 1.0241677741798514,
"learning_rate": 9.36249883636187e-06,
"loss": 1.5425,
"step": 1075
},
{
"epoch": 0.571958162319608,
"grad_norm": 0.9941017772339601,
"learning_rate": 9.27026128966949e-06,
"loss": 1.5142,
"step": 1080
},
{
"epoch": 0.5746061167747915,
"grad_norm": 0.9716061498004498,
"learning_rate": 9.178086118943556e-06,
"loss": 1.5455,
"step": 1085
},
{
"epoch": 0.5772540712299749,
"grad_norm": 1.0256633172012475,
"learning_rate": 9.085981203052594e-06,
"loss": 1.5383,
"step": 1090
},
{
"epoch": 0.5799020256851583,
"grad_norm": 1.0223919398580668,
"learning_rate": 8.993954414859944e-06,
"loss": 1.5331,
"step": 1095
},
{
"epoch": 0.5825499801403415,
"grad_norm": 1.007132533021316,
"learning_rate": 8.902013620550822e-06,
"loss": 1.5329,
"step": 1100
},
{
"epoch": 0.5851979345955249,
"grad_norm": 0.9942218744170546,
"learning_rate": 8.810166678959931e-06,
"loss": 1.5389,
"step": 1105
},
{
"epoch": 0.5878458890507083,
"grad_norm": 1.0110745590358547,
"learning_rate": 8.718421440899711e-06,
"loss": 1.5628,
"step": 1110
},
{
"epoch": 0.5904938435058917,
"grad_norm": 1.0107377987377537,
"learning_rate": 8.626785748489284e-06,
"loss": 1.5368,
"step": 1115
},
{
"epoch": 0.593141797961075,
"grad_norm": 0.9913006390349152,
"learning_rate": 8.535267434484116e-06,
"loss": 1.5344,
"step": 1120
},
{
"epoch": 0.5957897524162584,
"grad_norm": 0.9777988491979502,
"learning_rate": 8.443874321606505e-06,
"loss": 1.5227,
"step": 1125
},
{
"epoch": 0.5984377068714418,
"grad_norm": 1.0189135477068292,
"learning_rate": 8.352614221876932e-06,
"loss": 1.5214,
"step": 1130
},
{
"epoch": 0.6010856613266252,
"grad_norm": 1.0138767745745147,
"learning_rate": 8.261494935946271e-06,
"loss": 1.5247,
"step": 1135
},
{
"epoch": 0.6037336157818085,
"grad_norm": 0.9761877999287727,
"learning_rate": 8.170524252429059e-06,
"loss": 1.5103,
"step": 1140
},
{
"epoch": 0.6063815702369919,
"grad_norm": 1.0040567049619376,
"learning_rate": 8.079709947237719e-06,
"loss": 1.5022,
"step": 1145
},
{
"epoch": 0.6090295246921753,
"grad_norm": 1.013457073795383,
"learning_rate": 7.989059782917899e-06,
"loss": 1.53,
"step": 1150
},
{
"epoch": 0.6116774791473587,
"grad_norm": 0.9757606354115737,
"learning_rate": 7.898581507984966e-06,
"loss": 1.5178,
"step": 1155
},
{
"epoch": 0.614325433602542,
"grad_norm": 0.9943607585307255,
"learning_rate": 7.80828285626167e-06,
"loss": 1.5275,
"step": 1160
},
{
"epoch": 0.6169733880577254,
"grad_norm": 1.0023636505282656,
"learning_rate": 7.718171546217088e-06,
"loss": 1.5443,
"step": 1165
},
{
"epoch": 0.6196213425129088,
"grad_norm": 1.0171146246719223,
"learning_rate": 7.628255280306869e-06,
"loss": 1.5192,
"step": 1170
},
{
"epoch": 0.6222692969680922,
"grad_norm": 1.0247392112526459,
"learning_rate": 7.538541744314854e-06,
"loss": 1.5348,
"step": 1175
},
{
"epoch": 0.6249172514232755,
"grad_norm": 0.990257878872753,
"learning_rate": 7.449038606696102e-06,
"loss": 1.5396,
"step": 1180
},
{
"epoch": 0.6275652058784589,
"grad_norm": 0.9939434167335955,
"learning_rate": 7.359753517921441e-06,
"loss": 1.5167,
"step": 1185
},
{
"epoch": 0.6302131603336423,
"grad_norm": 0.9896269105787017,
"learning_rate": 7.2706941098234975e-06,
"loss": 1.5367,
"step": 1190
},
{
"epoch": 0.6328611147888257,
"grad_norm": 1.012229868356229,
"learning_rate": 7.1818679949443625e-06,
"loss": 1.5503,
"step": 1195
},
{
"epoch": 0.635509069244009,
"grad_norm": 1.000043265309018,
"learning_rate": 7.09328276588491e-06,
"loss": 1.5315,
"step": 1200
},
{
"epoch": 0.6381570236991924,
"grad_norm": 1.0289266588222385,
"learning_rate": 7.004945994655762e-06,
"loss": 1.4967,
"step": 1205
},
{
"epoch": 0.6408049781543758,
"grad_norm": 1.0025882987592574,
"learning_rate": 6.9168652320301034e-06,
"loss": 1.5477,
"step": 1210
},
{
"epoch": 0.6434529326095592,
"grad_norm": 0.9919331762414756,
"learning_rate": 6.829048006898223e-06,
"loss": 1.534,
"step": 1215
},
{
"epoch": 0.6461008870647424,
"grad_norm": 1.0019076590702611,
"learning_rate": 6.741501825623989e-06,
"loss": 1.5117,
"step": 1220
},
{
"epoch": 0.6487488415199258,
"grad_norm": 1.0543772866427898,
"learning_rate": 6.6542341714032226e-06,
"loss": 1.5244,
"step": 1225
},
{
"epoch": 0.6513967959751092,
"grad_norm": 1.0306054721119788,
"learning_rate": 6.567252503624049e-06,
"loss": 1.5411,
"step": 1230
},
{
"epoch": 0.6540447504302926,
"grad_norm": 1.0302893738157837,
"learning_rate": 6.480564257229294e-06,
"loss": 1.4942,
"step": 1235
},
{
"epoch": 0.6566927048854759,
"grad_norm": 1.0109127444615766,
"learning_rate": 6.394176842080975e-06,
"loss": 1.502,
"step": 1240
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.9781847599103843,
"learning_rate": 6.308097642326909e-06,
"loss": 1.5066,
"step": 1245
},
{
"epoch": 0.6619886137958427,
"grad_norm": 0.9824997539943708,
"learning_rate": 6.222334015769553e-06,
"loss": 1.5101,
"step": 1250
},
{
"epoch": 0.6646365682510261,
"grad_norm": 0.9987899689076005,
"learning_rate": 6.136893293237078e-06,
"loss": 1.5185,
"step": 1255
},
{
"epoch": 0.6672845227062094,
"grad_norm": 1.006107504524868,
"learning_rate": 6.051782777956738e-06,
"loss": 1.5239,
"step": 1260
},
{
"epoch": 0.6699324771613928,
"grad_norm": 1.0044418449699575,
"learning_rate": 5.967009744930633e-06,
"loss": 1.4952,
"step": 1265
},
{
"epoch": 0.6725804316165762,
"grad_norm": 1.0039662646096303,
"learning_rate": 5.882581440313842e-06,
"loss": 1.5116,
"step": 1270
},
{
"epoch": 0.6752283860717596,
"grad_norm": 1.0462978677216113,
"learning_rate": 5.798505080795047e-06,
"loss": 1.5258,
"step": 1275
},
{
"epoch": 0.6778763405269429,
"grad_norm": 0.9979354408371577,
"learning_rate": 5.7147878529796905e-06,
"loss": 1.5315,
"step": 1280
},
{
"epoch": 0.6805242949821263,
"grad_norm": 0.9776481970979145,
"learning_rate": 5.631436912775652e-06,
"loss": 1.5075,
"step": 1285
},
{
"epoch": 0.6831722494373097,
"grad_norm": 1.0087198024702337,
"learning_rate": 5.54845938478161e-06,
"loss": 1.5047,
"step": 1290
},
{
"epoch": 0.6858202038924931,
"grad_norm": 0.9903441971804162,
"learning_rate": 5.465862361678043e-06,
"loss": 1.5517,
"step": 1295
},
{
"epoch": 0.6884681583476764,
"grad_norm": 1.023066931211098,
"learning_rate": 5.383652903620952e-06,
"loss": 1.4905,
"step": 1300
},
{
"epoch": 0.6911161128028598,
"grad_norm": 0.9932405098752322,
"learning_rate": 5.3018380376384075e-06,
"loss": 1.5218,
"step": 1305
},
{
"epoch": 0.6937640672580432,
"grad_norm": 0.9757939837419622,
"learning_rate": 5.220424757029876e-06,
"loss": 1.5217,
"step": 1310
},
{
"epoch": 0.6964120217132266,
"grad_norm": 0.9861240044120464,
"learning_rate": 5.139420020768466e-06,
"loss": 1.5173,
"step": 1315
},
{
"epoch": 0.6990599761684099,
"grad_norm": 1.0526302805244943,
"learning_rate": 5.05883075290609e-06,
"loss": 1.5295,
"step": 1320
},
{
"epoch": 0.7017079306235933,
"grad_norm": 1.0185424558326355,
"learning_rate": 4.978663841981604e-06,
"loss": 1.516,
"step": 1325
},
{
"epoch": 0.7043558850787767,
"grad_norm": 1.018775036262236,
"learning_rate": 4.898926140432027e-06,
"loss": 1.5074,
"step": 1330
},
{
"epoch": 0.7070038395339601,
"grad_norm": 1.0312565088617913,
"learning_rate": 4.819624464006783e-06,
"loss": 1.5431,
"step": 1335
},
{
"epoch": 0.7096517939891434,
"grad_norm": 1.0212263411238394,
"learning_rate": 4.7407655911851205e-06,
"loss": 1.515,
"step": 1340
},
{
"epoch": 0.7122997484443268,
"grad_norm": 0.9933683646722576,
"learning_rate": 4.6623562625967165e-06,
"loss": 1.5281,
"step": 1345
},
{
"epoch": 0.7149477028995102,
"grad_norm": 0.9624331021666575,
"learning_rate": 4.5844031804455e-06,
"loss": 1.5367,
"step": 1350
},
{
"epoch": 0.7175956573546936,
"grad_norm": 1.026883861445322,
"learning_rate": 4.506913007936756e-06,
"loss": 1.5182,
"step": 1355
},
{
"epoch": 0.7202436118098768,
"grad_norm": 1.002938064771753,
"learning_rate": 4.429892368707594e-06,
"loss": 1.5185,
"step": 1360
},
{
"epoch": 0.7228915662650602,
"grad_norm": 0.9794563064534025,
"learning_rate": 4.3533478462607706e-06,
"loss": 1.5147,
"step": 1365
},
{
"epoch": 0.7255395207202436,
"grad_norm": 0.984697237202532,
"learning_rate": 4.2772859834019444e-06,
"loss": 1.5085,
"step": 1370
},
{
"epoch": 0.728187475175427,
"grad_norm": 1.0067564757025862,
"learning_rate": 4.201713281680417e-06,
"loss": 1.5337,
"step": 1375
},
{
"epoch": 0.7308354296306103,
"grad_norm": 0.9812201953008316,
"learning_rate": 4.126636200833407e-06,
"loss": 1.5331,
"step": 1380
},
{
"epoch": 0.7334833840857937,
"grad_norm": 1.007828581920917,
"learning_rate": 4.0520611582338874e-06,
"loss": 1.5258,
"step": 1385
},
{
"epoch": 0.7361313385409771,
"grad_norm": 1.0411554611974254,
"learning_rate": 3.977994528342049e-06,
"loss": 1.5241,
"step": 1390
},
{
"epoch": 0.7387792929961605,
"grad_norm": 1.0034067110278442,
"learning_rate": 3.904442642160412e-06,
"loss": 1.5204,
"step": 1395
},
{
"epoch": 0.7414272474513438,
"grad_norm": 0.9595126781640712,
"learning_rate": 3.831411786692698e-06,
"loss": 1.5158,
"step": 1400
},
{
"epoch": 0.7440752019065272,
"grad_norm": 0.9783084053302383,
"learning_rate": 3.7589082044064198e-06,
"loss": 1.5312,
"step": 1405
},
{
"epoch": 0.7467231563617106,
"grad_norm": 0.9678174617335311,
"learning_rate": 3.686938092699287e-06,
"loss": 1.5302,
"step": 1410
},
{
"epoch": 0.749371110816894,
"grad_norm": 0.9871715872104168,
"learning_rate": 3.6155076033694848e-06,
"loss": 1.517,
"step": 1415
},
{
"epoch": 0.7520190652720773,
"grad_norm": 1.0044736545312436,
"learning_rate": 3.5446228420898333e-06,
"loss": 1.4888,
"step": 1420
},
{
"epoch": 0.7546670197272607,
"grad_norm": 0.9716268636229163,
"learning_rate": 3.474289867885876e-06,
"loss": 1.5379,
"step": 1425
},
{
"epoch": 0.7573149741824441,
"grad_norm": 0.9890097406031959,
"learning_rate": 3.404514692617994e-06,
"loss": 1.523,
"step": 1430
},
{
"epoch": 0.7599629286376274,
"grad_norm": 1.0216348999301932,
"learning_rate": 3.3353032804675157e-06,
"loss": 1.5337,
"step": 1435
},
{
"epoch": 0.7626108830928108,
"grad_norm": 1.0038373151987001,
"learning_rate": 3.2666615474269202e-06,
"loss": 1.5187,
"step": 1440
},
{
"epoch": 0.7652588375479942,
"grad_norm": 0.9909609500438246,
"learning_rate": 3.19859536079416e-06,
"loss": 1.5172,
"step": 1445
},
{
"epoch": 0.7679067920031776,
"grad_norm": 0.9689018876021506,
"learning_rate": 3.1311105386711206e-06,
"loss": 1.5179,
"step": 1450
},
{
"epoch": 0.7705547464583609,
"grad_norm": 0.49237533241415254,
"learning_rate": 3.064212849466335e-06,
"loss": 1.5243,
"step": 1455
},
{
"epoch": 0.7732027009135443,
"grad_norm": 1.028791952556653,
"learning_rate": 2.997908011401902e-06,
"loss": 1.5131,
"step": 1460
},
{
"epoch": 0.7758506553687277,
"grad_norm": 0.988433671716438,
"learning_rate": 2.932201692024701e-06,
"loss": 1.4977,
"step": 1465
},
{
"epoch": 0.7784986098239111,
"grad_norm": 1.033980515849518,
"learning_rate": 2.8670995077219597e-06,
"loss": 1.5317,
"step": 1470
},
{
"epoch": 0.7811465642790943,
"grad_norm": 0.9775113095673127,
"learning_rate": 2.8026070232411852e-06,
"loss": 1.4968,
"step": 1475
},
{
"epoch": 0.7837945187342777,
"grad_norm": 0.9877497208445748,
"learning_rate": 2.7387297512144808e-06,
"loss": 1.5224,
"step": 1480
},
{
"epoch": 0.7864424731894611,
"grad_norm": 1.009024038211844,
"learning_rate": 2.67547315168737e-06,
"loss": 1.5423,
"step": 1485
},
{
"epoch": 0.7890904276446445,
"grad_norm": 0.9732391094592455,
"learning_rate": 2.6128426316520773e-06,
"loss": 1.5248,
"step": 1490
},
{
"epoch": 0.7917383820998278,
"grad_norm": 1.0039025745395442,
"learning_rate": 2.550843544585342e-06,
"loss": 1.5622,
"step": 1495
},
{
"epoch": 0.7943863365550112,
"grad_norm": 0.9788028397156042,
"learning_rate": 2.4894811899908387e-06,
"loss": 1.5103,
"step": 1500
},
{
"epoch": 0.7970342910101946,
"grad_norm": 0.9653871232501977,
"learning_rate": 2.428760812946177e-06,
"loss": 1.5425,
"step": 1505
},
{
"epoch": 0.799682245465378,
"grad_norm": 0.9738743806340848,
"learning_rate": 2.368687603654574e-06,
"loss": 1.5121,
"step": 1510
},
{
"epoch": 0.8023301999205613,
"grad_norm": 0.9969072135710934,
"learning_rate": 2.3092666970012103e-06,
"loss": 1.5026,
"step": 1515
},
{
"epoch": 0.8049781543757447,
"grad_norm": 0.9655875746133022,
"learning_rate": 2.250503172114301e-06,
"loss": 1.5075,
"step": 1520
},
{
"epoch": 0.8076261088309281,
"grad_norm": 0.9664980760046697,
"learning_rate": 2.1924020519309742e-06,
"loss": 1.5198,
"step": 1525
},
{
"epoch": 0.8102740632861115,
"grad_norm": 0.9699897090047268,
"learning_rate": 2.1349683027679e-06,
"loss": 1.5223,
"step": 1530
},
{
"epoch": 0.8129220177412948,
"grad_norm": 0.9900349045998372,
"learning_rate": 2.078206833896792e-06,
"loss": 1.5062,
"step": 1535
},
{
"epoch": 0.8155699721964782,
"grad_norm": 1.0154071244795133,
"learning_rate": 2.022122497124782e-06,
"loss": 1.4834,
"step": 1540
},
{
"epoch": 0.8182179266516616,
"grad_norm": 0.967706724069395,
"learning_rate": 1.9667200863796965e-06,
"loss": 1.5366,
"step": 1545
},
{
"epoch": 0.820865881106845,
"grad_norm": 0.9742445082631996,
"learning_rate": 1.9120043373002804e-06,
"loss": 1.5226,
"step": 1550
},
{
"epoch": 0.8235138355620283,
"grad_norm": 0.9855108838889343,
"learning_rate": 1.8579799268314224e-06,
"loss": 1.5561,
"step": 1555
},
{
"epoch": 0.8261617900172117,
"grad_norm": 1.0038064244529792,
"learning_rate": 1.8046514728243725e-06,
"loss": 1.5247,
"step": 1560
},
{
"epoch": 0.8288097444723951,
"grad_norm": 0.9739289064816902,
"learning_rate": 1.7520235336420144e-06,
"loss": 1.4929,
"step": 1565
},
{
"epoch": 0.8314576989275785,
"grad_norm": 0.9680126539518724,
"learning_rate": 1.7001006077692584e-06,
"loss": 1.4823,
"step": 1570
},
{
"epoch": 0.8341056533827618,
"grad_norm": 1.0214721547722743,
"learning_rate": 1.648887133428485e-06,
"loss": 1.51,
"step": 1575
},
{
"epoch": 0.8367536078379452,
"grad_norm": 0.98797077056357,
"learning_rate": 1.5983874882002083e-06,
"loss": 1.5218,
"step": 1580
},
{
"epoch": 0.8394015622931286,
"grad_norm": 0.9726850095038396,
"learning_rate": 1.5486059886488825e-06,
"loss": 1.5028,
"step": 1585
},
{
"epoch": 0.842049516748312,
"grad_norm": 0.9907275183986879,
"learning_rate": 1.4995468899539278e-06,
"loss": 1.5141,
"step": 1590
},
{
"epoch": 0.8446974712034953,
"grad_norm": 1.0095657865872754,
"learning_rate": 1.4512143855460237e-06,
"loss": 1.5251,
"step": 1595
},
{
"epoch": 0.8473454256586787,
"grad_norm": 0.9948902717671079,
"learning_rate": 1.403612606748659e-06,
"loss": 1.4785,
"step": 1600
},
{
"epoch": 0.849993380113862,
"grad_norm": 0.9845596560770083,
"learning_rate": 1.356745622424992e-06,
"loss": 1.5187,
"step": 1605
},
{
"epoch": 0.8526413345690455,
"grad_norm": 0.953506811187465,
"learning_rate": 1.3106174386300686e-06,
"loss": 1.5425,
"step": 1610
},
{
"epoch": 0.8552892890242287,
"grad_norm": 0.9618810193914135,
"learning_rate": 1.2652319982683926e-06,
"loss": 1.529,
"step": 1615
},
{
"epoch": 0.8579372434794121,
"grad_norm": 0.9947966334717282,
"learning_rate": 1.220593180756884e-06,
"loss": 1.5154,
"step": 1620
},
{
"epoch": 0.8605851979345955,
"grad_norm": 1.0030199127391055,
"learning_rate": 1.1767048016933024e-06,
"loss": 1.5311,
"step": 1625
},
{
"epoch": 0.8632331523897789,
"grad_norm": 0.9719704049091674,
"learning_rate": 1.1335706125300782e-06,
"loss": 1.4993,
"step": 1630
},
{
"epoch": 0.8658811068449622,
"grad_norm": 0.9971991350833769,
"learning_rate": 1.091194300253654e-06,
"loss": 1.5328,
"step": 1635
},
{
"epoch": 0.8685290613001456,
"grad_norm": 0.9386404691705372,
"learning_rate": 1.049579487069351e-06,
"loss": 1.5276,
"step": 1640
},
{
"epoch": 0.871177015755329,
"grad_norm": 0.956420931896452,
"learning_rate": 1.008729730091721e-06,
"loss": 1.5119,
"step": 1645
},
{
"epoch": 0.8738249702105124,
"grad_norm": 0.9735098420048076,
"learning_rate": 9.686485210405206e-07,
"loss": 1.5079,
"step": 1650
},
{
"epoch": 0.8764729246656957,
"grad_norm": 0.9920608419716006,
"learning_rate": 9.293392859422401e-07,
"loss": 1.5142,
"step": 1655
},
{
"epoch": 0.8791208791208791,
"grad_norm": 0.9643322536422883,
"learning_rate": 8.90805384837251e-07,
"loss": 1.5117,
"step": 1660
},
{
"epoch": 0.8817688335760625,
"grad_norm": 0.9788979391472972,
"learning_rate": 8.530501114926082e-07,
"loss": 1.5015,
"step": 1665
},
{
"epoch": 0.8844167880312459,
"grad_norm": 0.9647617399657337,
"learning_rate": 8.160766931205066e-07,
"loss": 1.5293,
"step": 1670
},
{
"epoch": 0.8870647424864292,
"grad_norm": 0.9564397438564627,
"learning_rate": 7.798882901024196e-07,
"loss": 1.5041,
"step": 1675
},
{
"epoch": 0.8897126969416126,
"grad_norm": 0.9552845261427283,
"learning_rate": 7.444879957189732e-07,
"loss": 1.5371,
"step": 1680
},
{
"epoch": 0.892360651396796,
"grad_norm": 0.9814428213129086,
"learning_rate": 7.098788358855313e-07,
"loss": 1.5187,
"step": 1685
},
{
"epoch": 0.8950086058519794,
"grad_norm": 0.9877612943504955,
"learning_rate": 6.760637688935457e-07,
"loss": 1.5049,
"step": 1690
},
{
"epoch": 0.8976565603071627,
"grad_norm": 0.9806604488270347,
"learning_rate": 6.430456851577072e-07,
"loss": 1.5063,
"step": 1695
},
{
"epoch": 0.9003045147623461,
"grad_norm": 0.9576410171206939,
"learning_rate": 6.108274069688603e-07,
"loss": 1.5208,
"step": 1700
},
{
"epoch": 0.9029524692175295,
"grad_norm": 0.9818044085686626,
"learning_rate": 5.794116882527712e-07,
"loss": 1.5124,
"step": 1705
},
{
"epoch": 0.9056004236727129,
"grad_norm": 0.9685653401983324,
"learning_rate": 5.488012143347399e-07,
"loss": 1.5219,
"step": 1710
},
{
"epoch": 0.9082483781278962,
"grad_norm": 0.9809825210830677,
"learning_rate": 5.189986017100446e-07,
"loss": 1.4738,
"step": 1715
},
{
"epoch": 0.9108963325830796,
"grad_norm": 0.975406693103622,
"learning_rate": 4.900063978203118e-07,
"loss": 1.5399,
"step": 1720
},
{
"epoch": 0.913544287038263,
"grad_norm": 0.986056861811607,
"learning_rate": 4.6182708083575724e-07,
"loss": 1.513,
"step": 1725
},
{
"epoch": 0.9161922414934464,
"grad_norm": 0.9798958647556985,
"learning_rate": 4.3446305944335856e-07,
"loss": 1.5153,
"step": 1730
},
{
"epoch": 0.9188401959486296,
"grad_norm": 0.9693236881798926,
"learning_rate": 4.079166726409767e-07,
"loss": 1.5199,
"step": 1735
},
{
"epoch": 0.921488150403813,
"grad_norm": 0.9743074736324623,
"learning_rate": 3.821901895374147e-07,
"loss": 1.5116,
"step": 1740
},
{
"epoch": 0.9241361048589964,
"grad_norm": 0.971024863447133,
"learning_rate": 3.572858091584641e-07,
"loss": 1.5119,
"step": 1745
},
{
"epoch": 0.9267840593141798,
"grad_norm": 0.9677442463184608,
"learning_rate": 3.3320566025894727e-07,
"loss": 1.5257,
"step": 1750
},
{
"epoch": 0.9294320137693631,
"grad_norm": 0.9827347277692877,
"learning_rate": 3.0995180114074206e-07,
"loss": 1.5172,
"step": 1755
},
{
"epoch": 0.9320799682245465,
"grad_norm": 0.9743959370781557,
"learning_rate": 2.875262194768513e-07,
"loss": 1.5366,
"step": 1760
},
{
"epoch": 0.9347279226797299,
"grad_norm": 0.9564493157330359,
"learning_rate": 2.6593083214151215e-07,
"loss": 1.5029,
"step": 1765
},
{
"epoch": 0.9373758771349133,
"grad_norm": 0.9809452479317344,
"learning_rate": 2.4516748504632815e-07,
"loss": 1.5233,
"step": 1770
},
{
"epoch": 0.9400238315900966,
"grad_norm": 0.9597734400844808,
"learning_rate": 2.2523795298249996e-07,
"loss": 1.5228,
"step": 1775
},
{
"epoch": 0.94267178604528,
"grad_norm": 0.9477114517816689,
"learning_rate": 2.0614393946911891e-07,
"loss": 1.5101,
"step": 1780
},
{
"epoch": 0.9453197405004634,
"grad_norm": 0.9698387988540002,
"learning_rate": 1.8788707660755024e-07,
"loss": 1.508,
"step": 1785
},
{
"epoch": 0.9479676949556468,
"grad_norm": 0.9757478306640798,
"learning_rate": 1.704689249419289e-07,
"loss": 1.5049,
"step": 1790
},
{
"epoch": 0.9506156494108301,
"grad_norm": 0.9668834988577203,
"learning_rate": 1.5389097332577318e-07,
"loss": 1.5293,
"step": 1795
},
{
"epoch": 0.9532636038660135,
"grad_norm": 0.9901171627850629,
"learning_rate": 1.381546387947097e-07,
"loss": 1.5221,
"step": 1800
},
{
"epoch": 0.9559115583211969,
"grad_norm": 0.9566404806968487,
"learning_rate": 1.2326126644536362e-07,
"loss": 1.5071,
"step": 1805
},
{
"epoch": 0.9585595127763803,
"grad_norm": 0.9607827035134089,
"learning_rate": 1.0921212932037517e-07,
"loss": 1.5157,
"step": 1810
},
{
"epoch": 0.9612074672315636,
"grad_norm": 0.9975142952632257,
"learning_rate": 9.600842829958101e-08,
"loss": 1.5242,
"step": 1815
},
{
"epoch": 0.963855421686747,
"grad_norm": 0.9753226507807833,
"learning_rate": 8.365129199737864e-08,
"loss": 1.5068,
"step": 1820
},
{
"epoch": 0.9665033761419304,
"grad_norm": 0.979318592057113,
"learning_rate": 7.214177666624134e-08,
"loss": 1.5272,
"step": 1825
},
{
"epoch": 0.9691513305971138,
"grad_norm": 0.9696032798439096,
"learning_rate": 6.148086610644144e-08,
"loss": 1.508,
"step": 1830
},
{
"epoch": 0.9717992850522971,
"grad_norm": 0.9600338608905342,
"learning_rate": 5.166947158195768e-08,
"loss": 1.496,
"step": 1835
},
{
"epoch": 0.9744472395074805,
"grad_norm": 0.9384033653578022,
"learning_rate": 4.2708431742577436e-08,
"loss": 1.5241,
"step": 1840
},
{
"epoch": 0.9770951939626639,
"grad_norm": 0.9567487185767485,
"learning_rate": 3.459851255221858e-08,
"loss": 1.5165,
"step": 1845
},
{
"epoch": 0.9797431484178473,
"grad_norm": 0.9880298117128525,
"learning_rate": 2.734040722345066e-08,
"loss": 1.5055,
"step": 1850
},
{
"epoch": 0.9823911028730306,
"grad_norm": 0.9695727389619365,
"learning_rate": 2.0934736158245707e-08,
"loss": 1.5072,
"step": 1855
},
{
"epoch": 0.985039057328214,
"grad_norm": 0.9611774727863346,
"learning_rate": 1.5382046894943936e-08,
"loss": 1.5124,
"step": 1860
},
{
"epoch": 0.9876870117833974,
"grad_norm": 0.9495491860194544,
"learning_rate": 1.068281406145788e-08,
"loss": 1.5035,
"step": 1865
},
{
"epoch": 0.9903349662385807,
"grad_norm": 1.3371313882358693,
"learning_rate": 6.837439334695939e-09,
"loss": 1.486,
"step": 1870
},
{
"epoch": 0.992982920693764,
"grad_norm": 0.9652831685373289,
"learning_rate": 3.8462514062298505e-09,
"loss": 1.5044,
"step": 1875
},
{
"epoch": 0.9956308751489474,
"grad_norm": 0.9593787027270587,
"learning_rate": 1.7095059542038272e-09,
"loss": 1.5225,
"step": 1880
},
{
"epoch": 0.9982788296041308,
"grad_norm": 0.9573474795742825,
"learning_rate": 4.273856214742633e-10,
"loss": 1.524,
"step": 1885
},
{
"epoch": 0.9998676022772408,
"eval_loss": 1.526898980140686,
"eval_runtime": 445.6497,
"eval_samples_per_second": 60.011,
"eval_steps_per_second": 3.752,
"step": 1888
},
{
"epoch": 0.9998676022772408,
"step": 1888,
"total_flos": 106218135748608.0,
"train_loss": 1.5447227579809852,
"train_runtime": 15813.94,
"train_samples_per_second": 15.283,
"train_steps_per_second": 0.119
}
],
"logging_steps": 5,
"max_steps": 1888,
"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": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 106218135748608.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}