kenanga-lora-b-1-6000 / trainer_state.json
rmdhirr's picture
Upload folder using huggingface_hub
e9bec88 verified
Raw
History Blame Contribute Delete
223 kB
{
"best_global_step": 6000,
"best_metric": 0.9046825170516968,
"best_model_checkpoint": "outputs/checkpoint-6000",
"epoch": 3.2769735045069655,
"eval_steps": 300,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0027314941272876263,
"grad_norm": 4.851426601409912,
"learning_rate": 6.521739130434783e-07,
"loss": 2.9623,
"step": 5
},
{
"epoch": 0.005462988254575253,
"grad_norm": 5.322866439819336,
"learning_rate": 1.4673913043478262e-06,
"loss": 2.8968,
"step": 10
},
{
"epoch": 0.00819448238186288,
"grad_norm": 4.726293563842773,
"learning_rate": 2.282608695652174e-06,
"loss": 3.0188,
"step": 15
},
{
"epoch": 0.010925976509150505,
"grad_norm": 4.048459529876709,
"learning_rate": 3.097826086956522e-06,
"loss": 2.8014,
"step": 20
},
{
"epoch": 0.013657470636438131,
"grad_norm": 4.118284225463867,
"learning_rate": 3.913043478260869e-06,
"loss": 2.7867,
"step": 25
},
{
"epoch": 0.01638896476372576,
"grad_norm": 4.78012752532959,
"learning_rate": 4.728260869565218e-06,
"loss": 2.7244,
"step": 30
},
{
"epoch": 0.019120458891013385,
"grad_norm": 3.870762586593628,
"learning_rate": 5.543478260869565e-06,
"loss": 2.7813,
"step": 35
},
{
"epoch": 0.02185195301830101,
"grad_norm": 3.015080451965332,
"learning_rate": 6.358695652173913e-06,
"loss": 2.4723,
"step": 40
},
{
"epoch": 0.024583447145588636,
"grad_norm": 2.9946231842041016,
"learning_rate": 7.173913043478261e-06,
"loss": 2.462,
"step": 45
},
{
"epoch": 0.027314941272876262,
"grad_norm": 2.191171884536743,
"learning_rate": 7.98913043478261e-06,
"loss": 2.3881,
"step": 50
},
{
"epoch": 0.030046435400163888,
"grad_norm": 2.354739189147949,
"learning_rate": 8.804347826086957e-06,
"loss": 2.1182,
"step": 55
},
{
"epoch": 0.03277792952745152,
"grad_norm": 1.6525721549987793,
"learning_rate": 9.619565217391304e-06,
"loss": 1.9386,
"step": 60
},
{
"epoch": 0.03550942365473914,
"grad_norm": 1.3781287670135498,
"learning_rate": 1.0434782608695653e-05,
"loss": 2.0235,
"step": 65
},
{
"epoch": 0.03824091778202677,
"grad_norm": 1.2135268449783325,
"learning_rate": 1.125e-05,
"loss": 1.8313,
"step": 70
},
{
"epoch": 0.040972411909314395,
"grad_norm": 0.9717159271240234,
"learning_rate": 1.2065217391304348e-05,
"loss": 1.9393,
"step": 75
},
{
"epoch": 0.04370390603660202,
"grad_norm": 1.1752846240997314,
"learning_rate": 1.2880434782608696e-05,
"loss": 1.9298,
"step": 80
},
{
"epoch": 0.04643540016388965,
"grad_norm": 0.9449806213378906,
"learning_rate": 1.3695652173913042e-05,
"loss": 1.823,
"step": 85
},
{
"epoch": 0.04916689429117727,
"grad_norm": 1.2805055379867554,
"learning_rate": 1.4510869565217392e-05,
"loss": 1.8492,
"step": 90
},
{
"epoch": 0.0518983884184649,
"grad_norm": 0.9438149333000183,
"learning_rate": 1.532608695652174e-05,
"loss": 1.663,
"step": 95
},
{
"epoch": 0.054629882545752524,
"grad_norm": 0.9939911961555481,
"learning_rate": 1.6141304347826086e-05,
"loss": 1.7269,
"step": 100
},
{
"epoch": 0.05736137667304015,
"grad_norm": 0.8572550415992737,
"learning_rate": 1.6956521739130433e-05,
"loss": 1.6393,
"step": 105
},
{
"epoch": 0.060092870800327776,
"grad_norm": 0.9384661912918091,
"learning_rate": 1.777173913043478e-05,
"loss": 1.6523,
"step": 110
},
{
"epoch": 0.06282436492761541,
"grad_norm": 0.8437032103538513,
"learning_rate": 1.858695652173913e-05,
"loss": 1.6622,
"step": 115
},
{
"epoch": 0.06555585905490303,
"grad_norm": 0.8985423445701599,
"learning_rate": 1.940217391304348e-05,
"loss": 1.5545,
"step": 120
},
{
"epoch": 0.06828735318219066,
"grad_norm": 0.9783689975738525,
"learning_rate": 2.0217391304347828e-05,
"loss": 1.5837,
"step": 125
},
{
"epoch": 0.07101884730947829,
"grad_norm": 0.77556312084198,
"learning_rate": 2.1032608695652175e-05,
"loss": 1.5758,
"step": 130
},
{
"epoch": 0.07375034143676591,
"grad_norm": 0.8036277294158936,
"learning_rate": 2.1847826086956523e-05,
"loss": 1.5933,
"step": 135
},
{
"epoch": 0.07648183556405354,
"grad_norm": 0.8047032952308655,
"learning_rate": 2.266304347826087e-05,
"loss": 1.4694,
"step": 140
},
{
"epoch": 0.07921332969134116,
"grad_norm": 0.8819392323493958,
"learning_rate": 2.347826086956522e-05,
"loss": 1.4516,
"step": 145
},
{
"epoch": 0.08194482381862879,
"grad_norm": 0.7637084722518921,
"learning_rate": 2.4293478260869566e-05,
"loss": 1.3716,
"step": 150
},
{
"epoch": 0.08467631794591642,
"grad_norm": 0.8421655893325806,
"learning_rate": 2.5108695652173914e-05,
"loss": 1.4497,
"step": 155
},
{
"epoch": 0.08740781207320404,
"grad_norm": 0.7615973949432373,
"learning_rate": 2.592391304347826e-05,
"loss": 1.4217,
"step": 160
},
{
"epoch": 0.09013930620049167,
"grad_norm": 0.8904805779457092,
"learning_rate": 2.673913043478261e-05,
"loss": 1.4529,
"step": 165
},
{
"epoch": 0.0928708003277793,
"grad_norm": 0.7236261367797852,
"learning_rate": 2.7554347826086957e-05,
"loss": 1.369,
"step": 170
},
{
"epoch": 0.09560229445506692,
"grad_norm": 0.7706332802772522,
"learning_rate": 2.8369565217391305e-05,
"loss": 1.3706,
"step": 175
},
{
"epoch": 0.09833378858235454,
"grad_norm": 0.7844731211662292,
"learning_rate": 2.9184782608695653e-05,
"loss": 1.4144,
"step": 180
},
{
"epoch": 0.10106528270964217,
"grad_norm": 0.872904360294342,
"learning_rate": 3e-05,
"loss": 1.2978,
"step": 185
},
{
"epoch": 0.1037967768369298,
"grad_norm": 0.7814828753471375,
"learning_rate": 2.9956871765382405e-05,
"loss": 1.3356,
"step": 190
},
{
"epoch": 0.10652827096421742,
"grad_norm": 0.9173154830932617,
"learning_rate": 2.9913743530764806e-05,
"loss": 1.3388,
"step": 195
},
{
"epoch": 0.10925976509150505,
"grad_norm": 0.8572229743003845,
"learning_rate": 2.987061529614721e-05,
"loss": 1.353,
"step": 200
},
{
"epoch": 0.11199125921879267,
"grad_norm": 0.7920759320259094,
"learning_rate": 2.9827487061529615e-05,
"loss": 1.305,
"step": 205
},
{
"epoch": 0.1147227533460803,
"grad_norm": 0.8120269775390625,
"learning_rate": 2.978435882691202e-05,
"loss": 1.2763,
"step": 210
},
{
"epoch": 0.11745424747336793,
"grad_norm": 0.7644383907318115,
"learning_rate": 2.974123059229442e-05,
"loss": 1.3108,
"step": 215
},
{
"epoch": 0.12018574160065555,
"grad_norm": 0.7263749241828918,
"learning_rate": 2.9698102357676825e-05,
"loss": 1.3364,
"step": 220
},
{
"epoch": 0.12291723572794319,
"grad_norm": 0.7868081331253052,
"learning_rate": 2.965497412305923e-05,
"loss": 1.2965,
"step": 225
},
{
"epoch": 0.12564872985523082,
"grad_norm": 0.7651657462120056,
"learning_rate": 2.9611845888441637e-05,
"loss": 1.3027,
"step": 230
},
{
"epoch": 0.12838022398251844,
"grad_norm": 0.7855558395385742,
"learning_rate": 2.9568717653824038e-05,
"loss": 1.3203,
"step": 235
},
{
"epoch": 0.13111171810980607,
"grad_norm": 0.7353278398513794,
"learning_rate": 2.9525589419206442e-05,
"loss": 1.1794,
"step": 240
},
{
"epoch": 0.1338432122370937,
"grad_norm": 0.9344907999038696,
"learning_rate": 2.9482461184588846e-05,
"loss": 1.2336,
"step": 245
},
{
"epoch": 0.13657470636438132,
"grad_norm": 0.7568232417106628,
"learning_rate": 2.943933294997125e-05,
"loss": 1.3051,
"step": 250
},
{
"epoch": 0.13930620049166895,
"grad_norm": 0.8257033228874207,
"learning_rate": 2.939620471535365e-05,
"loss": 1.2554,
"step": 255
},
{
"epoch": 0.14203769461895657,
"grad_norm": 0.7484506368637085,
"learning_rate": 2.9353076480736056e-05,
"loss": 1.2549,
"step": 260
},
{
"epoch": 0.1447691887462442,
"grad_norm": 0.7581287622451782,
"learning_rate": 2.930994824611846e-05,
"loss": 1.1332,
"step": 265
},
{
"epoch": 0.14750068287353182,
"grad_norm": 0.7606173753738403,
"learning_rate": 2.9266820011500865e-05,
"loss": 1.1799,
"step": 270
},
{
"epoch": 0.15023217700081945,
"grad_norm": 0.8215767741203308,
"learning_rate": 2.9223691776883266e-05,
"loss": 1.1879,
"step": 275
},
{
"epoch": 0.15296367112810708,
"grad_norm": 0.9438003897666931,
"learning_rate": 2.918056354226567e-05,
"loss": 1.1292,
"step": 280
},
{
"epoch": 0.1556951652553947,
"grad_norm": 0.6569656133651733,
"learning_rate": 2.9137435307648074e-05,
"loss": 1.1767,
"step": 285
},
{
"epoch": 0.15842665938268233,
"grad_norm": 0.8340663909912109,
"learning_rate": 2.909430707303048e-05,
"loss": 1.2064,
"step": 290
},
{
"epoch": 0.16115815350996995,
"grad_norm": 0.6959854364395142,
"learning_rate": 2.905117883841288e-05,
"loss": 1.1955,
"step": 295
},
{
"epoch": 0.16388964763725758,
"grad_norm": 0.7269774675369263,
"learning_rate": 2.9008050603795284e-05,
"loss": 1.1903,
"step": 300
},
{
"epoch": 0.16388964763725758,
"eval_loss": 1.2255185842514038,
"eval_runtime": 328.4188,
"eval_samples_per_second": 10.721,
"eval_steps_per_second": 2.683,
"step": 300
},
{
"epoch": 0.1666211417645452,
"grad_norm": 0.724984347820282,
"learning_rate": 2.896492236917769e-05,
"loss": 1.103,
"step": 305
},
{
"epoch": 0.16935263589183283,
"grad_norm": 0.7624502182006836,
"learning_rate": 2.8921794134560093e-05,
"loss": 1.1216,
"step": 310
},
{
"epoch": 0.17208413001912046,
"grad_norm": 0.6501736640930176,
"learning_rate": 2.8878665899942497e-05,
"loss": 1.0736,
"step": 315
},
{
"epoch": 0.17481562414640808,
"grad_norm": 0.7219209671020508,
"learning_rate": 2.88355376653249e-05,
"loss": 1.1018,
"step": 320
},
{
"epoch": 0.1775471182736957,
"grad_norm": 0.6269301176071167,
"learning_rate": 2.8792409430707306e-05,
"loss": 1.1242,
"step": 325
},
{
"epoch": 0.18027861240098333,
"grad_norm": 0.785416305065155,
"learning_rate": 2.8749281196089707e-05,
"loss": 1.0851,
"step": 330
},
{
"epoch": 0.18301010652827096,
"grad_norm": 0.7034997344017029,
"learning_rate": 2.870615296147211e-05,
"loss": 1.1384,
"step": 335
},
{
"epoch": 0.1857416006555586,
"grad_norm": 0.8468294739723206,
"learning_rate": 2.8663024726854516e-05,
"loss": 1.1302,
"step": 340
},
{
"epoch": 0.1884730947828462,
"grad_norm": 0.7820891737937927,
"learning_rate": 2.861989649223692e-05,
"loss": 1.0532,
"step": 345
},
{
"epoch": 0.19120458891013384,
"grad_norm": 0.8448447585105896,
"learning_rate": 2.857676825761932e-05,
"loss": 1.2118,
"step": 350
},
{
"epoch": 0.19393608303742146,
"grad_norm": 0.6977779269218445,
"learning_rate": 2.8533640023001725e-05,
"loss": 1.1829,
"step": 355
},
{
"epoch": 0.1966675771647091,
"grad_norm": 0.6859474778175354,
"learning_rate": 2.849051178838413e-05,
"loss": 0.9995,
"step": 360
},
{
"epoch": 0.19939907129199672,
"grad_norm": 0.7476114630699158,
"learning_rate": 2.8447383553766534e-05,
"loss": 1.0597,
"step": 365
},
{
"epoch": 0.20213056541928434,
"grad_norm": 0.7813637852668762,
"learning_rate": 2.8404255319148935e-05,
"loss": 1.1079,
"step": 370
},
{
"epoch": 0.20486205954657197,
"grad_norm": 0.8648521304130554,
"learning_rate": 2.836112708453134e-05,
"loss": 1.1522,
"step": 375
},
{
"epoch": 0.2075935536738596,
"grad_norm": 0.7016454339027405,
"learning_rate": 2.8317998849913744e-05,
"loss": 1.0281,
"step": 380
},
{
"epoch": 0.21032504780114722,
"grad_norm": 0.6951316595077515,
"learning_rate": 2.8274870615296148e-05,
"loss": 1.1146,
"step": 385
},
{
"epoch": 0.21305654192843484,
"grad_norm": 0.7843300700187683,
"learning_rate": 2.823174238067855e-05,
"loss": 1.1078,
"step": 390
},
{
"epoch": 0.21578803605572247,
"grad_norm": 0.7950036525726318,
"learning_rate": 2.8188614146060953e-05,
"loss": 1.0833,
"step": 395
},
{
"epoch": 0.2185195301830101,
"grad_norm": 0.7733429074287415,
"learning_rate": 2.814548591144336e-05,
"loss": 1.1077,
"step": 400
},
{
"epoch": 0.22125102431029772,
"grad_norm": 0.813205897808075,
"learning_rate": 2.8102357676825766e-05,
"loss": 1.1326,
"step": 405
},
{
"epoch": 0.22398251843758535,
"grad_norm": 0.7515183687210083,
"learning_rate": 2.8059229442208166e-05,
"loss": 1.0858,
"step": 410
},
{
"epoch": 0.22671401256487297,
"grad_norm": 0.775006890296936,
"learning_rate": 2.801610120759057e-05,
"loss": 1.1325,
"step": 415
},
{
"epoch": 0.2294455066921606,
"grad_norm": 0.7226970195770264,
"learning_rate": 2.7972972972972975e-05,
"loss": 1.113,
"step": 420
},
{
"epoch": 0.23217700081944823,
"grad_norm": 0.803119421005249,
"learning_rate": 2.792984473835538e-05,
"loss": 1.0701,
"step": 425
},
{
"epoch": 0.23490849494673585,
"grad_norm": 0.7977150678634644,
"learning_rate": 2.788671650373778e-05,
"loss": 1.1111,
"step": 430
},
{
"epoch": 0.23763998907402348,
"grad_norm": 0.7857878804206848,
"learning_rate": 2.7843588269120185e-05,
"loss": 1.0683,
"step": 435
},
{
"epoch": 0.2403714832013111,
"grad_norm": 0.7843796610832214,
"learning_rate": 2.780046003450259e-05,
"loss": 1.122,
"step": 440
},
{
"epoch": 0.24310297732859876,
"grad_norm": 0.7460730075836182,
"learning_rate": 2.775733179988499e-05,
"loss": 1.0579,
"step": 445
},
{
"epoch": 0.24583447145588638,
"grad_norm": 0.6824869513511658,
"learning_rate": 2.7714203565267395e-05,
"loss": 1.0787,
"step": 450
},
{
"epoch": 0.248565965583174,
"grad_norm": 0.6470029950141907,
"learning_rate": 2.76710753306498e-05,
"loss": 1.0975,
"step": 455
},
{
"epoch": 0.25129745971046163,
"grad_norm": 0.7347692847251892,
"learning_rate": 2.7627947096032203e-05,
"loss": 1.1854,
"step": 460
},
{
"epoch": 0.25402895383774926,
"grad_norm": 0.8426661491394043,
"learning_rate": 2.7584818861414604e-05,
"loss": 1.0489,
"step": 465
},
{
"epoch": 0.2567604479650369,
"grad_norm": 0.7579281330108643,
"learning_rate": 2.754169062679701e-05,
"loss": 1.0804,
"step": 470
},
{
"epoch": 0.2594919420923245,
"grad_norm": 0.8320958018302917,
"learning_rate": 2.7498562392179413e-05,
"loss": 1.1259,
"step": 475
},
{
"epoch": 0.26222343621961214,
"grad_norm": 0.8479028940200806,
"learning_rate": 2.7455434157561817e-05,
"loss": 1.0846,
"step": 480
},
{
"epoch": 0.26495493034689976,
"grad_norm": 0.7769616842269897,
"learning_rate": 2.7412305922944222e-05,
"loss": 1.0907,
"step": 485
},
{
"epoch": 0.2676864244741874,
"grad_norm": 0.6947383880615234,
"learning_rate": 2.7369177688326626e-05,
"loss": 1.0606,
"step": 490
},
{
"epoch": 0.270417918601475,
"grad_norm": 0.6838494539260864,
"learning_rate": 2.732604945370903e-05,
"loss": 1.0027,
"step": 495
},
{
"epoch": 0.27314941272876264,
"grad_norm": 0.7338347434997559,
"learning_rate": 2.7282921219091435e-05,
"loss": 1.0859,
"step": 500
},
{
"epoch": 0.27588090685605027,
"grad_norm": 0.7138042449951172,
"learning_rate": 2.7239792984473836e-05,
"loss": 1.0208,
"step": 505
},
{
"epoch": 0.2786124009833379,
"grad_norm": 0.8377683162689209,
"learning_rate": 2.719666474985624e-05,
"loss": 1.1176,
"step": 510
},
{
"epoch": 0.2813438951106255,
"grad_norm": 0.817639172077179,
"learning_rate": 2.7153536515238644e-05,
"loss": 1.1092,
"step": 515
},
{
"epoch": 0.28407538923791315,
"grad_norm": 0.7524867057800293,
"learning_rate": 2.711040828062105e-05,
"loss": 1.07,
"step": 520
},
{
"epoch": 0.28680688336520077,
"grad_norm": 0.7723881006240845,
"learning_rate": 2.706728004600345e-05,
"loss": 1.0319,
"step": 525
},
{
"epoch": 0.2895383774924884,
"grad_norm": 0.688042163848877,
"learning_rate": 2.7024151811385854e-05,
"loss": 1.0426,
"step": 530
},
{
"epoch": 0.292269871619776,
"grad_norm": 0.7268008589744568,
"learning_rate": 2.698102357676826e-05,
"loss": 1.0404,
"step": 535
},
{
"epoch": 0.29500136574706365,
"grad_norm": 0.6592392325401306,
"learning_rate": 2.6937895342150663e-05,
"loss": 1.0363,
"step": 540
},
{
"epoch": 0.2977328598743513,
"grad_norm": 0.694995641708374,
"learning_rate": 2.6894767107533064e-05,
"loss": 1.1075,
"step": 545
},
{
"epoch": 0.3004643540016389,
"grad_norm": 0.8423897624015808,
"learning_rate": 2.6851638872915468e-05,
"loss": 1.0985,
"step": 550
},
{
"epoch": 0.3031958481289265,
"grad_norm": 0.6766981482505798,
"learning_rate": 2.6808510638297873e-05,
"loss": 1.0216,
"step": 555
},
{
"epoch": 0.30592734225621415,
"grad_norm": 0.7330387830734253,
"learning_rate": 2.6765382403680274e-05,
"loss": 1.0111,
"step": 560
},
{
"epoch": 0.3086588363835018,
"grad_norm": 0.7680959105491638,
"learning_rate": 2.672225416906268e-05,
"loss": 1.0391,
"step": 565
},
{
"epoch": 0.3113903305107894,
"grad_norm": 0.8362131118774414,
"learning_rate": 2.6679125934445086e-05,
"loss": 1.0963,
"step": 570
},
{
"epoch": 0.31412182463807703,
"grad_norm": 0.9484680891036987,
"learning_rate": 2.663599769982749e-05,
"loss": 1.0853,
"step": 575
},
{
"epoch": 0.31685331876536466,
"grad_norm": 0.7578262090682983,
"learning_rate": 2.659286946520989e-05,
"loss": 1.0243,
"step": 580
},
{
"epoch": 0.3195848128926523,
"grad_norm": 0.7981600165367126,
"learning_rate": 2.6549741230592295e-05,
"loss": 1.0074,
"step": 585
},
{
"epoch": 0.3223163070199399,
"grad_norm": 0.7634698748588562,
"learning_rate": 2.65066129959747e-05,
"loss": 1.0407,
"step": 590
},
{
"epoch": 0.32504780114722753,
"grad_norm": 0.7340299487113953,
"learning_rate": 2.6463484761357104e-05,
"loss": 1.0205,
"step": 595
},
{
"epoch": 0.32777929527451516,
"grad_norm": 0.7297033667564392,
"learning_rate": 2.6420356526739505e-05,
"loss": 1.1023,
"step": 600
},
{
"epoch": 0.32777929527451516,
"eval_loss": 1.0993021726608276,
"eval_runtime": 306.2283,
"eval_samples_per_second": 11.498,
"eval_steps_per_second": 2.877,
"step": 600
},
{
"epoch": 0.3305107894018028,
"grad_norm": 0.645929217338562,
"learning_rate": 2.637722829212191e-05,
"loss": 0.9895,
"step": 605
},
{
"epoch": 0.3332422835290904,
"grad_norm": 0.7104042768478394,
"learning_rate": 2.6334100057504314e-05,
"loss": 1.0063,
"step": 610
},
{
"epoch": 0.33597377765637804,
"grad_norm": 0.7610509395599365,
"learning_rate": 2.6290971822886718e-05,
"loss": 0.9546,
"step": 615
},
{
"epoch": 0.33870527178366566,
"grad_norm": 0.7508594989776611,
"learning_rate": 2.624784358826912e-05,
"loss": 0.9908,
"step": 620
},
{
"epoch": 0.3414367659109533,
"grad_norm": 0.7074321508407593,
"learning_rate": 2.6204715353651523e-05,
"loss": 1.0301,
"step": 625
},
{
"epoch": 0.3441682600382409,
"grad_norm": 0.7267704010009766,
"learning_rate": 2.6161587119033928e-05,
"loss": 1.0927,
"step": 630
},
{
"epoch": 0.34689975416552854,
"grad_norm": 0.6761760711669922,
"learning_rate": 2.6118458884416332e-05,
"loss": 0.9735,
"step": 635
},
{
"epoch": 0.34963124829281617,
"grad_norm": 0.7219847440719604,
"learning_rate": 2.6075330649798733e-05,
"loss": 1.0233,
"step": 640
},
{
"epoch": 0.3523627424201038,
"grad_norm": 0.753565788269043,
"learning_rate": 2.6032202415181138e-05,
"loss": 1.0658,
"step": 645
},
{
"epoch": 0.3550942365473914,
"grad_norm": 0.7490048408508301,
"learning_rate": 2.5989074180563545e-05,
"loss": 1.0668,
"step": 650
},
{
"epoch": 0.35782573067467904,
"grad_norm": 0.7493592500686646,
"learning_rate": 2.594594594594595e-05,
"loss": 0.9936,
"step": 655
},
{
"epoch": 0.36055722480196667,
"grad_norm": 0.7734257578849792,
"learning_rate": 2.590281771132835e-05,
"loss": 0.9868,
"step": 660
},
{
"epoch": 0.3632887189292543,
"grad_norm": 0.7188918590545654,
"learning_rate": 2.5859689476710755e-05,
"loss": 0.9771,
"step": 665
},
{
"epoch": 0.3660202130565419,
"grad_norm": 0.7556160688400269,
"learning_rate": 2.581656124209316e-05,
"loss": 1.0392,
"step": 670
},
{
"epoch": 0.36875170718382955,
"grad_norm": 0.5352792739868164,
"learning_rate": 2.577343300747556e-05,
"loss": 0.941,
"step": 675
},
{
"epoch": 0.3714832013111172,
"grad_norm": 0.6794752478599548,
"learning_rate": 2.5730304772857965e-05,
"loss": 1.078,
"step": 680
},
{
"epoch": 0.3742146954384048,
"grad_norm": 0.7562423348426819,
"learning_rate": 2.568717653824037e-05,
"loss": 0.9774,
"step": 685
},
{
"epoch": 0.3769461895656924,
"grad_norm": 0.7022319436073303,
"learning_rate": 2.5644048303622773e-05,
"loss": 0.9832,
"step": 690
},
{
"epoch": 0.37967768369298005,
"grad_norm": 0.771272599697113,
"learning_rate": 2.5600920069005174e-05,
"loss": 1.0179,
"step": 695
},
{
"epoch": 0.3824091778202677,
"grad_norm": 0.6900454163551331,
"learning_rate": 2.555779183438758e-05,
"loss": 0.9452,
"step": 700
},
{
"epoch": 0.3851406719475553,
"grad_norm": 0.7504772543907166,
"learning_rate": 2.5514663599769983e-05,
"loss": 0.9733,
"step": 705
},
{
"epoch": 0.38787216607484293,
"grad_norm": 0.8242804408073425,
"learning_rate": 2.5471535365152387e-05,
"loss": 1.0468,
"step": 710
},
{
"epoch": 0.39060366020213055,
"grad_norm": 0.7705220580101013,
"learning_rate": 2.542840713053479e-05,
"loss": 1.0101,
"step": 715
},
{
"epoch": 0.3933351543294182,
"grad_norm": 0.7174106240272522,
"learning_rate": 2.5385278895917193e-05,
"loss": 0.9818,
"step": 720
},
{
"epoch": 0.3960666484567058,
"grad_norm": 0.7383962273597717,
"learning_rate": 2.5342150661299597e-05,
"loss": 1.0289,
"step": 725
},
{
"epoch": 0.39879814258399343,
"grad_norm": 0.6323188543319702,
"learning_rate": 2.5299022426682e-05,
"loss": 0.9597,
"step": 730
},
{
"epoch": 0.40152963671128106,
"grad_norm": 0.825609028339386,
"learning_rate": 2.5255894192064406e-05,
"loss": 0.978,
"step": 735
},
{
"epoch": 0.4042611308385687,
"grad_norm": 0.7169507741928101,
"learning_rate": 2.521276595744681e-05,
"loss": 0.9965,
"step": 740
},
{
"epoch": 0.4069926249658563,
"grad_norm": 0.7201241254806519,
"learning_rate": 2.5169637722829215e-05,
"loss": 1.0158,
"step": 745
},
{
"epoch": 0.40972411909314393,
"grad_norm": 0.7305246591567993,
"learning_rate": 2.512650948821162e-05,
"loss": 1.0034,
"step": 750
},
{
"epoch": 0.41245561322043156,
"grad_norm": 0.66969895362854,
"learning_rate": 2.508338125359402e-05,
"loss": 1.0505,
"step": 755
},
{
"epoch": 0.4151871073477192,
"grad_norm": 0.6087076663970947,
"learning_rate": 2.5040253018976424e-05,
"loss": 0.9876,
"step": 760
},
{
"epoch": 0.4179186014750068,
"grad_norm": 0.740016520023346,
"learning_rate": 2.499712478435883e-05,
"loss": 1.0002,
"step": 765
},
{
"epoch": 0.42065009560229444,
"grad_norm": 0.6993871331214905,
"learning_rate": 2.4953996549741233e-05,
"loss": 0.9828,
"step": 770
},
{
"epoch": 0.42338158972958206,
"grad_norm": 0.6651398539543152,
"learning_rate": 2.4910868315123634e-05,
"loss": 1.0651,
"step": 775
},
{
"epoch": 0.4261130838568697,
"grad_norm": 0.7585716247558594,
"learning_rate": 2.4867740080506038e-05,
"loss": 1.0542,
"step": 780
},
{
"epoch": 0.4288445779841573,
"grad_norm": 0.8134998679161072,
"learning_rate": 2.4824611845888443e-05,
"loss": 0.9729,
"step": 785
},
{
"epoch": 0.43157607211144494,
"grad_norm": 0.784631073474884,
"learning_rate": 2.4781483611270847e-05,
"loss": 0.9971,
"step": 790
},
{
"epoch": 0.43430756623873257,
"grad_norm": 0.8132376670837402,
"learning_rate": 2.4738355376653248e-05,
"loss": 0.9859,
"step": 795
},
{
"epoch": 0.4370390603660202,
"grad_norm": 0.6785438656806946,
"learning_rate": 2.4695227142035652e-05,
"loss": 0.9933,
"step": 800
},
{
"epoch": 0.4397705544933078,
"grad_norm": 0.7485066056251526,
"learning_rate": 2.4652098907418057e-05,
"loss": 1.0549,
"step": 805
},
{
"epoch": 0.44250204862059545,
"grad_norm": 0.626559853553772,
"learning_rate": 2.4608970672800458e-05,
"loss": 0.8987,
"step": 810
},
{
"epoch": 0.44523354274788307,
"grad_norm": 0.6525225639343262,
"learning_rate": 2.4565842438182862e-05,
"loss": 1.0055,
"step": 815
},
{
"epoch": 0.4479650368751707,
"grad_norm": 0.723646879196167,
"learning_rate": 2.452271420356527e-05,
"loss": 0.9561,
"step": 820
},
{
"epoch": 0.4506965310024583,
"grad_norm": 0.6696566343307495,
"learning_rate": 2.4479585968947674e-05,
"loss": 0.9626,
"step": 825
},
{
"epoch": 0.45342802512974595,
"grad_norm": 0.6937575936317444,
"learning_rate": 2.4436457734330075e-05,
"loss": 0.9679,
"step": 830
},
{
"epoch": 0.4561595192570336,
"grad_norm": 0.7571921944618225,
"learning_rate": 2.439332949971248e-05,
"loss": 1.0327,
"step": 835
},
{
"epoch": 0.4588910133843212,
"grad_norm": 0.7212653160095215,
"learning_rate": 2.4350201265094884e-05,
"loss": 0.9714,
"step": 840
},
{
"epoch": 0.4616225075116088,
"grad_norm": 0.6409651041030884,
"learning_rate": 2.4307073030477288e-05,
"loss": 1.0007,
"step": 845
},
{
"epoch": 0.46435400163889645,
"grad_norm": 0.7958700656890869,
"learning_rate": 2.426394479585969e-05,
"loss": 1.0335,
"step": 850
},
{
"epoch": 0.4670854957661841,
"grad_norm": 0.7226616740226746,
"learning_rate": 2.4220816561242094e-05,
"loss": 0.982,
"step": 855
},
{
"epoch": 0.4698169898934717,
"grad_norm": 0.6726953387260437,
"learning_rate": 2.4177688326624498e-05,
"loss": 0.9823,
"step": 860
},
{
"epoch": 0.47254848402075933,
"grad_norm": 0.7555478811264038,
"learning_rate": 2.4134560092006902e-05,
"loss": 0.9672,
"step": 865
},
{
"epoch": 0.47527997814804696,
"grad_norm": 0.8764699697494507,
"learning_rate": 2.4091431857389303e-05,
"loss": 0.9728,
"step": 870
},
{
"epoch": 0.4780114722753346,
"grad_norm": 0.8067215085029602,
"learning_rate": 2.4048303622771708e-05,
"loss": 1.0206,
"step": 875
},
{
"epoch": 0.4807429664026222,
"grad_norm": 0.7664445638656616,
"learning_rate": 2.4005175388154112e-05,
"loss": 0.9477,
"step": 880
},
{
"epoch": 0.48347446052990983,
"grad_norm": 0.7092654705047607,
"learning_rate": 2.3962047153536516e-05,
"loss": 1.0208,
"step": 885
},
{
"epoch": 0.4862059546571975,
"grad_norm": 0.6885917782783508,
"learning_rate": 2.3918918918918917e-05,
"loss": 1.0035,
"step": 890
},
{
"epoch": 0.48893744878448514,
"grad_norm": 0.7531325221061707,
"learning_rate": 2.387579068430132e-05,
"loss": 0.9716,
"step": 895
},
{
"epoch": 0.49166894291177277,
"grad_norm": 0.7733385562896729,
"learning_rate": 2.3832662449683726e-05,
"loss": 1.0056,
"step": 900
},
{
"epoch": 0.49166894291177277,
"eval_loss": 1.0448055267333984,
"eval_runtime": 307.1158,
"eval_samples_per_second": 11.465,
"eval_steps_per_second": 2.869,
"step": 900
},
{
"epoch": 0.4944004370390604,
"grad_norm": 0.8963056802749634,
"learning_rate": 2.3789534215066134e-05,
"loss": 0.9844,
"step": 905
},
{
"epoch": 0.497131931166348,
"grad_norm": 0.820163905620575,
"learning_rate": 2.3746405980448535e-05,
"loss": 1.0478,
"step": 910
},
{
"epoch": 0.49986342529363564,
"grad_norm": 0.6968187689781189,
"learning_rate": 2.370327774583094e-05,
"loss": 0.9435,
"step": 915
},
{
"epoch": 0.5025949194209233,
"grad_norm": 0.7683607339859009,
"learning_rate": 2.3660149511213343e-05,
"loss": 1.0467,
"step": 920
},
{
"epoch": 0.5053264135482108,
"grad_norm": 0.8514032959938049,
"learning_rate": 2.3617021276595744e-05,
"loss": 1.0109,
"step": 925
},
{
"epoch": 0.5080579076754985,
"grad_norm": 0.7920552492141724,
"learning_rate": 2.357389304197815e-05,
"loss": 0.9999,
"step": 930
},
{
"epoch": 0.5107894018027861,
"grad_norm": 0.6363257765769958,
"learning_rate": 2.3530764807360553e-05,
"loss": 0.963,
"step": 935
},
{
"epoch": 0.5135208959300738,
"grad_norm": 0.7315125465393066,
"learning_rate": 2.3487636572742957e-05,
"loss": 0.9841,
"step": 940
},
{
"epoch": 0.5162523900573613,
"grad_norm": 0.756065845489502,
"learning_rate": 2.344450833812536e-05,
"loss": 0.9945,
"step": 945
},
{
"epoch": 0.518983884184649,
"grad_norm": 0.7601234912872314,
"learning_rate": 2.3401380103507763e-05,
"loss": 0.9914,
"step": 950
},
{
"epoch": 0.5217153783119366,
"grad_norm": 0.7508507370948792,
"learning_rate": 2.3358251868890167e-05,
"loss": 0.9712,
"step": 955
},
{
"epoch": 0.5244468724392243,
"grad_norm": 0.768269419670105,
"learning_rate": 2.331512363427257e-05,
"loss": 1.0563,
"step": 960
},
{
"epoch": 0.5271783665665118,
"grad_norm": 0.6745092868804932,
"learning_rate": 2.3271995399654973e-05,
"loss": 0.9691,
"step": 965
},
{
"epoch": 0.5299098606937995,
"grad_norm": 0.7175255417823792,
"learning_rate": 2.3228867165037377e-05,
"loss": 0.9945,
"step": 970
},
{
"epoch": 0.5326413548210871,
"grad_norm": 0.7807250022888184,
"learning_rate": 2.318573893041978e-05,
"loss": 0.9538,
"step": 975
},
{
"epoch": 0.5353728489483748,
"grad_norm": 0.6616771221160889,
"learning_rate": 2.3142610695802186e-05,
"loss": 0.9973,
"step": 980
},
{
"epoch": 0.5381043430756624,
"grad_norm": 0.7407675981521606,
"learning_rate": 2.3099482461184587e-05,
"loss": 1.0041,
"step": 985
},
{
"epoch": 0.54083583720295,
"grad_norm": 0.7497495412826538,
"learning_rate": 2.3056354226566994e-05,
"loss": 0.9286,
"step": 990
},
{
"epoch": 0.5435673313302376,
"grad_norm": 0.6467530727386475,
"learning_rate": 2.30132259919494e-05,
"loss": 0.9433,
"step": 995
},
{
"epoch": 0.5462988254575253,
"grad_norm": 0.6888414621353149,
"learning_rate": 2.2970097757331803e-05,
"loss": 0.9507,
"step": 1000
},
{
"epoch": 0.5490303195848129,
"grad_norm": 0.8949408531188965,
"learning_rate": 2.2926969522714204e-05,
"loss": 0.9643,
"step": 1005
},
{
"epoch": 0.5517618137121005,
"grad_norm": 0.7237836122512817,
"learning_rate": 2.288384128809661e-05,
"loss": 0.917,
"step": 1010
},
{
"epoch": 0.5544933078393881,
"grad_norm": 0.6691592931747437,
"learning_rate": 2.2840713053479013e-05,
"loss": 0.999,
"step": 1015
},
{
"epoch": 0.5572248019666758,
"grad_norm": 0.7884166836738586,
"learning_rate": 2.2797584818861417e-05,
"loss": 0.9466,
"step": 1020
},
{
"epoch": 0.5599562960939634,
"grad_norm": 0.7341962456703186,
"learning_rate": 2.2754456584243818e-05,
"loss": 0.9567,
"step": 1025
},
{
"epoch": 0.562687790221251,
"grad_norm": 0.6674230098724365,
"learning_rate": 2.2711328349626222e-05,
"loss": 0.9487,
"step": 1030
},
{
"epoch": 0.5654192843485386,
"grad_norm": 0.6951179504394531,
"learning_rate": 2.2668200115008627e-05,
"loss": 0.9885,
"step": 1035
},
{
"epoch": 0.5681507784758263,
"grad_norm": 0.7464187741279602,
"learning_rate": 2.262507188039103e-05,
"loss": 0.9503,
"step": 1040
},
{
"epoch": 0.5708822726031139,
"grad_norm": 0.69831383228302,
"learning_rate": 2.2581943645773432e-05,
"loss": 0.9567,
"step": 1045
},
{
"epoch": 0.5736137667304015,
"grad_norm": 0.6780604720115662,
"learning_rate": 2.2538815411155836e-05,
"loss": 0.975,
"step": 1050
},
{
"epoch": 0.5763452608576891,
"grad_norm": 0.7216975688934326,
"learning_rate": 2.249568717653824e-05,
"loss": 0.9948,
"step": 1055
},
{
"epoch": 0.5790767549849768,
"grad_norm": 0.7621845006942749,
"learning_rate": 2.2452558941920642e-05,
"loss": 0.9995,
"step": 1060
},
{
"epoch": 0.5818082491122644,
"grad_norm": 0.7196091413497925,
"learning_rate": 2.2409430707303046e-05,
"loss": 1.0007,
"step": 1065
},
{
"epoch": 0.584539743239552,
"grad_norm": 0.6992865204811096,
"learning_rate": 2.236630247268545e-05,
"loss": 0.9363,
"step": 1070
},
{
"epoch": 0.5872712373668396,
"grad_norm": 0.6687476634979248,
"learning_rate": 2.2323174238067858e-05,
"loss": 1.0072,
"step": 1075
},
{
"epoch": 0.5900027314941273,
"grad_norm": 0.7828387022018433,
"learning_rate": 2.228004600345026e-05,
"loss": 0.994,
"step": 1080
},
{
"epoch": 0.5927342256214149,
"grad_norm": 0.7133594751358032,
"learning_rate": 2.2236917768832664e-05,
"loss": 0.8923,
"step": 1085
},
{
"epoch": 0.5954657197487025,
"grad_norm": 0.7610213160514832,
"learning_rate": 2.2193789534215068e-05,
"loss": 0.9855,
"step": 1090
},
{
"epoch": 0.5981972138759901,
"grad_norm": 0.8042429089546204,
"learning_rate": 2.2150661299597472e-05,
"loss": 0.8981,
"step": 1095
},
{
"epoch": 0.6009287080032778,
"grad_norm": 0.7705995440483093,
"learning_rate": 2.2107533064979873e-05,
"loss": 1.0007,
"step": 1100
},
{
"epoch": 0.6036602021305654,
"grad_norm": 0.8342954516410828,
"learning_rate": 2.2064404830362278e-05,
"loss": 0.9614,
"step": 1105
},
{
"epoch": 0.606391696257853,
"grad_norm": 0.7102698087692261,
"learning_rate": 2.2021276595744682e-05,
"loss": 0.9482,
"step": 1110
},
{
"epoch": 0.6091231903851406,
"grad_norm": 0.686964750289917,
"learning_rate": 2.1978148361127086e-05,
"loss": 0.9045,
"step": 1115
},
{
"epoch": 0.6118546845124283,
"grad_norm": 0.8660001158714294,
"learning_rate": 2.1935020126509487e-05,
"loss": 0.9551,
"step": 1120
},
{
"epoch": 0.6145861786397159,
"grad_norm": 0.689612090587616,
"learning_rate": 2.1891891891891892e-05,
"loss": 0.9795,
"step": 1125
},
{
"epoch": 0.6173176727670036,
"grad_norm": 0.7324284315109253,
"learning_rate": 2.1848763657274296e-05,
"loss": 0.9707,
"step": 1130
},
{
"epoch": 0.6200491668942911,
"grad_norm": 0.7044214010238647,
"learning_rate": 2.18056354226567e-05,
"loss": 0.9864,
"step": 1135
},
{
"epoch": 0.6227806610215788,
"grad_norm": 0.6462258696556091,
"learning_rate": 2.17625071880391e-05,
"loss": 0.9469,
"step": 1140
},
{
"epoch": 0.6255121551488664,
"grad_norm": 0.7109295129776001,
"learning_rate": 2.1719378953421506e-05,
"loss": 0.8984,
"step": 1145
},
{
"epoch": 0.6282436492761541,
"grad_norm": 0.5951446890830994,
"learning_rate": 2.167625071880391e-05,
"loss": 0.9383,
"step": 1150
},
{
"epoch": 0.6309751434034416,
"grad_norm": 0.7271871566772461,
"learning_rate": 2.1633122484186314e-05,
"loss": 0.9713,
"step": 1155
},
{
"epoch": 0.6337066375307293,
"grad_norm": 0.6672769784927368,
"learning_rate": 2.158999424956872e-05,
"loss": 0.9567,
"step": 1160
},
{
"epoch": 0.6364381316580169,
"grad_norm": 0.6343885064125061,
"learning_rate": 2.1546866014951123e-05,
"loss": 0.9575,
"step": 1165
},
{
"epoch": 0.6391696257853046,
"grad_norm": 0.6709259748458862,
"learning_rate": 2.1503737780333528e-05,
"loss": 0.9778,
"step": 1170
},
{
"epoch": 0.6419011199125921,
"grad_norm": 0.7463548183441162,
"learning_rate": 2.146060954571593e-05,
"loss": 0.9363,
"step": 1175
},
{
"epoch": 0.6446326140398798,
"grad_norm": 0.7336212396621704,
"learning_rate": 2.1417481311098333e-05,
"loss": 0.9984,
"step": 1180
},
{
"epoch": 0.6473641081671675,
"grad_norm": 0.7141072154045105,
"learning_rate": 2.1374353076480737e-05,
"loss": 0.959,
"step": 1185
},
{
"epoch": 0.6500956022944551,
"grad_norm": 0.7275980710983276,
"learning_rate": 2.133122484186314e-05,
"loss": 1.0157,
"step": 1190
},
{
"epoch": 0.6528270964217427,
"grad_norm": 0.7292263507843018,
"learning_rate": 2.1288096607245543e-05,
"loss": 0.9455,
"step": 1195
},
{
"epoch": 0.6555585905490303,
"grad_norm": 0.7778198719024658,
"learning_rate": 2.1244968372627947e-05,
"loss": 0.9972,
"step": 1200
},
{
"epoch": 0.6555585905490303,
"eval_loss": 1.0104354619979858,
"eval_runtime": 306.0261,
"eval_samples_per_second": 11.506,
"eval_steps_per_second": 2.879,
"step": 1200
},
{
"epoch": 0.658290084676318,
"grad_norm": 0.765852689743042,
"learning_rate": 2.120184013801035e-05,
"loss": 0.91,
"step": 1205
},
{
"epoch": 0.6610215788036056,
"grad_norm": 0.7371508479118347,
"learning_rate": 2.1158711903392756e-05,
"loss": 0.9148,
"step": 1210
},
{
"epoch": 0.6637530729308933,
"grad_norm": 0.6820752024650574,
"learning_rate": 2.1115583668775157e-05,
"loss": 0.9403,
"step": 1215
},
{
"epoch": 0.6664845670581808,
"grad_norm": 0.6960161924362183,
"learning_rate": 2.107245543415756e-05,
"loss": 0.8883,
"step": 1220
},
{
"epoch": 0.6692160611854685,
"grad_norm": 0.7612309455871582,
"learning_rate": 2.1029327199539965e-05,
"loss": 0.9822,
"step": 1225
},
{
"epoch": 0.6719475553127561,
"grad_norm": 0.7078716158866882,
"learning_rate": 2.098619896492237e-05,
"loss": 0.9557,
"step": 1230
},
{
"epoch": 0.6746790494400438,
"grad_norm": 0.8086084723472595,
"learning_rate": 2.094307073030477e-05,
"loss": 0.99,
"step": 1235
},
{
"epoch": 0.6774105435673313,
"grad_norm": 0.7762773036956787,
"learning_rate": 2.0899942495687175e-05,
"loss": 0.928,
"step": 1240
},
{
"epoch": 0.680142037694619,
"grad_norm": 0.7032769918441772,
"learning_rate": 2.0856814261069583e-05,
"loss": 0.925,
"step": 1245
},
{
"epoch": 0.6828735318219066,
"grad_norm": 0.7651206254959106,
"learning_rate": 2.0813686026451987e-05,
"loss": 1.0394,
"step": 1250
},
{
"epoch": 0.6856050259491943,
"grad_norm": 0.692830502986908,
"learning_rate": 2.0770557791834388e-05,
"loss": 1.0109,
"step": 1255
},
{
"epoch": 0.6883365200764818,
"grad_norm": 0.7856961488723755,
"learning_rate": 2.0727429557216792e-05,
"loss": 0.9447,
"step": 1260
},
{
"epoch": 0.6910680142037695,
"grad_norm": 0.6694244146347046,
"learning_rate": 2.0684301322599197e-05,
"loss": 0.9449,
"step": 1265
},
{
"epoch": 0.6937995083310571,
"grad_norm": 0.7393211126327515,
"learning_rate": 2.06411730879816e-05,
"loss": 0.919,
"step": 1270
},
{
"epoch": 0.6965310024583448,
"grad_norm": 0.6926017999649048,
"learning_rate": 2.0598044853364002e-05,
"loss": 0.9542,
"step": 1275
},
{
"epoch": 0.6992624965856323,
"grad_norm": 0.7787449955940247,
"learning_rate": 2.0554916618746407e-05,
"loss": 0.9872,
"step": 1280
},
{
"epoch": 0.70199399071292,
"grad_norm": 0.6585371494293213,
"learning_rate": 2.051178838412881e-05,
"loss": 0.9076,
"step": 1285
},
{
"epoch": 0.7047254848402076,
"grad_norm": 0.8140162825584412,
"learning_rate": 2.0468660149511212e-05,
"loss": 0.9859,
"step": 1290
},
{
"epoch": 0.7074569789674953,
"grad_norm": 0.7256448268890381,
"learning_rate": 2.0425531914893616e-05,
"loss": 0.9495,
"step": 1295
},
{
"epoch": 0.7101884730947828,
"grad_norm": 0.704347550868988,
"learning_rate": 2.038240368027602e-05,
"loss": 0.9382,
"step": 1300
},
{
"epoch": 0.7129199672220705,
"grad_norm": 0.7334429621696472,
"learning_rate": 2.0339275445658425e-05,
"loss": 1.0537,
"step": 1305
},
{
"epoch": 0.7156514613493581,
"grad_norm": 0.7472988367080688,
"learning_rate": 2.0296147211040826e-05,
"loss": 0.9578,
"step": 1310
},
{
"epoch": 0.7183829554766458,
"grad_norm": 0.7188481688499451,
"learning_rate": 2.025301897642323e-05,
"loss": 0.9126,
"step": 1315
},
{
"epoch": 0.7211144496039333,
"grad_norm": 0.6989107131958008,
"learning_rate": 2.0209890741805635e-05,
"loss": 0.9151,
"step": 1320
},
{
"epoch": 0.723845943731221,
"grad_norm": 0.7198164463043213,
"learning_rate": 2.0166762507188042e-05,
"loss": 1.0286,
"step": 1325
},
{
"epoch": 0.7265774378585086,
"grad_norm": 0.6929178237915039,
"learning_rate": 2.0123634272570443e-05,
"loss": 0.9355,
"step": 1330
},
{
"epoch": 0.7293089319857963,
"grad_norm": 0.7612504363059998,
"learning_rate": 2.0080506037952848e-05,
"loss": 0.9146,
"step": 1335
},
{
"epoch": 0.7320404261130838,
"grad_norm": 0.7512226104736328,
"learning_rate": 2.0037377803335252e-05,
"loss": 0.9341,
"step": 1340
},
{
"epoch": 0.7347719202403715,
"grad_norm": 0.6576052904129028,
"learning_rate": 1.9994249568717656e-05,
"loss": 0.9835,
"step": 1345
},
{
"epoch": 0.7375034143676591,
"grad_norm": 0.6750711798667908,
"learning_rate": 1.9951121334100057e-05,
"loss": 0.9306,
"step": 1350
},
{
"epoch": 0.7402349084949468,
"grad_norm": 0.7277622222900391,
"learning_rate": 1.9907993099482462e-05,
"loss": 0.9277,
"step": 1355
},
{
"epoch": 0.7429664026222343,
"grad_norm": 0.6992029547691345,
"learning_rate": 1.9864864864864866e-05,
"loss": 0.8974,
"step": 1360
},
{
"epoch": 0.745697896749522,
"grad_norm": 0.7547896504402161,
"learning_rate": 1.982173663024727e-05,
"loss": 0.9054,
"step": 1365
},
{
"epoch": 0.7484293908768096,
"grad_norm": 0.622846245765686,
"learning_rate": 1.977860839562967e-05,
"loss": 0.9397,
"step": 1370
},
{
"epoch": 0.7511608850040973,
"grad_norm": 0.7345914840698242,
"learning_rate": 1.9735480161012076e-05,
"loss": 0.9289,
"step": 1375
},
{
"epoch": 0.7538923791313848,
"grad_norm": 0.6609006524085999,
"learning_rate": 1.969235192639448e-05,
"loss": 0.9182,
"step": 1380
},
{
"epoch": 0.7566238732586725,
"grad_norm": 0.6038909554481506,
"learning_rate": 1.9649223691776885e-05,
"loss": 0.951,
"step": 1385
},
{
"epoch": 0.7593553673859601,
"grad_norm": 0.8150413632392883,
"learning_rate": 1.9606095457159286e-05,
"loss": 0.9485,
"step": 1390
},
{
"epoch": 0.7620868615132478,
"grad_norm": 0.7100688815116882,
"learning_rate": 1.956296722254169e-05,
"loss": 0.8858,
"step": 1395
},
{
"epoch": 0.7648183556405354,
"grad_norm": 0.8150034546852112,
"learning_rate": 1.9519838987924094e-05,
"loss": 0.8819,
"step": 1400
},
{
"epoch": 0.767549849767823,
"grad_norm": 0.6773537993431091,
"learning_rate": 1.94767107533065e-05,
"loss": 0.896,
"step": 1405
},
{
"epoch": 0.7702813438951106,
"grad_norm": 0.740321159362793,
"learning_rate": 1.9433582518688903e-05,
"loss": 0.999,
"step": 1410
},
{
"epoch": 0.7730128380223983,
"grad_norm": 0.7414593696594238,
"learning_rate": 1.9390454284071307e-05,
"loss": 0.9705,
"step": 1415
},
{
"epoch": 0.7757443321496859,
"grad_norm": 0.6770462393760681,
"learning_rate": 1.934732604945371e-05,
"loss": 0.8661,
"step": 1420
},
{
"epoch": 0.7784758262769735,
"grad_norm": 0.7381240725517273,
"learning_rate": 1.9304197814836113e-05,
"loss": 0.9294,
"step": 1425
},
{
"epoch": 0.7812073204042611,
"grad_norm": 0.7964140772819519,
"learning_rate": 1.9261069580218517e-05,
"loss": 0.9194,
"step": 1430
},
{
"epoch": 0.7839388145315488,
"grad_norm": 0.6870235800743103,
"learning_rate": 1.921794134560092e-05,
"loss": 0.9445,
"step": 1435
},
{
"epoch": 0.7866703086588364,
"grad_norm": 0.6794748306274414,
"learning_rate": 1.9174813110983326e-05,
"loss": 0.9056,
"step": 1440
},
{
"epoch": 0.789401802786124,
"grad_norm": 0.7200539112091064,
"learning_rate": 1.9131684876365727e-05,
"loss": 0.8967,
"step": 1445
},
{
"epoch": 0.7921332969134116,
"grad_norm": 0.607352614402771,
"learning_rate": 1.908855664174813e-05,
"loss": 0.9867,
"step": 1450
},
{
"epoch": 0.7948647910406993,
"grad_norm": 0.7188989520072937,
"learning_rate": 1.9045428407130535e-05,
"loss": 0.94,
"step": 1455
},
{
"epoch": 0.7975962851679869,
"grad_norm": 0.6703076958656311,
"learning_rate": 1.900230017251294e-05,
"loss": 0.923,
"step": 1460
},
{
"epoch": 0.8003277792952745,
"grad_norm": 0.7471827268600464,
"learning_rate": 1.895917193789534e-05,
"loss": 0.9722,
"step": 1465
},
{
"epoch": 0.8030592734225621,
"grad_norm": 0.7551170587539673,
"learning_rate": 1.8916043703277745e-05,
"loss": 1.0264,
"step": 1470
},
{
"epoch": 0.8057907675498498,
"grad_norm": 0.7488394975662231,
"learning_rate": 1.887291546866015e-05,
"loss": 0.92,
"step": 1475
},
{
"epoch": 0.8085222616771374,
"grad_norm": 0.727719783782959,
"learning_rate": 1.8829787234042554e-05,
"loss": 0.9529,
"step": 1480
},
{
"epoch": 0.811253755804425,
"grad_norm": 0.7175052762031555,
"learning_rate": 1.8786658999424955e-05,
"loss": 0.8721,
"step": 1485
},
{
"epoch": 0.8139852499317126,
"grad_norm": 0.7018330097198486,
"learning_rate": 1.874353076480736e-05,
"loss": 0.9407,
"step": 1490
},
{
"epoch": 0.8167167440590003,
"grad_norm": 0.6539778709411621,
"learning_rate": 1.8700402530189767e-05,
"loss": 0.858,
"step": 1495
},
{
"epoch": 0.8194482381862879,
"grad_norm": 0.7826074361801147,
"learning_rate": 1.865727429557217e-05,
"loss": 0.894,
"step": 1500
},
{
"epoch": 0.8194482381862879,
"eval_loss": 0.9872580766677856,
"eval_runtime": 306.8359,
"eval_samples_per_second": 11.475,
"eval_steps_per_second": 2.871,
"step": 1500
},
{
"epoch": 0.8221797323135756,
"grad_norm": 0.7110973596572876,
"learning_rate": 1.8614146060954572e-05,
"loss": 0.9763,
"step": 1505
},
{
"epoch": 0.8249112264408631,
"grad_norm": 0.7309880256652832,
"learning_rate": 1.8571017826336977e-05,
"loss": 0.9039,
"step": 1510
},
{
"epoch": 0.8276427205681508,
"grad_norm": 0.8011833429336548,
"learning_rate": 1.852788959171938e-05,
"loss": 0.9001,
"step": 1515
},
{
"epoch": 0.8303742146954384,
"grad_norm": 0.7755061984062195,
"learning_rate": 1.8484761357101785e-05,
"loss": 0.9879,
"step": 1520
},
{
"epoch": 0.833105708822726,
"grad_norm": 0.754245400428772,
"learning_rate": 1.8441633122484186e-05,
"loss": 0.9367,
"step": 1525
},
{
"epoch": 0.8358372029500136,
"grad_norm": 0.7638076543807983,
"learning_rate": 1.839850488786659e-05,
"loss": 0.974,
"step": 1530
},
{
"epoch": 0.8385686970773013,
"grad_norm": 0.6868399977684021,
"learning_rate": 1.8355376653248995e-05,
"loss": 0.901,
"step": 1535
},
{
"epoch": 0.8413001912045889,
"grad_norm": 0.7435300350189209,
"learning_rate": 1.8312248418631396e-05,
"loss": 0.9094,
"step": 1540
},
{
"epoch": 0.8440316853318766,
"grad_norm": 0.7442822456359863,
"learning_rate": 1.82691201840138e-05,
"loss": 0.9331,
"step": 1545
},
{
"epoch": 0.8467631794591641,
"grad_norm": 0.6578322052955627,
"learning_rate": 1.8225991949396205e-05,
"loss": 0.8728,
"step": 1550
},
{
"epoch": 0.8494946735864518,
"grad_norm": 0.7113497257232666,
"learning_rate": 1.818286371477861e-05,
"loss": 0.9407,
"step": 1555
},
{
"epoch": 0.8522261677137394,
"grad_norm": 0.6778536438941956,
"learning_rate": 1.813973548016101e-05,
"loss": 0.9075,
"step": 1560
},
{
"epoch": 0.8549576618410271,
"grad_norm": 0.617668092250824,
"learning_rate": 1.8096607245543414e-05,
"loss": 0.9012,
"step": 1565
},
{
"epoch": 0.8576891559683146,
"grad_norm": 0.6440238356590271,
"learning_rate": 1.805347901092582e-05,
"loss": 0.9127,
"step": 1570
},
{
"epoch": 0.8604206500956023,
"grad_norm": 0.8441850543022156,
"learning_rate": 1.8010350776308223e-05,
"loss": 0.9261,
"step": 1575
},
{
"epoch": 0.8631521442228899,
"grad_norm": 0.6639198064804077,
"learning_rate": 1.7967222541690627e-05,
"loss": 0.9025,
"step": 1580
},
{
"epoch": 0.8658836383501776,
"grad_norm": 0.7301929593086243,
"learning_rate": 1.7924094307073032e-05,
"loss": 0.9152,
"step": 1585
},
{
"epoch": 0.8686151324774651,
"grad_norm": 0.7648395299911499,
"learning_rate": 1.7880966072455436e-05,
"loss": 0.8786,
"step": 1590
},
{
"epoch": 0.8713466266047528,
"grad_norm": 0.8249919414520264,
"learning_rate": 1.783783783783784e-05,
"loss": 0.9453,
"step": 1595
},
{
"epoch": 0.8740781207320404,
"grad_norm": 0.7503889203071594,
"learning_rate": 1.779470960322024e-05,
"loss": 0.8989,
"step": 1600
},
{
"epoch": 0.8768096148593281,
"grad_norm": 0.6465786099433899,
"learning_rate": 1.7751581368602646e-05,
"loss": 0.9424,
"step": 1605
},
{
"epoch": 0.8795411089866156,
"grad_norm": 0.741681694984436,
"learning_rate": 1.770845313398505e-05,
"loss": 0.9749,
"step": 1610
},
{
"epoch": 0.8822726031139033,
"grad_norm": 0.6805129647254944,
"learning_rate": 1.7665324899367455e-05,
"loss": 0.8869,
"step": 1615
},
{
"epoch": 0.8850040972411909,
"grad_norm": 0.7567791938781738,
"learning_rate": 1.7622196664749856e-05,
"loss": 0.8947,
"step": 1620
},
{
"epoch": 0.8877355913684786,
"grad_norm": 0.6105583906173706,
"learning_rate": 1.757906843013226e-05,
"loss": 0.8362,
"step": 1625
},
{
"epoch": 0.8904670854957661,
"grad_norm": 0.7158373594284058,
"learning_rate": 1.7535940195514664e-05,
"loss": 0.9471,
"step": 1630
},
{
"epoch": 0.8931985796230538,
"grad_norm": 0.5763299465179443,
"learning_rate": 1.749281196089707e-05,
"loss": 0.864,
"step": 1635
},
{
"epoch": 0.8959300737503414,
"grad_norm": 0.6493390202522278,
"learning_rate": 1.744968372627947e-05,
"loss": 0.8604,
"step": 1640
},
{
"epoch": 0.8986615678776291,
"grad_norm": 0.6950406432151794,
"learning_rate": 1.7406555491661874e-05,
"loss": 0.8781,
"step": 1645
},
{
"epoch": 0.9013930620049166,
"grad_norm": 0.8326542973518372,
"learning_rate": 1.736342725704428e-05,
"loss": 0.954,
"step": 1650
},
{
"epoch": 0.9041245561322043,
"grad_norm": 0.6683987379074097,
"learning_rate": 1.7320299022426683e-05,
"loss": 0.882,
"step": 1655
},
{
"epoch": 0.9068560502594919,
"grad_norm": 0.6118180751800537,
"learning_rate": 1.7277170787809084e-05,
"loss": 0.9009,
"step": 1660
},
{
"epoch": 0.9095875443867796,
"grad_norm": 0.7796676754951477,
"learning_rate": 1.723404255319149e-05,
"loss": 0.829,
"step": 1665
},
{
"epoch": 0.9123190385140671,
"grad_norm": 0.8553198575973511,
"learning_rate": 1.7190914318573896e-05,
"loss": 0.9174,
"step": 1670
},
{
"epoch": 0.9150505326413548,
"grad_norm": 0.7575505971908569,
"learning_rate": 1.7147786083956297e-05,
"loss": 0.9401,
"step": 1675
},
{
"epoch": 0.9177820267686424,
"grad_norm": 0.7973514199256897,
"learning_rate": 1.71046578493387e-05,
"loss": 0.9088,
"step": 1680
},
{
"epoch": 0.9205135208959301,
"grad_norm": 0.7348738312721252,
"learning_rate": 1.7061529614721106e-05,
"loss": 1.0269,
"step": 1685
},
{
"epoch": 0.9232450150232177,
"grad_norm": 0.8025610446929932,
"learning_rate": 1.701840138010351e-05,
"loss": 0.9249,
"step": 1690
},
{
"epoch": 0.9259765091505053,
"grad_norm": 0.8233335614204407,
"learning_rate": 1.697527314548591e-05,
"loss": 0.9512,
"step": 1695
},
{
"epoch": 0.9287080032777929,
"grad_norm": 0.6626378893852234,
"learning_rate": 1.6932144910868315e-05,
"loss": 0.8922,
"step": 1700
},
{
"epoch": 0.9314394974050806,
"grad_norm": 0.6478386521339417,
"learning_rate": 1.688901667625072e-05,
"loss": 0.9199,
"step": 1705
},
{
"epoch": 0.9341709915323682,
"grad_norm": 0.6564362049102783,
"learning_rate": 1.6845888441633124e-05,
"loss": 0.948,
"step": 1710
},
{
"epoch": 0.9369024856596558,
"grad_norm": 0.7215321063995361,
"learning_rate": 1.6802760207015525e-05,
"loss": 0.9751,
"step": 1715
},
{
"epoch": 0.9396339797869434,
"grad_norm": 0.7329283952713013,
"learning_rate": 1.675963197239793e-05,
"loss": 0.8813,
"step": 1720
},
{
"epoch": 0.9423654739142311,
"grad_norm": 0.7088721394538879,
"learning_rate": 1.6716503737780334e-05,
"loss": 0.9062,
"step": 1725
},
{
"epoch": 0.9450969680415187,
"grad_norm": 0.7192842364311218,
"learning_rate": 1.6673375503162738e-05,
"loss": 0.9459,
"step": 1730
},
{
"epoch": 0.9478284621688063,
"grad_norm": 0.6714224219322205,
"learning_rate": 1.663024726854514e-05,
"loss": 0.9044,
"step": 1735
},
{
"epoch": 0.9505599562960939,
"grad_norm": 0.7423708438873291,
"learning_rate": 1.6587119033927543e-05,
"loss": 0.9037,
"step": 1740
},
{
"epoch": 0.9532914504233816,
"grad_norm": 0.7379775643348694,
"learning_rate": 1.6543990799309948e-05,
"loss": 0.887,
"step": 1745
},
{
"epoch": 0.9560229445506692,
"grad_norm": 0.7309372425079346,
"learning_rate": 1.6500862564692355e-05,
"loss": 0.8759,
"step": 1750
},
{
"epoch": 0.9587544386779568,
"grad_norm": 0.7975478768348694,
"learning_rate": 1.6457734330074756e-05,
"loss": 0.9037,
"step": 1755
},
{
"epoch": 0.9614859328052444,
"grad_norm": 0.745080292224884,
"learning_rate": 1.641460609545716e-05,
"loss": 0.8829,
"step": 1760
},
{
"epoch": 0.9642174269325321,
"grad_norm": 0.7956293821334839,
"learning_rate": 1.6371477860839565e-05,
"loss": 1.0524,
"step": 1765
},
{
"epoch": 0.9669489210598197,
"grad_norm": 0.696330189704895,
"learning_rate": 1.632834962622197e-05,
"loss": 0.9771,
"step": 1770
},
{
"epoch": 0.9696804151871073,
"grad_norm": 0.6705037951469421,
"learning_rate": 1.628522139160437e-05,
"loss": 0.8901,
"step": 1775
},
{
"epoch": 0.972411909314395,
"grad_norm": 0.7212891578674316,
"learning_rate": 1.6242093156986775e-05,
"loss": 0.954,
"step": 1780
},
{
"epoch": 0.9751434034416826,
"grad_norm": 0.7896215319633484,
"learning_rate": 1.619896492236918e-05,
"loss": 0.9846,
"step": 1785
},
{
"epoch": 0.9778748975689703,
"grad_norm": 0.6579116582870483,
"learning_rate": 1.615583668775158e-05,
"loss": 0.9433,
"step": 1790
},
{
"epoch": 0.9806063916962579,
"grad_norm": 0.7765350937843323,
"learning_rate": 1.6112708453133984e-05,
"loss": 0.9282,
"step": 1795
},
{
"epoch": 0.9833378858235455,
"grad_norm": 0.708436131477356,
"learning_rate": 1.606958021851639e-05,
"loss": 0.8686,
"step": 1800
},
{
"epoch": 0.9833378858235455,
"eval_loss": 0.9697180986404419,
"eval_runtime": 301.1632,
"eval_samples_per_second": 11.691,
"eval_steps_per_second": 2.925,
"step": 1800
},
{
"epoch": 0.9860693799508331,
"grad_norm": 0.8018620610237122,
"learning_rate": 1.6026451983898793e-05,
"loss": 1.0011,
"step": 1805
},
{
"epoch": 0.9888008740781208,
"grad_norm": 0.7609168291091919,
"learning_rate": 1.5983323749281194e-05,
"loss": 0.8624,
"step": 1810
},
{
"epoch": 0.9915323682054084,
"grad_norm": 0.6601422429084778,
"learning_rate": 1.59401955146636e-05,
"loss": 0.9233,
"step": 1815
},
{
"epoch": 0.994263862332696,
"grad_norm": 0.7912075519561768,
"learning_rate": 1.5897067280046003e-05,
"loss": 0.9028,
"step": 1820
},
{
"epoch": 0.9969953564599836,
"grad_norm": 0.7140695452690125,
"learning_rate": 1.5853939045428407e-05,
"loss": 0.9264,
"step": 1825
},
{
"epoch": 0.9997268505872713,
"grad_norm": 0.808732271194458,
"learning_rate": 1.5810810810810808e-05,
"loss": 0.9834,
"step": 1830
},
{
"epoch": 1.0021851953018301,
"grad_norm": 0.8098347783088684,
"learning_rate": 1.5767682576193216e-05,
"loss": 0.8197,
"step": 1835
},
{
"epoch": 1.0049166894291177,
"grad_norm": 0.6910871863365173,
"learning_rate": 1.572455434157562e-05,
"loss": 0.8297,
"step": 1840
},
{
"epoch": 1.0076481835564053,
"grad_norm": 0.6911448836326599,
"learning_rate": 1.5681426106958025e-05,
"loss": 0.8399,
"step": 1845
},
{
"epoch": 1.010379677683693,
"grad_norm": 0.6237926483154297,
"learning_rate": 1.5638297872340426e-05,
"loss": 0.883,
"step": 1850
},
{
"epoch": 1.0131111718109806,
"grad_norm": 0.7451146245002747,
"learning_rate": 1.559516963772283e-05,
"loss": 0.8211,
"step": 1855
},
{
"epoch": 1.0158426659382682,
"grad_norm": 0.8290321230888367,
"learning_rate": 1.5552041403105234e-05,
"loss": 0.8043,
"step": 1860
},
{
"epoch": 1.0185741600655558,
"grad_norm": 0.7983705997467041,
"learning_rate": 1.550891316848764e-05,
"loss": 0.869,
"step": 1865
},
{
"epoch": 1.0213056541928436,
"grad_norm": 0.6545166969299316,
"learning_rate": 1.546578493387004e-05,
"loss": 0.8163,
"step": 1870
},
{
"epoch": 1.0240371483201312,
"grad_norm": 0.7788228392601013,
"learning_rate": 1.5422656699252444e-05,
"loss": 0.8503,
"step": 1875
},
{
"epoch": 1.0267686424474187,
"grad_norm": 0.739607572555542,
"learning_rate": 1.537952846463485e-05,
"loss": 0.845,
"step": 1880
},
{
"epoch": 1.0295001365747063,
"grad_norm": 0.6919524073600769,
"learning_rate": 1.5336400230017253e-05,
"loss": 0.8252,
"step": 1885
},
{
"epoch": 1.032231630701994,
"grad_norm": 0.7420228719711304,
"learning_rate": 1.5293271995399654e-05,
"loss": 0.8708,
"step": 1890
},
{
"epoch": 1.0349631248292817,
"grad_norm": 0.769300103187561,
"learning_rate": 1.5250143760782058e-05,
"loss": 0.8684,
"step": 1895
},
{
"epoch": 1.0376946189565692,
"grad_norm": 0.6629747748374939,
"learning_rate": 1.5207015526164463e-05,
"loss": 0.7835,
"step": 1900
},
{
"epoch": 1.0404261130838568,
"grad_norm": 0.7395908832550049,
"learning_rate": 1.5163887291546865e-05,
"loss": 0.8569,
"step": 1905
},
{
"epoch": 1.0431576072111446,
"grad_norm": 0.7261918187141418,
"learning_rate": 1.5120759056929268e-05,
"loss": 0.8388,
"step": 1910
},
{
"epoch": 1.0458891013384322,
"grad_norm": 0.7595694065093994,
"learning_rate": 1.5077630822311672e-05,
"loss": 0.8228,
"step": 1915
},
{
"epoch": 1.0486205954657197,
"grad_norm": 0.8336328864097595,
"learning_rate": 1.5034502587694078e-05,
"loss": 0.8783,
"step": 1920
},
{
"epoch": 1.0513520895930073,
"grad_norm": 0.7210121750831604,
"learning_rate": 1.4991374353076481e-05,
"loss": 0.8403,
"step": 1925
},
{
"epoch": 1.054083583720295,
"grad_norm": 0.7384738326072693,
"learning_rate": 1.4948246118458884e-05,
"loss": 0.8853,
"step": 1930
},
{
"epoch": 1.0568150778475827,
"grad_norm": 0.6568289995193481,
"learning_rate": 1.4905117883841288e-05,
"loss": 0.799,
"step": 1935
},
{
"epoch": 1.0595465719748702,
"grad_norm": 0.8818139433860779,
"learning_rate": 1.4861989649223692e-05,
"loss": 0.927,
"step": 1940
},
{
"epoch": 1.0622780661021578,
"grad_norm": 0.7465585470199585,
"learning_rate": 1.4818861414606097e-05,
"loss": 0.9071,
"step": 1945
},
{
"epoch": 1.0650095602294456,
"grad_norm": 0.756374716758728,
"learning_rate": 1.47757331799885e-05,
"loss": 0.8751,
"step": 1950
},
{
"epoch": 1.0677410543567332,
"grad_norm": 0.7350252270698547,
"learning_rate": 1.4732604945370904e-05,
"loss": 0.8215,
"step": 1955
},
{
"epoch": 1.0704725484840207,
"grad_norm": 0.7299278974533081,
"learning_rate": 1.4689476710753306e-05,
"loss": 0.8626,
"step": 1960
},
{
"epoch": 1.0732040426113083,
"grad_norm": 0.7611562609672546,
"learning_rate": 1.464634847613571e-05,
"loss": 0.8473,
"step": 1965
},
{
"epoch": 1.075935536738596,
"grad_norm": 0.7419504523277283,
"learning_rate": 1.4603220241518113e-05,
"loss": 0.9122,
"step": 1970
},
{
"epoch": 1.0786670308658837,
"grad_norm": 0.7700083255767822,
"learning_rate": 1.4560092006900518e-05,
"loss": 0.898,
"step": 1975
},
{
"epoch": 1.0813985249931712,
"grad_norm": 0.815271258354187,
"learning_rate": 1.4516963772282922e-05,
"loss": 0.848,
"step": 1980
},
{
"epoch": 1.0841300191204588,
"grad_norm": 0.7537347674369812,
"learning_rate": 1.4473835537665326e-05,
"loss": 0.8751,
"step": 1985
},
{
"epoch": 1.0868615132477466,
"grad_norm": 0.6615073680877686,
"learning_rate": 1.4430707303047729e-05,
"loss": 0.8113,
"step": 1990
},
{
"epoch": 1.0895930073750342,
"grad_norm": 0.7301376461982727,
"learning_rate": 1.4387579068430133e-05,
"loss": 0.8486,
"step": 1995
},
{
"epoch": 1.0923245015023217,
"grad_norm": 0.7153547406196594,
"learning_rate": 1.4344450833812536e-05,
"loss": 0.7822,
"step": 2000
},
{
"epoch": 1.0950559956296093,
"grad_norm": 0.7003058791160583,
"learning_rate": 1.430132259919494e-05,
"loss": 0.8438,
"step": 2005
},
{
"epoch": 1.097787489756897,
"grad_norm": 0.6865559220314026,
"learning_rate": 1.4258194364577343e-05,
"loss": 0.8442,
"step": 2010
},
{
"epoch": 1.1005189838841847,
"grad_norm": 0.7226883172988892,
"learning_rate": 1.4215066129959748e-05,
"loss": 0.8487,
"step": 2015
},
{
"epoch": 1.1032504780114722,
"grad_norm": 0.8276675939559937,
"learning_rate": 1.417193789534215e-05,
"loss": 0.8383,
"step": 2020
},
{
"epoch": 1.1059819721387598,
"grad_norm": 0.710615336894989,
"learning_rate": 1.4128809660724555e-05,
"loss": 0.8396,
"step": 2025
},
{
"epoch": 1.1087134662660476,
"grad_norm": 0.708114743232727,
"learning_rate": 1.4085681426106959e-05,
"loss": 0.8451,
"step": 2030
},
{
"epoch": 1.1114449603933352,
"grad_norm": 0.8237577676773071,
"learning_rate": 1.4042553191489362e-05,
"loss": 0.8895,
"step": 2035
},
{
"epoch": 1.1141764545206227,
"grad_norm": 0.8851677775382996,
"learning_rate": 1.3999424956871766e-05,
"loss": 0.8576,
"step": 2040
},
{
"epoch": 1.1169079486479103,
"grad_norm": 0.6728988289833069,
"learning_rate": 1.3956296722254169e-05,
"loss": 0.8038,
"step": 2045
},
{
"epoch": 1.1196394427751981,
"grad_norm": 0.8209788799285889,
"learning_rate": 1.3913168487636573e-05,
"loss": 0.9329,
"step": 2050
},
{
"epoch": 1.1223709369024857,
"grad_norm": 0.8296043276786804,
"learning_rate": 1.3870040253018976e-05,
"loss": 0.8253,
"step": 2055
},
{
"epoch": 1.1251024310297733,
"grad_norm": 0.862583577632904,
"learning_rate": 1.382691201840138e-05,
"loss": 0.8362,
"step": 2060
},
{
"epoch": 1.1278339251570608,
"grad_norm": 0.7324648499488831,
"learning_rate": 1.3783783783783784e-05,
"loss": 0.8622,
"step": 2065
},
{
"epoch": 1.1305654192843486,
"grad_norm": 0.7577756643295288,
"learning_rate": 1.3740655549166189e-05,
"loss": 0.8403,
"step": 2070
},
{
"epoch": 1.1332969134116362,
"grad_norm": 0.7458604574203491,
"learning_rate": 1.3697527314548591e-05,
"loss": 0.8534,
"step": 2075
},
{
"epoch": 1.1360284075389238,
"grad_norm": 0.7610705494880676,
"learning_rate": 1.3654399079930996e-05,
"loss": 0.868,
"step": 2080
},
{
"epoch": 1.1387599016662113,
"grad_norm": 0.6969969868659973,
"learning_rate": 1.3611270845313398e-05,
"loss": 0.8137,
"step": 2085
},
{
"epoch": 1.1414913957934991,
"grad_norm": 0.8028571605682373,
"learning_rate": 1.3568142610695803e-05,
"loss": 0.9163,
"step": 2090
},
{
"epoch": 1.1442228899207867,
"grad_norm": 0.6725644469261169,
"learning_rate": 1.3525014376078205e-05,
"loss": 0.836,
"step": 2095
},
{
"epoch": 1.1469543840480743,
"grad_norm": 0.7271857261657715,
"learning_rate": 1.348188614146061e-05,
"loss": 0.8345,
"step": 2100
},
{
"epoch": 1.1469543840480743,
"eval_loss": 0.9603794813156128,
"eval_runtime": 299.8443,
"eval_samples_per_second": 11.743,
"eval_steps_per_second": 2.938,
"step": 2100
},
{
"epoch": 1.1496858781753618,
"grad_norm": 0.8495539426803589,
"learning_rate": 1.3438757906843012e-05,
"loss": 0.8977,
"step": 2105
},
{
"epoch": 1.1524173723026496,
"grad_norm": 0.7955543398857117,
"learning_rate": 1.3395629672225419e-05,
"loss": 0.8212,
"step": 2110
},
{
"epoch": 1.1551488664299372,
"grad_norm": 0.6666565537452698,
"learning_rate": 1.3352501437607821e-05,
"loss": 0.8875,
"step": 2115
},
{
"epoch": 1.1578803605572248,
"grad_norm": 0.8918675184249878,
"learning_rate": 1.3309373202990226e-05,
"loss": 0.8418,
"step": 2120
},
{
"epoch": 1.1606118546845123,
"grad_norm": 0.6826077699661255,
"learning_rate": 1.3266244968372628e-05,
"loss": 0.8562,
"step": 2125
},
{
"epoch": 1.1633433488118001,
"grad_norm": 0.7688910961151123,
"learning_rate": 1.3223116733755033e-05,
"loss": 0.8057,
"step": 2130
},
{
"epoch": 1.1660748429390877,
"grad_norm": 0.750607430934906,
"learning_rate": 1.3179988499137435e-05,
"loss": 0.8702,
"step": 2135
},
{
"epoch": 1.1688063370663753,
"grad_norm": 0.6954635977745056,
"learning_rate": 1.313686026451984e-05,
"loss": 0.8034,
"step": 2140
},
{
"epoch": 1.1715378311936628,
"grad_norm": 0.7350913286209106,
"learning_rate": 1.3093732029902242e-05,
"loss": 0.8551,
"step": 2145
},
{
"epoch": 1.1742693253209506,
"grad_norm": 0.611512303352356,
"learning_rate": 1.3050603795284647e-05,
"loss": 0.829,
"step": 2150
},
{
"epoch": 1.1770008194482382,
"grad_norm": 0.7744221687316895,
"learning_rate": 1.3007475560667051e-05,
"loss": 0.8439,
"step": 2155
},
{
"epoch": 1.1797323135755258,
"grad_norm": 0.6697201728820801,
"learning_rate": 1.2964347326049454e-05,
"loss": 0.8549,
"step": 2160
},
{
"epoch": 1.1824638077028133,
"grad_norm": 0.6822842955589294,
"learning_rate": 1.2921219091431858e-05,
"loss": 0.813,
"step": 2165
},
{
"epoch": 1.1851953018301011,
"grad_norm": 0.7313398718833923,
"learning_rate": 1.287809085681426e-05,
"loss": 0.8151,
"step": 2170
},
{
"epoch": 1.1879267959573887,
"grad_norm": 0.7455983757972717,
"learning_rate": 1.2834962622196665e-05,
"loss": 0.8477,
"step": 2175
},
{
"epoch": 1.1906582900846763,
"grad_norm": 0.7408328652381897,
"learning_rate": 1.2791834387579068e-05,
"loss": 0.8163,
"step": 2180
},
{
"epoch": 1.193389784211964,
"grad_norm": 0.7584601640701294,
"learning_rate": 1.2748706152961472e-05,
"loss": 0.861,
"step": 2185
},
{
"epoch": 1.1961212783392516,
"grad_norm": 0.7042814493179321,
"learning_rate": 1.2705577918343876e-05,
"loss": 0.794,
"step": 2190
},
{
"epoch": 1.1988527724665392,
"grad_norm": 0.7800438404083252,
"learning_rate": 1.266244968372628e-05,
"loss": 0.7924,
"step": 2195
},
{
"epoch": 1.2015842665938268,
"grad_norm": 0.653647243976593,
"learning_rate": 1.2619321449108683e-05,
"loss": 0.794,
"step": 2200
},
{
"epoch": 1.2043157607211143,
"grad_norm": 0.7376958131790161,
"learning_rate": 1.2576193214491088e-05,
"loss": 0.8922,
"step": 2205
},
{
"epoch": 1.2070472548484021,
"grad_norm": 0.7106969952583313,
"learning_rate": 1.253306497987349e-05,
"loss": 0.8205,
"step": 2210
},
{
"epoch": 1.2097787489756897,
"grad_norm": 0.719859778881073,
"learning_rate": 1.2489936745255895e-05,
"loss": 0.8202,
"step": 2215
},
{
"epoch": 1.2125102431029773,
"grad_norm": 0.762196958065033,
"learning_rate": 1.2446808510638298e-05,
"loss": 0.8512,
"step": 2220
},
{
"epoch": 1.215241737230265,
"grad_norm": 0.6730673909187317,
"learning_rate": 1.2403680276020702e-05,
"loss": 0.8402,
"step": 2225
},
{
"epoch": 1.2179732313575526,
"grad_norm": 0.6612475514411926,
"learning_rate": 1.2360552041403105e-05,
"loss": 0.857,
"step": 2230
},
{
"epoch": 1.2207047254848402,
"grad_norm": 0.6943302154541016,
"learning_rate": 1.231742380678551e-05,
"loss": 0.8807,
"step": 2235
},
{
"epoch": 1.2234362196121278,
"grad_norm": 0.680476725101471,
"learning_rate": 1.2274295572167913e-05,
"loss": 0.827,
"step": 2240
},
{
"epoch": 1.2261677137394154,
"grad_norm": 0.8686658143997192,
"learning_rate": 1.2231167337550318e-05,
"loss": 0.8558,
"step": 2245
},
{
"epoch": 1.2288992078667031,
"grad_norm": 0.8038902282714844,
"learning_rate": 1.218803910293272e-05,
"loss": 0.8664,
"step": 2250
},
{
"epoch": 1.2316307019939907,
"grad_norm": 0.7298166751861572,
"learning_rate": 1.2144910868315125e-05,
"loss": 0.8323,
"step": 2255
},
{
"epoch": 1.2343621961212783,
"grad_norm": 0.7598807215690613,
"learning_rate": 1.2101782633697527e-05,
"loss": 0.8666,
"step": 2260
},
{
"epoch": 1.237093690248566,
"grad_norm": 0.6743911504745483,
"learning_rate": 1.2058654399079932e-05,
"loss": 0.8133,
"step": 2265
},
{
"epoch": 1.2398251843758537,
"grad_norm": 0.7879360318183899,
"learning_rate": 1.2015526164462334e-05,
"loss": 0.8823,
"step": 2270
},
{
"epoch": 1.2425566785031412,
"grad_norm": 0.7517372369766235,
"learning_rate": 1.1972397929844739e-05,
"loss": 0.843,
"step": 2275
},
{
"epoch": 1.2452881726304288,
"grad_norm": 0.6552916169166565,
"learning_rate": 1.1929269695227143e-05,
"loss": 0.7984,
"step": 2280
},
{
"epoch": 1.2480196667577164,
"grad_norm": 0.6827423572540283,
"learning_rate": 1.1886141460609546e-05,
"loss": 0.8275,
"step": 2285
},
{
"epoch": 1.2507511608850042,
"grad_norm": 0.8822212815284729,
"learning_rate": 1.184301322599195e-05,
"loss": 0.9157,
"step": 2290
},
{
"epoch": 1.2534826550122917,
"grad_norm": 0.6565053462982178,
"learning_rate": 1.1799884991374353e-05,
"loss": 0.8521,
"step": 2295
},
{
"epoch": 1.2562141491395793,
"grad_norm": 0.7047061324119568,
"learning_rate": 1.1756756756756757e-05,
"loss": 0.8847,
"step": 2300
},
{
"epoch": 1.258945643266867,
"grad_norm": 0.6856869459152222,
"learning_rate": 1.171362852213916e-05,
"loss": 0.8797,
"step": 2305
},
{
"epoch": 1.2616771373941547,
"grad_norm": 0.7389653325080872,
"learning_rate": 1.1670500287521564e-05,
"loss": 0.8504,
"step": 2310
},
{
"epoch": 1.2644086315214422,
"grad_norm": 0.6907625794410706,
"learning_rate": 1.1627372052903967e-05,
"loss": 0.8129,
"step": 2315
},
{
"epoch": 1.2671401256487298,
"grad_norm": 0.6656849980354309,
"learning_rate": 1.1584243818286373e-05,
"loss": 0.8487,
"step": 2320
},
{
"epoch": 1.2698716197760174,
"grad_norm": 0.7104740738868713,
"learning_rate": 1.1541115583668776e-05,
"loss": 0.8195,
"step": 2325
},
{
"epoch": 1.2726031139033052,
"grad_norm": 0.6655605435371399,
"learning_rate": 1.149798734905118e-05,
"loss": 0.835,
"step": 2330
},
{
"epoch": 1.2753346080305927,
"grad_norm": 0.7858142852783203,
"learning_rate": 1.1454859114433583e-05,
"loss": 0.8462,
"step": 2335
},
{
"epoch": 1.2780661021578803,
"grad_norm": 0.7418481111526489,
"learning_rate": 1.1411730879815987e-05,
"loss": 0.8628,
"step": 2340
},
{
"epoch": 1.280797596285168,
"grad_norm": 0.667325496673584,
"learning_rate": 1.136860264519839e-05,
"loss": 0.853,
"step": 2345
},
{
"epoch": 1.2835290904124557,
"grad_norm": 0.7547652721405029,
"learning_rate": 1.1325474410580794e-05,
"loss": 0.8686,
"step": 2350
},
{
"epoch": 1.2862605845397432,
"grad_norm": 0.7846309542655945,
"learning_rate": 1.1282346175963197e-05,
"loss": 0.8614,
"step": 2355
},
{
"epoch": 1.2889920786670308,
"grad_norm": 0.7988253831863403,
"learning_rate": 1.1239217941345603e-05,
"loss": 0.7813,
"step": 2360
},
{
"epoch": 1.2917235727943184,
"grad_norm": 0.7061751484870911,
"learning_rate": 1.1196089706728005e-05,
"loss": 0.7982,
"step": 2365
},
{
"epoch": 1.2944550669216062,
"grad_norm": 0.7142939567565918,
"learning_rate": 1.115296147211041e-05,
"loss": 0.8418,
"step": 2370
},
{
"epoch": 1.2971865610488937,
"grad_norm": 0.7572714686393738,
"learning_rate": 1.1109833237492812e-05,
"loss": 0.8548,
"step": 2375
},
{
"epoch": 1.2999180551761813,
"grad_norm": 0.6468579173088074,
"learning_rate": 1.1066705002875217e-05,
"loss": 0.8206,
"step": 2380
},
{
"epoch": 1.302649549303469,
"grad_norm": 0.7635488510131836,
"learning_rate": 1.102357676825762e-05,
"loss": 0.8132,
"step": 2385
},
{
"epoch": 1.3053810434307567,
"grad_norm": 0.6327168941497803,
"learning_rate": 1.0980448533640024e-05,
"loss": 0.8129,
"step": 2390
},
{
"epoch": 1.3081125375580442,
"grad_norm": 0.7146739363670349,
"learning_rate": 1.0937320299022426e-05,
"loss": 0.7614,
"step": 2395
},
{
"epoch": 1.3108440316853318,
"grad_norm": 0.806710422039032,
"learning_rate": 1.0894192064404829e-05,
"loss": 0.8833,
"step": 2400
},
{
"epoch": 1.3108440316853318,
"eval_loss": 0.9514270424842834,
"eval_runtime": 300.7103,
"eval_samples_per_second": 11.709,
"eval_steps_per_second": 2.93,
"step": 2400
},
{
"epoch": 1.3135755258126194,
"grad_norm": 0.737932562828064,
"learning_rate": 1.0851063829787235e-05,
"loss": 0.8182,
"step": 2405
},
{
"epoch": 1.3163070199399072,
"grad_norm": 0.7519195675849915,
"learning_rate": 1.0807935595169638e-05,
"loss": 0.8565,
"step": 2410
},
{
"epoch": 1.3190385140671947,
"grad_norm": 0.7231210470199585,
"learning_rate": 1.0764807360552042e-05,
"loss": 0.884,
"step": 2415
},
{
"epoch": 1.3217700081944823,
"grad_norm": 0.790768027305603,
"learning_rate": 1.0721679125934445e-05,
"loss": 0.8609,
"step": 2420
},
{
"epoch": 1.32450150232177,
"grad_norm": 0.7810729742050171,
"learning_rate": 1.067855089131685e-05,
"loss": 0.8503,
"step": 2425
},
{
"epoch": 1.3272329964490577,
"grad_norm": 0.6903507113456726,
"learning_rate": 1.0635422656699252e-05,
"loss": 0.844,
"step": 2430
},
{
"epoch": 1.3299644905763452,
"grad_norm": 0.7500677704811096,
"learning_rate": 1.0592294422081656e-05,
"loss": 0.8753,
"step": 2435
},
{
"epoch": 1.3326959847036328,
"grad_norm": 0.8364259600639343,
"learning_rate": 1.0549166187464059e-05,
"loss": 0.8508,
"step": 2440
},
{
"epoch": 1.3354274788309204,
"grad_norm": 0.7395508885383606,
"learning_rate": 1.0506037952846465e-05,
"loss": 0.8851,
"step": 2445
},
{
"epoch": 1.3381589729582082,
"grad_norm": 0.7230052351951599,
"learning_rate": 1.0462909718228868e-05,
"loss": 0.8452,
"step": 2450
},
{
"epoch": 1.3408904670854958,
"grad_norm": 0.6834907531738281,
"learning_rate": 1.0419781483611272e-05,
"loss": 0.81,
"step": 2455
},
{
"epoch": 1.3436219612127833,
"grad_norm": 0.820035994052887,
"learning_rate": 1.0376653248993675e-05,
"loss": 0.8284,
"step": 2460
},
{
"epoch": 1.3463534553400711,
"grad_norm": 0.665709912776947,
"learning_rate": 1.0333525014376079e-05,
"loss": 0.8094,
"step": 2465
},
{
"epoch": 1.3490849494673587,
"grad_norm": 0.6796711683273315,
"learning_rate": 1.0290396779758482e-05,
"loss": 0.8182,
"step": 2470
},
{
"epoch": 1.3518164435946463,
"grad_norm": 0.7614695429801941,
"learning_rate": 1.0247268545140886e-05,
"loss": 0.8336,
"step": 2475
},
{
"epoch": 1.3545479377219338,
"grad_norm": 0.7171001434326172,
"learning_rate": 1.0204140310523289e-05,
"loss": 0.8347,
"step": 2480
},
{
"epoch": 1.3572794318492214,
"grad_norm": 0.8130117654800415,
"learning_rate": 1.0161012075905693e-05,
"loss": 0.8516,
"step": 2485
},
{
"epoch": 1.3600109259765092,
"grad_norm": 0.764981210231781,
"learning_rate": 1.0117883841288097e-05,
"loss": 0.8623,
"step": 2490
},
{
"epoch": 1.3627424201037968,
"grad_norm": 0.714309573173523,
"learning_rate": 1.0074755606670502e-05,
"loss": 0.8203,
"step": 2495
},
{
"epoch": 1.3654739142310843,
"grad_norm": 0.7773436903953552,
"learning_rate": 1.0031627372052904e-05,
"loss": 0.8181,
"step": 2500
},
{
"epoch": 1.3682054083583721,
"grad_norm": 0.7160648107528687,
"learning_rate": 9.988499137435309e-06,
"loss": 0.8081,
"step": 2505
},
{
"epoch": 1.3709369024856597,
"grad_norm": 0.6794509291648865,
"learning_rate": 9.945370902817711e-06,
"loss": 0.8498,
"step": 2510
},
{
"epoch": 1.3736683966129473,
"grad_norm": 0.7373344898223877,
"learning_rate": 9.902242668200114e-06,
"loss": 0.8283,
"step": 2515
},
{
"epoch": 1.3763998907402348,
"grad_norm": 0.7624025344848633,
"learning_rate": 9.859114433582518e-06,
"loss": 0.8564,
"step": 2520
},
{
"epoch": 1.3791313848675224,
"grad_norm": 0.7660391926765442,
"learning_rate": 9.815986198964921e-06,
"loss": 0.8129,
"step": 2525
},
{
"epoch": 1.3818628789948102,
"grad_norm": 0.7183862924575806,
"learning_rate": 9.772857964347327e-06,
"loss": 0.8769,
"step": 2530
},
{
"epoch": 1.3845943731220978,
"grad_norm": 0.7163282632827759,
"learning_rate": 9.72972972972973e-06,
"loss": 0.7862,
"step": 2535
},
{
"epoch": 1.3873258672493853,
"grad_norm": 0.786116361618042,
"learning_rate": 9.686601495112134e-06,
"loss": 0.8332,
"step": 2540
},
{
"epoch": 1.3900573613766731,
"grad_norm": 0.6772438287734985,
"learning_rate": 9.643473260494537e-06,
"loss": 0.7998,
"step": 2545
},
{
"epoch": 1.3927888555039607,
"grad_norm": 0.731532871723175,
"learning_rate": 9.600345025876941e-06,
"loss": 0.8058,
"step": 2550
},
{
"epoch": 1.3955203496312483,
"grad_norm": 0.7636890411376953,
"learning_rate": 9.557216791259344e-06,
"loss": 0.8652,
"step": 2555
},
{
"epoch": 1.3982518437585358,
"grad_norm": 0.7335514426231384,
"learning_rate": 9.514088556641748e-06,
"loss": 0.8642,
"step": 2560
},
{
"epoch": 1.4009833378858234,
"grad_norm": 0.781554639339447,
"learning_rate": 9.470960322024151e-06,
"loss": 0.8641,
"step": 2565
},
{
"epoch": 1.4037148320131112,
"grad_norm": 0.7264503240585327,
"learning_rate": 9.427832087406557e-06,
"loss": 0.8559,
"step": 2570
},
{
"epoch": 1.4064463261403988,
"grad_norm": 0.8563718795776367,
"learning_rate": 9.38470385278896e-06,
"loss": 0.8265,
"step": 2575
},
{
"epoch": 1.4091778202676863,
"grad_norm": 0.6975945830345154,
"learning_rate": 9.341575618171364e-06,
"loss": 0.8625,
"step": 2580
},
{
"epoch": 1.4119093143949741,
"grad_norm": 0.6844210624694824,
"learning_rate": 9.298447383553767e-06,
"loss": 0.8185,
"step": 2585
},
{
"epoch": 1.4146408085222617,
"grad_norm": 0.7747036814689636,
"learning_rate": 9.255319148936171e-06,
"loss": 0.8019,
"step": 2590
},
{
"epoch": 1.4173723026495493,
"grad_norm": 0.8067139387130737,
"learning_rate": 9.212190914318574e-06,
"loss": 0.7995,
"step": 2595
},
{
"epoch": 1.420103796776837,
"grad_norm": 0.8115991353988647,
"learning_rate": 9.169062679700978e-06,
"loss": 0.833,
"step": 2600
},
{
"epoch": 1.4228352909041246,
"grad_norm": 0.8172594308853149,
"learning_rate": 9.12593444508338e-06,
"loss": 0.8245,
"step": 2605
},
{
"epoch": 1.4255667850314122,
"grad_norm": 0.7747359275817871,
"learning_rate": 9.082806210465785e-06,
"loss": 0.8254,
"step": 2610
},
{
"epoch": 1.4282982791586998,
"grad_norm": 0.752096951007843,
"learning_rate": 9.03967797584819e-06,
"loss": 0.8552,
"step": 2615
},
{
"epoch": 1.4310297732859873,
"grad_norm": 0.7678769826889038,
"learning_rate": 8.996549741230594e-06,
"loss": 0.8295,
"step": 2620
},
{
"epoch": 1.4337612674132751,
"grad_norm": 0.7188131213188171,
"learning_rate": 8.953421506612996e-06,
"loss": 0.8236,
"step": 2625
},
{
"epoch": 1.4364927615405627,
"grad_norm": 0.7102415561676025,
"learning_rate": 8.9102932719954e-06,
"loss": 0.8171,
"step": 2630
},
{
"epoch": 1.4392242556678503,
"grad_norm": 0.6934943199157715,
"learning_rate": 8.867165037377803e-06,
"loss": 0.8314,
"step": 2635
},
{
"epoch": 1.441955749795138,
"grad_norm": 0.7500588297843933,
"learning_rate": 8.824036802760206e-06,
"loss": 0.8568,
"step": 2640
},
{
"epoch": 1.4446872439224256,
"grad_norm": 0.7399765253067017,
"learning_rate": 8.78090856814261e-06,
"loss": 0.8751,
"step": 2645
},
{
"epoch": 1.4474187380497132,
"grad_norm": 0.7341210842132568,
"learning_rate": 8.737780333525013e-06,
"loss": 0.9003,
"step": 2650
},
{
"epoch": 1.4501502321770008,
"grad_norm": 0.8152205944061279,
"learning_rate": 8.69465209890742e-06,
"loss": 0.8265,
"step": 2655
},
{
"epoch": 1.4528817263042884,
"grad_norm": 0.8102734088897705,
"learning_rate": 8.651523864289822e-06,
"loss": 0.8483,
"step": 2660
},
{
"epoch": 1.4556132204315761,
"grad_norm": 0.6146027445793152,
"learning_rate": 8.608395629672226e-06,
"loss": 0.8203,
"step": 2665
},
{
"epoch": 1.4583447145588637,
"grad_norm": 0.6515645980834961,
"learning_rate": 8.565267395054629e-06,
"loss": 0.8286,
"step": 2670
},
{
"epoch": 1.4610762086861513,
"grad_norm": 0.7171005010604858,
"learning_rate": 8.522139160437033e-06,
"loss": 0.7295,
"step": 2675
},
{
"epoch": 1.463807702813439,
"grad_norm": 0.9386002421379089,
"learning_rate": 8.479010925819436e-06,
"loss": 0.8543,
"step": 2680
},
{
"epoch": 1.4665391969407267,
"grad_norm": 0.713670551776886,
"learning_rate": 8.43588269120184e-06,
"loss": 0.807,
"step": 2685
},
{
"epoch": 1.4692706910680142,
"grad_norm": 0.7260085344314575,
"learning_rate": 8.392754456584243e-06,
"loss": 0.8553,
"step": 2690
},
{
"epoch": 1.4720021851953018,
"grad_norm": 0.7840970754623413,
"learning_rate": 8.349626221966647e-06,
"loss": 0.762,
"step": 2695
},
{
"epoch": 1.4747336793225894,
"grad_norm": 0.7410457730293274,
"learning_rate": 8.306497987349052e-06,
"loss": 0.7904,
"step": 2700
},
{
"epoch": 1.4747336793225894,
"eval_loss": 0.9441689848899841,
"eval_runtime": 301.0517,
"eval_samples_per_second": 11.696,
"eval_steps_per_second": 2.926,
"step": 2700
},
{
"epoch": 1.4774651734498772,
"grad_norm": 0.7552523016929626,
"learning_rate": 8.263369752731456e-06,
"loss": 0.8074,
"step": 2705
},
{
"epoch": 1.4801966675771647,
"grad_norm": 0.7052621841430664,
"learning_rate": 8.220241518113859e-06,
"loss": 0.7971,
"step": 2710
},
{
"epoch": 1.4829281617044523,
"grad_norm": 0.7879542708396912,
"learning_rate": 8.177113283496263e-06,
"loss": 0.8643,
"step": 2715
},
{
"epoch": 1.48565965583174,
"grad_norm": 0.7303378582000732,
"learning_rate": 8.133985048878666e-06,
"loss": 0.8859,
"step": 2720
},
{
"epoch": 1.4883911499590277,
"grad_norm": 0.7375146150588989,
"learning_rate": 8.09085681426107e-06,
"loss": 0.8092,
"step": 2725
},
{
"epoch": 1.4911226440863152,
"grad_norm": 0.8698132038116455,
"learning_rate": 8.047728579643473e-06,
"loss": 0.8553,
"step": 2730
},
{
"epoch": 1.4938541382136028,
"grad_norm": 0.7611997723579407,
"learning_rate": 8.004600345025877e-06,
"loss": 0.8381,
"step": 2735
},
{
"epoch": 1.4965856323408904,
"grad_norm": 0.6923120617866516,
"learning_rate": 7.961472110408281e-06,
"loss": 0.8,
"step": 2740
},
{
"epoch": 1.4993171264681782,
"grad_norm": 0.7281080484390259,
"learning_rate": 7.918343875790686e-06,
"loss": 0.8483,
"step": 2745
},
{
"epoch": 1.5020486205954657,
"grad_norm": 0.7408185601234436,
"learning_rate": 7.875215641173089e-06,
"loss": 0.8345,
"step": 2750
},
{
"epoch": 1.5047801147227533,
"grad_norm": 0.8271670341491699,
"learning_rate": 7.832087406555493e-06,
"loss": 0.8682,
"step": 2755
},
{
"epoch": 1.507511608850041,
"grad_norm": 0.7656266093254089,
"learning_rate": 7.788959171937896e-06,
"loss": 0.7815,
"step": 2760
},
{
"epoch": 1.5102431029773284,
"grad_norm": 0.8432281017303467,
"learning_rate": 7.745830937320298e-06,
"loss": 0.8209,
"step": 2765
},
{
"epoch": 1.5129745971046162,
"grad_norm": 0.6880435943603516,
"learning_rate": 7.702702702702703e-06,
"loss": 0.8327,
"step": 2770
},
{
"epoch": 1.5157060912319038,
"grad_norm": 0.755211591720581,
"learning_rate": 7.659574468085105e-06,
"loss": 0.7772,
"step": 2775
},
{
"epoch": 1.5184375853591914,
"grad_norm": 0.7103990316390991,
"learning_rate": 7.61644623346751e-06,
"loss": 0.7692,
"step": 2780
},
{
"epoch": 1.5211690794864792,
"grad_norm": 0.6834583878517151,
"learning_rate": 7.573317998849915e-06,
"loss": 0.8033,
"step": 2785
},
{
"epoch": 1.5239005736137667,
"grad_norm": 0.7348767518997192,
"learning_rate": 7.530189764232318e-06,
"loss": 0.8424,
"step": 2790
},
{
"epoch": 1.5266320677410543,
"grad_norm": 0.6979133486747742,
"learning_rate": 7.487061529614722e-06,
"loss": 0.8531,
"step": 2795
},
{
"epoch": 1.529363561868342,
"grad_norm": 0.7166607975959778,
"learning_rate": 7.443933294997125e-06,
"loss": 0.8352,
"step": 2800
},
{
"epoch": 1.5320950559956295,
"grad_norm": 0.728095531463623,
"learning_rate": 7.400805060379529e-06,
"loss": 0.7986,
"step": 2805
},
{
"epoch": 1.5348265501229172,
"grad_norm": 0.7192780375480652,
"learning_rate": 7.357676825761932e-06,
"loss": 0.8487,
"step": 2810
},
{
"epoch": 1.5375580442502048,
"grad_norm": 0.7558136582374573,
"learning_rate": 7.314548591144337e-06,
"loss": 0.7731,
"step": 2815
},
{
"epoch": 1.5402895383774924,
"grad_norm": 0.7416742444038391,
"learning_rate": 7.271420356526739e-06,
"loss": 0.8703,
"step": 2820
},
{
"epoch": 1.5430210325047802,
"grad_norm": 0.7492592930793762,
"learning_rate": 7.228292121909143e-06,
"loss": 0.8543,
"step": 2825
},
{
"epoch": 1.5457525266320677,
"grad_norm": 0.735135018825531,
"learning_rate": 7.1851638872915464e-06,
"loss": 0.8182,
"step": 2830
},
{
"epoch": 1.5484840207593553,
"grad_norm": 0.7999926805496216,
"learning_rate": 7.142035652673951e-06,
"loss": 0.8357,
"step": 2835
},
{
"epoch": 1.551215514886643,
"grad_norm": 0.6479154229164124,
"learning_rate": 7.098907418056354e-06,
"loss": 0.818,
"step": 2840
},
{
"epoch": 1.5539470090139305,
"grad_norm": 0.7310101985931396,
"learning_rate": 7.055779183438758e-06,
"loss": 0.8128,
"step": 2845
},
{
"epoch": 1.5566785031412183,
"grad_norm": 0.8505690693855286,
"learning_rate": 7.012650948821161e-06,
"loss": 0.8962,
"step": 2850
},
{
"epoch": 1.5594099972685058,
"grad_norm": 0.7174296379089355,
"learning_rate": 6.969522714203566e-06,
"loss": 0.8713,
"step": 2855
},
{
"epoch": 1.5621414913957934,
"grad_norm": 0.8072212934494019,
"learning_rate": 6.926394479585969e-06,
"loss": 0.8519,
"step": 2860
},
{
"epoch": 1.5648729855230812,
"grad_norm": 0.7206900119781494,
"learning_rate": 6.883266244968373e-06,
"loss": 0.8267,
"step": 2865
},
{
"epoch": 1.5676044796503688,
"grad_norm": 0.8404891490936279,
"learning_rate": 6.840138010350776e-06,
"loss": 0.7637,
"step": 2870
},
{
"epoch": 1.5703359737776563,
"grad_norm": 0.7053221464157104,
"learning_rate": 6.79700977573318e-06,
"loss": 0.866,
"step": 2875
},
{
"epoch": 1.5730674679049441,
"grad_norm": 0.6834285259246826,
"learning_rate": 6.753881541115584e-06,
"loss": 0.7982,
"step": 2880
},
{
"epoch": 1.5757989620322315,
"grad_norm": 0.6242473125457764,
"learning_rate": 6.710753306497988e-06,
"loss": 0.7846,
"step": 2885
},
{
"epoch": 1.5785304561595193,
"grad_norm": 0.7751233577728271,
"learning_rate": 6.667625071880391e-06,
"loss": 0.7999,
"step": 2890
},
{
"epoch": 1.581261950286807,
"grad_norm": 0.6637606024742126,
"learning_rate": 6.624496837262795e-06,
"loss": 0.8333,
"step": 2895
},
{
"epoch": 1.5839934444140944,
"grad_norm": 0.6839407086372375,
"learning_rate": 6.581368602645199e-06,
"loss": 0.8095,
"step": 2900
},
{
"epoch": 1.5867249385413822,
"grad_norm": 0.6986004114151001,
"learning_rate": 6.5382403680276025e-06,
"loss": 0.8145,
"step": 2905
},
{
"epoch": 1.5894564326686698,
"grad_norm": 0.6816026568412781,
"learning_rate": 6.495112133410006e-06,
"loss": 0.8627,
"step": 2910
},
{
"epoch": 1.5921879267959573,
"grad_norm": 0.741155207157135,
"learning_rate": 6.4519838987924095e-06,
"loss": 0.8205,
"step": 2915
},
{
"epoch": 1.5949194209232451,
"grad_norm": 0.7307175993919373,
"learning_rate": 6.408855664174814e-06,
"loss": 0.8277,
"step": 2920
},
{
"epoch": 1.5976509150505327,
"grad_norm": 0.7820848822593689,
"learning_rate": 6.365727429557217e-06,
"loss": 0.8987,
"step": 2925
},
{
"epoch": 1.6003824091778203,
"grad_norm": 1.0657157897949219,
"learning_rate": 6.322599194939621e-06,
"loss": 0.8832,
"step": 2930
},
{
"epoch": 1.603113903305108,
"grad_norm": 0.7115588784217834,
"learning_rate": 6.2794709603220244e-06,
"loss": 0.8223,
"step": 2935
},
{
"epoch": 1.6058453974323954,
"grad_norm": 0.7738519906997681,
"learning_rate": 6.236342725704428e-06,
"loss": 0.8419,
"step": 2940
},
{
"epoch": 1.6085768915596832,
"grad_norm": 0.803810179233551,
"learning_rate": 6.1932144910868315e-06,
"loss": 0.8971,
"step": 2945
},
{
"epoch": 1.6113083856869708,
"grad_norm": 0.7021570801734924,
"learning_rate": 6.150086256469235e-06,
"loss": 0.7942,
"step": 2950
},
{
"epoch": 1.6140398798142583,
"grad_norm": 0.7227820754051208,
"learning_rate": 6.1069580218516385e-06,
"loss": 0.8428,
"step": 2955
},
{
"epoch": 1.6167713739415461,
"grad_norm": 0.6469954252243042,
"learning_rate": 6.063829787234042e-06,
"loss": 0.7956,
"step": 2960
},
{
"epoch": 1.6195028680688337,
"grad_norm": 0.8556625247001648,
"learning_rate": 6.020701552616446e-06,
"loss": 0.8597,
"step": 2965
},
{
"epoch": 1.6222343621961213,
"grad_norm": 0.8201519250869751,
"learning_rate": 5.97757331799885e-06,
"loss": 0.8307,
"step": 2970
},
{
"epoch": 1.624965856323409,
"grad_norm": 0.7724832892417908,
"learning_rate": 5.934445083381253e-06,
"loss": 0.8356,
"step": 2975
},
{
"epoch": 1.6276973504506964,
"grad_norm": 0.8077118992805481,
"learning_rate": 5.891316848763657e-06,
"loss": 0.866,
"step": 2980
},
{
"epoch": 1.6304288445779842,
"grad_norm": 0.77112877368927,
"learning_rate": 5.848188614146061e-06,
"loss": 0.8655,
"step": 2985
},
{
"epoch": 1.6331603387052718,
"grad_norm": 0.7135609984397888,
"learning_rate": 5.805060379528465e-06,
"loss": 0.8123,
"step": 2990
},
{
"epoch": 1.6358918328325593,
"grad_norm": 0.728249192237854,
"learning_rate": 5.761932144910868e-06,
"loss": 0.8586,
"step": 2995
},
{
"epoch": 1.6386233269598471,
"grad_norm": 0.8270325660705566,
"learning_rate": 5.718803910293272e-06,
"loss": 0.8192,
"step": 3000
},
{
"epoch": 1.6386233269598471,
"eval_loss": 0.9388798475265503,
"eval_runtime": 300.7263,
"eval_samples_per_second": 11.708,
"eval_steps_per_second": 2.93,
"step": 3000
},
{
"epoch": 1.6413548210871347,
"grad_norm": 0.6866654753684998,
"learning_rate": 5.675675675675676e-06,
"loss": 0.8,
"step": 3005
},
{
"epoch": 1.6440863152144223,
"grad_norm": 0.7318571209907532,
"learning_rate": 5.63254744105808e-06,
"loss": 0.8246,
"step": 3010
},
{
"epoch": 1.64681780934171,
"grad_norm": 0.7500631809234619,
"learning_rate": 5.589419206440483e-06,
"loss": 0.8936,
"step": 3015
},
{
"epoch": 1.6495493034689974,
"grad_norm": 0.7019023299217224,
"learning_rate": 5.546290971822887e-06,
"loss": 0.858,
"step": 3020
},
{
"epoch": 1.6522807975962852,
"grad_norm": 0.7267279624938965,
"learning_rate": 5.503162737205291e-06,
"loss": 0.8347,
"step": 3025
},
{
"epoch": 1.6550122917235728,
"grad_norm": 0.6996795535087585,
"learning_rate": 5.4600345025876946e-06,
"loss": 0.7644,
"step": 3030
},
{
"epoch": 1.6577437858508604,
"grad_norm": 0.8153805136680603,
"learning_rate": 5.416906267970098e-06,
"loss": 0.8255,
"step": 3035
},
{
"epoch": 1.6604752799781481,
"grad_norm": 0.7931836247444153,
"learning_rate": 5.373778033352502e-06,
"loss": 0.7945,
"step": 3040
},
{
"epoch": 1.6632067741054357,
"grad_norm": 0.7283747792243958,
"learning_rate": 5.330649798734906e-06,
"loss": 0.8604,
"step": 3045
},
{
"epoch": 1.6659382682327233,
"grad_norm": 0.789698600769043,
"learning_rate": 5.2875215641173095e-06,
"loss": 0.8318,
"step": 3050
},
{
"epoch": 1.668669762360011,
"grad_norm": 0.7711718082427979,
"learning_rate": 5.244393329499713e-06,
"loss": 0.8161,
"step": 3055
},
{
"epoch": 1.6714012564872984,
"grad_norm": 0.6737769246101379,
"learning_rate": 5.2012650948821165e-06,
"loss": 0.8275,
"step": 3060
},
{
"epoch": 1.6741327506145862,
"grad_norm": 0.6363145709037781,
"learning_rate": 5.158136860264519e-06,
"loss": 0.771,
"step": 3065
},
{
"epoch": 1.6768642447418738,
"grad_norm": 0.6760769486427307,
"learning_rate": 5.1150086256469235e-06,
"loss": 0.8379,
"step": 3070
},
{
"epoch": 1.6795957388691614,
"grad_norm": 0.7138999104499817,
"learning_rate": 5.071880391029327e-06,
"loss": 0.8812,
"step": 3075
},
{
"epoch": 1.6823272329964492,
"grad_norm": 0.8640497326850891,
"learning_rate": 5.0287521564117306e-06,
"loss": 0.8405,
"step": 3080
},
{
"epoch": 1.6850587271237367,
"grad_norm": 0.7529298663139343,
"learning_rate": 4.985623921794134e-06,
"loss": 0.8373,
"step": 3085
},
{
"epoch": 1.6877902212510243,
"grad_norm": 0.7427359819412231,
"learning_rate": 4.9424956871765384e-06,
"loss": 0.8225,
"step": 3090
},
{
"epoch": 1.690521715378312,
"grad_norm": 0.7428495287895203,
"learning_rate": 4.899367452558942e-06,
"loss": 0.8534,
"step": 3095
},
{
"epoch": 1.6932532095055994,
"grad_norm": 0.7773987054824829,
"learning_rate": 4.8562392179413455e-06,
"loss": 0.8536,
"step": 3100
},
{
"epoch": 1.6959847036328872,
"grad_norm": 0.7582395672798157,
"learning_rate": 4.813110983323749e-06,
"loss": 0.7629,
"step": 3105
},
{
"epoch": 1.6987161977601748,
"grad_norm": 0.7156893610954285,
"learning_rate": 4.769982748706153e-06,
"loss": 0.8006,
"step": 3110
},
{
"epoch": 1.7014476918874624,
"grad_norm": 0.7617497444152832,
"learning_rate": 4.726854514088557e-06,
"loss": 0.8285,
"step": 3115
},
{
"epoch": 1.7041791860147502,
"grad_norm": 0.7520387172698975,
"learning_rate": 4.68372627947096e-06,
"loss": 0.8608,
"step": 3120
},
{
"epoch": 1.7069106801420377,
"grad_norm": 0.6886020302772522,
"learning_rate": 4.640598044853364e-06,
"loss": 0.8259,
"step": 3125
},
{
"epoch": 1.7096421742693253,
"grad_norm": 0.8330241441726685,
"learning_rate": 4.597469810235768e-06,
"loss": 0.7891,
"step": 3130
},
{
"epoch": 1.712373668396613,
"grad_norm": 0.7715080976486206,
"learning_rate": 4.554341575618172e-06,
"loss": 0.828,
"step": 3135
},
{
"epoch": 1.7151051625239004,
"grad_norm": 0.7944726943969727,
"learning_rate": 4.511213341000575e-06,
"loss": 0.7786,
"step": 3140
},
{
"epoch": 1.7178366566511882,
"grad_norm": 0.7173528075218201,
"learning_rate": 4.468085106382979e-06,
"loss": 0.8248,
"step": 3145
},
{
"epoch": 1.7205681507784758,
"grad_norm": 0.7944976091384888,
"learning_rate": 4.424956871765382e-06,
"loss": 0.8543,
"step": 3150
},
{
"epoch": 1.7232996449057634,
"grad_norm": 0.7700731158256531,
"learning_rate": 4.381828637147787e-06,
"loss": 0.8077,
"step": 3155
},
{
"epoch": 1.7260311390330512,
"grad_norm": 0.7129545211791992,
"learning_rate": 4.33870040253019e-06,
"loss": 0.8458,
"step": 3160
},
{
"epoch": 1.7287626331603387,
"grad_norm": 0.7916214466094971,
"learning_rate": 4.295572167912594e-06,
"loss": 0.828,
"step": 3165
},
{
"epoch": 1.7314941272876263,
"grad_norm": 0.7434884309768677,
"learning_rate": 4.252443933294997e-06,
"loss": 0.8267,
"step": 3170
},
{
"epoch": 1.734225621414914,
"grad_norm": 0.7301231622695923,
"learning_rate": 4.2093156986774015e-06,
"loss": 0.8221,
"step": 3175
},
{
"epoch": 1.7369571155422014,
"grad_norm": 0.6785838603973389,
"learning_rate": 4.166187464059805e-06,
"loss": 0.795,
"step": 3180
},
{
"epoch": 1.7396886096694892,
"grad_norm": 0.6249417066574097,
"learning_rate": 4.1230592294422086e-06,
"loss": 0.7943,
"step": 3185
},
{
"epoch": 1.7424201037967768,
"grad_norm": 0.7639848589897156,
"learning_rate": 4.079930994824611e-06,
"loss": 0.7893,
"step": 3190
},
{
"epoch": 1.7451515979240644,
"grad_norm": 0.7818441987037659,
"learning_rate": 4.036802760207016e-06,
"loss": 0.8562,
"step": 3195
},
{
"epoch": 1.7478830920513522,
"grad_norm": 0.8730034232139587,
"learning_rate": 3.993674525589419e-06,
"loss": 0.8542,
"step": 3200
},
{
"epoch": 1.7506145861786397,
"grad_norm": 0.6441556215286255,
"learning_rate": 3.950546290971823e-06,
"loss": 0.7838,
"step": 3205
},
{
"epoch": 1.7533460803059273,
"grad_norm": 0.6805165410041809,
"learning_rate": 3.907418056354226e-06,
"loss": 0.7945,
"step": 3210
},
{
"epoch": 1.756077574433215,
"grad_norm": 0.7056381106376648,
"learning_rate": 3.8642898217366305e-06,
"loss": 0.8046,
"step": 3215
},
{
"epoch": 1.7588090685605025,
"grad_norm": 0.7608081698417664,
"learning_rate": 3.821161587119034e-06,
"loss": 0.8143,
"step": 3220
},
{
"epoch": 1.7615405626877902,
"grad_norm": 0.7973917722702026,
"learning_rate": 3.7780333525014375e-06,
"loss": 0.8942,
"step": 3225
},
{
"epoch": 1.7642720568150778,
"grad_norm": 0.77592933177948,
"learning_rate": 3.7349051178838415e-06,
"loss": 0.8009,
"step": 3230
},
{
"epoch": 1.7670035509423654,
"grad_norm": 0.6842568516731262,
"learning_rate": 3.691776883266245e-06,
"loss": 0.8346,
"step": 3235
},
{
"epoch": 1.7697350450696532,
"grad_norm": 0.6500614881515503,
"learning_rate": 3.648648648648649e-06,
"loss": 0.8363,
"step": 3240
},
{
"epoch": 1.7724665391969407,
"grad_norm": 0.8021740317344666,
"learning_rate": 3.6055204140310524e-06,
"loss": 0.8026,
"step": 3245
},
{
"epoch": 1.7751980333242283,
"grad_norm": 0.7573009133338928,
"learning_rate": 3.562392179413456e-06,
"loss": 0.8014,
"step": 3250
},
{
"epoch": 1.7779295274515161,
"grad_norm": 0.8284993171691895,
"learning_rate": 3.51926394479586e-06,
"loss": 0.7968,
"step": 3255
},
{
"epoch": 1.7806610215788035,
"grad_norm": 0.9808593988418579,
"learning_rate": 3.4761357101782634e-06,
"loss": 0.8956,
"step": 3260
},
{
"epoch": 1.7833925157060913,
"grad_norm": 0.801047146320343,
"learning_rate": 3.4330074755606673e-06,
"loss": 0.8086,
"step": 3265
},
{
"epoch": 1.7861240098333788,
"grad_norm": 0.6470543146133423,
"learning_rate": 3.389879240943071e-06,
"loss": 0.7439,
"step": 3270
},
{
"epoch": 1.7888555039606664,
"grad_norm": 0.7826109528541565,
"learning_rate": 3.3467510063254748e-06,
"loss": 0.8315,
"step": 3275
},
{
"epoch": 1.7915869980879542,
"grad_norm": 0.7127923965454102,
"learning_rate": 3.303622771707878e-06,
"loss": 0.8047,
"step": 3280
},
{
"epoch": 1.7943184922152418,
"grad_norm": 0.7150490880012512,
"learning_rate": 3.260494537090282e-06,
"loss": 0.8151,
"step": 3285
},
{
"epoch": 1.7970499863425293,
"grad_norm": 0.6673474907875061,
"learning_rate": 3.2173663024726853e-06,
"loss": 0.8047,
"step": 3290
},
{
"epoch": 1.7997814804698171,
"grad_norm": 0.7676151394844055,
"learning_rate": 3.1742380678550892e-06,
"loss": 0.8339,
"step": 3295
},
{
"epoch": 1.8025129745971045,
"grad_norm": 0.8165467977523804,
"learning_rate": 3.1311098332374928e-06,
"loss": 0.8592,
"step": 3300
},
{
"epoch": 1.8025129745971045,
"eval_loss": 0.9352796673774719,
"eval_runtime": 299.4496,
"eval_samples_per_second": 11.758,
"eval_steps_per_second": 2.942,
"step": 3300
},
{
"epoch": 1.8052444687243923,
"grad_norm": 0.8313693404197693,
"learning_rate": 3.0879815986198967e-06,
"loss": 0.8396,
"step": 3305
},
{
"epoch": 1.8079759628516798,
"grad_norm": 0.8412713408470154,
"learning_rate": 3.0448533640023e-06,
"loss": 0.8887,
"step": 3310
},
{
"epoch": 1.8107074569789674,
"grad_norm": 0.6956152319908142,
"learning_rate": 3.001725129384704e-06,
"loss": 0.8436,
"step": 3315
},
{
"epoch": 1.8134389511062552,
"grad_norm": 0.9303175210952759,
"learning_rate": 2.9585968947671077e-06,
"loss": 0.8425,
"step": 3320
},
{
"epoch": 1.8161704452335428,
"grad_norm": 0.6691704988479614,
"learning_rate": 2.9154686601495116e-06,
"loss": 0.7799,
"step": 3325
},
{
"epoch": 1.8189019393608303,
"grad_norm": 0.6424058079719543,
"learning_rate": 2.872340425531915e-06,
"loss": 0.7835,
"step": 3330
},
{
"epoch": 1.8216334334881181,
"grad_norm": 0.7195141315460205,
"learning_rate": 2.829212190914319e-06,
"loss": 0.7964,
"step": 3335
},
{
"epoch": 1.8243649276154055,
"grad_norm": 0.7766082286834717,
"learning_rate": 2.786083956296722e-06,
"loss": 0.7849,
"step": 3340
},
{
"epoch": 1.8270964217426933,
"grad_norm": 0.7251452803611755,
"learning_rate": 2.7429557216791256e-06,
"loss": 0.8789,
"step": 3345
},
{
"epoch": 1.8298279158699808,
"grad_norm": 0.8340855836868286,
"learning_rate": 2.6998274870615296e-06,
"loss": 0.839,
"step": 3350
},
{
"epoch": 1.8325594099972684,
"grad_norm": 0.777708113193512,
"learning_rate": 2.656699252443933e-06,
"loss": 0.8307,
"step": 3355
},
{
"epoch": 1.8352909041245562,
"grad_norm": 0.7656396627426147,
"learning_rate": 2.613571017826337e-06,
"loss": 0.8267,
"step": 3360
},
{
"epoch": 1.8380223982518438,
"grad_norm": 0.7076913714408875,
"learning_rate": 2.5704427832087405e-06,
"loss": 0.8568,
"step": 3365
},
{
"epoch": 1.8407538923791313,
"grad_norm": 0.8412337899208069,
"learning_rate": 2.5273145485911445e-06,
"loss": 0.8134,
"step": 3370
},
{
"epoch": 1.8434853865064191,
"grad_norm": 0.6766529679298401,
"learning_rate": 2.484186313973548e-06,
"loss": 0.8416,
"step": 3375
},
{
"epoch": 1.8462168806337065,
"grad_norm": 0.8257123827934265,
"learning_rate": 2.441058079355952e-06,
"loss": 0.7869,
"step": 3380
},
{
"epoch": 1.8489483747609943,
"grad_norm": 0.8125414252281189,
"learning_rate": 2.3979298447383554e-06,
"loss": 0.8212,
"step": 3385
},
{
"epoch": 1.8516798688882818,
"grad_norm": 0.7885363698005676,
"learning_rate": 2.3548016101207594e-06,
"loss": 0.8491,
"step": 3390
},
{
"epoch": 1.8544113630155694,
"grad_norm": 0.6646851301193237,
"learning_rate": 2.311673375503163e-06,
"loss": 0.7664,
"step": 3395
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.7766485810279846,
"learning_rate": 2.2685451408855664e-06,
"loss": 0.8218,
"step": 3400
},
{
"epoch": 1.8598743512701448,
"grad_norm": 0.908065676689148,
"learning_rate": 2.22541690626797e-06,
"loss": 0.8301,
"step": 3405
},
{
"epoch": 1.8626058453974323,
"grad_norm": 0.8512767553329468,
"learning_rate": 2.182288671650374e-06,
"loss": 0.8579,
"step": 3410
},
{
"epoch": 1.8653373395247201,
"grad_norm": 0.8669475317001343,
"learning_rate": 2.1391604370327774e-06,
"loss": 0.8864,
"step": 3415
},
{
"epoch": 1.8680688336520075,
"grad_norm": 0.8183215856552124,
"learning_rate": 2.0960322024151813e-06,
"loss": 0.8684,
"step": 3420
},
{
"epoch": 1.8708003277792953,
"grad_norm": 0.8169001340866089,
"learning_rate": 2.052903967797585e-06,
"loss": 0.9152,
"step": 3425
},
{
"epoch": 1.8735318219065829,
"grad_norm": 0.6913219690322876,
"learning_rate": 2.0097757331799888e-06,
"loss": 0.7813,
"step": 3430
},
{
"epoch": 1.8762633160338704,
"grad_norm": 0.7832525372505188,
"learning_rate": 1.9666474985623923e-06,
"loss": 0.8205,
"step": 3435
},
{
"epoch": 1.8789948101611582,
"grad_norm": 0.8245301246643066,
"learning_rate": 1.9235192639447958e-06,
"loss": 0.8211,
"step": 3440
},
{
"epoch": 1.8817263042884458,
"grad_norm": 0.7154508829116821,
"learning_rate": 1.8803910293271997e-06,
"loss": 0.8073,
"step": 3445
},
{
"epoch": 1.8844577984157334,
"grad_norm": 0.7859438061714172,
"learning_rate": 1.8372627947096032e-06,
"loss": 0.8366,
"step": 3450
},
{
"epoch": 1.8871892925430211,
"grad_norm": 0.800834059715271,
"learning_rate": 1.794134560092007e-06,
"loss": 0.8302,
"step": 3455
},
{
"epoch": 1.8899207866703085,
"grad_norm": 0.8212534189224243,
"learning_rate": 1.7510063254744107e-06,
"loss": 0.8022,
"step": 3460
},
{
"epoch": 1.8926522807975963,
"grad_norm": 0.8553736209869385,
"learning_rate": 1.7078780908568144e-06,
"loss": 0.8454,
"step": 3465
},
{
"epoch": 1.8953837749248839,
"grad_norm": 0.7611083984375,
"learning_rate": 1.6647498562392181e-06,
"loss": 0.8274,
"step": 3470
},
{
"epoch": 1.8981152690521714,
"grad_norm": 0.8202541470527649,
"learning_rate": 1.6216216216216219e-06,
"loss": 0.8143,
"step": 3475
},
{
"epoch": 1.9008467631794592,
"grad_norm": 0.6400332450866699,
"learning_rate": 1.5784933870040254e-06,
"loss": 0.7993,
"step": 3480
},
{
"epoch": 1.9035782573067468,
"grad_norm": 0.7497656345367432,
"learning_rate": 1.5353651523864289e-06,
"loss": 0.8165,
"step": 3485
},
{
"epoch": 1.9063097514340344,
"grad_norm": 0.7206113338470459,
"learning_rate": 1.4922369177688326e-06,
"loss": 0.8809,
"step": 3490
},
{
"epoch": 1.9090412455613222,
"grad_norm": 0.7341408729553223,
"learning_rate": 1.4491086831512363e-06,
"loss": 0.8515,
"step": 3495
},
{
"epoch": 1.9117727396886097,
"grad_norm": 0.7438867688179016,
"learning_rate": 1.40598044853364e-06,
"loss": 0.7952,
"step": 3500
},
{
"epoch": 1.9145042338158973,
"grad_norm": 0.8853686451911926,
"learning_rate": 1.3628522139160438e-06,
"loss": 0.7949,
"step": 3505
},
{
"epoch": 1.917235727943185,
"grad_norm": 0.7891769409179688,
"learning_rate": 1.3197239792984473e-06,
"loss": 0.7935,
"step": 3510
},
{
"epoch": 1.9199672220704724,
"grad_norm": 1.0255788564682007,
"learning_rate": 1.276595744680851e-06,
"loss": 0.8227,
"step": 3515
},
{
"epoch": 1.9226987161977602,
"grad_norm": 0.7512651085853577,
"learning_rate": 1.2334675100632547e-06,
"loss": 0.8014,
"step": 3520
},
{
"epoch": 1.9254302103250478,
"grad_norm": 0.6517429351806641,
"learning_rate": 1.1903392754456585e-06,
"loss": 0.8186,
"step": 3525
},
{
"epoch": 1.9281617044523354,
"grad_norm": 0.6782920956611633,
"learning_rate": 1.1472110408280622e-06,
"loss": 0.7471,
"step": 3530
},
{
"epoch": 1.9308931985796232,
"grad_norm": 0.7998325228691101,
"learning_rate": 1.104082806210466e-06,
"loss": 0.7834,
"step": 3535
},
{
"epoch": 1.9336246927069107,
"grad_norm": 0.6881343722343445,
"learning_rate": 1.0609545715928694e-06,
"loss": 0.7815,
"step": 3540
},
{
"epoch": 1.9363561868341983,
"grad_norm": 0.8117784857749939,
"learning_rate": 1.0178263369752732e-06,
"loss": 0.8221,
"step": 3545
},
{
"epoch": 1.939087680961486,
"grad_norm": 0.7323679327964783,
"learning_rate": 9.746981023576769e-07,
"loss": 0.8436,
"step": 3550
},
{
"epoch": 1.9418191750887734,
"grad_norm": 0.804025411605835,
"learning_rate": 9.315698677400805e-07,
"loss": 0.835,
"step": 3555
},
{
"epoch": 1.9445506692160612,
"grad_norm": 0.6342939734458923,
"learning_rate": 8.884416331224842e-07,
"loss": 0.7668,
"step": 3560
},
{
"epoch": 1.9472821633433488,
"grad_norm": 0.9365503787994385,
"learning_rate": 8.453133985048878e-07,
"loss": 0.847,
"step": 3565
},
{
"epoch": 1.9500136574706364,
"grad_norm": 0.7761809825897217,
"learning_rate": 8.021851638872916e-07,
"loss": 0.8816,
"step": 3570
},
{
"epoch": 1.9527451515979242,
"grad_norm": 0.7353388667106628,
"learning_rate": 7.590569292696953e-07,
"loss": 0.8459,
"step": 3575
},
{
"epoch": 1.9554766457252117,
"grad_norm": 0.7061073780059814,
"learning_rate": 7.159286946520989e-07,
"loss": 0.782,
"step": 3580
},
{
"epoch": 1.9582081398524993,
"grad_norm": 0.6874290704727173,
"learning_rate": 6.728004600345026e-07,
"loss": 0.7976,
"step": 3585
},
{
"epoch": 1.960939633979787,
"grad_norm": 0.7184991836547852,
"learning_rate": 6.296722254169064e-07,
"loss": 0.826,
"step": 3590
},
{
"epoch": 1.9636711281070744,
"grad_norm": 0.7778326272964478,
"learning_rate": 5.8654399079931e-07,
"loss": 0.8151,
"step": 3595
},
{
"epoch": 1.9664026222343622,
"grad_norm": 0.7717835307121277,
"learning_rate": 5.434157561817137e-07,
"loss": 0.8702,
"step": 3600
},
{
"epoch": 1.9664026222343622,
"eval_loss": 0.9335657954216003,
"eval_runtime": 301.3,
"eval_samples_per_second": 11.686,
"eval_steps_per_second": 2.924,
"step": 3600
},
{
"epoch": 1.9691341163616498,
"grad_norm": 0.7777953743934631,
"learning_rate": 5.002875215641173e-07,
"loss": 0.7966,
"step": 3605
},
{
"epoch": 1.9718656104889374,
"grad_norm": 0.9295082688331604,
"learning_rate": 4.5715928694652105e-07,
"loss": 0.8906,
"step": 3610
},
{
"epoch": 1.9745971046162252,
"grad_norm": 0.7250046133995056,
"learning_rate": 4.1403105232892466e-07,
"loss": 0.8249,
"step": 3615
},
{
"epoch": 1.9773285987435127,
"grad_norm": 0.8891762495040894,
"learning_rate": 3.7090281771132834e-07,
"loss": 0.8635,
"step": 3620
},
{
"epoch": 1.9800600928708003,
"grad_norm": 0.7426323294639587,
"learning_rate": 3.2777458309373206e-07,
"loss": 0.8527,
"step": 3625
},
{
"epoch": 1.982791586998088,
"grad_norm": 0.8124968409538269,
"learning_rate": 2.8464634847613573e-07,
"loss": 0.889,
"step": 3630
},
{
"epoch": 1.9855230811253755,
"grad_norm": 0.7425868511199951,
"learning_rate": 2.415181138585394e-07,
"loss": 0.7681,
"step": 3635
},
{
"epoch": 1.9882545752526632,
"grad_norm": 0.6784554123878479,
"learning_rate": 1.9838987924094308e-07,
"loss": 0.7942,
"step": 3640
},
{
"epoch": 1.9909860693799508,
"grad_norm": 0.7988487482070923,
"learning_rate": 1.5526164462334675e-07,
"loss": 0.8488,
"step": 3645
},
{
"epoch": 1.9937175635072384,
"grad_norm": 0.6853664517402649,
"learning_rate": 1.1213341000575043e-07,
"loss": 0.7516,
"step": 3650
},
{
"epoch": 1.9964490576345262,
"grad_norm": 0.8320609927177429,
"learning_rate": 6.900517538815412e-08,
"loss": 0.7944,
"step": 3655
},
{
"epoch": 1.9991805517618138,
"grad_norm": 0.7473215460777283,
"learning_rate": 2.587694077055779e-08,
"loss": 0.8585,
"step": 3660
},
{
"epoch": 2.0016388964763725,
"grad_norm": 0.7319318056106567,
"learning_rate": 1.5782664941785253e-05,
"loss": 0.8188,
"step": 3665
},
{
"epoch": 2.0043703906036603,
"grad_norm": 0.7051223516464233,
"learning_rate": 1.576110392410522e-05,
"loss": 0.7581,
"step": 3670
},
{
"epoch": 2.0071018847309476,
"grad_norm": 0.7501633763313293,
"learning_rate": 1.5739542906425185e-05,
"loss": 0.7568,
"step": 3675
},
{
"epoch": 2.0098333788582354,
"grad_norm": 0.7506686449050903,
"learning_rate": 1.5717981888745148e-05,
"loss": 0.791,
"step": 3680
},
{
"epoch": 2.0125648729855232,
"grad_norm": 0.7914782166481018,
"learning_rate": 1.5696420871065114e-05,
"loss": 0.7865,
"step": 3685
},
{
"epoch": 2.0152963671128106,
"grad_norm": 0.7318350672721863,
"learning_rate": 1.567485985338508e-05,
"loss": 0.7548,
"step": 3690
},
{
"epoch": 2.0180278612400984,
"grad_norm": 0.694589376449585,
"learning_rate": 1.5653298835705046e-05,
"loss": 0.7808,
"step": 3695
},
{
"epoch": 2.020759355367386,
"grad_norm": 0.6557597517967224,
"learning_rate": 1.563173781802501e-05,
"loss": 0.753,
"step": 3700
},
{
"epoch": 2.0234908494946735,
"grad_norm": 0.6921776533126831,
"learning_rate": 1.561017680034498e-05,
"loss": 0.8208,
"step": 3705
},
{
"epoch": 2.0262223436219613,
"grad_norm": 0.7546330094337463,
"learning_rate": 1.558861578266494e-05,
"loss": 0.7923,
"step": 3710
},
{
"epoch": 2.0289538377492486,
"grad_norm": 0.9784765243530273,
"learning_rate": 1.5567054764984907e-05,
"loss": 0.8301,
"step": 3715
},
{
"epoch": 2.0316853318765364,
"grad_norm": 0.72115159034729,
"learning_rate": 1.5545493747304873e-05,
"loss": 0.8057,
"step": 3720
},
{
"epoch": 2.0344168260038242,
"grad_norm": 0.7705895900726318,
"learning_rate": 1.552393272962484e-05,
"loss": 0.7775,
"step": 3725
},
{
"epoch": 2.0371483201311116,
"grad_norm": 0.7333831787109375,
"learning_rate": 1.5502371711944802e-05,
"loss": 0.7796,
"step": 3730
},
{
"epoch": 2.0398798142583994,
"grad_norm": 0.8714722394943237,
"learning_rate": 1.5480810694264768e-05,
"loss": 0.8728,
"step": 3735
},
{
"epoch": 2.042611308385687,
"grad_norm": 0.7178484201431274,
"learning_rate": 1.5459249676584734e-05,
"loss": 0.8011,
"step": 3740
},
{
"epoch": 2.0453428025129745,
"grad_norm": 0.7613635659217834,
"learning_rate": 1.54376886589047e-05,
"loss": 0.8263,
"step": 3745
},
{
"epoch": 2.0480742966402623,
"grad_norm": 0.7936369776725769,
"learning_rate": 1.5416127641224666e-05,
"loss": 0.7467,
"step": 3750
},
{
"epoch": 2.0508057907675497,
"grad_norm": 0.666117787361145,
"learning_rate": 1.5394566623544633e-05,
"loss": 0.8015,
"step": 3755
},
{
"epoch": 2.0535372848948374,
"grad_norm": 0.6949426531791687,
"learning_rate": 1.53730056058646e-05,
"loss": 0.8087,
"step": 3760
},
{
"epoch": 2.0562687790221252,
"grad_norm": 0.7881883382797241,
"learning_rate": 1.535144458818456e-05,
"loss": 0.8145,
"step": 3765
},
{
"epoch": 2.0590002731494126,
"grad_norm": 0.7423451542854309,
"learning_rate": 1.532988357050453e-05,
"loss": 0.7835,
"step": 3770
},
{
"epoch": 2.0617317672767004,
"grad_norm": 0.7422988414764404,
"learning_rate": 1.5308322552824494e-05,
"loss": 0.8309,
"step": 3775
},
{
"epoch": 2.064463261403988,
"grad_norm": 0.7277097105979919,
"learning_rate": 1.528676153514446e-05,
"loss": 0.7736,
"step": 3780
},
{
"epoch": 2.0671947555312755,
"grad_norm": 0.7224512100219727,
"learning_rate": 1.5265200517464422e-05,
"loss": 0.8018,
"step": 3785
},
{
"epoch": 2.0699262496585633,
"grad_norm": 0.6958188414573669,
"learning_rate": 1.524363949978439e-05,
"loss": 0.8336,
"step": 3790
},
{
"epoch": 2.0726577437858507,
"grad_norm": 0.7252750992774963,
"learning_rate": 1.5222078482104354e-05,
"loss": 0.7878,
"step": 3795
},
{
"epoch": 2.0753892379131385,
"grad_norm": 0.758294403553009,
"learning_rate": 1.5200517464424322e-05,
"loss": 0.7854,
"step": 3800
},
{
"epoch": 2.0781207320404262,
"grad_norm": 0.752086877822876,
"learning_rate": 1.5178956446744285e-05,
"loss": 0.8175,
"step": 3805
},
{
"epoch": 2.0808522261677136,
"grad_norm": 0.895892322063446,
"learning_rate": 1.5157395429064253e-05,
"loss": 0.8081,
"step": 3810
},
{
"epoch": 2.0835837202950014,
"grad_norm": 0.8314038515090942,
"learning_rate": 1.5135834411384215e-05,
"loss": 0.7869,
"step": 3815
},
{
"epoch": 2.086315214422289,
"grad_norm": 0.7267419099807739,
"learning_rate": 1.5114273393704183e-05,
"loss": 0.7649,
"step": 3820
},
{
"epoch": 2.0890467085495765,
"grad_norm": 0.701091468334198,
"learning_rate": 1.5092712376024151e-05,
"loss": 0.8043,
"step": 3825
},
{
"epoch": 2.0917782026768643,
"grad_norm": 0.7192620038986206,
"learning_rate": 1.5071151358344114e-05,
"loss": 0.7558,
"step": 3830
},
{
"epoch": 2.0945096968041517,
"grad_norm": 0.8244616389274597,
"learning_rate": 1.5049590340664081e-05,
"loss": 0.8201,
"step": 3835
},
{
"epoch": 2.0972411909314395,
"grad_norm": 0.7200716733932495,
"learning_rate": 1.5028029322984044e-05,
"loss": 0.7394,
"step": 3840
},
{
"epoch": 2.0999726850587273,
"grad_norm": 0.9516389966011047,
"learning_rate": 1.5006468305304012e-05,
"loss": 0.8358,
"step": 3845
},
{
"epoch": 2.1027041791860146,
"grad_norm": 0.7172725200653076,
"learning_rate": 1.4984907287623976e-05,
"loss": 0.8957,
"step": 3850
},
{
"epoch": 2.1054356733133024,
"grad_norm": 0.6775708198547363,
"learning_rate": 1.496334626994394e-05,
"loss": 0.8274,
"step": 3855
},
{
"epoch": 2.10816716744059,
"grad_norm": 0.6522817015647888,
"learning_rate": 1.4941785252263907e-05,
"loss": 0.7731,
"step": 3860
},
{
"epoch": 2.1108986615678775,
"grad_norm": 0.830079972743988,
"learning_rate": 1.4920224234583873e-05,
"loss": 0.8334,
"step": 3865
},
{
"epoch": 2.1136301556951653,
"grad_norm": 0.8399609327316284,
"learning_rate": 1.4898663216903839e-05,
"loss": 0.8273,
"step": 3870
},
{
"epoch": 2.1163616498224527,
"grad_norm": 0.7075542211532593,
"learning_rate": 1.4877102199223805e-05,
"loss": 0.8263,
"step": 3875
},
{
"epoch": 2.1190931439497405,
"grad_norm": 0.8559184670448303,
"learning_rate": 1.485554118154377e-05,
"loss": 0.7854,
"step": 3880
},
{
"epoch": 2.1218246380770283,
"grad_norm": 0.7275727987289429,
"learning_rate": 1.4833980163863736e-05,
"loss": 0.7714,
"step": 3885
},
{
"epoch": 2.1245561322043156,
"grad_norm": 0.6957250237464905,
"learning_rate": 1.48124191461837e-05,
"loss": 0.7886,
"step": 3890
},
{
"epoch": 2.1272876263316034,
"grad_norm": 0.7279730439186096,
"learning_rate": 1.4790858128503666e-05,
"loss": 0.7642,
"step": 3895
},
{
"epoch": 2.130019120458891,
"grad_norm": 0.6682025790214539,
"learning_rate": 1.4769297110823632e-05,
"loss": 0.8177,
"step": 3900
},
{
"epoch": 2.130019120458891,
"eval_loss": 0.9341248869895935,
"eval_runtime": 296.5102,
"eval_samples_per_second": 11.875,
"eval_steps_per_second": 2.971,
"step": 3900
},
{
"epoch": 2.1327506145861785,
"grad_norm": 0.6160957217216492,
"learning_rate": 1.4747736093143596e-05,
"loss": 0.766,
"step": 3905
},
{
"epoch": 2.1354821087134663,
"grad_norm": 0.8791837096214294,
"learning_rate": 1.4726175075463563e-05,
"loss": 0.7801,
"step": 3910
},
{
"epoch": 2.1382136028407537,
"grad_norm": 0.6789302229881287,
"learning_rate": 1.4704614057783527e-05,
"loss": 0.7746,
"step": 3915
},
{
"epoch": 2.1409450969680415,
"grad_norm": 0.6534218192100525,
"learning_rate": 1.4683053040103493e-05,
"loss": 0.7422,
"step": 3920
},
{
"epoch": 2.1436765910953293,
"grad_norm": 0.6851027607917786,
"learning_rate": 1.4661492022423459e-05,
"loss": 0.762,
"step": 3925
},
{
"epoch": 2.1464080852226166,
"grad_norm": 0.8011928200721741,
"learning_rate": 1.4639931004743423e-05,
"loss": 0.7665,
"step": 3930
},
{
"epoch": 2.1491395793499044,
"grad_norm": 0.8282194137573242,
"learning_rate": 1.461836998706339e-05,
"loss": 0.8187,
"step": 3935
},
{
"epoch": 2.151871073477192,
"grad_norm": 0.7016075253486633,
"learning_rate": 1.4596808969383354e-05,
"loss": 0.7601,
"step": 3940
},
{
"epoch": 2.1546025676044795,
"grad_norm": 0.7013123631477356,
"learning_rate": 1.4575247951703322e-05,
"loss": 0.7542,
"step": 3945
},
{
"epoch": 2.1573340617317673,
"grad_norm": 0.7040947675704956,
"learning_rate": 1.4553686934023288e-05,
"loss": 0.7981,
"step": 3950
},
{
"epoch": 2.160065555859055,
"grad_norm": 0.8876264095306396,
"learning_rate": 1.4532125916343252e-05,
"loss": 0.8221,
"step": 3955
},
{
"epoch": 2.1627970499863425,
"grad_norm": 0.6969845294952393,
"learning_rate": 1.4510564898663218e-05,
"loss": 0.8246,
"step": 3960
},
{
"epoch": 2.1655285441136303,
"grad_norm": 0.8121285438537598,
"learning_rate": 1.4489003880983183e-05,
"loss": 0.8392,
"step": 3965
},
{
"epoch": 2.1682600382409176,
"grad_norm": 0.7749564051628113,
"learning_rate": 1.4467442863303149e-05,
"loss": 0.8084,
"step": 3970
},
{
"epoch": 2.1709915323682054,
"grad_norm": 0.9159696698188782,
"learning_rate": 1.4445881845623113e-05,
"loss": 0.8563,
"step": 3975
},
{
"epoch": 2.173723026495493,
"grad_norm": 0.8330530524253845,
"learning_rate": 1.442432082794308e-05,
"loss": 0.7882,
"step": 3980
},
{
"epoch": 2.1764545206227806,
"grad_norm": 0.6948736906051636,
"learning_rate": 1.4402759810263045e-05,
"loss": 0.8164,
"step": 3985
},
{
"epoch": 2.1791860147500683,
"grad_norm": 0.8895037174224854,
"learning_rate": 1.438119879258301e-05,
"loss": 0.7705,
"step": 3990
},
{
"epoch": 2.1819175088773557,
"grad_norm": 0.6750216484069824,
"learning_rate": 1.4359637774902976e-05,
"loss": 0.7435,
"step": 3995
},
{
"epoch": 2.1846490030046435,
"grad_norm": 0.7232965230941772,
"learning_rate": 1.433807675722294e-05,
"loss": 0.8289,
"step": 4000
},
{
"epoch": 2.1873804971319313,
"grad_norm": 0.7342071533203125,
"learning_rate": 1.4316515739542906e-05,
"loss": 0.7838,
"step": 4005
},
{
"epoch": 2.1901119912592186,
"grad_norm": 0.6869019269943237,
"learning_rate": 1.4294954721862872e-05,
"loss": 0.7482,
"step": 4010
},
{
"epoch": 2.1928434853865064,
"grad_norm": 0.8189377784729004,
"learning_rate": 1.4273393704182837e-05,
"loss": 0.7861,
"step": 4015
},
{
"epoch": 2.195574979513794,
"grad_norm": 0.7131912112236023,
"learning_rate": 1.4251832686502803e-05,
"loss": 0.7488,
"step": 4020
},
{
"epoch": 2.1983064736410816,
"grad_norm": 0.6690083146095276,
"learning_rate": 1.4230271668822767e-05,
"loss": 0.7593,
"step": 4025
},
{
"epoch": 2.2010379677683694,
"grad_norm": 0.7157140970230103,
"learning_rate": 1.4208710651142735e-05,
"loss": 0.8124,
"step": 4030
},
{
"epoch": 2.203769461895657,
"grad_norm": 0.7318872809410095,
"learning_rate": 1.4187149633462701e-05,
"loss": 0.793,
"step": 4035
},
{
"epoch": 2.2065009560229445,
"grad_norm": 0.7739484906196594,
"learning_rate": 1.4165588615782665e-05,
"loss": 0.788,
"step": 4040
},
{
"epoch": 2.2092324501502323,
"grad_norm": 0.7915065288543701,
"learning_rate": 1.4144027598102632e-05,
"loss": 0.8171,
"step": 4045
},
{
"epoch": 2.2119639442775196,
"grad_norm": 0.7829121351242065,
"learning_rate": 1.4122466580422596e-05,
"loss": 0.7548,
"step": 4050
},
{
"epoch": 2.2146954384048074,
"grad_norm": 0.7062816619873047,
"learning_rate": 1.4100905562742562e-05,
"loss": 0.7894,
"step": 4055
},
{
"epoch": 2.217426932532095,
"grad_norm": 0.7477509379386902,
"learning_rate": 1.4079344545062528e-05,
"loss": 0.8622,
"step": 4060
},
{
"epoch": 2.2201584266593826,
"grad_norm": 0.7906818389892578,
"learning_rate": 1.4057783527382493e-05,
"loss": 0.7972,
"step": 4065
},
{
"epoch": 2.2228899207866704,
"grad_norm": 0.9905873537063599,
"learning_rate": 1.4036222509702459e-05,
"loss": 0.8739,
"step": 4070
},
{
"epoch": 2.2256214149139577,
"grad_norm": 0.6984094977378845,
"learning_rate": 1.4014661492022423e-05,
"loss": 0.773,
"step": 4075
},
{
"epoch": 2.2283529090412455,
"grad_norm": 0.7641189098358154,
"learning_rate": 1.3993100474342389e-05,
"loss": 0.8112,
"step": 4080
},
{
"epoch": 2.2310844031685333,
"grad_norm": 0.935867965221405,
"learning_rate": 1.3971539456662355e-05,
"loss": 0.8833,
"step": 4085
},
{
"epoch": 2.2338158972958206,
"grad_norm": 0.861794114112854,
"learning_rate": 1.394997843898232e-05,
"loss": 0.7455,
"step": 4090
},
{
"epoch": 2.2365473914231084,
"grad_norm": 0.9031226634979248,
"learning_rate": 1.3928417421302286e-05,
"loss": 0.8022,
"step": 4095
},
{
"epoch": 2.2392788855503962,
"grad_norm": 0.6768134236335754,
"learning_rate": 1.390685640362225e-05,
"loss": 0.7694,
"step": 4100
},
{
"epoch": 2.2420103796776836,
"grad_norm": 0.701326847076416,
"learning_rate": 1.3885295385942216e-05,
"loss": 0.7764,
"step": 4105
},
{
"epoch": 2.2447418738049714,
"grad_norm": 0.7094439268112183,
"learning_rate": 1.3863734368262184e-05,
"loss": 0.7985,
"step": 4110
},
{
"epoch": 2.247473367932259,
"grad_norm": 0.7312394976615906,
"learning_rate": 1.3842173350582148e-05,
"loss": 0.8113,
"step": 4115
},
{
"epoch": 2.2502048620595465,
"grad_norm": 0.7001371383666992,
"learning_rate": 1.3820612332902114e-05,
"loss": 0.7564,
"step": 4120
},
{
"epoch": 2.2529363561868343,
"grad_norm": 0.6896631121635437,
"learning_rate": 1.3799051315222079e-05,
"loss": 0.8286,
"step": 4125
},
{
"epoch": 2.2556678503141216,
"grad_norm": 0.9941986203193665,
"learning_rate": 1.3777490297542045e-05,
"loss": 0.8587,
"step": 4130
},
{
"epoch": 2.2583993444414094,
"grad_norm": 0.7232380509376526,
"learning_rate": 1.3755929279862011e-05,
"loss": 0.726,
"step": 4135
},
{
"epoch": 2.2611308385686972,
"grad_norm": 0.7439639568328857,
"learning_rate": 1.3734368262181975e-05,
"loss": 0.8296,
"step": 4140
},
{
"epoch": 2.2638623326959846,
"grad_norm": 0.7760093808174133,
"learning_rate": 1.3712807244501941e-05,
"loss": 0.7572,
"step": 4145
},
{
"epoch": 2.2665938268232724,
"grad_norm": 0.8365876078605652,
"learning_rate": 1.3691246226821906e-05,
"loss": 0.8698,
"step": 4150
},
{
"epoch": 2.2693253209505597,
"grad_norm": 0.6379351019859314,
"learning_rate": 1.3669685209141872e-05,
"loss": 0.7298,
"step": 4155
},
{
"epoch": 2.2720568150778475,
"grad_norm": 0.7523884177207947,
"learning_rate": 1.3648124191461836e-05,
"loss": 0.7733,
"step": 4160
},
{
"epoch": 2.2747883092051353,
"grad_norm": 0.7487993836402893,
"learning_rate": 1.3626563173781802e-05,
"loss": 0.7618,
"step": 4165
},
{
"epoch": 2.2775198033324227,
"grad_norm": 0.7205899953842163,
"learning_rate": 1.3605002156101768e-05,
"loss": 0.8136,
"step": 4170
},
{
"epoch": 2.2802512974597104,
"grad_norm": 0.7175250053405762,
"learning_rate": 1.3583441138421733e-05,
"loss": 0.7354,
"step": 4175
},
{
"epoch": 2.2829827915869982,
"grad_norm": 0.7742190957069397,
"learning_rate": 1.3561880120741699e-05,
"loss": 0.7987,
"step": 4180
},
{
"epoch": 2.2857142857142856,
"grad_norm": 0.7730711102485657,
"learning_rate": 1.3540319103061663e-05,
"loss": 0.7648,
"step": 4185
},
{
"epoch": 2.2884457798415734,
"grad_norm": 0.6889259815216064,
"learning_rate": 1.3518758085381631e-05,
"loss": 0.8092,
"step": 4190
},
{
"epoch": 2.291177273968861,
"grad_norm": 0.6672682166099548,
"learning_rate": 1.3497197067701597e-05,
"loss": 0.8145,
"step": 4195
},
{
"epoch": 2.2939087680961485,
"grad_norm": 0.9464843273162842,
"learning_rate": 1.3475636050021562e-05,
"loss": 0.846,
"step": 4200
},
{
"epoch": 2.2939087680961485,
"eval_loss": 0.9262539744377136,
"eval_runtime": 297.4394,
"eval_samples_per_second": 11.838,
"eval_steps_per_second": 2.962,
"step": 4200
},
{
"epoch": 2.2966402622234363,
"grad_norm": 0.6689907312393188,
"learning_rate": 1.3454075032341528e-05,
"loss": 0.7643,
"step": 4205
},
{
"epoch": 2.2993717563507237,
"grad_norm": 0.78407883644104,
"learning_rate": 1.3432514014661492e-05,
"loss": 0.8049,
"step": 4210
},
{
"epoch": 2.3021032504780115,
"grad_norm": 0.8163665533065796,
"learning_rate": 1.3410952996981458e-05,
"loss": 0.8188,
"step": 4215
},
{
"epoch": 2.3048347446052992,
"grad_norm": 0.667530357837677,
"learning_rate": 1.3389391979301424e-05,
"loss": 0.7758,
"step": 4220
},
{
"epoch": 2.3075662387325866,
"grad_norm": 0.6950967311859131,
"learning_rate": 1.3367830961621389e-05,
"loss": 0.7657,
"step": 4225
},
{
"epoch": 2.3102977328598744,
"grad_norm": 0.7282412052154541,
"learning_rate": 1.3346269943941355e-05,
"loss": 0.766,
"step": 4230
},
{
"epoch": 2.3130292269871617,
"grad_norm": 0.8621053695678711,
"learning_rate": 1.3324708926261319e-05,
"loss": 0.7528,
"step": 4235
},
{
"epoch": 2.3157607211144495,
"grad_norm": 0.9072563052177429,
"learning_rate": 1.3303147908581285e-05,
"loss": 0.7814,
"step": 4240
},
{
"epoch": 2.3184922152417373,
"grad_norm": 0.8264155387878418,
"learning_rate": 1.3281586890901251e-05,
"loss": 0.8119,
"step": 4245
},
{
"epoch": 2.3212237093690247,
"grad_norm": 0.8605033159255981,
"learning_rate": 1.3260025873221216e-05,
"loss": 0.8205,
"step": 4250
},
{
"epoch": 2.3239552034963125,
"grad_norm": 0.6696557402610779,
"learning_rate": 1.3238464855541182e-05,
"loss": 0.747,
"step": 4255
},
{
"epoch": 2.3266866976236003,
"grad_norm": 0.7751865386962891,
"learning_rate": 1.3216903837861146e-05,
"loss": 0.7862,
"step": 4260
},
{
"epoch": 2.3294181917508876,
"grad_norm": 0.7971178293228149,
"learning_rate": 1.3195342820181112e-05,
"loss": 0.7831,
"step": 4265
},
{
"epoch": 2.3321496858781754,
"grad_norm": 0.7750131487846375,
"learning_rate": 1.3173781802501078e-05,
"loss": 0.7684,
"step": 4270
},
{
"epoch": 2.334881180005463,
"grad_norm": 0.788883626461029,
"learning_rate": 1.3152220784821044e-05,
"loss": 0.8209,
"step": 4275
},
{
"epoch": 2.3376126741327505,
"grad_norm": 0.8019657135009766,
"learning_rate": 1.313065976714101e-05,
"loss": 0.7794,
"step": 4280
},
{
"epoch": 2.3403441682600383,
"grad_norm": 0.7541218996047974,
"learning_rate": 1.3109098749460975e-05,
"loss": 0.7586,
"step": 4285
},
{
"epoch": 2.3430756623873257,
"grad_norm": 0.7851794958114624,
"learning_rate": 1.3087537731780941e-05,
"loss": 0.8057,
"step": 4290
},
{
"epoch": 2.3458071565146135,
"grad_norm": 0.7472942471504211,
"learning_rate": 1.3065976714100907e-05,
"loss": 0.7925,
"step": 4295
},
{
"epoch": 2.3485386506419013,
"grad_norm": 0.7513644099235535,
"learning_rate": 1.3044415696420871e-05,
"loss": 0.7911,
"step": 4300
},
{
"epoch": 2.3512701447691886,
"grad_norm": 0.7507604360580444,
"learning_rate": 1.3022854678740837e-05,
"loss": 0.7895,
"step": 4305
},
{
"epoch": 2.3540016388964764,
"grad_norm": 0.7856028079986572,
"learning_rate": 1.3001293661060802e-05,
"loss": 0.8078,
"step": 4310
},
{
"epoch": 2.356733133023764,
"grad_norm": 0.9324090480804443,
"learning_rate": 1.2979732643380768e-05,
"loss": 0.8163,
"step": 4315
},
{
"epoch": 2.3594646271510515,
"grad_norm": 0.722343921661377,
"learning_rate": 1.2958171625700734e-05,
"loss": 0.7511,
"step": 4320
},
{
"epoch": 2.3621961212783393,
"grad_norm": 0.9830405116081238,
"learning_rate": 1.2936610608020698e-05,
"loss": 0.787,
"step": 4325
},
{
"epoch": 2.3649276154056267,
"grad_norm": 0.8058767318725586,
"learning_rate": 1.2915049590340664e-05,
"loss": 0.7735,
"step": 4330
},
{
"epoch": 2.3676591095329145,
"grad_norm": 0.8515341281890869,
"learning_rate": 1.2893488572660629e-05,
"loss": 0.807,
"step": 4335
},
{
"epoch": 2.3703906036602023,
"grad_norm": 0.7659634351730347,
"learning_rate": 1.2871927554980595e-05,
"loss": 0.7515,
"step": 4340
},
{
"epoch": 2.3731220977874896,
"grad_norm": 0.8038457632064819,
"learning_rate": 1.2850366537300561e-05,
"loss": 0.8918,
"step": 4345
},
{
"epoch": 2.3758535919147774,
"grad_norm": 0.7973572015762329,
"learning_rate": 1.2828805519620525e-05,
"loss": 0.8241,
"step": 4350
},
{
"epoch": 2.378585086042065,
"grad_norm": 0.7273423075675964,
"learning_rate": 1.2807244501940493e-05,
"loss": 0.7819,
"step": 4355
},
{
"epoch": 2.3813165801693525,
"grad_norm": 0.6779032349586487,
"learning_rate": 1.2785683484260458e-05,
"loss": 0.8191,
"step": 4360
},
{
"epoch": 2.3840480742966403,
"grad_norm": 1.0431166887283325,
"learning_rate": 1.2764122466580424e-05,
"loss": 0.7695,
"step": 4365
},
{
"epoch": 2.386779568423928,
"grad_norm": 0.8091884255409241,
"learning_rate": 1.2742561448900388e-05,
"loss": 0.7774,
"step": 4370
},
{
"epoch": 2.3895110625512155,
"grad_norm": 0.819164514541626,
"learning_rate": 1.2721000431220354e-05,
"loss": 0.7451,
"step": 4375
},
{
"epoch": 2.3922425566785033,
"grad_norm": 0.7259253859519958,
"learning_rate": 1.269943941354032e-05,
"loss": 0.7748,
"step": 4380
},
{
"epoch": 2.3949740508057906,
"grad_norm": 0.6403051614761353,
"learning_rate": 1.2677878395860285e-05,
"loss": 0.7366,
"step": 4385
},
{
"epoch": 2.3977055449330784,
"grad_norm": 0.8575317859649658,
"learning_rate": 1.265631737818025e-05,
"loss": 0.8034,
"step": 4390
},
{
"epoch": 2.400437039060366,
"grad_norm": 0.7741707563400269,
"learning_rate": 1.2634756360500215e-05,
"loss": 0.7993,
"step": 4395
},
{
"epoch": 2.4031685331876536,
"grad_norm": 0.8399520516395569,
"learning_rate": 1.2613195342820181e-05,
"loss": 0.7915,
"step": 4400
},
{
"epoch": 2.4059000273149413,
"grad_norm": 0.7090021371841431,
"learning_rate": 1.2591634325140147e-05,
"loss": 0.7909,
"step": 4405
},
{
"epoch": 2.4086315214422287,
"grad_norm": 0.8017282485961914,
"learning_rate": 1.2570073307460112e-05,
"loss": 0.7945,
"step": 4410
},
{
"epoch": 2.4113630155695165,
"grad_norm": 0.9520066976547241,
"learning_rate": 1.2548512289780078e-05,
"loss": 0.869,
"step": 4415
},
{
"epoch": 2.4140945096968043,
"grad_norm": 0.8347050547599792,
"learning_rate": 1.2526951272100042e-05,
"loss": 0.8121,
"step": 4420
},
{
"epoch": 2.4168260038240916,
"grad_norm": 0.7482141852378845,
"learning_rate": 1.2505390254420008e-05,
"loss": 0.8008,
"step": 4425
},
{
"epoch": 2.4195574979513794,
"grad_norm": 0.7613436579704285,
"learning_rate": 1.2483829236739974e-05,
"loss": 0.7838,
"step": 4430
},
{
"epoch": 2.422288992078667,
"grad_norm": 0.7921198010444641,
"learning_rate": 1.246226821905994e-05,
"loss": 0.789,
"step": 4435
},
{
"epoch": 2.4250204862059546,
"grad_norm": 0.7739691138267517,
"learning_rate": 1.2440707201379906e-05,
"loss": 0.801,
"step": 4440
},
{
"epoch": 2.4277519803332424,
"grad_norm": 0.9030047059059143,
"learning_rate": 1.2419146183699871e-05,
"loss": 0.8809,
"step": 4445
},
{
"epoch": 2.43048347446053,
"grad_norm": 0.8139593601226807,
"learning_rate": 1.2397585166019837e-05,
"loss": 0.8302,
"step": 4450
},
{
"epoch": 2.4332149685878175,
"grad_norm": 0.7780411839485168,
"learning_rate": 1.2376024148339803e-05,
"loss": 0.7773,
"step": 4455
},
{
"epoch": 2.4359464627151053,
"grad_norm": 0.6775504946708679,
"learning_rate": 1.2354463130659767e-05,
"loss": 0.8039,
"step": 4460
},
{
"epoch": 2.4386779568423926,
"grad_norm": 0.7571560740470886,
"learning_rate": 1.2332902112979734e-05,
"loss": 0.7657,
"step": 4465
},
{
"epoch": 2.4414094509696804,
"grad_norm": 0.8740114569664001,
"learning_rate": 1.2311341095299698e-05,
"loss": 0.7904,
"step": 4470
},
{
"epoch": 2.444140945096968,
"grad_norm": 0.7589646577835083,
"learning_rate": 1.2289780077619664e-05,
"loss": 0.7992,
"step": 4475
},
{
"epoch": 2.4468724392242556,
"grad_norm": 0.8440977931022644,
"learning_rate": 1.226821905993963e-05,
"loss": 0.7876,
"step": 4480
},
{
"epoch": 2.4496039333515434,
"grad_norm": 0.7380586862564087,
"learning_rate": 1.2246658042259594e-05,
"loss": 0.7262,
"step": 4485
},
{
"epoch": 2.4523354274788307,
"grad_norm": 0.8782178163528442,
"learning_rate": 1.222509702457956e-05,
"loss": 0.8128,
"step": 4490
},
{
"epoch": 2.4550669216061185,
"grad_norm": 0.7687152028083801,
"learning_rate": 1.2203536006899525e-05,
"loss": 0.8181,
"step": 4495
},
{
"epoch": 2.4577984157334063,
"grad_norm": 0.710198700428009,
"learning_rate": 1.2181974989219491e-05,
"loss": 0.8592,
"step": 4500
},
{
"epoch": 2.4577984157334063,
"eval_loss": 0.920670747756958,
"eval_runtime": 297.7661,
"eval_samples_per_second": 11.825,
"eval_steps_per_second": 2.959,
"step": 4500
},
{
"epoch": 2.4605299098606936,
"grad_norm": 0.8350089192390442,
"learning_rate": 1.2160413971539457e-05,
"loss": 0.7771,
"step": 4505
},
{
"epoch": 2.4632614039879814,
"grad_norm": 0.779538631439209,
"learning_rate": 1.2138852953859421e-05,
"loss": 0.8373,
"step": 4510
},
{
"epoch": 2.4659928981152692,
"grad_norm": 0.7419815063476562,
"learning_rate": 1.211729193617939e-05,
"loss": 0.7919,
"step": 4515
},
{
"epoch": 2.4687243922425566,
"grad_norm": 0.686601459980011,
"learning_rate": 1.2095730918499354e-05,
"loss": 0.7649,
"step": 4520
},
{
"epoch": 2.4714558863698444,
"grad_norm": 0.823641836643219,
"learning_rate": 1.207416990081932e-05,
"loss": 0.7766,
"step": 4525
},
{
"epoch": 2.474187380497132,
"grad_norm": 0.7858705520629883,
"learning_rate": 1.2052608883139286e-05,
"loss": 0.8423,
"step": 4530
},
{
"epoch": 2.4769188746244195,
"grad_norm": 0.8001030087471008,
"learning_rate": 1.203104786545925e-05,
"loss": 0.8011,
"step": 4535
},
{
"epoch": 2.4796503687517073,
"grad_norm": 0.8217907547950745,
"learning_rate": 1.2009486847779216e-05,
"loss": 0.8341,
"step": 4540
},
{
"epoch": 2.4823818628789946,
"grad_norm": 0.7537449598312378,
"learning_rate": 1.198792583009918e-05,
"loss": 0.7272,
"step": 4545
},
{
"epoch": 2.4851133570062824,
"grad_norm": 0.7548356056213379,
"learning_rate": 1.1966364812419147e-05,
"loss": 0.7361,
"step": 4550
},
{
"epoch": 2.4878448511335702,
"grad_norm": 0.7265061140060425,
"learning_rate": 1.1944803794739111e-05,
"loss": 0.8617,
"step": 4555
},
{
"epoch": 2.4905763452608576,
"grad_norm": 0.8167422413825989,
"learning_rate": 1.1923242777059077e-05,
"loss": 0.8371,
"step": 4560
},
{
"epoch": 2.4933078393881454,
"grad_norm": 0.8406078219413757,
"learning_rate": 1.1901681759379043e-05,
"loss": 0.7942,
"step": 4565
},
{
"epoch": 2.4960393335154327,
"grad_norm": 0.6461910605430603,
"learning_rate": 1.1880120741699008e-05,
"loss": 0.7427,
"step": 4570
},
{
"epoch": 2.4987708276427205,
"grad_norm": 0.8043162226676941,
"learning_rate": 1.1858559724018974e-05,
"loss": 0.7838,
"step": 4575
},
{
"epoch": 2.5015023217700083,
"grad_norm": 0.7796498537063599,
"learning_rate": 1.1836998706338938e-05,
"loss": 0.7636,
"step": 4580
},
{
"epoch": 2.5042338158972957,
"grad_norm": 0.7185204029083252,
"learning_rate": 1.1815437688658904e-05,
"loss": 0.8285,
"step": 4585
},
{
"epoch": 2.5069653100245834,
"grad_norm": 0.7848299145698547,
"learning_rate": 1.179387667097887e-05,
"loss": 0.7762,
"step": 4590
},
{
"epoch": 2.5096968041518712,
"grad_norm": 0.8009158372879028,
"learning_rate": 1.1772315653298835e-05,
"loss": 0.7902,
"step": 4595
},
{
"epoch": 2.5124282982791586,
"grad_norm": 0.8115645051002502,
"learning_rate": 1.1750754635618803e-05,
"loss": 0.7787,
"step": 4600
},
{
"epoch": 2.5151597924064464,
"grad_norm": 0.8867664933204651,
"learning_rate": 1.1729193617938767e-05,
"loss": 0.8709,
"step": 4605
},
{
"epoch": 2.517891286533734,
"grad_norm": 0.8079234957695007,
"learning_rate": 1.1707632600258733e-05,
"loss": 0.7665,
"step": 4610
},
{
"epoch": 2.5206227806610215,
"grad_norm": 0.7213905453681946,
"learning_rate": 1.1686071582578699e-05,
"loss": 0.7946,
"step": 4615
},
{
"epoch": 2.5233542747883093,
"grad_norm": 0.7402395009994507,
"learning_rate": 1.1664510564898663e-05,
"loss": 0.7971,
"step": 4620
},
{
"epoch": 2.526085768915597,
"grad_norm": 0.6701128482818604,
"learning_rate": 1.164294954721863e-05,
"loss": 0.7801,
"step": 4625
},
{
"epoch": 2.5288172630428845,
"grad_norm": 0.7747988700866699,
"learning_rate": 1.1621388529538594e-05,
"loss": 0.7284,
"step": 4630
},
{
"epoch": 2.5315487571701722,
"grad_norm": 0.732720136642456,
"learning_rate": 1.159982751185856e-05,
"loss": 0.7934,
"step": 4635
},
{
"epoch": 2.5342802512974596,
"grad_norm": 0.7755371332168579,
"learning_rate": 1.1578266494178526e-05,
"loss": 0.7679,
"step": 4640
},
{
"epoch": 2.5370117454247474,
"grad_norm": 0.7975987195968628,
"learning_rate": 1.155670547649849e-05,
"loss": 0.7573,
"step": 4645
},
{
"epoch": 2.5397432395520347,
"grad_norm": 0.7659042477607727,
"learning_rate": 1.1535144458818457e-05,
"loss": 0.7842,
"step": 4650
},
{
"epoch": 2.5424747336793225,
"grad_norm": 0.8602875471115112,
"learning_rate": 1.1513583441138421e-05,
"loss": 0.7776,
"step": 4655
},
{
"epoch": 2.5452062278066103,
"grad_norm": 0.9775980710983276,
"learning_rate": 1.1492022423458387e-05,
"loss": 0.8129,
"step": 4660
},
{
"epoch": 2.5479377219338977,
"grad_norm": 0.8187624216079712,
"learning_rate": 1.1470461405778353e-05,
"loss": 0.7723,
"step": 4665
},
{
"epoch": 2.5506692160611855,
"grad_norm": 0.7742021679878235,
"learning_rate": 1.1448900388098318e-05,
"loss": 0.7808,
"step": 4670
},
{
"epoch": 2.5534007101884733,
"grad_norm": 0.7678861021995544,
"learning_rate": 1.1427339370418284e-05,
"loss": 0.7604,
"step": 4675
},
{
"epoch": 2.5561322043157606,
"grad_norm": 0.973621666431427,
"learning_rate": 1.140577835273825e-05,
"loss": 0.8316,
"step": 4680
},
{
"epoch": 2.5588636984430484,
"grad_norm": 0.75911545753479,
"learning_rate": 1.1384217335058216e-05,
"loss": 0.7803,
"step": 4685
},
{
"epoch": 2.561595192570336,
"grad_norm": 0.7606973648071289,
"learning_rate": 1.1362656317378182e-05,
"loss": 0.8103,
"step": 4690
},
{
"epoch": 2.5643266866976235,
"grad_norm": 0.9047139883041382,
"learning_rate": 1.1341095299698146e-05,
"loss": 0.7755,
"step": 4695
},
{
"epoch": 2.5670581808249113,
"grad_norm": 0.849153995513916,
"learning_rate": 1.1319534282018112e-05,
"loss": 0.8195,
"step": 4700
},
{
"epoch": 2.569789674952199,
"grad_norm": 0.7619132399559021,
"learning_rate": 1.1297973264338077e-05,
"loss": 0.8617,
"step": 4705
},
{
"epoch": 2.5725211690794865,
"grad_norm": 0.9894094467163086,
"learning_rate": 1.1276412246658043e-05,
"loss": 0.8164,
"step": 4710
},
{
"epoch": 2.5752526632067743,
"grad_norm": 0.8894760012626648,
"learning_rate": 1.1254851228978009e-05,
"loss": 0.7983,
"step": 4715
},
{
"epoch": 2.5779841573340616,
"grad_norm": 0.6793032288551331,
"learning_rate": 1.1233290211297973e-05,
"loss": 0.7317,
"step": 4720
},
{
"epoch": 2.5807156514613494,
"grad_norm": 0.7268416285514832,
"learning_rate": 1.121172919361794e-05,
"loss": 0.729,
"step": 4725
},
{
"epoch": 2.5834471455886368,
"grad_norm": 0.7058541178703308,
"learning_rate": 1.1190168175937904e-05,
"loss": 0.724,
"step": 4730
},
{
"epoch": 2.5861786397159245,
"grad_norm": 0.8915583491325378,
"learning_rate": 1.116860715825787e-05,
"loss": 0.7949,
"step": 4735
},
{
"epoch": 2.5889101338432123,
"grad_norm": 0.6411117315292358,
"learning_rate": 1.1147046140577834e-05,
"loss": 0.7458,
"step": 4740
},
{
"epoch": 2.5916416279704997,
"grad_norm": 0.7651311755180359,
"learning_rate": 1.11254851228978e-05,
"loss": 0.8048,
"step": 4745
},
{
"epoch": 2.5943731220977875,
"grad_norm": 0.8468698263168335,
"learning_rate": 1.1103924105217766e-05,
"loss": 0.7487,
"step": 4750
},
{
"epoch": 2.5971046162250753,
"grad_norm": 0.7958516478538513,
"learning_rate": 1.108236308753773e-05,
"loss": 0.7716,
"step": 4755
},
{
"epoch": 2.5998361103523626,
"grad_norm": 0.7221107482910156,
"learning_rate": 1.1060802069857699e-05,
"loss": 0.8122,
"step": 4760
},
{
"epoch": 2.6025676044796504,
"grad_norm": 0.7842141389846802,
"learning_rate": 1.1039241052177663e-05,
"loss": 0.7518,
"step": 4765
},
{
"epoch": 2.605299098606938,
"grad_norm": 0.7418232560157776,
"learning_rate": 1.1017680034497629e-05,
"loss": 0.7405,
"step": 4770
},
{
"epoch": 2.6080305927342256,
"grad_norm": 0.7389415502548218,
"learning_rate": 1.0996119016817595e-05,
"loss": 0.7259,
"step": 4775
},
{
"epoch": 2.6107620868615133,
"grad_norm": 0.8378607630729675,
"learning_rate": 1.097455799913756e-05,
"loss": 0.7358,
"step": 4780
},
{
"epoch": 2.613493580988801,
"grad_norm": 0.7662971615791321,
"learning_rate": 1.0952996981457526e-05,
"loss": 0.8267,
"step": 4785
},
{
"epoch": 2.6162250751160885,
"grad_norm": 0.7570760250091553,
"learning_rate": 1.093143596377749e-05,
"loss": 0.7746,
"step": 4790
},
{
"epoch": 2.6189565692433763,
"grad_norm": 0.8133824467658997,
"learning_rate": 1.0909874946097456e-05,
"loss": 0.8165,
"step": 4795
},
{
"epoch": 2.6216880633706636,
"grad_norm": 0.833907425403595,
"learning_rate": 1.0888313928417422e-05,
"loss": 0.8204,
"step": 4800
},
{
"epoch": 2.6216880633706636,
"eval_loss": 0.914101243019104,
"eval_runtime": 298.101,
"eval_samples_per_second": 11.811,
"eval_steps_per_second": 2.955,
"step": 4800
},
{
"epoch": 2.6244195574979514,
"grad_norm": 0.8671056628227234,
"learning_rate": 1.0866752910737387e-05,
"loss": 0.8404,
"step": 4805
},
{
"epoch": 2.6271510516252388,
"grad_norm": 0.7383393049240112,
"learning_rate": 1.0845191893057353e-05,
"loss": 0.7683,
"step": 4810
},
{
"epoch": 2.6298825457525266,
"grad_norm": 0.7541636824607849,
"learning_rate": 1.0823630875377317e-05,
"loss": 0.8044,
"step": 4815
},
{
"epoch": 2.6326140398798143,
"grad_norm": 0.8117208480834961,
"learning_rate": 1.0802069857697283e-05,
"loss": 0.7759,
"step": 4820
},
{
"epoch": 2.6353455340071017,
"grad_norm": 0.8050516247749329,
"learning_rate": 1.078050884001725e-05,
"loss": 0.7562,
"step": 4825
},
{
"epoch": 2.6380770281343895,
"grad_norm": 0.8634320497512817,
"learning_rate": 1.0758947822337214e-05,
"loss": 0.7643,
"step": 4830
},
{
"epoch": 2.6408085222616773,
"grad_norm": 0.7925430536270142,
"learning_rate": 1.073738680465718e-05,
"loss": 0.7803,
"step": 4835
},
{
"epoch": 2.6435400163889646,
"grad_norm": 0.8106513619422913,
"learning_rate": 1.0715825786977144e-05,
"loss": 0.8037,
"step": 4840
},
{
"epoch": 2.6462715105162524,
"grad_norm": 0.6673171520233154,
"learning_rate": 1.0694264769297112e-05,
"loss": 0.7435,
"step": 4845
},
{
"epoch": 2.64900300464354,
"grad_norm": 0.8566637635231018,
"learning_rate": 1.0672703751617078e-05,
"loss": 0.7851,
"step": 4850
},
{
"epoch": 2.6517344987708276,
"grad_norm": 0.7599483132362366,
"learning_rate": 1.0651142733937042e-05,
"loss": 0.8256,
"step": 4855
},
{
"epoch": 2.6544659928981154,
"grad_norm": 0.7473616003990173,
"learning_rate": 1.0629581716257008e-05,
"loss": 0.7593,
"step": 4860
},
{
"epoch": 2.657197487025403,
"grad_norm": 0.8565317988395691,
"learning_rate": 1.0608020698576973e-05,
"loss": 0.8051,
"step": 4865
},
{
"epoch": 2.6599289811526905,
"grad_norm": 0.7901437878608704,
"learning_rate": 1.0586459680896939e-05,
"loss": 0.8124,
"step": 4870
},
{
"epoch": 2.6626604752799783,
"grad_norm": 0.7486543655395508,
"learning_rate": 1.0564898663216905e-05,
"loss": 0.7863,
"step": 4875
},
{
"epoch": 2.6653919694072656,
"grad_norm": 0.9908071160316467,
"learning_rate": 1.054333764553687e-05,
"loss": 0.8213,
"step": 4880
},
{
"epoch": 2.6681234635345534,
"grad_norm": 0.7769798040390015,
"learning_rate": 1.0521776627856835e-05,
"loss": 0.7892,
"step": 4885
},
{
"epoch": 2.670854957661841,
"grad_norm": 0.8946226239204407,
"learning_rate": 1.05002156101768e-05,
"loss": 0.8194,
"step": 4890
},
{
"epoch": 2.6735864517891286,
"grad_norm": 0.7486757636070251,
"learning_rate": 1.0478654592496766e-05,
"loss": 0.7985,
"step": 4895
},
{
"epoch": 2.6763179459164164,
"grad_norm": 0.7342307567596436,
"learning_rate": 1.0457093574816732e-05,
"loss": 0.7887,
"step": 4900
},
{
"epoch": 2.6790494400437037,
"grad_norm": 0.7860587239265442,
"learning_rate": 1.0435532557136696e-05,
"loss": 0.7892,
"step": 4905
},
{
"epoch": 2.6817809341709915,
"grad_norm": 0.7645874619483948,
"learning_rate": 1.0413971539456663e-05,
"loss": 0.8244,
"step": 4910
},
{
"epoch": 2.6845124282982793,
"grad_norm": 0.7704142928123474,
"learning_rate": 1.0392410521776627e-05,
"loss": 0.7664,
"step": 4915
},
{
"epoch": 2.6872439224255666,
"grad_norm": 0.8156923651695251,
"learning_rate": 1.0370849504096593e-05,
"loss": 0.7568,
"step": 4920
},
{
"epoch": 2.6899754165528544,
"grad_norm": 0.71125328540802,
"learning_rate": 1.0349288486416559e-05,
"loss": 0.7673,
"step": 4925
},
{
"epoch": 2.6927069106801422,
"grad_norm": 0.6792523860931396,
"learning_rate": 1.0327727468736525e-05,
"loss": 0.7632,
"step": 4930
},
{
"epoch": 2.6954384048074296,
"grad_norm": 0.6375525593757629,
"learning_rate": 1.0306166451056491e-05,
"loss": 0.7467,
"step": 4935
},
{
"epoch": 2.6981698989347174,
"grad_norm": 0.8573178052902222,
"learning_rate": 1.0284605433376456e-05,
"loss": 0.8274,
"step": 4940
},
{
"epoch": 2.700901393062005,
"grad_norm": 0.6843066811561584,
"learning_rate": 1.0263044415696422e-05,
"loss": 0.7667,
"step": 4945
},
{
"epoch": 2.7036328871892925,
"grad_norm": 0.8079308867454529,
"learning_rate": 1.0241483398016386e-05,
"loss": 0.7447,
"step": 4950
},
{
"epoch": 2.7063643813165803,
"grad_norm": 0.7261304259300232,
"learning_rate": 1.0219922380336352e-05,
"loss": 0.7902,
"step": 4955
},
{
"epoch": 2.7090958754438677,
"grad_norm": 0.6953102350234985,
"learning_rate": 1.0198361362656318e-05,
"loss": 0.7991,
"step": 4960
},
{
"epoch": 2.7118273695711554,
"grad_norm": 0.7195969223976135,
"learning_rate": 1.0176800344976283e-05,
"loss": 0.7809,
"step": 4965
},
{
"epoch": 2.714558863698443,
"grad_norm": 0.7635664939880371,
"learning_rate": 1.0155239327296249e-05,
"loss": 0.7468,
"step": 4970
},
{
"epoch": 2.7172903578257306,
"grad_norm": 0.875450849533081,
"learning_rate": 1.0133678309616213e-05,
"loss": 0.7888,
"step": 4975
},
{
"epoch": 2.7200218519530184,
"grad_norm": 0.8408946990966797,
"learning_rate": 1.011211729193618e-05,
"loss": 0.783,
"step": 4980
},
{
"epoch": 2.7227533460803057,
"grad_norm": 0.7973111867904663,
"learning_rate": 1.0090556274256145e-05,
"loss": 0.8091,
"step": 4985
},
{
"epoch": 2.7254848402075935,
"grad_norm": 0.7177147269248962,
"learning_rate": 1.006899525657611e-05,
"loss": 0.815,
"step": 4990
},
{
"epoch": 2.7282163343348813,
"grad_norm": 0.6764112710952759,
"learning_rate": 1.0047434238896076e-05,
"loss": 0.7815,
"step": 4995
},
{
"epoch": 2.7309478284621687,
"grad_norm": 0.8373432159423828,
"learning_rate": 1.002587322121604e-05,
"loss": 0.765,
"step": 5000
},
{
"epoch": 2.7336793225894565,
"grad_norm": 0.8018892407417297,
"learning_rate": 1.0004312203536008e-05,
"loss": 0.7961,
"step": 5005
},
{
"epoch": 2.7364108167167442,
"grad_norm": 0.8066474199295044,
"learning_rate": 9.982751185855974e-06,
"loss": 0.8076,
"step": 5010
},
{
"epoch": 2.7391423108440316,
"grad_norm": 0.8018581867218018,
"learning_rate": 9.961190168175938e-06,
"loss": 0.7934,
"step": 5015
},
{
"epoch": 2.7418738049713194,
"grad_norm": 0.7070809006690979,
"learning_rate": 9.939629150495904e-06,
"loss": 0.7918,
"step": 5020
},
{
"epoch": 2.744605299098607,
"grad_norm": 0.7052949070930481,
"learning_rate": 9.918068132815869e-06,
"loss": 0.7297,
"step": 5025
},
{
"epoch": 2.7473367932258945,
"grad_norm": 0.7754566669464111,
"learning_rate": 9.896507115135835e-06,
"loss": 0.756,
"step": 5030
},
{
"epoch": 2.7500682873531823,
"grad_norm": 0.7512825727462769,
"learning_rate": 9.874946097455801e-06,
"loss": 0.7394,
"step": 5035
},
{
"epoch": 2.7527997814804697,
"grad_norm": 0.6898414492607117,
"learning_rate": 9.853385079775765e-06,
"loss": 0.7468,
"step": 5040
},
{
"epoch": 2.7555312756077575,
"grad_norm": 0.6388275623321533,
"learning_rate": 9.831824062095732e-06,
"loss": 0.7343,
"step": 5045
},
{
"epoch": 2.758262769735045,
"grad_norm": 0.8408862948417664,
"learning_rate": 9.810263044415696e-06,
"loss": 0.8101,
"step": 5050
},
{
"epoch": 2.7609942638623326,
"grad_norm": 0.7864372730255127,
"learning_rate": 9.788702026735662e-06,
"loss": 0.7753,
"step": 5055
},
{
"epoch": 2.7637257579896204,
"grad_norm": 0.7817166447639465,
"learning_rate": 9.767141009055628e-06,
"loss": 0.7906,
"step": 5060
},
{
"epoch": 2.7664572521169077,
"grad_norm": 0.7181990742683411,
"learning_rate": 9.745579991375592e-06,
"loss": 0.7896,
"step": 5065
},
{
"epoch": 2.7691887462441955,
"grad_norm": 0.802594006061554,
"learning_rate": 9.724018973695559e-06,
"loss": 0.7972,
"step": 5070
},
{
"epoch": 2.7719202403714833,
"grad_norm": 0.7054097652435303,
"learning_rate": 9.702457956015523e-06,
"loss": 0.7318,
"step": 5075
},
{
"epoch": 2.7746517344987707,
"grad_norm": 0.8892520070075989,
"learning_rate": 9.680896938335489e-06,
"loss": 0.8036,
"step": 5080
},
{
"epoch": 2.7773832286260585,
"grad_norm": 0.8432682752609253,
"learning_rate": 9.659335920655457e-06,
"loss": 0.8091,
"step": 5085
},
{
"epoch": 2.7801147227533463,
"grad_norm": 0.8742365837097168,
"learning_rate": 9.637774902975421e-06,
"loss": 0.7692,
"step": 5090
},
{
"epoch": 2.7828462168806336,
"grad_norm": 0.6473404765129089,
"learning_rate": 9.616213885295387e-06,
"loss": 0.7592,
"step": 5095
},
{
"epoch": 2.7855777110079214,
"grad_norm": 0.9212759733200073,
"learning_rate": 9.594652867615352e-06,
"loss": 0.8638,
"step": 5100
},
{
"epoch": 2.7855777110079214,
"eval_loss": 0.9100801348686218,
"eval_runtime": 298.6056,
"eval_samples_per_second": 11.791,
"eval_steps_per_second": 2.95,
"step": 5100
},
{
"epoch": 2.788309205135209,
"grad_norm": 0.7847127914428711,
"learning_rate": 9.573091849935318e-06,
"loss": 0.7516,
"step": 5105
},
{
"epoch": 2.7910406992624965,
"grad_norm": 0.9584234952926636,
"learning_rate": 9.551530832255284e-06,
"loss": 0.7918,
"step": 5110
},
{
"epoch": 2.7937721933897843,
"grad_norm": 0.8609654903411865,
"learning_rate": 9.529969814575248e-06,
"loss": 0.7517,
"step": 5115
},
{
"epoch": 2.7965036875170717,
"grad_norm": 0.7463063597679138,
"learning_rate": 9.508408796895214e-06,
"loss": 0.683,
"step": 5120
},
{
"epoch": 2.7992351816443595,
"grad_norm": 0.8521767854690552,
"learning_rate": 9.486847779215179e-06,
"loss": 0.7641,
"step": 5125
},
{
"epoch": 2.801966675771647,
"grad_norm": 0.7557817697525024,
"learning_rate": 9.465286761535145e-06,
"loss": 0.7781,
"step": 5130
},
{
"epoch": 2.8046981698989346,
"grad_norm": 0.7500202059745789,
"learning_rate": 9.44372574385511e-06,
"loss": 0.8064,
"step": 5135
},
{
"epoch": 2.8074296640262224,
"grad_norm": 0.7218493819236755,
"learning_rate": 9.422164726175075e-06,
"loss": 0.7344,
"step": 5140
},
{
"epoch": 2.8101611581535098,
"grad_norm": 0.8501706123352051,
"learning_rate": 9.400603708495041e-06,
"loss": 0.7591,
"step": 5145
},
{
"epoch": 2.8128926522807975,
"grad_norm": 0.691214382648468,
"learning_rate": 9.379042690815006e-06,
"loss": 0.7595,
"step": 5150
},
{
"epoch": 2.8156241464080853,
"grad_norm": 0.7975975871086121,
"learning_rate": 9.357481673134972e-06,
"loss": 0.7894,
"step": 5155
},
{
"epoch": 2.8183556405353727,
"grad_norm": 0.7674605250358582,
"learning_rate": 9.335920655454936e-06,
"loss": 0.7773,
"step": 5160
},
{
"epoch": 2.8210871346626605,
"grad_norm": 0.8946635127067566,
"learning_rate": 9.314359637774902e-06,
"loss": 0.787,
"step": 5165
},
{
"epoch": 2.8238186287899483,
"grad_norm": 0.8302443623542786,
"learning_rate": 9.29279862009487e-06,
"loss": 0.719,
"step": 5170
},
{
"epoch": 2.8265501229172356,
"grad_norm": 0.7362715005874634,
"learning_rate": 9.271237602414834e-06,
"loss": 0.7709,
"step": 5175
},
{
"epoch": 2.8292816170445234,
"grad_norm": 0.7691307663917542,
"learning_rate": 9.2496765847348e-06,
"loss": 0.6861,
"step": 5180
},
{
"epoch": 2.832013111171811,
"grad_norm": 0.7596755623817444,
"learning_rate": 9.228115567054765e-06,
"loss": 0.7909,
"step": 5185
},
{
"epoch": 2.8347446052990986,
"grad_norm": 0.7873607873916626,
"learning_rate": 9.206554549374731e-06,
"loss": 0.7367,
"step": 5190
},
{
"epoch": 2.8374760994263863,
"grad_norm": 0.9081354141235352,
"learning_rate": 9.184993531694697e-06,
"loss": 0.7863,
"step": 5195
},
{
"epoch": 2.840207593553674,
"grad_norm": 0.7981383204460144,
"learning_rate": 9.163432514014662e-06,
"loss": 0.7709,
"step": 5200
},
{
"epoch": 2.8429390876809615,
"grad_norm": 0.6903979182243347,
"learning_rate": 9.141871496334628e-06,
"loss": 0.7711,
"step": 5205
},
{
"epoch": 2.8456705818082493,
"grad_norm": 0.72367262840271,
"learning_rate": 9.120310478654592e-06,
"loss": 0.73,
"step": 5210
},
{
"epoch": 2.8484020759355366,
"grad_norm": 0.7095135450363159,
"learning_rate": 9.098749460974558e-06,
"loss": 0.775,
"step": 5215
},
{
"epoch": 2.8511335700628244,
"grad_norm": 0.7772736549377441,
"learning_rate": 9.077188443294524e-06,
"loss": 0.7953,
"step": 5220
},
{
"epoch": 2.8538650641901118,
"grad_norm": 0.9331889152526855,
"learning_rate": 9.055627425614489e-06,
"loss": 0.7912,
"step": 5225
},
{
"epoch": 2.8565965583173996,
"grad_norm": 0.722665548324585,
"learning_rate": 9.034066407934455e-06,
"loss": 0.7486,
"step": 5230
},
{
"epoch": 2.8593280524446874,
"grad_norm": 0.7647317051887512,
"learning_rate": 9.012505390254419e-06,
"loss": 0.7456,
"step": 5235
},
{
"epoch": 2.8620595465719747,
"grad_norm": 0.7717449069023132,
"learning_rate": 8.990944372574385e-06,
"loss": 0.8001,
"step": 5240
},
{
"epoch": 2.8647910406992625,
"grad_norm": 0.9723305106163025,
"learning_rate": 8.969383354894351e-06,
"loss": 0.7627,
"step": 5245
},
{
"epoch": 2.8675225348265503,
"grad_norm": 0.7806791067123413,
"learning_rate": 8.947822337214317e-06,
"loss": 0.754,
"step": 5250
},
{
"epoch": 2.8702540289538376,
"grad_norm": 0.788318932056427,
"learning_rate": 8.926261319534283e-06,
"loss": 0.7938,
"step": 5255
},
{
"epoch": 2.8729855230811254,
"grad_norm": 0.8084414601325989,
"learning_rate": 8.904700301854248e-06,
"loss": 0.7944,
"step": 5260
},
{
"epoch": 2.875717017208413,
"grad_norm": 0.7164191603660583,
"learning_rate": 8.883139284174214e-06,
"loss": 0.8009,
"step": 5265
},
{
"epoch": 2.8784485113357006,
"grad_norm": 0.875485897064209,
"learning_rate": 8.86157826649418e-06,
"loss": 0.8004,
"step": 5270
},
{
"epoch": 2.8811800054629884,
"grad_norm": 0.8927438259124756,
"learning_rate": 8.840017248814144e-06,
"loss": 0.7803,
"step": 5275
},
{
"epoch": 2.883911499590276,
"grad_norm": 0.725167989730835,
"learning_rate": 8.81845623113411e-06,
"loss": 0.7884,
"step": 5280
},
{
"epoch": 2.8866429937175635,
"grad_norm": 0.7986631989479065,
"learning_rate": 8.796895213454075e-06,
"loss": 0.7558,
"step": 5285
},
{
"epoch": 2.8893744878448513,
"grad_norm": 0.7309257388114929,
"learning_rate": 8.775334195774041e-06,
"loss": 0.7367,
"step": 5290
},
{
"epoch": 2.8921059819721386,
"grad_norm": 0.8264611959457397,
"learning_rate": 8.753773178094007e-06,
"loss": 0.7364,
"step": 5295
},
{
"epoch": 2.8948374760994264,
"grad_norm": 0.8610091805458069,
"learning_rate": 8.732212160413971e-06,
"loss": 0.7806,
"step": 5300
},
{
"epoch": 2.897568970226714,
"grad_norm": 0.9611162543296814,
"learning_rate": 8.710651142733937e-06,
"loss": 0.8356,
"step": 5305
},
{
"epoch": 2.9003004643540016,
"grad_norm": 0.7416754364967346,
"learning_rate": 8.689090125053902e-06,
"loss": 0.7524,
"step": 5310
},
{
"epoch": 2.9030319584812894,
"grad_norm": 0.9265521168708801,
"learning_rate": 8.667529107373868e-06,
"loss": 0.7933,
"step": 5315
},
{
"epoch": 2.9057634526085767,
"grad_norm": 0.9508645534515381,
"learning_rate": 8.645968089693832e-06,
"loss": 0.8514,
"step": 5320
},
{
"epoch": 2.9084949467358645,
"grad_norm": 0.7876265048980713,
"learning_rate": 8.624407072013798e-06,
"loss": 0.8432,
"step": 5325
},
{
"epoch": 2.9112264408631523,
"grad_norm": 1.0237846374511719,
"learning_rate": 8.602846054333766e-06,
"loss": 0.7792,
"step": 5330
},
{
"epoch": 2.9139579349904396,
"grad_norm": 0.7499310374259949,
"learning_rate": 8.58128503665373e-06,
"loss": 0.7334,
"step": 5335
},
{
"epoch": 2.9166894291177274,
"grad_norm": 0.8537408709526062,
"learning_rate": 8.559724018973697e-06,
"loss": 0.7967,
"step": 5340
},
{
"epoch": 2.9194209232450152,
"grad_norm": 0.8417090177536011,
"learning_rate": 8.538163001293661e-06,
"loss": 0.8368,
"step": 5345
},
{
"epoch": 2.9221524173723026,
"grad_norm": 0.91497802734375,
"learning_rate": 8.516601983613627e-06,
"loss": 0.7688,
"step": 5350
},
{
"epoch": 2.9248839114995904,
"grad_norm": 0.7559711337089539,
"learning_rate": 8.495040965933593e-06,
"loss": 0.7473,
"step": 5355
},
{
"epoch": 2.927615405626878,
"grad_norm": 0.7242297530174255,
"learning_rate": 8.473479948253558e-06,
"loss": 0.8165,
"step": 5360
},
{
"epoch": 2.9303468997541655,
"grad_norm": 0.7911830544471741,
"learning_rate": 8.451918930573524e-06,
"loss": 0.81,
"step": 5365
},
{
"epoch": 2.9330783938814533,
"grad_norm": 0.6985219120979309,
"learning_rate": 8.430357912893488e-06,
"loss": 0.8019,
"step": 5370
},
{
"epoch": 2.9358098880087407,
"grad_norm": 0.7943094968795776,
"learning_rate": 8.408796895213454e-06,
"loss": 0.7902,
"step": 5375
},
{
"epoch": 2.9385413821360284,
"grad_norm": 0.7524906992912292,
"learning_rate": 8.38723587753342e-06,
"loss": 0.7616,
"step": 5380
},
{
"epoch": 2.941272876263316,
"grad_norm": 0.8610596656799316,
"learning_rate": 8.365674859853385e-06,
"loss": 0.7554,
"step": 5385
},
{
"epoch": 2.9440043703906036,
"grad_norm": 0.7854871153831482,
"learning_rate": 8.34411384217335e-06,
"loss": 0.7412,
"step": 5390
},
{
"epoch": 2.9467358645178914,
"grad_norm": 0.738402247428894,
"learning_rate": 8.322552824493315e-06,
"loss": 0.815,
"step": 5395
},
{
"epoch": 2.9494673586451787,
"grad_norm": 0.6899759769439697,
"learning_rate": 8.300991806813281e-06,
"loss": 0.7723,
"step": 5400
},
{
"epoch": 2.9494673586451787,
"eval_loss": 0.9063332080841064,
"eval_runtime": 297.5232,
"eval_samples_per_second": 11.834,
"eval_steps_per_second": 2.961,
"step": 5400
},
{
"epoch": 2.9521988527724665,
"grad_norm": 0.7586565613746643,
"learning_rate": 8.279430789133247e-06,
"loss": 0.7925,
"step": 5405
},
{
"epoch": 2.9549303468997543,
"grad_norm": 0.7677170038223267,
"learning_rate": 8.257869771453212e-06,
"loss": 0.7585,
"step": 5410
},
{
"epoch": 2.9576618410270417,
"grad_norm": 0.6486620903015137,
"learning_rate": 8.23630875377318e-06,
"loss": 0.7712,
"step": 5415
},
{
"epoch": 2.9603933351543295,
"grad_norm": 0.7643607258796692,
"learning_rate": 8.214747736093144e-06,
"loss": 0.8175,
"step": 5420
},
{
"epoch": 2.9631248292816172,
"grad_norm": 0.8257291316986084,
"learning_rate": 8.19318671841311e-06,
"loss": 0.8093,
"step": 5425
},
{
"epoch": 2.9658563234089046,
"grad_norm": 0.8423243761062622,
"learning_rate": 8.171625700733076e-06,
"loss": 0.7726,
"step": 5430
},
{
"epoch": 2.9685878175361924,
"grad_norm": 0.7092588543891907,
"learning_rate": 8.15006468305304e-06,
"loss": 0.7392,
"step": 5435
},
{
"epoch": 2.97131931166348,
"grad_norm": 0.6785277128219604,
"learning_rate": 8.128503665373006e-06,
"loss": 0.7683,
"step": 5440
},
{
"epoch": 2.9740508057907675,
"grad_norm": 0.7288199067115784,
"learning_rate": 8.10694264769297e-06,
"loss": 0.7282,
"step": 5445
},
{
"epoch": 2.9767822999180553,
"grad_norm": 0.8532629013061523,
"learning_rate": 8.085381630012937e-06,
"loss": 0.7384,
"step": 5450
},
{
"epoch": 2.9795137940453427,
"grad_norm": 0.8098965287208557,
"learning_rate": 8.063820612332903e-06,
"loss": 0.8205,
"step": 5455
},
{
"epoch": 2.9822452881726305,
"grad_norm": 0.7966192364692688,
"learning_rate": 8.042259594652867e-06,
"loss": 0.7744,
"step": 5460
},
{
"epoch": 2.984976782299918,
"grad_norm": 0.7212642431259155,
"learning_rate": 8.020698576972833e-06,
"loss": 0.7576,
"step": 5465
},
{
"epoch": 2.9877082764272056,
"grad_norm": 0.7706379294395447,
"learning_rate": 7.999137559292798e-06,
"loss": 0.7342,
"step": 5470
},
{
"epoch": 2.9904397705544934,
"grad_norm": 0.8115203380584717,
"learning_rate": 7.977576541612764e-06,
"loss": 0.7622,
"step": 5475
},
{
"epoch": 2.9931712646817807,
"grad_norm": 0.7536317706108093,
"learning_rate": 7.95601552393273e-06,
"loss": 0.7404,
"step": 5480
},
{
"epoch": 2.9959027588090685,
"grad_norm": 0.7357735633850098,
"learning_rate": 7.934454506252694e-06,
"loss": 0.7306,
"step": 5485
},
{
"epoch": 2.9986342529363563,
"grad_norm": 0.8137198686599731,
"learning_rate": 7.91289348857266e-06,
"loss": 0.8075,
"step": 5490
},
{
"epoch": 3.001092597650915,
"grad_norm": 0.7922897338867188,
"learning_rate": 7.891332470892627e-06,
"loss": 0.9653,
"step": 5495
},
{
"epoch": 3.0038240917782026,
"grad_norm": 0.7555220127105713,
"learning_rate": 7.869771453212593e-06,
"loss": 0.7151,
"step": 5500
},
{
"epoch": 3.0065555859054904,
"grad_norm": 0.7075891494750977,
"learning_rate": 7.848210435532557e-06,
"loss": 0.7195,
"step": 5505
},
{
"epoch": 3.009287080032778,
"grad_norm": 0.7720159888267517,
"learning_rate": 7.826649417852523e-06,
"loss": 0.7436,
"step": 5510
},
{
"epoch": 3.0120185741600656,
"grad_norm": 0.6859265565872192,
"learning_rate": 7.80508840017249e-06,
"loss": 0.7296,
"step": 5515
},
{
"epoch": 3.0147500682873534,
"grad_norm": 0.6583262085914612,
"learning_rate": 7.783527382492454e-06,
"loss": 0.7235,
"step": 5520
},
{
"epoch": 3.0174815624146407,
"grad_norm": 0.7170140147209167,
"learning_rate": 7.76196636481242e-06,
"loss": 0.7122,
"step": 5525
},
{
"epoch": 3.0202130565419285,
"grad_norm": 0.9034721255302429,
"learning_rate": 7.740405347132384e-06,
"loss": 0.7249,
"step": 5530
},
{
"epoch": 3.022944550669216,
"grad_norm": 0.8089941143989563,
"learning_rate": 7.71884432945235e-06,
"loss": 0.7638,
"step": 5535
},
{
"epoch": 3.0256760447965036,
"grad_norm": 0.8177892565727234,
"learning_rate": 7.697283311772316e-06,
"loss": 0.7678,
"step": 5540
},
{
"epoch": 3.0284075389237914,
"grad_norm": 0.7905592322349548,
"learning_rate": 7.67572229409228e-06,
"loss": 0.7311,
"step": 5545
},
{
"epoch": 3.031139033051079,
"grad_norm": 0.7201488614082336,
"learning_rate": 7.654161276412247e-06,
"loss": 0.7239,
"step": 5550
},
{
"epoch": 3.0338705271783666,
"grad_norm": 0.725028932094574,
"learning_rate": 7.632600258732211e-06,
"loss": 0.7306,
"step": 5555
},
{
"epoch": 3.0366020213056544,
"grad_norm": 0.7748144865036011,
"learning_rate": 7.611039241052177e-06,
"loss": 0.7359,
"step": 5560
},
{
"epoch": 3.0393335154329417,
"grad_norm": 0.7894132137298584,
"learning_rate": 7.5894782233721425e-06,
"loss": 0.7677,
"step": 5565
},
{
"epoch": 3.0420650095602295,
"grad_norm": 0.8185566067695618,
"learning_rate": 7.567917205692108e-06,
"loss": 0.7293,
"step": 5570
},
{
"epoch": 3.044796503687517,
"grad_norm": 0.7175382375717163,
"learning_rate": 7.5463561880120755e-06,
"loss": 0.7543,
"step": 5575
},
{
"epoch": 3.0475279978148047,
"grad_norm": 0.8099451065063477,
"learning_rate": 7.524795170332041e-06,
"loss": 0.7007,
"step": 5580
},
{
"epoch": 3.0502594919420924,
"grad_norm": 0.9371067881584167,
"learning_rate": 7.503234152652006e-06,
"loss": 0.7748,
"step": 5585
},
{
"epoch": 3.05299098606938,
"grad_norm": 0.7716384530067444,
"learning_rate": 7.48167313497197e-06,
"loss": 0.7335,
"step": 5590
},
{
"epoch": 3.0557224801966676,
"grad_norm": 0.8236814737319946,
"learning_rate": 7.4601121172919364e-06,
"loss": 0.7944,
"step": 5595
},
{
"epoch": 3.0584539743239554,
"grad_norm": 0.8343513011932373,
"learning_rate": 7.4385510996119025e-06,
"loss": 0.7522,
"step": 5600
},
{
"epoch": 3.0611854684512427,
"grad_norm": 0.7970889806747437,
"learning_rate": 7.416990081931868e-06,
"loss": 0.7322,
"step": 5605
},
{
"epoch": 3.0639169625785305,
"grad_norm": 0.6767557859420776,
"learning_rate": 7.395429064251833e-06,
"loss": 0.6968,
"step": 5610
},
{
"epoch": 3.066648456705818,
"grad_norm": 0.7309384942054749,
"learning_rate": 7.373868046571798e-06,
"loss": 0.712,
"step": 5615
},
{
"epoch": 3.0693799508331057,
"grad_norm": 0.7825921177864075,
"learning_rate": 7.3523070288917635e-06,
"loss": 0.7812,
"step": 5620
},
{
"epoch": 3.0721114449603935,
"grad_norm": 0.8280141949653625,
"learning_rate": 7.3307460112117295e-06,
"loss": 0.7651,
"step": 5625
},
{
"epoch": 3.074842939087681,
"grad_norm": 0.7479425072669983,
"learning_rate": 7.309184993531695e-06,
"loss": 0.7427,
"step": 5630
},
{
"epoch": 3.0775744332149686,
"grad_norm": 0.7494877576828003,
"learning_rate": 7.287623975851661e-06,
"loss": 0.7157,
"step": 5635
},
{
"epoch": 3.0803059273422564,
"grad_norm": 0.7961239814758301,
"learning_rate": 7.266062958171626e-06,
"loss": 0.7455,
"step": 5640
},
{
"epoch": 3.0830374214695437,
"grad_norm": 0.84522944688797,
"learning_rate": 7.244501940491591e-06,
"loss": 0.768,
"step": 5645
},
{
"epoch": 3.0857689155968315,
"grad_norm": 0.8585657477378845,
"learning_rate": 7.222940922811557e-06,
"loss": 0.7919,
"step": 5650
},
{
"epoch": 3.088500409724119,
"grad_norm": 0.8459474444389343,
"learning_rate": 7.201379905131523e-06,
"loss": 0.7172,
"step": 5655
},
{
"epoch": 3.0912319038514067,
"grad_norm": 0.7859456539154053,
"learning_rate": 7.179818887451488e-06,
"loss": 0.7233,
"step": 5660
},
{
"epoch": 3.0939633979786945,
"grad_norm": 0.8313788175582886,
"learning_rate": 7.158257869771453e-06,
"loss": 0.7752,
"step": 5665
},
{
"epoch": 3.096694892105982,
"grad_norm": 0.7361313104629517,
"learning_rate": 7.136696852091418e-06,
"loss": 0.7507,
"step": 5670
},
{
"epoch": 3.0994263862332696,
"grad_norm": 0.7741536498069763,
"learning_rate": 7.115135834411384e-06,
"loss": 0.7164,
"step": 5675
},
{
"epoch": 3.1021578803605574,
"grad_norm": 0.7938446402549744,
"learning_rate": 7.0935748167313505e-06,
"loss": 0.7286,
"step": 5680
},
{
"epoch": 3.1048893744878447,
"grad_norm": 0.8923072218894958,
"learning_rate": 7.072013799051316e-06,
"loss": 0.7706,
"step": 5685
},
{
"epoch": 3.1076208686151325,
"grad_norm": 0.7862333655357361,
"learning_rate": 7.050452781371281e-06,
"loss": 0.782,
"step": 5690
},
{
"epoch": 3.11035236274242,
"grad_norm": 0.7718535661697388,
"learning_rate": 7.028891763691246e-06,
"loss": 0.7341,
"step": 5695
},
{
"epoch": 3.1130838568697077,
"grad_norm": 0.747524082660675,
"learning_rate": 7.0073307460112115e-06,
"loss": 0.7028,
"step": 5700
},
{
"epoch": 3.1130838568697077,
"eval_loss": 0.9074884653091431,
"eval_runtime": 299.3327,
"eval_samples_per_second": 11.763,
"eval_steps_per_second": 2.943,
"step": 5700
},
{
"epoch": 3.1158153509969955,
"grad_norm": 0.7153909206390381,
"learning_rate": 6.985769728331178e-06,
"loss": 0.7808,
"step": 5705
},
{
"epoch": 3.118546845124283,
"grad_norm": 0.6645474433898926,
"learning_rate": 6.964208710651143e-06,
"loss": 0.7289,
"step": 5710
},
{
"epoch": 3.1212783392515706,
"grad_norm": 1.0183302164077759,
"learning_rate": 6.942647692971108e-06,
"loss": 0.7468,
"step": 5715
},
{
"epoch": 3.1240098333788584,
"grad_norm": 0.7027918100357056,
"learning_rate": 6.921086675291074e-06,
"loss": 0.7143,
"step": 5720
},
{
"epoch": 3.1267413275061458,
"grad_norm": 0.8599754571914673,
"learning_rate": 6.899525657611039e-06,
"loss": 0.7373,
"step": 5725
},
{
"epoch": 3.1294728216334335,
"grad_norm": 0.73380446434021,
"learning_rate": 6.8779646399310055e-06,
"loss": 0.7115,
"step": 5730
},
{
"epoch": 3.1322043157607213,
"grad_norm": 0.6875489950180054,
"learning_rate": 6.856403622250971e-06,
"loss": 0.7186,
"step": 5735
},
{
"epoch": 3.1349358098880087,
"grad_norm": 0.7565447092056274,
"learning_rate": 6.834842604570936e-06,
"loss": 0.7686,
"step": 5740
},
{
"epoch": 3.1376673040152965,
"grad_norm": 0.8121775984764099,
"learning_rate": 6.813281586890901e-06,
"loss": 0.7716,
"step": 5745
},
{
"epoch": 3.140398798142584,
"grad_norm": 0.8609010577201843,
"learning_rate": 6.791720569210866e-06,
"loss": 0.7736,
"step": 5750
},
{
"epoch": 3.1431302922698716,
"grad_norm": 0.7285606861114502,
"learning_rate": 6.770159551530832e-06,
"loss": 0.7437,
"step": 5755
},
{
"epoch": 3.1458617863971594,
"grad_norm": 0.9312959313392639,
"learning_rate": 6.7485985338507986e-06,
"loss": 0.7623,
"step": 5760
},
{
"epoch": 3.1485932805244468,
"grad_norm": 0.7533763647079468,
"learning_rate": 6.727037516170764e-06,
"loss": 0.7042,
"step": 5765
},
{
"epoch": 3.1513247746517346,
"grad_norm": 0.7893332839012146,
"learning_rate": 6.705476498490729e-06,
"loss": 0.7522,
"step": 5770
},
{
"epoch": 3.154056268779022,
"grad_norm": 0.835340678691864,
"learning_rate": 6.683915480810694e-06,
"loss": 0.7713,
"step": 5775
},
{
"epoch": 3.1567877629063097,
"grad_norm": 0.7660753726959229,
"learning_rate": 6.6623544631306595e-06,
"loss": 0.7314,
"step": 5780
},
{
"epoch": 3.1595192570335975,
"grad_norm": 0.8737154006958008,
"learning_rate": 6.640793445450626e-06,
"loss": 0.7092,
"step": 5785
},
{
"epoch": 3.162250751160885,
"grad_norm": 0.7273027300834656,
"learning_rate": 6.619232427770591e-06,
"loss": 0.7062,
"step": 5790
},
{
"epoch": 3.1649822452881726,
"grad_norm": 0.6877878308296204,
"learning_rate": 6.597671410090556e-06,
"loss": 0.7636,
"step": 5795
},
{
"epoch": 3.1677137394154604,
"grad_norm": 0.7895363569259644,
"learning_rate": 6.576110392410522e-06,
"loss": 0.7124,
"step": 5800
},
{
"epoch": 3.1704452335427478,
"grad_norm": 0.812980055809021,
"learning_rate": 6.554549374730487e-06,
"loss": 0.7324,
"step": 5805
},
{
"epoch": 3.1731767276700356,
"grad_norm": 0.8730754852294922,
"learning_rate": 6.5329883570504535e-06,
"loss": 0.7314,
"step": 5810
},
{
"epoch": 3.1759082217973233,
"grad_norm": 0.8842508792877197,
"learning_rate": 6.511427339370419e-06,
"loss": 0.7775,
"step": 5815
},
{
"epoch": 3.1786397159246107,
"grad_norm": 0.749729573726654,
"learning_rate": 6.489866321690384e-06,
"loss": 0.7284,
"step": 5820
},
{
"epoch": 3.1813712100518985,
"grad_norm": 0.7484405636787415,
"learning_rate": 6.468305304010349e-06,
"loss": 0.6989,
"step": 5825
},
{
"epoch": 3.184102704179186,
"grad_norm": 0.8252250552177429,
"learning_rate": 6.4467442863303144e-06,
"loss": 0.7238,
"step": 5830
},
{
"epoch": 3.1868341983064736,
"grad_norm": 0.794208288192749,
"learning_rate": 6.4251832686502805e-06,
"loss": 0.7283,
"step": 5835
},
{
"epoch": 3.1895656924337614,
"grad_norm": 0.7774311304092407,
"learning_rate": 6.403622250970247e-06,
"loss": 0.7232,
"step": 5840
},
{
"epoch": 3.1922971865610488,
"grad_norm": 0.9857580661773682,
"learning_rate": 6.382061233290212e-06,
"loss": 0.7987,
"step": 5845
},
{
"epoch": 3.1950286806883366,
"grad_norm": 0.744079053401947,
"learning_rate": 6.360500215610177e-06,
"loss": 0.7764,
"step": 5850
},
{
"epoch": 3.197760174815624,
"grad_norm": 0.8476716876029968,
"learning_rate": 6.338939197930142e-06,
"loss": 0.7653,
"step": 5855
},
{
"epoch": 3.2004916689429117,
"grad_norm": 0.8362342715263367,
"learning_rate": 6.3173781802501076e-06,
"loss": 0.6875,
"step": 5860
},
{
"epoch": 3.2032231630701995,
"grad_norm": 0.838164210319519,
"learning_rate": 6.295817162570074e-06,
"loss": 0.7436,
"step": 5865
},
{
"epoch": 3.205954657197487,
"grad_norm": 0.6917914748191833,
"learning_rate": 6.274256144890039e-06,
"loss": 0.7077,
"step": 5870
},
{
"epoch": 3.2086861513247746,
"grad_norm": 0.8909876942634583,
"learning_rate": 6.252695127210004e-06,
"loss": 0.7257,
"step": 5875
},
{
"epoch": 3.2114176454520624,
"grad_norm": 0.8921764492988586,
"learning_rate": 6.23113410952997e-06,
"loss": 0.7231,
"step": 5880
},
{
"epoch": 3.21414913957935,
"grad_norm": 0.7965174317359924,
"learning_rate": 6.2095730918499354e-06,
"loss": 0.7677,
"step": 5885
},
{
"epoch": 3.2168806337066376,
"grad_norm": 0.9181920886039734,
"learning_rate": 6.1880120741699015e-06,
"loss": 0.7563,
"step": 5890
},
{
"epoch": 3.2196121278339254,
"grad_norm": 0.7486518025398254,
"learning_rate": 6.166451056489867e-06,
"loss": 0.751,
"step": 5895
},
{
"epoch": 3.2223436219612127,
"grad_norm": 0.794414758682251,
"learning_rate": 6.144890038809832e-06,
"loss": 0.7194,
"step": 5900
},
{
"epoch": 3.2250751160885005,
"grad_norm": 0.7770363092422485,
"learning_rate": 6.123329021129797e-06,
"loss": 0.7214,
"step": 5905
},
{
"epoch": 3.227806610215788,
"grad_norm": 0.804531455039978,
"learning_rate": 6.1017680034497625e-06,
"loss": 0.7472,
"step": 5910
},
{
"epoch": 3.2305381043430756,
"grad_norm": 0.7146393060684204,
"learning_rate": 6.0802069857697286e-06,
"loss": 0.7219,
"step": 5915
},
{
"epoch": 3.2332695984703634,
"grad_norm": 1.0326611995697021,
"learning_rate": 6.058645968089695e-06,
"loss": 0.7221,
"step": 5920
},
{
"epoch": 3.236001092597651,
"grad_norm": 0.6951677203178406,
"learning_rate": 6.03708495040966e-06,
"loss": 0.7308,
"step": 5925
},
{
"epoch": 3.2387325867249386,
"grad_norm": 0.9959564805030823,
"learning_rate": 6.015523932729625e-06,
"loss": 0.77,
"step": 5930
},
{
"epoch": 3.2414640808522264,
"grad_norm": 1.0677785873413086,
"learning_rate": 5.99396291504959e-06,
"loss": 0.7854,
"step": 5935
},
{
"epoch": 3.2441955749795137,
"grad_norm": 0.7543079257011414,
"learning_rate": 5.972401897369556e-06,
"loss": 0.6869,
"step": 5940
},
{
"epoch": 3.2469270691068015,
"grad_norm": 0.7693931460380554,
"learning_rate": 5.950840879689522e-06,
"loss": 0.7246,
"step": 5945
},
{
"epoch": 3.249658563234089,
"grad_norm": 0.8066092729568481,
"learning_rate": 5.929279862009487e-06,
"loss": 0.7541,
"step": 5950
},
{
"epoch": 3.2523900573613767,
"grad_norm": 0.7975667119026184,
"learning_rate": 5.907718844329452e-06,
"loss": 0.7092,
"step": 5955
},
{
"epoch": 3.2551215514886644,
"grad_norm": 0.8280119895935059,
"learning_rate": 5.886157826649417e-06,
"loss": 0.7208,
"step": 5960
},
{
"epoch": 3.257853045615952,
"grad_norm": 0.8499802350997925,
"learning_rate": 5.8645968089693835e-06,
"loss": 0.7709,
"step": 5965
},
{
"epoch": 3.2605845397432396,
"grad_norm": 0.8265390396118164,
"learning_rate": 5.8430357912893496e-06,
"loss": 0.7042,
"step": 5970
},
{
"epoch": 3.2633160338705274,
"grad_norm": 0.7472238540649414,
"learning_rate": 5.821474773609315e-06,
"loss": 0.758,
"step": 5975
},
{
"epoch": 3.2660475279978147,
"grad_norm": 0.8082042336463928,
"learning_rate": 5.79991375592928e-06,
"loss": 0.8441,
"step": 5980
},
{
"epoch": 3.2687790221251025,
"grad_norm": 0.718476414680481,
"learning_rate": 5.778352738249245e-06,
"loss": 0.7007,
"step": 5985
},
{
"epoch": 3.27151051625239,
"grad_norm": 0.8342536687850952,
"learning_rate": 5.7567917205692105e-06,
"loss": 0.7597,
"step": 5990
},
{
"epoch": 3.2742420103796777,
"grad_norm": 0.8257967233657837,
"learning_rate": 5.735230702889177e-06,
"loss": 0.7252,
"step": 5995
},
{
"epoch": 3.2769735045069655,
"grad_norm": 0.8357173800468445,
"learning_rate": 5.713669685209142e-06,
"loss": 0.7337,
"step": 6000
},
{
"epoch": 3.2769735045069655,
"eval_loss": 0.9046825170516968,
"eval_runtime": 298.2206,
"eval_samples_per_second": 11.807,
"eval_steps_per_second": 2.954,
"step": 6000
}
],
"logging_steps": 5,
"max_steps": 7324,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 300,
"stateful_callbacks": {
"EarlyStoppingCallback": [
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 2
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 2
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 3
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 3
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 4
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 4
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 6
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 6
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 6
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 6
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 2
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 2
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 3
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 3
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 4
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 4
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 6
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 6
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 7
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 7
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 8
}
},
{
"args": {
"early_stopping_patience": 8,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 8
}
}
],
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.961099498987015e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}