Orca_save / SFT /trainer_state.json
pepoo20's picture
Upload SFT/trainer_state.json with huggingface_hub
23c800b verified
{
"best_metric": 0.19655267894268036,
"best_model_checkpoint": "saves/Orca/SFT/checkpoint-2000",
"epoch": 2.0,
"eval_steps": 250,
"global_step": 2062,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004849660523763337,
"grad_norm": 1.569652795791626,
"learning_rate": 8.333333333333333e-07,
"loss": 1.763,
"step": 5
},
{
"epoch": 0.009699321047526674,
"grad_norm": 1.4889137744903564,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.7673,
"step": 10
},
{
"epoch": 0.014548981571290009,
"grad_norm": 1.3860485553741455,
"learning_rate": 2.5e-06,
"loss": 1.7696,
"step": 15
},
{
"epoch": 0.019398642095053348,
"grad_norm": 1.4874159097671509,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.7723,
"step": 20
},
{
"epoch": 0.02424830261881668,
"grad_norm": 1.4718151092529297,
"learning_rate": 4.166666666666667e-06,
"loss": 1.7295,
"step": 25
},
{
"epoch": 0.029097963142580018,
"grad_norm": 1.5262246131896973,
"learning_rate": 5e-06,
"loss": 1.7863,
"step": 30
},
{
"epoch": 0.03394762366634336,
"grad_norm": 1.6720690727233887,
"learning_rate": 5.833333333333334e-06,
"loss": 1.709,
"step": 35
},
{
"epoch": 0.038797284190106696,
"grad_norm": 1.462561845779419,
"learning_rate": 6.666666666666667e-06,
"loss": 1.6664,
"step": 40
},
{
"epoch": 0.04364694471387003,
"grad_norm": 1.6730310916900635,
"learning_rate": 7.5e-06,
"loss": 1.6421,
"step": 45
},
{
"epoch": 0.04849660523763336,
"grad_norm": 1.538442850112915,
"learning_rate": 8.333333333333334e-06,
"loss": 1.6169,
"step": 50
},
{
"epoch": 0.0533462657613967,
"grad_norm": 1.7747137546539307,
"learning_rate": 9.166666666666666e-06,
"loss": 1.5235,
"step": 55
},
{
"epoch": 0.058195926285160036,
"grad_norm": 1.600160837173462,
"learning_rate": 1e-05,
"loss": 1.4392,
"step": 60
},
{
"epoch": 0.06304558680892337,
"grad_norm": 1.3897379636764526,
"learning_rate": 1.0833333333333334e-05,
"loss": 1.3295,
"step": 65
},
{
"epoch": 0.06789524733268672,
"grad_norm": 1.3479865789413452,
"learning_rate": 1.1666666666666668e-05,
"loss": 1.1758,
"step": 70
},
{
"epoch": 0.07274490785645005,
"grad_norm": 1.0993175506591797,
"learning_rate": 1.25e-05,
"loss": 1.1012,
"step": 75
},
{
"epoch": 0.07759456838021339,
"grad_norm": 1.0077180862426758,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.9917,
"step": 80
},
{
"epoch": 0.08244422890397672,
"grad_norm": 0.8057171106338501,
"learning_rate": 1.4166666666666668e-05,
"loss": 0.8798,
"step": 85
},
{
"epoch": 0.08729388942774007,
"grad_norm": 0.6777159571647644,
"learning_rate": 1.5e-05,
"loss": 0.7895,
"step": 90
},
{
"epoch": 0.0921435499515034,
"grad_norm": 0.5001732707023621,
"learning_rate": 1.5833333333333333e-05,
"loss": 0.7364,
"step": 95
},
{
"epoch": 0.09699321047526673,
"grad_norm": 0.4005896747112274,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.6936,
"step": 100
},
{
"epoch": 0.10184287099903007,
"grad_norm": 0.3276143968105316,
"learning_rate": 1.75e-05,
"loss": 0.6595,
"step": 105
},
{
"epoch": 0.1066925315227934,
"grad_norm": 0.29122063517570496,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.6316,
"step": 110
},
{
"epoch": 0.11154219204655674,
"grad_norm": 0.2869010269641876,
"learning_rate": 1.9166666666666667e-05,
"loss": 0.6033,
"step": 115
},
{
"epoch": 0.11639185257032007,
"grad_norm": 0.25405701994895935,
"learning_rate": 2e-05,
"loss": 0.5716,
"step": 120
},
{
"epoch": 0.12124151309408342,
"grad_norm": 0.24002915620803833,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.5691,
"step": 125
},
{
"epoch": 0.12609117361784675,
"grad_norm": 0.2358996719121933,
"learning_rate": 2.1666666666666667e-05,
"loss": 0.554,
"step": 130
},
{
"epoch": 0.1309408341416101,
"grad_norm": 0.21090734004974365,
"learning_rate": 2.25e-05,
"loss": 0.5194,
"step": 135
},
{
"epoch": 0.13579049466537343,
"grad_norm": 0.20737610757350922,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.4918,
"step": 140
},
{
"epoch": 0.14064015518913675,
"grad_norm": 0.1901807337999344,
"learning_rate": 2.4166666666666667e-05,
"loss": 0.4705,
"step": 145
},
{
"epoch": 0.1454898157129001,
"grad_norm": 0.19849984347820282,
"learning_rate": 2.5e-05,
"loss": 0.4595,
"step": 150
},
{
"epoch": 0.15033947623666344,
"grad_norm": 0.18864648044109344,
"learning_rate": 2.5833333333333336e-05,
"loss": 0.4407,
"step": 155
},
{
"epoch": 0.15518913676042678,
"grad_norm": 0.17015086114406586,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.4214,
"step": 160
},
{
"epoch": 0.1600387972841901,
"grad_norm": 0.17595945298671722,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.4343,
"step": 165
},
{
"epoch": 0.16488845780795344,
"grad_norm": 0.16629475355148315,
"learning_rate": 2.8333333333333335e-05,
"loss": 0.4045,
"step": 170
},
{
"epoch": 0.1697381183317168,
"grad_norm": 0.16392391920089722,
"learning_rate": 2.916666666666667e-05,
"loss": 0.3803,
"step": 175
},
{
"epoch": 0.17458777885548013,
"grad_norm": 0.1675371527671814,
"learning_rate": 3e-05,
"loss": 0.3762,
"step": 180
},
{
"epoch": 0.17943743937924345,
"grad_norm": 0.15912921726703644,
"learning_rate": 3.0833333333333335e-05,
"loss": 0.3698,
"step": 185
},
{
"epoch": 0.1842870999030068,
"grad_norm": 0.1546890288591385,
"learning_rate": 3.1666666666666666e-05,
"loss": 0.359,
"step": 190
},
{
"epoch": 0.18913676042677013,
"grad_norm": 0.14289158582687378,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.349,
"step": 195
},
{
"epoch": 0.19398642095053345,
"grad_norm": 0.13693265616893768,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.3145,
"step": 200
},
{
"epoch": 0.1988360814742968,
"grad_norm": 0.15631736814975739,
"learning_rate": 3.4166666666666666e-05,
"loss": 0.3266,
"step": 205
},
{
"epoch": 0.20368574199806014,
"grad_norm": 0.13729828596115112,
"learning_rate": 3.5e-05,
"loss": 0.3368,
"step": 210
},
{
"epoch": 0.20853540252182348,
"grad_norm": 0.13479730486869812,
"learning_rate": 3.5833333333333335e-05,
"loss": 0.3025,
"step": 215
},
{
"epoch": 0.2133850630455868,
"grad_norm": 0.13599981367588043,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.3121,
"step": 220
},
{
"epoch": 0.21823472356935014,
"grad_norm": 0.1292022317647934,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.2982,
"step": 225
},
{
"epoch": 0.22308438409311349,
"grad_norm": 0.13855475187301636,
"learning_rate": 3.8333333333333334e-05,
"loss": 0.2709,
"step": 230
},
{
"epoch": 0.22793404461687683,
"grad_norm": 0.12373723834753036,
"learning_rate": 3.9166666666666665e-05,
"loss": 0.2903,
"step": 235
},
{
"epoch": 0.23278370514064015,
"grad_norm": 0.1207897961139679,
"learning_rate": 4e-05,
"loss": 0.3064,
"step": 240
},
{
"epoch": 0.2376333656644035,
"grad_norm": 0.12190013378858566,
"learning_rate": 4.0833333333333334e-05,
"loss": 0.3189,
"step": 245
},
{
"epoch": 0.24248302618816683,
"grad_norm": 0.11036136001348495,
"learning_rate": 4.166666666666667e-05,
"loss": 0.2823,
"step": 250
},
{
"epoch": 0.24248302618816683,
"eval_loss": 0.2783246636390686,
"eval_runtime": 48.1034,
"eval_samples_per_second": 14.011,
"eval_steps_per_second": 0.894,
"step": 250
},
{
"epoch": 0.24733268671193018,
"grad_norm": 0.11338551342487335,
"learning_rate": 4.25e-05,
"loss": 0.2865,
"step": 255
},
{
"epoch": 0.2521823472356935,
"grad_norm": 0.1275234967470169,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.279,
"step": 260
},
{
"epoch": 0.25703200775945684,
"grad_norm": 0.1382416933774948,
"learning_rate": 4.4166666666666665e-05,
"loss": 0.2578,
"step": 265
},
{
"epoch": 0.2618816682832202,
"grad_norm": 0.13280175626277924,
"learning_rate": 4.5e-05,
"loss": 0.3027,
"step": 270
},
{
"epoch": 0.2667313288069835,
"grad_norm": 0.11413029581308365,
"learning_rate": 4.5833333333333334e-05,
"loss": 0.2647,
"step": 275
},
{
"epoch": 0.27158098933074687,
"grad_norm": 0.12923401594161987,
"learning_rate": 4.666666666666667e-05,
"loss": 0.2984,
"step": 280
},
{
"epoch": 0.27643064985451016,
"grad_norm": 0.11887092143297195,
"learning_rate": 4.75e-05,
"loss": 0.2683,
"step": 285
},
{
"epoch": 0.2812803103782735,
"grad_norm": 0.12000833451747894,
"learning_rate": 4.8333333333333334e-05,
"loss": 0.2747,
"step": 290
},
{
"epoch": 0.28612997090203685,
"grad_norm": 0.11771322786808014,
"learning_rate": 4.9166666666666665e-05,
"loss": 0.233,
"step": 295
},
{
"epoch": 0.2909796314258002,
"grad_norm": 0.10835352540016174,
"learning_rate": 5e-05,
"loss": 0.2444,
"step": 300
},
{
"epoch": 0.29582929194956353,
"grad_norm": 0.12001065164804459,
"learning_rate": 4.999900657500545e-05,
"loss": 0.2234,
"step": 305
},
{
"epoch": 0.3006789524733269,
"grad_norm": 0.11877791583538055,
"learning_rate": 4.9996026378973266e-05,
"loss": 0.2467,
"step": 310
},
{
"epoch": 0.3055286129970902,
"grad_norm": 0.12458127737045288,
"learning_rate": 4.999105964875153e-05,
"loss": 0.2559,
"step": 315
},
{
"epoch": 0.31037827352085356,
"grad_norm": 0.11346752941608429,
"learning_rate": 4.9984106779066174e-05,
"loss": 0.2523,
"step": 320
},
{
"epoch": 0.31522793404461685,
"grad_norm": 0.13425442576408386,
"learning_rate": 4.9975168322489554e-05,
"loss": 0.2697,
"step": 325
},
{
"epoch": 0.3200775945683802,
"grad_norm": 0.11504397541284561,
"learning_rate": 4.996424498939656e-05,
"loss": 0.2553,
"step": 330
},
{
"epoch": 0.32492725509214354,
"grad_norm": 0.12158407270908356,
"learning_rate": 4.9951337647908165e-05,
"loss": 0.2477,
"step": 335
},
{
"epoch": 0.3297769156159069,
"grad_norm": 0.12656843662261963,
"learning_rate": 4.9936447323822424e-05,
"loss": 0.2328,
"step": 340
},
{
"epoch": 0.33462657613967023,
"grad_norm": 0.1163104996085167,
"learning_rate": 4.991957520053294e-05,
"loss": 0.2509,
"step": 345
},
{
"epoch": 0.3394762366634336,
"grad_norm": 0.12447489798069,
"learning_rate": 4.990072261893484e-05,
"loss": 0.2589,
"step": 350
},
{
"epoch": 0.3443258971871969,
"grad_norm": 0.11267515271902084,
"learning_rate": 4.9879891077318176e-05,
"loss": 0.2446,
"step": 355
},
{
"epoch": 0.34917555771096026,
"grad_norm": 0.13075344264507294,
"learning_rate": 4.985708223124888e-05,
"loss": 0.2587,
"step": 360
},
{
"epoch": 0.35402521823472355,
"grad_norm": 0.10673461854457855,
"learning_rate": 4.9832297893437186e-05,
"loss": 0.2457,
"step": 365
},
{
"epoch": 0.3588748787584869,
"grad_norm": 0.12786507606506348,
"learning_rate": 4.980554003359354e-05,
"loss": 0.2369,
"step": 370
},
{
"epoch": 0.36372453928225024,
"grad_norm": 0.1437879055738449,
"learning_rate": 4.9776810778272075e-05,
"loss": 0.2736,
"step": 375
},
{
"epoch": 0.3685741998060136,
"grad_norm": 0.12847022712230682,
"learning_rate": 4.9746112410701625e-05,
"loss": 0.2252,
"step": 380
},
{
"epoch": 0.3734238603297769,
"grad_norm": 0.11457338184118271,
"learning_rate": 4.9713447370604236e-05,
"loss": 0.2508,
"step": 385
},
{
"epoch": 0.37827352085354027,
"grad_norm": 0.11042597144842148,
"learning_rate": 4.967881825400129e-05,
"loss": 0.2306,
"step": 390
},
{
"epoch": 0.3831231813773036,
"grad_norm": 0.12592245638370514,
"learning_rate": 4.964222781300719e-05,
"loss": 0.2599,
"step": 395
},
{
"epoch": 0.3879728419010669,
"grad_norm": 0.11546192318201065,
"learning_rate": 4.960367895561063e-05,
"loss": 0.2225,
"step": 400
},
{
"epoch": 0.39282250242483024,
"grad_norm": 0.12539242208003998,
"learning_rate": 4.956317474544348e-05,
"loss": 0.2432,
"step": 405
},
{
"epoch": 0.3976721629485936,
"grad_norm": 0.10763729363679886,
"learning_rate": 4.952071840153732e-05,
"loss": 0.2307,
"step": 410
},
{
"epoch": 0.40252182347235693,
"grad_norm": 0.11994805932044983,
"learning_rate": 4.947631329806761e-05,
"loss": 0.2282,
"step": 415
},
{
"epoch": 0.4073714839961203,
"grad_norm": 0.13727760314941406,
"learning_rate": 4.9429962964085517e-05,
"loss": 0.2225,
"step": 420
},
{
"epoch": 0.4122211445198836,
"grad_norm": 0.1300915628671646,
"learning_rate": 4.9381671083237476e-05,
"loss": 0.2393,
"step": 425
},
{
"epoch": 0.41707080504364696,
"grad_norm": 0.12672416865825653,
"learning_rate": 4.9331441493472395e-05,
"loss": 0.2296,
"step": 430
},
{
"epoch": 0.4219204655674103,
"grad_norm": 0.13302814960479736,
"learning_rate": 4.9279278186736674e-05,
"loss": 0.2242,
"step": 435
},
{
"epoch": 0.4267701260911736,
"grad_norm": 0.12973704934120178,
"learning_rate": 4.922518530865693e-05,
"loss": 0.2329,
"step": 440
},
{
"epoch": 0.43161978661493694,
"grad_norm": 0.12950606644153595,
"learning_rate": 4.916916715821053e-05,
"loss": 0.2132,
"step": 445
},
{
"epoch": 0.4364694471387003,
"grad_norm": 0.12280883640050888,
"learning_rate": 4.911122818738394e-05,
"loss": 0.2255,
"step": 450
},
{
"epoch": 0.44131910766246363,
"grad_norm": 0.12878793478012085,
"learning_rate": 4.9051373000818887e-05,
"loss": 0.2268,
"step": 455
},
{
"epoch": 0.44616876818622697,
"grad_norm": 0.12943603098392487,
"learning_rate": 4.898960635544647e-05,
"loss": 0.2145,
"step": 460
},
{
"epoch": 0.4510184287099903,
"grad_norm": 0.13643978536128998,
"learning_rate": 4.8925933160109016e-05,
"loss": 0.2197,
"step": 465
},
{
"epoch": 0.45586808923375366,
"grad_norm": 0.1563604176044464,
"learning_rate": 4.886035847517003e-05,
"loss": 0.2449,
"step": 470
},
{
"epoch": 0.46071774975751695,
"grad_norm": 0.13257759809494019,
"learning_rate": 4.879288751211199e-05,
"loss": 0.2307,
"step": 475
},
{
"epoch": 0.4655674102812803,
"grad_norm": 0.13240696489810944,
"learning_rate": 4.8723525633122193e-05,
"loss": 0.2136,
"step": 480
},
{
"epoch": 0.47041707080504364,
"grad_norm": 0.14693856239318848,
"learning_rate": 4.8652278350666566e-05,
"loss": 0.2388,
"step": 485
},
{
"epoch": 0.475266731328807,
"grad_norm": 0.14097219705581665,
"learning_rate": 4.857915132705162e-05,
"loss": 0.2178,
"step": 490
},
{
"epoch": 0.4801163918525703,
"grad_norm": 0.1185833290219307,
"learning_rate": 4.850415037397439e-05,
"loss": 0.2283,
"step": 495
},
{
"epoch": 0.48496605237633367,
"grad_norm": 0.1279655396938324,
"learning_rate": 4.8427281452060594e-05,
"loss": 0.2186,
"step": 500
},
{
"epoch": 0.48496605237633367,
"eval_loss": 0.2229408472776413,
"eval_runtime": 48.0836,
"eval_samples_per_second": 14.017,
"eval_steps_per_second": 0.894,
"step": 500
},
{
"epoch": 0.489815712900097,
"grad_norm": 0.14021804928779602,
"learning_rate": 4.834855067039088e-05,
"loss": 0.227,
"step": 505
},
{
"epoch": 0.49466537342386036,
"grad_norm": 0.13102716207504272,
"learning_rate": 4.826796428601538e-05,
"loss": 0.2302,
"step": 510
},
{
"epoch": 0.49951503394762364,
"grad_norm": 0.11888754367828369,
"learning_rate": 4.818552870345635e-05,
"loss": 0.2245,
"step": 515
},
{
"epoch": 0.504364694471387,
"grad_norm": 0.13540378212928772,
"learning_rate": 4.810125047419926e-05,
"loss": 0.233,
"step": 520
},
{
"epoch": 0.5092143549951503,
"grad_norm": 0.12920723855495453,
"learning_rate": 4.8015136296172055e-05,
"loss": 0.2225,
"step": 525
},
{
"epoch": 0.5140640155189137,
"grad_norm": 0.12302406132221222,
"learning_rate": 4.792719301321289e-05,
"loss": 0.2155,
"step": 530
},
{
"epoch": 0.518913676042677,
"grad_norm": 0.12846626341342926,
"learning_rate": 4.783742761452619e-05,
"loss": 0.2285,
"step": 535
},
{
"epoch": 0.5237633365664404,
"grad_norm": 0.12521494925022125,
"learning_rate": 4.7745847234127206e-05,
"loss": 0.2112,
"step": 540
},
{
"epoch": 0.5286129970902037,
"grad_norm": 0.12830866873264313,
"learning_rate": 4.7652459150275055e-05,
"loss": 0.2246,
"step": 545
},
{
"epoch": 0.533462657613967,
"grad_norm": 0.14525972306728363,
"learning_rate": 4.7557270784894276e-05,
"loss": 0.2293,
"step": 550
},
{
"epoch": 0.5383123181377304,
"grad_norm": 0.14833694696426392,
"learning_rate": 4.746028970298497e-05,
"loss": 0.2366,
"step": 555
},
{
"epoch": 0.5431619786614937,
"grad_norm": 0.13993489742279053,
"learning_rate": 4.7361523612021616e-05,
"loss": 0.2456,
"step": 560
},
{
"epoch": 0.5480116391852571,
"grad_norm": 0.125143900513649,
"learning_rate": 4.726098036134046e-05,
"loss": 0.2365,
"step": 565
},
{
"epoch": 0.5528612997090203,
"grad_norm": 0.1390179991722107,
"learning_rate": 4.715866794151578e-05,
"loss": 0.233,
"step": 570
},
{
"epoch": 0.5577109602327837,
"grad_norm": 0.1502588987350464,
"learning_rate": 4.705459448372478e-05,
"loss": 0.234,
"step": 575
},
{
"epoch": 0.562560620756547,
"grad_norm": 0.1441139429807663,
"learning_rate": 4.6948768259101394e-05,
"loss": 0.2085,
"step": 580
},
{
"epoch": 0.5674102812803103,
"grad_norm": 0.136013925075531,
"learning_rate": 4.6841197678078965e-05,
"loss": 0.1938,
"step": 585
},
{
"epoch": 0.5722599418040737,
"grad_norm": 0.12127859890460968,
"learning_rate": 4.6731891289721786e-05,
"loss": 0.2009,
"step": 590
},
{
"epoch": 0.577109602327837,
"grad_norm": 0.14969481527805328,
"learning_rate": 4.6620857781045715e-05,
"loss": 0.2071,
"step": 595
},
{
"epoch": 0.5819592628516004,
"grad_norm": 0.13548845052719116,
"learning_rate": 4.65081059763278e-05,
"loss": 0.2265,
"step": 600
},
{
"epoch": 0.5868089233753637,
"grad_norm": 0.12766653299331665,
"learning_rate": 4.639364483640489e-05,
"loss": 0.2212,
"step": 605
},
{
"epoch": 0.5916585838991271,
"grad_norm": 0.13482384383678436,
"learning_rate": 4.627748345796158e-05,
"loss": 0.2145,
"step": 610
},
{
"epoch": 0.5965082444228904,
"grad_norm": 0.13684765994548798,
"learning_rate": 4.615963107280722e-05,
"loss": 0.2097,
"step": 615
},
{
"epoch": 0.6013579049466538,
"grad_norm": 0.1494571417570114,
"learning_rate": 4.604009704714219e-05,
"loss": 0.2282,
"step": 620
},
{
"epoch": 0.6062075654704171,
"grad_norm": 0.14703498780727386,
"learning_rate": 4.591889088081363e-05,
"loss": 0.1963,
"step": 625
},
{
"epoch": 0.6110572259941804,
"grad_norm": 0.151000514626503,
"learning_rate": 4.579602220656032e-05,
"loss": 0.2267,
"step": 630
},
{
"epoch": 0.6159068865179438,
"grad_norm": 0.1505574882030487,
"learning_rate": 4.567150078924723e-05,
"loss": 0.2298,
"step": 635
},
{
"epoch": 0.6207565470417071,
"grad_norm": 0.1409265249967575,
"learning_rate": 4.5545336525089444e-05,
"loss": 0.2051,
"step": 640
},
{
"epoch": 0.6256062075654704,
"grad_norm": 0.14167818427085876,
"learning_rate": 4.5417539440865616e-05,
"loss": 0.2302,
"step": 645
},
{
"epoch": 0.6304558680892337,
"grad_norm": 0.14084312319755554,
"learning_rate": 4.528811969312117e-05,
"loss": 0.2164,
"step": 650
},
{
"epoch": 0.635305528612997,
"grad_norm": 0.14464280009269714,
"learning_rate": 4.515708756736108e-05,
"loss": 0.1948,
"step": 655
},
{
"epoch": 0.6401551891367604,
"grad_norm": 0.141952782869339,
"learning_rate": 4.5024453477232444e-05,
"loss": 0.2193,
"step": 660
},
{
"epoch": 0.6450048496605237,
"grad_norm": 0.1446189135313034,
"learning_rate": 4.4890227963696895e-05,
"loss": 0.2141,
"step": 665
},
{
"epoch": 0.6498545101842871,
"grad_norm": 0.15042971074581146,
"learning_rate": 4.4754421694192835e-05,
"loss": 0.2125,
"step": 670
},
{
"epoch": 0.6547041707080504,
"grad_norm": 0.15916042029857635,
"learning_rate": 4.4617045461787665e-05,
"loss": 0.2215,
"step": 675
},
{
"epoch": 0.6595538312318138,
"grad_norm": 0.15135568380355835,
"learning_rate": 4.447811018432002e-05,
"loss": 0.1974,
"step": 680
},
{
"epoch": 0.6644034917555771,
"grad_norm": 0.12838397920131683,
"learning_rate": 4.4337626903532076e-05,
"loss": 0.2231,
"step": 685
},
{
"epoch": 0.6692531522793405,
"grad_norm": 0.145597442984581,
"learning_rate": 4.419560678419203e-05,
"loss": 0.2193,
"step": 690
},
{
"epoch": 0.6741028128031038,
"grad_norm": 0.14090026915073395,
"learning_rate": 4.40520611132068e-05,
"loss": 0.2196,
"step": 695
},
{
"epoch": 0.6789524733268671,
"grad_norm": 0.1343528777360916,
"learning_rate": 4.390700129872497e-05,
"loss": 0.1998,
"step": 700
},
{
"epoch": 0.6838021338506305,
"grad_norm": 0.14349782466888428,
"learning_rate": 4.376043886923015e-05,
"loss": 0.2073,
"step": 705
},
{
"epoch": 0.6886517943743938,
"grad_norm": 0.15432004630565643,
"learning_rate": 4.361238547262484e-05,
"loss": 0.2184,
"step": 710
},
{
"epoch": 0.6935014548981572,
"grad_norm": 0.13481660187244415,
"learning_rate": 4.346285287530458e-05,
"loss": 0.2248,
"step": 715
},
{
"epoch": 0.6983511154219205,
"grad_norm": 0.1398806869983673,
"learning_rate": 4.3311852961222966e-05,
"loss": 0.2384,
"step": 720
},
{
"epoch": 0.7032007759456838,
"grad_norm": 0.13174192607402802,
"learning_rate": 4.315939773094709e-05,
"loss": 0.213,
"step": 725
},
{
"epoch": 0.7080504364694471,
"grad_norm": 0.12232716381549835,
"learning_rate": 4.300549930070387e-05,
"loss": 0.2283,
"step": 730
},
{
"epoch": 0.7129000969932104,
"grad_norm": 0.14730586111545563,
"learning_rate": 4.2850169901417084e-05,
"loss": 0.2098,
"step": 735
},
{
"epoch": 0.7177497575169738,
"grad_norm": 0.13813212513923645,
"learning_rate": 4.269342187773532e-05,
"loss": 0.2062,
"step": 740
},
{
"epoch": 0.7225994180407371,
"grad_norm": 0.13183937966823578,
"learning_rate": 4.253526768705097e-05,
"loss": 0.2034,
"step": 745
},
{
"epoch": 0.7274490785645005,
"grad_norm": 0.14278775453567505,
"learning_rate": 4.237571989851011e-05,
"loss": 0.2227,
"step": 750
},
{
"epoch": 0.7274490785645005,
"eval_loss": 0.21041834354400635,
"eval_runtime": 48.0966,
"eval_samples_per_second": 14.013,
"eval_steps_per_second": 0.894,
"step": 750
},
{
"epoch": 0.7322987390882638,
"grad_norm": 0.16159804165363312,
"learning_rate": 4.221479119201362e-05,
"loss": 0.2191,
"step": 755
},
{
"epoch": 0.7371483996120272,
"grad_norm": 0.13423971831798553,
"learning_rate": 4.205249435720943e-05,
"loss": 0.1993,
"step": 760
},
{
"epoch": 0.7419980601357905,
"grad_norm": 0.14568765461444855,
"learning_rate": 4.1888842292476126e-05,
"loss": 0.2023,
"step": 765
},
{
"epoch": 0.7468477206595538,
"grad_norm": 0.13105235993862152,
"learning_rate": 4.172384800389784e-05,
"loss": 0.2048,
"step": 770
},
{
"epoch": 0.7516973811833172,
"grad_norm": 0.14081120491027832,
"learning_rate": 4.155752460423059e-05,
"loss": 0.2078,
"step": 775
},
{
"epoch": 0.7565470417070805,
"grad_norm": 0.13213010132312775,
"learning_rate": 4.138988531186016e-05,
"loss": 0.2183,
"step": 780
},
{
"epoch": 0.7613967022308439,
"grad_norm": 0.1357748806476593,
"learning_rate": 4.1220943449751606e-05,
"loss": 0.2016,
"step": 785
},
{
"epoch": 0.7662463627546072,
"grad_norm": 0.13532240688800812,
"learning_rate": 4.105071244439039e-05,
"loss": 0.2113,
"step": 790
},
{
"epoch": 0.7710960232783706,
"grad_norm": 0.14828477799892426,
"learning_rate": 4.0879205824715384e-05,
"loss": 0.2159,
"step": 795
},
{
"epoch": 0.7759456838021338,
"grad_norm": 0.1488686501979828,
"learning_rate": 4.070643722104358e-05,
"loss": 0.2124,
"step": 800
},
{
"epoch": 0.7807953443258971,
"grad_norm": 0.1575794368982315,
"learning_rate": 4.053242036398692e-05,
"loss": 0.2065,
"step": 805
},
{
"epoch": 0.7856450048496605,
"grad_norm": 0.13456198573112488,
"learning_rate": 4.035716908336102e-05,
"loss": 0.201,
"step": 810
},
{
"epoch": 0.7904946653734238,
"grad_norm": 0.13958740234375,
"learning_rate": 4.01806973070861e-05,
"loss": 0.2093,
"step": 815
},
{
"epoch": 0.7953443258971872,
"grad_norm": 0.14714553952217102,
"learning_rate": 4.000301906008001e-05,
"loss": 0.2082,
"step": 820
},
{
"epoch": 0.8001939864209505,
"grad_norm": 0.1589927226305008,
"learning_rate": 3.9824148463143685e-05,
"loss": 0.2279,
"step": 825
},
{
"epoch": 0.8050436469447139,
"grad_norm": 0.15132376551628113,
"learning_rate": 3.964409973183886e-05,
"loss": 0.204,
"step": 830
},
{
"epoch": 0.8098933074684772,
"grad_norm": 0.156170055270195,
"learning_rate": 3.946288717535833e-05,
"loss": 0.2051,
"step": 835
},
{
"epoch": 0.8147429679922406,
"grad_norm": 0.12180455029010773,
"learning_rate": 3.928052519538874e-05,
"loss": 0.2064,
"step": 840
},
{
"epoch": 0.8195926285160039,
"grad_norm": 0.1337326467037201,
"learning_rate": 3.9097028284966e-05,
"loss": 0.2025,
"step": 845
},
{
"epoch": 0.8244422890397672,
"grad_norm": 0.13768617808818817,
"learning_rate": 3.891241102732348e-05,
"loss": 0.2037,
"step": 850
},
{
"epoch": 0.8292919495635306,
"grad_norm": 0.15049096941947937,
"learning_rate": 3.872668809473304e-05,
"loss": 0.2028,
"step": 855
},
{
"epoch": 0.8341416100872939,
"grad_norm": 0.14802470803260803,
"learning_rate": 3.8539874247338956e-05,
"loss": 0.2137,
"step": 860
},
{
"epoch": 0.8389912706110573,
"grad_norm": 0.13950683176517487,
"learning_rate": 3.835198433198484e-05,
"loss": 0.2375,
"step": 865
},
{
"epoch": 0.8438409311348206,
"grad_norm": 0.13893653452396393,
"learning_rate": 3.816303328103374e-05,
"loss": 0.204,
"step": 870
},
{
"epoch": 0.8486905916585838,
"grad_norm": 0.1808776557445526,
"learning_rate": 3.7973036111181405e-05,
"loss": 0.2043,
"step": 875
},
{
"epoch": 0.8535402521823472,
"grad_norm": 0.1470966786146164,
"learning_rate": 3.7782007922262827e-05,
"loss": 0.2117,
"step": 880
},
{
"epoch": 0.8583899127061105,
"grad_norm": 0.15209127962589264,
"learning_rate": 3.758996389605222e-05,
"loss": 0.2187,
"step": 885
},
{
"epoch": 0.8632395732298739,
"grad_norm": 0.1539296954870224,
"learning_rate": 3.739691929505641e-05,
"loss": 0.2062,
"step": 890
},
{
"epoch": 0.8680892337536372,
"grad_norm": 0.13484741747379303,
"learning_rate": 3.720288946130197e-05,
"loss": 0.1985,
"step": 895
},
{
"epoch": 0.8729388942774006,
"grad_norm": 0.15806835889816284,
"learning_rate": 3.7007889815115796e-05,
"loss": 0.2144,
"step": 900
},
{
"epoch": 0.8777885548011639,
"grad_norm": 0.16019117832183838,
"learning_rate": 3.681193585389969e-05,
"loss": 0.1912,
"step": 905
},
{
"epoch": 0.8826382153249273,
"grad_norm": 0.1545192003250122,
"learning_rate": 3.6615043150898674e-05,
"loss": 0.2093,
"step": 910
},
{
"epoch": 0.8874878758486906,
"grad_norm": 0.1420498490333557,
"learning_rate": 3.641722735396336e-05,
"loss": 0.205,
"step": 915
},
{
"epoch": 0.8923375363724539,
"grad_norm": 0.15403462946414948,
"learning_rate": 3.6218504184306295e-05,
"loss": 0.1907,
"step": 920
},
{
"epoch": 0.8971871968962173,
"grad_norm": 0.1699294149875641,
"learning_rate": 3.6018889435252574e-05,
"loss": 0.2399,
"step": 925
},
{
"epoch": 0.9020368574199806,
"grad_norm": 0.1434181183576584,
"learning_rate": 3.581839897098468e-05,
"loss": 0.2033,
"step": 930
},
{
"epoch": 0.906886517943744,
"grad_norm": 0.14518964290618896,
"learning_rate": 3.561704872528169e-05,
"loss": 0.1908,
"step": 935
},
{
"epoch": 0.9117361784675073,
"grad_norm": 0.1436786949634552,
"learning_rate": 3.5414854700252945e-05,
"loss": 0.202,
"step": 940
},
{
"epoch": 0.9165858389912707,
"grad_norm": 0.1517830491065979,
"learning_rate": 3.521183296506628e-05,
"loss": 0.2088,
"step": 945
},
{
"epoch": 0.9214354995150339,
"grad_norm": 0.1423126757144928,
"learning_rate": 3.5007999654671004e-05,
"loss": 0.2026,
"step": 950
},
{
"epoch": 0.9262851600387972,
"grad_norm": 0.13826879858970642,
"learning_rate": 3.4803370968515535e-05,
"loss": 0.2048,
"step": 955
},
{
"epoch": 0.9311348205625606,
"grad_norm": 0.15552102029323578,
"learning_rate": 3.4597963169259994e-05,
"loss": 0.2074,
"step": 960
},
{
"epoch": 0.9359844810863239,
"grad_norm": 0.1478404849767685,
"learning_rate": 3.4391792581483724e-05,
"loss": 0.2,
"step": 965
},
{
"epoch": 0.9408341416100873,
"grad_norm": 0.15055781602859497,
"learning_rate": 3.4184875590387924e-05,
"loss": 0.2032,
"step": 970
},
{
"epoch": 0.9456838021338506,
"grad_norm": 0.14816974103450775,
"learning_rate": 3.397722864049347e-05,
"loss": 0.2095,
"step": 975
},
{
"epoch": 0.950533462657614,
"grad_norm": 0.15103183686733246,
"learning_rate": 3.376886823433395e-05,
"loss": 0.2133,
"step": 980
},
{
"epoch": 0.9553831231813773,
"grad_norm": 0.15531527996063232,
"learning_rate": 3.35598109311442e-05,
"loss": 0.2125,
"step": 985
},
{
"epoch": 0.9602327837051406,
"grad_norm": 0.13943400979042053,
"learning_rate": 3.335007334554423e-05,
"loss": 0.1981,
"step": 990
},
{
"epoch": 0.965082444228904,
"grad_norm": 0.14304272830486298,
"learning_rate": 3.3139672146218846e-05,
"loss": 0.2037,
"step": 995
},
{
"epoch": 0.9699321047526673,
"grad_norm": 0.16258351504802704,
"learning_rate": 3.2928624054592873e-05,
"loss": 0.1965,
"step": 1000
},
{
"epoch": 0.9699321047526673,
"eval_loss": 0.20380738377571106,
"eval_runtime": 48.08,
"eval_samples_per_second": 14.018,
"eval_steps_per_second": 0.894,
"step": 1000
},
{
"epoch": 0.9747817652764307,
"grad_norm": 0.14396609365940094,
"learning_rate": 3.2716945843502224e-05,
"loss": 0.2143,
"step": 1005
},
{
"epoch": 0.979631425800194,
"grad_norm": 0.1358533650636673,
"learning_rate": 3.2504654335860986e-05,
"loss": 0.2189,
"step": 1010
},
{
"epoch": 0.9844810863239574,
"grad_norm": 0.18899835646152496,
"learning_rate": 3.229176640332433e-05,
"loss": 0.2089,
"step": 1015
},
{
"epoch": 0.9893307468477207,
"grad_norm": 0.14681367576122284,
"learning_rate": 3.2078298964947715e-05,
"loss": 0.1817,
"step": 1020
},
{
"epoch": 0.9941804073714839,
"grad_norm": 0.13952337205410004,
"learning_rate": 3.186426898584225e-05,
"loss": 0.2128,
"step": 1025
},
{
"epoch": 0.9990300678952473,
"grad_norm": 0.14799629151821136,
"learning_rate": 3.164969347582639e-05,
"loss": 0.2014,
"step": 1030
},
{
"epoch": 1.0038797284190106,
"grad_norm": 0.16220593452453613,
"learning_rate": 3.143458948807414e-05,
"loss": 0.22,
"step": 1035
},
{
"epoch": 1.008729388942774,
"grad_norm": 0.1490844190120697,
"learning_rate": 3.1218974117759714e-05,
"loss": 0.2157,
"step": 1040
},
{
"epoch": 1.0135790494665373,
"grad_norm": 0.1579083800315857,
"learning_rate": 3.100286450069897e-05,
"loss": 0.1989,
"step": 1045
},
{
"epoch": 1.0184287099903007,
"grad_norm": 0.16225625574588776,
"learning_rate": 3.0786277811987505e-05,
"loss": 0.1976,
"step": 1050
},
{
"epoch": 1.023278370514064,
"grad_norm": 0.14916008710861206,
"learning_rate": 3.0569231264635756e-05,
"loss": 0.2004,
"step": 1055
},
{
"epoch": 1.0281280310378274,
"grad_norm": 0.14502666890621185,
"learning_rate": 3.0351742108200888e-05,
"loss": 0.2043,
"step": 1060
},
{
"epoch": 1.0329776915615907,
"grad_norm": 0.13275770843029022,
"learning_rate": 3.0133827627416057e-05,
"loss": 0.1969,
"step": 1065
},
{
"epoch": 1.037827352085354,
"grad_norm": 0.14670969545841217,
"learning_rate": 2.9915505140816597e-05,
"loss": 0.2154,
"step": 1070
},
{
"epoch": 1.0426770126091174,
"grad_norm": 0.15070156753063202,
"learning_rate": 2.9696791999363727e-05,
"loss": 0.2084,
"step": 1075
},
{
"epoch": 1.0475266731328807,
"grad_norm": 0.14457589387893677,
"learning_rate": 2.9477705585065546e-05,
"loss": 0.216,
"step": 1080
},
{
"epoch": 1.052376333656644,
"grad_norm": 0.1555938869714737,
"learning_rate": 2.925826330959564e-05,
"loss": 0.2024,
"step": 1085
},
{
"epoch": 1.0572259941804074,
"grad_norm": 0.15301556885242462,
"learning_rate": 2.9038482612909335e-05,
"loss": 0.2119,
"step": 1090
},
{
"epoch": 1.0620756547041708,
"grad_norm": 0.14304795861244202,
"learning_rate": 2.8818380961857615e-05,
"loss": 0.1878,
"step": 1095
},
{
"epoch": 1.066925315227934,
"grad_norm": 0.1455308496952057,
"learning_rate": 2.8597975848798992e-05,
"loss": 0.2073,
"step": 1100
},
{
"epoch": 1.0717749757516974,
"grad_norm": 0.15965287387371063,
"learning_rate": 2.837728479020933e-05,
"loss": 0.2036,
"step": 1105
},
{
"epoch": 1.0766246362754608,
"grad_norm": 0.1591757833957672,
"learning_rate": 2.8156325325289717e-05,
"loss": 0.1807,
"step": 1110
},
{
"epoch": 1.0814742967992241,
"grad_norm": 0.14703893661499023,
"learning_rate": 2.7935115014572593e-05,
"loss": 0.2166,
"step": 1115
},
{
"epoch": 1.0863239573229875,
"grad_norm": 0.14766725897789001,
"learning_rate": 2.7713671438526073e-05,
"loss": 0.2137,
"step": 1120
},
{
"epoch": 1.0911736178467508,
"grad_norm": 0.16928435862064362,
"learning_rate": 2.7492012196156835e-05,
"loss": 0.2041,
"step": 1125
},
{
"epoch": 1.0960232783705142,
"grad_norm": 0.16884630918502808,
"learning_rate": 2.7270154903611393e-05,
"loss": 0.1964,
"step": 1130
},
{
"epoch": 1.1008729388942773,
"grad_norm": 0.15490330755710602,
"learning_rate": 2.7048117192776146e-05,
"loss": 0.2096,
"step": 1135
},
{
"epoch": 1.1057225994180406,
"grad_norm": 0.15356089174747467,
"learning_rate": 2.6825916709876013e-05,
"loss": 0.2006,
"step": 1140
},
{
"epoch": 1.110572259941804,
"grad_norm": 0.14378608763217926,
"learning_rate": 2.6603571114072066e-05,
"loss": 0.2045,
"step": 1145
},
{
"epoch": 1.1154219204655673,
"grad_norm": 0.1541430503129959,
"learning_rate": 2.638109807605811e-05,
"loss": 0.2145,
"step": 1150
},
{
"epoch": 1.1202715809893307,
"grad_norm": 0.14816121757030487,
"learning_rate": 2.6158515276656253e-05,
"loss": 0.197,
"step": 1155
},
{
"epoch": 1.125121241513094,
"grad_norm": 0.15891754627227783,
"learning_rate": 2.5935840405411804e-05,
"loss": 0.2186,
"step": 1160
},
{
"epoch": 1.1299709020368573,
"grad_norm": 0.16058792173862457,
"learning_rate": 2.571309115918738e-05,
"loss": 0.2147,
"step": 1165
},
{
"epoch": 1.1348205625606207,
"grad_norm": 0.14306621253490448,
"learning_rate": 2.549028524075649e-05,
"loss": 0.2056,
"step": 1170
},
{
"epoch": 1.139670223084384,
"grad_norm": 0.1553443819284439,
"learning_rate": 2.5267440357396588e-05,
"loss": 0.1925,
"step": 1175
},
{
"epoch": 1.1445198836081474,
"grad_norm": 0.15235552191734314,
"learning_rate": 2.5044574219481832e-05,
"loss": 0.2173,
"step": 1180
},
{
"epoch": 1.1493695441319107,
"grad_norm": 0.13989904522895813,
"learning_rate": 2.4821704539075577e-05,
"loss": 0.1786,
"step": 1185
},
{
"epoch": 1.154219204655674,
"grad_norm": 0.1479206681251526,
"learning_rate": 2.4598849028522713e-05,
"loss": 0.2044,
"step": 1190
},
{
"epoch": 1.1590688651794374,
"grad_norm": 0.17453940212726593,
"learning_rate": 2.4376025399041985e-05,
"loss": 0.2086,
"step": 1195
},
{
"epoch": 1.1639185257032008,
"grad_norm": 0.15538154542446136,
"learning_rate": 2.4153251359318404e-05,
"loss": 0.1891,
"step": 1200
},
{
"epoch": 1.168768186226964,
"grad_norm": 0.14030437171459198,
"learning_rate": 2.3930544614095944e-05,
"loss": 0.1813,
"step": 1205
},
{
"epoch": 1.1736178467507274,
"grad_norm": 0.15048657357692719,
"learning_rate": 2.370792286277035e-05,
"loss": 0.2068,
"step": 1210
},
{
"epoch": 1.1784675072744908,
"grad_norm": 0.14109192788600922,
"learning_rate": 2.3485403797982586e-05,
"loss": 0.1992,
"step": 1215
},
{
"epoch": 1.1833171677982541,
"grad_norm": 0.1549970656633377,
"learning_rate": 2.326300510421273e-05,
"loss": 0.2067,
"step": 1220
},
{
"epoch": 1.1881668283220175,
"grad_norm": 0.15575067698955536,
"learning_rate": 2.3040744456374462e-05,
"loss": 0.1806,
"step": 1225
},
{
"epoch": 1.1930164888457808,
"grad_norm": 0.14550498127937317,
"learning_rate": 2.2818639518410414e-05,
"loss": 0.2088,
"step": 1230
},
{
"epoch": 1.1978661493695442,
"grad_norm": 0.15763843059539795,
"learning_rate": 2.259670794188833e-05,
"loss": 0.2121,
"step": 1235
},
{
"epoch": 1.2027158098933075,
"grad_norm": 0.17174339294433594,
"learning_rate": 2.2374967364598222e-05,
"loss": 0.1971,
"step": 1240
},
{
"epoch": 1.2075654704170709,
"grad_norm": 0.13719911873340607,
"learning_rate": 2.2153435409150635e-05,
"loss": 0.1851,
"step": 1245
},
{
"epoch": 1.2124151309408342,
"grad_norm": 0.1528056263923645,
"learning_rate": 2.1932129681576105e-05,
"loss": 0.2001,
"step": 1250
},
{
"epoch": 1.2124151309408342,
"eval_loss": 0.20025967061519623,
"eval_runtime": 48.0897,
"eval_samples_per_second": 14.015,
"eval_steps_per_second": 0.894,
"step": 1250
},
{
"epoch": 1.2172647914645975,
"grad_norm": 0.16801750659942627,
"learning_rate": 2.1711067769925914e-05,
"loss": 0.2184,
"step": 1255
},
{
"epoch": 1.2221144519883609,
"grad_norm": 0.1539103388786316,
"learning_rate": 2.149026724287435e-05,
"loss": 0.2176,
"step": 1260
},
{
"epoch": 1.2269641125121242,
"grad_norm": 0.15657076239585876,
"learning_rate": 2.126974564832239e-05,
"loss": 0.1989,
"step": 1265
},
{
"epoch": 1.2318137730358876,
"grad_norm": 0.15106332302093506,
"learning_rate": 2.104952051200315e-05,
"loss": 0.2045,
"step": 1270
},
{
"epoch": 1.236663433559651,
"grad_norm": 0.14375294744968414,
"learning_rate": 2.082960933608903e-05,
"loss": 0.1917,
"step": 1275
},
{
"epoch": 1.2415130940834143,
"grad_norm": 0.14703327417373657,
"learning_rate": 2.061002959780069e-05,
"loss": 0.1977,
"step": 1280
},
{
"epoch": 1.2463627546071776,
"grad_norm": 0.1680404096841812,
"learning_rate": 2.03907987480182e-05,
"loss": 0.2127,
"step": 1285
},
{
"epoch": 1.251212415130941,
"grad_norm": 0.14668302237987518,
"learning_rate": 2.0171934209893994e-05,
"loss": 0.2012,
"step": 1290
},
{
"epoch": 1.2560620756547043,
"grad_norm": 0.14603851735591888,
"learning_rate": 1.9953453377468282e-05,
"loss": 0.1996,
"step": 1295
},
{
"epoch": 1.2609117361784676,
"grad_norm": 0.1648787260055542,
"learning_rate": 1.973537361428665e-05,
"loss": 0.2164,
"step": 1300
},
{
"epoch": 1.265761396702231,
"grad_norm": 0.16897331178188324,
"learning_rate": 1.95177122520201e-05,
"loss": 0.1999,
"step": 1305
},
{
"epoch": 1.270611057225994,
"grad_norm": 0.16626134514808655,
"learning_rate": 1.9300486589087645e-05,
"loss": 0.1934,
"step": 1310
},
{
"epoch": 1.2754607177497574,
"grad_norm": 0.15668809413909912,
"learning_rate": 1.908371388928152e-05,
"loss": 0.2078,
"step": 1315
},
{
"epoch": 1.2803103782735208,
"grad_norm": 0.14479213953018188,
"learning_rate": 1.8867411380395177e-05,
"loss": 0.198,
"step": 1320
},
{
"epoch": 1.2851600387972841,
"grad_norm": 0.1500495970249176,
"learning_rate": 1.865159625285412e-05,
"loss": 0.2103,
"step": 1325
},
{
"epoch": 1.2900096993210475,
"grad_norm": 0.1683105230331421,
"learning_rate": 1.8436285658349694e-05,
"loss": 0.2045,
"step": 1330
},
{
"epoch": 1.2948593598448108,
"grad_norm": 0.16197173297405243,
"learning_rate": 1.822149670847599e-05,
"loss": 0.189,
"step": 1335
},
{
"epoch": 1.2997090203685742,
"grad_norm": 0.1493465155363083,
"learning_rate": 1.800724647336992e-05,
"loss": 0.1998,
"step": 1340
},
{
"epoch": 1.3045586808923375,
"grad_norm": 0.15609502792358398,
"learning_rate": 1.779355198035458e-05,
"loss": 0.1944,
"step": 1345
},
{
"epoch": 1.3094083414161009,
"grad_norm": 0.16641376912593842,
"learning_rate": 1.758043021258601e-05,
"loss": 0.2032,
"step": 1350
},
{
"epoch": 1.3142580019398642,
"grad_norm": 0.16449637711048126,
"learning_rate": 1.7367898107703497e-05,
"loss": 0.2099,
"step": 1355
},
{
"epoch": 1.3191076624636275,
"grad_norm": 0.14618897438049316,
"learning_rate": 1.7155972556483424e-05,
"loss": 0.1924,
"step": 1360
},
{
"epoch": 1.3239573229873909,
"grad_norm": 0.1407703310251236,
"learning_rate": 1.6944670401496997e-05,
"loss": 0.1909,
"step": 1365
},
{
"epoch": 1.3288069835111542,
"grad_norm": 0.17186439037322998,
"learning_rate": 1.673400843577156e-05,
"loss": 0.2035,
"step": 1370
},
{
"epoch": 1.3336566440349176,
"grad_norm": 0.14018838107585907,
"learning_rate": 1.652400340145609e-05,
"loss": 0.1949,
"step": 1375
},
{
"epoch": 1.338506304558681,
"grad_norm": 0.14712657034397125,
"learning_rate": 1.6314671988490603e-05,
"loss": 0.1878,
"step": 1380
},
{
"epoch": 1.3433559650824443,
"grad_norm": 0.15526027977466583,
"learning_rate": 1.610603083327971e-05,
"loss": 0.1971,
"step": 1385
},
{
"epoch": 1.3482056256062076,
"grad_norm": 0.14195865392684937,
"learning_rate": 1.5898096517370498e-05,
"loss": 0.196,
"step": 1390
},
{
"epoch": 1.353055286129971,
"grad_norm": 0.16893810033798218,
"learning_rate": 1.5690885566134696e-05,
"loss": 0.1897,
"step": 1395
},
{
"epoch": 1.3579049466537343,
"grad_norm": 0.16904611885547638,
"learning_rate": 1.5484414447455348e-05,
"loss": 0.1959,
"step": 1400
},
{
"epoch": 1.3627546071774976,
"grad_norm": 0.16385570168495178,
"learning_rate": 1.5278699570418056e-05,
"loss": 0.1971,
"step": 1405
},
{
"epoch": 1.367604267701261,
"grad_norm": 0.16677437722682953,
"learning_rate": 1.5073757284006868e-05,
"loss": 0.1823,
"step": 1410
},
{
"epoch": 1.3724539282250243,
"grad_norm": 0.1567675769329071,
"learning_rate": 1.4869603875804955e-05,
"loss": 0.1941,
"step": 1415
},
{
"epoch": 1.3773035887487877,
"grad_norm": 0.1708156019449234,
"learning_rate": 1.4666255570700202e-05,
"loss": 0.1997,
"step": 1420
},
{
"epoch": 1.3821532492725508,
"grad_norm": 0.14904044568538666,
"learning_rate": 1.4463728529595719e-05,
"loss": 0.1885,
"step": 1425
},
{
"epoch": 1.3870029097963141,
"grad_norm": 0.15045498311519623,
"learning_rate": 1.4262038848125475e-05,
"loss": 0.2168,
"step": 1430
},
{
"epoch": 1.3918525703200775,
"grad_norm": 0.1507643461227417,
"learning_rate": 1.4061202555375142e-05,
"loss": 0.1959,
"step": 1435
},
{
"epoch": 1.3967022308438408,
"grad_norm": 0.15534117817878723,
"learning_rate": 1.3861235612608142e-05,
"loss": 0.1976,
"step": 1440
},
{
"epoch": 1.4015518913676042,
"grad_norm": 0.14476318657398224,
"learning_rate": 1.366215391199721e-05,
"loss": 0.1878,
"step": 1445
},
{
"epoch": 1.4064015518913675,
"grad_norm": 0.144943967461586,
"learning_rate": 1.346397327536134e-05,
"loss": 0.1977,
"step": 1450
},
{
"epoch": 1.4112512124151309,
"grad_norm": 0.1705586314201355,
"learning_rate": 1.3266709452908348e-05,
"loss": 0.2113,
"step": 1455
},
{
"epoch": 1.4161008729388942,
"grad_norm": 0.14363010227680206,
"learning_rate": 1.3070378121983174e-05,
"loss": 0.1902,
"step": 1460
},
{
"epoch": 1.4209505334626575,
"grad_norm": 0.17444470524787903,
"learning_rate": 1.2874994885821933e-05,
"loss": 0.1994,
"step": 1465
},
{
"epoch": 1.4258001939864209,
"grad_norm": 0.15788498520851135,
"learning_rate": 1.268057527231186e-05,
"loss": 0.1999,
"step": 1470
},
{
"epoch": 1.4306498545101842,
"grad_norm": 0.1490585207939148,
"learning_rate": 1.2487134732757219e-05,
"loss": 0.1904,
"step": 1475
},
{
"epoch": 1.4354995150339476,
"grad_norm": 0.1542252153158188,
"learning_rate": 1.2294688640651355e-05,
"loss": 0.2078,
"step": 1480
},
{
"epoch": 1.440349175557711,
"grad_norm": 0.1651746928691864,
"learning_rate": 1.2103252290454942e-05,
"loss": 0.1843,
"step": 1485
},
{
"epoch": 1.4451988360814743,
"grad_norm": 0.15188032388687134,
"learning_rate": 1.191284089638037e-05,
"loss": 0.2107,
"step": 1490
},
{
"epoch": 1.4500484966052376,
"grad_norm": 0.15589340031147003,
"learning_rate": 1.1723469591182675e-05,
"loss": 0.1961,
"step": 1495
},
{
"epoch": 1.454898157129001,
"grad_norm": 0.1623036116361618,
"learning_rate": 1.1535153424956922e-05,
"loss": 0.2087,
"step": 1500
},
{
"epoch": 1.454898157129001,
"eval_loss": 0.197998046875,
"eval_runtime": 48.0919,
"eval_samples_per_second": 14.015,
"eval_steps_per_second": 0.894,
"step": 1500
},
{
"epoch": 1.4597478176527643,
"grad_norm": 0.1391475796699524,
"learning_rate": 1.134790736394199e-05,
"loss": 0.1829,
"step": 1505
},
{
"epoch": 1.4645974781765276,
"grad_norm": 0.15713264048099518,
"learning_rate": 1.116174628933127e-05,
"loss": 0.1862,
"step": 1510
},
{
"epoch": 1.469447138700291,
"grad_norm": 0.14922243356704712,
"learning_rate": 1.0976684996089911e-05,
"loss": 0.2022,
"step": 1515
},
{
"epoch": 1.4742967992240543,
"grad_norm": 0.15391802787780762,
"learning_rate": 1.0792738191779055e-05,
"loss": 0.199,
"step": 1520
},
{
"epoch": 1.4791464597478177,
"grad_norm": 0.16635461151599884,
"learning_rate": 1.0609920495386963e-05,
"loss": 0.183,
"step": 1525
},
{
"epoch": 1.483996120271581,
"grad_norm": 0.14732369780540466,
"learning_rate": 1.0428246436167136e-05,
"loss": 0.1946,
"step": 1530
},
{
"epoch": 1.4888457807953444,
"grad_norm": 0.15745453536510468,
"learning_rate": 1.0247730452483683e-05,
"loss": 0.1999,
"step": 1535
},
{
"epoch": 1.4936954413191077,
"grad_norm": 0.1535121500492096,
"learning_rate": 1.0068386890663828e-05,
"loss": 0.2131,
"step": 1540
},
{
"epoch": 1.498545101842871,
"grad_norm": 0.16908058524131775,
"learning_rate": 9.890230003857704e-06,
"loss": 0.1893,
"step": 1545
},
{
"epoch": 1.5033947623666344,
"grad_norm": 0.16990558803081512,
"learning_rate": 9.71327395090566e-06,
"loss": 0.2033,
"step": 1550
},
{
"epoch": 1.5082444228903977,
"grad_norm": 0.1563047617673874,
"learning_rate": 9.537532795212988e-06,
"loss": 0.1975,
"step": 1555
},
{
"epoch": 1.513094083414161,
"grad_norm": 0.16167347133159637,
"learning_rate": 9.363020503632197e-06,
"loss": 0.1923,
"step": 1560
},
{
"epoch": 1.5179437439379244,
"grad_norm": 0.1589316427707672,
"learning_rate": 9.189750945353082e-06,
"loss": 0.2131,
"step": 1565
},
{
"epoch": 1.5227934044616878,
"grad_norm": 0.15486431121826172,
"learning_rate": 9.01773789080045e-06,
"loss": 0.1961,
"step": 1570
},
{
"epoch": 1.527643064985451,
"grad_norm": 0.17133159935474396,
"learning_rate": 8.846995010539707e-06,
"loss": 0.179,
"step": 1575
},
{
"epoch": 1.5324927255092144,
"grad_norm": 0.1626712530851364,
"learning_rate": 8.67753587419046e-06,
"loss": 0.1977,
"step": 1580
},
{
"epoch": 1.5373423860329778,
"grad_norm": 0.15872539579868317,
"learning_rate": 8.509373949348012e-06,
"loss": 0.1981,
"step": 1585
},
{
"epoch": 1.5421920465567411,
"grad_norm": 0.15292125940322876,
"learning_rate": 8.34252260051314e-06,
"loss": 0.1971,
"step": 1590
},
{
"epoch": 1.5470417070805045,
"grad_norm": 0.15812063217163086,
"learning_rate": 8.176995088029852e-06,
"loss": 0.1964,
"step": 1595
},
{
"epoch": 1.5518913676042678,
"grad_norm": 0.15867389738559723,
"learning_rate": 8.01280456703159e-06,
"loss": 0.1971,
"step": 1600
},
{
"epoch": 1.5567410281280312,
"grad_norm": 0.1688418984413147,
"learning_rate": 7.84996408639576e-06,
"loss": 0.2117,
"step": 1605
},
{
"epoch": 1.5615906886517945,
"grad_norm": 0.16065895557403564,
"learning_rate": 7.688486587706661e-06,
"loss": 0.199,
"step": 1610
},
{
"epoch": 1.5664403491755579,
"grad_norm": 0.15269528329372406,
"learning_rate": 7.528384904226932e-06,
"loss": 0.1894,
"step": 1615
},
{
"epoch": 1.5712900096993212,
"grad_norm": 0.16433826088905334,
"learning_rate": 7.369671759877705e-06,
"loss": 0.2061,
"step": 1620
},
{
"epoch": 1.5761396702230845,
"grad_norm": 0.15707933902740479,
"learning_rate": 7.212359768227345e-06,
"loss": 0.201,
"step": 1625
},
{
"epoch": 1.5809893307468477,
"grad_norm": 0.15439623594284058,
"learning_rate": 7.056461431489015e-06,
"loss": 0.1866,
"step": 1630
},
{
"epoch": 1.585838991270611,
"grad_norm": 0.1509786695241928,
"learning_rate": 6.901989139527048e-06,
"loss": 0.1877,
"step": 1635
},
{
"epoch": 1.5906886517943744,
"grad_norm": 0.16154807806015015,
"learning_rate": 6.748955168872312e-06,
"loss": 0.1974,
"step": 1640
},
{
"epoch": 1.5955383123181377,
"grad_norm": 0.17238792777061462,
"learning_rate": 6.5973716817465365e-06,
"loss": 0.2212,
"step": 1645
},
{
"epoch": 1.600387972841901,
"grad_norm": 0.1707492172718048,
"learning_rate": 6.4472507250956994e-06,
"loss": 0.1852,
"step": 1650
},
{
"epoch": 1.6052376333656644,
"grad_norm": 0.16531886160373688,
"learning_rate": 6.2986042296326296e-06,
"loss": 0.1953,
"step": 1655
},
{
"epoch": 1.6100872938894277,
"grad_norm": 0.154957577586174,
"learning_rate": 6.1514440088888735e-06,
"loss": 0.2059,
"step": 1660
},
{
"epoch": 1.614936954413191,
"grad_norm": 0.16685739159584045,
"learning_rate": 6.005781758275731e-06,
"loss": 0.2111,
"step": 1665
},
{
"epoch": 1.6197866149369544,
"grad_norm": 0.16281373798847198,
"learning_rate": 5.861629054154852e-06,
"loss": 0.2048,
"step": 1670
},
{
"epoch": 1.6246362754607178,
"grad_norm": 0.16481256484985352,
"learning_rate": 5.7189973529181705e-06,
"loss": 0.2057,
"step": 1675
},
{
"epoch": 1.629485935984481,
"grad_norm": 0.15931367874145508,
"learning_rate": 5.577897990077458e-06,
"loss": 0.209,
"step": 1680
},
{
"epoch": 1.6343355965082444,
"grad_norm": 0.14951331913471222,
"learning_rate": 5.438342179363418e-06,
"loss": 0.2012,
"step": 1685
},
{
"epoch": 1.6391852570320078,
"grad_norm": 0.1307000368833542,
"learning_rate": 5.300341011834475e-06,
"loss": 0.1821,
"step": 1690
},
{
"epoch": 1.6440349175557711,
"grad_norm": 0.16035383939743042,
"learning_rate": 5.163905454995372e-06,
"loss": 0.1899,
"step": 1695
},
{
"epoch": 1.6488845780795345,
"grad_norm": 0.15784330666065216,
"learning_rate": 5.0290463519254925e-06,
"loss": 0.1949,
"step": 1700
},
{
"epoch": 1.6537342386032978,
"grad_norm": 0.1625281125307083,
"learning_rate": 4.895774420417124e-06,
"loss": 0.2106,
"step": 1705
},
{
"epoch": 1.658583899127061,
"grad_norm": 0.15070758759975433,
"learning_rate": 4.764100252123702e-06,
"loss": 0.1786,
"step": 1710
},
{
"epoch": 1.6634335596508243,
"grad_norm": 0.13678708672523499,
"learning_rate": 4.634034311718022e-06,
"loss": 0.1944,
"step": 1715
},
{
"epoch": 1.6682832201745876,
"grad_norm": 0.16914202272891998,
"learning_rate": 4.505586936060566e-06,
"loss": 0.2035,
"step": 1720
},
{
"epoch": 1.673132880698351,
"grad_norm": 0.15594607591629028,
"learning_rate": 4.378768333378017e-06,
"loss": 0.1883,
"step": 1725
},
{
"epoch": 1.6779825412221143,
"grad_norm": 0.15200097858905792,
"learning_rate": 4.253588582451954e-06,
"loss": 0.1786,
"step": 1730
},
{
"epoch": 1.6828322017458777,
"grad_norm": 0.1636827439069748,
"learning_rate": 4.130057631817838e-06,
"loss": 0.191,
"step": 1735
},
{
"epoch": 1.687681862269641,
"grad_norm": 0.14671088755130768,
"learning_rate": 4.008185298974393e-06,
"loss": 0.1992,
"step": 1740
},
{
"epoch": 1.6925315227934044,
"grad_norm": 0.1701505482196808,
"learning_rate": 3.887981269603333e-06,
"loss": 0.1913,
"step": 1745
},
{
"epoch": 1.6973811833171677,
"grad_norm": 0.15805399417877197,
"learning_rate": 3.7694550967996565e-06,
"loss": 0.1932,
"step": 1750
},
{
"epoch": 1.6973811833171677,
"eval_loss": 0.19688038527965546,
"eval_runtime": 48.0858,
"eval_samples_per_second": 14.017,
"eval_steps_per_second": 0.894,
"step": 1750
},
{
"epoch": 1.702230843840931,
"grad_norm": 0.15937374532222748,
"learning_rate": 3.6526162003123615e-06,
"loss": 0.1776,
"step": 1755
},
{
"epoch": 1.7070805043646944,
"grad_norm": 0.15453214943408966,
"learning_rate": 3.5374738657958454e-06,
"loss": 0.2025,
"step": 1760
},
{
"epoch": 1.7119301648884577,
"grad_norm": 0.15527448058128357,
"learning_rate": 3.4240372440719594e-06,
"loss": 0.2062,
"step": 1765
},
{
"epoch": 1.716779825412221,
"grad_norm": 0.1499599665403366,
"learning_rate": 3.3123153504027367e-06,
"loss": 0.1999,
"step": 1770
},
{
"epoch": 1.7216294859359844,
"grad_norm": 0.1412288248538971,
"learning_rate": 3.202317063773891e-06,
"loss": 0.1763,
"step": 1775
},
{
"epoch": 1.7264791464597478,
"grad_norm": 0.16038767993450165,
"learning_rate": 3.0940511261892154e-06,
"loss": 0.1941,
"step": 1780
},
{
"epoch": 1.731328806983511,
"grad_norm": 0.15138490498065948,
"learning_rate": 2.987526141975783e-06,
"loss": 0.1969,
"step": 1785
},
{
"epoch": 1.7361784675072744,
"grad_norm": 0.15238988399505615,
"learning_rate": 2.882750577100149e-06,
"loss": 0.1865,
"step": 1790
},
{
"epoch": 1.7410281280310378,
"grad_norm": 0.16951079666614532,
"learning_rate": 2.7797327584955014e-06,
"loss": 0.1931,
"step": 1795
},
{
"epoch": 1.7458777885548011,
"grad_norm": 0.1534978598356247,
"learning_rate": 2.6784808733999163e-06,
"loss": 0.194,
"step": 1800
},
{
"epoch": 1.7507274490785645,
"grad_norm": 0.15956641733646393,
"learning_rate": 2.579002968705668e-06,
"loss": 0.1865,
"step": 1805
},
{
"epoch": 1.7555771096023278,
"grad_norm": 0.1396978348493576,
"learning_rate": 2.481306950319706e-06,
"loss": 0.1871,
"step": 1810
},
{
"epoch": 1.7604267701260912,
"grad_norm": 0.1500706672668457,
"learning_rate": 2.3854005825353467e-06,
"loss": 0.206,
"step": 1815
},
{
"epoch": 1.7652764306498545,
"grad_norm": 0.15206393599510193,
"learning_rate": 2.29129148741524e-06,
"loss": 0.204,
"step": 1820
},
{
"epoch": 1.7701260911736179,
"grad_norm": 0.15631067752838135,
"learning_rate": 2.198987144185552e-06,
"loss": 0.2022,
"step": 1825
},
{
"epoch": 1.7749757516973812,
"grad_norm": 0.16704493761062622,
"learning_rate": 2.1084948886416295e-06,
"loss": 0.2087,
"step": 1830
},
{
"epoch": 1.7798254122211445,
"grad_norm": 0.14626185595989227,
"learning_rate": 2.0198219125649396e-06,
"loss": 0.2053,
"step": 1835
},
{
"epoch": 1.7846750727449079,
"grad_norm": 0.1546330451965332,
"learning_rate": 1.9329752631515513e-06,
"loss": 0.1893,
"step": 1840
},
{
"epoch": 1.7895247332686712,
"grad_norm": 0.1591494381427765,
"learning_rate": 1.8479618424520422e-06,
"loss": 0.1943,
"step": 1845
},
{
"epoch": 1.7943743937924346,
"grad_norm": 0.1502322554588318,
"learning_rate": 1.7647884068229676e-06,
"loss": 0.1899,
"step": 1850
},
{
"epoch": 1.799224054316198,
"grad_norm": 0.1708429455757141,
"learning_rate": 1.6834615663899155e-06,
"loss": 0.214,
"step": 1855
},
{
"epoch": 1.8040737148399613,
"grad_norm": 0.15139105916023254,
"learning_rate": 1.6039877845221735e-06,
"loss": 0.1921,
"step": 1860
},
{
"epoch": 1.8089233753637246,
"grad_norm": 0.15141288936138153,
"learning_rate": 1.5263733773190347e-06,
"loss": 0.2192,
"step": 1865
},
{
"epoch": 1.813773035887488,
"grad_norm": 0.18391959369182587,
"learning_rate": 1.4506245131078733e-06,
"loss": 0.2072,
"step": 1870
},
{
"epoch": 1.8186226964112513,
"grad_norm": 0.15688742697238922,
"learning_rate": 1.376747211953891e-06,
"loss": 0.1824,
"step": 1875
},
{
"epoch": 1.8234723569350146,
"grad_norm": 0.15558670461177826,
"learning_rate": 1.304747345181681e-06,
"loss": 0.1975,
"step": 1880
},
{
"epoch": 1.828322017458778,
"grad_norm": 0.18685834109783173,
"learning_rate": 1.2346306349086262e-06,
"loss": 0.1957,
"step": 1885
},
{
"epoch": 1.8331716779825413,
"grad_norm": 0.16459019482135773,
"learning_rate": 1.1664026535901318e-06,
"loss": 0.2068,
"step": 1890
},
{
"epoch": 1.8380213385063047,
"grad_norm": 0.156924769282341,
"learning_rate": 1.1000688235767525e-06,
"loss": 0.2086,
"step": 1895
},
{
"epoch": 1.842870999030068,
"grad_norm": 0.16359376907348633,
"learning_rate": 1.0356344166832648e-06,
"loss": 0.2163,
"step": 1900
},
{
"epoch": 1.8477206595538314,
"grad_norm": 0.16292302310466766,
"learning_rate": 9.73104553769691e-07,
"loss": 0.2034,
"step": 1905
},
{
"epoch": 1.8525703200775947,
"grad_norm": 0.17051053047180176,
"learning_rate": 9.124842043343407e-07,
"loss": 0.2168,
"step": 1910
},
{
"epoch": 1.857419980601358,
"grad_norm": 0.17267897725105286,
"learning_rate": 8.537781861188282e-07,
"loss": 0.2234,
"step": 1915
},
{
"epoch": 1.8622696411251214,
"grad_norm": 0.16032524406909943,
"learning_rate": 7.969911647252193e-07,
"loss": 0.1986,
"step": 1920
},
{
"epoch": 1.8671193016488847,
"grad_norm": 0.1543329358100891,
"learning_rate": 7.421276532452337e-07,
"loss": 0.173,
"step": 1925
},
{
"epoch": 1.871968962172648,
"grad_norm": 0.15669037401676178,
"learning_rate": 6.891920119015571e-07,
"loss": 0.1987,
"step": 1930
},
{
"epoch": 1.8768186226964112,
"grad_norm": 0.1615551859140396,
"learning_rate": 6.381884477013239e-07,
"loss": 0.1831,
"step": 1935
},
{
"epoch": 1.8816682832201745,
"grad_norm": 0.1686321347951889,
"learning_rate": 5.891210141017733e-07,
"loss": 0.2029,
"step": 1940
},
{
"epoch": 1.8865179437439379,
"grad_norm": 0.15177270770072937,
"learning_rate": 5.419936106881018e-07,
"loss": 0.2034,
"step": 1945
},
{
"epoch": 1.8913676042677012,
"grad_norm": 0.155603289604187,
"learning_rate": 4.968099828635525e-07,
"loss": 0.1962,
"step": 1950
},
{
"epoch": 1.8962172647914646,
"grad_norm": 0.14843294024467468,
"learning_rate": 4.535737215517366e-07,
"loss": 0.1949,
"step": 1955
},
{
"epoch": 1.901066925315228,
"grad_norm": 0.15314973890781403,
"learning_rate": 4.122882629112701e-07,
"loss": 0.2104,
"step": 1960
},
{
"epoch": 1.9059165858389913,
"grad_norm": 0.1589522510766983,
"learning_rate": 3.729568880626755e-07,
"loss": 0.193,
"step": 1965
},
{
"epoch": 1.9107662463627546,
"grad_norm": 0.14796093106269836,
"learning_rate": 3.355827228276182e-07,
"loss": 0.1712,
"step": 1970
},
{
"epoch": 1.915615906886518,
"grad_norm": 0.1589411497116089,
"learning_rate": 3.00168737480494e-07,
"loss": 0.1878,
"step": 1975
},
{
"epoch": 1.9204655674102813,
"grad_norm": 0.14060987532138824,
"learning_rate": 2.6671774651235437e-07,
"loss": 0.1762,
"step": 1980
},
{
"epoch": 1.9253152279340446,
"grad_norm": 0.15994738042354584,
"learning_rate": 2.3523240840724325e-07,
"loss": 0.1924,
"step": 1985
},
{
"epoch": 1.930164888457808,
"grad_norm": 0.15940771996974945,
"learning_rate": 2.0571522543090526e-07,
"loss": 0.2053,
"step": 1990
},
{
"epoch": 1.9350145489815713,
"grad_norm": 0.14268319308757782,
"learning_rate": 1.7816854343193357e-07,
"loss": 0.1847,
"step": 1995
},
{
"epoch": 1.9398642095053347,
"grad_norm": 0.15468433499336243,
"learning_rate": 1.5259455165531068e-07,
"loss": 0.2044,
"step": 2000
},
{
"epoch": 1.9398642095053347,
"eval_loss": 0.19655267894268036,
"eval_runtime": 48.0808,
"eval_samples_per_second": 14.018,
"eval_steps_per_second": 0.894,
"step": 2000
},
{
"epoch": 1.944713870029098,
"grad_norm": 0.1507444828748703,
"learning_rate": 1.2899528256845873e-07,
"loss": 0.1824,
"step": 2005
},
{
"epoch": 1.9495635305528611,
"grad_norm": 0.14235784113407135,
"learning_rate": 1.073726116996715e-07,
"loss": 0.1954,
"step": 2010
},
{
"epoch": 1.9544131910766245,
"grad_norm": 0.14553847908973694,
"learning_rate": 8.77282574890892e-08,
"loss": 0.2163,
"step": 2015
},
{
"epoch": 1.9592628516003878,
"grad_norm": 0.16772744059562683,
"learning_rate": 7.006378115210766e-08,
"loss": 0.1822,
"step": 2020
},
{
"epoch": 1.9641125121241512,
"grad_norm": 0.15165811777114868,
"learning_rate": 5.43805865553082e-08,
"loss": 0.1862,
"step": 2025
},
{
"epoch": 1.9689621726479145,
"grad_norm": 0.1540442407131195,
"learning_rate": 4.067992010489685e-08,
"loss": 0.2106,
"step": 2030
},
{
"epoch": 1.9738118331716779,
"grad_norm": 0.14102330803871155,
"learning_rate": 2.8962870647630814e-08,
"loss": 0.1879,
"step": 2035
},
{
"epoch": 1.9786614936954412,
"grad_norm": 0.14310438930988312,
"learning_rate": 1.9230369384293233e-08,
"loss": 0.1789,
"step": 2040
},
{
"epoch": 1.9835111542192045,
"grad_norm": 0.1545654982328415,
"learning_rate": 1.148318979568297e-08,
"loss": 0.193,
"step": 2045
},
{
"epoch": 1.9883608147429679,
"grad_norm": 0.15825237333774567,
"learning_rate": 5.7219475811526316e-09,
"loss": 0.1901,
"step": 2050
},
{
"epoch": 1.9932104752667312,
"grad_norm": 0.1504404991865158,
"learning_rate": 1.947100609661634e-09,
"loss": 0.2034,
"step": 2055
},
{
"epoch": 1.9980601357904946,
"grad_norm": 0.14141124486923218,
"learning_rate": 1.5894888339418324e-10,
"loss": 0.1773,
"step": 2060
},
{
"epoch": 2.0,
"step": 2062,
"total_flos": 2.6820605084455404e+18,
"train_loss": 0.2813772309560665,
"train_runtime": 15083.292,
"train_samples_per_second": 4.374,
"train_steps_per_second": 0.137
}
],
"logging_steps": 5,
"max_steps": 2062,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 250,
"total_flos": 2.6820605084455404e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}