chansung's picture
Model save
2206256 verified
raw
history blame
35.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 1025,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004878048780487805,
"grad_norm": 616.0,
"learning_rate": 1.941747572815534e-06,
"loss": 39.9034,
"step": 1
},
{
"epoch": 0.024390243902439025,
"grad_norm": 466.0,
"learning_rate": 9.70873786407767e-06,
"loss": 34.9341,
"step": 5
},
{
"epoch": 0.04878048780487805,
"grad_norm": 251.0,
"learning_rate": 1.941747572815534e-05,
"loss": 29.4015,
"step": 10
},
{
"epoch": 0.07317073170731707,
"grad_norm": 56.25,
"learning_rate": 2.912621359223301e-05,
"loss": 17.9289,
"step": 15
},
{
"epoch": 0.0975609756097561,
"grad_norm": 39.75,
"learning_rate": 3.883495145631068e-05,
"loss": 14.9717,
"step": 20
},
{
"epoch": 0.12195121951219512,
"grad_norm": 15.75,
"learning_rate": 4.854368932038835e-05,
"loss": 12.4657,
"step": 25
},
{
"epoch": 0.14634146341463414,
"grad_norm": 5.15625,
"learning_rate": 5.825242718446602e-05,
"loss": 10.6748,
"step": 30
},
{
"epoch": 0.17073170731707318,
"grad_norm": 3.890625,
"learning_rate": 6.79611650485437e-05,
"loss": 9.811,
"step": 35
},
{
"epoch": 0.1951219512195122,
"grad_norm": 6.75,
"learning_rate": 7.766990291262136e-05,
"loss": 9.6309,
"step": 40
},
{
"epoch": 0.21951219512195122,
"grad_norm": 15.3125,
"learning_rate": 8.737864077669902e-05,
"loss": 8.5315,
"step": 45
},
{
"epoch": 0.24390243902439024,
"grad_norm": 31.75,
"learning_rate": 9.70873786407767e-05,
"loss": 6.2519,
"step": 50
},
{
"epoch": 0.2682926829268293,
"grad_norm": 5.25,
"learning_rate": 0.00010679611650485437,
"loss": 2.2665,
"step": 55
},
{
"epoch": 0.2926829268292683,
"grad_norm": 2.40625,
"learning_rate": 0.00011650485436893204,
"loss": 1.5008,
"step": 60
},
{
"epoch": 0.3170731707317073,
"grad_norm": 1.2578125,
"learning_rate": 0.00012621359223300972,
"loss": 1.3289,
"step": 65
},
{
"epoch": 0.34146341463414637,
"grad_norm": 2.796875,
"learning_rate": 0.0001359223300970874,
"loss": 1.2198,
"step": 70
},
{
"epoch": 0.36585365853658536,
"grad_norm": 1.4375,
"learning_rate": 0.00014563106796116506,
"loss": 1.1493,
"step": 75
},
{
"epoch": 0.3902439024390244,
"grad_norm": 8.1875,
"learning_rate": 0.0001553398058252427,
"loss": 1.0862,
"step": 80
},
{
"epoch": 0.4146341463414634,
"grad_norm": 3.0625,
"learning_rate": 0.0001650485436893204,
"loss": 1.0768,
"step": 85
},
{
"epoch": 0.43902439024390244,
"grad_norm": 1.2109375,
"learning_rate": 0.00017475728155339805,
"loss": 1.0468,
"step": 90
},
{
"epoch": 0.4634146341463415,
"grad_norm": 4.21875,
"learning_rate": 0.00018446601941747576,
"loss": 0.9991,
"step": 95
},
{
"epoch": 0.4878048780487805,
"grad_norm": 2.0625,
"learning_rate": 0.0001941747572815534,
"loss": 0.9596,
"step": 100
},
{
"epoch": 0.5121951219512195,
"grad_norm": 1.5078125,
"learning_rate": 0.00019999767797859854,
"loss": 0.9712,
"step": 105
},
{
"epoch": 0.5365853658536586,
"grad_norm": 0.890625,
"learning_rate": 0.0001999715564762413,
"loss": 0.9139,
"step": 110
},
{
"epoch": 0.5609756097560976,
"grad_norm": 1.1875,
"learning_rate": 0.00019991641855173097,
"loss": 0.9175,
"step": 115
},
{
"epoch": 0.5853658536585366,
"grad_norm": 1.25,
"learning_rate": 0.00019983228020867242,
"loss": 0.8959,
"step": 120
},
{
"epoch": 0.6097560975609756,
"grad_norm": 1.3203125,
"learning_rate": 0.00019971916586794867,
"loss": 0.8605,
"step": 125
},
{
"epoch": 0.6341463414634146,
"grad_norm": 0.98828125,
"learning_rate": 0.00019957710836063263,
"loss": 0.8857,
"step": 130
},
{
"epoch": 0.6585365853658537,
"grad_norm": 1.8046875,
"learning_rate": 0.00019940614891845809,
"loss": 0.8533,
"step": 135
},
{
"epoch": 0.6829268292682927,
"grad_norm": 1.9140625,
"learning_rate": 0.00019920633716185226,
"loss": 0.8332,
"step": 140
},
{
"epoch": 0.7073170731707317,
"grad_norm": 0.9140625,
"learning_rate": 0.00019897773108553378,
"loss": 0.8485,
"step": 145
},
{
"epoch": 0.7317073170731707,
"grad_norm": 1.9296875,
"learning_rate": 0.00019872039704167964,
"loss": 0.8479,
"step": 150
},
{
"epoch": 0.7560975609756098,
"grad_norm": 1.4921875,
"learning_rate": 0.00019843440972066697,
"loss": 0.8418,
"step": 155
},
{
"epoch": 0.7804878048780488,
"grad_norm": 1.9296875,
"learning_rate": 0.00019811985212939416,
"loss": 0.8513,
"step": 160
},
{
"epoch": 0.8048780487804879,
"grad_norm": 1.5234375,
"learning_rate": 0.00019777681556718864,
"loss": 0.8217,
"step": 165
},
{
"epoch": 0.8292682926829268,
"grad_norm": 1.8671875,
"learning_rate": 0.00019740539959930725,
"loss": 0.8169,
"step": 170
},
{
"epoch": 0.8536585365853658,
"grad_norm": 1.046875,
"learning_rate": 0.00019700571202803797,
"loss": 0.8386,
"step": 175
},
{
"epoch": 0.8780487804878049,
"grad_norm": 1.2421875,
"learning_rate": 0.00019657786886141052,
"loss": 0.8144,
"step": 180
},
{
"epoch": 0.9024390243902439,
"grad_norm": 4.15625,
"learning_rate": 0.00019612199427952552,
"loss": 0.8229,
"step": 185
},
{
"epoch": 0.926829268292683,
"grad_norm": 0.70703125,
"learning_rate": 0.00019563822059851145,
"loss": 0.8128,
"step": 190
},
{
"epoch": 0.9512195121951219,
"grad_norm": 0.97265625,
"learning_rate": 0.00019512668823212055,
"loss": 0.8072,
"step": 195
},
{
"epoch": 0.975609756097561,
"grad_norm": 0.6484375,
"learning_rate": 0.0001945875456509739,
"loss": 0.8097,
"step": 200
},
{
"epoch": 1.0,
"grad_norm": 0.6953125,
"learning_rate": 0.00019402094933946857,
"loss": 0.7892,
"step": 205
},
{
"epoch": 1.0,
"eval_loss": 2.2406020164489746,
"eval_runtime": 0.9998,
"eval_samples_per_second": 5.001,
"eval_steps_per_second": 2.0,
"step": 205
},
{
"epoch": 1.024390243902439,
"grad_norm": 0.6796875,
"learning_rate": 0.0001934270637503584,
"loss": 0.7753,
"step": 210
},
{
"epoch": 1.048780487804878,
"grad_norm": 0.71875,
"learning_rate": 0.00019280606125702203,
"loss": 0.7289,
"step": 215
},
{
"epoch": 1.0731707317073171,
"grad_norm": 0.625,
"learning_rate": 0.00019215812210343226,
"loss": 0.7656,
"step": 220
},
{
"epoch": 1.0975609756097562,
"grad_norm": 0.65625,
"learning_rate": 0.00019148343435184079,
"loss": 0.7603,
"step": 225
},
{
"epoch": 1.1219512195121952,
"grad_norm": 0.671875,
"learning_rate": 0.00019078219382819353,
"loss": 0.7491,
"step": 230
},
{
"epoch": 1.146341463414634,
"grad_norm": 0.56640625,
"learning_rate": 0.00019005460406529311,
"loss": 0.7249,
"step": 235
},
{
"epoch": 1.170731707317073,
"grad_norm": 0.57421875,
"learning_rate": 0.00018930087624372387,
"loss": 0.7755,
"step": 240
},
{
"epoch": 1.1951219512195121,
"grad_norm": 0.703125,
"learning_rate": 0.00018852122913055742,
"loss": 0.7553,
"step": 245
},
{
"epoch": 1.2195121951219512,
"grad_norm": 0.890625,
"learning_rate": 0.00018771588901585635,
"loss": 0.7482,
"step": 250
},
{
"epoch": 1.2439024390243902,
"grad_norm": 0.77734375,
"learning_rate": 0.00018688508964699404,
"loss": 0.7402,
"step": 255
},
{
"epoch": 1.2682926829268293,
"grad_norm": 1.015625,
"learning_rate": 0.00018602907216081044,
"loss": 0.7263,
"step": 260
},
{
"epoch": 1.2926829268292683,
"grad_norm": 1.3828125,
"learning_rate": 0.0001851480850136228,
"loss": 0.7435,
"step": 265
},
{
"epoch": 1.3170731707317074,
"grad_norm": 0.58984375,
"learning_rate": 0.00018424238390911198,
"loss": 0.7457,
"step": 270
},
{
"epoch": 1.3414634146341464,
"grad_norm": 1.0078125,
"learning_rate": 0.00018331223172410535,
"loss": 0.7483,
"step": 275
},
{
"epoch": 1.3658536585365852,
"grad_norm": 0.609375,
"learning_rate": 0.00018235789843227756,
"loss": 0.7486,
"step": 280
},
{
"epoch": 1.3902439024390243,
"grad_norm": 1.265625,
"learning_rate": 0.00018137966102579176,
"loss": 0.7548,
"step": 285
},
{
"epoch": 1.4146341463414633,
"grad_norm": 1.1953125,
"learning_rate": 0.00018037780343490312,
"loss": 0.7282,
"step": 290
},
{
"epoch": 1.4390243902439024,
"grad_norm": 0.6875,
"learning_rate": 0.00017935261644554942,
"loss": 0.7415,
"step": 295
},
{
"epoch": 1.4634146341463414,
"grad_norm": 0.73046875,
"learning_rate": 0.0001783043976149511,
"loss": 0.7362,
"step": 300
},
{
"epoch": 1.4878048780487805,
"grad_norm": 0.578125,
"learning_rate": 0.0001772334511852463,
"loss": 0.724,
"step": 305
},
{
"epoch": 1.5121951219512195,
"grad_norm": 0.59765625,
"learning_rate": 0.0001761400879951856,
"loss": 0.7249,
"step": 310
},
{
"epoch": 1.5365853658536586,
"grad_norm": 1.6953125,
"learning_rate": 0.00017502462538991205,
"loss": 0.7212,
"step": 315
},
{
"epoch": 1.5609756097560976,
"grad_norm": 0.6328125,
"learning_rate": 0.00017388738712885275,
"loss": 0.7194,
"step": 320
},
{
"epoch": 1.5853658536585367,
"grad_norm": 1.3125,
"learning_rate": 0.0001727287032917487,
"loss": 0.765,
"step": 325
},
{
"epoch": 1.6097560975609757,
"grad_norm": 1.578125,
"learning_rate": 0.00017154891018285028,
"loss": 0.7318,
"step": 330
},
{
"epoch": 1.6341463414634148,
"grad_norm": 0.50390625,
"learning_rate": 0.00017034835023330597,
"loss": 0.7396,
"step": 335
},
{
"epoch": 1.6585365853658538,
"grad_norm": 2.0625,
"learning_rate": 0.00016912737190177292,
"loss": 0.737,
"step": 340
},
{
"epoch": 1.6829268292682928,
"grad_norm": 0.59765625,
"learning_rate": 0.00016788632957327772,
"loss": 0.7302,
"step": 345
},
{
"epoch": 1.7073170731707317,
"grad_norm": 0.65234375,
"learning_rate": 0.00016662558345635753,
"loss": 0.7193,
"step": 350
},
{
"epoch": 1.7317073170731707,
"grad_norm": 0.76953125,
"learning_rate": 0.00016534549947851062,
"loss": 0.7147,
"step": 355
},
{
"epoch": 1.7560975609756098,
"grad_norm": 0.73828125,
"learning_rate": 0.00016404644917998698,
"loss": 0.7539,
"step": 360
},
{
"epoch": 1.7804878048780488,
"grad_norm": 0.9453125,
"learning_rate": 0.00016272880960595024,
"loss": 0.754,
"step": 365
},
{
"epoch": 1.8048780487804879,
"grad_norm": 0.90625,
"learning_rate": 0.00016139296319704117,
"loss": 0.7346,
"step": 370
},
{
"epoch": 1.8292682926829267,
"grad_norm": 0.89453125,
"learning_rate": 0.00016003929767837588,
"loss": 0.6961,
"step": 375
},
{
"epoch": 1.8536585365853657,
"grad_norm": 1.078125,
"learning_rate": 0.00015866820594700944,
"loss": 0.7259,
"step": 380
},
{
"epoch": 1.8780487804878048,
"grad_norm": 0.65625,
"learning_rate": 0.00015728008595789926,
"loss": 0.7198,
"step": 385
},
{
"epoch": 1.9024390243902438,
"grad_norm": 0.515625,
"learning_rate": 0.0001558753406083995,
"loss": 0.6858,
"step": 390
},
{
"epoch": 1.9268292682926829,
"grad_norm": 0.60546875,
"learning_rate": 0.00015445437762132174,
"loss": 0.6987,
"step": 395
},
{
"epoch": 1.951219512195122,
"grad_norm": 0.5625,
"learning_rate": 0.0001530176094265945,
"loss": 0.7054,
"step": 400
},
{
"epoch": 1.975609756097561,
"grad_norm": 0.62890625,
"learning_rate": 0.00015156545304155698,
"loss": 0.7226,
"step": 405
},
{
"epoch": 2.0,
"grad_norm": 0.52734375,
"learning_rate": 0.00015009832994992102,
"loss": 0.7033,
"step": 410
},
{
"epoch": 2.0,
"eval_loss": 2.2004494667053223,
"eval_runtime": 1.0005,
"eval_samples_per_second": 4.998,
"eval_steps_per_second": 1.999,
"step": 410
},
{
"epoch": 2.024390243902439,
"grad_norm": 0.6328125,
"learning_rate": 0.0001486166659794368,
"loss": 0.6398,
"step": 415
},
{
"epoch": 2.048780487804878,
"grad_norm": 0.65234375,
"learning_rate": 0.00014712089117829776,
"loss": 0.647,
"step": 420
},
{
"epoch": 2.073170731707317,
"grad_norm": 0.66796875,
"learning_rate": 0.0001456114396903204,
"loss": 0.6333,
"step": 425
},
{
"epoch": 2.097560975609756,
"grad_norm": 0.60546875,
"learning_rate": 0.0001440887496289356,
"loss": 0.6296,
"step": 430
},
{
"epoch": 2.1219512195121952,
"grad_norm": 0.546875,
"learning_rate": 0.00014255326295002754,
"loss": 0.6516,
"step": 435
},
{
"epoch": 2.1463414634146343,
"grad_norm": 0.671875,
"learning_rate": 0.00014100542532365724,
"loss": 0.6468,
"step": 440
},
{
"epoch": 2.1707317073170733,
"grad_norm": 0.578125,
"learning_rate": 0.0001394456860047086,
"loss": 0.6472,
"step": 445
},
{
"epoch": 2.1951219512195124,
"grad_norm": 0.77734375,
"learning_rate": 0.00013787449770249336,
"loss": 0.6587,
"step": 450
},
{
"epoch": 2.2195121951219514,
"grad_norm": 0.70703125,
"learning_rate": 0.0001362923164493538,
"loss": 0.6505,
"step": 455
},
{
"epoch": 2.2439024390243905,
"grad_norm": 0.69140625,
"learning_rate": 0.00013469960146830073,
"loss": 0.6463,
"step": 460
},
{
"epoch": 2.2682926829268295,
"grad_norm": 0.72265625,
"learning_rate": 0.00013309681503972565,
"loss": 0.6372,
"step": 465
},
{
"epoch": 2.292682926829268,
"grad_norm": 0.80078125,
"learning_rate": 0.00013148442236722506,
"loss": 0.6285,
"step": 470
},
{
"epoch": 2.317073170731707,
"grad_norm": 0.7578125,
"learning_rate": 0.00012986289144257705,
"loss": 0.6645,
"step": 475
},
{
"epoch": 2.341463414634146,
"grad_norm": 1.0234375,
"learning_rate": 0.00012823269290990777,
"loss": 0.6663,
"step": 480
},
{
"epoch": 2.3658536585365852,
"grad_norm": 1.0625,
"learning_rate": 0.0001265942999290887,
"loss": 0.6495,
"step": 485
},
{
"epoch": 2.3902439024390243,
"grad_norm": 1.0078125,
"learning_rate": 0.00012494818803840367,
"loss": 0.6429,
"step": 490
},
{
"epoch": 2.4146341463414633,
"grad_norm": 1.796875,
"learning_rate": 0.00012329483501652492,
"loss": 0.6573,
"step": 495
},
{
"epoch": 2.4390243902439024,
"grad_norm": 0.921875,
"learning_rate": 0.00012163472074383994,
"loss": 0.6487,
"step": 500
},
{
"epoch": 2.4634146341463414,
"grad_norm": 0.59375,
"learning_rate": 0.00011996832706316739,
"loss": 0.6726,
"step": 505
},
{
"epoch": 2.4878048780487805,
"grad_norm": 0.5546875,
"learning_rate": 0.00011829613763990384,
"loss": 0.6546,
"step": 510
},
{
"epoch": 2.5121951219512195,
"grad_norm": 0.57421875,
"learning_rate": 0.00011661863782164153,
"loss": 0.6306,
"step": 515
},
{
"epoch": 2.5365853658536586,
"grad_norm": 0.61328125,
"learning_rate": 0.00011493631449729767,
"loss": 0.6591,
"step": 520
},
{
"epoch": 2.5609756097560976,
"grad_norm": 0.578125,
"learning_rate": 0.00011324965595579666,
"loss": 0.6387,
"step": 525
},
{
"epoch": 2.5853658536585367,
"grad_norm": 0.60546875,
"learning_rate": 0.00011155915174434561,
"loss": 0.6539,
"step": 530
},
{
"epoch": 2.6097560975609757,
"grad_norm": 0.87109375,
"learning_rate": 0.00010986529252634503,
"loss": 0.6654,
"step": 535
},
{
"epoch": 2.6341463414634148,
"grad_norm": 0.859375,
"learning_rate": 0.00010816856993897522,
"loss": 0.6471,
"step": 540
},
{
"epoch": 2.658536585365854,
"grad_norm": 0.5703125,
"learning_rate": 0.00010646947645050023,
"loss": 0.6482,
"step": 545
},
{
"epoch": 2.682926829268293,
"grad_norm": 0.5703125,
"learning_rate": 0.00010476850521733048,
"loss": 0.6252,
"step": 550
},
{
"epoch": 2.7073170731707314,
"grad_norm": 0.69140625,
"learning_rate": 0.00010306614994088582,
"loss": 0.6605,
"step": 555
},
{
"epoch": 2.7317073170731705,
"grad_norm": 0.52734375,
"learning_rate": 0.00010136290472430013,
"loss": 0.646,
"step": 560
},
{
"epoch": 2.7560975609756095,
"grad_norm": 0.64453125,
"learning_rate": 9.965926392900956e-05,
"loss": 0.6492,
"step": 565
},
{
"epoch": 2.7804878048780486,
"grad_norm": 0.63671875,
"learning_rate": 9.795572203126573e-05,
"loss": 0.6477,
"step": 570
},
{
"epoch": 2.8048780487804876,
"grad_norm": 0.703125,
"learning_rate": 9.625277347861553e-05,
"loss": 0.6268,
"step": 575
},
{
"epoch": 2.8292682926829267,
"grad_norm": 0.80078125,
"learning_rate": 9.455091254638939e-05,
"loss": 0.6364,
"step": 580
},
{
"epoch": 2.8536585365853657,
"grad_norm": 0.62890625,
"learning_rate": 9.285063319423939e-05,
"loss": 0.6497,
"step": 585
},
{
"epoch": 2.8780487804878048,
"grad_norm": 0.58203125,
"learning_rate": 9.115242892276909e-05,
"loss": 0.6446,
"step": 590
},
{
"epoch": 2.902439024390244,
"grad_norm": 0.70703125,
"learning_rate": 8.945679263029661e-05,
"loss": 0.6657,
"step": 595
},
{
"epoch": 2.926829268292683,
"grad_norm": 0.64453125,
"learning_rate": 8.776421646979232e-05,
"loss": 0.6498,
"step": 600
},
{
"epoch": 2.951219512195122,
"grad_norm": 0.5546875,
"learning_rate": 8.607519170603328e-05,
"loss": 0.6623,
"step": 605
},
{
"epoch": 2.975609756097561,
"grad_norm": 0.55078125,
"learning_rate": 8.439020857301503e-05,
"loss": 0.6467,
"step": 610
},
{
"epoch": 3.0,
"grad_norm": 0.6875,
"learning_rate": 8.270975613166281e-05,
"loss": 0.6346,
"step": 615
},
{
"epoch": 3.0,
"eval_loss": 2.245811939239502,
"eval_runtime": 1.001,
"eval_samples_per_second": 4.995,
"eval_steps_per_second": 1.998,
"step": 615
},
{
"epoch": 3.024390243902439,
"grad_norm": 0.609375,
"learning_rate": 8.103432212788323e-05,
"loss": 0.5718,
"step": 620
},
{
"epoch": 3.048780487804878,
"grad_norm": 0.66796875,
"learning_rate": 7.936439285099752e-05,
"loss": 0.5989,
"step": 625
},
{
"epoch": 3.073170731707317,
"grad_norm": 0.62890625,
"learning_rate": 7.770045299259774e-05,
"loss": 0.598,
"step": 630
},
{
"epoch": 3.097560975609756,
"grad_norm": 0.5625,
"learning_rate": 7.60429855058664e-05,
"loss": 0.5731,
"step": 635
},
{
"epoch": 3.1219512195121952,
"grad_norm": 0.56640625,
"learning_rate": 7.439247146540109e-05,
"loss": 0.6034,
"step": 640
},
{
"epoch": 3.1463414634146343,
"grad_norm": 0.6015625,
"learning_rate": 7.274938992758403e-05,
"loss": 0.5669,
"step": 645
},
{
"epoch": 3.1707317073170733,
"grad_norm": 0.59765625,
"learning_rate": 7.111421779153745e-05,
"loss": 0.5873,
"step": 650
},
{
"epoch": 3.1951219512195124,
"grad_norm": 0.60546875,
"learning_rate": 6.94874296607052e-05,
"loss": 0.5674,
"step": 655
},
{
"epoch": 3.2195121951219514,
"grad_norm": 0.54296875,
"learning_rate": 6.786949770510071e-05,
"loss": 0.5726,
"step": 660
},
{
"epoch": 3.2439024390243905,
"grad_norm": 0.578125,
"learning_rate": 6.626089152426097e-05,
"loss": 0.6006,
"step": 665
},
{
"epoch": 3.2682926829268295,
"grad_norm": 0.58984375,
"learning_rate": 6.4662078010947e-05,
"loss": 0.5729,
"step": 670
},
{
"epoch": 3.292682926829268,
"grad_norm": 0.546875,
"learning_rate": 6.307352121562949e-05,
"loss": 0.5719,
"step": 675
},
{
"epoch": 3.317073170731707,
"grad_norm": 0.5859375,
"learning_rate": 6.149568221179993e-05,
"loss": 0.571,
"step": 680
},
{
"epoch": 3.341463414634146,
"grad_norm": 0.5859375,
"learning_rate": 5.992901896214526e-05,
"loss": 0.5674,
"step": 685
},
{
"epoch": 3.3658536585365852,
"grad_norm": 0.6640625,
"learning_rate": 5.837398618562584e-05,
"loss": 0.5772,
"step": 690
},
{
"epoch": 3.3902439024390243,
"grad_norm": 0.58203125,
"learning_rate": 5.68310352254946e-05,
"loss": 0.5893,
"step": 695
},
{
"epoch": 3.4146341463414633,
"grad_norm": 0.62109375,
"learning_rate": 5.5300613918296295e-05,
"loss": 0.5771,
"step": 700
},
{
"epoch": 3.4390243902439024,
"grad_norm": 0.58203125,
"learning_rate": 5.378316646388424e-05,
"loss": 0.5721,
"step": 705
},
{
"epoch": 3.4634146341463414,
"grad_norm": 0.578125,
"learning_rate": 5.227913329649271e-05,
"loss": 0.5788,
"step": 710
},
{
"epoch": 3.4878048780487805,
"grad_norm": 0.59765625,
"learning_rate": 5.078895095690249e-05,
"loss": 0.5693,
"step": 715
},
{
"epoch": 3.5121951219512195,
"grad_norm": 0.5703125,
"learning_rate": 4.931305196573621e-05,
"loss": 0.6107,
"step": 720
},
{
"epoch": 3.5365853658536586,
"grad_norm": 0.58203125,
"learning_rate": 4.78518646979206e-05,
"loss": 0.5695,
"step": 725
},
{
"epoch": 3.5609756097560976,
"grad_norm": 0.58984375,
"learning_rate": 4.6405813258352135e-05,
"loss": 0.5707,
"step": 730
},
{
"epoch": 3.5853658536585367,
"grad_norm": 0.62109375,
"learning_rate": 4.4975317358801885e-05,
"loss": 0.5635,
"step": 735
},
{
"epoch": 3.6097560975609757,
"grad_norm": 0.57421875,
"learning_rate": 4.3560792196095543e-05,
"loss": 0.5747,
"step": 740
},
{
"epoch": 3.6341463414634148,
"grad_norm": 0.57421875,
"learning_rate": 4.216264833160396e-05,
"loss": 0.5856,
"step": 745
},
{
"epoch": 3.658536585365854,
"grad_norm": 0.6015625,
"learning_rate": 4.0781291572078806e-05,
"loss": 0.5797,
"step": 750
},
{
"epoch": 3.682926829268293,
"grad_norm": 0.55859375,
"learning_rate": 3.941712285186878e-05,
"loss": 0.5643,
"step": 755
},
{
"epoch": 3.7073170731707314,
"grad_norm": 0.5859375,
"learning_rate": 3.807053811654948e-05,
"loss": 0.5723,
"step": 760
},
{
"epoch": 3.7317073170731705,
"grad_norm": 0.59375,
"learning_rate": 3.674192820800156e-05,
"loss": 0.5894,
"step": 765
},
{
"epoch": 3.7560975609756095,
"grad_norm": 0.55859375,
"learning_rate": 3.543167875097013e-05,
"loss": 0.5505,
"step": 770
},
{
"epoch": 3.7804878048780486,
"grad_norm": 0.5859375,
"learning_rate": 3.4140170041138385e-05,
"loss": 0.5752,
"step": 775
},
{
"epoch": 3.8048780487804876,
"grad_norm": 0.55859375,
"learning_rate": 3.286777693474803e-05,
"loss": 0.5629,
"step": 780
},
{
"epoch": 3.8292682926829267,
"grad_norm": 0.59765625,
"learning_rate": 3.1614868739798495e-05,
"loss": 0.5787,
"step": 785
},
{
"epoch": 3.8536585365853657,
"grad_norm": 0.6015625,
"learning_rate": 3.0381809108856398e-05,
"loss": 0.574,
"step": 790
},
{
"epoch": 3.8780487804878048,
"grad_norm": 0.6171875,
"learning_rate": 2.9168955933506648e-05,
"loss": 0.5826,
"step": 795
},
{
"epoch": 3.902439024390244,
"grad_norm": 0.578125,
"learning_rate": 2.79766612404755e-05,
"loss": 0.5725,
"step": 800
},
{
"epoch": 3.926829268292683,
"grad_norm": 0.55859375,
"learning_rate": 2.6805271089455986e-05,
"loss": 0.5612,
"step": 805
},
{
"epoch": 3.951219512195122,
"grad_norm": 0.6328125,
"learning_rate": 2.565512547266511e-05,
"loss": 0.5721,
"step": 810
},
{
"epoch": 3.975609756097561,
"grad_norm": 0.5625,
"learning_rate": 2.4526558216162322e-05,
"loss": 0.5725,
"step": 815
},
{
"epoch": 4.0,
"grad_norm": 0.56640625,
"learning_rate": 2.3419896882957527e-05,
"loss": 0.5755,
"step": 820
},
{
"epoch": 4.0,
"eval_loss": 2.2934529781341553,
"eval_runtime": 0.9995,
"eval_samples_per_second": 5.002,
"eval_steps_per_second": 2.001,
"step": 820
},
{
"epoch": 4.024390243902439,
"grad_norm": 0.55859375,
"learning_rate": 2.2335462677936957e-05,
"loss": 0.5324,
"step": 825
},
{
"epoch": 4.048780487804878,
"grad_norm": 0.61328125,
"learning_rate": 2.1273570354634508e-05,
"loss": 0.5386,
"step": 830
},
{
"epoch": 4.073170731707317,
"grad_norm": 0.55859375,
"learning_rate": 2.023452812387555e-05,
"loss": 0.5296,
"step": 835
},
{
"epoch": 4.097560975609756,
"grad_norm": 0.62890625,
"learning_rate": 1.9218637564319696e-05,
"loss": 0.5304,
"step": 840
},
{
"epoch": 4.121951219512195,
"grad_norm": 0.57421875,
"learning_rate": 1.8226193534928604e-05,
"loss": 0.5554,
"step": 845
},
{
"epoch": 4.146341463414634,
"grad_norm": 0.578125,
"learning_rate": 1.725748408938408e-05,
"loss": 0.5376,
"step": 850
},
{
"epoch": 4.170731707317073,
"grad_norm": 0.58984375,
"learning_rate": 1.63127903924815e-05,
"loss": 0.5335,
"step": 855
},
{
"epoch": 4.195121951219512,
"grad_norm": 0.5625,
"learning_rate": 1.5392386638522482e-05,
"loss": 0.5298,
"step": 860
},
{
"epoch": 4.219512195121951,
"grad_norm": 0.60546875,
"learning_rate": 1.4496539971731026e-05,
"loss": 0.5239,
"step": 865
},
{
"epoch": 4.2439024390243905,
"grad_norm": 0.57421875,
"learning_rate": 1.3625510408715714e-05,
"loss": 0.5255,
"step": 870
},
{
"epoch": 4.2682926829268295,
"grad_norm": 0.5859375,
"learning_rate": 1.2779550763000703e-05,
"loss": 0.5382,
"step": 875
},
{
"epoch": 4.2926829268292686,
"grad_norm": 0.609375,
"learning_rate": 1.1958906571647421e-05,
"loss": 0.5469,
"step": 880
},
{
"epoch": 4.317073170731708,
"grad_norm": 0.59375,
"learning_rate": 1.1163816023988261e-05,
"loss": 0.547,
"step": 885
},
{
"epoch": 4.341463414634147,
"grad_norm": 0.56640625,
"learning_rate": 1.0394509892492833e-05,
"loss": 0.5387,
"step": 890
},
{
"epoch": 4.365853658536586,
"grad_norm": 0.58203125,
"learning_rate": 9.65121146578709e-06,
"loss": 0.5487,
"step": 895
},
{
"epoch": 4.390243902439025,
"grad_norm": 0.57421875,
"learning_rate": 8.934136483844391e-06,
"loss": 0.5306,
"step": 900
},
{
"epoch": 4.414634146341464,
"grad_norm": 0.58984375,
"learning_rate": 8.243493075367813e-06,
"loss": 0.5259,
"step": 905
},
{
"epoch": 4.439024390243903,
"grad_norm": 0.5703125,
"learning_rate": 7.579481697381363e-06,
"loss": 0.5473,
"step": 910
},
{
"epoch": 4.463414634146342,
"grad_norm": 0.55859375,
"learning_rate": 6.942295077048011e-06,
"loss": 0.5329,
"step": 915
},
{
"epoch": 4.487804878048781,
"grad_norm": 0.60546875,
"learning_rate": 6.3321181557312815e-06,
"loss": 0.551,
"step": 920
},
{
"epoch": 4.512195121951219,
"grad_norm": 0.5703125,
"learning_rate": 5.749128035316553e-06,
"loss": 0.5508,
"step": 925
},
{
"epoch": 4.536585365853659,
"grad_norm": 0.59375,
"learning_rate": 5.193493926807835e-06,
"loss": 0.5348,
"step": 930
},
{
"epoch": 4.560975609756097,
"grad_norm": 0.58984375,
"learning_rate": 4.665377101214863e-06,
"loss": 0.5168,
"step": 935
},
{
"epoch": 4.585365853658536,
"grad_norm": 0.61328125,
"learning_rate": 4.164930842744608e-06,
"loss": 0.5442,
"step": 940
},
{
"epoch": 4.609756097560975,
"grad_norm": 0.59375,
"learning_rate": 3.6923004043111444e-06,
"loss": 0.5296,
"step": 945
},
{
"epoch": 4.634146341463414,
"grad_norm": 0.546875,
"learning_rate": 3.2476229653763734e-06,
"loss": 0.5566,
"step": 950
},
{
"epoch": 4.658536585365853,
"grad_norm": 0.58984375,
"learning_rate": 2.8310275921341944e-06,
"loss": 0.5219,
"step": 955
},
{
"epoch": 4.682926829268292,
"grad_norm": 0.578125,
"learning_rate": 2.44263520004937e-06,
"loss": 0.5577,
"step": 960
},
{
"epoch": 4.7073170731707314,
"grad_norm": 0.57421875,
"learning_rate": 2.0825585187623007e-06,
"loss": 0.5235,
"step": 965
},
{
"epoch": 4.7317073170731705,
"grad_norm": 0.578125,
"learning_rate": 1.7509020593695302e-06,
"loss": 0.547,
"step": 970
},
{
"epoch": 4.7560975609756095,
"grad_norm": 0.57421875,
"learning_rate": 1.4477620840897766e-06,
"loss": 0.5331,
"step": 975
},
{
"epoch": 4.780487804878049,
"grad_norm": 0.59375,
"learning_rate": 1.1732265783241492e-06,
"loss": 0.5251,
"step": 980
},
{
"epoch": 4.804878048780488,
"grad_norm": 0.60546875,
"learning_rate": 9.273752251186096e-07,
"loss": 0.527,
"step": 985
},
{
"epoch": 4.829268292682927,
"grad_norm": 0.57421875,
"learning_rate": 7.102793820362829e-07,
"loss": 0.5353,
"step": 990
},
{
"epoch": 4.853658536585366,
"grad_norm": 0.58203125,
"learning_rate": 5.22002060446125e-07,
"loss": 0.5347,
"step": 995
},
{
"epoch": 4.878048780487805,
"grad_norm": 0.58984375,
"learning_rate": 3.6259790723409683e-07,
"loss": 0.5436,
"step": 1000
},
{
"epoch": 4.902439024390244,
"grad_norm": 0.5625,
"learning_rate": 2.3211318894205136e-07,
"loss": 0.535,
"step": 1005
},
{
"epoch": 4.926829268292683,
"grad_norm": 0.58984375,
"learning_rate": 1.3058577833905404e-07,
"loss": 0.5213,
"step": 1010
},
{
"epoch": 4.951219512195122,
"grad_norm": 0.55859375,
"learning_rate": 5.804514342889755e-08,
"loss": 0.5247,
"step": 1015
},
{
"epoch": 4.975609756097561,
"grad_norm": 0.60546875,
"learning_rate": 1.4512338897121335e-08,
"loss": 0.5333,
"step": 1020
},
{
"epoch": 5.0,
"grad_norm": 0.546875,
"learning_rate": 0.0,
"loss": 0.5144,
"step": 1025
},
{
"epoch": 5.0,
"eval_loss": 2.326845407485962,
"eval_runtime": 1.0003,
"eval_samples_per_second": 4.998,
"eval_steps_per_second": 1.999,
"step": 1025
},
{
"epoch": 5.0,
"step": 1025,
"total_flos": 1.5670950020754964e+18,
"train_loss": 1.4066738275202308,
"train_runtime": 8016.4558,
"train_samples_per_second": 2.044,
"train_steps_per_second": 0.128
}
],
"logging_steps": 5,
"max_steps": 1025,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.5670950020754964e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}