LLAMA-3.2-1B-MathInstrcu-LORA / trainer_state.json
SriSanth2345's picture
Upload 224 files
242ef39 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1875,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008,
"grad_norm": 0.8485889434814453,
"learning_rate": 0.0001999964908278481,
"loss": 1.2049,
"step": 5
},
{
"epoch": 0.016,
"grad_norm": 0.47789862751960754,
"learning_rate": 0.00019998596355767805,
"loss": 0.9333,
"step": 10
},
{
"epoch": 0.024,
"grad_norm": 1.017558217048645,
"learning_rate": 0.00019996841892833,
"loss": 0.8671,
"step": 15
},
{
"epoch": 0.032,
"grad_norm": 0.6610977053642273,
"learning_rate": 0.00019994385817114646,
"loss": 0.7979,
"step": 20
},
{
"epoch": 0.04,
"grad_norm": 0.6075429320335388,
"learning_rate": 0.00019991228300988585,
"loss": 0.7662,
"step": 25
},
{
"epoch": 0.048,
"grad_norm": 0.6595763564109802,
"learning_rate": 0.00019987369566060176,
"loss": 0.7929,
"step": 30
},
{
"epoch": 0.056,
"grad_norm": 0.6968618035316467,
"learning_rate": 0.00019982809883148722,
"loss": 0.7683,
"step": 35
},
{
"epoch": 0.064,
"grad_norm": 0.4889592230319977,
"learning_rate": 0.00019977549572268468,
"loss": 0.8667,
"step": 40
},
{
"epoch": 0.072,
"grad_norm": 0.6651108264923096,
"learning_rate": 0.0001997158900260614,
"loss": 0.8446,
"step": 45
},
{
"epoch": 0.08,
"grad_norm": 0.5898510217666626,
"learning_rate": 0.00019964928592495045,
"loss": 0.9051,
"step": 50
},
{
"epoch": 0.088,
"grad_norm": 0.4398016035556793,
"learning_rate": 0.00019957568809385694,
"loss": 0.7235,
"step": 55
},
{
"epoch": 0.096,
"grad_norm": 0.6901968121528625,
"learning_rate": 0.00019949510169813003,
"loss": 0.8169,
"step": 60
},
{
"epoch": 0.104,
"grad_norm": 0.6267213225364685,
"learning_rate": 0.00019940753239360047,
"loss": 0.8266,
"step": 65
},
{
"epoch": 0.112,
"grad_norm": 0.48524895310401917,
"learning_rate": 0.00019931298632618356,
"loss": 0.758,
"step": 70
},
{
"epoch": 0.12,
"grad_norm": 0.5294132232666016,
"learning_rate": 0.0001992114701314478,
"loss": 0.7759,
"step": 75
},
{
"epoch": 0.128,
"grad_norm": 0.48957982659339905,
"learning_rate": 0.0001991029909341493,
"loss": 0.7797,
"step": 80
},
{
"epoch": 0.136,
"grad_norm": 0.645412802696228,
"learning_rate": 0.00019898755634773158,
"loss": 0.7437,
"step": 85
},
{
"epoch": 0.144,
"grad_norm": 0.43297675251960754,
"learning_rate": 0.0001988651744737914,
"loss": 0.8043,
"step": 90
},
{
"epoch": 0.152,
"grad_norm": 0.5513920783996582,
"learning_rate": 0.00019873585390151003,
"loss": 0.7701,
"step": 95
},
{
"epoch": 0.16,
"grad_norm": 0.8462435007095337,
"learning_rate": 0.0001985996037070505,
"loss": 0.709,
"step": 100
},
{
"epoch": 0.168,
"grad_norm": 0.6892585158348083,
"learning_rate": 0.00019845643345292054,
"loss": 0.7377,
"step": 105
},
{
"epoch": 0.176,
"grad_norm": 0.4617864191532135,
"learning_rate": 0.00019830635318730154,
"loss": 0.8352,
"step": 110
},
{
"epoch": 0.184,
"grad_norm": 0.6300354599952698,
"learning_rate": 0.0001981493734433433,
"loss": 0.7738,
"step": 115
},
{
"epoch": 0.192,
"grad_norm": 0.8086859583854675,
"learning_rate": 0.0001979855052384247,
"loss": 0.8067,
"step": 120
},
{
"epoch": 0.2,
"grad_norm": 0.6272985935211182,
"learning_rate": 0.00019781476007338058,
"loss": 0.7456,
"step": 125
},
{
"epoch": 0.208,
"grad_norm": 0.44750839471817017,
"learning_rate": 0.00019763714993169452,
"loss": 0.758,
"step": 130
},
{
"epoch": 0.216,
"grad_norm": 0.5053977370262146,
"learning_rate": 0.00019745268727865774,
"loss": 0.7895,
"step": 135
},
{
"epoch": 0.224,
"grad_norm": 0.41920769214630127,
"learning_rate": 0.00019726138506049438,
"loss": 0.7302,
"step": 140
},
{
"epoch": 0.232,
"grad_norm": 0.38280290365219116,
"learning_rate": 0.00019706325670345275,
"loss": 0.8152,
"step": 145
},
{
"epoch": 0.24,
"grad_norm": 0.554710865020752,
"learning_rate": 0.0001968583161128631,
"loss": 0.8461,
"step": 150
},
{
"epoch": 0.248,
"grad_norm": 0.5612509250640869,
"learning_rate": 0.00019664657767216176,
"loss": 0.7787,
"step": 155
},
{
"epoch": 0.256,
"grad_norm": 0.610614538192749,
"learning_rate": 0.00019642805624188147,
"loss": 0.7574,
"step": 160
},
{
"epoch": 0.264,
"grad_norm": 0.679517924785614,
"learning_rate": 0.0001962027671586086,
"loss": 0.8487,
"step": 165
},
{
"epoch": 0.272,
"grad_norm": 0.6685434579849243,
"learning_rate": 0.00019597072623390668,
"loss": 0.6611,
"step": 170
},
{
"epoch": 0.28,
"grad_norm": 0.480293869972229,
"learning_rate": 0.00019573194975320673,
"loss": 0.7802,
"step": 175
},
{
"epoch": 0.288,
"grad_norm": 0.7727369070053101,
"learning_rate": 0.00019548645447466431,
"loss": 0.6727,
"step": 180
},
{
"epoch": 0.296,
"grad_norm": 0.6371043920516968,
"learning_rate": 0.00019523425762798329,
"loss": 0.7502,
"step": 185
},
{
"epoch": 0.304,
"grad_norm": 0.6399966478347778,
"learning_rate": 0.00019497537691320668,
"loss": 0.8401,
"step": 190
},
{
"epoch": 0.312,
"grad_norm": 0.7263137698173523,
"learning_rate": 0.00019470983049947444,
"loss": 0.7494,
"step": 195
},
{
"epoch": 0.32,
"grad_norm": 0.402416467666626,
"learning_rate": 0.00019443763702374812,
"loss": 0.7842,
"step": 200
},
{
"epoch": 0.328,
"grad_norm": 0.6639626026153564,
"learning_rate": 0.00019415881558950302,
"loss": 0.8082,
"step": 205
},
{
"epoch": 0.336,
"grad_norm": 0.5801042914390564,
"learning_rate": 0.00019387338576538744,
"loss": 0.7883,
"step": 210
},
{
"epoch": 0.344,
"grad_norm": 0.5533607006072998,
"learning_rate": 0.00019358136758384912,
"loss": 0.7356,
"step": 215
},
{
"epoch": 0.352,
"grad_norm": 0.6019654273986816,
"learning_rate": 0.00019328278153972947,
"loss": 0.7891,
"step": 220
},
{
"epoch": 0.36,
"grad_norm": 0.5344104170799255,
"learning_rate": 0.00019297764858882514,
"loss": 0.7671,
"step": 225
},
{
"epoch": 0.368,
"grad_norm": 0.5494843125343323,
"learning_rate": 0.0001926659901464172,
"loss": 0.6608,
"step": 230
},
{
"epoch": 0.376,
"grad_norm": 0.465420126914978,
"learning_rate": 0.00019234782808576824,
"loss": 0.647,
"step": 235
},
{
"epoch": 0.384,
"grad_norm": 0.5202775001525879,
"learning_rate": 0.00019202318473658705,
"loss": 0.729,
"step": 240
},
{
"epoch": 0.392,
"grad_norm": 0.5757818222045898,
"learning_rate": 0.00019169208288346166,
"loss": 0.6713,
"step": 245
},
{
"epoch": 0.4,
"grad_norm": 0.46555572748184204,
"learning_rate": 0.0001913545457642601,
"loss": 0.7049,
"step": 250
},
{
"epoch": 0.408,
"grad_norm": 0.5101790428161621,
"learning_rate": 0.00019101059706849957,
"loss": 0.7419,
"step": 255
},
{
"epoch": 0.416,
"grad_norm": 0.6083744764328003,
"learning_rate": 0.00019066026093568378,
"loss": 0.7148,
"step": 260
},
{
"epoch": 0.424,
"grad_norm": 0.4719640612602234,
"learning_rate": 0.00019030356195360874,
"loss": 0.7493,
"step": 265
},
{
"epoch": 0.432,
"grad_norm": 0.7365225553512573,
"learning_rate": 0.0001899405251566371,
"loss": 0.7652,
"step": 270
},
{
"epoch": 0.44,
"grad_norm": 0.4452705383300781,
"learning_rate": 0.0001895711760239413,
"loss": 0.7438,
"step": 275
},
{
"epoch": 0.448,
"grad_norm": 0.6071786284446716,
"learning_rate": 0.0001891955404777151,
"loss": 0.7683,
"step": 280
},
{
"epoch": 0.456,
"grad_norm": 0.5774498581886292,
"learning_rate": 0.00018881364488135448,
"loss": 0.8115,
"step": 285
},
{
"epoch": 0.464,
"grad_norm": 0.6134682893753052,
"learning_rate": 0.00018842551603760724,
"loss": 0.8335,
"step": 290
},
{
"epoch": 0.472,
"grad_norm": 0.4869893193244934,
"learning_rate": 0.00018803118118669202,
"loss": 0.6933,
"step": 295
},
{
"epoch": 0.48,
"grad_norm": 0.6457111239433289,
"learning_rate": 0.00018763066800438636,
"loss": 0.7515,
"step": 300
},
{
"epoch": 0.488,
"grad_norm": 0.59674471616745,
"learning_rate": 0.0001872240046000844,
"loss": 0.6931,
"step": 305
},
{
"epoch": 0.496,
"grad_norm": 0.44608160853385925,
"learning_rate": 0.00018681121951482393,
"loss": 0.782,
"step": 310
},
{
"epoch": 0.504,
"grad_norm": 0.5934664607048035,
"learning_rate": 0.00018639234171928353,
"loss": 0.7361,
"step": 315
},
{
"epoch": 0.512,
"grad_norm": 0.49716323614120483,
"learning_rate": 0.0001859674006117491,
"loss": 0.7443,
"step": 320
},
{
"epoch": 0.52,
"grad_norm": 0.47995495796203613,
"learning_rate": 0.00018553642601605068,
"loss": 0.7221,
"step": 325
},
{
"epoch": 0.528,
"grad_norm": 0.5177399516105652,
"learning_rate": 0.00018509944817946922,
"loss": 0.7622,
"step": 330
},
{
"epoch": 0.536,
"grad_norm": 0.6638798713684082,
"learning_rate": 0.0001846564977706138,
"loss": 0.8556,
"step": 335
},
{
"epoch": 0.544,
"grad_norm": 0.5056771636009216,
"learning_rate": 0.00018420760587726923,
"loss": 0.7814,
"step": 340
},
{
"epoch": 0.552,
"grad_norm": 0.44543707370758057,
"learning_rate": 0.0001837528040042142,
"loss": 0.722,
"step": 345
},
{
"epoch": 0.56,
"grad_norm": 0.6765120625495911,
"learning_rate": 0.00018329212407100994,
"loss": 0.7903,
"step": 350
},
{
"epoch": 0.568,
"grad_norm": 0.49232372641563416,
"learning_rate": 0.00018282559840976042,
"loss": 0.6996,
"step": 355
},
{
"epoch": 0.576,
"grad_norm": 0.47392791509628296,
"learning_rate": 0.00018235325976284275,
"loss": 0.773,
"step": 360
},
{
"epoch": 0.584,
"grad_norm": 0.5056615471839905,
"learning_rate": 0.00018187514128060946,
"loss": 0.728,
"step": 365
},
{
"epoch": 0.592,
"grad_norm": 0.5857616662979126,
"learning_rate": 0.00018139127651906184,
"loss": 0.7659,
"step": 370
},
{
"epoch": 0.6,
"grad_norm": 0.5966864228248596,
"learning_rate": 0.00018090169943749476,
"loss": 0.7039,
"step": 375
},
{
"epoch": 0.608,
"grad_norm": 0.4524347484111786,
"learning_rate": 0.00018040644439611348,
"loss": 0.7125,
"step": 380
},
{
"epoch": 0.616,
"grad_norm": 0.5570976138114929,
"learning_rate": 0.00017990554615362198,
"loss": 0.698,
"step": 385
},
{
"epoch": 0.624,
"grad_norm": 0.6045777201652527,
"learning_rate": 0.00017939903986478355,
"loss": 0.8255,
"step": 390
},
{
"epoch": 0.632,
"grad_norm": 0.6149687767028809,
"learning_rate": 0.00017888696107795342,
"loss": 0.6616,
"step": 395
},
{
"epoch": 0.64,
"grad_norm": 0.4873579144477844,
"learning_rate": 0.000178369345732584,
"loss": 0.7452,
"step": 400
},
{
"epoch": 0.648,
"grad_norm": 0.5569061636924744,
"learning_rate": 0.00017784623015670238,
"loss": 0.7652,
"step": 405
},
{
"epoch": 0.656,
"grad_norm": 0.5825181603431702,
"learning_rate": 0.00017731765106436073,
"loss": 0.7793,
"step": 410
},
{
"epoch": 0.664,
"grad_norm": 0.4047383666038513,
"learning_rate": 0.00017678364555305978,
"loss": 0.6875,
"step": 415
},
{
"epoch": 0.672,
"grad_norm": 0.5080836415290833,
"learning_rate": 0.0001762442511011448,
"loss": 0.7465,
"step": 420
},
{
"epoch": 0.68,
"grad_norm": 0.5825940370559692,
"learning_rate": 0.00017569950556517566,
"loss": 0.7205,
"step": 425
},
{
"epoch": 0.688,
"grad_norm": 0.476992666721344,
"learning_rate": 0.00017514944717726962,
"loss": 0.6589,
"step": 430
},
{
"epoch": 0.696,
"grad_norm": 0.7424727082252502,
"learning_rate": 0.00017459411454241822,
"loss": 0.7035,
"step": 435
},
{
"epoch": 0.704,
"grad_norm": 0.6544787287712097,
"learning_rate": 0.00017403354663577783,
"loss": 0.787,
"step": 440
},
{
"epoch": 0.712,
"grad_norm": 0.49425187706947327,
"learning_rate": 0.00017346778279993415,
"loss": 0.7515,
"step": 445
},
{
"epoch": 0.72,
"grad_norm": 0.5473236441612244,
"learning_rate": 0.00017289686274214118,
"loss": 0.7199,
"step": 450
},
{
"epoch": 0.728,
"grad_norm": 0.6773544549942017,
"learning_rate": 0.00017232082653153422,
"loss": 0.8037,
"step": 455
},
{
"epoch": 0.736,
"grad_norm": 0.6355096101760864,
"learning_rate": 0.00017173971459631787,
"loss": 0.7502,
"step": 460
},
{
"epoch": 0.744,
"grad_norm": 0.47867000102996826,
"learning_rate": 0.00017115356772092857,
"loss": 0.7446,
"step": 465
},
{
"epoch": 0.752,
"grad_norm": 0.5135357975959778,
"learning_rate": 0.0001705624270431721,
"loss": 0.6507,
"step": 470
},
{
"epoch": 0.76,
"grad_norm": 0.48866042494773865,
"learning_rate": 0.00016996633405133655,
"loss": 0.7164,
"step": 475
},
{
"epoch": 0.768,
"grad_norm": 0.5892354249954224,
"learning_rate": 0.0001693653305812805,
"loss": 0.7621,
"step": 480
},
{
"epoch": 0.776,
"grad_norm": 0.6633970141410828,
"learning_rate": 0.00016875945881349676,
"loss": 0.7623,
"step": 485
},
{
"epoch": 0.784,
"grad_norm": 0.6444060802459717,
"learning_rate": 0.000168148761270152,
"loss": 0.6606,
"step": 490
},
{
"epoch": 0.792,
"grad_norm": 0.7012648582458496,
"learning_rate": 0.00016753328081210245,
"loss": 0.6941,
"step": 495
},
{
"epoch": 0.8,
"grad_norm": 0.7064160704612732,
"learning_rate": 0.00016691306063588583,
"loss": 0.6841,
"step": 500
},
{
"epoch": 0.808,
"grad_norm": 0.7241398096084595,
"learning_rate": 0.00016628814427068953,
"loss": 0.6996,
"step": 505
},
{
"epoch": 0.816,
"grad_norm": 0.7807374596595764,
"learning_rate": 0.00016565857557529566,
"loss": 0.7542,
"step": 510
},
{
"epoch": 0.824,
"grad_norm": 0.763768196105957,
"learning_rate": 0.00016502439873500289,
"loss": 0.7175,
"step": 515
},
{
"epoch": 0.832,
"grad_norm": 0.6105090379714966,
"learning_rate": 0.0001643856582585254,
"loss": 0.7565,
"step": 520
},
{
"epoch": 0.84,
"grad_norm": 0.5686540603637695,
"learning_rate": 0.000163742398974869,
"loss": 0.7339,
"step": 525
},
{
"epoch": 0.848,
"grad_norm": 0.5341500043869019,
"learning_rate": 0.00016309466603018496,
"loss": 0.569,
"step": 530
},
{
"epoch": 0.856,
"grad_norm": 0.7274748682975769,
"learning_rate": 0.00016244250488460158,
"loss": 0.7556,
"step": 535
},
{
"epoch": 0.864,
"grad_norm": 0.7321165204048157,
"learning_rate": 0.00016178596130903344,
"loss": 0.7084,
"step": 540
},
{
"epoch": 0.872,
"grad_norm": 0.5086159110069275,
"learning_rate": 0.00016112508138196917,
"loss": 0.6935,
"step": 545
},
{
"epoch": 0.88,
"grad_norm": 0.4714389443397522,
"learning_rate": 0.0001604599114862375,
"loss": 0.7076,
"step": 550
},
{
"epoch": 0.888,
"grad_norm": 0.5031452178955078,
"learning_rate": 0.0001597904983057519,
"loss": 0.7151,
"step": 555
},
{
"epoch": 0.896,
"grad_norm": 0.7745943665504456,
"learning_rate": 0.0001591168888222342,
"loss": 0.7001,
"step": 560
},
{
"epoch": 0.904,
"grad_norm": 0.6076303124427795,
"learning_rate": 0.00015843913031191723,
"loss": 0.7285,
"step": 565
},
{
"epoch": 0.912,
"grad_norm": 0.7456529140472412,
"learning_rate": 0.00015775727034222675,
"loss": 0.8041,
"step": 570
},
{
"epoch": 0.92,
"grad_norm": 0.5760998725891113,
"learning_rate": 0.0001570713567684432,
"loss": 0.7353,
"step": 575
},
{
"epoch": 0.928,
"grad_norm": 0.7057327032089233,
"learning_rate": 0.00015638143773034267,
"loss": 0.7792,
"step": 580
},
{
"epoch": 0.936,
"grad_norm": 0.7615967392921448,
"learning_rate": 0.00015568756164881882,
"loss": 1.0121,
"step": 585
},
{
"epoch": 0.944,
"grad_norm": 0.6304950714111328,
"learning_rate": 0.000154989777222484,
"loss": 0.7727,
"step": 590
},
{
"epoch": 0.952,
"grad_norm": 0.6852543950080872,
"learning_rate": 0.00015428813342425177,
"loss": 0.741,
"step": 595
},
{
"epoch": 0.96,
"grad_norm": 0.6379660964012146,
"learning_rate": 0.00015358267949789966,
"loss": 0.6919,
"step": 600
},
{
"epoch": 0.968,
"grad_norm": 0.5846463441848755,
"learning_rate": 0.00015287346495461315,
"loss": 0.7163,
"step": 605
},
{
"epoch": 0.976,
"grad_norm": 0.5999557971954346,
"learning_rate": 0.0001521605395695108,
"loss": 0.8152,
"step": 610
},
{
"epoch": 0.984,
"grad_norm": 0.5806307196617126,
"learning_rate": 0.00015144395337815064,
"loss": 0.6709,
"step": 615
},
{
"epoch": 0.992,
"grad_norm": 0.6559942960739136,
"learning_rate": 0.00015072375667301893,
"loss": 0.6527,
"step": 620
},
{
"epoch": 1.0,
"grad_norm": 0.6287715435028076,
"learning_rate": 0.00015000000000000001,
"loss": 0.8194,
"step": 625
},
{
"epoch": 1.008,
"grad_norm": 0.616222620010376,
"learning_rate": 0.00014927273415482915,
"loss": 0.6627,
"step": 630
},
{
"epoch": 1.016,
"grad_norm": 0.4750412106513977,
"learning_rate": 0.0001485420101795274,
"loss": 0.6366,
"step": 635
},
{
"epoch": 1.024,
"grad_norm": 0.5122964978218079,
"learning_rate": 0.00014780787935881923,
"loss": 0.6717,
"step": 640
},
{
"epoch": 1.032,
"grad_norm": 0.7382633090019226,
"learning_rate": 0.0001470703932165333,
"loss": 0.6483,
"step": 645
},
{
"epoch": 1.04,
"grad_norm": 0.6540554761886597,
"learning_rate": 0.00014632960351198618,
"loss": 0.6151,
"step": 650
},
{
"epoch": 1.048,
"grad_norm": 0.4776591956615448,
"learning_rate": 0.00014558556223635003,
"loss": 0.6707,
"step": 655
},
{
"epoch": 1.056,
"grad_norm": 0.8012662529945374,
"learning_rate": 0.00014483832160900326,
"loss": 0.6125,
"step": 660
},
{
"epoch": 1.064,
"grad_norm": 0.6735953092575073,
"learning_rate": 0.00014408793407386588,
"loss": 0.6206,
"step": 665
},
{
"epoch": 1.072,
"grad_norm": 0.5640230774879456,
"learning_rate": 0.00014333445229571873,
"loss": 0.6161,
"step": 670
},
{
"epoch": 1.08,
"grad_norm": 0.5928654074668884,
"learning_rate": 0.00014257792915650728,
"loss": 0.6583,
"step": 675
},
{
"epoch": 1.088,
"grad_norm": 0.7347397208213806,
"learning_rate": 0.00014181841775163013,
"loss": 0.6222,
"step": 680
},
{
"epoch": 1.096,
"grad_norm": 0.593773365020752,
"learning_rate": 0.0001410559713862128,
"loss": 0.716,
"step": 685
},
{
"epoch": 1.104,
"grad_norm": 0.6244611144065857,
"learning_rate": 0.00014029064357136628,
"loss": 0.6198,
"step": 690
},
{
"epoch": 1.112,
"grad_norm": 0.5083370804786682,
"learning_rate": 0.00013952248802043165,
"loss": 0.6389,
"step": 695
},
{
"epoch": 1.12,
"grad_norm": 0.5241413116455078,
"learning_rate": 0.0001387515586452103,
"loss": 0.6842,
"step": 700
},
{
"epoch": 1.1280000000000001,
"grad_norm": 0.524029016494751,
"learning_rate": 0.00013797790955218014,
"loss": 0.6071,
"step": 705
},
{
"epoch": 1.1360000000000001,
"grad_norm": 0.5097878575325012,
"learning_rate": 0.00013720159503869815,
"loss": 0.5915,
"step": 710
},
{
"epoch": 1.144,
"grad_norm": 0.5782963037490845,
"learning_rate": 0.00013642266958918984,
"loss": 0.6794,
"step": 715
},
{
"epoch": 1.152,
"grad_norm": 0.6088266372680664,
"learning_rate": 0.00013564118787132506,
"loss": 0.6773,
"step": 720
},
{
"epoch": 1.16,
"grad_norm": 0.7768995761871338,
"learning_rate": 0.00013485720473218154,
"loss": 0.668,
"step": 725
},
{
"epoch": 1.168,
"grad_norm": 0.6645551919937134,
"learning_rate": 0.0001340707751943952,
"loss": 0.6997,
"step": 730
},
{
"epoch": 1.176,
"grad_norm": 0.9228842258453369,
"learning_rate": 0.00013328195445229868,
"loss": 0.831,
"step": 735
},
{
"epoch": 1.184,
"grad_norm": 0.7556049823760986,
"learning_rate": 0.00013249079786804765,
"loss": 0.6378,
"step": 740
},
{
"epoch": 1.192,
"grad_norm": 0.832775354385376,
"learning_rate": 0.0001316973609677352,
"loss": 0.6547,
"step": 745
},
{
"epoch": 1.2,
"grad_norm": 0.7329304814338684,
"learning_rate": 0.00013090169943749476,
"loss": 0.5808,
"step": 750
},
{
"epoch": 1.208,
"grad_norm": 0.7193475961685181,
"learning_rate": 0.00013010386911959206,
"loss": 0.5582,
"step": 755
},
{
"epoch": 1.216,
"grad_norm": 0.6274734735488892,
"learning_rate": 0.00012930392600850573,
"loss": 0.5801,
"step": 760
},
{
"epoch": 1.224,
"grad_norm": 0.6485865712165833,
"learning_rate": 0.0001285019262469976,
"loss": 0.65,
"step": 765
},
{
"epoch": 1.232,
"grad_norm": 0.7164427042007446,
"learning_rate": 0.00012769792612217224,
"loss": 0.6627,
"step": 770
},
{
"epoch": 1.24,
"grad_norm": 0.600775957107544,
"learning_rate": 0.00012689198206152657,
"loss": 0.5603,
"step": 775
},
{
"epoch": 1.248,
"grad_norm": 0.8377975225448608,
"learning_rate": 0.00012608415062898972,
"loss": 0.6525,
"step": 780
},
{
"epoch": 1.256,
"grad_norm": 0.8069924116134644,
"learning_rate": 0.00012527448852095295,
"loss": 0.6731,
"step": 785
},
{
"epoch": 1.264,
"grad_norm": 0.6501213908195496,
"learning_rate": 0.00012446305256229073,
"loss": 0.6255,
"step": 790
},
{
"epoch": 1.272,
"grad_norm": 0.62812340259552,
"learning_rate": 0.00012364989970237248,
"loss": 0.6585,
"step": 795
},
{
"epoch": 1.28,
"grad_norm": 0.5702307820320129,
"learning_rate": 0.00012283508701106557,
"loss": 0.5996,
"step": 800
},
{
"epoch": 1.288,
"grad_norm": 0.6311281323432922,
"learning_rate": 0.00012201867167473015,
"loss": 0.6355,
"step": 805
},
{
"epoch": 1.296,
"grad_norm": 0.5885419249534607,
"learning_rate": 0.00012120071099220549,
"loss": 0.6615,
"step": 810
},
{
"epoch": 1.304,
"grad_norm": 0.5239307284355164,
"learning_rate": 0.0001203812623707885,
"loss": 0.6096,
"step": 815
},
{
"epoch": 1.312,
"grad_norm": 0.6101869940757751,
"learning_rate": 0.00011956038332220483,
"loss": 0.5984,
"step": 820
},
{
"epoch": 1.32,
"grad_norm": 0.4395413100719452,
"learning_rate": 0.00011873813145857249,
"loss": 0.5569,
"step": 825
},
{
"epoch": 1.328,
"grad_norm": 0.8984820246696472,
"learning_rate": 0.00011791456448835825,
"loss": 0.7088,
"step": 830
},
{
"epoch": 1.336,
"grad_norm": 0.7709664106369019,
"learning_rate": 0.00011708974021232769,
"loss": 0.6731,
"step": 835
},
{
"epoch": 1.3439999999999999,
"grad_norm": 0.6782217025756836,
"learning_rate": 0.00011626371651948838,
"loss": 0.6188,
"step": 840
},
{
"epoch": 1.3519999999999999,
"grad_norm": 0.6427358984947205,
"learning_rate": 0.00011543655138302714,
"loss": 0.7004,
"step": 845
},
{
"epoch": 1.3599999999999999,
"grad_norm": 0.5902594923973083,
"learning_rate": 0.00011460830285624118,
"loss": 0.5884,
"step": 850
},
{
"epoch": 1.3679999999999999,
"grad_norm": 0.5935835838317871,
"learning_rate": 0.0001137790290684638,
"loss": 0.5739,
"step": 855
},
{
"epoch": 1.376,
"grad_norm": 0.6752728223800659,
"learning_rate": 0.00011294878822098469,
"loss": 0.6435,
"step": 860
},
{
"epoch": 1.384,
"grad_norm": 0.7927135825157166,
"learning_rate": 0.00011211763858296507,
"loss": 0.6897,
"step": 865
},
{
"epoch": 1.392,
"grad_norm": 0.714499294757843,
"learning_rate": 0.00011128563848734816,
"loss": 0.6641,
"step": 870
},
{
"epoch": 1.4,
"grad_norm": 0.7086356282234192,
"learning_rate": 0.00011045284632676536,
"loss": 0.6273,
"step": 875
},
{
"epoch": 1.408,
"grad_norm": 0.6125518679618835,
"learning_rate": 0.00010961932054943778,
"loss": 0.6437,
"step": 880
},
{
"epoch": 1.416,
"grad_norm": 0.5635287165641785,
"learning_rate": 0.00010878511965507434,
"loss": 0.6345,
"step": 885
},
{
"epoch": 1.424,
"grad_norm": 0.47936007380485535,
"learning_rate": 0.00010795030219076599,
"loss": 0.5913,
"step": 890
},
{
"epoch": 1.432,
"grad_norm": 0.7142558097839355,
"learning_rate": 0.00010711492674687671,
"loss": 0.6482,
"step": 895
},
{
"epoch": 1.44,
"grad_norm": 0.5252729058265686,
"learning_rate": 0.00010627905195293135,
"loss": 0.6165,
"step": 900
},
{
"epoch": 1.448,
"grad_norm": 0.896318793296814,
"learning_rate": 0.00010544273647350092,
"loss": 0.634,
"step": 905
},
{
"epoch": 1.456,
"grad_norm": 0.6029036045074463,
"learning_rate": 0.00010460603900408523,
"loss": 0.6509,
"step": 910
},
{
"epoch": 1.464,
"grad_norm": 0.6835671663284302,
"learning_rate": 0.00010376901826699348,
"loss": 0.6212,
"step": 915
},
{
"epoch": 1.472,
"grad_norm": 0.7098750472068787,
"learning_rate": 0.00010293173300722285,
"loss": 0.7305,
"step": 920
},
{
"epoch": 1.48,
"grad_norm": 0.675316333770752,
"learning_rate": 0.0001020942419883357,
"loss": 0.6685,
"step": 925
},
{
"epoch": 1.488,
"grad_norm": 0.6675406098365784,
"learning_rate": 0.00010125660398833528,
"loss": 0.6214,
"step": 930
},
{
"epoch": 1.496,
"grad_norm": 0.6629154682159424,
"learning_rate": 0.0001004188777955404,
"loss": 0.6035,
"step": 935
},
{
"epoch": 1.504,
"grad_norm": 0.7732692360877991,
"learning_rate": 9.958112220445963e-05,
"loss": 0.5868,
"step": 940
},
{
"epoch": 1.512,
"grad_norm": 0.6238484978675842,
"learning_rate": 9.874339601166473e-05,
"loss": 0.6003,
"step": 945
},
{
"epoch": 1.52,
"grad_norm": 0.6622412800788879,
"learning_rate": 9.790575801166432e-05,
"loss": 0.5854,
"step": 950
},
{
"epoch": 1.528,
"grad_norm": 0.7598085999488831,
"learning_rate": 9.706826699277718e-05,
"loss": 0.5882,
"step": 955
},
{
"epoch": 1.536,
"grad_norm": 0.8870390057563782,
"learning_rate": 9.623098173300654e-05,
"loss": 0.7187,
"step": 960
},
{
"epoch": 1.544,
"grad_norm": 0.702232837677002,
"learning_rate": 9.539396099591476e-05,
"loss": 0.6156,
"step": 965
},
{
"epoch": 1.552,
"grad_norm": 0.694139301776886,
"learning_rate": 9.455726352649911e-05,
"loss": 0.6488,
"step": 970
},
{
"epoch": 1.56,
"grad_norm": 0.5684956312179565,
"learning_rate": 9.372094804706867e-05,
"loss": 0.6601,
"step": 975
},
{
"epoch": 1.568,
"grad_norm": 0.6327118277549744,
"learning_rate": 9.288507325312335e-05,
"loss": 0.5968,
"step": 980
},
{
"epoch": 1.576,
"grad_norm": 0.5732144117355347,
"learning_rate": 9.204969780923403e-05,
"loss": 0.7034,
"step": 985
},
{
"epoch": 1.584,
"grad_norm": 0.7025273442268372,
"learning_rate": 9.121488034492569e-05,
"loss": 0.5973,
"step": 990
},
{
"epoch": 1.592,
"grad_norm": 0.9270740151405334,
"learning_rate": 9.038067945056227e-05,
"loss": 0.7877,
"step": 995
},
{
"epoch": 1.6,
"grad_norm": 0.6676818132400513,
"learning_rate": 8.954715367323468e-05,
"loss": 0.644,
"step": 1000
},
{
"epoch": 1.608,
"grad_norm": 0.6687547564506531,
"learning_rate": 8.871436151265184e-05,
"loss": 0.6678,
"step": 1005
},
{
"epoch": 1.616,
"grad_norm": 0.7400322556495667,
"learning_rate": 8.788236141703498e-05,
"loss": 0.6088,
"step": 1010
},
{
"epoch": 1.624,
"grad_norm": 0.5504963994026184,
"learning_rate": 8.705121177901532e-05,
"loss": 0.6219,
"step": 1015
},
{
"epoch": 1.6320000000000001,
"grad_norm": 0.8088738322257996,
"learning_rate": 8.62209709315362e-05,
"loss": 0.6698,
"step": 1020
},
{
"epoch": 1.6400000000000001,
"grad_norm": 0.7380816340446472,
"learning_rate": 8.539169714375885e-05,
"loss": 0.6207,
"step": 1025
},
{
"epoch": 1.6480000000000001,
"grad_norm": 0.6346850395202637,
"learning_rate": 8.456344861697289e-05,
"loss": 0.626,
"step": 1030
},
{
"epoch": 1.6560000000000001,
"grad_norm": 0.49918702244758606,
"learning_rate": 8.373628348051165e-05,
"loss": 0.6972,
"step": 1035
},
{
"epoch": 1.6640000000000001,
"grad_norm": 0.7200607657432556,
"learning_rate": 8.291025978767235e-05,
"loss": 0.6282,
"step": 1040
},
{
"epoch": 1.6720000000000002,
"grad_norm": 0.8350688815116882,
"learning_rate": 8.208543551164178e-05,
"loss": 0.6219,
"step": 1045
},
{
"epoch": 1.6800000000000002,
"grad_norm": 0.5957468748092651,
"learning_rate": 8.126186854142752e-05,
"loss": 0.622,
"step": 1050
},
{
"epoch": 1.688,
"grad_norm": 0.7494757175445557,
"learning_rate": 8.04396166777952e-05,
"loss": 0.5801,
"step": 1055
},
{
"epoch": 1.696,
"grad_norm": 0.7109113931655884,
"learning_rate": 7.961873762921153e-05,
"loss": 0.598,
"step": 1060
},
{
"epoch": 1.704,
"grad_norm": 0.7941219210624695,
"learning_rate": 7.879928900779456e-05,
"loss": 0.699,
"step": 1065
},
{
"epoch": 1.712,
"grad_norm": 0.7282152771949768,
"learning_rate": 7.798132832526986e-05,
"loss": 0.5882,
"step": 1070
},
{
"epoch": 1.72,
"grad_norm": 0.5923735499382019,
"learning_rate": 7.716491298893442e-05,
"loss": 0.5321,
"step": 1075
},
{
"epoch": 1.728,
"grad_norm": 0.5571523308753967,
"learning_rate": 7.635010029762756e-05,
"loss": 0.6647,
"step": 1080
},
{
"epoch": 1.736,
"grad_norm": 0.6043043732643127,
"learning_rate": 7.553694743770928e-05,
"loss": 0.628,
"step": 1085
},
{
"epoch": 1.744,
"grad_norm": 0.8733720183372498,
"learning_rate": 7.472551147904708e-05,
"loss": 0.6262,
"step": 1090
},
{
"epoch": 1.752,
"grad_norm": 0.5561848878860474,
"learning_rate": 7.391584937101033e-05,
"loss": 0.6131,
"step": 1095
},
{
"epoch": 1.76,
"grad_norm": 0.6611356735229492,
"learning_rate": 7.310801793847344e-05,
"loss": 0.6494,
"step": 1100
},
{
"epoch": 1.768,
"grad_norm": 0.5700333714485168,
"learning_rate": 7.230207387782776e-05,
"loss": 0.5514,
"step": 1105
},
{
"epoch": 1.776,
"grad_norm": 0.705662727355957,
"learning_rate": 7.149807375300239e-05,
"loss": 0.5823,
"step": 1110
},
{
"epoch": 1.784,
"grad_norm": 0.9632449150085449,
"learning_rate": 7.069607399149428e-05,
"loss": 0.7207,
"step": 1115
},
{
"epoch": 1.792,
"grad_norm": 0.6412242650985718,
"learning_rate": 6.989613088040796e-05,
"loss": 0.7006,
"step": 1120
},
{
"epoch": 1.8,
"grad_norm": 0.538044273853302,
"learning_rate": 6.909830056250527e-05,
"loss": 0.6222,
"step": 1125
},
{
"epoch": 1.808,
"grad_norm": 0.6124762296676636,
"learning_rate": 6.830263903226483e-05,
"loss": 0.6569,
"step": 1130
},
{
"epoch": 1.8159999999999998,
"grad_norm": 0.7250857949256897,
"learning_rate": 6.750920213195238e-05,
"loss": 0.543,
"step": 1135
},
{
"epoch": 1.8239999999999998,
"grad_norm": 0.6840488910675049,
"learning_rate": 6.671804554770135e-05,
"loss": 0.6334,
"step": 1140
},
{
"epoch": 1.8319999999999999,
"grad_norm": 0.8932304382324219,
"learning_rate": 6.592922480560483e-05,
"loss": 0.6701,
"step": 1145
},
{
"epoch": 1.8399999999999999,
"grad_norm": 0.9220761656761169,
"learning_rate": 6.51427952678185e-05,
"loss": 0.6216,
"step": 1150
},
{
"epoch": 1.8479999999999999,
"grad_norm": 0.688731849193573,
"learning_rate": 6.435881212867493e-05,
"loss": 0.5877,
"step": 1155
},
{
"epoch": 1.8559999999999999,
"grad_norm": 0.6370134949684143,
"learning_rate": 6.357733041081018e-05,
"loss": 0.6256,
"step": 1160
},
{
"epoch": 1.8639999999999999,
"grad_norm": 0.7421153783798218,
"learning_rate": 6.27984049613019e-05,
"loss": 0.7062,
"step": 1165
},
{
"epoch": 1.8719999999999999,
"grad_norm": 0.8129108548164368,
"learning_rate": 6.20220904478199e-05,
"loss": 0.6304,
"step": 1170
},
{
"epoch": 1.88,
"grad_norm": 0.7866687774658203,
"learning_rate": 6.12484413547897e-05,
"loss": 0.7695,
"step": 1175
},
{
"epoch": 1.888,
"grad_norm": 0.8307198882102966,
"learning_rate": 6.047751197956838e-05,
"loss": 0.5723,
"step": 1180
},
{
"epoch": 1.896,
"grad_norm": 0.5541536211967468,
"learning_rate": 5.9709356428633746e-05,
"loss": 0.6847,
"step": 1185
},
{
"epoch": 1.904,
"grad_norm": 0.731555163860321,
"learning_rate": 5.8944028613787206e-05,
"loss": 0.6618,
"step": 1190
},
{
"epoch": 1.912,
"grad_norm": 1.020991325378418,
"learning_rate": 5.818158224836987e-05,
"loss": 0.6275,
"step": 1195
},
{
"epoch": 1.92,
"grad_norm": 0.7172287702560425,
"learning_rate": 5.7422070843492734e-05,
"loss": 0.5617,
"step": 1200
},
{
"epoch": 1.928,
"grad_norm": 0.7232096791267395,
"learning_rate": 5.666554770428129e-05,
"loss": 0.6278,
"step": 1205
},
{
"epoch": 1.936,
"grad_norm": 0.7234194278717041,
"learning_rate": 5.591206592613416e-05,
"loss": 0.6713,
"step": 1210
},
{
"epoch": 1.944,
"grad_norm": 0.6906010508537292,
"learning_rate": 5.5161678390996796e-05,
"loss": 0.6113,
"step": 1215
},
{
"epoch": 1.952,
"grad_norm": 0.9057906270027161,
"learning_rate": 5.441443776365003e-05,
"loss": 0.5587,
"step": 1220
},
{
"epoch": 1.96,
"grad_norm": 0.7144932150840759,
"learning_rate": 5.3670396488013854e-05,
"loss": 0.5601,
"step": 1225
},
{
"epoch": 1.968,
"grad_norm": 1.0071252584457397,
"learning_rate": 5.292960678346675e-05,
"loss": 0.5941,
"step": 1230
},
{
"epoch": 1.976,
"grad_norm": 0.7061260342597961,
"learning_rate": 5.2192120641180786e-05,
"loss": 0.6285,
"step": 1235
},
{
"epoch": 1.984,
"grad_norm": 0.6937069892883301,
"learning_rate": 5.145798982047261e-05,
"loss": 0.6516,
"step": 1240
},
{
"epoch": 1.992,
"grad_norm": 0.5176392793655396,
"learning_rate": 5.072726584517086e-05,
"loss": 0.5904,
"step": 1245
},
{
"epoch": 2.0,
"grad_norm": 0.8501409292221069,
"learning_rate": 5.000000000000002e-05,
"loss": 0.619,
"step": 1250
},
{
"epoch": 2.008,
"grad_norm": 0.5451085567474365,
"learning_rate": 4.927624332698109e-05,
"loss": 0.6058,
"step": 1255
},
{
"epoch": 2.016,
"grad_norm": 0.8410437107086182,
"learning_rate": 4.8556046621849346e-05,
"loss": 0.6248,
"step": 1260
},
{
"epoch": 2.024,
"grad_norm": 0.6089378595352173,
"learning_rate": 4.783946043048923e-05,
"loss": 0.5247,
"step": 1265
},
{
"epoch": 2.032,
"grad_norm": 0.47437986731529236,
"learning_rate": 4.712653504538683e-05,
"loss": 0.5439,
"step": 1270
},
{
"epoch": 2.04,
"grad_norm": 0.6925654411315918,
"learning_rate": 4.6417320502100316e-05,
"loss": 0.4491,
"step": 1275
},
{
"epoch": 2.048,
"grad_norm": 0.8538162708282471,
"learning_rate": 4.5711866575748276e-05,
"loss": 0.52,
"step": 1280
},
{
"epoch": 2.056,
"grad_norm": 0.8048768639564514,
"learning_rate": 4.501022277751602e-05,
"loss": 0.5259,
"step": 1285
},
{
"epoch": 2.064,
"grad_norm": 0.7191641330718994,
"learning_rate": 4.431243835118124e-05,
"loss": 0.5025,
"step": 1290
},
{
"epoch": 2.072,
"grad_norm": 1.0918892621994019,
"learning_rate": 4.361856226965733e-05,
"loss": 0.4772,
"step": 1295
},
{
"epoch": 2.08,
"grad_norm": 0.8152824640274048,
"learning_rate": 4.2928643231556844e-05,
"loss": 0.5945,
"step": 1300
},
{
"epoch": 2.088,
"grad_norm": 0.640073299407959,
"learning_rate": 4.224272965777326e-05,
"loss": 0.4813,
"step": 1305
},
{
"epoch": 2.096,
"grad_norm": 0.7172432541847229,
"learning_rate": 4.15608696880828e-05,
"loss": 0.5315,
"step": 1310
},
{
"epoch": 2.104,
"grad_norm": 1.1283674240112305,
"learning_rate": 4.08831111777658e-05,
"loss": 0.5591,
"step": 1315
},
{
"epoch": 2.112,
"grad_norm": 0.8184736967086792,
"learning_rate": 4.020950169424815e-05,
"loss": 0.605,
"step": 1320
},
{
"epoch": 2.12,
"grad_norm": 0.6823618412017822,
"learning_rate": 3.954008851376252e-05,
"loss": 0.4955,
"step": 1325
},
{
"epoch": 2.128,
"grad_norm": 0.8576385378837585,
"learning_rate": 3.887491861803085e-05,
"loss": 0.5757,
"step": 1330
},
{
"epoch": 2.136,
"grad_norm": 0.967835009098053,
"learning_rate": 3.821403869096658e-05,
"loss": 0.5313,
"step": 1335
},
{
"epoch": 2.144,
"grad_norm": 0.7330173254013062,
"learning_rate": 3.755749511539845e-05,
"loss": 0.5904,
"step": 1340
},
{
"epoch": 2.152,
"grad_norm": 0.6664792895317078,
"learning_rate": 3.690533396981504e-05,
"loss": 0.4679,
"step": 1345
},
{
"epoch": 2.16,
"grad_norm": 0.7639065980911255,
"learning_rate": 3.6257601025131026e-05,
"loss": 0.5235,
"step": 1350
},
{
"epoch": 2.168,
"grad_norm": 0.6960520148277283,
"learning_rate": 3.561434174147463e-05,
"loss": 0.5797,
"step": 1355
},
{
"epoch": 2.176,
"grad_norm": 0.8231356143951416,
"learning_rate": 3.497560126499709e-05,
"loss": 0.5772,
"step": 1360
},
{
"epoch": 2.184,
"grad_norm": 0.8968437910079956,
"learning_rate": 3.4341424424704375e-05,
"loss": 0.5316,
"step": 1365
},
{
"epoch": 2.192,
"grad_norm": 0.8037480711936951,
"learning_rate": 3.371185572931048e-05,
"loss": 0.5646,
"step": 1370
},
{
"epoch": 2.2,
"grad_norm": 0.9330148696899414,
"learning_rate": 3.308693936411421e-05,
"loss": 0.5431,
"step": 1375
},
{
"epoch": 2.208,
"grad_norm": 0.6958775520324707,
"learning_rate": 3.246671918789755e-05,
"loss": 0.5403,
"step": 1380
},
{
"epoch": 2.216,
"grad_norm": 0.9870476126670837,
"learning_rate": 3.1851238729848034e-05,
"loss": 0.5329,
"step": 1385
},
{
"epoch": 2.224,
"grad_norm": 0.5036590099334717,
"learning_rate": 3.124054118650327e-05,
"loss": 0.5696,
"step": 1390
},
{
"epoch": 2.232,
"grad_norm": 0.8640053868293762,
"learning_rate": 3.063466941871952e-05,
"loss": 0.59,
"step": 1395
},
{
"epoch": 2.24,
"grad_norm": 0.6065173149108887,
"learning_rate": 3.0033665948663448e-05,
"loss": 0.5116,
"step": 1400
},
{
"epoch": 2.248,
"grad_norm": 1.083775520324707,
"learning_rate": 2.9437572956827964e-05,
"loss": 0.5783,
"step": 1405
},
{
"epoch": 2.2560000000000002,
"grad_norm": 0.7090497016906738,
"learning_rate": 2.8846432279071467e-05,
"loss": 0.6259,
"step": 1410
},
{
"epoch": 2.2640000000000002,
"grad_norm": 0.742468535900116,
"learning_rate": 2.826028540368215e-05,
"loss": 0.5759,
"step": 1415
},
{
"epoch": 2.2720000000000002,
"grad_norm": 0.9219839572906494,
"learning_rate": 2.7679173468465812e-05,
"loss": 0.497,
"step": 1420
},
{
"epoch": 2.2800000000000002,
"grad_norm": 0.7159206867218018,
"learning_rate": 2.7103137257858868e-05,
"loss": 0.619,
"step": 1425
},
{
"epoch": 2.288,
"grad_norm": 0.6997727751731873,
"learning_rate": 2.6532217200065858e-05,
"loss": 0.5858,
"step": 1430
},
{
"epoch": 2.296,
"grad_norm": 0.7493643164634705,
"learning_rate": 2.5966453364222186e-05,
"loss": 0.6291,
"step": 1435
},
{
"epoch": 2.304,
"grad_norm": 0.8311699032783508,
"learning_rate": 2.540588545758179e-05,
"loss": 0.6418,
"step": 1440
},
{
"epoch": 2.312,
"grad_norm": 0.7084354758262634,
"learning_rate": 2.48505528227304e-05,
"loss": 0.5483,
"step": 1445
},
{
"epoch": 2.32,
"grad_norm": 0.734438955783844,
"learning_rate": 2.4300494434824373e-05,
"loss": 0.6071,
"step": 1450
},
{
"epoch": 2.328,
"grad_norm": 0.8913635015487671,
"learning_rate": 2.37557488988552e-05,
"loss": 0.5099,
"step": 1455
},
{
"epoch": 2.336,
"grad_norm": 0.8349048495292664,
"learning_rate": 2.321635444694028e-05,
"loss": 0.5186,
"step": 1460
},
{
"epoch": 2.344,
"grad_norm": 0.6164011359214783,
"learning_rate": 2.2682348935639274e-05,
"loss": 0.5043,
"step": 1465
},
{
"epoch": 2.352,
"grad_norm": 1.044892430305481,
"learning_rate": 2.2153769843297667e-05,
"loss": 0.61,
"step": 1470
},
{
"epoch": 2.36,
"grad_norm": 0.9142879247665405,
"learning_rate": 2.163065426741603e-05,
"loss": 0.5987,
"step": 1475
},
{
"epoch": 2.368,
"grad_norm": 0.6232836842536926,
"learning_rate": 2.1113038922046602e-05,
"loss": 0.5212,
"step": 1480
},
{
"epoch": 2.376,
"grad_norm": 0.49558231234550476,
"learning_rate": 2.0600960135216462e-05,
"loss": 0.4796,
"step": 1485
},
{
"epoch": 2.384,
"grad_norm": 0.7887687683105469,
"learning_rate": 2.009445384637805e-05,
"loss": 0.4844,
"step": 1490
},
{
"epoch": 2.392,
"grad_norm": 0.8086990714073181,
"learning_rate": 1.9593555603886538e-05,
"loss": 0.5085,
"step": 1495
},
{
"epoch": 2.4,
"grad_norm": 0.6713303327560425,
"learning_rate": 1.9098300562505266e-05,
"loss": 0.4839,
"step": 1500
},
{
"epoch": 2.408,
"grad_norm": 0.6262741684913635,
"learning_rate": 1.8608723480938206e-05,
"loss": 0.5715,
"step": 1505
},
{
"epoch": 2.416,
"grad_norm": 0.8025808334350586,
"learning_rate": 1.812485871939056e-05,
"loss": 0.5266,
"step": 1510
},
{
"epoch": 2.424,
"grad_norm": 0.8753231167793274,
"learning_rate": 1.7646740237157256e-05,
"loss": 0.5422,
"step": 1515
},
{
"epoch": 2.432,
"grad_norm": 0.6459301710128784,
"learning_rate": 1.7174401590239587e-05,
"loss": 0.5553,
"step": 1520
},
{
"epoch": 2.44,
"grad_norm": 0.6917416453361511,
"learning_rate": 1.6707875928990058e-05,
"loss": 0.5765,
"step": 1525
},
{
"epoch": 2.448,
"grad_norm": 0.7890029549598694,
"learning_rate": 1.6247195995785837e-05,
"loss": 0.549,
"step": 1530
},
{
"epoch": 2.456,
"grad_norm": 0.9913660883903503,
"learning_rate": 1.579239412273078e-05,
"loss": 0.4876,
"step": 1535
},
{
"epoch": 2.464,
"grad_norm": 0.9030985832214355,
"learning_rate": 1.5343502229386207e-05,
"loss": 0.5546,
"step": 1540
},
{
"epoch": 2.472,
"grad_norm": 0.9133403301239014,
"learning_rate": 1.4900551820530828e-05,
"loss": 0.5356,
"step": 1545
},
{
"epoch": 2.48,
"grad_norm": 0.7083793878555298,
"learning_rate": 1.4463573983949341e-05,
"loss": 0.5142,
"step": 1550
},
{
"epoch": 2.488,
"grad_norm": 1.095435619354248,
"learning_rate": 1.40325993882509e-05,
"loss": 0.6054,
"step": 1555
},
{
"epoch": 2.496,
"grad_norm": 0.8825190663337708,
"learning_rate": 1.3607658280716473e-05,
"loss": 0.5294,
"step": 1560
},
{
"epoch": 2.504,
"grad_norm": 0.9436343908309937,
"learning_rate": 1.3188780485176088e-05,
"loss": 0.5294,
"step": 1565
},
{
"epoch": 2.512,
"grad_norm": 1.0125439167022705,
"learning_rate": 1.2775995399915631e-05,
"loss": 0.4905,
"step": 1570
},
{
"epoch": 2.52,
"grad_norm": 0.8476350903511047,
"learning_rate": 1.2369331995613665e-05,
"loss": 0.5186,
"step": 1575
},
{
"epoch": 2.528,
"grad_norm": 0.9092681407928467,
"learning_rate": 1.196881881330798e-05,
"loss": 0.4909,
"step": 1580
},
{
"epoch": 2.536,
"grad_norm": 0.7970360517501831,
"learning_rate": 1.1574483962392767e-05,
"loss": 0.5303,
"step": 1585
},
{
"epoch": 2.544,
"grad_norm": 0.8575041890144348,
"learning_rate": 1.1186355118645554e-05,
"loss": 0.5169,
"step": 1590
},
{
"epoch": 2.552,
"grad_norm": 0.7397408485412598,
"learning_rate": 1.0804459522284926e-05,
"loss": 0.5339,
"step": 1595
},
{
"epoch": 2.56,
"grad_norm": 0.7415968179702759,
"learning_rate": 1.042882397605871e-05,
"loss": 0.5283,
"step": 1600
},
{
"epoch": 2.568,
"grad_norm": 0.7035180926322937,
"learning_rate": 1.0059474843362892e-05,
"loss": 0.5576,
"step": 1605
},
{
"epoch": 2.576,
"grad_norm": 0.9805112481117249,
"learning_rate": 9.696438046391288e-06,
"loss": 0.5136,
"step": 1610
},
{
"epoch": 2.584,
"grad_norm": 0.6661838889122009,
"learning_rate": 9.339739064316233e-06,
"loss": 0.5885,
"step": 1615
},
{
"epoch": 2.592,
"grad_norm": 0.8581559062004089,
"learning_rate": 8.989402931500434e-06,
"loss": 0.5,
"step": 1620
},
{
"epoch": 2.6,
"grad_norm": 0.7146279811859131,
"learning_rate": 8.645454235739903e-06,
"loss": 0.5325,
"step": 1625
},
{
"epoch": 2.608,
"grad_norm": 0.9474234580993652,
"learning_rate": 8.307917116538378e-06,
"loss": 0.5772,
"step": 1630
},
{
"epoch": 2.616,
"grad_norm": 0.9583209753036499,
"learning_rate": 7.976815263412963e-06,
"loss": 0.5736,
"step": 1635
},
{
"epoch": 2.624,
"grad_norm": 0.7156705260276794,
"learning_rate": 7.652171914231776e-06,
"loss": 0.5199,
"step": 1640
},
{
"epoch": 2.632,
"grad_norm": 0.8224849700927734,
"learning_rate": 7.3340098535827905e-06,
"loss": 0.5753,
"step": 1645
},
{
"epoch": 2.64,
"grad_norm": 0.8689257502555847,
"learning_rate": 7.022351411174866e-06,
"loss": 0.5424,
"step": 1650
},
{
"epoch": 2.648,
"grad_norm": 0.6636053323745728,
"learning_rate": 6.717218460270536e-06,
"loss": 0.5555,
"step": 1655
},
{
"epoch": 2.656,
"grad_norm": 0.8688860535621643,
"learning_rate": 6.418632416150927e-06,
"loss": 0.4936,
"step": 1660
},
{
"epoch": 2.664,
"grad_norm": 0.6272854208946228,
"learning_rate": 6.126614234612593e-06,
"loss": 0.6291,
"step": 1665
},
{
"epoch": 2.672,
"grad_norm": 1.2240337133407593,
"learning_rate": 5.8411844104969916e-06,
"loss": 0.5197,
"step": 1670
},
{
"epoch": 2.68,
"grad_norm": 0.9820936918258667,
"learning_rate": 5.562362976251901e-06,
"loss": 0.5398,
"step": 1675
},
{
"epoch": 2.6879999999999997,
"grad_norm": 1.1582359075546265,
"learning_rate": 5.290169500525577e-06,
"loss": 0.6059,
"step": 1680
},
{
"epoch": 2.6959999999999997,
"grad_norm": 0.5501114726066589,
"learning_rate": 5.024623086793323e-06,
"loss": 0.531,
"step": 1685
},
{
"epoch": 2.7039999999999997,
"grad_norm": 0.8848717212677002,
"learning_rate": 4.765742372016735e-06,
"loss": 0.6054,
"step": 1690
},
{
"epoch": 2.7119999999999997,
"grad_norm": 0.7358693480491638,
"learning_rate": 4.513545525335705e-06,
"loss": 0.5173,
"step": 1695
},
{
"epoch": 2.7199999999999998,
"grad_norm": 0.9218215942382812,
"learning_rate": 4.268050246793276e-06,
"loss": 0.4944,
"step": 1700
},
{
"epoch": 2.7279999999999998,
"grad_norm": 0.6374716758728027,
"learning_rate": 4.029273766093333e-06,
"loss": 0.5183,
"step": 1705
},
{
"epoch": 2.7359999999999998,
"grad_norm": 0.583243191242218,
"learning_rate": 3.797232841391407e-06,
"loss": 0.668,
"step": 1710
},
{
"epoch": 2.7439999999999998,
"grad_norm": 0.8384690284729004,
"learning_rate": 3.5719437581185454e-06,
"loss": 0.5068,
"step": 1715
},
{
"epoch": 2.752,
"grad_norm": 0.8034130334854126,
"learning_rate": 3.3534223278382405e-06,
"loss": 0.5823,
"step": 1720
},
{
"epoch": 2.76,
"grad_norm": 0.8146041631698608,
"learning_rate": 3.1416838871368924e-06,
"loss": 0.6111,
"step": 1725
},
{
"epoch": 2.768,
"grad_norm": 0.8122982382774353,
"learning_rate": 2.936743296547273e-06,
"loss": 0.5231,
"step": 1730
},
{
"epoch": 2.776,
"grad_norm": 0.7326982021331787,
"learning_rate": 2.738614939505646e-06,
"loss": 0.5236,
"step": 1735
},
{
"epoch": 2.784,
"grad_norm": 0.7472147345542908,
"learning_rate": 2.5473127213422763e-06,
"loss": 0.5657,
"step": 1740
},
{
"epoch": 2.792,
"grad_norm": 0.8197700381278992,
"learning_rate": 2.3628500683055222e-06,
"loss": 0.5518,
"step": 1745
},
{
"epoch": 2.8,
"grad_norm": 0.8733732104301453,
"learning_rate": 2.1852399266194314e-06,
"loss": 0.4908,
"step": 1750
},
{
"epoch": 2.808,
"grad_norm": 0.8913092017173767,
"learning_rate": 2.014494761575314e-06,
"loss": 0.5459,
"step": 1755
},
{
"epoch": 2.816,
"grad_norm": 1.1259772777557373,
"learning_rate": 1.8506265566567094e-06,
"loss": 0.5208,
"step": 1760
},
{
"epoch": 2.824,
"grad_norm": 0.7692184448242188,
"learning_rate": 1.6936468126984572e-06,
"loss": 0.5824,
"step": 1765
},
{
"epoch": 2.832,
"grad_norm": 0.588602602481842,
"learning_rate": 1.543566547079467e-06,
"loss": 0.5512,
"step": 1770
},
{
"epoch": 2.84,
"grad_norm": 0.6324055790901184,
"learning_rate": 1.400396292949513e-06,
"loss": 0.6327,
"step": 1775
},
{
"epoch": 2.848,
"grad_norm": 0.7608378529548645,
"learning_rate": 1.26414609848996e-06,
"loss": 0.5292,
"step": 1780
},
{
"epoch": 2.856,
"grad_norm": 0.7972851395606995,
"learning_rate": 1.134825526208605e-06,
"loss": 0.5692,
"step": 1785
},
{
"epoch": 2.864,
"grad_norm": 0.9705446362495422,
"learning_rate": 1.0124436522684243e-06,
"loss": 0.5532,
"step": 1790
},
{
"epoch": 2.872,
"grad_norm": 0.6317399144172668,
"learning_rate": 8.970090658507291e-07,
"loss": 0.5314,
"step": 1795
},
{
"epoch": 2.88,
"grad_norm": 0.6457757949829102,
"learning_rate": 7.885298685522235e-07,
"loss": 0.524,
"step": 1800
},
{
"epoch": 2.888,
"grad_norm": 0.8593656420707703,
"learning_rate": 6.870136738164612e-07,
"loss": 0.5227,
"step": 1805
},
{
"epoch": 2.896,
"grad_norm": 1.0187020301818848,
"learning_rate": 5.924676063995382e-07,
"loss": 0.5993,
"step": 1810
},
{
"epoch": 2.904,
"grad_norm": 0.7082214951515198,
"learning_rate": 5.048983018699827e-07,
"loss": 0.5618,
"step": 1815
},
{
"epoch": 2.912,
"grad_norm": 0.6521438956260681,
"learning_rate": 4.2431190614309335e-07,
"loss": 0.5504,
"step": 1820
},
{
"epoch": 2.92,
"grad_norm": 0.8906036615371704,
"learning_rate": 3.50714075049563e-07,
"loss": 0.5147,
"step": 1825
},
{
"epoch": 2.928,
"grad_norm": 1.0908008813858032,
"learning_rate": 2.841099739386066e-07,
"loss": 0.5564,
"step": 1830
},
{
"epoch": 2.936,
"grad_norm": 0.6374122500419617,
"learning_rate": 2.2450427731534053e-07,
"loss": 0.5188,
"step": 1835
},
{
"epoch": 2.944,
"grad_norm": 0.9616740345954895,
"learning_rate": 1.7190116851280026e-07,
"loss": 0.5438,
"step": 1840
},
{
"epoch": 2.952,
"grad_norm": 1.0712924003601074,
"learning_rate": 1.2630433939825327e-07,
"loss": 0.4962,
"step": 1845
},
{
"epoch": 2.96,
"grad_norm": 0.8226613998413086,
"learning_rate": 8.771699011416168e-08,
"loss": 0.5021,
"step": 1850
},
{
"epoch": 2.968,
"grad_norm": 0.9519492983818054,
"learning_rate": 5.6141828853573106e-08,
"loss": 0.5277,
"step": 1855
},
{
"epoch": 2.976,
"grad_norm": 0.9817518591880798,
"learning_rate": 3.1581071670006015e-08,
"loss": 0.5764,
"step": 1860
},
{
"epoch": 2.984,
"grad_norm": 0.7039242386817932,
"learning_rate": 1.4036442321962995e-08,
"loss": 0.5408,
"step": 1865
},
{
"epoch": 2.992,
"grad_norm": 0.591012179851532,
"learning_rate": 3.509172151938689e-09,
"loss": 0.5014,
"step": 1870
},
{
"epoch": 3.0,
"grad_norm": 0.7672661542892456,
"learning_rate": 0.0,
"loss": 0.6182,
"step": 1875
},
{
"epoch": 3.0,
"step": 1875,
"total_flos": 1.1764404625814323e+17,
"train_loss": 0.6465437274932861,
"train_runtime": 2365.2475,
"train_samples_per_second": 12.684,
"train_steps_per_second": 0.793
}
],
"logging_steps": 5,
"max_steps": 1875,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1764404625814323e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}