{
  "best_metric": 0.22815725207328796,
  "best_model_checkpoint": "./xlam_lora_new_ete_over_size_3epoch_multi_mix/checkpoint-820",
  "epoch": 1.3348934221905682,
  "eval_steps": 205,
  "global_step": 820,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016279188075494735,
      "grad_norm": 0.7572630643844604,
      "learning_rate": 2.688172043010753e-06,
      "loss": 0.5223,
      "step": 10
    },
    {
      "epoch": 0.03255837615098947,
      "grad_norm": 0.417061984539032,
      "learning_rate": 5.376344086021506e-06,
      "loss": 0.4858,
      "step": 20
    },
    {
      "epoch": 0.048837564226484206,
      "grad_norm": 0.3718095123767853,
      "learning_rate": 8.064516129032258e-06,
      "loss": 0.4246,
      "step": 30
    },
    {
      "epoch": 0.06511675230197894,
      "grad_norm": 0.2949349582195282,
      "learning_rate": 1.0752688172043012e-05,
      "loss": 0.4405,
      "step": 40
    },
    {
      "epoch": 0.08139594037747368,
      "grad_norm": 0.3159159719944,
      "learning_rate": 1.3440860215053763e-05,
      "loss": 0.4148,
      "step": 50
    },
    {
      "epoch": 0.09767512845296841,
      "grad_norm": 0.4167034327983856,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 0.3393,
      "step": 60
    },
    {
      "epoch": 0.11395431652846315,
      "grad_norm": 0.39410400390625,
      "learning_rate": 1.881720430107527e-05,
      "loss": 0.2464,
      "step": 70
    },
    {
      "epoch": 0.13023350460395788,
      "grad_norm": 0.3644021153450012,
      "learning_rate": 2.1505376344086024e-05,
      "loss": 0.2294,
      "step": 80
    },
    {
      "epoch": 0.1465126926794526,
      "grad_norm": 0.30372634530067444,
      "learning_rate": 2.4193548387096777e-05,
      "loss": 0.2315,
      "step": 90
    },
    {
      "epoch": 0.16279188075494735,
      "grad_norm": 0.2586315870285034,
      "learning_rate": 2.4999011923655086e-05,
      "loss": 0.1932,
      "step": 100
    },
    {
      "epoch": 0.17907106883044208,
      "grad_norm": 0.37825971841812134,
      "learning_rate": 2.4994172742085852e-05,
      "loss": 0.2204,
      "step": 110
    },
    {
      "epoch": 0.19535025690593683,
      "grad_norm": 0.21422357857227325,
      "learning_rate": 2.4985302531208654e-05,
      "loss": 0.1795,
      "step": 120
    },
    {
      "epoch": 0.21162944498143155,
      "grad_norm": 0.2566869854927063,
      "learning_rate": 2.4972404152844008e-05,
      "loss": 0.1668,
      "step": 130
    },
    {
      "epoch": 0.2279086330569263,
      "grad_norm": 0.28194501996040344,
      "learning_rate": 2.49554817684312e-05,
      "loss": 0.1476,
      "step": 140
    },
    {
      "epoch": 0.24418782113242102,
      "grad_norm": 0.24139340221881866,
      "learning_rate": 2.4934540837685647e-05,
      "loss": 0.1609,
      "step": 150
    },
    {
      "epoch": 0.26046700920791577,
      "grad_norm": 0.3306334614753723,
      "learning_rate": 2.490958811683741e-05,
      "loss": 0.1638,
      "step": 160
    },
    {
      "epoch": 0.2767461972834105,
      "grad_norm": 0.27301114797592163,
      "learning_rate": 2.4880631656451447e-05,
      "loss": 0.1494,
      "step": 170
    },
    {
      "epoch": 0.2930253853589052,
      "grad_norm": 0.34037259221076965,
      "learning_rate": 2.484768079883018e-05,
      "loss": 0.1534,
      "step": 180
    },
    {
      "epoch": 0.30930457343439993,
      "grad_norm": 0.2306762933731079,
      "learning_rate": 2.4810746174999418e-05,
      "loss": 0.1749,
      "step": 190
    },
    {
      "epoch": 0.3255837615098947,
      "grad_norm": 0.3183388113975525,
      "learning_rate": 2.476983970127841e-05,
      "loss": 0.1482,
      "step": 200
    },
    {
      "epoch": 0.33372335554764204,
      "eval_loss": 0.3089325428009033,
      "eval_runtime": 34.8769,
      "eval_samples_per_second": 5.419,
      "eval_steps_per_second": 5.419,
      "step": 205
    },
    {
      "epoch": 0.34186294958538943,
      "grad_norm": 0.28704971075057983,
      "learning_rate": 2.472497457543525e-05,
      "loss": 0.1471,
      "step": 210
    },
    {
      "epoch": 0.35814213766088415,
      "grad_norm": 0.2939195930957794,
      "learning_rate": 2.4676165272428866e-05,
      "loss": 0.1631,
      "step": 220
    },
    {
      "epoch": 0.3744213257363789,
      "grad_norm": 0.31506845355033875,
      "learning_rate": 2.4623427539738897e-05,
      "loss": 0.1353,
      "step": 230
    },
    {
      "epoch": 0.39070051381187365,
      "grad_norm": 0.3761660158634186,
      "learning_rate": 2.456677839228506e-05,
      "loss": 0.1716,
      "step": 240
    },
    {
      "epoch": 0.4069797018873684,
      "grad_norm": 0.29187777638435364,
      "learning_rate": 2.450623610693757e-05,
      "loss": 0.1195,
      "step": 250
    },
    {
      "epoch": 0.4232588899628631,
      "grad_norm": 0.46237581968307495,
      "learning_rate": 2.4441820216620425e-05,
      "loss": 0.1484,
      "step": 260
    },
    {
      "epoch": 0.4395380780383578,
      "grad_norm": 0.4580917954444885,
      "learning_rate": 2.437355150400945e-05,
      "loss": 0.1009,
      "step": 270
    },
    {
      "epoch": 0.4558172661138526,
      "grad_norm": 0.4181467890739441,
      "learning_rate": 2.4301451994827112e-05,
      "loss": 0.1376,
      "step": 280
    },
    {
      "epoch": 0.4720964541893473,
      "grad_norm": 0.3629908561706543,
      "learning_rate": 2.422554495073633e-05,
      "loss": 0.1083,
      "step": 290
    },
    {
      "epoch": 0.48837564226484204,
      "grad_norm": 0.4282682240009308,
      "learning_rate": 2.4145854861835447e-05,
      "loss": 0.1373,
      "step": 300
    },
    {
      "epoch": 0.5046548303403368,
      "grad_norm": 0.4914080500602722,
      "learning_rate": 2.406240743875699e-05,
      "loss": 0.156,
      "step": 310
    },
    {
      "epoch": 0.5209340184158315,
      "grad_norm": 0.3880573511123657,
      "learning_rate": 2.3975229604372526e-05,
      "loss": 0.1415,
      "step": 320
    },
    {
      "epoch": 0.5372132064913262,
      "grad_norm": 0.42599862813949585,
      "learning_rate": 2.3884349485106477e-05,
      "loss": 0.1338,
      "step": 330
    },
    {
      "epoch": 0.553492394566821,
      "grad_norm": 0.4339046776294708,
      "learning_rate": 2.378979640186163e-05,
      "loss": 0.1368,
      "step": 340
    },
    {
      "epoch": 0.5697715826423158,
      "grad_norm": 0.30713170766830444,
      "learning_rate": 2.3691600860559222e-05,
      "loss": 0.1154,
      "step": 350
    },
    {
      "epoch": 0.5860507707178104,
      "grad_norm": 0.4618566036224365,
      "learning_rate": 2.3589794542296764e-05,
      "loss": 0.1203,
      "step": 360
    },
    {
      "epoch": 0.6023299587933052,
      "grad_norm": 0.40802672505378723,
      "learning_rate": 2.3484410293126664e-05,
      "loss": 0.1144,
      "step": 370
    },
    {
      "epoch": 0.6186091468687999,
      "grad_norm": 0.5242702960968018,
      "learning_rate": 2.3375482113459014e-05,
      "loss": 0.1281,
      "step": 380
    },
    {
      "epoch": 0.6348883349442946,
      "grad_norm": 0.4045926630496979,
      "learning_rate": 2.3263045147091944e-05,
      "loss": 0.1145,
      "step": 390
    },
    {
      "epoch": 0.6511675230197894,
      "grad_norm": 0.5347346067428589,
      "learning_rate": 2.3147135669873096e-05,
      "loss": 0.1256,
      "step": 400
    },
    {
      "epoch": 0.6674467110952841,
      "grad_norm": 0.4755608141422272,
      "learning_rate": 2.302779107799583e-05,
      "loss": 0.1251,
      "step": 410
    },
    {
      "epoch": 0.6674467110952841,
      "eval_loss": 0.26128318905830383,
      "eval_runtime": 34.9177,
      "eval_samples_per_second": 5.413,
      "eval_steps_per_second": 5.413,
      "step": 410
    },
    {
      "epoch": 0.6837258991707789,
      "grad_norm": 0.4720211923122406,
      "learning_rate": 2.290504987593399e-05,
      "loss": 0.1399,
      "step": 420
    },
    {
      "epoch": 0.7000050872462736,
      "grad_norm": 0.709035336971283,
      "learning_rate": 2.2778951664019105e-05,
      "loss": 0.1375,
      "step": 430
    },
    {
      "epoch": 0.7162842753217683,
      "grad_norm": 0.534866213798523,
      "learning_rate": 2.2649537125664034e-05,
      "loss": 0.1125,
      "step": 440
    },
    {
      "epoch": 0.7325634633972631,
      "grad_norm": 0.522056519985199,
      "learning_rate": 2.2516848014237146e-05,
      "loss": 0.0943,
      "step": 450
    },
    {
      "epoch": 0.7488426514727577,
      "grad_norm": 0.2830965518951416,
      "learning_rate": 2.238092713959133e-05,
      "loss": 0.1248,
      "step": 460
    },
    {
      "epoch": 0.7651218395482525,
      "grad_norm": 0.39431601762771606,
      "learning_rate": 2.2241818354252113e-05,
      "loss": 0.1248,
      "step": 470
    },
    {
      "epoch": 0.7814010276237473,
      "grad_norm": 0.4821482002735138,
      "learning_rate": 2.209956653926944e-05,
      "loss": 0.1359,
      "step": 480
    },
    {
      "epoch": 0.797680215699242,
      "grad_norm": 0.4956236481666565,
      "learning_rate": 2.1954217589737535e-05,
      "loss": 0.1232,
      "step": 490
    },
    {
      "epoch": 0.8139594037747367,
      "grad_norm": 0.49444642663002014,
      "learning_rate": 2.180581839998766e-05,
      "loss": 0.1031,
      "step": 500
    },
    {
      "epoch": 0.8302385918502315,
      "grad_norm": 0.3857091963291168,
      "learning_rate": 2.165441684845847e-05,
      "loss": 0.1023,
      "step": 510
    },
    {
      "epoch": 0.8465177799257262,
      "grad_norm": 0.4830643832683563,
      "learning_rate": 2.150006178224886e-05,
      "loss": 0.1067,
      "step": 520
    },
    {
      "epoch": 0.862796968001221,
      "grad_norm": 0.5119408965110779,
      "learning_rate": 2.1342803001358278e-05,
      "loss": 0.1209,
      "step": 530
    },
    {
      "epoch": 0.8790761560767156,
      "grad_norm": 0.46363013982772827,
      "learning_rate": 2.118269124261963e-05,
      "loss": 0.1134,
      "step": 540
    },
    {
      "epoch": 0.8953553441522104,
      "grad_norm": 0.42933255434036255,
      "learning_rate": 2.1019778163329912e-05,
      "loss": 0.1101,
      "step": 550
    },
    {
      "epoch": 0.9116345322277052,
      "grad_norm": 0.5474070906639099,
      "learning_rate": 2.0854116324583867e-05,
      "loss": 0.1291,
      "step": 560
    },
    {
      "epoch": 0.9279137203031999,
      "grad_norm": 0.43502509593963623,
      "learning_rate": 2.0685759174316066e-05,
      "loss": 0.0936,
      "step": 570
    },
    {
      "epoch": 0.9441929083786946,
      "grad_norm": 0.632621169090271,
      "learning_rate": 2.051476103005684e-05,
      "loss": 0.1196,
      "step": 580
    },
    {
      "epoch": 0.9604720964541893,
      "grad_norm": 0.553187906742096,
      "learning_rate": 2.034117706140768e-05,
      "loss": 0.1186,
      "step": 590
    },
    {
      "epoch": 0.9767512845296841,
      "grad_norm": 0.48446330428123474,
      "learning_rate": 2.0165063272241712e-05,
      "loss": 0.1249,
      "step": 600
    },
    {
      "epoch": 0.9930304726051788,
      "grad_norm": 0.47837090492248535,
      "learning_rate": 1.9986476482635003e-05,
      "loss": 0.1097,
      "step": 610
    },
    {
      "epoch": 1.0011700666429262,
      "eval_loss": 0.2388339340686798,
      "eval_runtime": 34.8769,
      "eval_samples_per_second": 5.419,
      "eval_steps_per_second": 5.419,
      "step": 615
    },
    {
      "epoch": 1.0093096606806735,
      "grad_norm": 0.5520356893539429,
      "learning_rate": 1.980547431053456e-05,
      "loss": 0.131,
      "step": 620
    },
    {
      "epoch": 1.0255888487561682,
      "grad_norm": 0.6150078177452087,
      "learning_rate": 1.9622115153168884e-05,
      "loss": 0.1187,
      "step": 630
    },
    {
      "epoch": 1.041868036831663,
      "grad_norm": 0.5100656151771545,
      "learning_rate": 1.9436458168207117e-05,
      "loss": 0.114,
      "step": 640
    },
    {
      "epoch": 1.0581472249071577,
      "grad_norm": 0.5156052112579346,
      "learning_rate": 1.9248563254672825e-05,
      "loss": 0.1099,
      "step": 650
    },
    {
      "epoch": 1.0744264129826524,
      "grad_norm": 0.4662775993347168,
      "learning_rate": 1.9058491033618632e-05,
      "loss": 0.1135,
      "step": 660
    },
    {
      "epoch": 1.0907056010581473,
      "grad_norm": 0.4357255697250366,
      "learning_rate": 1.886630282856787e-05,
      "loss": 0.1036,
      "step": 670
    },
    {
      "epoch": 1.106984789133642,
      "grad_norm": 0.3861764967441559,
      "learning_rate": 1.867206064572962e-05,
      "loss": 0.1145,
      "step": 680
    },
    {
      "epoch": 1.1232639772091366,
      "grad_norm": 0.4562045633792877,
      "learning_rate": 1.8475827153993447e-05,
      "loss": 0.1107,
      "step": 690
    },
    {
      "epoch": 1.1395431652846315,
      "grad_norm": 0.332917720079422,
      "learning_rate": 1.8277665664710387e-05,
      "loss": 0.1266,
      "step": 700
    },
    {
      "epoch": 1.1558223533601262,
      "grad_norm": 0.5971720814704895,
      "learning_rate": 1.807764011126663e-05,
      "loss": 0.1122,
      "step": 710
    },
    {
      "epoch": 1.1721015414356208,
      "grad_norm": 0.6102172136306763,
      "learning_rate": 1.787581502845651e-05,
      "loss": 0.1046,
      "step": 720
    },
    {
      "epoch": 1.1883807295111157,
      "grad_norm": 0.5294010043144226,
      "learning_rate": 1.767225553166146e-05,
      "loss": 0.1044,
      "step": 730
    },
    {
      "epoch": 1.2046599175866104,
      "grad_norm": 0.5074148178100586,
      "learning_rate": 1.7467027295841688e-05,
      "loss": 0.1251,
      "step": 740
    },
    {
      "epoch": 1.220939105662105,
      "grad_norm": 0.6349917650222778,
      "learning_rate": 1.7260196534347235e-05,
      "loss": 0.1037,
      "step": 750
    },
    {
      "epoch": 1.2372182937376,
      "grad_norm": 0.34580153226852417,
      "learning_rate": 1.7051829977555426e-05,
      "loss": 0.0831,
      "step": 760
    },
    {
      "epoch": 1.2534974818130946,
      "grad_norm": 0.4629954993724823,
      "learning_rate": 1.684199485134144e-05,
      "loss": 0.1068,
      "step": 770
    },
    {
      "epoch": 1.2697766698885893,
      "grad_norm": 0.6406750082969666,
      "learning_rate": 1.6630758855389055e-05,
      "loss": 0.1192,
      "step": 780
    },
    {
      "epoch": 1.286055857964084,
      "grad_norm": 0.4982251226902008,
      "learning_rate": 1.6418190141348485e-05,
      "loss": 0.123,
      "step": 790
    },
    {
      "epoch": 1.3023350460395788,
      "grad_norm": 0.5146717429161072,
      "learning_rate": 1.6204357290848464e-05,
      "loss": 0.0831,
      "step": 800
    },
    {
      "epoch": 1.3186142341150735,
      "grad_norm": 0.4735712707042694,
      "learning_rate": 1.5989329293369538e-05,
      "loss": 0.0971,
      "step": 810
    },
    {
      "epoch": 1.3348934221905682,
      "grad_norm": 0.7393200397491455,
      "learning_rate": 1.5773175523985818e-05,
      "loss": 0.0923,
      "step": 820
    },
    {
      "epoch": 1.3348934221905682,
      "eval_loss": 0.22815725207328796,
      "eval_runtime": 34.8794,
      "eval_samples_per_second": 5.419,
      "eval_steps_per_second": 5.419,
      "step": 820
    }
  ],
  "logging_steps": 10,
  "max_steps": 1842,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 205,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.989312360723251e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}