{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 395,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012658227848101266,
      "grad_norm": 6.695639272540547,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.1195,
      "step": 1
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": 13.683866082279918,
      "learning_rate": 2.5e-06,
      "loss": 1.0968,
      "step": 5
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 2.7914110872997275,
      "learning_rate": 5e-06,
      "loss": 1.0868,
      "step": 10
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 2.2869962494889995,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.0771,
      "step": 15
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 2.315595057148159,
      "learning_rate": 1e-05,
      "loss": 1.0546,
      "step": 20
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 1.9266353743480364,
      "learning_rate": 1.25e-05,
      "loss": 1.084,
      "step": 25
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 2.150532379708014,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.0654,
      "step": 30
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 2.1018953026935905,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.0817,
      "step": 35
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 2.3849545878679272,
      "learning_rate": 2e-05,
      "loss": 1.0971,
      "step": 40
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 2.345688862339495,
      "learning_rate": 1.9990212265199738e-05,
      "loss": 1.086,
      "step": 45
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 2.5866807131537906,
      "learning_rate": 1.996086822074945e-05,
      "loss": 1.0656,
      "step": 50
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 2.4392627537159655,
      "learning_rate": 1.9912025308994146e-05,
      "loss": 1.1059,
      "step": 55
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 2.2706485443813276,
      "learning_rate": 1.9843779142227258e-05,
      "loss": 1.0973,
      "step": 60
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 2.3020097653483496,
      "learning_rate": 1.975626331552507e-05,
      "loss": 1.1083,
      "step": 65
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 2.0670888705685955,
      "learning_rate": 1.96496491452281e-05,
      "loss": 1.1039,
      "step": 70
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 2.371742516361207,
      "learning_rate": 1.9524145333581315e-05,
      "loss": 1.0895,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7223408222198486,
      "eval_runtime": 213.2984,
      "eval_samples_per_second": 47.375,
      "eval_steps_per_second": 0.741,
      "step": 79
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 8.106924593883994,
      "learning_rate": 1.9379997560189677e-05,
      "loss": 1.0198,
      "step": 80
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 3.486817193319529,
      "learning_rate": 1.9217488001088784e-05,
      "loss": 0.6812,
      "step": 85
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 2.921219837737029,
      "learning_rate": 1.903693477637204e-05,
      "loss": 0.6683,
      "step": 90
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 3.1078224489011683,
      "learning_rate": 1.883869132745561e-05,
      "loss": 0.653,
      "step": 95
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 2.8280645620621874,
      "learning_rate": 1.862314572520028e-05,
      "loss": 0.6501,
      "step": 100
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 2.920193489057834,
      "learning_rate": 1.8390719910244487e-05,
      "loss": 0.647,
      "step": 105
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 2.647561794905359,
      "learning_rate": 1.8141868867035745e-05,
      "loss": 0.6531,
      "step": 110
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 2.7660605803019447,
      "learning_rate": 1.7877079733177185e-05,
      "loss": 0.6232,
      "step": 115
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 2.497219995540892,
      "learning_rate": 1.759687084583285e-05,
      "loss": 0.6401,
      "step": 120
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 2.447623483254921,
      "learning_rate": 1.7301790727058344e-05,
      "loss": 0.6592,
      "step": 125
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 2.4783693483832563,
      "learning_rate": 1.6992417010043144e-05,
      "loss": 0.6441,
      "step": 130
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 2.348228472338975,
      "learning_rate": 1.666935530836651e-05,
      "loss": 0.6439,
      "step": 135
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 2.316917620320839,
      "learning_rate": 1.6333238030480473e-05,
      "loss": 0.6572,
      "step": 140
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 2.614503810192861,
      "learning_rate": 1.5984723141740578e-05,
      "loss": 0.6764,
      "step": 145
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 2.452736422029602,
      "learning_rate": 1.562449287640781e-05,
      "loss": 0.6555,
      "step": 150
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 2.737510300725156,
      "learning_rate": 1.5253252402142989e-05,
      "loss": 0.6454,
      "step": 155
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.33173683285713196,
      "eval_runtime": 213.2106,
      "eval_samples_per_second": 47.394,
      "eval_steps_per_second": 0.741,
      "step": 158
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 3.9057198522311167,
      "learning_rate": 1.4871728439607967e-05,
      "loss": 0.5134,
      "step": 160
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 3.4868328352161817,
      "learning_rate": 1.4480667839875786e-05,
      "loss": 0.3096,
      "step": 165
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 2.9717493172755014,
      "learning_rate": 1.408083612243465e-05,
      "loss": 0.2909,
      "step": 170
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 2.642444961402327,
      "learning_rate": 1.367301597664757e-05,
      "loss": 0.2837,
      "step": 175
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 2.3997899647768346,
      "learning_rate": 1.3258005729601178e-05,
      "loss": 0.2818,
      "step": 180
    },
    {
      "epoch": 2.3417721518987342,
      "grad_norm": 2.7423823494323774,
      "learning_rate": 1.2836617783342968e-05,
      "loss": 0.2907,
      "step": 185
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 2.3807259553082276,
      "learning_rate": 1.2409677024566145e-05,
      "loss": 0.2872,
      "step": 190
    },
    {
      "epoch": 2.4683544303797467,
      "grad_norm": 2.336572941961749,
      "learning_rate": 1.1978019209855174e-05,
      "loss": 0.2866,
      "step": 195
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 2.2601309613900757,
      "learning_rate": 1.1542489329653024e-05,
      "loss": 0.2945,
      "step": 200
    },
    {
      "epoch": 2.5949367088607596,
      "grad_norm": 2.3050926972713968,
      "learning_rate": 1.11039399541527e-05,
      "loss": 0.2937,
      "step": 205
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 2.221130883158219,
      "learning_rate": 1.066322956435104e-05,
      "loss": 0.2961,
      "step": 210
    },
    {
      "epoch": 2.721518987341772,
      "grad_norm": 2.270387701106379,
      "learning_rate": 1.022122087153187e-05,
      "loss": 0.2965,
      "step": 215
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 2.279056997659604,
      "learning_rate": 9.778779128468133e-06,
      "loss": 0.2964,
      "step": 220
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 2.1417041666216696,
      "learning_rate": 9.336770435648963e-06,
      "loss": 0.2931,
      "step": 225
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 2.439196726609028,
      "learning_rate": 8.896060045847305e-06,
      "loss": 0.2977,
      "step": 230
    },
    {
      "epoch": 2.9746835443037973,
      "grad_norm": 2.2397521488796417,
      "learning_rate": 8.457510670346976e-06,
      "loss": 0.2926,
      "step": 235
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.12934371829032898,
      "eval_runtime": 213.237,
      "eval_samples_per_second": 47.389,
      "eval_steps_per_second": 0.741,
      "step": 237
    },
    {
      "epoch": 3.037974683544304,
      "grad_norm": 2.2704813832171142,
      "learning_rate": 8.021980790144828e-06,
      "loss": 0.199,
      "step": 240
    },
    {
      "epoch": 3.1012658227848102,
      "grad_norm": 2.132226843273487,
      "learning_rate": 7.590322975433857e-06,
      "loss": 0.1128,
      "step": 245
    },
    {
      "epoch": 3.1645569620253164,
      "grad_norm": 2.0782142465832236,
      "learning_rate": 7.163382216657033e-06,
      "loss": 0.1129,
      "step": 250
    },
    {
      "epoch": 3.2278481012658227,
      "grad_norm": 1.761669140987703,
      "learning_rate": 6.741994270398826e-06,
      "loss": 0.1099,
      "step": 255
    },
    {
      "epoch": 3.291139240506329,
      "grad_norm": 1.717634933034142,
      "learning_rate": 6.326984023352435e-06,
      "loss": 0.1086,
      "step": 260
    },
    {
      "epoch": 3.3544303797468356,
      "grad_norm": 1.6608157157785954,
      "learning_rate": 5.919163877565351e-06,
      "loss": 0.1068,
      "step": 265
    },
    {
      "epoch": 3.4177215189873418,
      "grad_norm": 1.6064024695135044,
      "learning_rate": 5.519332160124215e-06,
      "loss": 0.1101,
      "step": 270
    },
    {
      "epoch": 3.481012658227848,
      "grad_norm": 1.6349645931027217,
      "learning_rate": 5.128271560392037e-06,
      "loss": 0.1074,
      "step": 275
    },
    {
      "epoch": 3.5443037974683547,
      "grad_norm": 1.7679069294086043,
      "learning_rate": 4.746747597857014e-06,
      "loss": 0.1118,
      "step": 280
    },
    {
      "epoch": 3.607594936708861,
      "grad_norm": 1.5530405205049536,
      "learning_rate": 4.375507123592194e-06,
      "loss": 0.1077,
      "step": 285
    },
    {
      "epoch": 3.670886075949367,
      "grad_norm": 1.5871889705183277,
      "learning_rate": 4.015276858259427e-06,
      "loss": 0.1082,
      "step": 290
    },
    {
      "epoch": 3.7341772151898733,
      "grad_norm": 1.5985959451025067,
      "learning_rate": 3.6667619695195287e-06,
      "loss": 0.1063,
      "step": 295
    },
    {
      "epoch": 3.7974683544303796,
      "grad_norm": 1.567040797684349,
      "learning_rate": 3.330644691633492e-06,
      "loss": 0.1067,
      "step": 300
    },
    {
      "epoch": 3.8607594936708862,
      "grad_norm": 1.6098560275600409,
      "learning_rate": 3.00758298995686e-06,
      "loss": 0.1045,
      "step": 305
    },
    {
      "epoch": 3.9240506329113924,
      "grad_norm": 1.495424841878041,
      "learning_rate": 2.698209272941659e-06,
      "loss": 0.1076,
      "step": 310
    },
    {
      "epoch": 3.9873417721518987,
      "grad_norm": 1.4612235257248143,
      "learning_rate": 2.403129154167153e-06,
      "loss": 0.1048,
      "step": 315
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.054249346256256104,
      "eval_runtime": 213.4038,
      "eval_samples_per_second": 47.352,
      "eval_steps_per_second": 0.74,
      "step": 316
    },
    {
      "epoch": 4.050632911392405,
      "grad_norm": 0.8970304833218358,
      "learning_rate": 2.1229202668228197e-06,
      "loss": 0.0643,
      "step": 320
    },
    {
      "epoch": 4.113924050632911,
      "grad_norm": 1.3031778574429476,
      "learning_rate": 1.8581311329642592e-06,
      "loss": 0.0496,
      "step": 325
    },
    {
      "epoch": 4.177215189873418,
      "grad_norm": 1.0494986965992847,
      "learning_rate": 1.609280089755515e-06,
      "loss": 0.0498,
      "step": 330
    },
    {
      "epoch": 4.2405063291139244,
      "grad_norm": 0.8871889072165642,
      "learning_rate": 1.3768542747997215e-06,
      "loss": 0.048,
      "step": 335
    },
    {
      "epoch": 4.30379746835443,
      "grad_norm": 0.8947823783464494,
      "learning_rate": 1.161308672544389e-06,
      "loss": 0.0491,
      "step": 340
    },
    {
      "epoch": 4.367088607594937,
      "grad_norm": 0.8681171283598373,
      "learning_rate": 9.630652236279626e-07,
      "loss": 0.0467,
      "step": 345
    },
    {
      "epoch": 4.430379746835443,
      "grad_norm": 0.8483515397273593,
      "learning_rate": 7.825119989112173e-07,
      "loss": 0.0474,
      "step": 350
    },
    {
      "epoch": 4.493670886075949,
      "grad_norm": 0.883073997111795,
      "learning_rate": 6.200024398103255e-07,
      "loss": 0.0461,
      "step": 355
    },
    {
      "epoch": 4.556962025316456,
      "grad_norm": 0.8423665781515933,
      "learning_rate": 4.7585466641868696e-07,
      "loss": 0.0474,
      "step": 360
    },
    {
      "epoch": 4.620253164556962,
      "grad_norm": 1.0038851569615406,
      "learning_rate": 3.5035085477190143e-07,
      "loss": 0.0476,
      "step": 365
    },
    {
      "epoch": 4.6835443037974684,
      "grad_norm": 0.9089402076181121,
      "learning_rate": 2.4373668447493225e-07,
      "loss": 0.0467,
      "step": 370
    },
    {
      "epoch": 4.746835443037975,
      "grad_norm": 0.8530919153878059,
      "learning_rate": 1.562208577727442e-07,
      "loss": 0.0469,
      "step": 375
    },
    {
      "epoch": 4.810126582278481,
      "grad_norm": 0.8298393668849166,
      "learning_rate": 8.797469100585432e-08,
      "loss": 0.0481,
      "step": 380
    },
    {
      "epoch": 4.8734177215189876,
      "grad_norm": 0.986632852960438,
      "learning_rate": 3.913177925055189e-08,
      "loss": 0.0471,
      "step": 385
    },
    {
      "epoch": 4.936708860759493,
      "grad_norm": 0.9075462948662969,
      "learning_rate": 9.78773480026396e-09,
      "loss": 0.0474,
      "step": 390
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7480159011876264,
      "learning_rate": 0.0,
      "loss": 0.0465,
      "step": 395
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.039588429033756256,
      "eval_runtime": 213.3054,
      "eval_samples_per_second": 47.373,
      "eval_steps_per_second": 0.741,
      "step": 395
    },
    {
      "epoch": 5.0,
      "step": 395,
      "total_flos": 165305238159360.0,
      "train_loss": 0.43836132314386245,
      "train_runtime": 6288.8643,
      "train_samples_per_second": 8.034,
      "train_steps_per_second": 0.063
    }
  ],
  "logging_steps": 5,
  "max_steps": 395,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 165305238159360.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}