{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 269,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01858736059479554,
      "grad_norm": 4.007935378868762,
      "learning_rate": 1.785714285714286e-05,
      "loss": 1.0011,
      "num_tokens": 10465392.0,
      "step": 5
    },
    {
      "epoch": 0.03717472118959108,
      "grad_norm": 1.779777071622888,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.9383,
      "num_tokens": 20951152.0,
      "step": 10
    },
    {
      "epoch": 0.055762081784386616,
      "grad_norm": 1.5165754407115957,
      "learning_rate": 4.9998292477583695e-05,
      "loss": 0.8576,
      "num_tokens": 31436912.0,
      "step": 15
    },
    {
      "epoch": 0.07434944237918216,
      "grad_norm": 1.1112753601995564,
      "learning_rate": 4.993855640118024e-05,
      "loss": 0.8136,
      "num_tokens": 41909269.0,
      "step": 20
    },
    {
      "epoch": 0.09293680297397769,
      "grad_norm": 0.8850229226974969,
      "learning_rate": 4.9793703194560106e-05,
      "loss": 0.7908,
      "num_tokens": 52353719.0,
      "step": 25
    },
    {
      "epoch": 0.11152416356877323,
      "grad_norm": 0.8157290536352468,
      "learning_rate": 4.9564282335552e-05,
      "loss": 0.7732,
      "num_tokens": 62792124.0,
      "step": 30
    },
    {
      "epoch": 0.13011152416356878,
      "grad_norm": 0.8304768081951895,
      "learning_rate": 4.9251164096056716e-05,
      "loss": 0.7563,
      "num_tokens": 73260442.0,
      "step": 35
    },
    {
      "epoch": 0.14869888475836432,
      "grad_norm": 0.7191983564484024,
      "learning_rate": 4.885553624080778e-05,
      "loss": 0.7385,
      "num_tokens": 83727556.0,
      "step": 40
    },
    {
      "epoch": 0.16728624535315986,
      "grad_norm": 1.1043662370540017,
      "learning_rate": 4.8378899521772935e-05,
      "loss": 0.7367,
      "num_tokens": 94201938.0,
      "step": 45
    },
    {
      "epoch": 0.18587360594795538,
      "grad_norm": 0.8443906045895648,
      "learning_rate": 4.78230619852879e-05,
      "loss": 0.7287,
      "num_tokens": 104670740.0,
      "step": 50
    },
    {
      "epoch": 0.20446096654275092,
      "grad_norm": 0.8981056349681326,
      "learning_rate": 4.719013211351733e-05,
      "loss": 0.7317,
      "num_tokens": 115151933.0,
      "step": 55
    },
    {
      "epoch": 0.22304832713754646,
      "grad_norm": 0.7188198075786009,
      "learning_rate": 4.648251082625975e-05,
      "loss": 0.7208,
      "num_tokens": 125607410.0,
      "step": 60
    },
    {
      "epoch": 0.241635687732342,
      "grad_norm": 0.8256122130547718,
      "learning_rate": 4.570288237343632e-05,
      "loss": 0.7187,
      "num_tokens": 136036466.0,
      "step": 65
    },
    {
      "epoch": 0.26022304832713755,
      "grad_norm": 0.7434853803962486,
      "learning_rate": 4.4854204152811567e-05,
      "loss": 0.7144,
      "num_tokens": 146502251.0,
      "step": 70
    },
    {
      "epoch": 0.2788104089219331,
      "grad_norm": 0.5368593293506128,
      "learning_rate": 4.39396954915706e-05,
      "loss": 0.71,
      "num_tokens": 156977308.0,
      "step": 75
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 0.5684059848173332,
      "learning_rate": 4.2962825434308415e-05,
      "loss": 0.7031,
      "num_tokens": 167423794.0,
      "step": 80
    },
    {
      "epoch": 0.3159851301115242,
      "grad_norm": 0.6000054082622095,
      "learning_rate": 4.1927299583755515e-05,
      "loss": 0.694,
      "num_tokens": 177900466.0,
      "step": 85
    },
    {
      "epoch": 0.3345724907063197,
      "grad_norm": 0.4683216334004466,
      "learning_rate": 4.083704604415748e-05,
      "loss": 0.6978,
      "num_tokens": 188373813.0,
      "step": 90
    },
    {
      "epoch": 0.35315985130111527,
      "grad_norm": 0.6564460791865333,
      "learning_rate": 3.969620052063012e-05,
      "loss": 0.6958,
      "num_tokens": 198859382.0,
      "step": 95
    },
    {
      "epoch": 0.37174721189591076,
      "grad_norm": 0.43872776684737724,
      "learning_rate": 3.850909063101328e-05,
      "loss": 0.6916,
      "num_tokens": 209345142.0,
      "step": 100
    },
    {
      "epoch": 0.3903345724907063,
      "grad_norm": 0.5046190722656403,
      "learning_rate": 3.728021948973421e-05,
      "loss": 0.691,
      "num_tokens": 219820636.0,
      "step": 105
    },
    {
      "epoch": 0.40892193308550184,
      "grad_norm": 0.5244162239520259,
      "learning_rate": 3.6014248625951984e-05,
      "loss": 0.6813,
      "num_tokens": 230306396.0,
      "step": 110
    },
    {
      "epoch": 0.4275092936802974,
      "grad_norm": 0.5719480684589926,
      "learning_rate": 3.4715980300780745e-05,
      "loss": 0.6857,
      "num_tokens": 240792156.0,
      "step": 115
    },
    {
      "epoch": 0.44609665427509293,
      "grad_norm": 0.478683730476968,
      "learning_rate": 3.339033929066841e-05,
      "loss": 0.6842,
      "num_tokens": 251259365.0,
      "step": 120
    },
    {
      "epoch": 0.4646840148698885,
      "grad_norm": 0.4095390097161309,
      "learning_rate": 3.204235420603273e-05,
      "loss": 0.6871,
      "num_tokens": 261736444.0,
      "step": 125
    },
    {
      "epoch": 0.483271375464684,
      "grad_norm": 0.4823863786072732,
      "learning_rate": 3.0677138416019556e-05,
      "loss": 0.6861,
      "num_tokens": 272205866.0,
      "step": 130
    },
    {
      "epoch": 0.5018587360594795,
      "grad_norm": 0.3712185789520159,
      "learning_rate": 2.9299870651742188e-05,
      "loss": 0.6803,
      "num_tokens": 282683327.0,
      "step": 135
    },
    {
      "epoch": 0.5204460966542751,
      "grad_norm": 0.43259713240817316,
      "learning_rate": 2.7915775361580428e-05,
      "loss": 0.6843,
      "num_tokens": 293122806.0,
      "step": 140
    },
    {
      "epoch": 0.5390334572490706,
      "grad_norm": 0.3914497825473669,
      "learning_rate": 2.6530102893058357e-05,
      "loss": 0.6831,
      "num_tokens": 303598947.0,
      "step": 145
    },
    {
      "epoch": 0.5576208178438662,
      "grad_norm": 0.34581475770903225,
      "learning_rate": 2.5148109576477802e-05,
      "loss": 0.6796,
      "num_tokens": 314077641.0,
      "step": 150
    },
    {
      "epoch": 0.5762081784386617,
      "grad_norm": 0.39302670660254074,
      "learning_rate": 2.3775037785857073e-05,
      "loss": 0.6684,
      "num_tokens": 324545386.0,
      "step": 155
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 0.35089723644158544,
      "learning_rate": 2.2416096052810688e-05,
      "loss": 0.6834,
      "num_tokens": 335031146.0,
      "step": 160
    },
    {
      "epoch": 0.6133828996282528,
      "grad_norm": 0.37127645861899733,
      "learning_rate": 2.1076439308804808e-05,
      "loss": 0.6597,
      "num_tokens": 345504904.0,
      "step": 165
    },
    {
      "epoch": 0.6319702602230484,
      "grad_norm": 0.35866979447691283,
      "learning_rate": 1.976114933073662e-05,
      "loss": 0.6708,
      "num_tokens": 355956520.0,
      "step": 170
    },
    {
      "epoch": 0.6505576208178439,
      "grad_norm": 0.3542786775444148,
      "learning_rate": 1.847521546401383e-05,
      "loss": 0.6726,
      "num_tokens": 366434348.0,
      "step": 175
    },
    {
      "epoch": 0.6691449814126395,
      "grad_norm": 0.3663755936620364,
      "learning_rate": 1.7223515696258592e-05,
      "loss": 0.6754,
      "num_tokens": 376908695.0,
      "step": 180
    },
    {
      "epoch": 0.6877323420074349,
      "grad_norm": 0.3973873941404514,
      "learning_rate": 1.60107981534296e-05,
      "loss": 0.6788,
      "num_tokens": 387384301.0,
      "step": 185
    },
    {
      "epoch": 0.7063197026022305,
      "grad_norm": 0.3099192574655377,
      "learning_rate": 1.484166308855398e-05,
      "loss": 0.6678,
      "num_tokens": 397835323.0,
      "step": 190
    },
    {
      "epoch": 0.724907063197026,
      "grad_norm": 0.332309833872801,
      "learning_rate": 1.372054543139188e-05,
      "loss": 0.6658,
      "num_tokens": 408298322.0,
      "step": 195
    },
    {
      "epoch": 0.7434944237918215,
      "grad_norm": 0.31105138947653627,
      "learning_rate": 1.2651697965228748e-05,
      "loss": 0.6733,
      "num_tokens": 418781566.0,
      "step": 200
    },
    {
      "epoch": 0.7620817843866171,
      "grad_norm": 0.30171220361735157,
      "learning_rate": 1.1639175194611693e-05,
      "loss": 0.6683,
      "num_tokens": 429246222.0,
      "step": 205
    },
    {
      "epoch": 0.7806691449814126,
      "grad_norm": 0.3197255345493862,
      "learning_rate": 1.0686817965224952e-05,
      "loss": 0.6616,
      "num_tokens": 439717644.0,
      "step": 210
    },
    {
      "epoch": 0.7992565055762082,
      "grad_norm": 0.29017687856686264,
      "learning_rate": 9.798238894246628e-06,
      "loss": 0.6725,
      "num_tokens": 450170885.0,
      "step": 215
    },
    {
      "epoch": 0.8178438661710037,
      "grad_norm": 0.30650176056828654,
      "learning_rate": 8.976808666454292e-06,
      "loss": 0.6673,
      "num_tokens": 460656645.0,
      "step": 220
    },
    {
      "epoch": 0.8364312267657993,
      "grad_norm": 0.3090230351140059,
      "learning_rate": 8.225643248063091e-06,
      "loss": 0.6578,
      "num_tokens": 471142405.0,
      "step": 225
    },
    {
      "epoch": 0.8550185873605948,
      "grad_norm": 0.2586717237531077,
      "learning_rate": 7.547592066798609e-06,
      "loss": 0.6635,
      "num_tokens": 481616409.0,
      "step": 230
    },
    {
      "epoch": 0.8736059479553904,
      "grad_norm": 0.28938628080409906,
      "learning_rate": 6.94522720304148e-06,
      "loss": 0.6621,
      "num_tokens": 492097674.0,
      "step": 235
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 0.26794626813474093,
      "learning_rate": 6.420833633045514e-06,
      "loss": 0.6594,
      "num_tokens": 502555042.0,
      "step": 240
    },
    {
      "epoch": 0.9107806691449815,
      "grad_norm": 0.2651571481097874,
      "learning_rate": 5.976400561240085e-06,
      "loss": 0.657,
      "num_tokens": 513031521.0,
      "step": 245
    },
    {
      "epoch": 0.929368029739777,
      "grad_norm": 0.26526678159109557,
      "learning_rate": 5.613613874496393e-06,
      "loss": 0.6667,
      "num_tokens": 523517281.0,
      "step": 250
    },
    {
      "epoch": 0.9479553903345725,
      "grad_norm": 0.25932352659544855,
      "learning_rate": 5.333849746981104e-06,
      "loss": 0.6625,
      "num_tokens": 533998146.0,
      "step": 255
    },
    {
      "epoch": 0.966542750929368,
      "grad_norm": 0.25169356243372,
      "learning_rate": 5.138169419856345e-06,
      "loss": 0.6577,
      "num_tokens": 544470561.0,
      "step": 260
    },
    {
      "epoch": 0.9851301115241635,
      "grad_norm": 0.257589406808037,
      "learning_rate": 5.027315175628478e-06,
      "loss": 0.6536,
      "num_tokens": 554934577.0,
      "step": 265
    },
    {
      "epoch": 1.0,
      "num_tokens": 562274609.0,
      "step": 269,
      "total_flos": 242189447725056.0,
      "train_loss": 0.7043104473099833,
      "train_runtime": 6478.7341,
      "train_samples_per_second": 5.295,
      "train_steps_per_second": 0.042
    }
  ],
  "logging_steps": 5,
  "max_steps": 269,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 242189447725056.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}