{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07142857142857142,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014285714285714286,
      "grad_norm": 160.0,
      "learning_rate": 5.399999999999999e-05,
      "loss": 3.334370803833008,
      "step": 10
    },
    {
      "epoch": 0.002857142857142857,
      "grad_norm": 143.0,
      "learning_rate": 0.00011399999999999999,
      "loss": 3.312285232543945,
      "step": 20
    },
    {
      "epoch": 0.004285714285714286,
      "grad_norm": 91.0,
      "learning_rate": 0.00017399999999999997,
      "loss": 3.3183692932128905,
      "step": 30
    },
    {
      "epoch": 0.005714285714285714,
      "grad_norm": 306.0,
      "learning_rate": 0.000234,
      "loss": 3.232763671875,
      "step": 40
    },
    {
      "epoch": 0.007142857142857143,
      "grad_norm": 114.5,
      "learning_rate": 0.000294,
      "loss": 3.1770435333251954,
      "step": 50
    },
    {
      "epoch": 0.008571428571428572,
      "grad_norm": 148.0,
      "learning_rate": 0.00029999875870267496,
      "loss": 3.1800256729125977,
      "step": 60
    },
    {
      "epoch": 0.01,
      "grad_norm": 25.0,
      "learning_rate": 0.0002999944678247173,
      "loss": 3.166558837890625,
      "step": 70
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 22.75,
      "learning_rate": 0.0002999871121291227,
      "loss": 3.203672409057617,
      "step": 80
    },
    {
      "epoch": 0.012857142857142857,
      "grad_norm": 6.4375,
      "learning_rate": 0.00029997669176618923,
      "loss": 3.155362129211426,
      "step": 90
    },
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 142.0,
      "learning_rate": 0.0002999632069488347,
      "loss": 3.1418533325195312,
      "step": 100
    },
    {
      "epoch": 0.014285714285714285,
      "eval_loss": 3.406630277633667,
      "eval_runtime": 4.5564,
      "eval_samples_per_second": 65.402,
      "eval_steps_per_second": 3.731,
      "step": 100
    },
    {
      "epoch": 0.015714285714285715,
      "grad_norm": 200.0,
      "learning_rate": 0.00029994665795259274,
      "loss": 3.106761932373047,
      "step": 110
    },
    {
      "epoch": 0.017142857142857144,
      "grad_norm": 193.0,
      "learning_rate": 0.0002999270451156068,
      "loss": 3.1113397598266603,
      "step": 120
    },
    {
      "epoch": 0.018571428571428572,
      "grad_norm": 39.5,
      "learning_rate": 0.0002999043688386235,
      "loss": 3.0628725051879884,
      "step": 130
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.125,
      "learning_rate": 0.0002998786295849843,
      "loss": 3.030979347229004,
      "step": 140
    },
    {
      "epoch": 0.02142857142857143,
      "grad_norm": 10.0625,
      "learning_rate": 0.000299849827880616,
      "loss": 3.0148197174072267,
      "step": 150
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 4.03125,
      "learning_rate": 0.00029981796431402015,
      "loss": 2.963352394104004,
      "step": 160
    },
    {
      "epoch": 0.024285714285714285,
      "grad_norm": 28.5,
      "learning_rate": 0.0002997830395362608,
      "loss": 2.951630401611328,
      "step": 170
    },
    {
      "epoch": 0.025714285714285714,
      "grad_norm": 5.15625,
      "learning_rate": 0.00029974505426095166,
      "loss": 2.903683662414551,
      "step": 180
    },
    {
      "epoch": 0.027142857142857142,
      "grad_norm": 2.359375,
      "learning_rate": 0.0002997040092642407,
      "loss": 2.911179542541504,
      "step": 190
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.484375,
      "learning_rate": 0.00029965990538479526,
      "loss": 2.8417181015014648,
      "step": 200
    },
    {
      "epoch": 0.02857142857142857,
      "eval_loss": 3.159050703048706,
      "eval_runtime": 4.4564,
      "eval_samples_per_second": 66.87,
      "eval_steps_per_second": 3.815,
      "step": 200
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.515625,
      "learning_rate": 0.0002996127435237841,
      "loss": 2.815742301940918,
      "step": 210
    },
    {
      "epoch": 0.03142857142857143,
      "grad_norm": 1.71875,
      "learning_rate": 0.0002995625246448595,
      "loss": 2.7929365158081056,
      "step": 220
    },
    {
      "epoch": 0.032857142857142856,
      "grad_norm": 0.765625,
      "learning_rate": 0.00029950924977413735,
      "loss": 2.7637331008911135,
      "step": 230
    },
    {
      "epoch": 0.03428571428571429,
      "grad_norm": 0.609375,
      "learning_rate": 0.0002994529200001762,
      "loss": 2.73776912689209,
      "step": 240
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 1.5703125,
      "learning_rate": 0.00029939353647395506,
      "loss": 2.723506736755371,
      "step": 250
    },
    {
      "epoch": 0.037142857142857144,
      "grad_norm": 0.66015625,
      "learning_rate": 0.00029933110040884987,
      "loss": 2.6915863037109373,
      "step": 260
    },
    {
      "epoch": 0.03857142857142857,
      "grad_norm": 0.9609375,
      "learning_rate": 0.00029926561308060874,
      "loss": 2.663774871826172,
      "step": 270
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.65234375,
      "learning_rate": 0.00029919707582732577,
      "loss": 2.6552204132080077,
      "step": 280
    },
    {
      "epoch": 0.041428571428571426,
      "grad_norm": 0.1708984375,
      "learning_rate": 0.0002991254900494139,
      "loss": 2.6489795684814452,
      "step": 290
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 0.984375,
      "learning_rate": 0.000299050857209576,
      "loss": 2.6665163040161133,
      "step": 300
    },
    {
      "epoch": 0.04285714285714286,
      "eval_loss": 3.0404820442199707,
      "eval_runtime": 4.4652,
      "eval_samples_per_second": 66.739,
      "eval_steps_per_second": 3.807,
      "step": 300
    },
    {
      "epoch": 0.04428571428571428,
      "grad_norm": 1.2890625,
      "learning_rate": 0.00029897317883277537,
      "loss": 2.6572853088378907,
      "step": 310
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.2265625,
      "learning_rate": 0.00029889245650620413,
      "loss": 2.642633056640625,
      "step": 320
    },
    {
      "epoch": 0.047142857142857146,
      "grad_norm": 0.6484375,
      "learning_rate": 0.0002988086918792514,
      "loss": 2.6547801971435545,
      "step": 330
    },
    {
      "epoch": 0.04857142857142857,
      "grad_norm": 4.625,
      "learning_rate": 0.0002987218866634688,
      "loss": 2.651763153076172,
      "step": 340
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.00029863204263253624,
      "loss": 2.635426902770996,
      "step": 350
    },
    {
      "epoch": 0.05142857142857143,
      "grad_norm": 0.11328125,
      "learning_rate": 0.0002985391616222252,
      "loss": 2.6323591232299806,
      "step": 360
    },
    {
      "epoch": 0.05285714285714286,
      "grad_norm": 3.125,
      "learning_rate": 0.0002984432455303614,
      "loss": 2.655726432800293,
      "step": 370
    },
    {
      "epoch": 0.054285714285714284,
      "grad_norm": 0.3359375,
      "learning_rate": 0.00029834429631678597,
      "loss": 2.6482254028320313,
      "step": 380
    },
    {
      "epoch": 0.055714285714285716,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00029824231600331547,
      "loss": 2.6480077743530273,
      "step": 390
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.166015625,
      "learning_rate": 0.0002981373066737005,
      "loss": 2.6565391540527346,
      "step": 400
    },
    {
      "epoch": 0.05714285714285714,
      "eval_loss": 3.0312750339508057,
      "eval_runtime": 4.4433,
      "eval_samples_per_second": 67.068,
      "eval_steps_per_second": 3.826,
      "step": 400
    },
    {
      "epoch": 0.05857142857142857,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0002980292704735831,
      "loss": 2.663307762145996,
      "step": 410
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.0966796875,
      "learning_rate": 0.00029791820961045317,
      "loss": 2.6410280227661134,
      "step": 420
    },
    {
      "epoch": 0.06142857142857143,
      "grad_norm": 0.3125,
      "learning_rate": 0.0002978041263536029,
      "loss": 2.6257579803466795,
      "step": 430
    },
    {
      "epoch": 0.06285714285714286,
      "grad_norm": 0.310546875,
      "learning_rate": 0.0002976870230340808,
      "loss": 2.650602912902832,
      "step": 440
    },
    {
      "epoch": 0.06428571428571428,
      "grad_norm": 0.115234375,
      "learning_rate": 0.0002975669020446439,
      "loss": 2.6274070739746094,
      "step": 450
    },
    {
      "epoch": 0.06571428571428571,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00029744376583970897,
      "loss": 2.629538154602051,
      "step": 460
    },
    {
      "epoch": 0.06714285714285714,
      "grad_norm": 0.111328125,
      "learning_rate": 0.0002973176169353022,
      "loss": 2.6362348556518556,
      "step": 470
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 1.1015625,
      "learning_rate": 0.00029718845790900785,
      "loss": 2.613158416748047,
      "step": 480
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00029705629139991567,
      "loss": 2.658156967163086,
      "step": 490
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.42578125,
      "learning_rate": 0.000296921120108567,
      "loss": 2.6301057815551756,
      "step": 500
    },
    {
      "epoch": 0.07142857142857142,
      "eval_loss": 3.0305709838867188,
      "eval_runtime": 4.4742,
      "eval_samples_per_second": 66.604,
      "eval_steps_per_second": 3.8,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 7000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.63077257428992e+17,
  "train_batch_size": 18,
  "trial_name": null,
  "trial_params": null
}