{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024451372333272204,
  "eval_steps": 34,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004890274466654441,
      "grad_norm": Infinity,
      "learning_rate": 6.666666666666667e-06,
      "loss": 9.0513,
      "step": 1
    },
    {
      "epoch": 0.0004890274466654441,
      "eval_loss": 9.337614059448242,
      "eval_runtime": 876.8823,
      "eval_samples_per_second": 2.946,
      "eval_steps_per_second": 0.982,
      "step": 1
    },
    {
      "epoch": 0.0009780548933308881,
      "grad_norm": Infinity,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 9.4794,
      "step": 2
    },
    {
      "epoch": 0.0014670823399963323,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 8.6541,
      "step": 3
    },
    {
      "epoch": 0.0019561097866617762,
      "grad_norm": Infinity,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 10.0028,
      "step": 4
    },
    {
      "epoch": 0.0024451372333272204,
      "grad_norm": Infinity,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 8.8885,
      "step": 5
    },
    {
      "epoch": 0.0029341646799926646,
      "grad_norm": 8.087092190490132e+18,
      "learning_rate": 4e-05,
      "loss": 9.0537,
      "step": 6
    },
    {
      "epoch": 0.0034231921266581087,
      "grad_norm": Infinity,
      "learning_rate": 4.666666666666667e-05,
      "loss": 8.6808,
      "step": 7
    },
    {
      "epoch": 0.0039122195733235525,
      "grad_norm": Infinity,
      "learning_rate": 5.333333333333333e-05,
      "loss": 8.8092,
      "step": 8
    },
    {
      "epoch": 0.004401247019988997,
      "grad_norm": Infinity,
      "learning_rate": 6e-05,
      "loss": 9.7075,
      "step": 9
    },
    {
      "epoch": 0.004890274466654441,
      "grad_norm": Infinity,
      "learning_rate": 6.666666666666667e-05,
      "loss": 9.2624,
      "step": 10
    },
    {
      "epoch": 0.005379301913319885,
      "grad_norm": Infinity,
      "learning_rate": 7.333333333333333e-05,
      "loss": 8.4931,
      "step": 11
    },
    {
      "epoch": 0.005868329359985329,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 9.3205,
      "step": 12
    },
    {
      "epoch": 0.006357356806650773,
      "grad_norm": Infinity,
      "learning_rate": 8.666666666666667e-05,
      "loss": 9.8934,
      "step": 13
    },
    {
      "epoch": 0.0068463842533162175,
      "grad_norm": Infinity,
      "learning_rate": 9.333333333333334e-05,
      "loss": 9.1796,
      "step": 14
    },
    {
      "epoch": 0.007335411699981661,
      "grad_norm": 1.2167695950759854e+19,
      "learning_rate": 0.0001,
      "loss": 9.3987,
      "step": 15
    },
    {
      "epoch": 0.007824439146647105,
      "grad_norm": 5.4412064499695616e+17,
      "learning_rate": 0.00010666666666666667,
      "loss": 9.0077,
      "step": 16
    },
    {
      "epoch": 0.00831346659331255,
      "grad_norm": Infinity,
      "learning_rate": 0.00011333333333333334,
      "loss": 9.8072,
      "step": 17
    },
    {
      "epoch": 0.008802494039977994,
      "grad_norm": Infinity,
      "learning_rate": 0.00012,
      "loss": 9.2775,
      "step": 18
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 9.411642512390488e+18,
      "learning_rate": 0.00012666666666666666,
      "loss": 9.1326,
      "step": 19
    },
    {
      "epoch": 0.009780548933308882,
      "grad_norm": 1.3229755463714734e+18,
      "learning_rate": 0.00013333333333333334,
      "loss": 8.2326,
      "step": 20
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": Infinity,
      "learning_rate": 0.00014,
      "loss": 9.7804,
      "step": 21
    },
    {
      "epoch": 0.01075860382663977,
      "grad_norm": Infinity,
      "learning_rate": 0.00014666666666666666,
      "loss": 9.2763,
      "step": 22
    },
    {
      "epoch": 0.011247631273305215,
      "grad_norm": Infinity,
      "learning_rate": 0.00015333333333333334,
      "loss": 9.1653,
      "step": 23
    },
    {
      "epoch": 0.011736658719970658,
      "grad_norm": Infinity,
      "learning_rate": 0.00016,
      "loss": 8.6687,
      "step": 24
    },
    {
      "epoch": 0.012225686166636102,
      "grad_norm": Infinity,
      "learning_rate": 0.0001666666666666667,
      "loss": 9.1022,
      "step": 25
    },
    {
      "epoch": 0.012714713613301546,
      "grad_norm": 3.8149141971211387e+18,
      "learning_rate": 0.00017333333333333334,
      "loss": 8.8296,
      "step": 26
    },
    {
      "epoch": 0.013203741059966991,
      "grad_norm": Infinity,
      "learning_rate": 0.00018,
      "loss": 9.8113,
      "step": 27
    },
    {
      "epoch": 0.013692768506632435,
      "grad_norm": Infinity,
      "learning_rate": 0.0001866666666666667,
      "loss": 9.417,
      "step": 28
    },
    {
      "epoch": 0.014181795953297879,
      "grad_norm": Infinity,
      "learning_rate": 0.00019333333333333333,
      "loss": 9.168,
      "step": 29
    },
    {
      "epoch": 0.014670823399963322,
      "grad_norm": Infinity,
      "learning_rate": 0.0002,
      "loss": 10.644,
      "step": 30
    },
    {
      "epoch": 0.015159850846628768,
      "grad_norm": Infinity,
      "learning_rate": 0.00019998292504580528,
      "loss": 8.4753,
      "step": 31
    },
    {
      "epoch": 0.01564887829329421,
      "grad_norm": Infinity,
      "learning_rate": 0.0001999317060143023,
      "loss": 9.0983,
      "step": 32
    },
    {
      "epoch": 0.016137905739959654,
      "grad_norm": 1.1584913556352532e+18,
      "learning_rate": 0.0001998463603967434,
      "loss": 7.7383,
      "step": 33
    },
    {
      "epoch": 0.0166269331866251,
      "grad_norm": Infinity,
      "learning_rate": 0.00019972691733857883,
      "loss": 9.1453,
      "step": 34
    },
    {
      "epoch": 0.0166269331866251,
      "eval_loss": 9.285249710083008,
      "eval_runtime": 881.9276,
      "eval_samples_per_second": 2.929,
      "eval_steps_per_second": 0.976,
      "step": 34
    },
    {
      "epoch": 0.017115960633290545,
      "grad_norm": Infinity,
      "learning_rate": 0.00019957341762950344,
      "loss": 10.3859,
      "step": 35
    },
    {
      "epoch": 0.017604988079955988,
      "grad_norm": Infinity,
      "learning_rate": 0.0001993859136895274,
      "loss": 8.1513,
      "step": 36
    },
    {
      "epoch": 0.018094015526621432,
      "grad_norm": 7.999064190058758e+18,
      "learning_rate": 0.00019916446955107428,
      "loss": 9.6598,
      "step": 37
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 2.2595998866116444e+18,
      "learning_rate": 0.0001989091608371146,
      "loss": 8.1904,
      "step": 38
    },
    {
      "epoch": 0.01907207041995232,
      "grad_norm": Infinity,
      "learning_rate": 0.00019862007473534025,
      "loss": 9.4891,
      "step": 39
    },
    {
      "epoch": 0.019561097866617763,
      "grad_norm": Infinity,
      "learning_rate": 0.0001982973099683902,
      "loss": 9.481,
      "step": 40
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": Infinity,
      "learning_rate": 0.0001979409767601366,
      "loss": 9.684,
      "step": 41
    },
    {
      "epoch": 0.02053915275994865,
      "grad_norm": 1.0845123650277868e+18,
      "learning_rate": 0.00019755119679804367,
      "loss": 9.2871,
      "step": 42
    },
    {
      "epoch": 0.021028180206614098,
      "grad_norm": Infinity,
      "learning_rate": 0.0001971281031916114,
      "loss": 9.423,
      "step": 43
    },
    {
      "epoch": 0.02151720765327954,
      "grad_norm": Infinity,
      "learning_rate": 0.00019667184042691875,
      "loss": 8.6827,
      "step": 44
    },
    {
      "epoch": 0.022006235099944985,
      "grad_norm": Infinity,
      "learning_rate": 0.00019618256431728194,
      "loss": 9.9237,
      "step": 45
    },
    {
      "epoch": 0.02249526254661043,
      "grad_norm": 9.941431195118076e+18,
      "learning_rate": 0.0001956604419500441,
      "loss": 8.1136,
      "step": 46
    },
    {
      "epoch": 0.022984289993275873,
      "grad_norm": Infinity,
      "learning_rate": 0.00019510565162951537,
      "loss": 9.7949,
      "step": 47
    },
    {
      "epoch": 0.023473317439941317,
      "grad_norm": Infinity,
      "learning_rate": 0.00019451838281608197,
      "loss": 10.1889,
      "step": 48
    },
    {
      "epoch": 0.02396234488660676,
      "grad_norm": Infinity,
      "learning_rate": 0.00019389883606150566,
      "loss": 8.871,
      "step": 49
    },
    {
      "epoch": 0.024451372333272204,
      "grad_norm": Infinity,
      "learning_rate": 0.00019324722294043558,
      "loss": 10.5181,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.102239837978624e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}