{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10471204188481675,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020942408376963353,
      "grad_norm": 0.34981271624565125,
      "learning_rate": 1e-05,
      "loss": 3.2781,
      "step": 1
    },
    {
      "epoch": 0.0020942408376963353,
      "eval_loss": 1.7277591228485107,
      "eval_runtime": 53.6735,
      "eval_samples_per_second": 7.508,
      "eval_steps_per_second": 0.95,
      "step": 1
    },
    {
      "epoch": 0.004188481675392671,
      "grad_norm": 0.801185667514801,
      "learning_rate": 2e-05,
      "loss": 3.5415,
      "step": 2
    },
    {
      "epoch": 0.0062827225130890054,
      "grad_norm": 0.3677161931991577,
      "learning_rate": 3e-05,
      "loss": 3.5543,
      "step": 3
    },
    {
      "epoch": 0.008376963350785341,
      "grad_norm": 0.448595255613327,
      "learning_rate": 4e-05,
      "loss": 3.4746,
      "step": 4
    },
    {
      "epoch": 0.010471204188481676,
      "grad_norm": 0.40933072566986084,
      "learning_rate": 5e-05,
      "loss": 3.3815,
      "step": 5
    },
    {
      "epoch": 0.012565445026178011,
      "grad_norm": 0.4692118465900421,
      "learning_rate": 6e-05,
      "loss": 3.5705,
      "step": 6
    },
    {
      "epoch": 0.014659685863874346,
      "grad_norm": 0.5187078714370728,
      "learning_rate": 7e-05,
      "loss": 3.3902,
      "step": 7
    },
    {
      "epoch": 0.016753926701570682,
      "grad_norm": 0.4143497347831726,
      "learning_rate": 8e-05,
      "loss": 3.1211,
      "step": 8
    },
    {
      "epoch": 0.018848167539267015,
      "grad_norm": 0.4992891848087311,
      "learning_rate": 9e-05,
      "loss": 3.3897,
      "step": 9
    },
    {
      "epoch": 0.018848167539267015,
      "eval_loss": 1.690635323524475,
      "eval_runtime": 54.4943,
      "eval_samples_per_second": 7.395,
      "eval_steps_per_second": 0.936,
      "step": 9
    },
    {
      "epoch": 0.020942408376963352,
      "grad_norm": 0.5181413292884827,
      "learning_rate": 0.0001,
      "loss": 3.1257,
      "step": 10
    },
    {
      "epoch": 0.023036649214659685,
      "grad_norm": 0.573737621307373,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.135,
      "step": 11
    },
    {
      "epoch": 0.025130890052356022,
      "grad_norm": 0.5204129219055176,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.2358,
      "step": 12
    },
    {
      "epoch": 0.027225130890052355,
      "grad_norm": 0.5474736094474792,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.2861,
      "step": 13
    },
    {
      "epoch": 0.02931937172774869,
      "grad_norm": 0.5524812340736389,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.2345,
      "step": 14
    },
    {
      "epoch": 0.031413612565445025,
      "grad_norm": 0.5993866324424744,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.025,
      "step": 15
    },
    {
      "epoch": 0.033507853403141365,
      "grad_norm": 0.5874714851379395,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.9435,
      "step": 16
    },
    {
      "epoch": 0.0356020942408377,
      "grad_norm": 0.5276877284049988,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.9228,
      "step": 17
    },
    {
      "epoch": 0.03769633507853403,
      "grad_norm": 0.5134425759315491,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.0417,
      "step": 18
    },
    {
      "epoch": 0.03769633507853403,
      "eval_loss": 1.5175120830535889,
      "eval_runtime": 54.491,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 0.936,
      "step": 18
    },
    {
      "epoch": 0.039790575916230364,
      "grad_norm": 0.6345006823539734,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.0776,
      "step": 19
    },
    {
      "epoch": 0.041884816753926704,
      "grad_norm": 0.5065171122550964,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.7851,
      "step": 20
    },
    {
      "epoch": 0.04397905759162304,
      "grad_norm": 0.6690090894699097,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.9525,
      "step": 21
    },
    {
      "epoch": 0.04607329842931937,
      "grad_norm": 0.5420049428939819,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.0601,
      "step": 22
    },
    {
      "epoch": 0.048167539267015703,
      "grad_norm": 0.6415935754776001,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.9687,
      "step": 23
    },
    {
      "epoch": 0.050261780104712044,
      "grad_norm": 0.4800170063972473,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.6966,
      "step": 24
    },
    {
      "epoch": 0.05235602094240838,
      "grad_norm": 0.5702900290489197,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.9085,
      "step": 25
    },
    {
      "epoch": 0.05445026178010471,
      "grad_norm": 0.5642029047012329,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.8261,
      "step": 26
    },
    {
      "epoch": 0.05654450261780105,
      "grad_norm": 0.6375811100006104,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.9975,
      "step": 27
    },
    {
      "epoch": 0.05654450261780105,
      "eval_loss": 1.4399325847625732,
      "eval_runtime": 54.4669,
      "eval_samples_per_second": 7.399,
      "eval_steps_per_second": 0.936,
      "step": 27
    },
    {
      "epoch": 0.05863874345549738,
      "grad_norm": 0.5609163045883179,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.794,
      "step": 28
    },
    {
      "epoch": 0.060732984293193716,
      "grad_norm": 0.6879402995109558,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.7103,
      "step": 29
    },
    {
      "epoch": 0.06282722513089005,
      "grad_norm": 0.5450217127799988,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.7324,
      "step": 30
    },
    {
      "epoch": 0.06492146596858639,
      "grad_norm": 0.6222276091575623,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.9903,
      "step": 31
    },
    {
      "epoch": 0.06701570680628273,
      "grad_norm": 0.5290335416793823,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.8003,
      "step": 32
    },
    {
      "epoch": 0.06910994764397906,
      "grad_norm": 0.643876850605011,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.7036,
      "step": 33
    },
    {
      "epoch": 0.0712041884816754,
      "grad_norm": 0.6455150842666626,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.758,
      "step": 34
    },
    {
      "epoch": 0.07329842931937172,
      "grad_norm": 0.6009905934333801,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.86,
      "step": 35
    },
    {
      "epoch": 0.07539267015706806,
      "grad_norm": 0.5729888081550598,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.7763,
      "step": 36
    },
    {
      "epoch": 0.07539267015706806,
      "eval_loss": 1.404931902885437,
      "eval_runtime": 54.4896,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 0.936,
      "step": 36
    },
    {
      "epoch": 0.0774869109947644,
      "grad_norm": 0.6812015175819397,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.8235,
      "step": 37
    },
    {
      "epoch": 0.07958115183246073,
      "grad_norm": 0.5715813636779785,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.6603,
      "step": 38
    },
    {
      "epoch": 0.08167539267015707,
      "grad_norm": 0.5004135966300964,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.7355,
      "step": 39
    },
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 0.5744718313217163,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.8711,
      "step": 40
    },
    {
      "epoch": 0.08586387434554973,
      "grad_norm": 0.6692417860031128,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.6734,
      "step": 41
    },
    {
      "epoch": 0.08795811518324607,
      "grad_norm": 0.601163923740387,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.7693,
      "step": 42
    },
    {
      "epoch": 0.09005235602094241,
      "grad_norm": 0.5379462838172913,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.8922,
      "step": 43
    },
    {
      "epoch": 0.09214659685863874,
      "grad_norm": 0.5941004753112793,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.5804,
      "step": 44
    },
    {
      "epoch": 0.09424083769633508,
      "grad_norm": 0.5219014286994934,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.9221,
      "step": 45
    },
    {
      "epoch": 0.09424083769633508,
      "eval_loss": 1.3878324031829834,
      "eval_runtime": 54.4731,
      "eval_samples_per_second": 7.398,
      "eval_steps_per_second": 0.936,
      "step": 45
    },
    {
      "epoch": 0.09633507853403141,
      "grad_norm": 0.6687893271446228,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.7832,
      "step": 46
    },
    {
      "epoch": 0.09842931937172775,
      "grad_norm": 0.5477647185325623,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.6517,
      "step": 47
    },
    {
      "epoch": 0.10052356020942409,
      "grad_norm": 0.5874961018562317,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.6161,
      "step": 48
    },
    {
      "epoch": 0.10261780104712041,
      "grad_norm": 0.518980860710144,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.7782,
      "step": 49
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 0.8065228462219238,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.7772,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.26732322177024e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}