{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09014084507042254,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004507042253521127,
      "eval_loss": NaN,
      "eval_runtime": 70.3612,
      "eval_samples_per_second": 13.289,
      "eval_steps_per_second": 6.651,
      "step": 1
    },
    {
      "epoch": 0.0022535211267605635,
      "grad_norm": 2.048182487487793,
      "learning_rate": 5e-05,
      "loss": 2.9451,
      "step": 5
    },
    {
      "epoch": 0.004507042253521127,
      "grad_norm": 0.45942896604537964,
      "learning_rate": 0.0001,
      "loss": 3.126,
      "step": 10
    },
    {
      "epoch": 0.0067605633802816905,
      "grad_norm": 0.9196521639823914,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.2125,
      "step": 15
    },
    {
      "epoch": 0.009014084507042254,
      "grad_norm": 1.8022595643997192,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.8373,
      "step": 20
    },
    {
      "epoch": 0.011267605633802818,
      "grad_norm": 2.658519744873047,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.1407,
      "step": 25
    },
    {
      "epoch": 0.013521126760563381,
      "grad_norm": 2.7902963161468506,
      "learning_rate": 9.729086208503174e-05,
      "loss": 4.0626,
      "step": 30
    },
    {
      "epoch": 0.015774647887323943,
      "grad_norm": 3.3748669624328613,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.981,
      "step": 35
    },
    {
      "epoch": 0.018028169014084508,
      "grad_norm": 7.324255466461182,
      "learning_rate": 9.397368756032445e-05,
      "loss": 4.6299,
      "step": 40
    },
    {
      "epoch": 0.02028169014084507,
      "grad_norm": 0.0,
      "learning_rate": 9.185832391312644e-05,
      "loss": 7.6624,
      "step": 45
    },
    {
      "epoch": 0.022535211267605635,
      "grad_norm": 0.0,
      "learning_rate": 8.945702546981969e-05,
      "loss": 93.2553,
      "step": 50
    },
    {
      "epoch": 0.022535211267605635,
      "eval_loss": NaN,
      "eval_runtime": 70.9161,
      "eval_samples_per_second": 13.185,
      "eval_steps_per_second": 6.599,
      "step": 50
    },
    {
      "epoch": 0.024788732394366197,
      "grad_norm": 5.263653755187988,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.3143,
      "step": 55
    },
    {
      "epoch": 0.027042253521126762,
      "grad_norm": 1.324364185333252,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.088,
      "step": 60
    },
    {
      "epoch": 0.029295774647887324,
      "grad_norm": 1.4408124685287476,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.1917,
      "step": 65
    },
    {
      "epoch": 0.031549295774647886,
      "grad_norm": 2.004734992980957,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.4692,
      "step": 70
    },
    {
      "epoch": 0.03380281690140845,
      "grad_norm": 2.3384110927581787,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.8527,
      "step": 75
    },
    {
      "epoch": 0.036056338028169016,
      "grad_norm": 2.706864356994629,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.0247,
      "step": 80
    },
    {
      "epoch": 0.03830985915492958,
      "grad_norm": 3.0277934074401855,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.9878,
      "step": 85
    },
    {
      "epoch": 0.04056338028169014,
      "grad_norm": 9.624770164489746,
      "learning_rate": 6.227427435703997e-05,
      "loss": 4.3297,
      "step": 90
    },
    {
      "epoch": 0.0428169014084507,
      "grad_norm": 0.0,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 11.911,
      "step": 95
    },
    {
      "epoch": 0.04507042253521127,
      "grad_norm": 0.0,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.04507042253521127,
      "eval_loss": NaN,
      "eval_runtime": 70.987,
      "eval_samples_per_second": 13.171,
      "eval_steps_per_second": 6.593,
      "step": 100
    },
    {
      "epoch": 0.04732394366197183,
      "grad_norm": 2.5935168266296387,
      "learning_rate": 5e-05,
      "loss": 2.4918,
      "step": 105
    },
    {
      "epoch": 0.049577464788732394,
      "grad_norm": 1.0245670080184937,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.5954,
      "step": 110
    },
    {
      "epoch": 0.051830985915492955,
      "grad_norm": 2.9991183280944824,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.1508,
      "step": 115
    },
    {
      "epoch": 0.054084507042253524,
      "grad_norm": 2.4905731678009033,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.4471,
      "step": 120
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 8.376192092895508,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.6582,
      "step": 125
    },
    {
      "epoch": 0.05859154929577465,
      "grad_norm": 9.796344757080078,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.8493,
      "step": 130
    },
    {
      "epoch": 0.06084507042253521,
      "grad_norm": 15.544617652893066,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 4.088,
      "step": 135
    },
    {
      "epoch": 0.06309859154929577,
      "grad_norm": 16.23596954345703,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 4.6748,
      "step": 140
    },
    {
      "epoch": 0.06535211267605634,
      "grad_norm": 0.0,
      "learning_rate": 1.928936436551661e-05,
      "loss": 19.1379,
      "step": 145
    },
    {
      "epoch": 0.0676056338028169,
      "grad_norm": 0.0,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 77.277,
      "step": 150
    },
    {
      "epoch": 0.0676056338028169,
      "eval_loss": NaN,
      "eval_runtime": 70.8459,
      "eval_samples_per_second": 13.198,
      "eval_steps_per_second": 6.606,
      "step": 150
    },
    {
      "epoch": 0.06985915492957746,
      "grad_norm": 42.216453552246094,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.2347,
      "step": 155
    },
    {
      "epoch": 0.07211267605633803,
      "grad_norm": 0.8450806736946106,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.1994,
      "step": 160
    },
    {
      "epoch": 0.07436619718309859,
      "grad_norm": 1.1214216947555542,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.1031,
      "step": 165
    },
    {
      "epoch": 0.07661971830985916,
      "grad_norm": 1.5792582035064697,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.3192,
      "step": 170
    },
    {
      "epoch": 0.07887323943661972,
      "grad_norm": 2.753544807434082,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.4139,
      "step": 175
    },
    {
      "epoch": 0.08112676056338028,
      "grad_norm": 2.4559876918792725,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.8069,
      "step": 180
    },
    {
      "epoch": 0.08338028169014085,
      "grad_norm": 2.7296509742736816,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.7459,
      "step": 185
    },
    {
      "epoch": 0.0856338028169014,
      "grad_norm": 4.482161521911621,
      "learning_rate": 6.819348298638839e-07,
      "loss": 4.4724,
      "step": 190
    },
    {
      "epoch": 0.08788732394366197,
      "grad_norm": 0.0,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 8.4755,
      "step": 195
    },
    {
      "epoch": 0.09014084507042254,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.09014084507042254,
      "eval_loss": NaN,
      "eval_runtime": 71.2258,
      "eval_samples_per_second": 13.127,
      "eval_steps_per_second": 6.571,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 7.031536445974118e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}