{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1583217890362161,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007916089451810805,
      "eval_loss": 1.6783689260482788,
      "eval_runtime": 26.0033,
      "eval_samples_per_second": 40.918,
      "eval_steps_per_second": 20.459,
      "step": 1
    },
    {
      "epoch": 0.003958044725905403,
      "grad_norm": 2.201160192489624,
      "learning_rate": 5e-05,
      "loss": 1.2759,
      "step": 5
    },
    {
      "epoch": 0.007916089451810805,
      "grad_norm": 1.9438554048538208,
      "learning_rate": 0.0001,
      "loss": 1.2923,
      "step": 10
    },
    {
      "epoch": 0.011874134177716208,
      "grad_norm": 1.907136082649231,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.3826,
      "step": 15
    },
    {
      "epoch": 0.01345735206807837,
      "eval_loss": 1.463081955909729,
      "eval_runtime": 25.9374,
      "eval_samples_per_second": 41.022,
      "eval_steps_per_second": 20.511,
      "step": 17
    },
    {
      "epoch": 0.01583217890362161,
      "grad_norm": 1.7567541599273682,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.3199,
      "step": 20
    },
    {
      "epoch": 0.019790223629527013,
      "grad_norm": 2.00892972946167,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.3275,
      "step": 25
    },
    {
      "epoch": 0.023748268355432416,
      "grad_norm": 1.9397120475769043,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.4035,
      "step": 30
    },
    {
      "epoch": 0.02691470413615674,
      "eval_loss": 1.4135560989379883,
      "eval_runtime": 25.9817,
      "eval_samples_per_second": 40.952,
      "eval_steps_per_second": 20.476,
      "step": 34
    },
    {
      "epoch": 0.027706313081337818,
      "grad_norm": 2.267307758331299,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3731,
      "step": 35
    },
    {
      "epoch": 0.03166435780724322,
      "grad_norm": 2.1668777465820312,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.4531,
      "step": 40
    },
    {
      "epoch": 0.03562240253314863,
      "grad_norm": 2.3527231216430664,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.4923,
      "step": 45
    },
    {
      "epoch": 0.039580447259054026,
      "grad_norm": 4.546135902404785,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6113,
      "step": 50
    },
    {
      "epoch": 0.040372056204235104,
      "eval_loss": 1.4322738647460938,
      "eval_runtime": 25.8037,
      "eval_samples_per_second": 41.234,
      "eval_steps_per_second": 20.617,
      "step": 51
    },
    {
      "epoch": 0.04353849198495943,
      "grad_norm": 1.4479423761367798,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2008,
      "step": 55
    },
    {
      "epoch": 0.04749653671086483,
      "grad_norm": 1.4737143516540527,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2783,
      "step": 60
    },
    {
      "epoch": 0.05145458143677024,
      "grad_norm": 1.5889619588851929,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2898,
      "step": 65
    },
    {
      "epoch": 0.05382940827231348,
      "eval_loss": 1.3583840131759644,
      "eval_runtime": 25.8569,
      "eval_samples_per_second": 41.15,
      "eval_steps_per_second": 20.575,
      "step": 68
    },
    {
      "epoch": 0.055412626162675636,
      "grad_norm": 1.5757551193237305,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2421,
      "step": 70
    },
    {
      "epoch": 0.05937067088858104,
      "grad_norm": 1.9485254287719727,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.3999,
      "step": 75
    },
    {
      "epoch": 0.06332871561448644,
      "grad_norm": 1.766582727432251,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.3335,
      "step": 80
    },
    {
      "epoch": 0.06728676034039184,
      "grad_norm": 1.8992124795913696,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.4323,
      "step": 85
    },
    {
      "epoch": 0.06728676034039184,
      "eval_loss": 1.3332414627075195,
      "eval_runtime": 25.9264,
      "eval_samples_per_second": 41.039,
      "eval_steps_per_second": 20.52,
      "step": 85
    },
    {
      "epoch": 0.07124480506629725,
      "grad_norm": 2.0524697303771973,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3971,
      "step": 90
    },
    {
      "epoch": 0.07520284979220265,
      "grad_norm": 2.077540636062622,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.5092,
      "step": 95
    },
    {
      "epoch": 0.07916089451810805,
      "grad_norm": 5.257937431335449,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5137,
      "step": 100
    },
    {
      "epoch": 0.08074411240847021,
      "eval_loss": 1.3336191177368164,
      "eval_runtime": 25.9341,
      "eval_samples_per_second": 41.027,
      "eval_steps_per_second": 20.513,
      "step": 102
    },
    {
      "epoch": 0.08311893924401345,
      "grad_norm": 1.3437187671661377,
      "learning_rate": 5e-05,
      "loss": 1.0527,
      "step": 105
    },
    {
      "epoch": 0.08707698396991886,
      "grad_norm": 1.438896656036377,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.1543,
      "step": 110
    },
    {
      "epoch": 0.09103502869582426,
      "grad_norm": 1.536594271659851,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.2092,
      "step": 115
    },
    {
      "epoch": 0.09420146447654859,
      "eval_loss": 1.3171730041503906,
      "eval_runtime": 26.0153,
      "eval_samples_per_second": 40.899,
      "eval_steps_per_second": 20.449,
      "step": 119
    },
    {
      "epoch": 0.09499307342172966,
      "grad_norm": 1.4326410293579102,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.2,
      "step": 120
    },
    {
      "epoch": 0.09895111814763506,
      "grad_norm": 1.632464051246643,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.2842,
      "step": 125
    },
    {
      "epoch": 0.10290916287354047,
      "grad_norm": 1.8602347373962402,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.32,
      "step": 130
    },
    {
      "epoch": 0.10686720759944587,
      "grad_norm": 2.0330450534820557,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.3365,
      "step": 135
    },
    {
      "epoch": 0.10765881654462696,
      "eval_loss": 1.3025051355361938,
      "eval_runtime": 26.0309,
      "eval_samples_per_second": 40.875,
      "eval_steps_per_second": 20.437,
      "step": 136
    },
    {
      "epoch": 0.11082525232535127,
      "grad_norm": 1.9935216903686523,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.386,
      "step": 140
    },
    {
      "epoch": 0.11478329705125669,
      "grad_norm": 2.2302839756011963,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.4219,
      "step": 145
    },
    {
      "epoch": 0.11874134177716208,
      "grad_norm": 2.92394757270813,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.4495,
      "step": 150
    },
    {
      "epoch": 0.12111616861270533,
      "eval_loss": 1.2989846467971802,
      "eval_runtime": 25.9807,
      "eval_samples_per_second": 40.954,
      "eval_steps_per_second": 20.477,
      "step": 153
    },
    {
      "epoch": 0.12269938650306748,
      "grad_norm": 1.2223429679870605,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0833,
      "step": 155
    },
    {
      "epoch": 0.12665743122897288,
      "grad_norm": 1.4344662427902222,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.1737,
      "step": 160
    },
    {
      "epoch": 0.1306154759548783,
      "grad_norm": 1.3127787113189697,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.2013,
      "step": 165
    },
    {
      "epoch": 0.13457352068078368,
      "grad_norm": 1.4188923835754395,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2569,
      "step": 170
    },
    {
      "epoch": 0.13457352068078368,
      "eval_loss": 1.2919445037841797,
      "eval_runtime": 25.9521,
      "eval_samples_per_second": 40.999,
      "eval_steps_per_second": 20.499,
      "step": 170
    },
    {
      "epoch": 0.1385315654066891,
      "grad_norm": 1.4968329668045044,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.2569,
      "step": 175
    },
    {
      "epoch": 0.1424896101325945,
      "grad_norm": 1.6496553421020508,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.2825,
      "step": 180
    },
    {
      "epoch": 0.1464476548584999,
      "grad_norm": 1.7205731868743896,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.3165,
      "step": 185
    },
    {
      "epoch": 0.14803087274886206,
      "eval_loss": 1.288711667060852,
      "eval_runtime": 26.0228,
      "eval_samples_per_second": 40.887,
      "eval_steps_per_second": 20.444,
      "step": 187
    },
    {
      "epoch": 0.1504056995844053,
      "grad_norm": 2.053647994995117,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.3614,
      "step": 190
    },
    {
      "epoch": 0.15436374431031072,
      "grad_norm": 2.2067551612854004,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.318,
      "step": 195
    },
    {
      "epoch": 0.1583217890362161,
      "grad_norm": 4.184986114501953,
      "learning_rate": 0.0,
      "loss": 1.5303,
      "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": 7728482431795200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}