{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 282,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 1.3688955307006836,
      "learning_rate": 9e-05,
      "loss": 3.273609924316406,
      "step": 10
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 1.6823779344558716,
      "learning_rate": 0.00019,
      "loss": 2.013600540161133,
      "step": 20
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 1.3549606800079346,
      "learning_rate": 0.0001994182576820673,
      "loss": 0.9827978134155273,
      "step": 30
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.704963207244873,
      "learning_rate": 0.00019741598475167175,
      "loss": 0.6513552665710449,
      "step": 40
    },
    {
      "epoch": 0.1773049645390071,
      "grad_norm": 0.5734719038009644,
      "learning_rate": 0.0001940147464327637,
      "loss": 0.5401387691497803,
      "step": 50
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 0.7053222060203552,
      "learning_rate": 0.00018926338701612738,
      "loss": 0.5485860347747803,
      "step": 60
    },
    {
      "epoch": 0.24822695035460993,
      "grad_norm": 0.5607346892356873,
      "learning_rate": 0.00018323013952726875,
      "loss": 0.5408585071563721,
      "step": 70
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.6696723699569702,
      "learning_rate": 0.00017600164584984546,
      "loss": 0.5451176166534424,
      "step": 80
    },
    {
      "epoch": 0.3191489361702128,
      "grad_norm": 0.6198937892913818,
      "learning_rate": 0.00016768171248431602,
      "loss": 0.4622413158416748,
      "step": 90
    },
    {
      "epoch": 0.3546099290780142,
      "grad_norm": 0.49034929275512695,
      "learning_rate": 0.00015838981981003273,
      "loss": 0.5463218688964844,
      "step": 100
    },
    {
      "epoch": 0.3900709219858156,
      "grad_norm": 0.46550455689430237,
      "learning_rate": 0.00014825940625887342,
      "loss": 0.45171518325805665,
      "step": 110
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.3953458368778229,
      "learning_rate": 0.0001374359520409444,
      "loss": 0.43686976432800295,
      "step": 120
    },
    {
      "epoch": 0.46099290780141844,
      "grad_norm": 0.4815589487552643,
      "learning_rate": 0.00012607488994146704,
      "loss": 0.518321418762207,
      "step": 130
    },
    {
      "epoch": 0.49645390070921985,
      "grad_norm": 0.37568503618240356,
      "learning_rate": 0.00011433937319134511,
      "loss": 0.34571166038513185,
      "step": 140
    },
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 0.5359418392181396,
      "learning_rate": 0.00010239793246643819,
      "loss": 0.48325700759887696,
      "step": 150
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.5425746440887451,
      "learning_rate": 9.042205566275951e-05,
      "loss": 0.429827356338501,
      "step": 160
    },
    {
      "epoch": 0.6028368794326241,
      "grad_norm": 0.5164040923118591,
      "learning_rate": 7.858372520381119e-05,
      "loss": 0.4601579189300537,
      "step": 170
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 0.5248101949691772,
      "learning_rate": 6.705294824614004e-05,
      "loss": 0.3804056644439697,
      "step": 180
    },
    {
      "epoch": 0.6737588652482269,
      "grad_norm": 0.34143301844596863,
      "learning_rate": 5.5995315251183734e-05,
      "loss": 0.3424631118774414,
      "step": 190
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 0.5679530501365662,
      "learning_rate": 4.556962198411631e-05,
      "loss": 0.46054668426513673,
      "step": 200
    },
    {
      "epoch": 0.7446808510638298,
      "grad_norm": 0.46360042691230774,
      "learning_rate": 3.592558908954295e-05,
      "loss": 0.41877241134643556,
      "step": 210
    },
    {
      "epoch": 0.7801418439716312,
      "grad_norm": 0.4703761041164398,
      "learning_rate": 2.720171199261987e-05,
      "loss": 0.4663556575775146,
      "step": 220
    },
    {
      "epoch": 0.8156028368794326,
      "grad_norm": 0.530480146408081,
      "learning_rate": 1.9523272002603742e-05,
      "loss": 0.4497820377349854,
      "step": 230
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.48615142703056335,
      "learning_rate": 1.3000537180852212e-05,
      "loss": 0.3560842275619507,
      "step": 240
    },
    {
      "epoch": 0.8865248226950354,
      "grad_norm": 0.4983954131603241,
      "learning_rate": 7.727178810136093e-06,
      "loss": 0.45021347999572753,
      "step": 250
    },
    {
      "epoch": 0.9219858156028369,
      "grad_norm": 0.5884110927581787,
      "learning_rate": 3.778926205933342e-06,
      "loss": 0.4234372615814209,
      "step": 260
    },
    {
      "epoch": 0.9574468085106383,
      "grad_norm": 0.4866378903388977,
      "learning_rate": 1.212479187605897e-06,
      "loss": 0.4674375534057617,
      "step": 270
    },
    {
      "epoch": 0.9929078014184397,
      "grad_norm": 0.4536786377429962,
      "learning_rate": 6.469382717563255e-08,
      "loss": 0.4669623374938965,
      "step": 280
    }
  ],
  "logging_steps": 10,
  "max_steps": 282,
  "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": 3881477709846528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}