{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 287,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 1.8211296796798706,
      "learning_rate": 9e-05,
      "loss": 3.1205413818359373,
      "step": 10
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 2.2983880043029785,
      "learning_rate": 0.00019,
      "loss": 1.7317464828491211,
      "step": 20
    },
    {
      "epoch": 0.10480349344978165,
      "grad_norm": 0.7729952335357666,
      "learning_rate": 0.00019986979101058972,
      "loss": 0.8218430519104004,
      "step": 30
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 0.7794175744056702,
      "learning_rate": 0.00019942012118204737,
      "loss": 0.6791059017181397,
      "step": 40
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 0.6147348880767822,
      "learning_rate": 0.0001986508282827419,
      "loss": 0.5647100448608399,
      "step": 50
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 0.5721135139465332,
      "learning_rate": 0.0001975643854917025,
      "loss": 0.4464299201965332,
      "step": 60
    },
    {
      "epoch": 0.2445414847161572,
      "grad_norm": 0.4910798668861389,
      "learning_rate": 0.00019616428558460634,
      "loss": 0.5486050605773926,
      "step": 70
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 0.4786812365055084,
      "learning_rate": 0.00019445502970494787,
      "loss": 0.6309103965759277,
      "step": 80
    },
    {
      "epoch": 0.314410480349345,
      "grad_norm": 0.3899824321269989,
      "learning_rate": 0.00019244211289343397,
      "loss": 0.47461185455322263,
      "step": 90
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 0.21079467236995697,
      "learning_rate": 0.00019013200642212545,
      "loss": 0.41464600563049314,
      "step": 100
    },
    {
      "epoch": 0.38427947598253276,
      "grad_norm": 0.42337626218795776,
      "learning_rate": 0.00018753213699011876,
      "loss": 0.4927196979522705,
      "step": 110
    },
    {
      "epoch": 0.4192139737991266,
      "grad_norm": 0.4860546588897705,
      "learning_rate": 0.00018465086284765093,
      "loss": 0.4953155040740967,
      "step": 120
    },
    {
      "epoch": 0.45414847161572053,
      "grad_norm": 0.5280138850212097,
      "learning_rate": 0.0001814974469253861,
      "loss": 0.3739574432373047,
      "step": 130
    },
    {
      "epoch": 0.4890829694323144,
      "grad_norm": 0.3762610852718353,
      "learning_rate": 0.000178082027055269,
      "loss": 0.5111323833465576,
      "step": 140
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 0.5376149415969849,
      "learning_rate": 0.00017441558337868198,
      "loss": 0.5593331813812256,
      "step": 150
    },
    {
      "epoch": 0.5589519650655022,
      "grad_norm": 0.472368448972702,
      "learning_rate": 0.00017050990304668423,
      "loss": 0.5056246757507324,
      "step": 160
    },
    {
      "epoch": 0.5938864628820961,
      "grad_norm": 0.44528254866600037,
      "learning_rate": 0.00016637754232581698,
      "loss": 0.4254063606262207,
      "step": 170
    },
    {
      "epoch": 0.62882096069869,
      "grad_norm": 0.38811150193214417,
      "learning_rate": 0.0001620317862313006,
      "loss": 0.5141812324523926,
      "step": 180
    },
    {
      "epoch": 0.6637554585152838,
      "grad_norm": 0.5775936841964722,
      "learning_rate": 0.00015748660581739655,
      "loss": 0.49105257987976075,
      "step": 190
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 0.47975367307662964,
      "learning_rate": 0.0001527566132622413,
      "loss": 0.5170726299285888,
      "step": 200
    },
    {
      "epoch": 0.7336244541484717,
      "grad_norm": 0.3569624125957489,
      "learning_rate": 0.0001478570148915483,
      "loss": 0.42121267318725586,
      "step": 210
    },
    {
      "epoch": 0.7685589519650655,
      "grad_norm": 0.5059508085250854,
      "learning_rate": 0.0001428035622922009,
      "loss": 0.41593084335327146,
      "step": 220
    },
    {
      "epoch": 0.8034934497816594,
      "grad_norm": 0.45586642622947693,
      "learning_rate": 0.0001376125016728996,
      "loss": 0.38859803676605226,
      "step": 230
    },
    {
      "epoch": 0.8384279475982532,
      "grad_norm": 0.41792041063308716,
      "learning_rate": 0.00013230052163466335,
      "loss": 0.4688732147216797,
      "step": 240
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 0.46951380372047424,
      "learning_rate": 0.0001268846995190953,
      "loss": 0.4584070682525635,
      "step": 250
    },
    {
      "epoch": 0.9082969432314411,
      "grad_norm": 0.44923996925354004,
      "learning_rate": 0.00012138244650689714,
      "loss": 0.4507625102996826,
      "step": 260
    },
    {
      "epoch": 0.9432314410480349,
      "grad_norm": 0.4775308072566986,
      "learning_rate": 0.00011581145164313307,
      "loss": 0.4381150722503662,
      "step": 270
    },
    {
      "epoch": 0.9781659388646288,
      "grad_norm": 0.3662133812904358,
      "learning_rate": 0.000110189624969195,
      "loss": 0.4980125427246094,
      "step": 280
    }
  ],
  "logging_steps": 10,
  "max_steps": 574,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3744560261514240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}