{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.125,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.31839632987976074,
      "learning_rate": 4.5e-06,
      "loss": 1.2127,
      "step": 10
    },
    {
      "grad_norm": 0.19609376788139343,
      "learning_rate": 9.5e-06,
      "loss": 1.1842,
      "step": 20
    },
    {
      "grad_norm": 0.4635807275772095,
      "learning_rate": 1.45e-05,
      "loss": 1.1838,
      "step": 30
    },
    {
      "grad_norm": 0.3277273178100586,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 1.1629,
      "step": 40
    },
    {
      "grad_norm": 0.40489643812179565,
      "learning_rate": 2.45e-05,
      "loss": 1.1264,
      "step": 50
    },
    {
      "grad_norm": 1.2546579837799072,
      "learning_rate": 2.95e-05,
      "loss": 1.1117,
      "step": 60
    },
    {
      "grad_norm": 0.3789711594581604,
      "learning_rate": 3.45e-05,
      "loss": 1.1066,
      "step": 70
    },
    {
      "grad_norm": 0.3612673878669739,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 1.1082,
      "step": 80
    },
    {
      "grad_norm": 0.28633758425712585,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 1.1211,
      "step": 90
    },
    {
      "grad_norm": 0.41268351674079895,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 1.0998,
      "step": 100
    },
    {
      "grad_norm": 0.2796061933040619,
      "learning_rate": 5.45e-05,
      "loss": 1.1131,
      "step": 110
    },
    {
      "grad_norm": 0.3423110544681549,
      "learning_rate": 5.95e-05,
      "loss": 1.1004,
      "step": 120
    },
    {
      "grad_norm": 0.33770301938056946,
      "learning_rate": 6.450000000000001e-05,
      "loss": 1.0887,
      "step": 130
    },
    {
      "grad_norm": 0.4104395806789398,
      "learning_rate": 6.95e-05,
      "loss": 1.1043,
      "step": 140
    },
    {
      "grad_norm": 0.38792213797569275,
      "learning_rate": 7.450000000000001e-05,
      "loss": 1.093,
      "step": 150
    },
    {
      "grad_norm": 0.31532591581344604,
      "learning_rate": 7.950000000000001e-05,
      "loss": 1.0992,
      "step": 160
    },
    {
      "grad_norm": 0.37639284133911133,
      "learning_rate": 8.450000000000001e-05,
      "loss": 1.1033,
      "step": 170
    },
    {
      "grad_norm": 0.4326634407043457,
      "learning_rate": 8.950000000000001e-05,
      "loss": 1.0834,
      "step": 180
    },
    {
      "grad_norm": 0.4046025276184082,
      "learning_rate": 9.449999999999999e-05,
      "loss": 1.0852,
      "step": 190
    },
    {
      "grad_norm": 0.45471683144569397,
      "learning_rate": 9.95e-05,
      "loss": 1.0775,
      "step": 200
    },
    {
      "grad_norm": 0.5478058457374573,
      "learning_rate": 9.999861593790126e-05,
      "loss": 1.0781,
      "step": 210
    },
    {
      "grad_norm": 0.3471389412879944,
      "learning_rate": 9.999383162408304e-05,
      "loss": 1.0828,
      "step": 220
    },
    {
      "grad_norm": 0.4683222770690918,
      "learning_rate": 9.998563029828259e-05,
      "loss": 1.0568,
      "step": 230
    },
    {
      "grad_norm": 0.3368767499923706,
      "learning_rate": 9.997401252104962e-05,
      "loss": 1.0364,
      "step": 240
    },
    {
      "grad_norm": 0.425786554813385,
      "learning_rate": 9.995897908644378e-05,
      "loss": 1.0061,
      "step": 250
    },
    {
      "grad_norm": 0.38125181198120117,
      "learning_rate": 9.994053102198034e-05,
      "loss": 1.0064,
      "step": 260
    },
    {
      "grad_norm": 0.569205105304718,
      "learning_rate": 9.991866958856003e-05,
      "loss": 1.0119,
      "step": 270
    },
    {
      "grad_norm": 0.360039621591568,
      "learning_rate": 9.989339628038276e-05,
      "loss": 0.9783,
      "step": 280
    },
    {
      "grad_norm": 0.3894808292388916,
      "learning_rate": 9.98647128248456e-05,
      "loss": 0.9876,
      "step": 290
    },
    {
      "grad_norm": 0.49482613801956177,
      "learning_rate": 9.98326211824246e-05,
      "loss": 0.9774,
      "step": 300
    },
    {
      "grad_norm": 0.43771424889564514,
      "learning_rate": 9.979712354654091e-05,
      "loss": 0.9528,
      "step": 310
    },
    {
      "grad_norm": 0.3924391269683838,
      "learning_rate": 9.975822234341079e-05,
      "loss": 0.949,
      "step": 320
    },
    {
      "grad_norm": 0.3948723077774048,
      "learning_rate": 9.97159202318798e-05,
      "loss": 0.95,
      "step": 330
    },
    {
      "grad_norm": 0.4701744019985199,
      "learning_rate": 9.967022010324105e-05,
      "loss": 0.9263,
      "step": 340
    },
    {
      "grad_norm": 0.5202460289001465,
      "learning_rate": 9.962112508103765e-05,
      "loss": 0.9409,
      "step": 350
    },
    {
      "grad_norm": 0.4282516837120056,
      "learning_rate": 9.956863852084914e-05,
      "loss": 0.9107,
      "step": 360
    },
    {
      "grad_norm": 0.5906583666801453,
      "learning_rate": 9.951276401006221e-05,
      "loss": 0.9072,
      "step": 370
    },
    {
      "grad_norm": 0.4856233298778534,
      "learning_rate": 9.945350536762543e-05,
      "loss": 0.9142,
      "step": 380
    },
    {
      "grad_norm": 0.44197753071784973,
      "learning_rate": 9.939086664378829e-05,
      "loss": 0.8903,
      "step": 390
    },
    {
      "grad_norm": 0.6055497527122498,
      "learning_rate": 9.932485211982437e-05,
      "loss": 0.8942,
      "step": 400
    },
    {
      "grad_norm": 0.5160871744155884,
      "learning_rate": 9.92554663077387e-05,
      "loss": 0.8765,
      "step": 410
    },
    {
      "grad_norm": 0.479907751083374,
      "learning_rate": 9.918271394995935e-05,
      "loss": 0.8774,
      "step": 420
    },
    {
      "grad_norm": 0.5040944218635559,
      "learning_rate": 9.910660001901335e-05,
      "loss": 0.8775,
      "step": 430
    },
    {
      "grad_norm": 0.5206490755081177,
      "learning_rate": 9.902712971718675e-05,
      "loss": 0.8647,
      "step": 440
    },
    {
      "grad_norm": 0.44746702909469604,
      "learning_rate": 9.894430847616915e-05,
      "loss": 0.8619,
      "step": 450
    },
    {
      "grad_norm": 0.4645554721355438,
      "learning_rate": 9.885814195668232e-05,
      "loss": 0.8444,
      "step": 460
    },
    {
      "grad_norm": 0.47834452986717224,
      "learning_rate": 9.876863604809344e-05,
      "loss": 0.8333,
      "step": 470
    },
    {
      "grad_norm": 0.43582776188850403,
      "learning_rate": 9.867579686801245e-05,
      "loss": 0.8598,
      "step": 480
    },
    {
      "grad_norm": 0.4257030189037323,
      "learning_rate": 9.8579630761874e-05,
      "loss": 0.8198,
      "step": 490
    },
    {
      "grad_norm": 0.5325835943222046,
      "learning_rate": 9.848014430250367e-05,
      "loss": 0.8271,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}