{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 179,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 4.828463554382324,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.4719,
      "step": 5
    },
    {
      "epoch": 0.055865921787709494,
      "grad_norm": 3.8758130073547363,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.4276,
      "step": 10
    },
    {
      "epoch": 0.08379888268156424,
      "grad_norm": 3.6739842891693115,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.4003,
      "step": 15
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": 3.945585250854492,
      "learning_rate": 9.999635004278054e-06,
      "loss": 0.3761,
      "step": 20
    },
    {
      "epoch": 0.13966480446927373,
      "grad_norm": 4.055810451507568,
      "learning_rate": 9.995529414369582e-06,
      "loss": 0.3017,
      "step": 25
    },
    {
      "epoch": 0.16759776536312848,
      "grad_norm": 3.2087514400482178,
      "learning_rate": 9.986865748457457e-06,
      "loss": 0.2388,
      "step": 30
    },
    {
      "epoch": 0.19553072625698323,
      "grad_norm": 2.5950117111206055,
      "learning_rate": 9.973651911539209e-06,
      "loss": 0.205,
      "step": 35
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 2.1962437629699707,
      "learning_rate": 9.955899960329546e-06,
      "loss": 0.2056,
      "step": 40
    },
    {
      "epoch": 0.25139664804469275,
      "grad_norm": 2.396777629852295,
      "learning_rate": 9.933626092259439e-06,
      "loss": 0.1962,
      "step": 45
    },
    {
      "epoch": 0.27932960893854747,
      "grad_norm": 2.2164466381073,
      "learning_rate": 9.906850630697068e-06,
      "loss": 0.1846,
      "step": 50
    },
    {
      "epoch": 0.30726256983240224,
      "grad_norm": 2.0118980407714844,
      "learning_rate": 9.875598006404164e-06,
      "loss": 0.1801,
      "step": 55
    },
    {
      "epoch": 0.33519553072625696,
      "grad_norm": 1.8344327211380005,
      "learning_rate": 9.839896735244615e-06,
      "loss": 0.1647,
      "step": 60
    },
    {
      "epoch": 0.36312849162011174,
      "grad_norm": 1.9841200113296509,
      "learning_rate": 9.799779392165716e-06,
      "loss": 0.1755,
      "step": 65
    },
    {
      "epoch": 0.39106145251396646,
      "grad_norm": 1.8493112325668335,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.1663,
      "step": 70
    },
    {
      "epoch": 0.41899441340782123,
      "grad_norm": 2.081803560256958,
      "learning_rate": 9.706446903445179e-06,
      "loss": 0.1709,
      "step": 75
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 1.8965290784835815,
      "learning_rate": 9.653316917261511e-06,
      "loss": 0.1476,
      "step": 80
    },
    {
      "epoch": 0.4748603351955307,
      "grad_norm": 1.9217299222946167,
      "learning_rate": 9.595941100372301e-06,
      "loss": 0.169,
      "step": 85
    },
    {
      "epoch": 0.5027932960893855,
      "grad_norm": 1.8738741874694824,
      "learning_rate": 9.534371804252727e-06,
      "loss": 0.159,
      "step": 90
    },
    {
      "epoch": 0.5307262569832403,
      "grad_norm": 1.8862131834030151,
      "learning_rate": 9.46866520663851e-06,
      "loss": 0.1548,
      "step": 95
    },
    {
      "epoch": 0.5586592178770949,
      "grad_norm": 1.8590192794799805,
      "learning_rate": 9.398881260267589e-06,
      "loss": 0.1606,
      "step": 100
    },
    {
      "epoch": 0.5865921787709497,
      "grad_norm": 2.076671838760376,
      "learning_rate": 9.325083638177401e-06,
      "loss": 0.1619,
      "step": 105
    },
    {
      "epoch": 0.6145251396648045,
      "grad_norm": 1.9296963214874268,
      "learning_rate": 9.247339675607606e-06,
      "loss": 0.1533,
      "step": 110
    },
    {
      "epoch": 0.6424581005586593,
      "grad_norm": 1.7060136795043945,
      "learning_rate": 9.165720308561347e-06,
      "loss": 0.1582,
      "step": 115
    },
    {
      "epoch": 0.6703910614525139,
      "grad_norm": 1.9099347591400146,
      "learning_rate": 9.080300009081025e-06,
      "loss": 0.1599,
      "step": 120
    },
    {
      "epoch": 0.6983240223463687,
      "grad_norm": 1.634581208229065,
      "learning_rate": 8.991156717297702e-06,
      "loss": 0.1513,
      "step": 125
    },
    {
      "epoch": 0.7262569832402235,
      "grad_norm": 1.541104793548584,
      "learning_rate": 8.898371770316113e-06,
      "loss": 0.141,
      "step": 130
    },
    {
      "epoch": 0.7541899441340782,
      "grad_norm": 1.8300049304962158,
      "learning_rate": 8.802029828000157e-06,
      "loss": 0.1671,
      "step": 135
    },
    {
      "epoch": 0.7821229050279329,
      "grad_norm": 1.7759796380996704,
      "learning_rate": 8.702218795726619e-06,
      "loss": 0.1599,
      "step": 140
    },
    {
      "epoch": 0.8100558659217877,
      "grad_norm": 2.0563571453094482,
      "learning_rate": 8.599029744177577e-06,
      "loss": 0.1452,
      "step": 145
    },
    {
      "epoch": 0.8379888268156425,
      "grad_norm": 2.060739755630493,
      "learning_rate": 8.492556826244687e-06,
      "loss": 0.1525,
      "step": 150
    },
    {
      "epoch": 0.8659217877094972,
      "grad_norm": 1.742621898651123,
      "learning_rate": 8.382897191121157e-06,
      "loss": 0.1578,
      "step": 155
    },
    {
      "epoch": 0.8938547486033519,
      "grad_norm": 1.5601977109909058,
      "learning_rate": 8.270150895659824e-06,
      "loss": 0.1437,
      "step": 160
    },
    {
      "epoch": 0.9217877094972067,
      "grad_norm": 1.8811984062194824,
      "learning_rate": 8.154420813078155e-06,
      "loss": 0.1586,
      "step": 165
    },
    {
      "epoch": 0.9497206703910615,
      "grad_norm": 1.730596899986267,
      "learning_rate": 8.035812539093557e-06,
      "loss": 0.1463,
      "step": 170
    },
    {
      "epoch": 0.9776536312849162,
      "grad_norm": 1.8510273694992065,
      "learning_rate": 7.914434295574552e-06,
      "loss": 0.149,
      "step": 175
    }
  ],
  "logging_steps": 5,
  "max_steps": 537,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.422076336903291e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}