{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 250.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 0.679200291633606,
      "learning_rate": 0.0005,
      "loss": 12.211211204528809,
      "step": 1
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.23044489324092865,
      "learning_rate": 0.00049775,
      "loss": 11.982609219021267,
      "step": 10
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.1907351166009903,
      "learning_rate": 0.00049525,
      "loss": 11.555101013183593,
      "step": 20
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.19268812239170074,
      "learning_rate": 0.00049275,
      "loss": 11.236198425292969,
      "step": 30
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.17933021485805511,
      "learning_rate": 0.00049025,
      "loss": 10.943867492675782,
      "step": 40
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.1976073980331421,
      "learning_rate": 0.00048775,
      "loss": 10.657130432128906,
      "step": 50
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.18433284759521484,
      "learning_rate": 0.00048525,
      "loss": 10.351960754394531,
      "step": 60
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.1888311803340912,
      "learning_rate": 0.00048275,
      "loss": 10.020181274414062,
      "step": 70
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.19162487983703613,
      "learning_rate": 0.00048025000000000005,
      "loss": 9.66613540649414,
      "step": 80
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.19730256497859955,
      "learning_rate": 0.00047775000000000004,
      "loss": 9.297232818603515,
      "step": 90
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.2213529646396637,
      "learning_rate": 0.00047525000000000003,
      "loss": 8.914820861816406,
      "step": 100
    },
    {
      "epoch": 55.0,
      "grad_norm": 0.2195209115743637,
      "learning_rate": 0.00047275,
      "loss": 8.521177673339844,
      "step": 110
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.2313990592956543,
      "learning_rate": 0.00047025,
      "loss": 8.118896484375,
      "step": 120
    },
    {
      "epoch": 65.0,
      "grad_norm": 0.23104608058929443,
      "learning_rate": 0.00046775,
      "loss": 7.713725280761719,
      "step": 130
    },
    {
      "epoch": 70.0,
      "grad_norm": 0.2376953512430191,
      "learning_rate": 0.00046525,
      "loss": 7.309984588623047,
      "step": 140
    },
    {
      "epoch": 75.0,
      "grad_norm": 0.24835970997810364,
      "learning_rate": 0.00046275,
      "loss": 6.910225677490234,
      "step": 150
    },
    {
      "epoch": 80.0,
      "grad_norm": 0.2480894923210144,
      "learning_rate": 0.00046025,
      "loss": 6.521015167236328,
      "step": 160
    },
    {
      "epoch": 85.0,
      "grad_norm": 0.2478545904159546,
      "learning_rate": 0.00045775,
      "loss": 6.150957870483398,
      "step": 170
    },
    {
      "epoch": 90.0,
      "grad_norm": 0.23328417539596558,
      "learning_rate": 0.00045525,
      "loss": 5.809443664550781,
      "step": 180
    },
    {
      "epoch": 95.0,
      "grad_norm": 0.23083385825157166,
      "learning_rate": 0.00045275,
      "loss": 5.494760131835937,
      "step": 190
    },
    {
      "epoch": 100.0,
      "grad_norm": 0.2354152798652649,
      "learning_rate": 0.00045024999999999997,
      "loss": 5.214201736450195,
      "step": 200
    },
    {
      "epoch": 105.0,
      "grad_norm": 0.2212478518486023,
      "learning_rate": 0.00044775,
      "loss": 4.965381622314453,
      "step": 210
    },
    {
      "epoch": 110.0,
      "grad_norm": 0.22108030319213867,
      "learning_rate": 0.00044525,
      "loss": 4.736624145507813,
      "step": 220
    },
    {
      "epoch": 115.0,
      "grad_norm": 0.2202872782945633,
      "learning_rate": 0.00044275,
      "loss": 4.5371543884277346,
      "step": 230
    },
    {
      "epoch": 120.0,
      "grad_norm": 0.21908171474933624,
      "learning_rate": 0.00044025,
      "loss": 4.3416389465332035,
      "step": 240
    },
    {
      "epoch": 125.0,
      "grad_norm": 0.2539515495300293,
      "learning_rate": 0.00043775,
      "loss": 4.155947875976563,
      "step": 250
    },
    {
      "epoch": 130.0,
      "grad_norm": 0.2240767925977707,
      "learning_rate": 0.00043525000000000004,
      "loss": 3.977610397338867,
      "step": 260
    },
    {
      "epoch": 135.0,
      "grad_norm": 0.20758213102817535,
      "learning_rate": 0.00043275000000000003,
      "loss": 3.791416549682617,
      "step": 270
    },
    {
      "epoch": 140.0,
      "grad_norm": 0.21930797398090363,
      "learning_rate": 0.00043025,
      "loss": 3.613859939575195,
      "step": 280
    },
    {
      "epoch": 145.0,
      "grad_norm": 0.20898985862731934,
      "learning_rate": 0.00042775,
      "loss": 3.4412445068359374,
      "step": 290
    },
    {
      "epoch": 150.0,
      "grad_norm": 0.21812506020069122,
      "learning_rate": 0.00042525,
      "loss": 3.2678699493408203,
      "step": 300
    },
    {
      "epoch": 155.0,
      "grad_norm": 0.20785079896450043,
      "learning_rate": 0.00042275,
      "loss": 3.101655387878418,
      "step": 310
    },
    {
      "epoch": 160.0,
      "grad_norm": 0.20621119439601898,
      "learning_rate": 0.00042025,
      "loss": 2.9381855010986326,
      "step": 320
    },
    {
      "epoch": 165.0,
      "grad_norm": 0.2516527771949768,
      "learning_rate": 0.00041775000000000004,
      "loss": 2.779329299926758,
      "step": 330
    },
    {
      "epoch": 170.0,
      "grad_norm": 0.2031988501548767,
      "learning_rate": 0.00041525000000000004,
      "loss": 2.6272861480712892,
      "step": 340
    },
    {
      "epoch": 175.0,
      "grad_norm": 0.19911770522594452,
      "learning_rate": 0.00041275000000000003,
      "loss": 2.466817855834961,
      "step": 350
    },
    {
      "epoch": 180.0,
      "grad_norm": 0.19864623248577118,
      "learning_rate": 0.00041025,
      "loss": 2.3201425552368162,
      "step": 360
    },
    {
      "epoch": 185.0,
      "grad_norm": 0.1971900314092636,
      "learning_rate": 0.00040775,
      "loss": 2.173211097717285,
      "step": 370
    },
    {
      "epoch": 190.0,
      "grad_norm": 0.19130639731884003,
      "learning_rate": 0.00040525,
      "loss": 2.038584518432617,
      "step": 380
    },
    {
      "epoch": 195.0,
      "grad_norm": 0.2037324756383896,
      "learning_rate": 0.00040275,
      "loss": 1.9071189880371093,
      "step": 390
    },
    {
      "epoch": 200.0,
      "grad_norm": 0.18795250356197357,
      "learning_rate": 0.00040025,
      "loss": 1.782277488708496,
      "step": 400
    },
    {
      "epoch": 205.0,
      "grad_norm": 0.18380966782569885,
      "learning_rate": 0.00039775,
      "loss": 1.663627815246582,
      "step": 410
    },
    {
      "epoch": 210.0,
      "grad_norm": 0.1786879301071167,
      "learning_rate": 0.00039525,
      "loss": 1.5451311111450194,
      "step": 420
    },
    {
      "epoch": 215.0,
      "grad_norm": 0.17858438193798065,
      "learning_rate": 0.00039275,
      "loss": 1.4358247756958007,
      "step": 430
    },
    {
      "epoch": 220.0,
      "grad_norm": 0.1655775010585785,
      "learning_rate": 0.00039024999999999997,
      "loss": 1.332811450958252,
      "step": 440
    },
    {
      "epoch": 225.0,
      "grad_norm": 0.1637052446603775,
      "learning_rate": 0.00038774999999999997,
      "loss": 1.2332740783691407,
      "step": 450
    },
    {
      "epoch": 230.0,
      "grad_norm": 0.16148947179317474,
      "learning_rate": 0.00038525,
      "loss": 1.1397903442382813,
      "step": 460
    },
    {
      "epoch": 235.0,
      "grad_norm": 0.15098616480827332,
      "learning_rate": 0.00038275,
      "loss": 1.055152416229248,
      "step": 470
    },
    {
      "epoch": 240.0,
      "grad_norm": 0.15136969089508057,
      "learning_rate": 0.00038025,
      "loss": 0.9760448455810546,
      "step": 480
    },
    {
      "epoch": 245.0,
      "grad_norm": 0.1447116583585739,
      "learning_rate": 0.00037775,
      "loss": 0.8991727828979492,
      "step": 490
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.1393691748380661,
      "learning_rate": 0.00037525,
      "loss": 0.8312561988830567,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1000,
  "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": 1341838872576000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}