{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 14.794451141440259,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.4571,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 12.330152509991866,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.1268,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 8.971397217939737,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.9902,
      "step": 30
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 11.380519787446628,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.0981,
      "step": 40
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 8.32821194659884,
      "learning_rate": 9.996239762521152e-06,
      "loss": 1.1456,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 11.654451105296685,
      "learning_rate": 9.966191788709716e-06,
      "loss": 1.2093,
      "step": 60
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 11.171797199934552,
      "learning_rate": 9.906276553136924e-06,
      "loss": 1.1195,
      "step": 70
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 10.63201216756226,
      "learning_rate": 9.816854393079402e-06,
      "loss": 1.2135,
      "step": 80
    },
    {
      "epoch": 0.2,
      "grad_norm": 12.127051170150766,
      "learning_rate": 9.698463103929542e-06,
      "loss": 1.112,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 8.340113584933913,
      "learning_rate": 9.551814704830734e-06,
      "loss": 1.1888,
      "step": 100
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 1.1302675008773804,
      "eval_runtime": 62.5953,
      "eval_samples_per_second": 3.195,
      "eval_steps_per_second": 1.598,
      "step": 100
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 9.682769825951436,
      "learning_rate": 9.377791156510456e-06,
      "loss": 1.1125,
      "step": 110
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 14.086506817284633,
      "learning_rate": 9.177439057064684e-06,
      "loss": 1.177,
      "step": 120
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 8.237466620205819,
      "learning_rate": 8.951963347593797e-06,
      "loss": 1.1346,
      "step": 130
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 8.579137067307839,
      "learning_rate": 8.702720065545024e-06,
      "loss": 1.0721,
      "step": 140
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 8.611204899822935,
      "learning_rate": 8.43120818934367e-06,
      "loss": 1.093,
      "step": 150
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 7.369274623301555,
      "learning_rate": 8.139060623360494e-06,
      "loss": 1.0672,
      "step": 160
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 7.384026754463874,
      "learning_rate": 7.828034377432694e-06,
      "loss": 1.0878,
      "step": 170
    },
    {
      "epoch": 0.4,
      "grad_norm": 9.367116824672664,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1554,
      "step": 180
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 7.854674767057573,
      "learning_rate": 7.156930328406268e-06,
      "loss": 1.0949,
      "step": 190
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 10.543523819074338,
      "learning_rate": 6.800888624023552e-06,
      "loss": 1.1374,
      "step": 200
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 1.0855395793914795,
      "eval_runtime": 62.5647,
      "eval_samples_per_second": 3.197,
      "eval_steps_per_second": 1.598,
      "step": 200
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 6.663061590801563,
      "learning_rate": 6.434016163555452e-06,
      "loss": 1.0843,
      "step": 210
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 9.136163397935082,
      "learning_rate": 6.058519361147055e-06,
      "loss": 0.9452,
      "step": 220
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 7.799360475311237,
      "learning_rate": 5.6766564987506564e-06,
      "loss": 1.1135,
      "step": 230
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 6.972887929630408,
      "learning_rate": 5.290724144552379e-06,
      "loss": 1.0685,
      "step": 240
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 8.93812579790191,
      "learning_rate": 4.903043341140879e-06,
      "loss": 1.0343,
      "step": 250
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 9.23106351125222,
      "learning_rate": 4.515945646484105e-06,
      "loss": 1.0521,
      "step": 260
    },
    {
      "epoch": 0.6,
      "grad_norm": 7.595576360000174,
      "learning_rate": 4.131759111665349e-06,
      "loss": 1.033,
      "step": 270
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 7.381000068171981,
      "learning_rate": 3.752794279710094e-06,
      "loss": 1.0148,
      "step": 280
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 9.167346260019274,
      "learning_rate": 3.3813302897083955e-06,
      "loss": 1.0207,
      "step": 290
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 9.155136420217675,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.9925,
      "step": 300
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 1.0038442611694336,
      "eval_runtime": 62.6452,
      "eval_samples_per_second": 3.193,
      "eval_steps_per_second": 1.596,
      "step": 300
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 8.635406192747224,
      "learning_rate": 2.6697824014873076e-06,
      "loss": 1.0074,
      "step": 310
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 9.430288206068186,
      "learning_rate": 2.333977835991545e-06,
      "loss": 0.9849,
      "step": 320
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 8.470290269408297,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.8921,
      "step": 330
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 7.414324470893291,
      "learning_rate": 1.7123931571546826e-06,
      "loss": 0.9733,
      "step": 340
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 7.216639003366927,
      "learning_rate": 1.4303513272105057e-06,
      "loss": 0.958,
      "step": 350
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.774509403514598,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.9337,
      "step": 360
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 7.175423562878317,
      "learning_rate": 9.322396486851626e-07,
      "loss": 0.9707,
      "step": 370
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 7.281982923970571,
      "learning_rate": 7.191655023486682e-07,
      "loss": 0.9158,
      "step": 380
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 7.000334583529529,
      "learning_rate": 5.318367983829393e-07,
      "loss": 0.9862,
      "step": 390
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 7.67116447376839,
      "learning_rate": 3.7138015365554834e-07,
      "loss": 0.9863,
      "step": 400
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.9608938694000244,
      "eval_runtime": 62.6139,
      "eval_samples_per_second": 3.194,
      "eval_steps_per_second": 1.597,
      "step": 400
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 5.925338984084342,
      "learning_rate": 2.3876057330792344e-07,
      "loss": 0.9407,
      "step": 410
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 8.253102891632325,
      "learning_rate": 1.3477564710088097e-07,
      "loss": 1.0322,
      "step": 420
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 7.949511306868007,
      "learning_rate": 6.005075261595495e-08,
      "loss": 0.9011,
      "step": 430
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 9.263574509045368,
      "learning_rate": 1.5035294161039882e-08,
      "loss": 0.9997,
      "step": 440
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.382357767710938,
      "learning_rate": 0.0,
      "loss": 1.0307,
      "step": 450
    },
    {
      "epoch": 1.0,
      "step": 450,
      "total_flos": 859103232000.0,
      "train_loss": 1.0592134835984972,
      "train_runtime": 1868.7127,
      "train_samples_per_second": 0.963,
      "train_steps_per_second": 0.241
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 859103232000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}