{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 19.25,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.10224462747573852,
      "step": 5
    },
    {
      "epoch": 0.4,
      "grad_norm": 30.625,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.0848326861858368,
      "step": 10
    },
    {
      "epoch": 0.6,
      "grad_norm": 32.75,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 0.12984503507614137,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 27.125,
      "learning_rate": 3.0400000000000004e-05,
      "loss": 0.10488946437835693,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 52.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.17124745845794678,
      "step": 25
    },
    {
      "epoch": 1.2,
      "grad_norm": 173.0,
      "learning_rate": 3.9288888888888894e-05,
      "loss": -0.6979187965393067,
      "step": 30
    },
    {
      "epoch": 1.4,
      "grad_norm": 174.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": -0.7409286499023438,
      "step": 35
    },
    {
      "epoch": 1.6,
      "grad_norm": 362.0,
      "learning_rate": 3.7511111111111116e-05,
      "loss": -2.4813100814819338,
      "step": 40
    },
    {
      "epoch": 1.8,
      "grad_norm": 1200.0,
      "learning_rate": 3.662222222222223e-05,
      "loss": -35.63023376464844,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 596.0,
      "learning_rate": 3.573333333333333e-05,
      "loss": -81.30550537109374,
      "step": 50
    },
    {
      "epoch": 2.2,
      "grad_norm": 14976.0,
      "learning_rate": 3.4844444444444444e-05,
      "loss": -91.82175903320312,
      "step": 55
    },
    {
      "epoch": 2.4,
      "grad_norm": 2224.0,
      "learning_rate": 3.395555555555556e-05,
      "loss": -89.76885375976562,
      "step": 60
    },
    {
      "epoch": 2.6,
      "grad_norm": 239.0,
      "learning_rate": 3.3066666666666666e-05,
      "loss": -90.85068359375,
      "step": 65
    },
    {
      "epoch": 2.8,
      "grad_norm": 115.5,
      "learning_rate": 3.217777777777778e-05,
      "loss": -97.28173828125,
      "step": 70
    },
    {
      "epoch": 3.0,
      "grad_norm": 114.0,
      "learning_rate": 3.1288888888888896e-05,
      "loss": -95.29666748046876,
      "step": 75
    },
    {
      "epoch": 3.2,
      "grad_norm": 284.0,
      "learning_rate": 3.0400000000000004e-05,
      "loss": -92.7463623046875,
      "step": 80
    },
    {
      "epoch": 3.4,
      "grad_norm": 126.5,
      "learning_rate": 2.951111111111111e-05,
      "loss": -96.7171142578125,
      "step": 85
    },
    {
      "epoch": 3.6,
      "grad_norm": 137.0,
      "learning_rate": 2.8622222222222223e-05,
      "loss": -98.34115600585938,
      "step": 90
    },
    {
      "epoch": 3.8,
      "grad_norm": 110.0,
      "learning_rate": 2.7733333333333338e-05,
      "loss": -99.39224243164062,
      "step": 95
    },
    {
      "epoch": 4.0,
      "grad_norm": 108.0,
      "learning_rate": 2.6844444444444446e-05,
      "loss": -97.4651611328125,
      "step": 100
    },
    {
      "epoch": 4.2,
      "grad_norm": 113.5,
      "learning_rate": 2.5955555555555557e-05,
      "loss": -99.03679809570312,
      "step": 105
    },
    {
      "epoch": 4.4,
      "grad_norm": 113.0,
      "learning_rate": 2.5066666666666672e-05,
      "loss": -102.26163940429687,
      "step": 110
    },
    {
      "epoch": 4.6,
      "grad_norm": 262.0,
      "learning_rate": 2.417777777777778e-05,
      "loss": -99.7196533203125,
      "step": 115
    },
    {
      "epoch": 4.8,
      "grad_norm": 118.5,
      "learning_rate": 2.328888888888889e-05,
      "loss": -100.89335327148437,
      "step": 120
    },
    {
      "epoch": 5.0,
      "grad_norm": 112.5,
      "learning_rate": 2.2400000000000002e-05,
      "loss": -99.00946655273438,
      "step": 125
    },
    {
      "epoch": 5.2,
      "grad_norm": 133.0,
      "learning_rate": 2.1511111111111114e-05,
      "loss": -102.15584716796874,
      "step": 130
    },
    {
      "epoch": 5.4,
      "grad_norm": 115.5,
      "learning_rate": 2.0622222222222225e-05,
      "loss": -104.1073486328125,
      "step": 135
    },
    {
      "epoch": 5.6,
      "grad_norm": 112.5,
      "learning_rate": 1.9733333333333336e-05,
      "loss": -101.88866577148437,
      "step": 140
    },
    {
      "epoch": 5.8,
      "grad_norm": 144.0,
      "learning_rate": 1.8844444444444444e-05,
      "loss": -104.56612548828124,
      "step": 145
    },
    {
      "epoch": 6.0,
      "grad_norm": 182.0,
      "learning_rate": 1.7955555555555556e-05,
      "loss": -105.870458984375,
      "step": 150
    },
    {
      "epoch": 6.2,
      "grad_norm": 118.5,
      "learning_rate": 1.706666666666667e-05,
      "loss": -105.58726806640625,
      "step": 155
    },
    {
      "epoch": 6.4,
      "grad_norm": 114.5,
      "learning_rate": 1.617777777777778e-05,
      "loss": -105.295947265625,
      "step": 160
    },
    {
      "epoch": 6.6,
      "grad_norm": 135.0,
      "learning_rate": 1.528888888888889e-05,
      "loss": -103.418505859375,
      "step": 165
    },
    {
      "epoch": 6.8,
      "grad_norm": 119.5,
      "learning_rate": 1.4400000000000001e-05,
      "loss": -105.86998291015625,
      "step": 170
    },
    {
      "epoch": 7.0,
      "grad_norm": 114.5,
      "learning_rate": 1.3511111111111112e-05,
      "loss": -103.21275634765625,
      "step": 175
    },
    {
      "epoch": 7.2,
      "grad_norm": 118.0,
      "learning_rate": 1.2622222222222222e-05,
      "loss": -106.66414794921874,
      "step": 180
    },
    {
      "epoch": 7.4,
      "grad_norm": 125.0,
      "learning_rate": 1.1733333333333335e-05,
      "loss": -104.7695556640625,
      "step": 185
    },
    {
      "epoch": 7.6,
      "grad_norm": 118.0,
      "learning_rate": 1.0844444444444446e-05,
      "loss": -104.51566162109376,
      "step": 190
    },
    {
      "epoch": 7.8,
      "grad_norm": 131.0,
      "learning_rate": 9.955555555555556e-06,
      "loss": -106.18931884765625,
      "step": 195
    },
    {
      "epoch": 8.0,
      "grad_norm": 129.0,
      "learning_rate": 9.066666666666667e-06,
      "loss": -106.0660400390625,
      "step": 200
    },
    {
      "epoch": 8.2,
      "grad_norm": 376.0,
      "learning_rate": 8.177777777777779e-06,
      "loss": -106.21219482421876,
      "step": 205
    },
    {
      "epoch": 8.4,
      "grad_norm": 114.5,
      "learning_rate": 7.28888888888889e-06,
      "loss": -106.3694580078125,
      "step": 210
    },
    {
      "epoch": 8.6,
      "grad_norm": 154.0,
      "learning_rate": 6.4000000000000006e-06,
      "loss": -104.23822021484375,
      "step": 215
    },
    {
      "epoch": 8.8,
      "grad_norm": 120.0,
      "learning_rate": 5.511111111111112e-06,
      "loss": -106.70201416015625,
      "step": 220
    },
    {
      "epoch": 9.0,
      "grad_norm": 111.0,
      "learning_rate": 4.622222222222222e-06,
      "loss": -105.63419189453126,
      "step": 225
    },
    {
      "epoch": 9.2,
      "grad_norm": 127.5,
      "learning_rate": 3.7333333333333337e-06,
      "loss": -103.74107666015625,
      "step": 230
    },
    {
      "epoch": 9.4,
      "grad_norm": 108.5,
      "learning_rate": 2.8444444444444446e-06,
      "loss": -105.2689697265625,
      "step": 235
    },
    {
      "epoch": 9.6,
      "grad_norm": 115.0,
      "learning_rate": 1.955555555555556e-06,
      "loss": -106.94022216796876,
      "step": 240
    },
    {
      "epoch": 9.8,
      "grad_norm": 111.0,
      "learning_rate": 1.066666666666667e-06,
      "loss": -107.48389892578125,
      "step": 245
    },
    {
      "epoch": 10.0,
      "grad_norm": 206.0,
      "learning_rate": 1.777777777777778e-07,
      "loss": -107.09498291015625,
      "step": 250
    },
    {
      "epoch": 10.0,
      "step": 250,
      "total_flos": 0.0,
      "train_loss": -84.0145669285059,
      "train_runtime": 389.2786,
      "train_samples_per_second": 10.275,
      "train_steps_per_second": 0.642
    }
  ],
  "logging_steps": 5,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}