{
  "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": 11.125,
      "learning_rate": 6.4000000000000006e-06,
      "loss": -0.011411023139953614,
      "step": 5
    },
    {
      "epoch": 0.4,
      "grad_norm": 12.0625,
      "learning_rate": 1.4400000000000001e-05,
      "loss": -0.02921934425830841,
      "step": 10
    },
    {
      "epoch": 0.6,
      "grad_norm": 28.875,
      "learning_rate": 2.2400000000000002e-05,
      "loss": -0.02916721999645233,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 90.0,
      "learning_rate": 3.0400000000000004e-05,
      "loss": -0.11180627346038818,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 236.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": -0.62957763671875,
      "step": 25
    },
    {
      "epoch": 1.2,
      "grad_norm": 332.0,
      "learning_rate": 3.9288888888888894e-05,
      "loss": -2.0658231735229493,
      "step": 30
    },
    {
      "epoch": 1.4,
      "grad_norm": 398.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": -3.0921772003173826,
      "step": 35
    },
    {
      "epoch": 1.6,
      "grad_norm": 1584.0,
      "learning_rate": 3.7511111111111116e-05,
      "loss": -14.95286865234375,
      "step": 40
    },
    {
      "epoch": 1.8,
      "grad_norm": 2848.0,
      "learning_rate": 3.662222222222223e-05,
      "loss": -43.402197265625,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 294.0,
      "learning_rate": 3.573333333333333e-05,
      "loss": -54.48800048828125,
      "step": 50
    },
    {
      "epoch": 2.2,
      "grad_norm": 382.0,
      "learning_rate": 3.4844444444444444e-05,
      "loss": -62.52164916992187,
      "step": 55
    },
    {
      "epoch": 2.4,
      "grad_norm": 181.0,
      "learning_rate": 3.395555555555556e-05,
      "loss": -69.7565185546875,
      "step": 60
    },
    {
      "epoch": 2.6,
      "grad_norm": 1384.0,
      "learning_rate": 3.3066666666666666e-05,
      "loss": -68.15775756835937,
      "step": 65
    },
    {
      "epoch": 2.8,
      "grad_norm": 122.5,
      "learning_rate": 3.217777777777778e-05,
      "loss": -74.51124877929688,
      "step": 70
    },
    {
      "epoch": 3.0,
      "grad_norm": 460.0,
      "learning_rate": 3.1288888888888896e-05,
      "loss": -74.828271484375,
      "step": 75
    },
    {
      "epoch": 3.2,
      "grad_norm": 122.0,
      "learning_rate": 3.0400000000000004e-05,
      "loss": -72.76103515625,
      "step": 80
    },
    {
      "epoch": 3.4,
      "grad_norm": 151.0,
      "learning_rate": 2.951111111111111e-05,
      "loss": -73.82017822265625,
      "step": 85
    },
    {
      "epoch": 3.6,
      "grad_norm": 171.0,
      "learning_rate": 2.8622222222222223e-05,
      "loss": -77.53640747070312,
      "step": 90
    },
    {
      "epoch": 3.8,
      "grad_norm": 120.5,
      "learning_rate": 2.7733333333333338e-05,
      "loss": -78.69415283203125,
      "step": 95
    },
    {
      "epoch": 4.0,
      "grad_norm": 112.5,
      "learning_rate": 2.6844444444444446e-05,
      "loss": -79.16287841796876,
      "step": 100
    },
    {
      "epoch": 4.2,
      "grad_norm": 103.5,
      "learning_rate": 2.5955555555555557e-05,
      "loss": -78.008203125,
      "step": 105
    },
    {
      "epoch": 4.4,
      "grad_norm": 186.0,
      "learning_rate": 2.5066666666666672e-05,
      "loss": -81.25070190429688,
      "step": 110
    },
    {
      "epoch": 4.6,
      "grad_norm": 314.0,
      "learning_rate": 2.417777777777778e-05,
      "loss": -80.52830200195312,
      "step": 115
    },
    {
      "epoch": 4.8,
      "grad_norm": 988.0,
      "learning_rate": 2.328888888888889e-05,
      "loss": -77.89945068359376,
      "step": 120
    },
    {
      "epoch": 5.0,
      "grad_norm": 110.5,
      "learning_rate": 2.2400000000000002e-05,
      "loss": -79.39564208984375,
      "step": 125
    },
    {
      "epoch": 5.2,
      "grad_norm": 144.0,
      "learning_rate": 2.1511111111111114e-05,
      "loss": -80.58895874023438,
      "step": 130
    },
    {
      "epoch": 5.4,
      "grad_norm": 113.5,
      "learning_rate": 2.0622222222222225e-05,
      "loss": -82.10526123046876,
      "step": 135
    },
    {
      "epoch": 5.6,
      "grad_norm": 109.0,
      "learning_rate": 1.9733333333333336e-05,
      "loss": -80.39559936523438,
      "step": 140
    },
    {
      "epoch": 5.8,
      "grad_norm": 122.0,
      "learning_rate": 1.8844444444444444e-05,
      "loss": -82.06431274414062,
      "step": 145
    },
    {
      "epoch": 6.0,
      "grad_norm": 111.0,
      "learning_rate": 1.7955555555555556e-05,
      "loss": -84.17305297851563,
      "step": 150
    },
    {
      "epoch": 6.2,
      "grad_norm": 108.5,
      "learning_rate": 1.706666666666667e-05,
      "loss": -84.07409057617187,
      "step": 155
    },
    {
      "epoch": 6.4,
      "grad_norm": 112.5,
      "learning_rate": 1.617777777777778e-05,
      "loss": -85.04705200195312,
      "step": 160
    },
    {
      "epoch": 6.6,
      "grad_norm": 118.0,
      "learning_rate": 1.528888888888889e-05,
      "loss": -82.29384155273438,
      "step": 165
    },
    {
      "epoch": 6.8,
      "grad_norm": 116.5,
      "learning_rate": 1.4400000000000001e-05,
      "loss": -85.50375366210938,
      "step": 170
    },
    {
      "epoch": 7.0,
      "grad_norm": 312.0,
      "learning_rate": 1.3511111111111112e-05,
      "loss": -85.09585571289062,
      "step": 175
    },
    {
      "epoch": 7.2,
      "grad_norm": 158.0,
      "learning_rate": 1.2622222222222222e-05,
      "loss": -88.86329956054688,
      "step": 180
    },
    {
      "epoch": 7.4,
      "grad_norm": 195.0,
      "learning_rate": 1.1733333333333335e-05,
      "loss": -88.39931640625,
      "step": 185
    },
    {
      "epoch": 7.6,
      "grad_norm": 189.0,
      "learning_rate": 1.0844444444444446e-05,
      "loss": -90.6859130859375,
      "step": 190
    },
    {
      "epoch": 7.8,
      "grad_norm": 229.0,
      "learning_rate": 9.955555555555556e-06,
      "loss": -93.2937255859375,
      "step": 195
    },
    {
      "epoch": 8.0,
      "grad_norm": 616.0,
      "learning_rate": 9.066666666666667e-06,
      "loss": -93.46704711914063,
      "step": 200
    },
    {
      "epoch": 8.2,
      "grad_norm": 1056.0,
      "learning_rate": 8.177777777777779e-06,
      "loss": -94.84644775390625,
      "step": 205
    },
    {
      "epoch": 8.4,
      "grad_norm": 176.0,
      "learning_rate": 7.28888888888889e-06,
      "loss": -96.15100708007813,
      "step": 210
    },
    {
      "epoch": 8.6,
      "grad_norm": 436.0,
      "learning_rate": 6.4000000000000006e-06,
      "loss": -97.54093017578126,
      "step": 215
    },
    {
      "epoch": 8.8,
      "grad_norm": 190.0,
      "learning_rate": 5.511111111111112e-06,
      "loss": -96.87262573242188,
      "step": 220
    },
    {
      "epoch": 9.0,
      "grad_norm": 258.0,
      "learning_rate": 4.622222222222222e-06,
      "loss": -95.371240234375,
      "step": 225
    },
    {
      "epoch": 9.2,
      "grad_norm": 175.0,
      "learning_rate": 3.7333333333333337e-06,
      "loss": -95.70596923828126,
      "step": 230
    },
    {
      "epoch": 9.4,
      "grad_norm": 390.0,
      "learning_rate": 2.8444444444444446e-06,
      "loss": -97.079931640625,
      "step": 235
    },
    {
      "epoch": 9.6,
      "grad_norm": 260.0,
      "learning_rate": 1.955555555555556e-06,
      "loss": -97.48558349609375,
      "step": 240
    },
    {
      "epoch": 9.8,
      "grad_norm": 468.0,
      "learning_rate": 1.066666666666667e-06,
      "loss": -98.60989379882812,
      "step": 245
    },
    {
      "epoch": 10.0,
      "grad_norm": 140.0,
      "learning_rate": 1.777777777777778e-07,
      "loss": -98.44088134765624,
      "step": 250
    },
    {
      "epoch": 10.0,
      "step": 250,
      "total_flos": 0.0,
      "train_loss": -70.03600473117828,
      "train_runtime": 299.093,
      "train_samples_per_second": 13.374,
      "train_steps_per_second": 0.836
    }
  ],
  "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
}