{
  "best_metric": 0.5373075008392334,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.15873015873015872,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007936507936507937,
      "eval_loss": 6.810345649719238,
      "eval_runtime": 28.5873,
      "eval_samples_per_second": 13.922,
      "eval_steps_per_second": 3.498,
      "step": 1
    },
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 12.51639175415039,
      "learning_rate": 5.095e-06,
      "loss": 4.7296,
      "step": 10
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 11.45109748840332,
      "learning_rate": 1.019e-05,
      "loss": 5.4391,
      "step": 20
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 6.5851359367370605,
      "learning_rate": 9.623888888888889e-06,
      "loss": 4.6711,
      "step": 30
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 9.905716896057129,
      "learning_rate": 9.057777777777777e-06,
      "loss": 5.4699,
      "step": 40
    },
    {
      "epoch": 0.03968253968253968,
      "grad_norm": 14.33770751953125,
      "learning_rate": 8.491666666666667e-06,
      "loss": 5.3696,
      "step": 50
    },
    {
      "epoch": 0.03968253968253968,
      "eval_loss": 4.328246593475342,
      "eval_runtime": 28.9921,
      "eval_samples_per_second": 13.728,
      "eval_steps_per_second": 3.449,
      "step": 50
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 5.936036109924316,
      "learning_rate": 7.925555555555557e-06,
      "loss": 2.5798,
      "step": 60
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 8.582554817199707,
      "learning_rate": 7.359444444444445e-06,
      "loss": 2.2367,
      "step": 70
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 12.786343574523926,
      "learning_rate": 6.793333333333333e-06,
      "loss": 1.8391,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 22.405052185058594,
      "learning_rate": 6.227222222222223e-06,
      "loss": 1.3989,
      "step": 90
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 16.31127166748047,
      "learning_rate": 5.661111111111112e-06,
      "loss": 1.4442,
      "step": 100
    },
    {
      "epoch": 0.07936507936507936,
      "eval_loss": 0.9730060696601868,
      "eval_runtime": 29.0537,
      "eval_samples_per_second": 13.699,
      "eval_steps_per_second": 3.442,
      "step": 100
    },
    {
      "epoch": 0.0873015873015873,
      "grad_norm": 11.517756462097168,
      "learning_rate": 5.095e-06,
      "loss": 0.7625,
      "step": 110
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 8.872756004333496,
      "learning_rate": 4.5288888888888885e-06,
      "loss": 0.5658,
      "step": 120
    },
    {
      "epoch": 0.10317460317460317,
      "grad_norm": 11.381665229797363,
      "learning_rate": 3.9627777777777784e-06,
      "loss": 0.5982,
      "step": 130
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 28.924938201904297,
      "learning_rate": 3.3966666666666666e-06,
      "loss": 0.4895,
      "step": 140
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 9.414434432983398,
      "learning_rate": 2.830555555555556e-06,
      "loss": 0.737,
      "step": 150
    },
    {
      "epoch": 0.11904761904761904,
      "eval_loss": 0.582314670085907,
      "eval_runtime": 29.0563,
      "eval_samples_per_second": 13.698,
      "eval_steps_per_second": 3.442,
      "step": 150
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 9.03739070892334,
      "learning_rate": 2.2644444444444443e-06,
      "loss": 0.4166,
      "step": 160
    },
    {
      "epoch": 0.1349206349206349,
      "grad_norm": 5.134159088134766,
      "learning_rate": 1.6983333333333333e-06,
      "loss": 0.3406,
      "step": 170
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 7.450616836547852,
      "learning_rate": 1.1322222222222221e-06,
      "loss": 0.4627,
      "step": 180
    },
    {
      "epoch": 0.15079365079365079,
      "grad_norm": 12.882534980773926,
      "learning_rate": 5.661111111111111e-07,
      "loss": 0.5223,
      "step": 190
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 17.285032272338867,
      "learning_rate": 0.0,
      "loss": 0.6207,
      "step": 200
    },
    {
      "epoch": 0.15873015873015872,
      "eval_loss": 0.5373075008392334,
      "eval_runtime": 29.0493,
      "eval_samples_per_second": 13.701,
      "eval_steps_per_second": 3.442,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.27255432331264e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}