{
  "best_metric": 2.7498366832733154,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.05685048322910745,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002842524161455372,
      "eval_loss": 3.3774149417877197,
      "eval_runtime": 108.0913,
      "eval_samples_per_second": 10.278,
      "eval_steps_per_second": 2.572,
      "step": 1
    },
    {
      "epoch": 0.0028425241614553724,
      "grad_norm": 0.7144923210144043,
      "learning_rate": 5.05e-06,
      "loss": 2.6939,
      "step": 10
    },
    {
      "epoch": 0.005685048322910745,
      "grad_norm": 0.7308325171470642,
      "learning_rate": 1.01e-05,
      "loss": 2.8417,
      "step": 20
    },
    {
      "epoch": 0.008527572484366117,
      "grad_norm": 1.346327543258667,
      "learning_rate": 9.538888888888889e-06,
      "loss": 2.9471,
      "step": 30
    },
    {
      "epoch": 0.01137009664582149,
      "grad_norm": 1.253548264503479,
      "learning_rate": 8.977777777777778e-06,
      "loss": 3.2571,
      "step": 40
    },
    {
      "epoch": 0.014212620807276862,
      "grad_norm": 7.0101542472839355,
      "learning_rate": 8.416666666666667e-06,
      "loss": 3.7735,
      "step": 50
    },
    {
      "epoch": 0.014212620807276862,
      "eval_loss": 3.071653366088867,
      "eval_runtime": 108.7773,
      "eval_samples_per_second": 10.214,
      "eval_steps_per_second": 2.556,
      "step": 50
    },
    {
      "epoch": 0.017055144968732235,
      "grad_norm": 0.5917300581932068,
      "learning_rate": 7.855555555555556e-06,
      "loss": 2.6179,
      "step": 60
    },
    {
      "epoch": 0.019897669130187607,
      "grad_norm": 0.7418400645256042,
      "learning_rate": 7.294444444444444e-06,
      "loss": 2.7997,
      "step": 70
    },
    {
      "epoch": 0.02274019329164298,
      "grad_norm": 0.8529344201087952,
      "learning_rate": 6.733333333333333e-06,
      "loss": 2.8546,
      "step": 80
    },
    {
      "epoch": 0.025582717453098352,
      "grad_norm": 1.5713469982147217,
      "learning_rate": 6.172222222222223e-06,
      "loss": 3.0046,
      "step": 90
    },
    {
      "epoch": 0.028425241614553724,
      "grad_norm": 9.486610412597656,
      "learning_rate": 5.611111111111111e-06,
      "loss": 3.4553,
      "step": 100
    },
    {
      "epoch": 0.028425241614553724,
      "eval_loss": 2.856630563735962,
      "eval_runtime": 108.4543,
      "eval_samples_per_second": 10.244,
      "eval_steps_per_second": 2.563,
      "step": 100
    },
    {
      "epoch": 0.03126776577600909,
      "grad_norm": 0.7328553199768066,
      "learning_rate": 5.05e-06,
      "loss": 2.6002,
      "step": 110
    },
    {
      "epoch": 0.03411028993746447,
      "grad_norm": 0.8945074677467346,
      "learning_rate": 4.488888888888889e-06,
      "loss": 2.656,
      "step": 120
    },
    {
      "epoch": 0.03695281409891984,
      "grad_norm": 1.1075009107589722,
      "learning_rate": 3.927777777777778e-06,
      "loss": 2.7215,
      "step": 130
    },
    {
      "epoch": 0.039795338260375214,
      "grad_norm": 1.4025484323501587,
      "learning_rate": 3.3666666666666665e-06,
      "loss": 2.8693,
      "step": 140
    },
    {
      "epoch": 0.04263786242183058,
      "grad_norm": 4.004952907562256,
      "learning_rate": 2.8055555555555555e-06,
      "loss": 3.2109,
      "step": 150
    },
    {
      "epoch": 0.04263786242183058,
      "eval_loss": 2.762577533721924,
      "eval_runtime": 108.4563,
      "eval_samples_per_second": 10.244,
      "eval_steps_per_second": 2.563,
      "step": 150
    },
    {
      "epoch": 0.04548038658328596,
      "grad_norm": 0.8140513300895691,
      "learning_rate": 2.2444444444444445e-06,
      "loss": 2.5306,
      "step": 160
    },
    {
      "epoch": 0.04832291074474133,
      "grad_norm": 0.7513759136199951,
      "learning_rate": 1.6833333333333332e-06,
      "loss": 2.5396,
      "step": 170
    },
    {
      "epoch": 0.051165434906196704,
      "grad_norm": 0.9424188733100891,
      "learning_rate": 1.1222222222222222e-06,
      "loss": 2.6997,
      "step": 180
    },
    {
      "epoch": 0.05400795906765207,
      "grad_norm": 1.511574625968933,
      "learning_rate": 5.611111111111111e-07,
      "loss": 2.8946,
      "step": 190
    },
    {
      "epoch": 0.05685048322910745,
      "grad_norm": 6.663346767425537,
      "learning_rate": 0.0,
      "loss": 3.1014,
      "step": 200
    },
    {
      "epoch": 0.05685048322910745,
      "eval_loss": 2.7498366832733154,
      "eval_runtime": 108.0244,
      "eval_samples_per_second": 10.285,
      "eval_steps_per_second": 2.573,
      "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": 1.072893655032791e+17,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}