{
  "best_metric": 2.30838942527771,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.09556966345825654,
  "eval_steps": 100,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001365280906546522,
      "eval_loss": 3.064284086227417,
      "eval_runtime": 175.2575,
      "eval_samples_per_second": 35.194,
      "eval_steps_per_second": 8.798,
      "step": 1
    },
    {
      "epoch": 0.00682640453273261,
      "grad_norm": 46.66130828857422,
      "learning_rate": 0.00025,
      "loss": 8.7201,
      "step": 50
    },
    {
      "epoch": 0.01365280906546522,
      "grad_norm": 86.1082992553711,
      "learning_rate": 0.00025,
      "loss": 8.9435,
      "step": 100
    },
    {
      "epoch": 0.01365280906546522,
      "eval_loss": 2.4705960750579834,
      "eval_runtime": 175.403,
      "eval_samples_per_second": 35.165,
      "eval_steps_per_second": 8.791,
      "step": 100
    },
    {
      "epoch": 0.020479213598197828,
      "grad_norm": 59.893226623535156,
      "learning_rate": 0.00025,
      "loss": 8.5449,
      "step": 150
    },
    {
      "epoch": 0.02730561813093044,
      "grad_norm": 58.9417839050293,
      "learning_rate": 0.00025,
      "loss": 8.9737,
      "step": 200
    },
    {
      "epoch": 0.02730561813093044,
      "eval_loss": 2.4184000492095947,
      "eval_runtime": 175.3962,
      "eval_samples_per_second": 35.166,
      "eval_steps_per_second": 8.792,
      "step": 200
    },
    {
      "epoch": 0.034132022663663046,
      "grad_norm": 123.4080810546875,
      "learning_rate": 0.00025,
      "loss": 9.002,
      "step": 250
    },
    {
      "epoch": 0.040958427196395655,
      "grad_norm": 60.00017547607422,
      "learning_rate": 0.00025,
      "loss": 8.804,
      "step": 300
    },
    {
      "epoch": 0.040958427196395655,
      "eval_loss": 2.3906490802764893,
      "eval_runtime": 175.3105,
      "eval_samples_per_second": 35.183,
      "eval_steps_per_second": 8.796,
      "step": 300
    },
    {
      "epoch": 0.04778483172912827,
      "grad_norm": 48.440155029296875,
      "learning_rate": 0.00025,
      "loss": 8.7073,
      "step": 350
    },
    {
      "epoch": 0.05461123626186088,
      "grad_norm": 143.95608520507812,
      "learning_rate": 0.00025,
      "loss": 8.7399,
      "step": 400
    },
    {
      "epoch": 0.05461123626186088,
      "eval_loss": 2.447601318359375,
      "eval_runtime": 175.5057,
      "eval_samples_per_second": 35.144,
      "eval_steps_per_second": 8.786,
      "step": 400
    },
    {
      "epoch": 0.06143764079459349,
      "grad_norm": 64.72782135009766,
      "learning_rate": 0.00025,
      "loss": 8.8676,
      "step": 450
    },
    {
      "epoch": 0.06826404532732609,
      "grad_norm": 61.32781219482422,
      "learning_rate": 0.00025,
      "loss": 8.8788,
      "step": 500
    },
    {
      "epoch": 0.06826404532732609,
      "eval_loss": 2.30838942527771,
      "eval_runtime": 175.6465,
      "eval_samples_per_second": 35.116,
      "eval_steps_per_second": 8.779,
      "step": 500
    },
    {
      "epoch": 0.07509044986005871,
      "grad_norm": 115.34134674072266,
      "learning_rate": 0.00025,
      "loss": 8.8665,
      "step": 550
    },
    {
      "epoch": 0.08191685439279131,
      "grad_norm": 85.31719207763672,
      "learning_rate": 0.00025,
      "loss": 9.0255,
      "step": 600
    },
    {
      "epoch": 0.08191685439279131,
      "eval_loss": 2.3584725856781006,
      "eval_runtime": 175.5365,
      "eval_samples_per_second": 35.138,
      "eval_steps_per_second": 8.784,
      "step": 600
    },
    {
      "epoch": 0.08874325892552393,
      "grad_norm": 78.84331512451172,
      "learning_rate": 0.00025,
      "loss": 9.1057,
      "step": 650
    },
    {
      "epoch": 0.09556966345825654,
      "grad_norm": 82.10652923583984,
      "learning_rate": 0.00025,
      "loss": 9.2502,
      "step": 700
    },
    {
      "epoch": 0.09556966345825654,
      "eval_loss": 2.4388105869293213,
      "eval_runtime": 175.7023,
      "eval_samples_per_second": 35.105,
      "eval_steps_per_second": 8.776,
      "step": 700
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.475384335499264e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}