{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.00046560353858689327,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.3280176929344664e-05,
      "grad_norm": 1.1166245937347412,
      "learning_rate": 2e-05,
      "loss": 44.3167,
      "step": 1
    },
    {
      "epoch": 2.3280176929344664e-05,
      "eval_loss": NaN,
      "eval_runtime": 96.613,
      "eval_samples_per_second": 187.211,
      "eval_steps_per_second": 93.611,
      "step": 1
    },
    {
      "epoch": 4.656035385868933e-05,
      "grad_norm": 1.9174872636795044,
      "learning_rate": 4e-05,
      "loss": 44.3644,
      "step": 2
    },
    {
      "epoch": 6.984053078803399e-05,
      "grad_norm": 1.5179235935211182,
      "learning_rate": 6e-05,
      "loss": 44.3975,
      "step": 3
    },
    {
      "epoch": 9.312070771737865e-05,
      "grad_norm": 1.755682110786438,
      "learning_rate": 8e-05,
      "loss": 33.2456,
      "step": 4
    },
    {
      "epoch": 0.00011640088464672332,
      "grad_norm": 1.1574366092681885,
      "learning_rate": 0.0001,
      "loss": 22.2917,
      "step": 5
    },
    {
      "epoch": 0.00011640088464672332,
      "eval_loss": NaN,
      "eval_runtime": 95.7262,
      "eval_samples_per_second": 188.945,
      "eval_steps_per_second": 94.478,
      "step": 5
    },
    {
      "epoch": 0.00013968106157606798,
      "grad_norm": 1.8003005981445312,
      "learning_rate": 0.00012,
      "loss": 44.2875,
      "step": 6
    },
    {
      "epoch": 0.00016296123850541265,
      "grad_norm": 1.5077505111694336,
      "learning_rate": 0.00014,
      "loss": 44.258,
      "step": 7
    },
    {
      "epoch": 0.0001862414154347573,
      "grad_norm": 1.3881042003631592,
      "learning_rate": 0.00016,
      "loss": 44.4831,
      "step": 8
    },
    {
      "epoch": 0.00020952159236410197,
      "grad_norm": 1.6329082250595093,
      "learning_rate": 0.00018,
      "loss": 33.283,
      "step": 9
    },
    {
      "epoch": 0.00023280176929344664,
      "grad_norm": 1.3479140996932983,
      "learning_rate": 0.0002,
      "loss": 33.3667,
      "step": 10
    },
    {
      "epoch": 0.00023280176929344664,
      "eval_loss": NaN,
      "eval_runtime": 96.0626,
      "eval_samples_per_second": 188.283,
      "eval_steps_per_second": 94.147,
      "step": 10
    },
    {
      "epoch": 0.00025608194622279127,
      "grad_norm": 1.559240698814392,
      "learning_rate": 0.00019781476007338058,
      "loss": 55.5735,
      "step": 11
    },
    {
      "epoch": 0.00027936212315213596,
      "grad_norm": 1.7035174369812012,
      "learning_rate": 0.0001913545457642601,
      "loss": 44.3113,
      "step": 12
    },
    {
      "epoch": 0.0003026423000814806,
      "grad_norm": 1.2186126708984375,
      "learning_rate": 0.00018090169943749476,
      "loss": 33.1336,
      "step": 13
    },
    {
      "epoch": 0.0003259224770108253,
      "grad_norm": 1.8298100233078003,
      "learning_rate": 0.00016691306063588583,
      "loss": 22.3458,
      "step": 14
    },
    {
      "epoch": 0.0003492026539401699,
      "grad_norm": 1.9966983795166016,
      "learning_rate": 0.00015000000000000001,
      "loss": 44.3434,
      "step": 15
    },
    {
      "epoch": 0.0003492026539401699,
      "eval_loss": NaN,
      "eval_runtime": 95.5077,
      "eval_samples_per_second": 189.377,
      "eval_steps_per_second": 94.694,
      "step": 15
    },
    {
      "epoch": 0.0003724828308695146,
      "grad_norm": 2.083956003189087,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.3103,
      "step": 16
    },
    {
      "epoch": 0.00039576300779885925,
      "grad_norm": 1.572965383529663,
      "learning_rate": 0.00011045284632676536,
      "loss": 22.2272,
      "step": 17
    },
    {
      "epoch": 0.00041904318472820394,
      "grad_norm": 2.212663173675537,
      "learning_rate": 8.954715367323468e-05,
      "loss": 44.2203,
      "step": 18
    },
    {
      "epoch": 0.0004423233616575486,
      "grad_norm": 1.2902798652648926,
      "learning_rate": 6.909830056250527e-05,
      "loss": 22.1232,
      "step": 19
    },
    {
      "epoch": 0.00046560353858689327,
      "grad_norm": 1.6444133520126343,
      "learning_rate": 5.000000000000002e-05,
      "loss": 66.6363,
      "step": 20
    },
    {
      "epoch": 0.00046560353858689327,
      "eval_loss": NaN,
      "eval_runtime": 95.8412,
      "eval_samples_per_second": 188.718,
      "eval_steps_per_second": 94.364,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 15502540800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}