{
  "best_metric": 1.8228825330734253,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3109211037699184,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012436844150796735,
      "grad_norm": 4.070582389831543,
      "learning_rate": 5e-05,
      "loss": 4.2908,
      "step": 1
    },
    {
      "epoch": 0.012436844150796735,
      "eval_loss": 6.697080135345459,
      "eval_runtime": 4.2989,
      "eval_samples_per_second": 11.631,
      "eval_steps_per_second": 3.024,
      "step": 1
    },
    {
      "epoch": 0.02487368830159347,
      "grad_norm": 4.343489646911621,
      "learning_rate": 0.0001,
      "loss": 4.86,
      "step": 2
    },
    {
      "epoch": 0.03731053245239021,
      "grad_norm": 4.6962361335754395,
      "learning_rate": 9.990365154573717e-05,
      "loss": 4.8283,
      "step": 3
    },
    {
      "epoch": 0.04974737660318694,
      "grad_norm": 4.616434097290039,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.0479,
      "step": 4
    },
    {
      "epoch": 0.06218422075398368,
      "grad_norm": 4.6326904296875,
      "learning_rate": 9.913533761814537e-05,
      "loss": 3.208,
      "step": 5
    },
    {
      "epoch": 0.07462106490478042,
      "grad_norm": 3.4674623012542725,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.7493,
      "step": 6
    },
    {
      "epoch": 0.08705790905557714,
      "grad_norm": 3.225517749786377,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.5875,
      "step": 7
    },
    {
      "epoch": 0.09949475320637388,
      "grad_norm": 3.2241368293762207,
      "learning_rate": 9.657457896300791e-05,
      "loss": 2.4383,
      "step": 8
    },
    {
      "epoch": 0.11193159735717062,
      "grad_norm": 3.3204712867736816,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.211,
      "step": 9
    },
    {
      "epoch": 0.12436844150796736,
      "grad_norm": 2.812617301940918,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0978,
      "step": 10
    },
    {
      "epoch": 0.1368052856587641,
      "grad_norm": 2.866771936416626,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.8688,
      "step": 11
    },
    {
      "epoch": 0.14924212980956084,
      "grad_norm": 6.981631755828857,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.6069,
      "step": 12
    },
    {
      "epoch": 0.16167897396035755,
      "grad_norm": 10.564940452575684,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.8817,
      "step": 13
    },
    {
      "epoch": 0.17411581811115429,
      "grad_norm": 8.371127128601074,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.7034,
      "step": 14
    },
    {
      "epoch": 0.18655266226195102,
      "grad_norm": 3.5405235290527344,
      "learning_rate": 8.467056167950311e-05,
      "loss": 2.462,
      "step": 15
    },
    {
      "epoch": 0.19898950641274776,
      "grad_norm": 2.1815154552459717,
      "learning_rate": 8.239426430539243e-05,
      "loss": 2.2772,
      "step": 16
    },
    {
      "epoch": 0.2114263505635445,
      "grad_norm": 2.2907159328460693,
      "learning_rate": 8.000066048588211e-05,
      "loss": 2.1571,
      "step": 17
    },
    {
      "epoch": 0.22386319471434124,
      "grad_norm": 2.2352960109710693,
      "learning_rate": 7.75e-05,
      "loss": 2.1092,
      "step": 18
    },
    {
      "epoch": 0.23630003886513798,
      "grad_norm": 2.1429026126861572,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.1112,
      "step": 19
    },
    {
      "epoch": 0.24873688301593472,
      "grad_norm": 2.0608441829681396,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.9141,
      "step": 20
    },
    {
      "epoch": 0.26117372716673143,
      "grad_norm": 1.994292974472046,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.7083,
      "step": 21
    },
    {
      "epoch": 0.2736105713175282,
      "grad_norm": 1.7245221138000488,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.7911,
      "step": 22
    },
    {
      "epoch": 0.2860474154683249,
      "grad_norm": 1.8327735662460327,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.6479,
      "step": 23
    },
    {
      "epoch": 0.2984842596191217,
      "grad_norm": 1.897107720375061,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.3578,
      "step": 24
    },
    {
      "epoch": 0.3109211037699184,
      "grad_norm": 7.827093124389648,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.7274,
      "step": 25
    },
    {
      "epoch": 0.3109211037699184,
      "eval_loss": 1.8228825330734253,
      "eval_runtime": 4.3671,
      "eval_samples_per_second": 11.449,
      "eval_steps_per_second": 2.977,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.984041808658432e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}