{
  "best_metric": 1.0661097764968872,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.015503875968992248,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00062015503875969,
      "grad_norm": 14.920880317687988,
      "learning_rate": 0.0001,
      "loss": 7.1109,
      "step": 1
    },
    {
      "epoch": 0.00062015503875969,
      "eval_loss": 6.155733585357666,
      "eval_runtime": 49.6251,
      "eval_samples_per_second": 13.683,
      "eval_steps_per_second": 6.851,
      "step": 1
    },
    {
      "epoch": 0.00124031007751938,
      "grad_norm": 12.616119384765625,
      "learning_rate": 0.0002,
      "loss": 5.6612,
      "step": 2
    },
    {
      "epoch": 0.0018604651162790699,
      "grad_norm": 15.625079154968262,
      "learning_rate": 0.00019978589232386035,
      "loss": 6.7293,
      "step": 3
    },
    {
      "epoch": 0.00248062015503876,
      "grad_norm": 13.348905563354492,
      "learning_rate": 0.00019914448613738106,
      "loss": 4.7204,
      "step": 4
    },
    {
      "epoch": 0.0031007751937984496,
      "grad_norm": 9.438117980957031,
      "learning_rate": 0.00019807852804032305,
      "loss": 3.0829,
      "step": 5
    },
    {
      "epoch": 0.0037209302325581397,
      "grad_norm": 17.93440055847168,
      "learning_rate": 0.00019659258262890683,
      "loss": 3.057,
      "step": 6
    },
    {
      "epoch": 0.004341085271317829,
      "grad_norm": 11.800411224365234,
      "learning_rate": 0.0001946930129495106,
      "loss": 1.9626,
      "step": 7
    },
    {
      "epoch": 0.00496124031007752,
      "grad_norm": 11.008665084838867,
      "learning_rate": 0.0001923879532511287,
      "loss": 1.8794,
      "step": 8
    },
    {
      "epoch": 0.005581395348837209,
      "grad_norm": 15.072994232177734,
      "learning_rate": 0.00018968727415326884,
      "loss": 1.6519,
      "step": 9
    },
    {
      "epoch": 0.006201550387596899,
      "grad_norm": 10.600494384765625,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.0895,
      "step": 10
    },
    {
      "epoch": 0.006821705426356589,
      "grad_norm": 17.598783493041992,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.3181,
      "step": 11
    },
    {
      "epoch": 0.0074418604651162795,
      "grad_norm": 11.936248779296875,
      "learning_rate": 0.00017933533402912354,
      "loss": 1.3033,
      "step": 12
    },
    {
      "epoch": 0.00806201550387597,
      "grad_norm": 14.608379364013672,
      "learning_rate": 0.00017518398074789775,
      "loss": 1.1154,
      "step": 13
    },
    {
      "epoch": 0.008682170542635658,
      "grad_norm": 13.892497062683105,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.1172,
      "step": 14
    },
    {
      "epoch": 0.009302325581395349,
      "grad_norm": 12.43130874633789,
      "learning_rate": 0.00016593458151000688,
      "loss": 1.4043,
      "step": 15
    },
    {
      "epoch": 0.00992248062015504,
      "grad_norm": 8.64314079284668,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.639,
      "step": 16
    },
    {
      "epoch": 0.010542635658914728,
      "grad_norm": 12.006380081176758,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.269,
      "step": 17
    },
    {
      "epoch": 0.011162790697674419,
      "grad_norm": 15.379800796508789,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0862,
      "step": 18
    },
    {
      "epoch": 0.011782945736434108,
      "grad_norm": 10.780191421508789,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.6742,
      "step": 19
    },
    {
      "epoch": 0.012403100775193798,
      "grad_norm": 8.979784965515137,
      "learning_rate": 0.000138268343236509,
      "loss": 0.5997,
      "step": 20
    },
    {
      "epoch": 0.013023255813953489,
      "grad_norm": 7.553980827331543,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.2945,
      "step": 21
    },
    {
      "epoch": 0.013643410852713178,
      "grad_norm": 9.615273475646973,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.6348,
      "step": 22
    },
    {
      "epoch": 0.014263565891472868,
      "grad_norm": 8.001143455505371,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.2675,
      "step": 23
    },
    {
      "epoch": 0.014883720930232559,
      "grad_norm": 14.149334907531738,
      "learning_rate": 0.00011305261922200519,
      "loss": 1.1478,
      "step": 24
    },
    {
      "epoch": 0.015503875968992248,
      "grad_norm": 7.33767032623291,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.6085,
      "step": 25
    },
    {
      "epoch": 0.015503875968992248,
      "eval_loss": 1.0661097764968872,
      "eval_runtime": 49.2266,
      "eval_samples_per_second": 13.793,
      "eval_steps_per_second": 6.907,
      "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": 1802385752064000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}