{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.07164286034119913,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014328572068239825,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2328947.75,
      "step": 1
    },
    {
      "epoch": 0.0014328572068239825,
      "eval_loss": NaN,
      "eval_runtime": 0.0829,
      "eval_samples_per_second": 602.985,
      "eval_steps_per_second": 156.776,
      "step": 1
    },
    {
      "epoch": 0.002865714413647965,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004298571620471947,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00573142882729593,
      "grad_norm": NaN,
      "learning_rate": 9.99571699711836e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.007164286034119912,
      "grad_norm": NaN,
      "learning_rate": 9.982876141412856e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.008597143240943895,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010030000447767877,
      "grad_norm": NaN,
      "learning_rate": 9.931634888554937e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.01146285765459186,
      "grad_norm": NaN,
      "learning_rate": 9.893332032039701e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.012895714861415842,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.014328572068239825,
      "grad_norm": NaN,
      "learning_rate": 9.791726278367022e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.015761429275063805,
      "grad_norm": NaN,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.01719428648188779,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.01862714368871177,
      "grad_norm": NaN,
      "learning_rate": 9.578385041664925e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.020060000895535755,
      "grad_norm": NaN,
      "learning_rate": 9.491548749301997e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.021492858102359735,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.02292571530918372,
      "grad_norm": NaN,
      "learning_rate": 9.295261506157986e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0243585725160077,
      "grad_norm": NaN,
      "learning_rate": 9.186184199300464e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.025791429722831685,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.027224286929655665,
      "grad_norm": NaN,
      "learning_rate": 8.947199994035401e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.02865714413647965,
      "grad_norm": NaN,
      "learning_rate": 8.817748015645558e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03009000134330363,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.03152285855012761,
      "grad_norm": NaN,
      "learning_rate": 8.540155934270471e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.032955715756951595,
      "grad_norm": NaN,
      "learning_rate": 8.392544243589427e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.03438857296377558,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.035821430170599564,
      "grad_norm": NaN,
      "learning_rate": 8.081093963579707e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.035821430170599564,
      "eval_loss": NaN,
      "eval_runtime": 0.0852,
      "eval_samples_per_second": 586.961,
      "eval_steps_per_second": 152.61,
      "step": 25
    },
    {
      "epoch": 0.03725428737742354,
      "grad_norm": NaN,
      "learning_rate": 7.917848237560709e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.038687144584247525,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.04012000179107151,
      "grad_norm": NaN,
      "learning_rate": 7.577868759557654e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.041552858997895493,
      "grad_norm": NaN,
      "learning_rate": 7.401782177833148e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.04298571620471947,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.044418573411543455,
      "grad_norm": NaN,
      "learning_rate": 7.03909064496551e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.04585143061836744,
      "grad_norm": NaN,
      "learning_rate": 6.853176097769229e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.04728428782519142,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0487171450320154,
      "grad_norm": NaN,
      "learning_rate": 6.473978262721463e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.050150002238839385,
      "grad_norm": NaN,
      "learning_rate": 6.281416799501188e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.05158285944566337,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.05301571665248735,
      "grad_norm": NaN,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.05444857385931133,
      "grad_norm": NaN,
      "learning_rate": 5.696287243144013e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.055881431066135315,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0573142882729593,
      "grad_norm": NaN,
      "learning_rate": 5.303712756855988e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.05874714547978328,
      "grad_norm": NaN,
      "learning_rate": 5.107799157635538e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.06018000268660726,
      "grad_norm": NaN,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.061612859893431245,
      "grad_norm": NaN,
      "learning_rate": 4.718583200498814e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.06304571710025522,
      "grad_norm": NaN,
      "learning_rate": 4.526021737278538e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.0644785743070792,
      "grad_norm": NaN,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.06591143151390319,
      "grad_norm": NaN,
      "learning_rate": 4.146823902230772e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.06734428872072717,
      "grad_norm": NaN,
      "learning_rate": 3.960909355034491e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.06877714592755116,
      "grad_norm": NaN,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.07021000313437514,
      "grad_norm": NaN,
      "learning_rate": 3.598217822166854e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.07164286034119913,
      "grad_norm": NaN,
      "learning_rate": 3.422131240442349e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.07164286034119913,
      "eval_loss": NaN,
      "eval_runtime": 0.0962,
      "eval_samples_per_second": 519.778,
      "eval_steps_per_second": 135.142,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 85177596641280.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}