{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.08984725965858041,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017969451931716084,
      "grad_norm": NaN,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.302,
      "step": 1
    },
    {
      "epoch": 0.0017969451931716084,
      "eval_loss": NaN,
      "eval_runtime": 4.7012,
      "eval_samples_per_second": 10.635,
      "eval_steps_per_second": 1.489,
      "step": 1
    },
    {
      "epoch": 0.0035938903863432167,
      "grad_norm": NaN,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.005390835579514825,
      "grad_norm": NaN,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0071877807726864335,
      "grad_norm": NaN,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.008984725965858042,
      "grad_norm": NaN,
      "learning_rate": 0.00015,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01078167115902965,
      "grad_norm": NaN,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.012578616352201259,
      "grad_norm": NaN,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.014375561545372867,
      "grad_norm": NaN,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.016172506738544475,
      "grad_norm": NaN,
      "learning_rate": 0.00027,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.017969451931716084,
      "grad_norm": NaN,
      "learning_rate": 0.0003,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.019766397124887692,
      "grad_norm": NaN,
      "learning_rate": 0.0002999794957488703,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0215633423180593,
      "grad_norm": NaN,
      "learning_rate": 0.0002999179886011389,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.02336028751123091,
      "grad_norm": NaN,
      "learning_rate": 0.0002998154953722457,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.025157232704402517,
      "grad_norm": NaN,
      "learning_rate": 0.00029967204408281613,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.026954177897574125,
      "grad_norm": NaN,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.028751123090745734,
      "grad_norm": NaN,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.030548068283917342,
      "grad_norm": NaN,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.03234501347708895,
      "grad_norm": NaN,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.034141958670260555,
      "grad_norm": NaN,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.03593890386343217,
      "grad_norm": NaN,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03773584905660377,
      "grad_norm": NaN,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.039532794249775384,
      "grad_norm": NaN,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.04132973944294699,
      "grad_norm": NaN,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0431266846361186,
      "grad_norm": NaN,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.044923629829290206,
      "grad_norm": NaN,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.044923629829290206,
      "eval_loss": NaN,
      "eval_runtime": 4.2237,
      "eval_samples_per_second": 11.838,
      "eval_steps_per_second": 1.657,
      "step": 25
    },
    {
      "epoch": 0.04672057502246182,
      "grad_norm": NaN,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.04851752021563342,
      "grad_norm": NaN,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": NaN,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.05211141060197664,
      "grad_norm": NaN,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.05390835579514825,
      "grad_norm": NaN,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.055705300988319856,
      "grad_norm": NaN,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.05750224618149147,
      "grad_norm": NaN,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.05929919137466307,
      "grad_norm": NaN,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.061096136567834684,
      "grad_norm": NaN,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.06289308176100629,
      "grad_norm": NaN,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0646900269541779,
      "grad_norm": NaN,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0664869721473495,
      "grad_norm": NaN,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.06828391734052111,
      "grad_norm": NaN,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.07008086253369272,
      "grad_norm": NaN,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.07187780772686433,
      "grad_norm": NaN,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.07367475292003593,
      "grad_norm": NaN,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": NaN,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.07726864330637916,
      "grad_norm": NaN,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.07906558849955077,
      "grad_norm": NaN,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.08086253369272237,
      "grad_norm": NaN,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.08265947888589398,
      "grad_norm": NaN,
      "learning_rate": 0.000274201324672203,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.08445642407906559,
      "grad_norm": NaN,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.0862533692722372,
      "grad_norm": NaN,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0880503144654088,
      "grad_norm": NaN,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.08984725965858041,
      "grad_norm": NaN,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.08984725965858041,
      "eval_loss": NaN,
      "eval_runtime": 4.23,
      "eval_samples_per_second": 11.82,
      "eval_steps_per_second": 1.655,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 7.501558977763738e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}