{
  "best_metric": 1.2871240377426147,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.008165931732810714,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016331863465621427,
      "grad_norm": 1.671673059463501,
      "learning_rate": 1.001e-05,
      "loss": 1.0081,
      "step": 1
    },
    {
      "epoch": 0.00016331863465621427,
      "eval_loss": 1.9000940322875977,
      "eval_runtime": 345.3153,
      "eval_samples_per_second": 7.466,
      "eval_steps_per_second": 1.868,
      "step": 1
    },
    {
      "epoch": 0.00032663726931242854,
      "grad_norm": 2.1853973865509033,
      "learning_rate": 2.002e-05,
      "loss": 1.0249,
      "step": 2
    },
    {
      "epoch": 0.0004899559039686428,
      "grad_norm": 2.061541795730591,
      "learning_rate": 3.0029999999999995e-05,
      "loss": 1.0868,
      "step": 3
    },
    {
      "epoch": 0.0006532745386248571,
      "grad_norm": 2.0026113986968994,
      "learning_rate": 4.004e-05,
      "loss": 1.2093,
      "step": 4
    },
    {
      "epoch": 0.0008165931732810714,
      "grad_norm": 1.3478747606277466,
      "learning_rate": 5.005e-05,
      "loss": 0.9586,
      "step": 5
    },
    {
      "epoch": 0.0009799118079372856,
      "grad_norm": 1.2198477983474731,
      "learning_rate": 6.005999999999999e-05,
      "loss": 1.001,
      "step": 6
    },
    {
      "epoch": 0.0011432304425935,
      "grad_norm": 1.0008301734924316,
      "learning_rate": 7.006999999999998e-05,
      "loss": 1.0274,
      "step": 7
    },
    {
      "epoch": 0.0013065490772497142,
      "grad_norm": 0.9373151063919067,
      "learning_rate": 8.008e-05,
      "loss": 1.0383,
      "step": 8
    },
    {
      "epoch": 0.0014698677119059284,
      "grad_norm": 0.984042763710022,
      "learning_rate": 9.009e-05,
      "loss": 0.9748,
      "step": 9
    },
    {
      "epoch": 0.0016331863465621427,
      "grad_norm": 0.9123459458351135,
      "learning_rate": 0.0001001,
      "loss": 1.0147,
      "step": 10
    },
    {
      "epoch": 0.001796504981218357,
      "grad_norm": 0.941821277141571,
      "learning_rate": 9.957315789473684e-05,
      "loss": 0.8924,
      "step": 11
    },
    {
      "epoch": 0.0019598236158745713,
      "grad_norm": 0.8732932209968567,
      "learning_rate": 9.904631578947367e-05,
      "loss": 0.9978,
      "step": 12
    },
    {
      "epoch": 0.0021231422505307855,
      "grad_norm": 0.8224309086799622,
      "learning_rate": 9.851947368421052e-05,
      "loss": 1.064,
      "step": 13
    },
    {
      "epoch": 0.002286460885187,
      "grad_norm": 0.9332011342048645,
      "learning_rate": 9.799263157894736e-05,
      "loss": 1.0589,
      "step": 14
    },
    {
      "epoch": 0.002449779519843214,
      "grad_norm": 0.9349180459976196,
      "learning_rate": 9.746578947368421e-05,
      "loss": 1.1028,
      "step": 15
    },
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": 0.8387799263000488,
      "learning_rate": 9.693894736842104e-05,
      "loss": 1.0083,
      "step": 16
    },
    {
      "epoch": 0.0027764167891556426,
      "grad_norm": 0.8592500686645508,
      "learning_rate": 9.641210526315789e-05,
      "loss": 1.0184,
      "step": 17
    },
    {
      "epoch": 0.002939735423811857,
      "grad_norm": 0.8980984687805176,
      "learning_rate": 9.588526315789473e-05,
      "loss": 0.937,
      "step": 18
    },
    {
      "epoch": 0.003103054058468071,
      "grad_norm": 0.8308787941932678,
      "learning_rate": 9.535842105263157e-05,
      "loss": 0.9237,
      "step": 19
    },
    {
      "epoch": 0.0032663726931242854,
      "grad_norm": 1.0007582902908325,
      "learning_rate": 9.483157894736841e-05,
      "loss": 1.0406,
      "step": 20
    },
    {
      "epoch": 0.0034296913277804997,
      "grad_norm": 1.081726312637329,
      "learning_rate": 9.430473684210526e-05,
      "loss": 1.007,
      "step": 21
    },
    {
      "epoch": 0.003593009962436714,
      "grad_norm": 0.9985299110412598,
      "learning_rate": 9.37778947368421e-05,
      "loss": 1.0914,
      "step": 22
    },
    {
      "epoch": 0.0037563285970929282,
      "grad_norm": 1.0678647756576538,
      "learning_rate": 9.325105263157894e-05,
      "loss": 1.2774,
      "step": 23
    },
    {
      "epoch": 0.0039196472317491425,
      "grad_norm": 1.0457429885864258,
      "learning_rate": 9.272421052631578e-05,
      "loss": 0.9798,
      "step": 24
    },
    {
      "epoch": 0.004082965866405357,
      "grad_norm": 1.1700959205627441,
      "learning_rate": 9.219736842105263e-05,
      "loss": 1.2144,
      "step": 25
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 1.3236618041992188,
      "learning_rate": 9.167052631578946e-05,
      "loss": 1.1766,
      "step": 26
    },
    {
      "epoch": 0.004409603135717786,
      "grad_norm": 1.2073756456375122,
      "learning_rate": 9.114368421052632e-05,
      "loss": 0.8459,
      "step": 27
    },
    {
      "epoch": 0.004572921770374,
      "grad_norm": 1.3933292627334595,
      "learning_rate": 9.061684210526315e-05,
      "loss": 1.0467,
      "step": 28
    },
    {
      "epoch": 0.004736240405030214,
      "grad_norm": 1.4482253789901733,
      "learning_rate": 9.009e-05,
      "loss": 1.1401,
      "step": 29
    },
    {
      "epoch": 0.004899559039686428,
      "grad_norm": 1.365537405014038,
      "learning_rate": 8.956315789473683e-05,
      "loss": 0.9932,
      "step": 30
    },
    {
      "epoch": 0.005062877674342643,
      "grad_norm": 1.475220799446106,
      "learning_rate": 8.903631578947368e-05,
      "loss": 1.2499,
      "step": 31
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": 1.531992793083191,
      "learning_rate": 8.850947368421052e-05,
      "loss": 1.0115,
      "step": 32
    },
    {
      "epoch": 0.005389514943655071,
      "grad_norm": 2.305574655532837,
      "learning_rate": 8.798263157894736e-05,
      "loss": 0.9368,
      "step": 33
    },
    {
      "epoch": 0.005552833578311285,
      "grad_norm": 1.7354161739349365,
      "learning_rate": 8.745578947368422e-05,
      "loss": 1.049,
      "step": 34
    },
    {
      "epoch": 0.0057161522129675,
      "grad_norm": 2.7026562690734863,
      "learning_rate": 8.692894736842105e-05,
      "loss": 1.3359,
      "step": 35
    },
    {
      "epoch": 0.005879470847623714,
      "grad_norm": 2.1211535930633545,
      "learning_rate": 8.64021052631579e-05,
      "loss": 1.2523,
      "step": 36
    },
    {
      "epoch": 0.0060427894822799285,
      "grad_norm": 2.5288071632385254,
      "learning_rate": 8.587526315789473e-05,
      "loss": 1.43,
      "step": 37
    },
    {
      "epoch": 0.006206108116936142,
      "grad_norm": 2.433478832244873,
      "learning_rate": 8.534842105263157e-05,
      "loss": 1.214,
      "step": 38
    },
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 2.750303268432617,
      "learning_rate": 8.482157894736842e-05,
      "loss": 1.0099,
      "step": 39
    },
    {
      "epoch": 0.006532745386248571,
      "grad_norm": 2.981351375579834,
      "learning_rate": 8.429473684210525e-05,
      "loss": 1.6271,
      "step": 40
    },
    {
      "epoch": 0.0066960640209047856,
      "grad_norm": 3.7224624156951904,
      "learning_rate": 8.376789473684211e-05,
      "loss": 1.733,
      "step": 41
    },
    {
      "epoch": 0.006859382655560999,
      "grad_norm": 3.8278751373291016,
      "learning_rate": 8.324105263157894e-05,
      "loss": 1.5315,
      "step": 42
    },
    {
      "epoch": 0.007022701290217214,
      "grad_norm": 2.7715137004852295,
      "learning_rate": 8.271421052631579e-05,
      "loss": 1.103,
      "step": 43
    },
    {
      "epoch": 0.007186019924873428,
      "grad_norm": 4.1672892570495605,
      "learning_rate": 8.218736842105262e-05,
      "loss": 1.6296,
      "step": 44
    },
    {
      "epoch": 0.007349338559529643,
      "grad_norm": 4.840080261230469,
      "learning_rate": 8.166052631578947e-05,
      "loss": 1.3456,
      "step": 45
    },
    {
      "epoch": 0.0075126571941858565,
      "grad_norm": 4.377506256103516,
      "learning_rate": 8.113368421052631e-05,
      "loss": 1.6744,
      "step": 46
    },
    {
      "epoch": 0.007675975828842071,
      "grad_norm": 4.180212497711182,
      "learning_rate": 8.060684210526315e-05,
      "loss": 1.4903,
      "step": 47
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": 4.473518371582031,
      "learning_rate": 8.008e-05,
      "loss": 2.0731,
      "step": 48
    },
    {
      "epoch": 0.008002613098154499,
      "grad_norm": 7.101559162139893,
      "learning_rate": 7.955315789473684e-05,
      "loss": 2.0784,
      "step": 49
    },
    {
      "epoch": 0.008165931732810714,
      "grad_norm": 12.615863800048828,
      "learning_rate": 7.902631578947368e-05,
      "loss": 3.4556,
      "step": 50
    },
    {
      "epoch": 0.008165931732810714,
      "eval_loss": 1.2871240377426147,
      "eval_runtime": 345.3086,
      "eval_samples_per_second": 7.466,
      "eval_steps_per_second": 1.868,
      "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": 5,
        "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": 2.1806176530333696e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}