{
  "best_metric": 0.922777533531189,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.08743169398907104,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008743169398907104,
      "grad_norm": 13.654485702514648,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 7.2397,
      "step": 1
    },
    {
      "epoch": 0.0008743169398907104,
      "eval_loss": 2.0816423892974854,
      "eval_runtime": 234.4717,
      "eval_samples_per_second": 32.857,
      "eval_steps_per_second": 4.107,
      "step": 1
    },
    {
      "epoch": 0.0017486338797814208,
      "grad_norm": 16.08323097229004,
      "learning_rate": 6.666666666666667e-06,
      "loss": 7.3886,
      "step": 2
    },
    {
      "epoch": 0.002622950819672131,
      "grad_norm": 16.72583770751953,
      "learning_rate": 1e-05,
      "loss": 7.2155,
      "step": 3
    },
    {
      "epoch": 0.0034972677595628415,
      "grad_norm": 16.019792556762695,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 6.8998,
      "step": 4
    },
    {
      "epoch": 0.004371584699453552,
      "grad_norm": 10.719884872436523,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 6.1133,
      "step": 5
    },
    {
      "epoch": 0.005245901639344262,
      "grad_norm": 99.27400207519531,
      "learning_rate": 2e-05,
      "loss": 10.2652,
      "step": 6
    },
    {
      "epoch": 0.006120218579234973,
      "grad_norm": 85.72102355957031,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 9.529,
      "step": 7
    },
    {
      "epoch": 0.006994535519125683,
      "grad_norm": 15.085773468017578,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 5.6537,
      "step": 8
    },
    {
      "epoch": 0.007868852459016393,
      "grad_norm": 12.465982437133789,
      "learning_rate": 3e-05,
      "loss": 5.3902,
      "step": 9
    },
    {
      "epoch": 0.008743169398907104,
      "grad_norm": 9.44223403930664,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.2389,
      "step": 10
    },
    {
      "epoch": 0.009617486338797814,
      "grad_norm": 7.920454025268555,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 4.7169,
      "step": 11
    },
    {
      "epoch": 0.010491803278688525,
      "grad_norm": 8.882831573486328,
      "learning_rate": 4e-05,
      "loss": 4.4305,
      "step": 12
    },
    {
      "epoch": 0.011366120218579235,
      "grad_norm": 6.801806926727295,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 4.3088,
      "step": 13
    },
    {
      "epoch": 0.012240437158469945,
      "grad_norm": 7.269967555999756,
      "learning_rate": 4.666666666666667e-05,
      "loss": 5.6956,
      "step": 14
    },
    {
      "epoch": 0.013114754098360656,
      "grad_norm": 6.725127220153809,
      "learning_rate": 5e-05,
      "loss": 5.209,
      "step": 15
    },
    {
      "epoch": 0.013989071038251366,
      "grad_norm": 6.431244373321533,
      "learning_rate": 5.333333333333333e-05,
      "loss": 5.1324,
      "step": 16
    },
    {
      "epoch": 0.014863387978142076,
      "grad_norm": 5.522418975830078,
      "learning_rate": 5.666666666666667e-05,
      "loss": 4.8785,
      "step": 17
    },
    {
      "epoch": 0.015737704918032787,
      "grad_norm": 13.761688232421875,
      "learning_rate": 6e-05,
      "loss": 3.9461,
      "step": 18
    },
    {
      "epoch": 0.016612021857923497,
      "grad_norm": 23.60154914855957,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.3604,
      "step": 19
    },
    {
      "epoch": 0.017486338797814208,
      "grad_norm": 14.374363899230957,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.9006,
      "step": 20
    },
    {
      "epoch": 0.018360655737704918,
      "grad_norm": 8.315186500549316,
      "learning_rate": 7e-05,
      "loss": 4.7994,
      "step": 21
    },
    {
      "epoch": 0.01923497267759563,
      "grad_norm": 6.13319730758667,
      "learning_rate": 7.333333333333333e-05,
      "loss": 4.6416,
      "step": 22
    },
    {
      "epoch": 0.02010928961748634,
      "grad_norm": 5.479979038238525,
      "learning_rate": 7.666666666666667e-05,
      "loss": 4.4633,
      "step": 23
    },
    {
      "epoch": 0.02098360655737705,
      "grad_norm": 6.043623924255371,
      "learning_rate": 8e-05,
      "loss": 4.2832,
      "step": 24
    },
    {
      "epoch": 0.02185792349726776,
      "grad_norm": 6.044895172119141,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.8783,
      "step": 25
    },
    {
      "epoch": 0.02273224043715847,
      "grad_norm": 6.741650104522705,
      "learning_rate": 8.666666666666667e-05,
      "loss": 5.4952,
      "step": 26
    },
    {
      "epoch": 0.02360655737704918,
      "grad_norm": 6.030343532562256,
      "learning_rate": 9e-05,
      "loss": 5.1832,
      "step": 27
    },
    {
      "epoch": 0.02448087431693989,
      "grad_norm": 5.912640571594238,
      "learning_rate": 9.333333333333334e-05,
      "loss": 4.8941,
      "step": 28
    },
    {
      "epoch": 0.0253551912568306,
      "grad_norm": 4.158953666687012,
      "learning_rate": 9.666666666666667e-05,
      "loss": 4.8204,
      "step": 29
    },
    {
      "epoch": 0.02622950819672131,
      "grad_norm": 4.939655303955078,
      "learning_rate": 0.0001,
      "loss": 4.4874,
      "step": 30
    },
    {
      "epoch": 0.027103825136612022,
      "grad_norm": 6.877912521362305,
      "learning_rate": 9.999146252290264e-05,
      "loss": 3.2959,
      "step": 31
    },
    {
      "epoch": 0.027978142076502732,
      "grad_norm": 7.6934590339660645,
      "learning_rate": 9.996585300715116e-05,
      "loss": 1.1399,
      "step": 32
    },
    {
      "epoch": 0.028852459016393443,
      "grad_norm": 5.374224662780762,
      "learning_rate": 9.99231801983717e-05,
      "loss": 4.0316,
      "step": 33
    },
    {
      "epoch": 0.029726775956284153,
      "grad_norm": 4.416872978210449,
      "learning_rate": 9.986345866928941e-05,
      "loss": 4.449,
      "step": 34
    },
    {
      "epoch": 0.030601092896174863,
      "grad_norm": 4.096227645874023,
      "learning_rate": 9.978670881475172e-05,
      "loss": 4.4694,
      "step": 35
    },
    {
      "epoch": 0.031475409836065574,
      "grad_norm": 4.204520225524902,
      "learning_rate": 9.96929568447637e-05,
      "loss": 4.1511,
      "step": 36
    },
    {
      "epoch": 0.03234972677595629,
      "grad_norm": 4.906490802764893,
      "learning_rate": 9.958223477553714e-05,
      "loss": 3.9031,
      "step": 37
    },
    {
      "epoch": 0.033224043715846995,
      "grad_norm": 4.104410171508789,
      "learning_rate": 9.94545804185573e-05,
      "loss": 3.9166,
      "step": 38
    },
    {
      "epoch": 0.03409836065573771,
      "grad_norm": 4.067167282104492,
      "learning_rate": 9.931003736767013e-05,
      "loss": 5.0196,
      "step": 39
    },
    {
      "epoch": 0.034972677595628415,
      "grad_norm": 3.7131476402282715,
      "learning_rate": 9.91486549841951e-05,
      "loss": 4.8069,
      "step": 40
    },
    {
      "epoch": 0.03584699453551913,
      "grad_norm": 3.895036220550537,
      "learning_rate": 9.89704883800683e-05,
      "loss": 4.7326,
      "step": 41
    },
    {
      "epoch": 0.036721311475409836,
      "grad_norm": 3.369447946548462,
      "learning_rate": 9.877559839902184e-05,
      "loss": 4.5296,
      "step": 42
    },
    {
      "epoch": 0.03759562841530055,
      "grad_norm": 3.4959802627563477,
      "learning_rate": 9.85640515958057e-05,
      "loss": 3.6448,
      "step": 43
    },
    {
      "epoch": 0.03846994535519126,
      "grad_norm": 3.181074619293213,
      "learning_rate": 9.833592021345937e-05,
      "loss": 1.2202,
      "step": 44
    },
    {
      "epoch": 0.03934426229508197,
      "grad_norm": 6.853686332702637,
      "learning_rate": 9.809128215864097e-05,
      "loss": 3.2771,
      "step": 45
    },
    {
      "epoch": 0.04021857923497268,
      "grad_norm": 4.203513145446777,
      "learning_rate": 9.783022097502204e-05,
      "loss": 4.3558,
      "step": 46
    },
    {
      "epoch": 0.04109289617486339,
      "grad_norm": 3.710810422897339,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.2005,
      "step": 47
    },
    {
      "epoch": 0.0419672131147541,
      "grad_norm": 4.0080156326293945,
      "learning_rate": 9.725919140804099e-05,
      "loss": 4.1753,
      "step": 48
    },
    {
      "epoch": 0.04284153005464481,
      "grad_norm": 4.323927402496338,
      "learning_rate": 9.694941803075283e-05,
      "loss": 4.033,
      "step": 49
    },
    {
      "epoch": 0.04371584699453552,
      "grad_norm": 5.3773722648620605,
      "learning_rate": 9.662361147021779e-05,
      "loss": 3.0192,
      "step": 50
    },
    {
      "epoch": 0.04371584699453552,
      "eval_loss": 0.959044873714447,
      "eval_runtime": 235.9651,
      "eval_samples_per_second": 32.649,
      "eval_steps_per_second": 4.081,
      "step": 50
    },
    {
      "epoch": 0.04459016393442623,
      "grad_norm": 4.682861804962158,
      "learning_rate": 9.628188298907782e-05,
      "loss": 5.3309,
      "step": 51
    },
    {
      "epoch": 0.04546448087431694,
      "grad_norm": 3.6267170906066895,
      "learning_rate": 9.592434928729616e-05,
      "loss": 4.896,
      "step": 52
    },
    {
      "epoch": 0.046338797814207654,
      "grad_norm": 2.9397659301757812,
      "learning_rate": 9.555113246230442e-05,
      "loss": 4.594,
      "step": 53
    },
    {
      "epoch": 0.04721311475409836,
      "grad_norm": 3.7889232635498047,
      "learning_rate": 9.516235996730645e-05,
      "loss": 4.6179,
      "step": 54
    },
    {
      "epoch": 0.048087431693989074,
      "grad_norm": 3.4238991737365723,
      "learning_rate": 9.475816456775313e-05,
      "loss": 4.3046,
      "step": 55
    },
    {
      "epoch": 0.04896174863387978,
      "grad_norm": 6.835710048675537,
      "learning_rate": 9.43386842960031e-05,
      "loss": 1.9497,
      "step": 56
    },
    {
      "epoch": 0.049836065573770495,
      "grad_norm": 6.923791885375977,
      "learning_rate": 9.39040624041849e-05,
      "loss": 2.179,
      "step": 57
    },
    {
      "epoch": 0.0507103825136612,
      "grad_norm": 4.5648932456970215,
      "learning_rate": 9.345444731527642e-05,
      "loss": 4.3407,
      "step": 58
    },
    {
      "epoch": 0.051584699453551916,
      "grad_norm": 3.808917284011841,
      "learning_rate": 9.298999257241863e-05,
      "loss": 4.3087,
      "step": 59
    },
    {
      "epoch": 0.05245901639344262,
      "grad_norm": 3.44407320022583,
      "learning_rate": 9.251085678648072e-05,
      "loss": 4.0944,
      "step": 60
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 3.4684829711914062,
      "learning_rate": 9.201720358189464e-05,
      "loss": 3.9452,
      "step": 61
    },
    {
      "epoch": 0.054207650273224044,
      "grad_norm": 4.555397033691406,
      "learning_rate": 9.150920154077754e-05,
      "loss": 3.8704,
      "step": 62
    },
    {
      "epoch": 0.05508196721311476,
      "grad_norm": 3.6485466957092285,
      "learning_rate": 9.098702414536107e-05,
      "loss": 3.9606,
      "step": 63
    },
    {
      "epoch": 0.055956284153005464,
      "grad_norm": 3.0883123874664307,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.0169,
      "step": 64
    },
    {
      "epoch": 0.05683060109289618,
      "grad_norm": 2.731473684310913,
      "learning_rate": 8.9900861364012e-05,
      "loss": 4.6796,
      "step": 65
    },
    {
      "epoch": 0.057704918032786885,
      "grad_norm": 3.1372900009155273,
      "learning_rate": 8.933724690167417e-05,
      "loss": 4.5271,
      "step": 66
    },
    {
      "epoch": 0.0585792349726776,
      "grad_norm": 2.9355735778808594,
      "learning_rate": 8.876019880555649e-05,
      "loss": 4.2805,
      "step": 67
    },
    {
      "epoch": 0.059453551912568306,
      "grad_norm": 2.6107537746429443,
      "learning_rate": 8.816991413705516e-05,
      "loss": 3.3194,
      "step": 68
    },
    {
      "epoch": 0.06032786885245902,
      "grad_norm": 9.008191108703613,
      "learning_rate": 8.756659447784368e-05,
      "loss": 1.2466,
      "step": 69
    },
    {
      "epoch": 0.06120218579234973,
      "grad_norm": 3.1812331676483154,
      "learning_rate": 8.695044586103296e-05,
      "loss": 3.4345,
      "step": 70
    },
    {
      "epoch": 0.06207650273224044,
      "grad_norm": 3.384528636932373,
      "learning_rate": 8.632167870081121e-05,
      "loss": 4.3751,
      "step": 71
    },
    {
      "epoch": 0.06295081967213115,
      "grad_norm": 2.8234190940856934,
      "learning_rate": 8.568050772058762e-05,
      "loss": 4.2436,
      "step": 72
    },
    {
      "epoch": 0.06382513661202185,
      "grad_norm": 3.3963890075683594,
      "learning_rate": 8.502715187966455e-05,
      "loss": 4.0892,
      "step": 73
    },
    {
      "epoch": 0.06469945355191258,
      "grad_norm": 3.8028182983398438,
      "learning_rate": 8.436183429846313e-05,
      "loss": 3.8655,
      "step": 74
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 4.164633274078369,
      "learning_rate": 8.368478218232787e-05,
      "loss": 3.1239,
      "step": 75
    },
    {
      "epoch": 0.06644808743169399,
      "grad_norm": 2.5254907608032227,
      "learning_rate": 8.299622674393614e-05,
      "loss": 5.017,
      "step": 76
    },
    {
      "epoch": 0.0673224043715847,
      "grad_norm": 2.449016809463501,
      "learning_rate": 8.229640312433937e-05,
      "loss": 4.8344,
      "step": 77
    },
    {
      "epoch": 0.06819672131147542,
      "grad_norm": 2.4585683345794678,
      "learning_rate": 8.158555031266254e-05,
      "loss": 4.6238,
      "step": 78
    },
    {
      "epoch": 0.06907103825136612,
      "grad_norm": 2.7618460655212402,
      "learning_rate": 8.086391106448965e-05,
      "loss": 4.4138,
      "step": 79
    },
    {
      "epoch": 0.06994535519125683,
      "grad_norm": 2.7431366443634033,
      "learning_rate": 8.013173181896283e-05,
      "loss": 4.3351,
      "step": 80
    },
    {
      "epoch": 0.07081967213114754,
      "grad_norm": 2.915708541870117,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.7006,
      "step": 81
    },
    {
      "epoch": 0.07169398907103826,
      "grad_norm": 6.260775566101074,
      "learning_rate": 7.863675700402526e-05,
      "loss": 1.3999,
      "step": 82
    },
    {
      "epoch": 0.07256830601092897,
      "grad_norm": 3.342338800430298,
      "learning_rate": 7.787447196714427e-05,
      "loss": 3.8281,
      "step": 83
    },
    {
      "epoch": 0.07344262295081967,
      "grad_norm": 3.0507147312164307,
      "learning_rate": 7.710266782362247e-05,
      "loss": 4.256,
      "step": 84
    },
    {
      "epoch": 0.07431693989071038,
      "grad_norm": 3.881892681121826,
      "learning_rate": 7.63216081438678e-05,
      "loss": 4.2829,
      "step": 85
    },
    {
      "epoch": 0.0751912568306011,
      "grad_norm": 3.3180391788482666,
      "learning_rate": 7.553155965904535e-05,
      "loss": 3.8737,
      "step": 86
    },
    {
      "epoch": 0.0760655737704918,
      "grad_norm": 3.3876357078552246,
      "learning_rate": 7.473279216998895e-05,
      "loss": 3.9718,
      "step": 87
    },
    {
      "epoch": 0.07693989071038251,
      "grad_norm": 5.030557155609131,
      "learning_rate": 7.392557845506432e-05,
      "loss": 3.6383,
      "step": 88
    },
    {
      "epoch": 0.07781420765027322,
      "grad_norm": 2.6808958053588867,
      "learning_rate": 7.311019417701566e-05,
      "loss": 4.9168,
      "step": 89
    },
    {
      "epoch": 0.07868852459016394,
      "grad_norm": 2.51533842086792,
      "learning_rate": 7.228691778882693e-05,
      "loss": 4.7042,
      "step": 90
    },
    {
      "epoch": 0.07956284153005465,
      "grad_norm": 2.41265869140625,
      "learning_rate": 7.145603043863045e-05,
      "loss": 4.3564,
      "step": 91
    },
    {
      "epoch": 0.08043715846994536,
      "grad_norm": 2.5100467205047607,
      "learning_rate": 7.061781587369519e-05,
      "loss": 4.3584,
      "step": 92
    },
    {
      "epoch": 0.08131147540983606,
      "grad_norm": 2.604959487915039,
      "learning_rate": 6.977256034352712e-05,
      "loss": 4.0976,
      "step": 93
    },
    {
      "epoch": 0.08218579234972678,
      "grad_norm": 5.754001617431641,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.9558,
      "step": 94
    },
    {
      "epoch": 0.08306010928961749,
      "grad_norm": 3.077754020690918,
      "learning_rate": 6.806208330935766e-05,
      "loss": 3.4805,
      "step": 95
    },
    {
      "epoch": 0.0839344262295082,
      "grad_norm": 2.9729459285736084,
      "learning_rate": 6.719744593169641e-05,
      "loss": 4.2485,
      "step": 96
    },
    {
      "epoch": 0.0848087431693989,
      "grad_norm": 2.972970962524414,
      "learning_rate": 6.632693564200416e-05,
      "loss": 4.1844,
      "step": 97
    },
    {
      "epoch": 0.08568306010928962,
      "grad_norm": 2.8650026321411133,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.9211,
      "step": 98
    },
    {
      "epoch": 0.08655737704918033,
      "grad_norm": 3.496151924133301,
      "learning_rate": 6.456948734446624e-05,
      "loss": 3.981,
      "step": 99
    },
    {
      "epoch": 0.08743169398907104,
      "grad_norm": 4.358485698699951,
      "learning_rate": 6.368314950360415e-05,
      "loss": 3.0869,
      "step": 100
    },
    {
      "epoch": 0.08743169398907104,
      "eval_loss": 0.922777533531189,
      "eval_runtime": 236.35,
      "eval_samples_per_second": 32.596,
      "eval_steps_per_second": 4.074,
      "step": 100
    }
  ],
  "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": 8.940170116071424e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}