{
  "best_metric": 3.6099913120269775,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.362098138747885,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01353637901861252,
      "grad_norm": 0.9948562979698181,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.8518,
      "step": 1
    },
    {
      "epoch": 0.01353637901861252,
      "eval_loss": 3.73663592338562,
      "eval_runtime": 3.0532,
      "eval_samples_per_second": 40.941,
      "eval_steps_per_second": 10.481,
      "step": 1
    },
    {
      "epoch": 0.02707275803722504,
      "grad_norm": 0.8523895144462585,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.6192,
      "step": 2
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 0.87421715259552,
      "learning_rate": 1.5e-06,
      "loss": 3.4214,
      "step": 3
    },
    {
      "epoch": 0.05414551607445008,
      "grad_norm": 0.8437895774841309,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.4929,
      "step": 4
    },
    {
      "epoch": 0.0676818950930626,
      "grad_norm": 0.9417490363121033,
      "learning_rate": 2.5e-06,
      "loss": 3.8509,
      "step": 5
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 1.0578491687774658,
      "learning_rate": 3e-06,
      "loss": 3.611,
      "step": 6
    },
    {
      "epoch": 0.09475465313028765,
      "grad_norm": 0.9789345860481262,
      "learning_rate": 3.5e-06,
      "loss": 3.6955,
      "step": 7
    },
    {
      "epoch": 0.10829103214890017,
      "grad_norm": 1.0157725811004639,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.4882,
      "step": 8
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 0.925398051738739,
      "learning_rate": 4.5e-06,
      "loss": 3.5624,
      "step": 9
    },
    {
      "epoch": 0.1353637901861252,
      "grad_norm": 1.0446271896362305,
      "learning_rate": 5e-06,
      "loss": 3.4926,
      "step": 10
    },
    {
      "epoch": 0.14890016920473773,
      "grad_norm": 1.1525206565856934,
      "learning_rate": 4.99847706754774e-06,
      "loss": 3.8015,
      "step": 11
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 1.1337149143218994,
      "learning_rate": 4.993910125649561e-06,
      "loss": 3.8748,
      "step": 12
    },
    {
      "epoch": 0.17597292724196278,
      "grad_norm": 1.2873902320861816,
      "learning_rate": 4.986304738420684e-06,
      "loss": 3.6576,
      "step": 13
    },
    {
      "epoch": 0.1895093062605753,
      "grad_norm": 1.2369529008865356,
      "learning_rate": 4.975670171853926e-06,
      "loss": 3.7863,
      "step": 14
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 1.4233301877975464,
      "learning_rate": 4.962019382530521e-06,
      "loss": 4.0813,
      "step": 15
    },
    {
      "epoch": 0.21658206429780033,
      "grad_norm": 1.3197875022888184,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 3.6418,
      "step": 16
    },
    {
      "epoch": 0.23011844331641285,
      "grad_norm": 1.519278645515442,
      "learning_rate": 4.925739315689991e-06,
      "loss": 3.6749,
      "step": 17
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 1.6284841299057007,
      "learning_rate": 4.903154239845798e-06,
      "loss": 3.8066,
      "step": 18
    },
    {
      "epoch": 0.2571912013536379,
      "grad_norm": 0.8777332901954651,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 3.7021,
      "step": 19
    },
    {
      "epoch": 0.2707275803722504,
      "grad_norm": 1.0336490869522095,
      "learning_rate": 4.849231551964771e-06,
      "loss": 3.8224,
      "step": 20
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 0.8481849431991577,
      "learning_rate": 4.817959636416969e-06,
      "loss": 3.4932,
      "step": 21
    },
    {
      "epoch": 0.29780033840947545,
      "grad_norm": 0.8440786004066467,
      "learning_rate": 4.783863644106502e-06,
      "loss": 3.5257,
      "step": 22
    },
    {
      "epoch": 0.311336717428088,
      "grad_norm": 0.969007134437561,
      "learning_rate": 4.746985115747918e-06,
      "loss": 3.4107,
      "step": 23
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 1.0689656734466553,
      "learning_rate": 4.707368982147318e-06,
      "loss": 3.5495,
      "step": 24
    },
    {
      "epoch": 0.338409475465313,
      "grad_norm": 1.026020884513855,
      "learning_rate": 4.665063509461098e-06,
      "loss": 3.6805,
      "step": 25
    },
    {
      "epoch": 0.35194585448392557,
      "grad_norm": 1.0092445611953735,
      "learning_rate": 4.620120240391065e-06,
      "loss": 3.6131,
      "step": 26
    },
    {
      "epoch": 0.36548223350253806,
      "grad_norm": 1.1854077577590942,
      "learning_rate": 4.572593931387604e-06,
      "loss": 3.562,
      "step": 27
    },
    {
      "epoch": 0.3790186125211506,
      "grad_norm": 1.1046980619430542,
      "learning_rate": 4.522542485937369e-06,
      "loss": 3.4708,
      "step": 28
    },
    {
      "epoch": 0.3925549915397631,
      "grad_norm": 1.0798814296722412,
      "learning_rate": 4.470026884016805e-06,
      "loss": 3.5845,
      "step": 29
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 1.3098347187042236,
      "learning_rate": 4.415111107797445e-06,
      "loss": 3.7222,
      "step": 30
    },
    {
      "epoch": 0.4196277495769882,
      "grad_norm": 1.1865979433059692,
      "learning_rate": 4.357862063693486e-06,
      "loss": 3.8202,
      "step": 31
    },
    {
      "epoch": 0.43316412859560066,
      "grad_norm": 1.3540643453598022,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 3.8541,
      "step": 32
    },
    {
      "epoch": 0.4467005076142132,
      "grad_norm": 1.3513485193252563,
      "learning_rate": 4.236645926147493e-06,
      "loss": 3.7572,
      "step": 33
    },
    {
      "epoch": 0.4602368866328257,
      "grad_norm": 1.4294140338897705,
      "learning_rate": 4.172826515897146e-06,
      "loss": 3.8498,
      "step": 34
    },
    {
      "epoch": 0.47377326565143824,
      "grad_norm": 1.4952620267868042,
      "learning_rate": 4.106969024216348e-06,
      "loss": 3.8439,
      "step": 35
    },
    {
      "epoch": 0.4873096446700508,
      "grad_norm": 1.7355625629425049,
      "learning_rate": 4.039153688314146e-06,
      "loss": 3.8003,
      "step": 36
    },
    {
      "epoch": 0.5008460236886633,
      "grad_norm": 0.8707943558692932,
      "learning_rate": 3.969463130731183e-06,
      "loss": 3.6308,
      "step": 37
    },
    {
      "epoch": 0.5143824027072758,
      "grad_norm": 1.0384621620178223,
      "learning_rate": 3.897982258676867e-06,
      "loss": 3.5805,
      "step": 38
    },
    {
      "epoch": 0.5279187817258884,
      "grad_norm": 0.9388870000839233,
      "learning_rate": 3.824798160583012e-06,
      "loss": 3.7473,
      "step": 39
    },
    {
      "epoch": 0.5414551607445008,
      "grad_norm": 1.0139713287353516,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 3.6321,
      "step": 40
    },
    {
      "epoch": 0.5549915397631133,
      "grad_norm": 1.038153052330017,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 3.57,
      "step": 41
    },
    {
      "epoch": 0.5685279187817259,
      "grad_norm": 1.0182040929794312,
      "learning_rate": 3.595927866972694e-06,
      "loss": 3.4588,
      "step": 42
    },
    {
      "epoch": 0.5820642978003384,
      "grad_norm": 1.0943628549575806,
      "learning_rate": 3.516841607689501e-06,
      "loss": 3.6839,
      "step": 43
    },
    {
      "epoch": 0.5956006768189509,
      "grad_norm": 0.9982971549034119,
      "learning_rate": 3.436516483539781e-06,
      "loss": 3.4144,
      "step": 44
    },
    {
      "epoch": 0.6091370558375635,
      "grad_norm": 1.1169984340667725,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 3.745,
      "step": 45
    },
    {
      "epoch": 0.622673434856176,
      "grad_norm": 1.181325912475586,
      "learning_rate": 3.272542485937369e-06,
      "loss": 3.6186,
      "step": 46
    },
    {
      "epoch": 0.6362098138747885,
      "grad_norm": 1.1740070581436157,
      "learning_rate": 3.189093389542498e-06,
      "loss": 3.4177,
      "step": 47
    },
    {
      "epoch": 0.649746192893401,
      "grad_norm": 1.236719012260437,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 3.4231,
      "step": 48
    },
    {
      "epoch": 0.6632825719120136,
      "grad_norm": 1.3131681680679321,
      "learning_rate": 3.019779227044398e-06,
      "loss": 3.5528,
      "step": 49
    },
    {
      "epoch": 0.676818950930626,
      "grad_norm": 1.3397260904312134,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 3.7156,
      "step": 50
    },
    {
      "epoch": 0.676818950930626,
      "eval_loss": 3.658907413482666,
      "eval_runtime": 2.6656,
      "eval_samples_per_second": 46.894,
      "eval_steps_per_second": 12.005,
      "step": 50
    },
    {
      "epoch": 0.6903553299492385,
      "grad_norm": 1.3157494068145752,
      "learning_rate": 2.847932752400164e-06,
      "loss": 3.6715,
      "step": 51
    },
    {
      "epoch": 0.7038917089678511,
      "grad_norm": 1.6480339765548706,
      "learning_rate": 2.761321158169134e-06,
      "loss": 4.1417,
      "step": 52
    },
    {
      "epoch": 0.7174280879864636,
      "grad_norm": 1.518749713897705,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 3.6444,
      "step": 53
    },
    {
      "epoch": 0.7309644670050761,
      "grad_norm": 1.8039215803146362,
      "learning_rate": 2.587248741756253e-06,
      "loss": 3.9769,
      "step": 54
    },
    {
      "epoch": 0.7445008460236887,
      "grad_norm": 1.06398606300354,
      "learning_rate": 2.5e-06,
      "loss": 3.6596,
      "step": 55
    },
    {
      "epoch": 0.7580372250423012,
      "grad_norm": 1.0259342193603516,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 3.717,
      "step": 56
    },
    {
      "epoch": 0.7715736040609137,
      "grad_norm": 0.9348158836364746,
      "learning_rate": 2.325608815639687e-06,
      "loss": 3.3873,
      "step": 57
    },
    {
      "epoch": 0.7851099830795262,
      "grad_norm": 1.033394455909729,
      "learning_rate": 2.238678841830867e-06,
      "loss": 3.5139,
      "step": 58
    },
    {
      "epoch": 0.7986463620981388,
      "grad_norm": 1.0691534280776978,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 3.4741,
      "step": 59
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 1.0994362831115723,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 3.5142,
      "step": 60
    },
    {
      "epoch": 0.8257191201353637,
      "grad_norm": 1.0791237354278564,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 3.3452,
      "step": 61
    },
    {
      "epoch": 0.8392554991539763,
      "grad_norm": 1.16475248336792,
      "learning_rate": 1.895195261000831e-06,
      "loss": 3.7296,
      "step": 62
    },
    {
      "epoch": 0.8527918781725888,
      "grad_norm": 1.1288127899169922,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 3.3933,
      "step": 63
    },
    {
      "epoch": 0.8663282571912013,
      "grad_norm": 1.2290265560150146,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 3.5753,
      "step": 64
    },
    {
      "epoch": 0.8798646362098139,
      "grad_norm": 1.143328070640564,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 3.6006,
      "step": 65
    },
    {
      "epoch": 0.8934010152284264,
      "grad_norm": 1.249060034751892,
      "learning_rate": 1.56348351646022e-06,
      "loss": 3.4214,
      "step": 66
    },
    {
      "epoch": 0.9069373942470389,
      "grad_norm": 1.3204628229141235,
      "learning_rate": 1.4831583923105e-06,
      "loss": 3.3819,
      "step": 67
    },
    {
      "epoch": 0.9204737732656514,
      "grad_norm": 1.3643982410430908,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 3.8538,
      "step": 68
    },
    {
      "epoch": 0.934010152284264,
      "grad_norm": 1.2954354286193848,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 3.8072,
      "step": 69
    },
    {
      "epoch": 0.9475465313028765,
      "grad_norm": 1.635848045349121,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 3.6974,
      "step": 70
    },
    {
      "epoch": 0.961082910321489,
      "grad_norm": 1.5739266872406006,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 3.8517,
      "step": 71
    },
    {
      "epoch": 0.9746192893401016,
      "grad_norm": 1.9741549491882324,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 4.3486,
      "step": 72
    },
    {
      "epoch": 0.988155668358714,
      "grad_norm": 1.0924246311187744,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 3.5943,
      "step": 73
    },
    {
      "epoch": 1.0101522842639594,
      "grad_norm": 1.7769662141799927,
      "learning_rate": 9.608463116858544e-07,
      "loss": 5.9384,
      "step": 74
    },
    {
      "epoch": 1.023688663282572,
      "grad_norm": 1.0755778551101685,
      "learning_rate": 8.930309757836517e-07,
      "loss": 3.7781,
      "step": 75
    },
    {
      "epoch": 1.0372250423011844,
      "grad_norm": 0.9576964974403381,
      "learning_rate": 8.271734841028553e-07,
      "loss": 3.274,
      "step": 76
    },
    {
      "epoch": 1.0507614213197969,
      "grad_norm": 1.0078204870224,
      "learning_rate": 7.633540738525066e-07,
      "loss": 3.5456,
      "step": 77
    },
    {
      "epoch": 1.0642978003384094,
      "grad_norm": 0.9900814890861511,
      "learning_rate": 7.016504991533727e-07,
      "loss": 3.7089,
      "step": 78
    },
    {
      "epoch": 1.077834179357022,
      "grad_norm": 1.0500483512878418,
      "learning_rate": 6.421379363065142e-07,
      "loss": 3.5293,
      "step": 79
    },
    {
      "epoch": 1.0913705583756346,
      "grad_norm": 1.1538033485412598,
      "learning_rate": 5.848888922025553e-07,
      "loss": 3.4348,
      "step": 80
    },
    {
      "epoch": 1.104906937394247,
      "grad_norm": 1.0635679960250854,
      "learning_rate": 5.299731159831953e-07,
      "loss": 3.4902,
      "step": 81
    },
    {
      "epoch": 1.1184433164128595,
      "grad_norm": 1.1531682014465332,
      "learning_rate": 4.774575140626317e-07,
      "loss": 3.5306,
      "step": 82
    },
    {
      "epoch": 1.131979695431472,
      "grad_norm": 1.1337559223175049,
      "learning_rate": 4.27406068612396e-07,
      "loss": 3.6038,
      "step": 83
    },
    {
      "epoch": 1.1455160744500845,
      "grad_norm": 1.1763681173324585,
      "learning_rate": 3.798797596089351e-07,
      "loss": 3.4732,
      "step": 84
    },
    {
      "epoch": 1.1590524534686972,
      "grad_norm": 1.3725019693374634,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 3.5141,
      "step": 85
    },
    {
      "epoch": 1.1725888324873097,
      "grad_norm": 1.287148356437683,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 3.4666,
      "step": 86
    },
    {
      "epoch": 1.1861252115059222,
      "grad_norm": 1.2582811117172241,
      "learning_rate": 2.53014884252083e-07,
      "loss": 3.5794,
      "step": 87
    },
    {
      "epoch": 1.1996615905245347,
      "grad_norm": 1.3983982801437378,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 3.6621,
      "step": 88
    },
    {
      "epoch": 1.2131979695431472,
      "grad_norm": 1.4939510822296143,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 3.6124,
      "step": 89
    },
    {
      "epoch": 1.2267343485617597,
      "grad_norm": 1.648148536682129,
      "learning_rate": 1.507684480352292e-07,
      "loss": 3.7459,
      "step": 90
    },
    {
      "epoch": 1.2402707275803722,
      "grad_norm": 1.8571910858154297,
      "learning_rate": 1.223587092621162e-07,
      "loss": 4.112,
      "step": 91
    },
    {
      "epoch": 1.2538071065989849,
      "grad_norm": 1.3094947338104248,
      "learning_rate": 9.684576015420277e-08,
      "loss": 3.7015,
      "step": 92
    },
    {
      "epoch": 1.2673434856175974,
      "grad_norm": 1.080057978630066,
      "learning_rate": 7.426068431000883e-08,
      "loss": 3.5508,
      "step": 93
    },
    {
      "epoch": 1.2808798646362098,
      "grad_norm": 1.052301049232483,
      "learning_rate": 5.463099816548578e-08,
      "loss": 3.5461,
      "step": 94
    },
    {
      "epoch": 1.2944162436548223,
      "grad_norm": 1.0805667638778687,
      "learning_rate": 3.798061746947995e-08,
      "loss": 3.672,
      "step": 95
    },
    {
      "epoch": 1.3079526226734348,
      "grad_norm": 1.0864343643188477,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 3.4411,
      "step": 96
    },
    {
      "epoch": 1.3214890016920473,
      "grad_norm": 1.0621790885925293,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 3.3916,
      "step": 97
    },
    {
      "epoch": 1.3350253807106598,
      "grad_norm": 1.1159321069717407,
      "learning_rate": 6.089874350439507e-09,
      "loss": 3.4388,
      "step": 98
    },
    {
      "epoch": 1.3485617597292725,
      "grad_norm": 1.1290203332901,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 3.4397,
      "step": 99
    },
    {
      "epoch": 1.362098138747885,
      "grad_norm": 1.1767339706420898,
      "learning_rate": 0.0,
      "loss": 3.4482,
      "step": 100
    },
    {
      "epoch": 1.362098138747885,
      "eval_loss": 3.6099913120269775,
      "eval_runtime": 2.6641,
      "eval_samples_per_second": 46.92,
      "eval_steps_per_second": 12.011,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.066457809859379e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}