{
  "best_metric": 8.485151290893555,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.06755705682348496,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007111269139314207,
      "grad_norm": 4.551875591278076,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.2843,
      "step": 1
    },
    {
      "epoch": 0.0007111269139314207,
      "eval_loss": 10.709673881530762,
      "eval_runtime": 0.4786,
      "eval_samples_per_second": 104.474,
      "eval_steps_per_second": 27.163,
      "step": 1
    },
    {
      "epoch": 0.0014222538278628415,
      "grad_norm": 4.867107391357422,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.4354,
      "step": 2
    },
    {
      "epoch": 0.002133380741794262,
      "grad_norm": 5.008926868438721,
      "learning_rate": 0.0001,
      "loss": 10.5558,
      "step": 3
    },
    {
      "epoch": 0.002844507655725683,
      "grad_norm": 4.5886006355285645,
      "learning_rate": 9.997376600647783e-05,
      "loss": 10.7391,
      "step": 4
    },
    {
      "epoch": 0.0035556345696571034,
      "grad_norm": 4.7824931144714355,
      "learning_rate": 9.989509461357426e-05,
      "loss": 10.5872,
      "step": 5
    },
    {
      "epoch": 0.004266761483588524,
      "grad_norm": 4.664742946624756,
      "learning_rate": 9.976407754861426e-05,
      "loss": 10.5323,
      "step": 6
    },
    {
      "epoch": 0.004977888397519945,
      "grad_norm": 4.836978912353516,
      "learning_rate": 9.958086757163489e-05,
      "loss": 10.5264,
      "step": 7
    },
    {
      "epoch": 0.005689015311451366,
      "grad_norm": 4.371374607086182,
      "learning_rate": 9.934567829727386e-05,
      "loss": 10.2373,
      "step": 8
    },
    {
      "epoch": 0.006400142225382786,
      "grad_norm": 4.762342929840088,
      "learning_rate": 9.905878394570453e-05,
      "loss": 10.4186,
      "step": 9
    },
    {
      "epoch": 0.007111269139314207,
      "grad_norm": 4.17842435836792,
      "learning_rate": 9.872051902290737e-05,
      "loss": 10.331,
      "step": 10
    },
    {
      "epoch": 0.007822396053245627,
      "grad_norm": 4.5304059982299805,
      "learning_rate": 9.833127793065098e-05,
      "loss": 10.4491,
      "step": 11
    },
    {
      "epoch": 0.008533522967177049,
      "grad_norm": 4.463905334472656,
      "learning_rate": 9.789151450663723e-05,
      "loss": 10.2205,
      "step": 12
    },
    {
      "epoch": 0.00924464988110847,
      "grad_norm": 3.405884027481079,
      "learning_rate": 9.740174149534693e-05,
      "loss": 9.3648,
      "step": 13
    },
    {
      "epoch": 0.00995577679503989,
      "grad_norm": 3.4769484996795654,
      "learning_rate": 9.686252995020249e-05,
      "loss": 9.4946,
      "step": 14
    },
    {
      "epoch": 0.01066690370897131,
      "grad_norm": 3.3445122241973877,
      "learning_rate": 9.627450856774539e-05,
      "loss": 9.4722,
      "step": 15
    },
    {
      "epoch": 0.011378030622902732,
      "grad_norm": 3.351897716522217,
      "learning_rate": 9.563836295460398e-05,
      "loss": 9.4804,
      "step": 16
    },
    {
      "epoch": 0.012089157536834151,
      "grad_norm": 3.094649314880371,
      "learning_rate": 9.495483482810688e-05,
      "loss": 9.5855,
      "step": 17
    },
    {
      "epoch": 0.012800284450765573,
      "grad_norm": 2.8600270748138428,
      "learning_rate": 9.422472115147382e-05,
      "loss": 9.812,
      "step": 18
    },
    {
      "epoch": 0.013511411364696994,
      "grad_norm": 2.8953499794006348,
      "learning_rate": 9.3448873204592e-05,
      "loss": 9.3379,
      "step": 19
    },
    {
      "epoch": 0.014222538278628414,
      "grad_norm": 2.8371353149414062,
      "learning_rate": 9.2628195591462e-05,
      "loss": 9.3945,
      "step": 20
    },
    {
      "epoch": 0.014933665192559835,
      "grad_norm": 2.5929179191589355,
      "learning_rate": 9.176364518546989e-05,
      "loss": 9.698,
      "step": 21
    },
    {
      "epoch": 0.015644792106491254,
      "grad_norm": 2.513587474822998,
      "learning_rate": 9.08562300137157e-05,
      "loss": 9.4719,
      "step": 22
    },
    {
      "epoch": 0.016355919020422677,
      "grad_norm": 2.3741440773010254,
      "learning_rate": 8.990700808169889e-05,
      "loss": 9.5754,
      "step": 23
    },
    {
      "epoch": 0.017067045934354097,
      "grad_norm": 2.4249138832092285,
      "learning_rate": 8.891708613973126e-05,
      "loss": 9.6962,
      "step": 24
    },
    {
      "epoch": 0.017778172848285517,
      "grad_norm": 2.4952895641326904,
      "learning_rate": 8.788761839251559e-05,
      "loss": 9.6702,
      "step": 25
    },
    {
      "epoch": 0.017778172848285517,
      "eval_loss": 9.109885215759277,
      "eval_runtime": 0.4854,
      "eval_samples_per_second": 103.018,
      "eval_steps_per_second": 26.785,
      "step": 25
    },
    {
      "epoch": 0.01848929976221694,
      "grad_norm": 2.8521015644073486,
      "learning_rate": 8.681980515339464e-05,
      "loss": 8.6864,
      "step": 26
    },
    {
      "epoch": 0.01920042667614836,
      "grad_norm": 2.44402813911438,
      "learning_rate": 8.571489144483944e-05,
      "loss": 8.9519,
      "step": 27
    },
    {
      "epoch": 0.01991155359007978,
      "grad_norm": 2.12821102142334,
      "learning_rate": 8.457416554680877e-05,
      "loss": 9.0138,
      "step": 28
    },
    {
      "epoch": 0.0206226805040112,
      "grad_norm": 2.280055522918701,
      "learning_rate": 8.339895749467238e-05,
      "loss": 8.9783,
      "step": 29
    },
    {
      "epoch": 0.02133380741794262,
      "grad_norm": 2.1755645275115967,
      "learning_rate": 8.219063752844926e-05,
      "loss": 9.1297,
      "step": 30
    },
    {
      "epoch": 0.02204493433187404,
      "grad_norm": 1.9306710958480835,
      "learning_rate": 8.095061449516903e-05,
      "loss": 9.2654,
      "step": 31
    },
    {
      "epoch": 0.022756061245805464,
      "grad_norm": 1.8951246738433838,
      "learning_rate": 7.968033420621935e-05,
      "loss": 9.178,
      "step": 32
    },
    {
      "epoch": 0.023467188159736883,
      "grad_norm": 1.691171646118164,
      "learning_rate": 7.838127775159452e-05,
      "loss": 9.2195,
      "step": 33
    },
    {
      "epoch": 0.024178315073668303,
      "grad_norm": 1.6155242919921875,
      "learning_rate": 7.705495977301078e-05,
      "loss": 9.2252,
      "step": 34
    },
    {
      "epoch": 0.024889441987599726,
      "grad_norm": 1.6779975891113281,
      "learning_rate": 7.570292669790186e-05,
      "loss": 9.3166,
      "step": 35
    },
    {
      "epoch": 0.025600568901531146,
      "grad_norm": 1.8211243152618408,
      "learning_rate": 7.43267549363537e-05,
      "loss": 9.5693,
      "step": 36
    },
    {
      "epoch": 0.026311695815462565,
      "grad_norm": 1.7902308702468872,
      "learning_rate": 7.292804904308087e-05,
      "loss": 9.2382,
      "step": 37
    },
    {
      "epoch": 0.027022822729393988,
      "grad_norm": 1.4765057563781738,
      "learning_rate": 7.150843984658754e-05,
      "loss": 8.6352,
      "step": 38
    },
    {
      "epoch": 0.027733949643325408,
      "grad_norm": 1.5339429378509521,
      "learning_rate": 7.006958254769438e-05,
      "loss": 8.7898,
      "step": 39
    },
    {
      "epoch": 0.028445076557256827,
      "grad_norm": 1.5897561311721802,
      "learning_rate": 6.861315478964841e-05,
      "loss": 8.5414,
      "step": 40
    },
    {
      "epoch": 0.02915620347118825,
      "grad_norm": 1.5000419616699219,
      "learning_rate": 6.714085470206609e-05,
      "loss": 8.7796,
      "step": 41
    },
    {
      "epoch": 0.02986733038511967,
      "grad_norm": 1.3983110189437866,
      "learning_rate": 6.56543989209901e-05,
      "loss": 8.8589,
      "step": 42
    },
    {
      "epoch": 0.03057845729905109,
      "grad_norm": 1.286163330078125,
      "learning_rate": 6.415552058736854e-05,
      "loss": 8.8781,
      "step": 43
    },
    {
      "epoch": 0.03128958421298251,
      "grad_norm": 1.181894302368164,
      "learning_rate": 6.264596732629e-05,
      "loss": 8.9106,
      "step": 44
    },
    {
      "epoch": 0.03200071112691393,
      "grad_norm": 1.153061032295227,
      "learning_rate": 6.112749920933111e-05,
      "loss": 8.9586,
      "step": 45
    },
    {
      "epoch": 0.032711838040845355,
      "grad_norm": 1.2370038032531738,
      "learning_rate": 5.960188670239154e-05,
      "loss": 9.1853,
      "step": 46
    },
    {
      "epoch": 0.03342296495477677,
      "grad_norm": 1.2129719257354736,
      "learning_rate": 5.80709086014102e-05,
      "loss": 9.0873,
      "step": 47
    },
    {
      "epoch": 0.034134091868708194,
      "grad_norm": 1.4687657356262207,
      "learning_rate": 5.653634995836856e-05,
      "loss": 9.0932,
      "step": 48
    },
    {
      "epoch": 0.03484521878263962,
      "grad_norm": 1.6727079153060913,
      "learning_rate": 5.500000000000001e-05,
      "loss": 9.198,
      "step": 49
    },
    {
      "epoch": 0.03555634569657103,
      "grad_norm": 1.8865216970443726,
      "learning_rate": 5.346365004163145e-05,
      "loss": 9.2588,
      "step": 50
    },
    {
      "epoch": 0.03555634569657103,
      "eval_loss": 8.629364013671875,
      "eval_runtime": 0.4759,
      "eval_samples_per_second": 105.064,
      "eval_steps_per_second": 27.317,
      "step": 50
    },
    {
      "epoch": 0.036267472610502456,
      "grad_norm": 1.2948602437973022,
      "learning_rate": 5.192909139858981e-05,
      "loss": 8.3854,
      "step": 51
    },
    {
      "epoch": 0.03697859952443388,
      "grad_norm": 1.202957272529602,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 8.4592,
      "step": 52
    },
    {
      "epoch": 0.037689726438365295,
      "grad_norm": 1.0991284847259521,
      "learning_rate": 4.887250079066892e-05,
      "loss": 8.3654,
      "step": 53
    },
    {
      "epoch": 0.03840085335229672,
      "grad_norm": 1.049133539199829,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 8.5559,
      "step": 54
    },
    {
      "epoch": 0.03911198026622814,
      "grad_norm": 1.0683585405349731,
      "learning_rate": 4.584447941263149e-05,
      "loss": 8.8506,
      "step": 55
    },
    {
      "epoch": 0.03982310718015956,
      "grad_norm": 1.2173759937286377,
      "learning_rate": 4.43456010790099e-05,
      "loss": 8.7193,
      "step": 56
    },
    {
      "epoch": 0.04053423409409098,
      "grad_norm": 1.0298593044281006,
      "learning_rate": 4.285914529793391e-05,
      "loss": 8.8945,
      "step": 57
    },
    {
      "epoch": 0.0412453610080224,
      "grad_norm": 1.0951929092407227,
      "learning_rate": 4.13868452103516e-05,
      "loss": 9.0274,
      "step": 58
    },
    {
      "epoch": 0.04195648792195382,
      "grad_norm": 0.9960741996765137,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 8.904,
      "step": 59
    },
    {
      "epoch": 0.04266761483588524,
      "grad_norm": 1.194457769393921,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 8.9637,
      "step": 60
    },
    {
      "epoch": 0.043378741749816666,
      "grad_norm": 1.4879592657089233,
      "learning_rate": 3.707195095691913e-05,
      "loss": 9.1381,
      "step": 61
    },
    {
      "epoch": 0.04408986866374808,
      "grad_norm": 1.7354305982589722,
      "learning_rate": 3.567324506364632e-05,
      "loss": 8.9569,
      "step": 62
    },
    {
      "epoch": 0.044800995577679505,
      "grad_norm": 1.2308183908462524,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 8.0746,
      "step": 63
    },
    {
      "epoch": 0.04551212249161093,
      "grad_norm": 1.1788955926895142,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 8.4578,
      "step": 64
    },
    {
      "epoch": 0.046223249405542344,
      "grad_norm": 1.1902447938919067,
      "learning_rate": 3.16187222484055e-05,
      "loss": 8.1835,
      "step": 65
    },
    {
      "epoch": 0.04693437631947377,
      "grad_norm": 1.241468906402588,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 8.0961,
      "step": 66
    },
    {
      "epoch": 0.04764550323340519,
      "grad_norm": 1.0362024307250977,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 8.6565,
      "step": 67
    },
    {
      "epoch": 0.048356630147336606,
      "grad_norm": 0.9590556621551514,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 8.8393,
      "step": 68
    },
    {
      "epoch": 0.04906775706126803,
      "grad_norm": 0.9237630367279053,
      "learning_rate": 2.660104250532764e-05,
      "loss": 8.8098,
      "step": 69
    },
    {
      "epoch": 0.04977888397519945,
      "grad_norm": 0.9075753092765808,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 8.8575,
      "step": 70
    },
    {
      "epoch": 0.05049001088913087,
      "grad_norm": 1.0483438968658447,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 8.9505,
      "step": 71
    },
    {
      "epoch": 0.05120113780306229,
      "grad_norm": 1.1041228771209717,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 8.9506,
      "step": 72
    },
    {
      "epoch": 0.051912264716993714,
      "grad_norm": 1.2572849988937378,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 8.8908,
      "step": 73
    },
    {
      "epoch": 0.05262339163092513,
      "grad_norm": 1.5153453350067139,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 9.1148,
      "step": 74
    },
    {
      "epoch": 0.05333451854485655,
      "grad_norm": 2.149052619934082,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 9.13,
      "step": 75
    },
    {
      "epoch": 0.05333451854485655,
      "eval_loss": 8.485151290893555,
      "eval_runtime": 0.4834,
      "eval_samples_per_second": 103.437,
      "eval_steps_per_second": 26.894,
      "step": 75
    },
    {
      "epoch": 0.054045645458787976,
      "grad_norm": 1.2563050985336304,
      "learning_rate": 1.91437699862843e-05,
      "loss": 8.1814,
      "step": 76
    },
    {
      "epoch": 0.05475677237271939,
      "grad_norm": 1.031311273574829,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 8.4385,
      "step": 77
    },
    {
      "epoch": 0.055467899286650815,
      "grad_norm": 1.0750837326049805,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 8.5048,
      "step": 78
    },
    {
      "epoch": 0.05617902620058224,
      "grad_norm": 1.2149912118911743,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 8.2128,
      "step": 79
    },
    {
      "epoch": 0.056890153114513654,
      "grad_norm": 0.8455520272254944,
      "learning_rate": 1.577527884852619e-05,
      "loss": 8.585,
      "step": 80
    },
    {
      "epoch": 0.05760128002844508,
      "grad_norm": 0.9065818190574646,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 8.8332,
      "step": 81
    },
    {
      "epoch": 0.0583124069423765,
      "grad_norm": 0.9263755083084106,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 8.7434,
      "step": 82
    },
    {
      "epoch": 0.059023533856307916,
      "grad_norm": 0.953991174697876,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 8.4833,
      "step": 83
    },
    {
      "epoch": 0.05973466077023934,
      "grad_norm": 0.9421951174736023,
      "learning_rate": 1.313747004979751e-05,
      "loss": 8.9237,
      "step": 84
    },
    {
      "epoch": 0.06044578768417076,
      "grad_norm": 0.9801391959190369,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 8.7981,
      "step": 85
    },
    {
      "epoch": 0.06115691459810218,
      "grad_norm": 1.2952722311019897,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 8.8525,
      "step": 86
    },
    {
      "epoch": 0.0618680415120336,
      "grad_norm": 1.563397765159607,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 8.9335,
      "step": 87
    },
    {
      "epoch": 0.06257916842596502,
      "grad_norm": 1.1210330724716187,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 8.1383,
      "step": 88
    },
    {
      "epoch": 0.06329029533989644,
      "grad_norm": 1.132744312286377,
      "learning_rate": 1.094121605429547e-05,
      "loss": 8.304,
      "step": 89
    },
    {
      "epoch": 0.06400142225382786,
      "grad_norm": 1.082865595817566,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 8.348,
      "step": 90
    },
    {
      "epoch": 0.06471254916775929,
      "grad_norm": 0.9174438118934631,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 8.3503,
      "step": 91
    },
    {
      "epoch": 0.06542367608169071,
      "grad_norm": 0.9113219380378723,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 8.5919,
      "step": 92
    },
    {
      "epoch": 0.06613480299562212,
      "grad_norm": 0.8231514096260071,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 8.509,
      "step": 93
    },
    {
      "epoch": 0.06684592990955354,
      "grad_norm": 0.9372797012329102,
      "learning_rate": 1.002623399352217e-05,
      "loss": 8.7682,
      "step": 94
    },
    {
      "epoch": 0.06755705682348496,
      "grad_norm": 0.9878532290458679,
      "learning_rate": 1e-05,
      "loss": 8.678,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 440826215792640.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}