{
  "best_metric": 1.047793984413147,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 1.4975514201762978,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015670910871694418,
      "grad_norm": 0.29767322540283203,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.9246,
      "step": 1
    },
    {
      "epoch": 0.015670910871694418,
      "eval_loss": 1.304062843322754,
      "eval_runtime": 3.9908,
      "eval_samples_per_second": 12.529,
      "eval_steps_per_second": 3.257,
      "step": 1
    },
    {
      "epoch": 0.031341821743388835,
      "grad_norm": 0.40373367071151733,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1013,
      "step": 2
    },
    {
      "epoch": 0.04701273261508325,
      "grad_norm": 0.4160795509815216,
      "learning_rate": 0.0001,
      "loss": 1.1442,
      "step": 3
    },
    {
      "epoch": 0.06268364348677767,
      "grad_norm": 0.4283720552921295,
      "learning_rate": 9.997376600647783e-05,
      "loss": 1.224,
      "step": 4
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.3914691209793091,
      "learning_rate": 9.989509461357426e-05,
      "loss": 1.2021,
      "step": 5
    },
    {
      "epoch": 0.0940254652301665,
      "grad_norm": 0.4357539117336273,
      "learning_rate": 9.976407754861426e-05,
      "loss": 1.1337,
      "step": 6
    },
    {
      "epoch": 0.10969637610186092,
      "grad_norm": 1.1058809757232666,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.1854,
      "step": 7
    },
    {
      "epoch": 0.12536728697355534,
      "grad_norm": 0.46191996335983276,
      "learning_rate": 9.934567829727386e-05,
      "loss": 1.2568,
      "step": 8
    },
    {
      "epoch": 0.14103819784524976,
      "grad_norm": 0.5207685828208923,
      "learning_rate": 9.905878394570453e-05,
      "loss": 1.2159,
      "step": 9
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.3888891637325287,
      "learning_rate": 9.872051902290737e-05,
      "loss": 1.2202,
      "step": 10
    },
    {
      "epoch": 0.17238001958863858,
      "grad_norm": 0.4745905101299286,
      "learning_rate": 9.833127793065098e-05,
      "loss": 1.2759,
      "step": 11
    },
    {
      "epoch": 0.188050930460333,
      "grad_norm": 0.5267218351364136,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.2916,
      "step": 12
    },
    {
      "epoch": 0.20372184133202742,
      "grad_norm": 0.8792022466659546,
      "learning_rate": 9.740174149534693e-05,
      "loss": 0.8306,
      "step": 13
    },
    {
      "epoch": 0.21939275220372184,
      "grad_norm": 0.26823920011520386,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.9342,
      "step": 14
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.2649416923522949,
      "learning_rate": 9.627450856774539e-05,
      "loss": 1.0404,
      "step": 15
    },
    {
      "epoch": 0.2507345739471107,
      "grad_norm": 0.23979641497135162,
      "learning_rate": 9.563836295460398e-05,
      "loss": 1.0284,
      "step": 16
    },
    {
      "epoch": 0.2664054848188051,
      "grad_norm": 0.26043349504470825,
      "learning_rate": 9.495483482810688e-05,
      "loss": 1.1433,
      "step": 17
    },
    {
      "epoch": 0.2820763956904995,
      "grad_norm": 0.31806784868240356,
      "learning_rate": 9.422472115147382e-05,
      "loss": 1.1376,
      "step": 18
    },
    {
      "epoch": 0.29774730656219395,
      "grad_norm": 0.39123252034187317,
      "learning_rate": 9.3448873204592e-05,
      "loss": 1.1006,
      "step": 19
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.3064460754394531,
      "learning_rate": 9.2628195591462e-05,
      "loss": 1.136,
      "step": 20
    },
    {
      "epoch": 0.32908912830558273,
      "grad_norm": 0.34411901235580444,
      "learning_rate": 9.176364518546989e-05,
      "loss": 1.2004,
      "step": 21
    },
    {
      "epoch": 0.34476003917727716,
      "grad_norm": 0.3156793415546417,
      "learning_rate": 9.08562300137157e-05,
      "loss": 1.1716,
      "step": 22
    },
    {
      "epoch": 0.3604309500489716,
      "grad_norm": 0.3718337416648865,
      "learning_rate": 8.990700808169889e-05,
      "loss": 1.1469,
      "step": 23
    },
    {
      "epoch": 0.376101860920666,
      "grad_norm": 0.390572726726532,
      "learning_rate": 8.891708613973126e-05,
      "loss": 1.1902,
      "step": 24
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.47578996419906616,
      "learning_rate": 8.788761839251559e-05,
      "loss": 1.2673,
      "step": 25
    },
    {
      "epoch": 0.3917727717923604,
      "eval_loss": 1.0815237760543823,
      "eval_runtime": 4.047,
      "eval_samples_per_second": 12.355,
      "eval_steps_per_second": 3.212,
      "step": 25
    },
    {
      "epoch": 0.40744368266405484,
      "grad_norm": 0.21479928493499756,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.9019,
      "step": 26
    },
    {
      "epoch": 0.42311459353574926,
      "grad_norm": 0.49321261048316956,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.9811,
      "step": 27
    },
    {
      "epoch": 0.4387855044074437,
      "grad_norm": 0.2518619894981384,
      "learning_rate": 8.457416554680877e-05,
      "loss": 1.0605,
      "step": 28
    },
    {
      "epoch": 0.4544564152791381,
      "grad_norm": 0.3146817088127136,
      "learning_rate": 8.339895749467238e-05,
      "loss": 1.0428,
      "step": 29
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.2659796476364136,
      "learning_rate": 8.219063752844926e-05,
      "loss": 1.0745,
      "step": 30
    },
    {
      "epoch": 0.48579823702252695,
      "grad_norm": 0.33549588918685913,
      "learning_rate": 8.095061449516903e-05,
      "loss": 1.0516,
      "step": 31
    },
    {
      "epoch": 0.5014691478942214,
      "grad_norm": 0.4037955403327942,
      "learning_rate": 7.968033420621935e-05,
      "loss": 1.1396,
      "step": 32
    },
    {
      "epoch": 0.5171400587659157,
      "grad_norm": 0.37785473465919495,
      "learning_rate": 7.838127775159452e-05,
      "loss": 1.1947,
      "step": 33
    },
    {
      "epoch": 0.5328109696376102,
      "grad_norm": 0.3148077130317688,
      "learning_rate": 7.705495977301078e-05,
      "loss": 1.255,
      "step": 34
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.3045358657836914,
      "learning_rate": 7.570292669790186e-05,
      "loss": 1.1391,
      "step": 35
    },
    {
      "epoch": 0.564152791380999,
      "grad_norm": 0.39100587368011475,
      "learning_rate": 7.43267549363537e-05,
      "loss": 1.2991,
      "step": 36
    },
    {
      "epoch": 0.5798237022526934,
      "grad_norm": 0.4057651460170746,
      "learning_rate": 7.292804904308087e-05,
      "loss": 1.1892,
      "step": 37
    },
    {
      "epoch": 0.5954946131243879,
      "grad_norm": 0.14880803227424622,
      "learning_rate": 7.150843984658754e-05,
      "loss": 0.8033,
      "step": 38
    },
    {
      "epoch": 0.6111655239960823,
      "grad_norm": 0.2568841874599457,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.9227,
      "step": 39
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 0.2077617049217224,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.9912,
      "step": 40
    },
    {
      "epoch": 0.6425073457394711,
      "grad_norm": 0.19598203897476196,
      "learning_rate": 6.714085470206609e-05,
      "loss": 1.0314,
      "step": 41
    },
    {
      "epoch": 0.6581782566111655,
      "grad_norm": 0.41721493005752563,
      "learning_rate": 6.56543989209901e-05,
      "loss": 1.0608,
      "step": 42
    },
    {
      "epoch": 0.67384916748286,
      "grad_norm": 0.2374984472990036,
      "learning_rate": 6.415552058736854e-05,
      "loss": 1.1116,
      "step": 43
    },
    {
      "epoch": 0.6895200783545543,
      "grad_norm": 0.35157710313796997,
      "learning_rate": 6.264596732629e-05,
      "loss": 1.1291,
      "step": 44
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.2867555022239685,
      "learning_rate": 6.112749920933111e-05,
      "loss": 1.1885,
      "step": 45
    },
    {
      "epoch": 0.7208619000979432,
      "grad_norm": 0.32455042004585266,
      "learning_rate": 5.960188670239154e-05,
      "loss": 1.1524,
      "step": 46
    },
    {
      "epoch": 0.7365328109696376,
      "grad_norm": 0.35270676016807556,
      "learning_rate": 5.80709086014102e-05,
      "loss": 1.1318,
      "step": 47
    },
    {
      "epoch": 0.752203721841332,
      "grad_norm": 0.31786665320396423,
      "learning_rate": 5.653634995836856e-05,
      "loss": 1.1251,
      "step": 48
    },
    {
      "epoch": 0.7678746327130265,
      "grad_norm": 0.36152154207229614,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.156,
      "step": 49
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.5608299970626831,
      "learning_rate": 5.346365004163145e-05,
      "loss": 1.2629,
      "step": 50
    },
    {
      "epoch": 0.7835455435847208,
      "eval_loss": 1.0549283027648926,
      "eval_runtime": 4.0607,
      "eval_samples_per_second": 12.313,
      "eval_steps_per_second": 3.201,
      "step": 50
    },
    {
      "epoch": 0.7992164544564153,
      "grad_norm": 0.1754002571105957,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.7828,
      "step": 51
    },
    {
      "epoch": 0.8148873653281097,
      "grad_norm": 0.20335985720157623,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.9504,
      "step": 52
    },
    {
      "epoch": 0.8305582761998042,
      "grad_norm": 0.21644321084022522,
      "learning_rate": 4.887250079066892e-05,
      "loss": 1.0545,
      "step": 53
    },
    {
      "epoch": 0.8462291870714985,
      "grad_norm": 0.34582144021987915,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 1.0353,
      "step": 54
    },
    {
      "epoch": 0.861900097943193,
      "grad_norm": 0.26850616931915283,
      "learning_rate": 4.584447941263149e-05,
      "loss": 1.1242,
      "step": 55
    },
    {
      "epoch": 0.8775710088148874,
      "grad_norm": 0.2919338643550873,
      "learning_rate": 4.43456010790099e-05,
      "loss": 1.0954,
      "step": 56
    },
    {
      "epoch": 0.8932419196865817,
      "grad_norm": 0.2782425880432129,
      "learning_rate": 4.285914529793391e-05,
      "loss": 1.1289,
      "step": 57
    },
    {
      "epoch": 0.9089128305582762,
      "grad_norm": 0.3175053894519806,
      "learning_rate": 4.13868452103516e-05,
      "loss": 1.0851,
      "step": 58
    },
    {
      "epoch": 0.9245837414299706,
      "grad_norm": 0.2930164039134979,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 1.1517,
      "step": 59
    },
    {
      "epoch": 0.940254652301665,
      "grad_norm": 0.3636202812194824,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 1.1053,
      "step": 60
    },
    {
      "epoch": 0.9559255631733594,
      "grad_norm": 0.3651005029678345,
      "learning_rate": 3.707195095691913e-05,
      "loss": 1.1965,
      "step": 61
    },
    {
      "epoch": 0.9715964740450539,
      "grad_norm": 0.41222521662712097,
      "learning_rate": 3.567324506364632e-05,
      "loss": 1.1197,
      "step": 62
    },
    {
      "epoch": 0.9872673849167483,
      "grad_norm": 0.21965429186820984,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.9987,
      "step": 63
    },
    {
      "epoch": 1.0117531831537707,
      "grad_norm": 0.555340588092804,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 1.7151,
      "step": 64
    },
    {
      "epoch": 1.0274240940254653,
      "grad_norm": 0.173969104886055,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.9017,
      "step": 65
    },
    {
      "epoch": 1.0430950048971597,
      "grad_norm": 0.1953618973493576,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.9592,
      "step": 66
    },
    {
      "epoch": 1.058765915768854,
      "grad_norm": 0.19902163743972778,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.9845,
      "step": 67
    },
    {
      "epoch": 1.0744368266405484,
      "grad_norm": 0.21973180770874023,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 1.0679,
      "step": 68
    },
    {
      "epoch": 1.090107737512243,
      "grad_norm": 0.24290187656879425,
      "learning_rate": 2.660104250532764e-05,
      "loss": 1.0286,
      "step": 69
    },
    {
      "epoch": 1.1057786483839374,
      "grad_norm": 0.23160521686077118,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.9822,
      "step": 70
    },
    {
      "epoch": 1.1214495592556317,
      "grad_norm": 0.2505468726158142,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 1.102,
      "step": 71
    },
    {
      "epoch": 1.137120470127326,
      "grad_norm": 0.32072898745536804,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.1261,
      "step": 72
    },
    {
      "epoch": 1.1527913809990205,
      "grad_norm": 0.3113213777542114,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 1.0748,
      "step": 73
    },
    {
      "epoch": 1.168462291870715,
      "grad_norm": 0.36183857917785645,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 1.1085,
      "step": 74
    },
    {
      "epoch": 1.1841332027424094,
      "grad_norm": 0.3712606728076935,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 1.1292,
      "step": 75
    },
    {
      "epoch": 1.1841332027424094,
      "eval_loss": 1.047793984413147,
      "eval_runtime": 4.0481,
      "eval_samples_per_second": 12.351,
      "eval_steps_per_second": 3.211,
      "step": 75
    },
    {
      "epoch": 1.1998041136141038,
      "grad_norm": 0.20321336388587952,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.6967,
      "step": 76
    },
    {
      "epoch": 1.2154750244857984,
      "grad_norm": 0.29565516114234924,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 1.0459,
      "step": 77
    },
    {
      "epoch": 1.2311459353574927,
      "grad_norm": 0.21626198291778564,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.8837,
      "step": 78
    },
    {
      "epoch": 1.246816846229187,
      "grad_norm": 0.21457991003990173,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.9977,
      "step": 79
    },
    {
      "epoch": 1.2624877571008815,
      "grad_norm": 0.23749592900276184,
      "learning_rate": 1.577527884852619e-05,
      "loss": 1.0405,
      "step": 80
    },
    {
      "epoch": 1.2781586679725758,
      "grad_norm": 0.2553286850452423,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 1.0177,
      "step": 81
    },
    {
      "epoch": 1.2938295788442704,
      "grad_norm": 0.25675755739212036,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 1.0387,
      "step": 82
    },
    {
      "epoch": 1.3095004897159648,
      "grad_norm": 0.3346741795539856,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 1.0614,
      "step": 83
    },
    {
      "epoch": 1.3251714005876591,
      "grad_norm": 0.29241129755973816,
      "learning_rate": 1.313747004979751e-05,
      "loss": 1.1101,
      "step": 84
    },
    {
      "epoch": 1.3408423114593535,
      "grad_norm": 0.30398261547088623,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 1.0412,
      "step": 85
    },
    {
      "epoch": 1.3565132223310479,
      "grad_norm": 0.35737118124961853,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 1.0841,
      "step": 86
    },
    {
      "epoch": 1.3721841332027425,
      "grad_norm": 0.3579014241695404,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 1.0572,
      "step": 87
    },
    {
      "epoch": 1.3878550440744368,
      "grad_norm": 0.45231765508651733,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 1.171,
      "step": 88
    },
    {
      "epoch": 1.4035259549461312,
      "grad_norm": 0.21733441948890686,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.8669,
      "step": 89
    },
    {
      "epoch": 1.4191968658178258,
      "grad_norm": 0.2003743052482605,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.8578,
      "step": 90
    },
    {
      "epoch": 1.4348677766895201,
      "grad_norm": 0.21388119459152222,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 1.0007,
      "step": 91
    },
    {
      "epoch": 1.4505386875612145,
      "grad_norm": 0.23207959532737732,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.9724,
      "step": 92
    },
    {
      "epoch": 1.4662095984329089,
      "grad_norm": 0.22219336032867432,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 1.0635,
      "step": 93
    },
    {
      "epoch": 1.4818805093046032,
      "grad_norm": 0.2789229452610016,
      "learning_rate": 1.002623399352217e-05,
      "loss": 1.0651,
      "step": 94
    },
    {
      "epoch": 1.4975514201762978,
      "grad_norm": 0.2932514548301697,
      "learning_rate": 1e-05,
      "loss": 1.0618,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.1368266762320609e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}