{
  "best_metric": 0.8693193197250366,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.05466721333880006,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005466721333880005,
      "grad_norm": 0.4661848545074463,
      "learning_rate": 2.333333333333333e-06,
      "loss": 0.7648,
      "step": 1
    },
    {
      "epoch": 0.0005466721333880005,
      "eval_loss": 1.3695563077926636,
      "eval_runtime": 94.695,
      "eval_samples_per_second": 32.536,
      "eval_steps_per_second": 8.142,
      "step": 1
    },
    {
      "epoch": 0.001093344266776001,
      "grad_norm": 0.411937952041626,
      "learning_rate": 4.666666666666666e-06,
      "loss": 0.7517,
      "step": 2
    },
    {
      "epoch": 0.0016400164001640015,
      "grad_norm": 0.539547324180603,
      "learning_rate": 7e-06,
      "loss": 0.9216,
      "step": 3
    },
    {
      "epoch": 0.002186688533552002,
      "grad_norm": 0.5318194627761841,
      "learning_rate": 9.333333333333333e-06,
      "loss": 0.8582,
      "step": 4
    },
    {
      "epoch": 0.0027333606669400026,
      "grad_norm": 0.5687560439109802,
      "learning_rate": 1.1666666666666665e-05,
      "loss": 0.9711,
      "step": 5
    },
    {
      "epoch": 0.003280032800328003,
      "grad_norm": 0.7335965633392334,
      "learning_rate": 1.4e-05,
      "loss": 0.9818,
      "step": 6
    },
    {
      "epoch": 0.003826704933716004,
      "grad_norm": 0.4608137309551239,
      "learning_rate": 1.633333333333333e-05,
      "loss": 0.8496,
      "step": 7
    },
    {
      "epoch": 0.004373377067104004,
      "grad_norm": 0.5464603900909424,
      "learning_rate": 1.8666666666666665e-05,
      "loss": 0.9922,
      "step": 8
    },
    {
      "epoch": 0.004920049200492005,
      "grad_norm": 0.557895839214325,
      "learning_rate": 2.1e-05,
      "loss": 1.0499,
      "step": 9
    },
    {
      "epoch": 0.005466721333880005,
      "grad_norm": 0.43142303824424744,
      "learning_rate": 2.333333333333333e-05,
      "loss": 0.9916,
      "step": 10
    },
    {
      "epoch": 0.006013393467268006,
      "grad_norm": 0.39260706305503845,
      "learning_rate": 2.5666666666666663e-05,
      "loss": 0.9236,
      "step": 11
    },
    {
      "epoch": 0.006560065600656006,
      "grad_norm": 0.40968865156173706,
      "learning_rate": 2.8e-05,
      "loss": 1.0978,
      "step": 12
    },
    {
      "epoch": 0.007106737734044007,
      "grad_norm": 0.4441259503364563,
      "learning_rate": 3.0333333333333333e-05,
      "loss": 1.0146,
      "step": 13
    },
    {
      "epoch": 0.007653409867432008,
      "grad_norm": 0.40066277980804443,
      "learning_rate": 3.266666666666666e-05,
      "loss": 0.916,
      "step": 14
    },
    {
      "epoch": 0.008200082000820008,
      "grad_norm": 0.4672339856624603,
      "learning_rate": 3.5e-05,
      "loss": 1.0468,
      "step": 15
    },
    {
      "epoch": 0.008746754134208008,
      "grad_norm": 0.48708584904670715,
      "learning_rate": 3.733333333333333e-05,
      "loss": 1.049,
      "step": 16
    },
    {
      "epoch": 0.00929342626759601,
      "grad_norm": 0.5237523913383484,
      "learning_rate": 3.9666666666666664e-05,
      "loss": 1.0419,
      "step": 17
    },
    {
      "epoch": 0.00984009840098401,
      "grad_norm": 0.5612183213233948,
      "learning_rate": 4.2e-05,
      "loss": 0.9977,
      "step": 18
    },
    {
      "epoch": 0.01038677053437201,
      "grad_norm": 0.5430253148078918,
      "learning_rate": 4.4333333333333324e-05,
      "loss": 1.146,
      "step": 19
    },
    {
      "epoch": 0.01093344266776001,
      "grad_norm": 0.5050835013389587,
      "learning_rate": 4.666666666666666e-05,
      "loss": 0.9679,
      "step": 20
    },
    {
      "epoch": 0.011480114801148012,
      "grad_norm": 0.4491889774799347,
      "learning_rate": 4.899999999999999e-05,
      "loss": 0.8918,
      "step": 21
    },
    {
      "epoch": 0.012026786934536012,
      "grad_norm": 0.46133682131767273,
      "learning_rate": 5.1333333333333325e-05,
      "loss": 0.891,
      "step": 22
    },
    {
      "epoch": 0.012573459067924012,
      "grad_norm": 0.5220205783843994,
      "learning_rate": 5.3666666666666666e-05,
      "loss": 0.9138,
      "step": 23
    },
    {
      "epoch": 0.013120131201312012,
      "grad_norm": 0.5471235513687134,
      "learning_rate": 5.6e-05,
      "loss": 1.0219,
      "step": 24
    },
    {
      "epoch": 0.013666803334700014,
      "grad_norm": 0.5401260852813721,
      "learning_rate": 5.833333333333333e-05,
      "loss": 0.9114,
      "step": 25
    },
    {
      "epoch": 0.014213475468088014,
      "grad_norm": 0.5504897236824036,
      "learning_rate": 6.0666666666666666e-05,
      "loss": 0.9869,
      "step": 26
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.6574556827545166,
      "learning_rate": 6.3e-05,
      "loss": 0.9166,
      "step": 27
    },
    {
      "epoch": 0.015306819734864016,
      "grad_norm": 0.6381729245185852,
      "learning_rate": 6.533333333333333e-05,
      "loss": 1.0102,
      "step": 28
    },
    {
      "epoch": 0.015853491868252016,
      "grad_norm": 0.6967756748199463,
      "learning_rate": 6.766666666666667e-05,
      "loss": 0.9655,
      "step": 29
    },
    {
      "epoch": 0.016400164001640016,
      "grad_norm": 0.7127764225006104,
      "learning_rate": 7e-05,
      "loss": 1.0242,
      "step": 30
    },
    {
      "epoch": 0.016946836135028016,
      "grad_norm": 0.6833203434944153,
      "learning_rate": 6.999402376603183e-05,
      "loss": 0.9315,
      "step": 31
    },
    {
      "epoch": 0.017493508268416016,
      "grad_norm": 0.8914316296577454,
      "learning_rate": 6.99760971050058e-05,
      "loss": 1.0732,
      "step": 32
    },
    {
      "epoch": 0.018040180401804017,
      "grad_norm": 1.0326182842254639,
      "learning_rate": 6.994622613886018e-05,
      "loss": 1.0459,
      "step": 33
    },
    {
      "epoch": 0.01858685253519202,
      "grad_norm": 0.8010824918746948,
      "learning_rate": 6.990442106850258e-05,
      "loss": 0.986,
      "step": 34
    },
    {
      "epoch": 0.01913352466858002,
      "grad_norm": 0.9589248895645142,
      "learning_rate": 6.98506961703262e-05,
      "loss": 0.9221,
      "step": 35
    },
    {
      "epoch": 0.01968019680196802,
      "grad_norm": 0.7887236475944519,
      "learning_rate": 6.978506979133457e-05,
      "loss": 1.0374,
      "step": 36
    },
    {
      "epoch": 0.02022686893535602,
      "grad_norm": 0.8019972443580627,
      "learning_rate": 6.9707564342876e-05,
      "loss": 0.8858,
      "step": 37
    },
    {
      "epoch": 0.02077354106874402,
      "grad_norm": 0.8885377049446106,
      "learning_rate": 6.96182062929901e-05,
      "loss": 1.0831,
      "step": 38
    },
    {
      "epoch": 0.02132021320213202,
      "grad_norm": 0.9791058301925659,
      "learning_rate": 6.951702615736908e-05,
      "loss": 1.0472,
      "step": 39
    },
    {
      "epoch": 0.02186688533552002,
      "grad_norm": 1.0434457063674927,
      "learning_rate": 6.940405848893656e-05,
      "loss": 0.9667,
      "step": 40
    },
    {
      "epoch": 0.022413557468908024,
      "grad_norm": 1.0951871871948242,
      "learning_rate": 6.92793418660478e-05,
      "loss": 1.1452,
      "step": 41
    },
    {
      "epoch": 0.022960229602296024,
      "grad_norm": 1.0019595623016357,
      "learning_rate": 6.914291887931528e-05,
      "loss": 0.8607,
      "step": 42
    },
    {
      "epoch": 0.023506901735684024,
      "grad_norm": 1.2730623483657837,
      "learning_rate": 6.899483611706398e-05,
      "loss": 1.0172,
      "step": 43
    },
    {
      "epoch": 0.024053573869072024,
      "grad_norm": 1.064156413078308,
      "learning_rate": 6.883514414942155e-05,
      "loss": 0.9434,
      "step": 44
    },
    {
      "epoch": 0.024600246002460024,
      "grad_norm": 1.1558951139450073,
      "learning_rate": 6.866389751104867e-05,
      "loss": 0.9083,
      "step": 45
    },
    {
      "epoch": 0.025146918135848025,
      "grad_norm": 1.3744535446166992,
      "learning_rate": 6.848115468251542e-05,
      "loss": 0.8842,
      "step": 46
    },
    {
      "epoch": 0.025693590269236025,
      "grad_norm": 1.5875253677368164,
      "learning_rate": 6.828697807033038e-05,
      "loss": 1.0323,
      "step": 47
    },
    {
      "epoch": 0.026240262402624025,
      "grad_norm": 1.4661047458648682,
      "learning_rate": 6.808143398562868e-05,
      "loss": 0.8986,
      "step": 48
    },
    {
      "epoch": 0.026786934536012028,
      "grad_norm": 1.6527341604232788,
      "learning_rate": 6.786459262152698e-05,
      "loss": 1.0423,
      "step": 49
    },
    {
      "epoch": 0.02733360666940003,
      "grad_norm": 4.2761406898498535,
      "learning_rate": 6.763652802915244e-05,
      "loss": 1.1307,
      "step": 50
    },
    {
      "epoch": 0.02733360666940003,
      "eval_loss": 0.9474524855613708,
      "eval_runtime": 94.8645,
      "eval_samples_per_second": 32.478,
      "eval_steps_per_second": 8.127,
      "step": 50
    },
    {
      "epoch": 0.02788027880278803,
      "grad_norm": 0.9167900681495667,
      "learning_rate": 6.739731809235446e-05,
      "loss": 0.7292,
      "step": 51
    },
    {
      "epoch": 0.02842695093617603,
      "grad_norm": 1.0346499681472778,
      "learning_rate": 6.71470445011073e-05,
      "loss": 0.7878,
      "step": 52
    },
    {
      "epoch": 0.02897362306956403,
      "grad_norm": 0.9062778949737549,
      "learning_rate": 6.688579272361309e-05,
      "loss": 0.8643,
      "step": 53
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 0.6097351908683777,
      "learning_rate": 6.66136519771145e-05,
      "loss": 0.8222,
      "step": 54
    },
    {
      "epoch": 0.03006696733634003,
      "grad_norm": 0.5191702246665955,
      "learning_rate": 6.633071519742718e-05,
      "loss": 0.9669,
      "step": 55
    },
    {
      "epoch": 0.030613639469728032,
      "grad_norm": 0.37056273221969604,
      "learning_rate": 6.603707900720217e-05,
      "loss": 0.8109,
      "step": 56
    },
    {
      "epoch": 0.031160311603116032,
      "grad_norm": 0.3645178973674774,
      "learning_rate": 6.573284368292943e-05,
      "loss": 0.921,
      "step": 57
    },
    {
      "epoch": 0.03170698373650403,
      "grad_norm": 0.35407713055610657,
      "learning_rate": 6.541811312069348e-05,
      "loss": 0.8393,
      "step": 58
    },
    {
      "epoch": 0.03225365586989203,
      "grad_norm": 0.30585721135139465,
      "learning_rate": 6.509299480069303e-05,
      "loss": 0.8196,
      "step": 59
    },
    {
      "epoch": 0.03280032800328003,
      "grad_norm": 0.31569743156433105,
      "learning_rate": 6.47575997505365e-05,
      "loss": 0.9089,
      "step": 60
    },
    {
      "epoch": 0.03334700013666803,
      "grad_norm": 0.31442388892173767,
      "learning_rate": 6.441204250732624e-05,
      "loss": 0.7743,
      "step": 61
    },
    {
      "epoch": 0.03389367227005603,
      "grad_norm": 0.3461879789829254,
      "learning_rate": 6.405644107854427e-05,
      "loss": 0.8485,
      "step": 62
    },
    {
      "epoch": 0.03444034440344403,
      "grad_norm": 0.346314400434494,
      "learning_rate": 6.369091690175273e-05,
      "loss": 0.7661,
      "step": 63
    },
    {
      "epoch": 0.03498701653683203,
      "grad_norm": 0.3185812532901764,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.8583,
      "step": 64
    },
    {
      "epoch": 0.03553368867022003,
      "grad_norm": 0.3503943979740143,
      "learning_rate": 6.293060295480838e-05,
      "loss": 0.8725,
      "step": 65
    },
    {
      "epoch": 0.03608036080360803,
      "grad_norm": 0.3459616005420685,
      "learning_rate": 6.25360728311719e-05,
      "loss": 0.8382,
      "step": 66
    },
    {
      "epoch": 0.03662703293699603,
      "grad_norm": 0.38812822103500366,
      "learning_rate": 6.213213916388954e-05,
      "loss": 0.9174,
      "step": 67
    },
    {
      "epoch": 0.03717370507038404,
      "grad_norm": 0.37094104290008545,
      "learning_rate": 6.171893989593859e-05,
      "loss": 0.881,
      "step": 68
    },
    {
      "epoch": 0.03772037720377204,
      "grad_norm": 0.5786832571029663,
      "learning_rate": 6.129661613449057e-05,
      "loss": 0.9016,
      "step": 69
    },
    {
      "epoch": 0.03826704933716004,
      "grad_norm": 0.6645287871360779,
      "learning_rate": 6.086531210272306e-05,
      "loss": 0.965,
      "step": 70
    },
    {
      "epoch": 0.03881372147054804,
      "grad_norm": 0.43764594197273254,
      "learning_rate": 6.042517509056784e-05,
      "loss": 0.9049,
      "step": 71
    },
    {
      "epoch": 0.03936039360393604,
      "grad_norm": 0.34731465578079224,
      "learning_rate": 5.997635540441133e-05,
      "loss": 0.8948,
      "step": 72
    },
    {
      "epoch": 0.03990706573732404,
      "grad_norm": 0.40091952681541443,
      "learning_rate": 5.9519006315765176e-05,
      "loss": 0.8426,
      "step": 73
    },
    {
      "epoch": 0.04045373787071204,
      "grad_norm": 0.3977827727794647,
      "learning_rate": 5.9053284008924185e-05,
      "loss": 0.8352,
      "step": 74
    },
    {
      "epoch": 0.04100041000410004,
      "grad_norm": 0.4238167107105255,
      "learning_rate": 5.85793475276295e-05,
      "loss": 0.8615,
      "step": 75
    },
    {
      "epoch": 0.04154708213748804,
      "grad_norm": 0.46092405915260315,
      "learning_rate": 5.809735872075529e-05,
      "loss": 0.8255,
      "step": 76
    },
    {
      "epoch": 0.04209375427087604,
      "grad_norm": 0.4420395791530609,
      "learning_rate": 5.760748218703755e-05,
      "loss": 0.7647,
      "step": 77
    },
    {
      "epoch": 0.04264042640426404,
      "grad_norm": 0.4960534870624542,
      "learning_rate": 5.710988521886378e-05,
      "loss": 0.909,
      "step": 78
    },
    {
      "epoch": 0.04318709853765204,
      "grad_norm": 0.49868643283843994,
      "learning_rate": 5.660473774514275e-05,
      "loss": 0.7568,
      "step": 79
    },
    {
      "epoch": 0.04373377067104004,
      "grad_norm": 0.5315876603126526,
      "learning_rate": 5.6092212273273975e-05,
      "loss": 0.8924,
      "step": 80
    },
    {
      "epoch": 0.04428044280442804,
      "grad_norm": 0.5740758776664734,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.8379,
      "step": 81
    },
    {
      "epoch": 0.04482711493781605,
      "grad_norm": 0.613091766834259,
      "learning_rate": 5.5045729902817676e-05,
      "loss": 0.9659,
      "step": 82
    },
    {
      "epoch": 0.04537378707120405,
      "grad_norm": 0.6900278329849243,
      "learning_rate": 5.4512130377000987e-05,
      "loss": 0.9506,
      "step": 83
    },
    {
      "epoch": 0.04592045920459205,
      "grad_norm": 0.6675617694854736,
      "learning_rate": 5.397186747653573e-05,
      "loss": 0.9986,
      "step": 84
    },
    {
      "epoch": 0.04646713133798005,
      "grad_norm": 0.6233535408973694,
      "learning_rate": 5.342512570070745e-05,
      "loss": 0.9033,
      "step": 85
    },
    {
      "epoch": 0.04701380347136805,
      "grad_norm": 0.659621000289917,
      "learning_rate": 5.287209176133174e-05,
      "loss": 0.9068,
      "step": 86
    },
    {
      "epoch": 0.04756047560475605,
      "grad_norm": 0.759048342704773,
      "learning_rate": 5.231295451899226e-05,
      "loss": 0.9384,
      "step": 87
    },
    {
      "epoch": 0.04810714773814405,
      "grad_norm": 0.8321371078491211,
      "learning_rate": 5.174790491854502e-05,
      "loss": 1.0077,
      "step": 88
    },
    {
      "epoch": 0.04865381987153205,
      "grad_norm": 0.7181084156036377,
      "learning_rate": 5.117713592391096e-05,
      "loss": 1.0386,
      "step": 89
    },
    {
      "epoch": 0.04920049200492005,
      "grad_norm": 0.8390389084815979,
      "learning_rate": 5.060084245217884e-05,
      "loss": 1.0526,
      "step": 90
    },
    {
      "epoch": 0.04974716413830805,
      "grad_norm": 0.7568452954292297,
      "learning_rate": 5.0019221307041306e-05,
      "loss": 0.9571,
      "step": 91
    },
    {
      "epoch": 0.05029383627169605,
      "grad_norm": 1.033366322517395,
      "learning_rate": 4.943247111158662e-05,
      "loss": 0.9084,
      "step": 92
    },
    {
      "epoch": 0.05084050840508405,
      "grad_norm": 0.9008201360702515,
      "learning_rate": 4.884079224046898e-05,
      "loss": 0.8388,
      "step": 93
    },
    {
      "epoch": 0.05138718053847205,
      "grad_norm": 0.8567910194396973,
      "learning_rate": 4.824438675148086e-05,
      "loss": 0.9807,
      "step": 94
    },
    {
      "epoch": 0.05193385267186005,
      "grad_norm": 1.0424281358718872,
      "learning_rate": 4.764345831655036e-05,
      "loss": 1.0143,
      "step": 95
    },
    {
      "epoch": 0.05248052480524805,
      "grad_norm": 1.1355541944503784,
      "learning_rate": 4.703821215218748e-05,
      "loss": 0.9176,
      "step": 96
    },
    {
      "epoch": 0.053027196938636056,
      "grad_norm": 1.2170919179916382,
      "learning_rate": 4.642885494940291e-05,
      "loss": 0.8303,
      "step": 97
    },
    {
      "epoch": 0.053573869072024057,
      "grad_norm": 1.626427173614502,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.8297,
      "step": 98
    },
    {
      "epoch": 0.05412054120541206,
      "grad_norm": 1.3740547895431519,
      "learning_rate": 4.519864114112636e-05,
      "loss": 0.7661,
      "step": 99
    },
    {
      "epoch": 0.05466721333880006,
      "grad_norm": 2.6349620819091797,
      "learning_rate": 4.45782046525229e-05,
      "loss": 1.0357,
      "step": 100
    },
    {
      "epoch": 0.05466721333880006,
      "eval_loss": 0.8693193197250366,
      "eval_runtime": 94.6807,
      "eval_samples_per_second": 32.541,
      "eval_steps_per_second": 8.143,
      "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": 4,
        "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": 2.896121962482893e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}