{
  "best_metric": 1.8860944509506226,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 3.0093457943925235,
  "eval_steps": 50,
  "global_step": 161,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 2.296740770339966,
      "learning_rate": 1e-05,
      "loss": 3.2482,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 3.4806039333343506,
      "eval_runtime": 2.8285,
      "eval_samples_per_second": 31.819,
      "eval_steps_per_second": 8.132,
      "step": 1
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 2.284867763519287,
      "learning_rate": 2e-05,
      "loss": 3.3361,
      "step": 2
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 2.7166192531585693,
      "learning_rate": 3e-05,
      "loss": 3.4911,
      "step": 3
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 1.7645537853240967,
      "learning_rate": 4e-05,
      "loss": 3.3154,
      "step": 4
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.3278175592422485,
      "learning_rate": 5e-05,
      "loss": 3.4047,
      "step": 5
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 2.5081405639648438,
      "learning_rate": 6e-05,
      "loss": 3.4888,
      "step": 6
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 2.534463882446289,
      "learning_rate": 7e-05,
      "loss": 3.3864,
      "step": 7
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 1.9155189990997314,
      "learning_rate": 8e-05,
      "loss": 3.3969,
      "step": 8
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 1.3549368381500244,
      "learning_rate": 9e-05,
      "loss": 3.2768,
      "step": 9
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 1.19645094871521,
      "learning_rate": 0.0001,
      "loss": 3.1702,
      "step": 10
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 1.1062113046646118,
      "learning_rate": 9.998917893031616e-05,
      "loss": 3.2351,
      "step": 11
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 1.2079566717147827,
      "learning_rate": 9.995672040508655e-05,
      "loss": 3.1467,
      "step": 12
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 1.1398067474365234,
      "learning_rate": 9.990263847374976e-05,
      "loss": 3.241,
      "step": 13
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.954265296459198,
      "learning_rate": 9.982695654527965e-05,
      "loss": 2.828,
      "step": 14
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.8539099097251892,
      "learning_rate": 9.972970737805311e-05,
      "loss": 2.8598,
      "step": 15
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.8245346546173096,
      "learning_rate": 9.961093306567075e-05,
      "loss": 2.9461,
      "step": 16
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 0.7474632859230042,
      "learning_rate": 9.947068501873701e-05,
      "loss": 2.9326,
      "step": 17
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 0.82054603099823,
      "learning_rate": 9.930902394260747e-05,
      "loss": 2.9542,
      "step": 18
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.8387004733085632,
      "learning_rate": 9.912601981111286e-05,
      "loss": 3.0623,
      "step": 19
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.7888436317443848,
      "learning_rate": 9.892175183627161e-05,
      "loss": 2.8506,
      "step": 20
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.7061635851860046,
      "learning_rate": 9.86963084340033e-05,
      "loss": 2.7815,
      "step": 21
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 0.8253240585327148,
      "learning_rate": 9.844978718585855e-05,
      "loss": 2.6168,
      "step": 22
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 0.8144713640213013,
      "learning_rate": 9.818229479678158e-05,
      "loss": 2.6312,
      "step": 23
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.9038909077644348,
      "learning_rate": 9.789394704892364e-05,
      "loss": 2.6686,
      "step": 24
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.8796248435974121,
      "learning_rate": 9.758486875152766e-05,
      "loss": 2.6703,
      "step": 25
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 1.1331161260604858,
      "learning_rate": 9.725519368690538e-05,
      "loss": 2.7249,
      "step": 26
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 0.8963878750801086,
      "learning_rate": 9.690506455253073e-05,
      "loss": 2.4582,
      "step": 27
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 0.7376312017440796,
      "learning_rate": 9.653463289927411e-05,
      "loss": 2.5318,
      "step": 28
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": 0.7899859547615051,
      "learning_rate": 9.614405906580485e-05,
      "loss": 2.6016,
      "step": 29
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.8779508471488953,
      "learning_rate": 9.573351210918974e-05,
      "loss": 2.6294,
      "step": 30
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": 0.708345890045166,
      "learning_rate": 9.53031697317178e-05,
      "loss": 2.6299,
      "step": 31
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 0.7444483637809753,
      "learning_rate": 9.485321820398321e-05,
      "loss": 2.6241,
      "step": 32
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 0.7320617437362671,
      "learning_rate": 9.438385228425938e-05,
      "loss": 2.4524,
      "step": 33
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 0.7435760498046875,
      "learning_rate": 9.389527513419934e-05,
      "loss": 2.4579,
      "step": 34
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.7211119532585144,
      "learning_rate": 9.338769823089853e-05,
      "loss": 2.3929,
      "step": 35
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 0.6858555674552917,
      "learning_rate": 9.286134127535859e-05,
      "loss": 2.2946,
      "step": 36
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": 0.7764372229576111,
      "learning_rate": 9.231643209739128e-05,
      "loss": 2.4114,
      "step": 37
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 0.8257884979248047,
      "learning_rate": 9.175320655700406e-05,
      "loss": 2.3745,
      "step": 38
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 1.0175106525421143,
      "learning_rate": 9.117190844230971e-05,
      "loss": 2.2885,
      "step": 39
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.7008936405181885,
      "learning_rate": 9.057278936400453e-05,
      "loss": 2.211,
      "step": 40
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": 0.8204365968704224,
      "learning_rate": 8.99561086464603e-05,
      "loss": 2.3415,
      "step": 41
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 0.7042631506919861,
      "learning_rate": 8.93221332154777e-05,
      "loss": 2.4065,
      "step": 42
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": 0.7198204398155212,
      "learning_rate": 8.86711374827494e-05,
      "loss": 2.464,
      "step": 43
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 0.7631362676620483,
      "learning_rate": 8.800340322708291e-05,
      "loss": 2.4188,
      "step": 44
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.8775385022163391,
      "learning_rate": 8.731921947243469e-05,
      "loss": 2.483,
      "step": 45
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 0.7206557989120483,
      "learning_rate": 8.661888236280813e-05,
      "loss": 2.3681,
      "step": 46
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": 0.8242782354354858,
      "learning_rate": 8.590269503406985e-05,
      "loss": 2.1287,
      "step": 47
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.7271357774734497,
      "learning_rate": 8.517096748273951e-05,
      "loss": 2.2487,
      "step": 48
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": 0.7304548621177673,
      "learning_rate": 8.442401643181e-05,
      "loss": 2.1553,
      "step": 49
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.9046958684921265,
      "learning_rate": 8.366216519365621e-05,
      "loss": 2.1993,
      "step": 50
    },
    {
      "epoch": 0.9345794392523364,
      "eval_loss": 2.160761833190918,
      "eval_runtime": 2.9196,
      "eval_samples_per_second": 30.826,
      "eval_steps_per_second": 7.878,
      "step": 50
    },
    {
      "epoch": 0.9532710280373832,
      "grad_norm": 0.8336485624313354,
      "learning_rate": 8.288574353009164e-05,
      "loss": 2.2049,
      "step": 51
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": 1.1437318325042725,
      "learning_rate": 8.209508750963328e-05,
      "loss": 2.3231,
      "step": 52
    },
    {
      "epoch": 0.9906542056074766,
      "grad_norm": 0.855793297290802,
      "learning_rate": 8.129053936203687e-05,
      "loss": 2.3364,
      "step": 53
    },
    {
      "epoch": 1.0093457943925233,
      "grad_norm": 1.6889846324920654,
      "learning_rate": 8.047244733016522e-05,
      "loss": 3.3313,
      "step": 54
    },
    {
      "epoch": 1.02803738317757,
      "grad_norm": 0.7058824300765991,
      "learning_rate": 7.964116551925365e-05,
      "loss": 2.054,
      "step": 55
    },
    {
      "epoch": 1.0467289719626167,
      "grad_norm": 0.7893012166023254,
      "learning_rate": 7.879705374363831e-05,
      "loss": 2.2002,
      "step": 56
    },
    {
      "epoch": 1.0654205607476634,
      "grad_norm": 0.7453466057777405,
      "learning_rate": 7.794047737101297e-05,
      "loss": 2.2385,
      "step": 57
    },
    {
      "epoch": 1.0841121495327102,
      "grad_norm": 0.7690429091453552,
      "learning_rate": 7.707180716428237e-05,
      "loss": 2.2034,
      "step": 58
    },
    {
      "epoch": 1.102803738317757,
      "grad_norm": 0.7656447887420654,
      "learning_rate": 7.619141912108008e-05,
      "loss": 2.2872,
      "step": 59
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 0.7192561030387878,
      "learning_rate": 7.529969431102064e-05,
      "loss": 2.2796,
      "step": 60
    },
    {
      "epoch": 1.1401869158878504,
      "grad_norm": 0.809199333190918,
      "learning_rate": 7.439701871075641e-05,
      "loss": 2.091,
      "step": 61
    },
    {
      "epoch": 1.158878504672897,
      "grad_norm": 0.8106621503829956,
      "learning_rate": 7.34837830369103e-05,
      "loss": 2.1432,
      "step": 62
    },
    {
      "epoch": 1.1775700934579438,
      "grad_norm": 0.7354812026023865,
      "learning_rate": 7.256038257695687e-05,
      "loss": 1.9456,
      "step": 63
    },
    {
      "epoch": 1.1962616822429906,
      "grad_norm": 0.8421512246131897,
      "learning_rate": 7.162721701812505e-05,
      "loss": 2.0369,
      "step": 64
    },
    {
      "epoch": 1.2149532710280373,
      "grad_norm": 0.854413628578186,
      "learning_rate": 7.068469027439642e-05,
      "loss": 2.0718,
      "step": 65
    },
    {
      "epoch": 1.233644859813084,
      "grad_norm": 1.0003541707992554,
      "learning_rate": 6.973321031167383e-05,
      "loss": 2.0248,
      "step": 66
    },
    {
      "epoch": 1.2523364485981308,
      "grad_norm": 0.8742265105247498,
      "learning_rate": 6.87731889711965e-05,
      "loss": 1.927,
      "step": 67
    },
    {
      "epoch": 1.2710280373831775,
      "grad_norm": 0.737220823764801,
      "learning_rate": 6.780504179127734e-05,
      "loss": 2.0441,
      "step": 68
    },
    {
      "epoch": 1.2897196261682242,
      "grad_norm": 0.8562338352203369,
      "learning_rate": 6.682918782744032e-05,
      "loss": 2.1308,
      "step": 69
    },
    {
      "epoch": 1.308411214953271,
      "grad_norm": 0.8714187145233154,
      "learning_rate": 6.584604947103514e-05,
      "loss": 2.2225,
      "step": 70
    },
    {
      "epoch": 1.3271028037383177,
      "grad_norm": 0.8110138177871704,
      "learning_rate": 6.485605226640837e-05,
      "loss": 2.2244,
      "step": 71
    },
    {
      "epoch": 1.3457943925233644,
      "grad_norm": 0.9689570069313049,
      "learning_rate": 6.385962472670953e-05,
      "loss": 2.2437,
      "step": 72
    },
    {
      "epoch": 1.3644859813084111,
      "grad_norm": 0.818893313407898,
      "learning_rate": 6.28571981484123e-05,
      "loss": 2.2427,
      "step": 73
    },
    {
      "epoch": 1.3831775700934579,
      "grad_norm": 0.8552919626235962,
      "learning_rate": 6.184920642463094e-05,
      "loss": 2.0945,
      "step": 74
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 0.8439993858337402,
      "learning_rate": 6.083608585731283e-05,
      "loss": 2.0605,
      "step": 75
    },
    {
      "epoch": 1.4205607476635513,
      "grad_norm": 0.767800509929657,
      "learning_rate": 5.981827496838822e-05,
      "loss": 2.0379,
      "step": 76
    },
    {
      "epoch": 1.439252336448598,
      "grad_norm": 0.8443582653999329,
      "learning_rate": 5.8796214309959276e-05,
      "loss": 2.04,
      "step": 77
    },
    {
      "epoch": 1.4579439252336448,
      "grad_norm": 0.9296259880065918,
      "learning_rate": 5.7770346273610254e-05,
      "loss": 1.9812,
      "step": 78
    },
    {
      "epoch": 1.4766355140186915,
      "grad_norm": 0.9575769305229187,
      "learning_rate": 5.674111489892144e-05,
      "loss": 1.9104,
      "step": 79
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 0.8796722888946533,
      "learning_rate": 5.570896568126993e-05,
      "loss": 1.7835,
      "step": 80
    },
    {
      "epoch": 1.514018691588785,
      "grad_norm": 0.7112849354743958,
      "learning_rate": 5.4674345379e-05,
      "loss": 1.9897,
      "step": 81
    },
    {
      "epoch": 1.5327102803738317,
      "grad_norm": 0.7640280723571777,
      "learning_rate": 5.36377018200472e-05,
      "loss": 1.9836,
      "step": 82
    },
    {
      "epoch": 1.5514018691588785,
      "grad_norm": 0.8502132296562195,
      "learning_rate": 5.2599483708099016e-05,
      "loss": 2.0886,
      "step": 83
    },
    {
      "epoch": 1.5700934579439252,
      "grad_norm": 0.7334374785423279,
      "learning_rate": 5.1560140428376956e-05,
      "loss": 2.1808,
      "step": 84
    },
    {
      "epoch": 1.588785046728972,
      "grad_norm": 0.7758664488792419,
      "learning_rate": 5.052012185312322e-05,
      "loss": 2.1578,
      "step": 85
    },
    {
      "epoch": 1.6074766355140186,
      "grad_norm": 0.8244055509567261,
      "learning_rate": 4.9479878146876794e-05,
      "loss": 2.1404,
      "step": 86
    },
    {
      "epoch": 1.6261682242990654,
      "grad_norm": 0.9261210560798645,
      "learning_rate": 4.8439859571623035e-05,
      "loss": 2.0294,
      "step": 87
    },
    {
      "epoch": 1.644859813084112,
      "grad_norm": 0.7333531379699707,
      "learning_rate": 4.740051629190099e-05,
      "loss": 1.9124,
      "step": 88
    },
    {
      "epoch": 1.6635514018691588,
      "grad_norm": 0.8007596731185913,
      "learning_rate": 4.636229817995281e-05,
      "loss": 1.9221,
      "step": 89
    },
    {
      "epoch": 1.6822429906542056,
      "grad_norm": 0.9177943468093872,
      "learning_rate": 4.532565462099999e-05,
      "loss": 1.97,
      "step": 90
    },
    {
      "epoch": 1.7009345794392523,
      "grad_norm": 0.8639528751373291,
      "learning_rate": 4.429103431873009e-05,
      "loss": 1.9488,
      "step": 91
    },
    {
      "epoch": 1.719626168224299,
      "grad_norm": 1.0700504779815674,
      "learning_rate": 4.325888510107856e-05,
      "loss": 1.8802,
      "step": 92
    },
    {
      "epoch": 1.7383177570093458,
      "grad_norm": 0.9686967134475708,
      "learning_rate": 4.2229653726389765e-05,
      "loss": 1.7992,
      "step": 93
    },
    {
      "epoch": 1.7570093457943925,
      "grad_norm": 0.8226217031478882,
      "learning_rate": 4.120378569004074e-05,
      "loss": 1.9656,
      "step": 94
    },
    {
      "epoch": 1.7757009345794392,
      "grad_norm": 0.7883921265602112,
      "learning_rate": 4.0181725031611795e-05,
      "loss": 1.9715,
      "step": 95
    },
    {
      "epoch": 1.794392523364486,
      "grad_norm": 0.7362433671951294,
      "learning_rate": 3.9163914142687184e-05,
      "loss": 2.0661,
      "step": 96
    },
    {
      "epoch": 1.8130841121495327,
      "grad_norm": 0.754984974861145,
      "learning_rate": 3.8150793575369066e-05,
      "loss": 2.16,
      "step": 97
    },
    {
      "epoch": 1.8317757009345794,
      "grad_norm": 0.8556288480758667,
      "learning_rate": 3.714280185158771e-05,
      "loss": 2.2234,
      "step": 98
    },
    {
      "epoch": 1.8504672897196262,
      "grad_norm": 0.8051014542579651,
      "learning_rate": 3.614037527329048e-05,
      "loss": 2.0493,
      "step": 99
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 0.8376341462135315,
      "learning_rate": 3.514394773359163e-05,
      "loss": 1.9779,
      "step": 100
    },
    {
      "epoch": 1.8691588785046729,
      "eval_loss": 1.9384918212890625,
      "eval_runtime": 2.7889,
      "eval_samples_per_second": 32.27,
      "eval_steps_per_second": 8.247,
      "step": 100
    },
    {
      "epoch": 1.8878504672897196,
      "grad_norm": 0.8476997017860413,
      "learning_rate": 3.415395052896487e-05,
      "loss": 1.8944,
      "step": 101
    },
    {
      "epoch": 1.9065420560747663,
      "grad_norm": 0.7590591311454773,
      "learning_rate": 3.31708121725597e-05,
      "loss": 1.9007,
      "step": 102
    },
    {
      "epoch": 1.925233644859813,
      "grad_norm": 0.8914473652839661,
      "learning_rate": 3.219495820872265e-05,
      "loss": 1.8704,
      "step": 103
    },
    {
      "epoch": 1.9439252336448598,
      "grad_norm": 0.9904480576515198,
      "learning_rate": 3.122681102880352e-05,
      "loss": 1.9588,
      "step": 104
    },
    {
      "epoch": 1.9626168224299065,
      "grad_norm": 1.0886353254318237,
      "learning_rate": 3.0266789688326186e-05,
      "loss": 2.0084,
      "step": 105
    },
    {
      "epoch": 1.9813084112149533,
      "grad_norm": 0.9867513179779053,
      "learning_rate": 2.9315309725603596e-05,
      "loss": 1.9471,
      "step": 106
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.565618634223938,
      "learning_rate": 2.8372782981874963e-05,
      "loss": 2.8595,
      "step": 107
    },
    {
      "epoch": 2.0186915887850465,
      "grad_norm": 0.750761866569519,
      "learning_rate": 2.7439617423043145e-05,
      "loss": 1.7939,
      "step": 108
    },
    {
      "epoch": 2.0373831775700935,
      "grad_norm": 0.7188526391983032,
      "learning_rate": 2.6516216963089698e-05,
      "loss": 1.948,
      "step": 109
    },
    {
      "epoch": 2.05607476635514,
      "grad_norm": 0.6620720028877258,
      "learning_rate": 2.5602981289243578e-05,
      "loss": 2.0243,
      "step": 110
    },
    {
      "epoch": 2.074766355140187,
      "grad_norm": 0.7385666966438293,
      "learning_rate": 2.470030568897938e-05,
      "loss": 2.0093,
      "step": 111
    },
    {
      "epoch": 2.0934579439252334,
      "grad_norm": 0.6927978992462158,
      "learning_rate": 2.3808580878919946e-05,
      "loss": 2.0141,
      "step": 112
    },
    {
      "epoch": 2.1121495327102804,
      "grad_norm": 0.8042175769805908,
      "learning_rate": 2.2928192835717644e-05,
      "loss": 2.1099,
      "step": 113
    },
    {
      "epoch": 2.130841121495327,
      "grad_norm": 0.8042687177658081,
      "learning_rate": 2.205952262898704e-05,
      "loss": 1.9512,
      "step": 114
    },
    {
      "epoch": 2.149532710280374,
      "grad_norm": 0.6975992918014526,
      "learning_rate": 2.120294625636171e-05,
      "loss": 1.9388,
      "step": 115
    },
    {
      "epoch": 2.1682242990654204,
      "grad_norm": 0.730394721031189,
      "learning_rate": 2.0358834480746365e-05,
      "loss": 1.8403,
      "step": 116
    },
    {
      "epoch": 2.1869158878504673,
      "grad_norm": 0.8232110738754272,
      "learning_rate": 1.9527552669834798e-05,
      "loss": 1.7969,
      "step": 117
    },
    {
      "epoch": 2.205607476635514,
      "grad_norm": 0.853557288646698,
      "learning_rate": 1.8709460637963123e-05,
      "loss": 1.8426,
      "step": 118
    },
    {
      "epoch": 2.2242990654205608,
      "grad_norm": 0.9900144338607788,
      "learning_rate": 1.790491249036672e-05,
      "loss": 1.8337,
      "step": 119
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 1.1342283487319946,
      "learning_rate": 1.711425646990838e-05,
      "loss": 1.8367,
      "step": 120
    },
    {
      "epoch": 2.2616822429906542,
      "grad_norm": 0.7156676650047302,
      "learning_rate": 1.6337834806343783e-05,
      "loss": 1.8456,
      "step": 121
    },
    {
      "epoch": 2.2803738317757007,
      "grad_norm": 0.779453694820404,
      "learning_rate": 1.557598356819e-05,
      "loss": 1.9779,
      "step": 122
    },
    {
      "epoch": 2.2990654205607477,
      "grad_norm": 0.8929774165153503,
      "learning_rate": 1.4829032517260489e-05,
      "loss": 1.9999,
      "step": 123
    },
    {
      "epoch": 2.317757009345794,
      "grad_norm": 0.8750218152999878,
      "learning_rate": 1.4097304965930158e-05,
      "loss": 2.0485,
      "step": 124
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 0.7915140986442566,
      "learning_rate": 1.3381117637191886e-05,
      "loss": 2.146,
      "step": 125
    },
    {
      "epoch": 2.3551401869158877,
      "grad_norm": 0.7732717990875244,
      "learning_rate": 1.268078052756531e-05,
      "loss": 2.1118,
      "step": 126
    },
    {
      "epoch": 2.3738317757009346,
      "grad_norm": 0.7107844948768616,
      "learning_rate": 1.199659677291709e-05,
      "loss": 1.8324,
      "step": 127
    },
    {
      "epoch": 2.392523364485981,
      "grad_norm": 0.6969010829925537,
      "learning_rate": 1.132886251725061e-05,
      "loss": 1.8862,
      "step": 128
    },
    {
      "epoch": 2.411214953271028,
      "grad_norm": 0.7186504602432251,
      "learning_rate": 1.0677866784522317e-05,
      "loss": 1.8288,
      "step": 129
    },
    {
      "epoch": 2.4299065420560746,
      "grad_norm": 0.7537363171577454,
      "learning_rate": 1.004389135353972e-05,
      "loss": 1.8198,
      "step": 130
    },
    {
      "epoch": 2.4485981308411215,
      "grad_norm": 0.9697016477584839,
      "learning_rate": 9.427210635995482e-06,
      "loss": 1.8064,
      "step": 131
    },
    {
      "epoch": 2.467289719626168,
      "grad_norm": 1.0445103645324707,
      "learning_rate": 8.828091557690289e-06,
      "loss": 1.7067,
      "step": 132
    },
    {
      "epoch": 2.485981308411215,
      "grad_norm": 1.219523310661316,
      "learning_rate": 8.246793442995954e-06,
      "loss": 1.7276,
      "step": 133
    },
    {
      "epoch": 2.5046728971962615,
      "grad_norm": 0.6436533331871033,
      "learning_rate": 7.683567902608729e-06,
      "loss": 1.8227,
      "step": 134
    },
    {
      "epoch": 2.5233644859813085,
      "grad_norm": 0.6645519733428955,
      "learning_rate": 7.138658724641417e-06,
      "loss": 1.8911,
      "step": 135
    },
    {
      "epoch": 2.542056074766355,
      "grad_norm": 0.7499832510948181,
      "learning_rate": 6.6123017691014645e-06,
      "loss": 2.0121,
      "step": 136
    },
    {
      "epoch": 2.560747663551402,
      "grad_norm": 0.8042947053909302,
      "learning_rate": 6.104724865800665e-06,
      "loss": 2.0352,
      "step": 137
    },
    {
      "epoch": 2.5794392523364484,
      "grad_norm": 0.8424281477928162,
      "learning_rate": 5.616147715740611e-06,
      "loss": 2.0103,
      "step": 138
    },
    {
      "epoch": 2.5981308411214954,
      "grad_norm": 0.8324230313301086,
      "learning_rate": 5.1467817960167975e-06,
      "loss": 2.0734,
      "step": 139
    },
    {
      "epoch": 2.616822429906542,
      "grad_norm": 0.7521181106567383,
      "learning_rate": 4.696830268282204e-06,
      "loss": 2.0144,
      "step": 140
    },
    {
      "epoch": 2.635514018691589,
      "grad_norm": 0.7921295762062073,
      "learning_rate": 4.266487890810256e-06,
      "loss": 1.8382,
      "step": 141
    },
    {
      "epoch": 2.6542056074766354,
      "grad_norm": 0.6855363845825195,
      "learning_rate": 3.855940934195146e-06,
      "loss": 1.8084,
      "step": 142
    },
    {
      "epoch": 2.6728971962616823,
      "grad_norm": 0.7162411212921143,
      "learning_rate": 3.465367100725908e-06,
      "loss": 1.7642,
      "step": 143
    },
    {
      "epoch": 2.691588785046729,
      "grad_norm": 0.7779765129089355,
      "learning_rate": 3.0949354474692937e-06,
      "loss": 1.8011,
      "step": 144
    },
    {
      "epoch": 2.710280373831776,
      "grad_norm": 0.8959972262382507,
      "learning_rate": 2.7448063130946224e-06,
      "loss": 1.7792,
      "step": 145
    },
    {
      "epoch": 2.7289719626168223,
      "grad_norm": 1.1299974918365479,
      "learning_rate": 2.4151312484723465e-06,
      "loss": 1.8124,
      "step": 146
    },
    {
      "epoch": 2.7476635514018692,
      "grad_norm": 0.6512258648872375,
      "learning_rate": 2.106052951076365e-06,
      "loss": 1.8297,
      "step": 147
    },
    {
      "epoch": 2.7663551401869158,
      "grad_norm": 0.6378995776176453,
      "learning_rate": 1.8177052032184283e-06,
      "loss": 1.8168,
      "step": 148
    },
    {
      "epoch": 2.7850467289719627,
      "grad_norm": 0.6217026114463806,
      "learning_rate": 1.5502128141414495e-06,
      "loss": 1.8971,
      "step": 149
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 0.6214033365249634,
      "learning_rate": 1.303691565996712e-06,
      "loss": 1.9555,
      "step": 150
    },
    {
      "epoch": 2.803738317757009,
      "eval_loss": 1.8860944509506226,
      "eval_runtime": 2.8551,
      "eval_samples_per_second": 31.522,
      "eval_steps_per_second": 8.056,
      "step": 150
    },
    {
      "epoch": 2.822429906542056,
      "grad_norm": 0.6506467461585999,
      "learning_rate": 1.0782481637284013e-06,
      "loss": 2.092,
      "step": 151
    },
    {
      "epoch": 2.8411214953271027,
      "grad_norm": 0.6492933034896851,
      "learning_rate": 8.739801888871469e-07,
      "loss": 2.0848,
      "step": 152
    },
    {
      "epoch": 2.8598130841121496,
      "grad_norm": 0.6631085276603699,
      "learning_rate": 6.909760573925561e-07,
      "loss": 1.9667,
      "step": 153
    },
    {
      "epoch": 2.878504672897196,
      "grad_norm": 0.649787962436676,
      "learning_rate": 5.29314981262985e-07,
      "loss": 1.8179,
      "step": 154
    },
    {
      "epoch": 2.897196261682243,
      "grad_norm": 0.6452500820159912,
      "learning_rate": 3.8906693432924634e-07,
      "loss": 1.8398,
      "step": 155
    },
    {
      "epoch": 2.9158878504672896,
      "grad_norm": 0.7174021005630493,
      "learning_rate": 2.702926219468882e-07,
      "loss": 1.7707,
      "step": 156
    },
    {
      "epoch": 2.9345794392523366,
      "grad_norm": 0.8035185933113098,
      "learning_rate": 1.7304345472035631e-07,
      "loss": 1.8442,
      "step": 157
    },
    {
      "epoch": 2.953271028037383,
      "grad_norm": 0.947287917137146,
      "learning_rate": 9.73615262502503e-08,
      "loss": 1.7605,
      "step": 158
    },
    {
      "epoch": 2.97196261682243,
      "grad_norm": 1.1001157760620117,
      "learning_rate": 4.3279594913447905e-08,
      "loss": 1.743,
      "step": 159
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 0.6397191286087036,
      "learning_rate": 1.082106968385288e-08,
      "loss": 1.9085,
      "step": 160
    },
    {
      "epoch": 3.0093457943925235,
      "grad_norm": 1.4585297107696533,
      "learning_rate": 0.0,
      "loss": 2.6033,
      "step": 161
    }
  ],
  "logging_steps": 1,
  "max_steps": 161,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 5.515520416048742e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}