{
  "best_metric": 0.18359769880771637,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.11230388109000826,
  "eval_steps": 25,
  "global_step": 119,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009437300931933467,
      "grad_norm": 3.160567045211792,
      "learning_rate": 2e-05,
      "loss": 3.7567,
      "step": 1
    },
    {
      "epoch": 0.0009437300931933467,
      "eval_loss": 4.042717456817627,
      "eval_runtime": 0.9968,
      "eval_samples_per_second": 50.162,
      "eval_steps_per_second": 13.042,
      "step": 1
    },
    {
      "epoch": 0.0018874601863866935,
      "grad_norm": 3.04227614402771,
      "learning_rate": 4e-05,
      "loss": 4.2187,
      "step": 2
    },
    {
      "epoch": 0.00283119027958004,
      "grad_norm": 2.9732751846313477,
      "learning_rate": 6e-05,
      "loss": 3.8159,
      "step": 3
    },
    {
      "epoch": 0.003774920372773387,
      "grad_norm": 2.9514777660369873,
      "learning_rate": 8e-05,
      "loss": 3.5658,
      "step": 4
    },
    {
      "epoch": 0.0047186504659667335,
      "grad_norm": 3.053494691848755,
      "learning_rate": 0.0001,
      "loss": 3.1504,
      "step": 5
    },
    {
      "epoch": 0.00566238055916008,
      "grad_norm": 3.0063374042510986,
      "learning_rate": 9.998291381612281e-05,
      "loss": 2.7114,
      "step": 6
    },
    {
      "epoch": 0.006606110652353427,
      "grad_norm": 2.4902377128601074,
      "learning_rate": 9.993166823949923e-05,
      "loss": 1.9711,
      "step": 7
    },
    {
      "epoch": 0.007549840745546774,
      "grad_norm": 1.8327195644378662,
      "learning_rate": 9.984630218530014e-05,
      "loss": 1.4732,
      "step": 8
    },
    {
      "epoch": 0.00849357083874012,
      "grad_norm": 1.453201413154602,
      "learning_rate": 9.972688047930772e-05,
      "loss": 1.1737,
      "step": 9
    },
    {
      "epoch": 0.009437300931933467,
      "grad_norm": 1.3615171909332275,
      "learning_rate": 9.957349380868764e-05,
      "loss": 0.9125,
      "step": 10
    },
    {
      "epoch": 0.010381031025126814,
      "grad_norm": 1.2617502212524414,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.7211,
      "step": 11
    },
    {
      "epoch": 0.01132476111832016,
      "grad_norm": 1.0414522886276245,
      "learning_rate": 9.916531719635881e-05,
      "loss": 0.5865,
      "step": 12
    },
    {
      "epoch": 0.012268491211513508,
      "grad_norm": 1.51614248752594,
      "learning_rate": 9.891083721823461e-05,
      "loss": 0.9089,
      "step": 13
    },
    {
      "epoch": 0.013212221304706853,
      "grad_norm": 2.9659416675567627,
      "learning_rate": 9.862301196726987e-05,
      "loss": 1.2334,
      "step": 14
    },
    {
      "epoch": 0.0141559513979002,
      "grad_norm": 1.000846266746521,
      "learning_rate": 9.830206001391626e-05,
      "loss": 0.4075,
      "step": 15
    },
    {
      "epoch": 0.015099681491093548,
      "grad_norm": 0.8368968367576599,
      "learning_rate": 9.794822508457784e-05,
      "loss": 0.3667,
      "step": 16
    },
    {
      "epoch": 0.016043411584286894,
      "grad_norm": 0.48357707262039185,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.3149,
      "step": 17
    },
    {
      "epoch": 0.01698714167748024,
      "grad_norm": 0.528506875038147,
      "learning_rate": 9.714300585386747e-05,
      "loss": 0.3147,
      "step": 18
    },
    {
      "epoch": 0.01793087177067359,
      "grad_norm": 0.7525439858436584,
      "learning_rate": 9.669223302466608e-05,
      "loss": 0.3128,
      "step": 19
    },
    {
      "epoch": 0.018874601863866934,
      "grad_norm": 0.8638641834259033,
      "learning_rate": 9.620979969947759e-05,
      "loss": 0.317,
      "step": 20
    },
    {
      "epoch": 0.01981833195706028,
      "grad_norm": 0.410800039768219,
      "learning_rate": 9.5696072231391e-05,
      "loss": 0.2799,
      "step": 21
    },
    {
      "epoch": 0.02076206205025363,
      "grad_norm": 0.1946195811033249,
      "learning_rate": 9.515144073782774e-05,
      "loss": 0.2837,
      "step": 22
    },
    {
      "epoch": 0.021705792143446975,
      "grad_norm": 0.3468669652938843,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.2776,
      "step": 23
    },
    {
      "epoch": 0.02264952223664032,
      "grad_norm": 0.5359954833984375,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.2646,
      "step": 24
    },
    {
      "epoch": 0.023593252329833666,
      "grad_norm": 0.44181787967681885,
      "learning_rate": 9.333637339772472e-05,
      "loss": 0.2667,
      "step": 25
    },
    {
      "epoch": 0.023593252329833666,
      "eval_loss": 0.3099350035190582,
      "eval_runtime": 0.9945,
      "eval_samples_per_second": 50.276,
      "eval_steps_per_second": 13.072,
      "step": 25
    },
    {
      "epoch": 0.024536982423027015,
      "grad_norm": 1.1429702043533325,
      "learning_rate": 9.267249152181379e-05,
      "loss": 0.4415,
      "step": 26
    },
    {
      "epoch": 0.02548071251622036,
      "grad_norm": 0.6452208757400513,
      "learning_rate": 9.198000168513604e-05,
      "loss": 0.3879,
      "step": 27
    },
    {
      "epoch": 0.026424442609413706,
      "grad_norm": 0.3990679085254669,
      "learning_rate": 9.125942975474403e-05,
      "loss": 0.2871,
      "step": 28
    },
    {
      "epoch": 0.027368172702607056,
      "grad_norm": 0.2523767948150635,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.263,
      "step": 29
    },
    {
      "epoch": 0.0283119027958004,
      "grad_norm": 0.2475036233663559,
      "learning_rate": 8.973624929123445e-05,
      "loss": 0.2693,
      "step": 30
    },
    {
      "epoch": 0.029255632888993747,
      "grad_norm": 0.25849035382270813,
      "learning_rate": 8.893479743996034e-05,
      "loss": 0.2643,
      "step": 31
    },
    {
      "epoch": 0.030199362982187096,
      "grad_norm": 0.3408520221710205,
      "learning_rate": 8.810757598029093e-05,
      "loss": 0.267,
      "step": 32
    },
    {
      "epoch": 0.03114309307538044,
      "grad_norm": 0.4147489666938782,
      "learning_rate": 8.725521309258031e-05,
      "loss": 0.2645,
      "step": 33
    },
    {
      "epoch": 0.03208682316857379,
      "grad_norm": 0.36394861340522766,
      "learning_rate": 8.637835604922979e-05,
      "loss": 0.2596,
      "step": 34
    },
    {
      "epoch": 0.03303055326176713,
      "grad_norm": 0.20617513358592987,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.2668,
      "step": 35
    },
    {
      "epoch": 0.03397428335496048,
      "grad_norm": 0.25404950976371765,
      "learning_rate": 8.455384108214805e-05,
      "loss": 0.2651,
      "step": 36
    },
    {
      "epoch": 0.03491801344815383,
      "grad_norm": 0.3631896674633026,
      "learning_rate": 8.360756866944858e-05,
      "loss": 0.2594,
      "step": 37
    },
    {
      "epoch": 0.03586174354134718,
      "grad_norm": 0.3934739828109741,
      "learning_rate": 8.263957207103507e-05,
      "loss": 0.2608,
      "step": 38
    },
    {
      "epoch": 0.03680547363454052,
      "grad_norm": 0.41364550590515137,
      "learning_rate": 8.165058636992411e-05,
      "loss": 0.2771,
      "step": 39
    },
    {
      "epoch": 0.03774920372773387,
      "grad_norm": 1.3705769777297974,
      "learning_rate": 8.064136258796198e-05,
      "loss": 0.3437,
      "step": 40
    },
    {
      "epoch": 0.038692933820927214,
      "grad_norm": 1.066591739654541,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.3018,
      "step": 41
    },
    {
      "epoch": 0.03963666391412056,
      "grad_norm": 0.2451457381248474,
      "learning_rate": 7.856528112945452e-05,
      "loss": 0.2415,
      "step": 42
    },
    {
      "epoch": 0.040580394007313905,
      "grad_norm": 0.24031850695610046,
      "learning_rate": 7.75e-05,
      "loss": 0.246,
      "step": 43
    },
    {
      "epoch": 0.04152412410050726,
      "grad_norm": 1.0646287202835083,
      "learning_rate": 7.641763268666831e-05,
      "loss": 0.267,
      "step": 44
    },
    {
      "epoch": 0.042467854193700603,
      "grad_norm": 0.9229537844657898,
      "learning_rate": 7.531900112399004e-05,
      "loss": 0.2811,
      "step": 45
    },
    {
      "epoch": 0.04341158428689395,
      "grad_norm": 0.39775267243385315,
      "learning_rate": 7.420493959733816e-05,
      "loss": 0.2581,
      "step": 46
    },
    {
      "epoch": 0.044355314380087295,
      "grad_norm": 0.3674805164337158,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.2455,
      "step": 47
    },
    {
      "epoch": 0.04529904447328064,
      "grad_norm": 0.24181093275547028,
      "learning_rate": 7.193392173765261e-05,
      "loss": 0.2466,
      "step": 48
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 0.19443802535533905,
      "learning_rate": 7.077868998367395e-05,
      "loss": 0.239,
      "step": 49
    },
    {
      "epoch": 0.04718650465966733,
      "grad_norm": 0.25048816204071045,
      "learning_rate": 6.961147611421075e-05,
      "loss": 0.2369,
      "step": 50
    },
    {
      "epoch": 0.04718650465966733,
      "eval_loss": 0.2570982277393341,
      "eval_runtime": 1.0048,
      "eval_samples_per_second": 49.764,
      "eval_steps_per_second": 12.939,
      "step": 50
    },
    {
      "epoch": 0.048130234752860684,
      "grad_norm": 0.48732152581214905,
      "learning_rate": 6.843316649507626e-05,
      "loss": 0.2634,
      "step": 51
    },
    {
      "epoch": 0.04907396484605403,
      "grad_norm": 0.4416004717350006,
      "learning_rate": 6.724465591804008e-05,
      "loss": 0.2494,
      "step": 52
    },
    {
      "epoch": 0.050017694939247376,
      "grad_norm": 0.5777482390403748,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.2685,
      "step": 53
    },
    {
      "epoch": 0.05096142503244072,
      "grad_norm": 0.6688599586486816,
      "learning_rate": 6.484064910428692e-05,
      "loss": 0.2626,
      "step": 54
    },
    {
      "epoch": 0.05190515512563407,
      "grad_norm": 0.5525055527687073,
      "learning_rate": 6.362697843656823e-05,
      "loss": 0.2506,
      "step": 55
    },
    {
      "epoch": 0.05284888521882741,
      "grad_norm": 0.4974307119846344,
      "learning_rate": 6.240675656263303e-05,
      "loss": 0.2361,
      "step": 56
    },
    {
      "epoch": 0.053792615312020765,
      "grad_norm": 0.29403093457221985,
      "learning_rate": 6.118091010182837e-05,
      "loss": 0.2196,
      "step": 57
    },
    {
      "epoch": 0.05473634540521411,
      "grad_norm": 0.2774328589439392,
      "learning_rate": 5.995036994473357e-05,
      "loss": 0.2291,
      "step": 58
    },
    {
      "epoch": 0.05568007549840746,
      "grad_norm": 0.2612267732620239,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.2241,
      "step": 59
    },
    {
      "epoch": 0.0566238055916008,
      "grad_norm": 0.3055221140384674,
      "learning_rate": 5.747894921601396e-05,
      "loss": 0.213,
      "step": 60
    },
    {
      "epoch": 0.05756753568479415,
      "grad_norm": 0.37357643246650696,
      "learning_rate": 5.62399454065673e-05,
      "loss": 0.2206,
      "step": 61
    },
    {
      "epoch": 0.058511265777987494,
      "grad_norm": 0.48611095547676086,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.2383,
      "step": 62
    },
    {
      "epoch": 0.05945499587118084,
      "grad_norm": 0.8126237392425537,
      "learning_rate": 5.376005459343272e-05,
      "loss": 0.3158,
      "step": 63
    },
    {
      "epoch": 0.06039872596437419,
      "grad_norm": 1.5249502658843994,
      "learning_rate": 5.2521050783986046e-05,
      "loss": 0.3773,
      "step": 64
    },
    {
      "epoch": 0.06134245605756754,
      "grad_norm": 0.4674637019634247,
      "learning_rate": 5.128392945374505e-05,
      "loss": 0.2159,
      "step": 65
    },
    {
      "epoch": 0.06228618615076088,
      "grad_norm": 0.2695397138595581,
      "learning_rate": 5.004963005526644e-05,
      "loss": 0.2065,
      "step": 66
    },
    {
      "epoch": 0.06322991624395423,
      "grad_norm": 0.19801601767539978,
      "learning_rate": 4.881908989817163e-05,
      "loss": 0.1862,
      "step": 67
    },
    {
      "epoch": 0.06417364633714757,
      "grad_norm": 0.27344810962677,
      "learning_rate": 4.7593243437366975e-05,
      "loss": 0.1887,
      "step": 68
    },
    {
      "epoch": 0.06511737643034092,
      "grad_norm": 0.2628972828388214,
      "learning_rate": 4.6373021563431784e-05,
      "loss": 0.2018,
      "step": 69
    },
    {
      "epoch": 0.06606110652353427,
      "grad_norm": 0.3281818926334381,
      "learning_rate": 4.515935089571309e-05,
      "loss": 0.2013,
      "step": 70
    },
    {
      "epoch": 0.06700483661672761,
      "grad_norm": 0.3598101735115051,
      "learning_rate": 4.395315307866405e-05,
      "loss": 0.1972,
      "step": 71
    },
    {
      "epoch": 0.06794856670992096,
      "grad_norm": 0.41488173604011536,
      "learning_rate": 4.275534408195991e-05,
      "loss": 0.198,
      "step": 72
    },
    {
      "epoch": 0.0688922968031143,
      "grad_norm": 0.41623586416244507,
      "learning_rate": 4.156683350492376e-05,
      "loss": 0.2004,
      "step": 73
    },
    {
      "epoch": 0.06983602689630766,
      "grad_norm": 0.32774344086647034,
      "learning_rate": 4.0388523885789256e-05,
      "loss": 0.2025,
      "step": 74
    },
    {
      "epoch": 0.07077975698950101,
      "grad_norm": 0.3913571238517761,
      "learning_rate": 3.922131001632606e-05,
      "loss": 0.2174,
      "step": 75
    },
    {
      "epoch": 0.07077975698950101,
      "eval_loss": 0.19621771574020386,
      "eval_runtime": 1.0112,
      "eval_samples_per_second": 49.447,
      "eval_steps_per_second": 12.856,
      "step": 75
    },
    {
      "epoch": 0.07172348708269435,
      "grad_norm": 0.48670119047164917,
      "learning_rate": 3.8066078262347406e-05,
      "loss": 0.248,
      "step": 76
    },
    {
      "epoch": 0.0726672171758877,
      "grad_norm": 0.34487494826316833,
      "learning_rate": 3.692370589061639e-05,
      "loss": 0.1985,
      "step": 77
    },
    {
      "epoch": 0.07361094726908105,
      "grad_norm": 0.1863425225019455,
      "learning_rate": 3.579506040266184e-05,
      "loss": 0.1804,
      "step": 78
    },
    {
      "epoch": 0.07455467736227439,
      "grad_norm": 0.19545269012451172,
      "learning_rate": 3.468099887600999e-05,
      "loss": 0.1795,
      "step": 79
    },
    {
      "epoch": 0.07549840745546774,
      "grad_norm": 0.20196500420570374,
      "learning_rate": 3.358236731333169e-05,
      "loss": 0.1766,
      "step": 80
    },
    {
      "epoch": 0.07644213754866108,
      "grad_norm": 0.2229662984609604,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.1834,
      "step": 81
    },
    {
      "epoch": 0.07738586764185443,
      "grad_norm": 0.16917945444583893,
      "learning_rate": 3.14347188705455e-05,
      "loss": 0.1745,
      "step": 82
    },
    {
      "epoch": 0.07832959773504777,
      "grad_norm": 0.18550167977809906,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.1787,
      "step": 83
    },
    {
      "epoch": 0.07927332782824112,
      "grad_norm": 0.23968204855918884,
      "learning_rate": 2.9358637412038027e-05,
      "loss": 0.1864,
      "step": 84
    },
    {
      "epoch": 0.08021705792143446,
      "grad_norm": 0.22192811965942383,
      "learning_rate": 2.8349413630075906e-05,
      "loss": 0.1931,
      "step": 85
    },
    {
      "epoch": 0.08116078801462781,
      "grad_norm": 0.2770540118217468,
      "learning_rate": 2.736042792896495e-05,
      "loss": 0.1746,
      "step": 86
    },
    {
      "epoch": 0.08210451810782117,
      "grad_norm": 0.2459287792444229,
      "learning_rate": 2.639243133055145e-05,
      "loss": 0.1803,
      "step": 87
    },
    {
      "epoch": 0.08304824820101452,
      "grad_norm": 0.43496978282928467,
      "learning_rate": 2.5446158917851958e-05,
      "loss": 0.2465,
      "step": 88
    },
    {
      "epoch": 0.08399197829420786,
      "grad_norm": 0.5976945757865906,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.2248,
      "step": 89
    },
    {
      "epoch": 0.08493570838740121,
      "grad_norm": 0.291526734828949,
      "learning_rate": 2.362164395077021e-05,
      "loss": 0.1671,
      "step": 90
    },
    {
      "epoch": 0.08587943848059455,
      "grad_norm": 0.2855542302131653,
      "learning_rate": 2.2744786907419703e-05,
      "loss": 0.1743,
      "step": 91
    },
    {
      "epoch": 0.0868231685737879,
      "grad_norm": 0.2278595119714737,
      "learning_rate": 2.189242401970908e-05,
      "loss": 0.164,
      "step": 92
    },
    {
      "epoch": 0.08776689866698124,
      "grad_norm": 0.1674998253583908,
      "learning_rate": 2.1065202560039677e-05,
      "loss": 0.1697,
      "step": 93
    },
    {
      "epoch": 0.08871062876017459,
      "grad_norm": 0.22201752662658691,
      "learning_rate": 2.026375070876556e-05,
      "loss": 0.1659,
      "step": 94
    },
    {
      "epoch": 0.08965435885336794,
      "grad_norm": 0.23097634315490723,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.1779,
      "step": 95
    },
    {
      "epoch": 0.09059808894656128,
      "grad_norm": 0.31884652376174927,
      "learning_rate": 1.8740570245255984e-05,
      "loss": 0.1704,
      "step": 96
    },
    {
      "epoch": 0.09154181903975463,
      "grad_norm": 0.2808215320110321,
      "learning_rate": 1.8019998314863974e-05,
      "loss": 0.1699,
      "step": 97
    },
    {
      "epoch": 0.09248554913294797,
      "grad_norm": 0.31133246421813965,
      "learning_rate": 1.7327508478186218e-05,
      "loss": 0.173,
      "step": 98
    },
    {
      "epoch": 0.09342927922614132,
      "grad_norm": 0.3080236613750458,
      "learning_rate": 1.6663626602275288e-05,
      "loss": 0.1652,
      "step": 99
    },
    {
      "epoch": 0.09437300931933466,
      "grad_norm": 0.3504279553890228,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.2068,
      "step": 100
    },
    {
      "epoch": 0.09437300931933466,
      "eval_loss": 0.18359769880771637,
      "eval_runtime": 0.996,
      "eval_samples_per_second": 50.2,
      "eval_steps_per_second": 13.052,
      "step": 100
    },
    {
      "epoch": 0.09531673941252802,
      "grad_norm": 0.5977703928947449,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.2196,
      "step": 101
    },
    {
      "epoch": 0.09626046950572137,
      "grad_norm": 0.4760293960571289,
      "learning_rate": 1.484855926217227e-05,
      "loss": 0.1857,
      "step": 102
    },
    {
      "epoch": 0.09720419959891471,
      "grad_norm": 0.2669781744480133,
      "learning_rate": 1.4303927768609015e-05,
      "loss": 0.1815,
      "step": 103
    },
    {
      "epoch": 0.09814792969210806,
      "grad_norm": 0.18762975931167603,
      "learning_rate": 1.3790200300522413e-05,
      "loss": 0.1615,
      "step": 104
    },
    {
      "epoch": 0.0990916597853014,
      "grad_norm": 0.22948940098285675,
      "learning_rate": 1.330776697533392e-05,
      "loss": 0.1608,
      "step": 105
    },
    {
      "epoch": 0.10003538987849475,
      "grad_norm": 0.17586657404899597,
      "learning_rate": 1.2856994146132542e-05,
      "loss": 0.1506,
      "step": 106
    },
    {
      "epoch": 0.1009791199716881,
      "grad_norm": 0.23077844083309174,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 0.162,
      "step": 107
    },
    {
      "epoch": 0.10192285006488144,
      "grad_norm": 0.21372710168361664,
      "learning_rate": 1.2051774915422163e-05,
      "loss": 0.1605,
      "step": 108
    },
    {
      "epoch": 0.10286658015807479,
      "grad_norm": 0.16886736452579498,
      "learning_rate": 1.1697939986083733e-05,
      "loss": 0.1506,
      "step": 109
    },
    {
      "epoch": 0.10381031025126813,
      "grad_norm": 0.2670663595199585,
      "learning_rate": 1.1376988032730134e-05,
      "loss": 0.1698,
      "step": 110
    },
    {
      "epoch": 0.10475404034446148,
      "grad_norm": 0.1998496651649475,
      "learning_rate": 1.1089162781765398e-05,
      "loss": 0.1691,
      "step": 111
    },
    {
      "epoch": 0.10569777043765483,
      "grad_norm": 0.17204442620277405,
      "learning_rate": 1.0834682803641197e-05,
      "loss": 0.1822,
      "step": 112
    },
    {
      "epoch": 0.10664150053084817,
      "grad_norm": 0.3721541464328766,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 0.2265,
      "step": 113
    },
    {
      "epoch": 0.10758523062404153,
      "grad_norm": 0.5235680937767029,
      "learning_rate": 1.0426506191312355e-05,
      "loss": 0.1901,
      "step": 114
    },
    {
      "epoch": 0.10852896071723488,
      "grad_norm": 0.312836229801178,
      "learning_rate": 1.0273119520692275e-05,
      "loss": 0.1713,
      "step": 115
    },
    {
      "epoch": 0.10947269081042822,
      "grad_norm": 0.18158796429634094,
      "learning_rate": 1.0153697814699859e-05,
      "loss": 0.1683,
      "step": 116
    },
    {
      "epoch": 0.11041642090362157,
      "grad_norm": 0.24202579259872437,
      "learning_rate": 1.0068331760500774e-05,
      "loss": 0.1639,
      "step": 117
    },
    {
      "epoch": 0.11136015099681491,
      "grad_norm": 0.24022828042507172,
      "learning_rate": 1.0017086183877188e-05,
      "loss": 0.1677,
      "step": 118
    },
    {
      "epoch": 0.11230388109000826,
      "grad_norm": 0.2230340838432312,
      "learning_rate": 1e-05,
      "loss": 0.1475,
      "step": 119
    }
  ],
  "logging_steps": 1,
  "max_steps": 119,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 20,
        "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": 1.3299091053509345e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}