{
  "best_metric": 2.0041327476501465,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.01856406924397828,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.28203462198914e-05,
      "grad_norm": 0.5333740711212158,
      "learning_rate": 1.004e-05,
      "loss": 2.123,
      "step": 1
    },
    {
      "epoch": 9.28203462198914e-05,
      "eval_loss": 2.1500566005706787,
      "eval_runtime": 212.426,
      "eval_samples_per_second": 21.358,
      "eval_steps_per_second": 5.343,
      "step": 1
    },
    {
      "epoch": 0.0001856406924397828,
      "grad_norm": 0.5310633182525635,
      "learning_rate": 2.008e-05,
      "loss": 2.1533,
      "step": 2
    },
    {
      "epoch": 0.0002784610386596742,
      "grad_norm": 0.570530116558075,
      "learning_rate": 3.012e-05,
      "loss": 1.9656,
      "step": 3
    },
    {
      "epoch": 0.0003712813848795656,
      "grad_norm": 0.5866032242774963,
      "learning_rate": 4.016e-05,
      "loss": 1.9126,
      "step": 4
    },
    {
      "epoch": 0.000464101731099457,
      "grad_norm": 0.5609645247459412,
      "learning_rate": 5.02e-05,
      "loss": 1.9268,
      "step": 5
    },
    {
      "epoch": 0.0005569220773193484,
      "grad_norm": 0.5599470138549805,
      "learning_rate": 6.024e-05,
      "loss": 2.1493,
      "step": 6
    },
    {
      "epoch": 0.0006497424235392398,
      "grad_norm": 0.5012790560722351,
      "learning_rate": 7.028e-05,
      "loss": 1.9697,
      "step": 7
    },
    {
      "epoch": 0.0007425627697591312,
      "grad_norm": 0.5099210739135742,
      "learning_rate": 8.032e-05,
      "loss": 2.1438,
      "step": 8
    },
    {
      "epoch": 0.0008353831159790226,
      "grad_norm": 0.5398349165916443,
      "learning_rate": 9.036000000000001e-05,
      "loss": 1.9605,
      "step": 9
    },
    {
      "epoch": 0.000928203462198914,
      "grad_norm": 0.5319710969924927,
      "learning_rate": 0.0001004,
      "loss": 2.274,
      "step": 10
    },
    {
      "epoch": 0.0010210238084188054,
      "grad_norm": 0.5919522047042847,
      "learning_rate": 9.987157894736842e-05,
      "loss": 2.1037,
      "step": 11
    },
    {
      "epoch": 0.0011138441546386967,
      "grad_norm": 0.5564264059066772,
      "learning_rate": 9.934315789473684e-05,
      "loss": 2.1668,
      "step": 12
    },
    {
      "epoch": 0.0012066645008585882,
      "grad_norm": 0.5003729462623596,
      "learning_rate": 9.881473684210525e-05,
      "loss": 1.8983,
      "step": 13
    },
    {
      "epoch": 0.0012994848470784797,
      "grad_norm": 0.5218623876571655,
      "learning_rate": 9.828631578947369e-05,
      "loss": 2.063,
      "step": 14
    },
    {
      "epoch": 0.001392305193298371,
      "grad_norm": 0.5020257830619812,
      "learning_rate": 9.77578947368421e-05,
      "loss": 2.119,
      "step": 15
    },
    {
      "epoch": 0.0014851255395182624,
      "grad_norm": 0.510440468788147,
      "learning_rate": 9.722947368421052e-05,
      "loss": 2.0224,
      "step": 16
    },
    {
      "epoch": 0.0015779458857381537,
      "grad_norm": 0.5378854274749756,
      "learning_rate": 9.670105263157895e-05,
      "loss": 2.0703,
      "step": 17
    },
    {
      "epoch": 0.0016707662319580452,
      "grad_norm": 0.5330931544303894,
      "learning_rate": 9.617263157894737e-05,
      "loss": 1.9227,
      "step": 18
    },
    {
      "epoch": 0.0017635865781779367,
      "grad_norm": 0.4982943534851074,
      "learning_rate": 9.564421052631579e-05,
      "loss": 1.7878,
      "step": 19
    },
    {
      "epoch": 0.001856406924397828,
      "grad_norm": 0.5345494747161865,
      "learning_rate": 9.511578947368421e-05,
      "loss": 2.0192,
      "step": 20
    },
    {
      "epoch": 0.0019492272706177194,
      "grad_norm": 0.5428488254547119,
      "learning_rate": 9.458736842105264e-05,
      "loss": 1.8952,
      "step": 21
    },
    {
      "epoch": 0.002042047616837611,
      "grad_norm": 0.4932510256767273,
      "learning_rate": 9.405894736842106e-05,
      "loss": 2.0396,
      "step": 22
    },
    {
      "epoch": 0.002134867963057502,
      "grad_norm": 0.5346501469612122,
      "learning_rate": 9.353052631578947e-05,
      "loss": 2.06,
      "step": 23
    },
    {
      "epoch": 0.0022276883092773934,
      "grad_norm": 0.5654396414756775,
      "learning_rate": 9.300210526315789e-05,
      "loss": 2.1686,
      "step": 24
    },
    {
      "epoch": 0.002320508655497285,
      "grad_norm": 0.5074037313461304,
      "learning_rate": 9.247368421052631e-05,
      "loss": 2.0209,
      "step": 25
    },
    {
      "epoch": 0.0024133290017171764,
      "grad_norm": 0.5299178957939148,
      "learning_rate": 9.194526315789473e-05,
      "loss": 2.0733,
      "step": 26
    },
    {
      "epoch": 0.0025061493479370677,
      "grad_norm": 0.4903567135334015,
      "learning_rate": 9.141684210526316e-05,
      "loss": 1.8781,
      "step": 27
    },
    {
      "epoch": 0.0025989696941569594,
      "grad_norm": 0.5466001629829407,
      "learning_rate": 9.088842105263158e-05,
      "loss": 2.2091,
      "step": 28
    },
    {
      "epoch": 0.0026917900403768506,
      "grad_norm": 0.5639941692352295,
      "learning_rate": 9.036000000000001e-05,
      "loss": 2.0417,
      "step": 29
    },
    {
      "epoch": 0.002784610386596742,
      "grad_norm": 0.547460675239563,
      "learning_rate": 8.983157894736843e-05,
      "loss": 2.3328,
      "step": 30
    },
    {
      "epoch": 0.0028774307328166336,
      "grad_norm": 0.5575900077819824,
      "learning_rate": 8.930315789473684e-05,
      "loss": 1.9555,
      "step": 31
    },
    {
      "epoch": 0.002970251079036525,
      "grad_norm": 0.5688737034797668,
      "learning_rate": 8.877473684210526e-05,
      "loss": 2.2341,
      "step": 32
    },
    {
      "epoch": 0.003063071425256416,
      "grad_norm": 0.5598611235618591,
      "learning_rate": 8.824631578947368e-05,
      "loss": 2.0329,
      "step": 33
    },
    {
      "epoch": 0.0031558917714763074,
      "grad_norm": 0.5636963248252869,
      "learning_rate": 8.771789473684211e-05,
      "loss": 2.1278,
      "step": 34
    },
    {
      "epoch": 0.003248712117696199,
      "grad_norm": 0.5724871754646301,
      "learning_rate": 8.718947368421053e-05,
      "loss": 2.1822,
      "step": 35
    },
    {
      "epoch": 0.0033415324639160904,
      "grad_norm": 0.5909259915351868,
      "learning_rate": 8.666105263157895e-05,
      "loss": 2.1601,
      "step": 36
    },
    {
      "epoch": 0.0034343528101359816,
      "grad_norm": 0.5581693053245544,
      "learning_rate": 8.613263157894737e-05,
      "loss": 2.1731,
      "step": 37
    },
    {
      "epoch": 0.0035271731563558733,
      "grad_norm": 0.5789634585380554,
      "learning_rate": 8.560421052631578e-05,
      "loss": 2.0267,
      "step": 38
    },
    {
      "epoch": 0.0036199935025757646,
      "grad_norm": 0.5522585511207581,
      "learning_rate": 8.50757894736842e-05,
      "loss": 2.149,
      "step": 39
    },
    {
      "epoch": 0.003712813848795656,
      "grad_norm": 0.5890622735023499,
      "learning_rate": 8.454736842105263e-05,
      "loss": 2.3245,
      "step": 40
    },
    {
      "epoch": 0.0038056341950155476,
      "grad_norm": 0.6173768043518066,
      "learning_rate": 8.401894736842106e-05,
      "loss": 2.4872,
      "step": 41
    },
    {
      "epoch": 0.003898454541235439,
      "grad_norm": 0.5873492360115051,
      "learning_rate": 8.349052631578948e-05,
      "loss": 1.9492,
      "step": 42
    },
    {
      "epoch": 0.00399127488745533,
      "grad_norm": 0.6083503365516663,
      "learning_rate": 8.29621052631579e-05,
      "loss": 2.2825,
      "step": 43
    },
    {
      "epoch": 0.004084095233675222,
      "grad_norm": 0.5901498794555664,
      "learning_rate": 8.243368421052632e-05,
      "loss": 2.0717,
      "step": 44
    },
    {
      "epoch": 0.004176915579895113,
      "grad_norm": 0.627431333065033,
      "learning_rate": 8.190526315789474e-05,
      "loss": 2.2892,
      "step": 45
    },
    {
      "epoch": 0.004269735926115004,
      "grad_norm": 0.5825062394142151,
      "learning_rate": 8.137684210526315e-05,
      "loss": 2.1311,
      "step": 46
    },
    {
      "epoch": 0.004362556272334896,
      "grad_norm": 0.600988507270813,
      "learning_rate": 8.084842105263157e-05,
      "loss": 2.1318,
      "step": 47
    },
    {
      "epoch": 0.004455376618554787,
      "grad_norm": 0.660859227180481,
      "learning_rate": 8.032e-05,
      "loss": 2.1271,
      "step": 48
    },
    {
      "epoch": 0.0045481969647746786,
      "grad_norm": 0.6793040633201599,
      "learning_rate": 7.979157894736842e-05,
      "loss": 2.3411,
      "step": 49
    },
    {
      "epoch": 0.00464101731099457,
      "grad_norm": 0.6588550806045532,
      "learning_rate": 7.926315789473684e-05,
      "loss": 2.3991,
      "step": 50
    },
    {
      "epoch": 0.00464101731099457,
      "eval_loss": 2.0389838218688965,
      "eval_runtime": 212.2309,
      "eval_samples_per_second": 21.378,
      "eval_steps_per_second": 5.348,
      "step": 50
    },
    {
      "epoch": 0.004733837657214461,
      "grad_norm": 0.4591948688030243,
      "learning_rate": 7.873473684210526e-05,
      "loss": 2.2252,
      "step": 51
    },
    {
      "epoch": 0.004826658003434353,
      "grad_norm": 0.44009777903556824,
      "learning_rate": 7.820631578947369e-05,
      "loss": 2.0146,
      "step": 52
    },
    {
      "epoch": 0.0049194783496542445,
      "grad_norm": 0.45978692173957825,
      "learning_rate": 7.76778947368421e-05,
      "loss": 1.861,
      "step": 53
    },
    {
      "epoch": 0.005012298695874135,
      "grad_norm": 0.4349885582923889,
      "learning_rate": 7.714947368421052e-05,
      "loss": 1.7471,
      "step": 54
    },
    {
      "epoch": 0.005105119042094027,
      "grad_norm": 0.4415923058986664,
      "learning_rate": 7.662105263157896e-05,
      "loss": 1.9122,
      "step": 55
    },
    {
      "epoch": 0.005197939388313919,
      "grad_norm": 0.43709808588027954,
      "learning_rate": 7.609263157894737e-05,
      "loss": 1.8768,
      "step": 56
    },
    {
      "epoch": 0.0052907597345338096,
      "grad_norm": 0.42503705620765686,
      "learning_rate": 7.556421052631579e-05,
      "loss": 1.8632,
      "step": 57
    },
    {
      "epoch": 0.005383580080753701,
      "grad_norm": 0.4333106279373169,
      "learning_rate": 7.503578947368421e-05,
      "loss": 1.998,
      "step": 58
    },
    {
      "epoch": 0.005476400426973593,
      "grad_norm": 0.44236087799072266,
      "learning_rate": 7.450736842105263e-05,
      "loss": 1.903,
      "step": 59
    },
    {
      "epoch": 0.005569220773193484,
      "grad_norm": 0.42541614174842834,
      "learning_rate": 7.397894736842105e-05,
      "loss": 1.7882,
      "step": 60
    },
    {
      "epoch": 0.0056620411194133755,
      "grad_norm": 0.43183577060699463,
      "learning_rate": 7.345052631578948e-05,
      "loss": 2.0504,
      "step": 61
    },
    {
      "epoch": 0.005754861465633267,
      "grad_norm": 0.4386312961578369,
      "learning_rate": 7.29221052631579e-05,
      "loss": 1.8203,
      "step": 62
    },
    {
      "epoch": 0.005847681811853158,
      "grad_norm": 0.46675723791122437,
      "learning_rate": 7.239368421052631e-05,
      "loss": 1.8889,
      "step": 63
    },
    {
      "epoch": 0.00594050215807305,
      "grad_norm": 0.43209633231163025,
      "learning_rate": 7.186526315789474e-05,
      "loss": 1.7206,
      "step": 64
    },
    {
      "epoch": 0.006033322504292941,
      "grad_norm": 0.46005451679229736,
      "learning_rate": 7.133684210526316e-05,
      "loss": 2.0714,
      "step": 65
    },
    {
      "epoch": 0.006126142850512832,
      "grad_norm": 0.43874305486679077,
      "learning_rate": 7.080842105263158e-05,
      "loss": 1.9384,
      "step": 66
    },
    {
      "epoch": 0.006218963196732724,
      "grad_norm": 0.44712334871292114,
      "learning_rate": 7.028e-05,
      "loss": 2.0105,
      "step": 67
    },
    {
      "epoch": 0.006311783542952615,
      "grad_norm": 0.47745460271835327,
      "learning_rate": 6.975157894736843e-05,
      "loss": 1.9495,
      "step": 68
    },
    {
      "epoch": 0.0064046038891725065,
      "grad_norm": 0.49662894010543823,
      "learning_rate": 6.922315789473685e-05,
      "loss": 2.2379,
      "step": 69
    },
    {
      "epoch": 0.006497424235392398,
      "grad_norm": 0.5316717028617859,
      "learning_rate": 6.869473684210527e-05,
      "loss": 2.1759,
      "step": 70
    },
    {
      "epoch": 0.006590244581612289,
      "grad_norm": 0.4947868585586548,
      "learning_rate": 6.816631578947368e-05,
      "loss": 2.0152,
      "step": 71
    },
    {
      "epoch": 0.006683064927832181,
      "grad_norm": 0.47361937165260315,
      "learning_rate": 6.76378947368421e-05,
      "loss": 1.7754,
      "step": 72
    },
    {
      "epoch": 0.006775885274052072,
      "grad_norm": 0.5122577548027039,
      "learning_rate": 6.710947368421052e-05,
      "loss": 2.2441,
      "step": 73
    },
    {
      "epoch": 0.006868705620271963,
      "grad_norm": 0.4984202980995178,
      "learning_rate": 6.658105263157894e-05,
      "loss": 1.9172,
      "step": 74
    },
    {
      "epoch": 0.006961525966491855,
      "grad_norm": 0.4806360900402069,
      "learning_rate": 6.605263157894737e-05,
      "loss": 2.0002,
      "step": 75
    },
    {
      "epoch": 0.007054346312711747,
      "grad_norm": 0.4529125392436981,
      "learning_rate": 6.55242105263158e-05,
      "loss": 1.8867,
      "step": 76
    },
    {
      "epoch": 0.0071471666589316375,
      "grad_norm": 0.4892098307609558,
      "learning_rate": 6.499578947368422e-05,
      "loss": 2.0669,
      "step": 77
    },
    {
      "epoch": 0.007239987005151529,
      "grad_norm": 0.5047986507415771,
      "learning_rate": 6.446736842105264e-05,
      "loss": 2.0941,
      "step": 78
    },
    {
      "epoch": 0.007332807351371421,
      "grad_norm": 0.4794524312019348,
      "learning_rate": 6.393894736842105e-05,
      "loss": 1.8961,
      "step": 79
    },
    {
      "epoch": 0.007425627697591312,
      "grad_norm": 0.4937351644039154,
      "learning_rate": 6.341052631578947e-05,
      "loss": 1.9912,
      "step": 80
    },
    {
      "epoch": 0.007518448043811203,
      "grad_norm": 0.4996980130672455,
      "learning_rate": 6.288210526315789e-05,
      "loss": 2.0763,
      "step": 81
    },
    {
      "epoch": 0.007611268390031095,
      "grad_norm": 0.5066346526145935,
      "learning_rate": 6.235368421052632e-05,
      "loss": 2.0239,
      "step": 82
    },
    {
      "epoch": 0.007704088736250986,
      "grad_norm": 0.5465410947799683,
      "learning_rate": 6.182526315789474e-05,
      "loss": 1.965,
      "step": 83
    },
    {
      "epoch": 0.007796909082470878,
      "grad_norm": 0.49924957752227783,
      "learning_rate": 6.129684210526316e-05,
      "loss": 1.7469,
      "step": 84
    },
    {
      "epoch": 0.007889729428690768,
      "grad_norm": 0.5318244695663452,
      "learning_rate": 6.076842105263158e-05,
      "loss": 1.9024,
      "step": 85
    },
    {
      "epoch": 0.00798254977491066,
      "grad_norm": 0.5169056057929993,
      "learning_rate": 6.024e-05,
      "loss": 1.9984,
      "step": 86
    },
    {
      "epoch": 0.008075370121130552,
      "grad_norm": 0.5733655095100403,
      "learning_rate": 5.971157894736842e-05,
      "loss": 2.1394,
      "step": 87
    },
    {
      "epoch": 0.008168190467350444,
      "grad_norm": 0.5268761515617371,
      "learning_rate": 5.9183157894736835e-05,
      "loss": 1.9004,
      "step": 88
    },
    {
      "epoch": 0.008261010813570335,
      "grad_norm": 0.5536757111549377,
      "learning_rate": 5.8654736842105267e-05,
      "loss": 2.0655,
      "step": 89
    },
    {
      "epoch": 0.008353831159790225,
      "grad_norm": 0.5382729172706604,
      "learning_rate": 5.8126315789473684e-05,
      "loss": 1.7562,
      "step": 90
    },
    {
      "epoch": 0.008446651506010117,
      "grad_norm": 0.5523245930671692,
      "learning_rate": 5.759789473684211e-05,
      "loss": 2.1592,
      "step": 91
    },
    {
      "epoch": 0.008539471852230009,
      "grad_norm": 0.6106486320495605,
      "learning_rate": 5.706947368421053e-05,
      "loss": 2.39,
      "step": 92
    },
    {
      "epoch": 0.0086322921984499,
      "grad_norm": 0.6065232753753662,
      "learning_rate": 5.6541052631578945e-05,
      "loss": 2.1217,
      "step": 93
    },
    {
      "epoch": 0.008725112544669792,
      "grad_norm": 0.57742840051651,
      "learning_rate": 5.601263157894736e-05,
      "loss": 1.9459,
      "step": 94
    },
    {
      "epoch": 0.008817932890889684,
      "grad_norm": 0.6233941316604614,
      "learning_rate": 5.5484210526315794e-05,
      "loss": 2.1776,
      "step": 95
    },
    {
      "epoch": 0.008910753237109574,
      "grad_norm": 0.624778687953949,
      "learning_rate": 5.495578947368421e-05,
      "loss": 1.9676,
      "step": 96
    },
    {
      "epoch": 0.009003573583329465,
      "grad_norm": 0.5832610130310059,
      "learning_rate": 5.442736842105264e-05,
      "loss": 2.0999,
      "step": 97
    },
    {
      "epoch": 0.009096393929549357,
      "grad_norm": 0.6290329694747925,
      "learning_rate": 5.3898947368421055e-05,
      "loss": 2.1532,
      "step": 98
    },
    {
      "epoch": 0.009189214275769249,
      "grad_norm": 0.6240950226783752,
      "learning_rate": 5.337052631578947e-05,
      "loss": 2.1017,
      "step": 99
    },
    {
      "epoch": 0.00928203462198914,
      "grad_norm": 0.6797816753387451,
      "learning_rate": 5.284210526315789e-05,
      "loss": 1.9699,
      "step": 100
    },
    {
      "epoch": 0.00928203462198914,
      "eval_loss": 2.0185234546661377,
      "eval_runtime": 212.0665,
      "eval_samples_per_second": 21.394,
      "eval_steps_per_second": 5.352,
      "step": 100
    },
    {
      "epoch": 0.009374854968209032,
      "grad_norm": 0.4157350957393646,
      "learning_rate": 5.231368421052631e-05,
      "loss": 1.9556,
      "step": 101
    },
    {
      "epoch": 0.009467675314428922,
      "grad_norm": 0.433269739151001,
      "learning_rate": 5.178526315789474e-05,
      "loss": 1.7989,
      "step": 102
    },
    {
      "epoch": 0.009560495660648814,
      "grad_norm": 0.43151503801345825,
      "learning_rate": 5.1256842105263165e-05,
      "loss": 1.8229,
      "step": 103
    },
    {
      "epoch": 0.009653316006868706,
      "grad_norm": 0.44042569398880005,
      "learning_rate": 5.072842105263158e-05,
      "loss": 1.7344,
      "step": 104
    },
    {
      "epoch": 0.009746136353088597,
      "grad_norm": 0.4146162271499634,
      "learning_rate": 5.02e-05,
      "loss": 1.9032,
      "step": 105
    },
    {
      "epoch": 0.009838956699308489,
      "grad_norm": 0.4360559582710266,
      "learning_rate": 4.967157894736842e-05,
      "loss": 2.0677,
      "step": 106
    },
    {
      "epoch": 0.00993177704552838,
      "grad_norm": 0.4013524651527405,
      "learning_rate": 4.914315789473684e-05,
      "loss": 1.9427,
      "step": 107
    },
    {
      "epoch": 0.01002459739174827,
      "grad_norm": 0.44252482056617737,
      "learning_rate": 4.861473684210526e-05,
      "loss": 1.9804,
      "step": 108
    },
    {
      "epoch": 0.010117417737968162,
      "grad_norm": 0.41882866621017456,
      "learning_rate": 4.8086315789473686e-05,
      "loss": 1.799,
      "step": 109
    },
    {
      "epoch": 0.010210238084188054,
      "grad_norm": 0.43453121185302734,
      "learning_rate": 4.7557894736842104e-05,
      "loss": 2.0016,
      "step": 110
    },
    {
      "epoch": 0.010303058430407946,
      "grad_norm": 0.49610668420791626,
      "learning_rate": 4.702947368421053e-05,
      "loss": 2.0242,
      "step": 111
    },
    {
      "epoch": 0.010395878776627837,
      "grad_norm": 0.42180904746055603,
      "learning_rate": 4.6501052631578946e-05,
      "loss": 1.8779,
      "step": 112
    },
    {
      "epoch": 0.010488699122847727,
      "grad_norm": 0.4709084928035736,
      "learning_rate": 4.5972631578947364e-05,
      "loss": 1.8693,
      "step": 113
    },
    {
      "epoch": 0.010581519469067619,
      "grad_norm": 0.4451385736465454,
      "learning_rate": 4.544421052631579e-05,
      "loss": 1.8203,
      "step": 114
    },
    {
      "epoch": 0.01067433981528751,
      "grad_norm": 0.4565402865409851,
      "learning_rate": 4.4915789473684213e-05,
      "loss": 1.897,
      "step": 115
    },
    {
      "epoch": 0.010767160161507403,
      "grad_norm": 0.4602057635784149,
      "learning_rate": 4.438736842105263e-05,
      "loss": 1.9684,
      "step": 116
    },
    {
      "epoch": 0.010859980507727294,
      "grad_norm": 0.4286463260650635,
      "learning_rate": 4.3858947368421056e-05,
      "loss": 1.8134,
      "step": 117
    },
    {
      "epoch": 0.010952800853947186,
      "grad_norm": 0.4532035291194916,
      "learning_rate": 4.3330526315789474e-05,
      "loss": 1.9204,
      "step": 118
    },
    {
      "epoch": 0.011045621200167076,
      "grad_norm": 0.49677908420562744,
      "learning_rate": 4.280210526315789e-05,
      "loss": 2.0517,
      "step": 119
    },
    {
      "epoch": 0.011138441546386968,
      "grad_norm": 0.4839816391468048,
      "learning_rate": 4.2273684210526317e-05,
      "loss": 2.0162,
      "step": 120
    },
    {
      "epoch": 0.01123126189260686,
      "grad_norm": 0.4714973568916321,
      "learning_rate": 4.174526315789474e-05,
      "loss": 1.9792,
      "step": 121
    },
    {
      "epoch": 0.011324082238826751,
      "grad_norm": 0.48217833042144775,
      "learning_rate": 4.121684210526316e-05,
      "loss": 2.1381,
      "step": 122
    },
    {
      "epoch": 0.011416902585046643,
      "grad_norm": 0.45825913548469543,
      "learning_rate": 4.068842105263158e-05,
      "loss": 1.9006,
      "step": 123
    },
    {
      "epoch": 0.011509722931266534,
      "grad_norm": 0.5154534578323364,
      "learning_rate": 4.016e-05,
      "loss": 2.0451,
      "step": 124
    },
    {
      "epoch": 0.011602543277486424,
      "grad_norm": 0.49753981828689575,
      "learning_rate": 3.963157894736842e-05,
      "loss": 1.9921,
      "step": 125
    },
    {
      "epoch": 0.011695363623706316,
      "grad_norm": 0.48420360684394836,
      "learning_rate": 3.9103157894736844e-05,
      "loss": 1.8454,
      "step": 126
    },
    {
      "epoch": 0.011788183969926208,
      "grad_norm": 0.5063680410385132,
      "learning_rate": 3.857473684210526e-05,
      "loss": 1.8294,
      "step": 127
    },
    {
      "epoch": 0.0118810043161461,
      "grad_norm": 0.4992259740829468,
      "learning_rate": 3.804631578947369e-05,
      "loss": 1.9348,
      "step": 128
    },
    {
      "epoch": 0.011973824662365991,
      "grad_norm": 0.508219301700592,
      "learning_rate": 3.7517894736842105e-05,
      "loss": 2.0251,
      "step": 129
    },
    {
      "epoch": 0.012066645008585883,
      "grad_norm": 0.4896531105041504,
      "learning_rate": 3.698947368421052e-05,
      "loss": 1.7667,
      "step": 130
    },
    {
      "epoch": 0.012159465354805773,
      "grad_norm": 0.5085623264312744,
      "learning_rate": 3.646105263157895e-05,
      "loss": 1.8525,
      "step": 131
    },
    {
      "epoch": 0.012252285701025665,
      "grad_norm": 0.49702784419059753,
      "learning_rate": 3.593263157894737e-05,
      "loss": 1.9041,
      "step": 132
    },
    {
      "epoch": 0.012345106047245556,
      "grad_norm": 0.5175393223762512,
      "learning_rate": 3.540421052631579e-05,
      "loss": 2.1606,
      "step": 133
    },
    {
      "epoch": 0.012437926393465448,
      "grad_norm": 0.5096806287765503,
      "learning_rate": 3.4875789473684215e-05,
      "loss": 1.8375,
      "step": 134
    },
    {
      "epoch": 0.01253074673968534,
      "grad_norm": 0.5583460927009583,
      "learning_rate": 3.434736842105263e-05,
      "loss": 2.2475,
      "step": 135
    },
    {
      "epoch": 0.01262356708590523,
      "grad_norm": 0.5094785690307617,
      "learning_rate": 3.381894736842105e-05,
      "loss": 2.019,
      "step": 136
    },
    {
      "epoch": 0.012716387432125121,
      "grad_norm": 0.554124116897583,
      "learning_rate": 3.329052631578947e-05,
      "loss": 2.0397,
      "step": 137
    },
    {
      "epoch": 0.012809207778345013,
      "grad_norm": 0.5521702170372009,
      "learning_rate": 3.27621052631579e-05,
      "loss": 2.067,
      "step": 138
    },
    {
      "epoch": 0.012902028124564905,
      "grad_norm": 0.5431244373321533,
      "learning_rate": 3.223368421052632e-05,
      "loss": 1.9676,
      "step": 139
    },
    {
      "epoch": 0.012994848470784796,
      "grad_norm": 0.5575247406959534,
      "learning_rate": 3.1705263157894736e-05,
      "loss": 1.7978,
      "step": 140
    },
    {
      "epoch": 0.013087668817004688,
      "grad_norm": 0.5787823796272278,
      "learning_rate": 3.117684210526316e-05,
      "loss": 2.1306,
      "step": 141
    },
    {
      "epoch": 0.013180489163224578,
      "grad_norm": 0.5557217001914978,
      "learning_rate": 3.064842105263158e-05,
      "loss": 2.0982,
      "step": 142
    },
    {
      "epoch": 0.01327330950944447,
      "grad_norm": 0.5702773928642273,
      "learning_rate": 3.012e-05,
      "loss": 1.9572,
      "step": 143
    },
    {
      "epoch": 0.013366129855664361,
      "grad_norm": 0.5814855098724365,
      "learning_rate": 2.9591578947368418e-05,
      "loss": 1.9171,
      "step": 144
    },
    {
      "epoch": 0.013458950201884253,
      "grad_norm": 0.5961145162582397,
      "learning_rate": 2.9063157894736842e-05,
      "loss": 2.06,
      "step": 145
    },
    {
      "epoch": 0.013551770548104145,
      "grad_norm": 0.5634588599205017,
      "learning_rate": 2.8534736842105264e-05,
      "loss": 2.0661,
      "step": 146
    },
    {
      "epoch": 0.013644590894324037,
      "grad_norm": 0.6884035468101501,
      "learning_rate": 2.800631578947368e-05,
      "loss": 1.9846,
      "step": 147
    },
    {
      "epoch": 0.013737411240543927,
      "grad_norm": 0.592460572719574,
      "learning_rate": 2.7477894736842106e-05,
      "loss": 2.0338,
      "step": 148
    },
    {
      "epoch": 0.013830231586763818,
      "grad_norm": 0.598613440990448,
      "learning_rate": 2.6949473684210527e-05,
      "loss": 2.1441,
      "step": 149
    },
    {
      "epoch": 0.01392305193298371,
      "grad_norm": 0.6344769597053528,
      "learning_rate": 2.6421052631578945e-05,
      "loss": 2.3666,
      "step": 150
    },
    {
      "epoch": 0.01392305193298371,
      "eval_loss": 2.0085387229919434,
      "eval_runtime": 211.7337,
      "eval_samples_per_second": 21.428,
      "eval_steps_per_second": 5.361,
      "step": 150
    },
    {
      "epoch": 0.014015872279203602,
      "grad_norm": 0.4076049029827118,
      "learning_rate": 2.589263157894737e-05,
      "loss": 2.2603,
      "step": 151
    },
    {
      "epoch": 0.014108692625423493,
      "grad_norm": 0.4122617244720459,
      "learning_rate": 2.536421052631579e-05,
      "loss": 2.0841,
      "step": 152
    },
    {
      "epoch": 0.014201512971643385,
      "grad_norm": 0.4217035472393036,
      "learning_rate": 2.483578947368421e-05,
      "loss": 2.0217,
      "step": 153
    },
    {
      "epoch": 0.014294333317863275,
      "grad_norm": 0.4271675646305084,
      "learning_rate": 2.430736842105263e-05,
      "loss": 1.7876,
      "step": 154
    },
    {
      "epoch": 0.014387153664083167,
      "grad_norm": 0.4109157621860504,
      "learning_rate": 2.3778947368421052e-05,
      "loss": 1.8487,
      "step": 155
    },
    {
      "epoch": 0.014479974010303058,
      "grad_norm": 0.42467454075813293,
      "learning_rate": 2.3250526315789473e-05,
      "loss": 1.8176,
      "step": 156
    },
    {
      "epoch": 0.01457279435652295,
      "grad_norm": 0.43306881189346313,
      "learning_rate": 2.2722105263157894e-05,
      "loss": 2.0096,
      "step": 157
    },
    {
      "epoch": 0.014665614702742842,
      "grad_norm": 0.4301247298717499,
      "learning_rate": 2.2193684210526316e-05,
      "loss": 1.7983,
      "step": 158
    },
    {
      "epoch": 0.014758435048962733,
      "grad_norm": 0.43399932980537415,
      "learning_rate": 2.1665263157894737e-05,
      "loss": 2.138,
      "step": 159
    },
    {
      "epoch": 0.014851255395182623,
      "grad_norm": 0.4387844204902649,
      "learning_rate": 2.1136842105263158e-05,
      "loss": 1.6287,
      "step": 160
    },
    {
      "epoch": 0.014944075741402515,
      "grad_norm": 0.4472537636756897,
      "learning_rate": 2.060842105263158e-05,
      "loss": 2.1351,
      "step": 161
    },
    {
      "epoch": 0.015036896087622407,
      "grad_norm": 0.45660072565078735,
      "learning_rate": 2.008e-05,
      "loss": 2.0469,
      "step": 162
    },
    {
      "epoch": 0.015129716433842299,
      "grad_norm": 0.7435435056686401,
      "learning_rate": 1.9551578947368422e-05,
      "loss": 1.919,
      "step": 163
    },
    {
      "epoch": 0.01522253678006219,
      "grad_norm": 0.4554401934146881,
      "learning_rate": 1.9023157894736843e-05,
      "loss": 1.951,
      "step": 164
    },
    {
      "epoch": 0.01531535712628208,
      "grad_norm": 0.4483166038990021,
      "learning_rate": 1.849473684210526e-05,
      "loss": 2.0071,
      "step": 165
    },
    {
      "epoch": 0.015408177472501972,
      "grad_norm": 0.4810929596424103,
      "learning_rate": 1.7966315789473686e-05,
      "loss": 2.0367,
      "step": 166
    },
    {
      "epoch": 0.015500997818721864,
      "grad_norm": 0.4459546208381653,
      "learning_rate": 1.7437894736842107e-05,
      "loss": 1.8893,
      "step": 167
    },
    {
      "epoch": 0.015593818164941755,
      "grad_norm": 0.4915485084056854,
      "learning_rate": 1.6909473684210525e-05,
      "loss": 1.9784,
      "step": 168
    },
    {
      "epoch": 0.015686638511161647,
      "grad_norm": 0.4772583544254303,
      "learning_rate": 1.638105263157895e-05,
      "loss": 1.9509,
      "step": 169
    },
    {
      "epoch": 0.015779458857381537,
      "grad_norm": 0.4593046307563782,
      "learning_rate": 1.5852631578947368e-05,
      "loss": 1.8422,
      "step": 170
    },
    {
      "epoch": 0.01587227920360143,
      "grad_norm": 0.4797092080116272,
      "learning_rate": 1.532421052631579e-05,
      "loss": 1.8923,
      "step": 171
    },
    {
      "epoch": 0.01596509954982132,
      "grad_norm": 0.4819195866584778,
      "learning_rate": 1.4795789473684209e-05,
      "loss": 1.9566,
      "step": 172
    },
    {
      "epoch": 0.016057919896041214,
      "grad_norm": 0.5063287615776062,
      "learning_rate": 1.4267368421052632e-05,
      "loss": 2.1537,
      "step": 173
    },
    {
      "epoch": 0.016150740242261104,
      "grad_norm": 0.47720491886138916,
      "learning_rate": 1.3738947368421053e-05,
      "loss": 2.0131,
      "step": 174
    },
    {
      "epoch": 0.016243560588480994,
      "grad_norm": 0.4763629138469696,
      "learning_rate": 1.3210526315789473e-05,
      "loss": 1.9978,
      "step": 175
    },
    {
      "epoch": 0.016336380934700887,
      "grad_norm": 0.4971455931663513,
      "learning_rate": 1.2682105263157896e-05,
      "loss": 1.9961,
      "step": 176
    },
    {
      "epoch": 0.016429201280920777,
      "grad_norm": 0.5000568628311157,
      "learning_rate": 1.2153684210526315e-05,
      "loss": 1.9357,
      "step": 177
    },
    {
      "epoch": 0.01652202162714067,
      "grad_norm": 0.5184934139251709,
      "learning_rate": 1.1625263157894737e-05,
      "loss": 1.9728,
      "step": 178
    },
    {
      "epoch": 0.01661484197336056,
      "grad_norm": 0.5139727592468262,
      "learning_rate": 1.1096842105263158e-05,
      "loss": 1.9561,
      "step": 179
    },
    {
      "epoch": 0.01670766231958045,
      "grad_norm": 0.49820300936698914,
      "learning_rate": 1.0568421052631579e-05,
      "loss": 1.9569,
      "step": 180
    },
    {
      "epoch": 0.016800482665800344,
      "grad_norm": 0.5008655190467834,
      "learning_rate": 1.004e-05,
      "loss": 2.0881,
      "step": 181
    },
    {
      "epoch": 0.016893303012020234,
      "grad_norm": 0.5131986737251282,
      "learning_rate": 9.511578947368422e-06,
      "loss": 2.066,
      "step": 182
    },
    {
      "epoch": 0.016986123358240127,
      "grad_norm": 0.5675308108329773,
      "learning_rate": 8.983157894736843e-06,
      "loss": 1.9731,
      "step": 183
    },
    {
      "epoch": 0.017078943704460017,
      "grad_norm": 0.5388391017913818,
      "learning_rate": 8.454736842105263e-06,
      "loss": 2.0149,
      "step": 184
    },
    {
      "epoch": 0.01717176405067991,
      "grad_norm": 0.5240312814712524,
      "learning_rate": 7.926315789473684e-06,
      "loss": 1.8937,
      "step": 185
    },
    {
      "epoch": 0.0172645843968998,
      "grad_norm": 0.5105009078979492,
      "learning_rate": 7.397894736842104e-06,
      "loss": 2.041,
      "step": 186
    },
    {
      "epoch": 0.01735740474311969,
      "grad_norm": 0.5370680689811707,
      "learning_rate": 6.8694736842105265e-06,
      "loss": 2.0445,
      "step": 187
    },
    {
      "epoch": 0.017450225089339584,
      "grad_norm": 0.5596001744270325,
      "learning_rate": 6.341052631578948e-06,
      "loss": 2.1666,
      "step": 188
    },
    {
      "epoch": 0.017543045435559474,
      "grad_norm": 0.5792972445487976,
      "learning_rate": 5.812631578947368e-06,
      "loss": 2.0378,
      "step": 189
    },
    {
      "epoch": 0.017635865781779368,
      "grad_norm": 0.5508564114570618,
      "learning_rate": 5.2842105263157896e-06,
      "loss": 1.968,
      "step": 190
    },
    {
      "epoch": 0.017728686127999257,
      "grad_norm": 0.5679344534873962,
      "learning_rate": 4.755789473684211e-06,
      "loss": 2.0277,
      "step": 191
    },
    {
      "epoch": 0.017821506474219147,
      "grad_norm": 0.529935359954834,
      "learning_rate": 4.227368421052631e-06,
      "loss": 2.0955,
      "step": 192
    },
    {
      "epoch": 0.01791432682043904,
      "grad_norm": 0.6319153904914856,
      "learning_rate": 3.698947368421052e-06,
      "loss": 2.0734,
      "step": 193
    },
    {
      "epoch": 0.01800714716665893,
      "grad_norm": 0.5862286686897278,
      "learning_rate": 3.170526315789474e-06,
      "loss": 2.1698,
      "step": 194
    },
    {
      "epoch": 0.018099967512878824,
      "grad_norm": 0.5513949990272522,
      "learning_rate": 2.6421052631578948e-06,
      "loss": 2.0404,
      "step": 195
    },
    {
      "epoch": 0.018192787859098714,
      "grad_norm": 0.5874564051628113,
      "learning_rate": 2.1136842105263157e-06,
      "loss": 2.0934,
      "step": 196
    },
    {
      "epoch": 0.018285608205318604,
      "grad_norm": 0.6707521677017212,
      "learning_rate": 1.585263157894737e-06,
      "loss": 2.2616,
      "step": 197
    },
    {
      "epoch": 0.018378428551538498,
      "grad_norm": 0.6378986239433289,
      "learning_rate": 1.0568421052631578e-06,
      "loss": 2.0425,
      "step": 198
    },
    {
      "epoch": 0.018471248897758388,
      "grad_norm": 0.7162299156188965,
      "learning_rate": 5.284210526315789e-07,
      "loss": 2.3415,
      "step": 199
    },
    {
      "epoch": 0.01856406924397828,
      "grad_norm": 0.6265064477920532,
      "learning_rate": 0.0,
      "loss": 2.1299,
      "step": 200
    },
    {
      "epoch": 0.01856406924397828,
      "eval_loss": 2.0041327476501465,
      "eval_runtime": 212.1368,
      "eval_samples_per_second": 21.387,
      "eval_steps_per_second": 5.35,
      "step": 200
    }
  ],
  "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": 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": 1.472983354834944e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}