{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.996996996996997,
  "eval_steps": 50,
  "global_step": 998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004004004004004004,
      "grad_norm": 1.060176968574524,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.2427,
      "step": 2
    },
    {
      "epoch": 0.008008008008008008,
      "grad_norm": 1.2065035104751587,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.2909,
      "step": 4
    },
    {
      "epoch": 0.012012012012012012,
      "grad_norm": 1.3198168277740479,
      "learning_rate": 3e-06,
      "loss": 1.2386,
      "step": 6
    },
    {
      "epoch": 0.016016016016016016,
      "grad_norm": 1.1702309846878052,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2236,
      "step": 8
    },
    {
      "epoch": 0.02002002002002002,
      "grad_norm": 1.0895090103149414,
      "learning_rate": 5e-06,
      "loss": 1.2185,
      "step": 10
    },
    {
      "epoch": 0.024024024024024024,
      "grad_norm": 0.8205417394638062,
      "learning_rate": 6e-06,
      "loss": 1.2538,
      "step": 12
    },
    {
      "epoch": 0.028028028028028028,
      "grad_norm": 0.9537830352783203,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.2461,
      "step": 14
    },
    {
      "epoch": 0.03203203203203203,
      "grad_norm": 0.8598117828369141,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2755,
      "step": 16
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 0.5490444302558899,
      "learning_rate": 9e-06,
      "loss": 1.205,
      "step": 18
    },
    {
      "epoch": 0.04004004004004004,
      "grad_norm": 0.3910800814628601,
      "learning_rate": 1e-05,
      "loss": 1.1335,
      "step": 20
    },
    {
      "epoch": 0.044044044044044044,
      "grad_norm": 0.360065758228302,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.1258,
      "step": 22
    },
    {
      "epoch": 0.04804804804804805,
      "grad_norm": 0.36001095175743103,
      "learning_rate": 1.2e-05,
      "loss": 1.1287,
      "step": 24
    },
    {
      "epoch": 0.05205205205205205,
      "grad_norm": 0.3197377026081085,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.1417,
      "step": 26
    },
    {
      "epoch": 0.056056056056056056,
      "grad_norm": 0.31732141971588135,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.1494,
      "step": 28
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 0.30313611030578613,
      "learning_rate": 1.5e-05,
      "loss": 1.07,
      "step": 30
    },
    {
      "epoch": 0.06406406406406406,
      "grad_norm": 0.3234356641769409,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0969,
      "step": 32
    },
    {
      "epoch": 0.06806806806806807,
      "grad_norm": 0.3222120404243469,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 1.1026,
      "step": 34
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.324735164642334,
      "learning_rate": 1.8e-05,
      "loss": 1.1261,
      "step": 36
    },
    {
      "epoch": 0.07607607607607608,
      "grad_norm": 0.2944203317165375,
      "learning_rate": 1.9e-05,
      "loss": 1.1191,
      "step": 38
    },
    {
      "epoch": 0.08008008008008008,
      "grad_norm": 0.290088027715683,
      "learning_rate": 2e-05,
      "loss": 1.0987,
      "step": 40
    },
    {
      "epoch": 0.08408408408408409,
      "grad_norm": 0.32874158024787903,
      "learning_rate": 2.1e-05,
      "loss": 1.0157,
      "step": 42
    },
    {
      "epoch": 0.08808808808808809,
      "grad_norm": 0.2925970256328583,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.0582,
      "step": 44
    },
    {
      "epoch": 0.0920920920920921,
      "grad_norm": 0.3364258408546448,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 1.1005,
      "step": 46
    },
    {
      "epoch": 0.0960960960960961,
      "grad_norm": 0.28330081701278687,
      "learning_rate": 2.4e-05,
      "loss": 1.0767,
      "step": 48
    },
    {
      "epoch": 0.1001001001001001,
      "grad_norm": 0.3321577310562134,
      "learning_rate": 2.5e-05,
      "loss": 1.0742,
      "step": 50
    },
    {
      "epoch": 0.1001001001001001,
      "eval_flock_task4_val_loss": 1.279232382774353,
      "eval_flock_task4_val_runtime": 2.3219,
      "eval_flock_task4_val_samples_per_second": 24.979,
      "eval_flock_task4_val_steps_per_second": 24.979,
      "step": 50
    },
    {
      "epoch": 0.1041041041041041,
      "grad_norm": 0.32319924235343933,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.0973,
      "step": 52
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.29113537073135376,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.0901,
      "step": 54
    },
    {
      "epoch": 0.11211211211211211,
      "grad_norm": 0.28851303458213806,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.0673,
      "step": 56
    },
    {
      "epoch": 0.11611611611611612,
      "grad_norm": 0.28908097743988037,
      "learning_rate": 2.9e-05,
      "loss": 1.0743,
      "step": 58
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 0.35320213437080383,
      "learning_rate": 3e-05,
      "loss": 1.0607,
      "step": 60
    },
    {
      "epoch": 0.12412412412412413,
      "grad_norm": 0.32404547929763794,
      "learning_rate": 3.1e-05,
      "loss": 1.1015,
      "step": 62
    },
    {
      "epoch": 0.12812812812812813,
      "grad_norm": 0.2997118830680847,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.0559,
      "step": 64
    },
    {
      "epoch": 0.13213213213213212,
      "grad_norm": 0.3611145317554474,
      "learning_rate": 3.3e-05,
      "loss": 1.0911,
      "step": 66
    },
    {
      "epoch": 0.13613613613613615,
      "grad_norm": 0.32707688212394714,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.0275,
      "step": 68
    },
    {
      "epoch": 0.14014014014014015,
      "grad_norm": 0.329102098941803,
      "learning_rate": 3.5e-05,
      "loss": 1.0566,
      "step": 70
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.34922876954078674,
      "learning_rate": 3.6e-05,
      "loss": 1.0025,
      "step": 72
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.359674334526062,
      "learning_rate": 3.7e-05,
      "loss": 1.0193,
      "step": 74
    },
    {
      "epoch": 0.15215215215215216,
      "grad_norm": 0.34301552176475525,
      "learning_rate": 3.8e-05,
      "loss": 0.9956,
      "step": 76
    },
    {
      "epoch": 0.15615615615615616,
      "grad_norm": 0.6669041514396667,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 1.0541,
      "step": 78
    },
    {
      "epoch": 0.16016016016016016,
      "grad_norm": 0.3566424548625946,
      "learning_rate": 4e-05,
      "loss": 0.9843,
      "step": 80
    },
    {
      "epoch": 0.16416416416416416,
      "grad_norm": 0.35163360834121704,
      "learning_rate": 4.1e-05,
      "loss": 1.0346,
      "step": 82
    },
    {
      "epoch": 0.16816816816816818,
      "grad_norm": 0.366845041513443,
      "learning_rate": 4.2e-05,
      "loss": 1.0351,
      "step": 84
    },
    {
      "epoch": 0.17217217217217218,
      "grad_norm": 0.32546719908714294,
      "learning_rate": 4.3e-05,
      "loss": 0.9796,
      "step": 86
    },
    {
      "epoch": 0.17617617617617617,
      "grad_norm": 0.3467786908149719,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.0147,
      "step": 88
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 0.32737115025520325,
      "learning_rate": 4.5e-05,
      "loss": 0.9844,
      "step": 90
    },
    {
      "epoch": 0.1841841841841842,
      "grad_norm": 0.3682878911495209,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.0255,
      "step": 92
    },
    {
      "epoch": 0.1881881881881882,
      "grad_norm": 0.31999263167381287,
      "learning_rate": 4.7e-05,
      "loss": 0.9682,
      "step": 94
    },
    {
      "epoch": 0.1921921921921922,
      "grad_norm": 0.3726351857185364,
      "learning_rate": 4.8e-05,
      "loss": 1.0133,
      "step": 96
    },
    {
      "epoch": 0.1961961961961962,
      "grad_norm": 0.3108680248260498,
      "learning_rate": 4.9e-05,
      "loss": 0.9993,
      "step": 98
    },
    {
      "epoch": 0.2002002002002002,
      "grad_norm": 0.3874660134315491,
      "learning_rate": 5e-05,
      "loss": 1.0419,
      "step": 100
    },
    {
      "epoch": 0.2002002002002002,
      "eval_flock_task4_val_loss": 1.2305223941802979,
      "eval_flock_task4_val_runtime": 2.2833,
      "eval_flock_task4_val_samples_per_second": 25.402,
      "eval_flock_task4_val_steps_per_second": 25.402,
      "step": 100
    },
    {
      "epoch": 0.2042042042042042,
      "grad_norm": 0.3987262547016144,
      "learning_rate": 4.999938805089407e-05,
      "loss": 1.0371,
      "step": 102
    },
    {
      "epoch": 0.2082082082082082,
      "grad_norm": 0.37408047914505005,
      "learning_rate": 4.999755223353482e-05,
      "loss": 0.9826,
      "step": 104
    },
    {
      "epoch": 0.2122122122122122,
      "grad_norm": 0.4258411228656769,
      "learning_rate": 4.99944926377964e-05,
      "loss": 0.9828,
      "step": 106
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.3484812378883362,
      "learning_rate": 4.9990209413464136e-05,
      "loss": 0.9749,
      "step": 108
    },
    {
      "epoch": 0.22022022022022023,
      "grad_norm": 0.32916268706321716,
      "learning_rate": 4.9984702770227274e-05,
      "loss": 1.0086,
      "step": 110
    },
    {
      "epoch": 0.22422422422422422,
      "grad_norm": 0.38607460260391235,
      "learning_rate": 4.997797297766864e-05,
      "loss": 1.065,
      "step": 112
    },
    {
      "epoch": 0.22822822822822822,
      "grad_norm": 0.3449179530143738,
      "learning_rate": 4.997002036525148e-05,
      "loss": 1.02,
      "step": 114
    },
    {
      "epoch": 0.23223223223223224,
      "grad_norm": 0.3890361785888672,
      "learning_rate": 4.9960845322303315e-05,
      "loss": 1.015,
      "step": 116
    },
    {
      "epoch": 0.23623623623623624,
      "grad_norm": 0.4259144961833954,
      "learning_rate": 4.995044829799689e-05,
      "loss": 0.9431,
      "step": 118
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 0.3735407292842865,
      "learning_rate": 4.993882980132819e-05,
      "loss": 1.0119,
      "step": 120
    },
    {
      "epoch": 0.24424424424424424,
      "grad_norm": 0.3555149734020233,
      "learning_rate": 4.99259904010915e-05,
      "loss": 0.9911,
      "step": 122
    },
    {
      "epoch": 0.24824824824824826,
      "grad_norm": 0.3151463270187378,
      "learning_rate": 4.9911930725851583e-05,
      "loss": 0.9923,
      "step": 124
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 0.4180292785167694,
      "learning_rate": 4.989665146391289e-05,
      "loss": 1.0518,
      "step": 126
    },
    {
      "epoch": 0.25625625625625625,
      "grad_norm": 0.42882630228996277,
      "learning_rate": 4.988015336328589e-05,
      "loss": 0.9655,
      "step": 128
    },
    {
      "epoch": 0.2602602602602603,
      "grad_norm": 0.3915731608867645,
      "learning_rate": 4.986243723165039e-05,
      "loss": 1.0272,
      "step": 130
    },
    {
      "epoch": 0.26426426426426425,
      "grad_norm": 0.33155953884124756,
      "learning_rate": 4.9843503936316095e-05,
      "loss": 1.0169,
      "step": 132
    },
    {
      "epoch": 0.2682682682682683,
      "grad_norm": 0.35307884216308594,
      "learning_rate": 4.982335440418004e-05,
      "loss": 0.9822,
      "step": 134
    },
    {
      "epoch": 0.2722722722722723,
      "grad_norm": 0.35521459579467773,
      "learning_rate": 4.980198962168128e-05,
      "loss": 0.9748,
      "step": 136
    },
    {
      "epoch": 0.27627627627627627,
      "grad_norm": 0.3592588007450104,
      "learning_rate": 4.977941063475258e-05,
      "loss": 0.9795,
      "step": 138
    },
    {
      "epoch": 0.2802802802802803,
      "grad_norm": 0.36695194244384766,
      "learning_rate": 4.97556185487692e-05,
      "loss": 0.9808,
      "step": 140
    },
    {
      "epoch": 0.28428428428428426,
      "grad_norm": 0.38413292169570923,
      "learning_rate": 4.973061452849481e-05,
      "loss": 0.9791,
      "step": 142
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.36240625381469727,
      "learning_rate": 4.970439979802445e-05,
      "loss": 0.9871,
      "step": 144
    },
    {
      "epoch": 0.2922922922922923,
      "grad_norm": 0.36706650257110596,
      "learning_rate": 4.9676975640724565e-05,
      "loss": 0.9562,
      "step": 146
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.3560505509376526,
      "learning_rate": 4.964834339917025e-05,
      "loss": 1.0059,
      "step": 148
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 0.3984704911708832,
      "learning_rate": 4.961850447507948e-05,
      "loss": 0.9505,
      "step": 150
    },
    {
      "epoch": 0.3003003003003003,
      "eval_flock_task4_val_loss": 1.2094024419784546,
      "eval_flock_task4_val_runtime": 2.2824,
      "eval_flock_task4_val_samples_per_second": 25.412,
      "eval_flock_task4_val_steps_per_second": 25.412,
      "step": 150
    },
    {
      "epoch": 0.30430430430430433,
      "grad_norm": 0.35331350564956665,
      "learning_rate": 4.958746032924448e-05,
      "loss": 1.0262,
      "step": 152
    },
    {
      "epoch": 0.3083083083083083,
      "grad_norm": 0.36896494030952454,
      "learning_rate": 4.955521248146024e-05,
      "loss": 0.9835,
      "step": 154
    },
    {
      "epoch": 0.3123123123123123,
      "grad_norm": 0.3230743706226349,
      "learning_rate": 4.952176251045008e-05,
      "loss": 1.0156,
      "step": 156
    },
    {
      "epoch": 0.3163163163163163,
      "grad_norm": 0.3876803517341614,
      "learning_rate": 4.94871120537884e-05,
      "loss": 0.963,
      "step": 158
    },
    {
      "epoch": 0.3203203203203203,
      "grad_norm": 0.3794425129890442,
      "learning_rate": 4.9451262807820466e-05,
      "loss": 1.0087,
      "step": 160
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.31706008315086365,
      "learning_rate": 4.941421652757941e-05,
      "loss": 0.9365,
      "step": 162
    },
    {
      "epoch": 0.3283283283283283,
      "grad_norm": 0.35730335116386414,
      "learning_rate": 4.937597502670027e-05,
      "loss": 1.0208,
      "step": 164
    },
    {
      "epoch": 0.33233233233233234,
      "grad_norm": 0.3496227562427521,
      "learning_rate": 4.933654017733123e-05,
      "loss": 1.0172,
      "step": 166
    },
    {
      "epoch": 0.33633633633633636,
      "grad_norm": 0.3538665175437927,
      "learning_rate": 4.929591391004196e-05,
      "loss": 0.9329,
      "step": 168
    },
    {
      "epoch": 0.34034034034034033,
      "grad_norm": 0.3327396512031555,
      "learning_rate": 4.925409821372908e-05,
      "loss": 0.9326,
      "step": 170
    },
    {
      "epoch": 0.34434434434434436,
      "grad_norm": 0.3335298001766205,
      "learning_rate": 4.921109513551885e-05,
      "loss": 1.0233,
      "step": 172
    },
    {
      "epoch": 0.3483483483483483,
      "grad_norm": 0.38584664463996887,
      "learning_rate": 4.9166906780666874e-05,
      "loss": 0.9675,
      "step": 174
    },
    {
      "epoch": 0.35235235235235235,
      "grad_norm": 0.30182167887687683,
      "learning_rate": 4.912153531245511e-05,
      "loss": 0.8978,
      "step": 176
    },
    {
      "epoch": 0.3563563563563564,
      "grad_norm": 0.3465532958507538,
      "learning_rate": 4.907498295208589e-05,
      "loss": 0.9589,
      "step": 178
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.3306107223033905,
      "learning_rate": 4.9027251978573244e-05,
      "loss": 0.9715,
      "step": 180
    },
    {
      "epoch": 0.36436436436436437,
      "grad_norm": 0.33348309993743896,
      "learning_rate": 4.8978344728631306e-05,
      "loss": 0.9542,
      "step": 182
    },
    {
      "epoch": 0.3683683683683684,
      "grad_norm": 0.32247722148895264,
      "learning_rate": 4.89282635965599e-05,
      "loss": 0.937,
      "step": 184
    },
    {
      "epoch": 0.37237237237237236,
      "grad_norm": 0.3330734074115753,
      "learning_rate": 4.887701103412734e-05,
      "loss": 0.9882,
      "step": 186
    },
    {
      "epoch": 0.3763763763763764,
      "grad_norm": 0.3942042887210846,
      "learning_rate": 4.8824589550450415e-05,
      "loss": 1.005,
      "step": 188
    },
    {
      "epoch": 0.38038038038038036,
      "grad_norm": 0.3293454349040985,
      "learning_rate": 4.8771001711871534e-05,
      "loss": 0.9591,
      "step": 190
    },
    {
      "epoch": 0.3843843843843844,
      "grad_norm": 0.31077539920806885,
      "learning_rate": 4.8716250141833075e-05,
      "loss": 0.9016,
      "step": 192
    },
    {
      "epoch": 0.3883883883883884,
      "grad_norm": 0.355177104473114,
      "learning_rate": 4.8660337520749e-05,
      "loss": 0.9712,
      "step": 194
    },
    {
      "epoch": 0.3923923923923924,
      "grad_norm": 0.3732739984989166,
      "learning_rate": 4.860326658587358e-05,
      "loss": 0.9971,
      "step": 196
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 0.32691335678100586,
      "learning_rate": 4.8545040131167415e-05,
      "loss": 0.9658,
      "step": 198
    },
    {
      "epoch": 0.4004004004004004,
      "grad_norm": 0.31721362471580505,
      "learning_rate": 4.848566100716066e-05,
      "loss": 0.9486,
      "step": 200
    },
    {
      "epoch": 0.4004004004004004,
      "eval_flock_task4_val_loss": 1.200321078300476,
      "eval_flock_task4_val_runtime": 2.2838,
      "eval_flock_task4_val_samples_per_second": 25.396,
      "eval_flock_task4_val_steps_per_second": 25.396,
      "step": 200
    },
    {
      "epoch": 0.4044044044044044,
      "grad_norm": 0.31772664189338684,
      "learning_rate": 4.8425132120813474e-05,
      "loss": 0.9132,
      "step": 202
    },
    {
      "epoch": 0.4084084084084084,
      "grad_norm": 0.33230283856391907,
      "learning_rate": 4.8363456435373686e-05,
      "loss": 0.932,
      "step": 204
    },
    {
      "epoch": 0.4124124124124124,
      "grad_norm": 0.34045132994651794,
      "learning_rate": 4.830063697023173e-05,
      "loss": 0.958,
      "step": 206
    },
    {
      "epoch": 0.4164164164164164,
      "grad_norm": 0.3456396162509918,
      "learning_rate": 4.8236676800772845e-05,
      "loss": 0.9708,
      "step": 208
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 0.31616365909576416,
      "learning_rate": 4.817157905822652e-05,
      "loss": 0.933,
      "step": 210
    },
    {
      "epoch": 0.4244244244244244,
      "grad_norm": 0.3686939477920532,
      "learning_rate": 4.8105346929513195e-05,
      "loss": 0.937,
      "step": 212
    },
    {
      "epoch": 0.42842842842842843,
      "grad_norm": 0.34076109528541565,
      "learning_rate": 4.803798365708821e-05,
      "loss": 0.929,
      "step": 214
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.3262769877910614,
      "learning_rate": 4.796949253878311e-05,
      "loss": 1.0037,
      "step": 216
    },
    {
      "epoch": 0.4364364364364364,
      "grad_norm": 0.32373276352882385,
      "learning_rate": 4.789987692764419e-05,
      "loss": 0.9531,
      "step": 218
    },
    {
      "epoch": 0.44044044044044045,
      "grad_norm": 0.33934321999549866,
      "learning_rate": 4.7829140231768335e-05,
      "loss": 1.0434,
      "step": 220
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.3485037386417389,
      "learning_rate": 4.775728591413616e-05,
      "loss": 0.9829,
      "step": 222
    },
    {
      "epoch": 0.44844844844844844,
      "grad_norm": 0.32307952642440796,
      "learning_rate": 4.768431749244251e-05,
      "loss": 0.9767,
      "step": 224
    },
    {
      "epoch": 0.45245245245245247,
      "grad_norm": 0.340285986661911,
      "learning_rate": 4.76102385389242e-05,
      "loss": 0.9601,
      "step": 226
    },
    {
      "epoch": 0.45645645645645644,
      "grad_norm": 0.32007983326911926,
      "learning_rate": 4.75350526801852e-05,
      "loss": 0.9489,
      "step": 228
    },
    {
      "epoch": 0.46046046046046046,
      "grad_norm": 0.3099637031555176,
      "learning_rate": 4.7458763597019015e-05,
      "loss": 0.9807,
      "step": 230
    },
    {
      "epoch": 0.4644644644644645,
      "grad_norm": 0.3507792353630066,
      "learning_rate": 4.7381375024228556e-05,
      "loss": 0.9714,
      "step": 232
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 0.34930968284606934,
      "learning_rate": 4.7302890750443256e-05,
      "loss": 0.9243,
      "step": 234
    },
    {
      "epoch": 0.4724724724724725,
      "grad_norm": 0.34382864832878113,
      "learning_rate": 4.7223314617933605e-05,
      "loss": 0.9245,
      "step": 236
    },
    {
      "epoch": 0.47647647647647645,
      "grad_norm": 0.3135361075401306,
      "learning_rate": 4.714265052242306e-05,
      "loss": 0.9382,
      "step": 238
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 0.3600904047489166,
      "learning_rate": 4.7060902412897304e-05,
      "loss": 0.9611,
      "step": 240
    },
    {
      "epoch": 0.4844844844844845,
      "grad_norm": 0.32109400629997253,
      "learning_rate": 4.697807429141094e-05,
      "loss": 0.9217,
      "step": 242
    },
    {
      "epoch": 0.48848848848848847,
      "grad_norm": 0.3754291534423828,
      "learning_rate": 4.689417021289157e-05,
      "loss": 1.0129,
      "step": 244
    },
    {
      "epoch": 0.4924924924924925,
      "grad_norm": 0.3417948782444,
      "learning_rate": 4.6809194284941236e-05,
      "loss": 0.9551,
      "step": 246
    },
    {
      "epoch": 0.4964964964964965,
      "grad_norm": 0.3459557294845581,
      "learning_rate": 4.672315066763542e-05,
      "loss": 0.9363,
      "step": 248
    },
    {
      "epoch": 0.5005005005005005,
      "grad_norm": 0.3685155212879181,
      "learning_rate": 4.6636043573319275e-05,
      "loss": 0.9385,
      "step": 250
    },
    {
      "epoch": 0.5005005005005005,
      "eval_flock_task4_val_loss": 1.1836485862731934,
      "eval_flock_task4_val_runtime": 2.2789,
      "eval_flock_task4_val_samples_per_second": 25.451,
      "eval_flock_task4_val_steps_per_second": 25.451,
      "step": 250
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.3467947542667389,
      "learning_rate": 4.65478772664015e-05,
      "loss": 0.9636,
      "step": 252
    },
    {
      "epoch": 0.5085085085085085,
      "grad_norm": 0.340094655752182,
      "learning_rate": 4.6458656063145475e-05,
      "loss": 0.9531,
      "step": 254
    },
    {
      "epoch": 0.5125125125125125,
      "grad_norm": 0.29998838901519775,
      "learning_rate": 4.6368384331458085e-05,
      "loss": 0.9295,
      "step": 256
    },
    {
      "epoch": 0.5165165165165165,
      "grad_norm": 0.3876248002052307,
      "learning_rate": 4.627706649067575e-05,
      "loss": 0.8926,
      "step": 258
    },
    {
      "epoch": 0.5205205205205206,
      "grad_norm": 0.3211461007595062,
      "learning_rate": 4.618470701134815e-05,
      "loss": 0.8939,
      "step": 260
    },
    {
      "epoch": 0.5245245245245245,
      "grad_norm": 0.31540125608444214,
      "learning_rate": 4.609131041501935e-05,
      "loss": 0.9418,
      "step": 262
    },
    {
      "epoch": 0.5285285285285285,
      "grad_norm": 0.3534470200538635,
      "learning_rate": 4.5996881274006446e-05,
      "loss": 0.9571,
      "step": 264
    },
    {
      "epoch": 0.5325325325325325,
      "grad_norm": 0.369412362575531,
      "learning_rate": 4.5901424211175715e-05,
      "loss": 0.9212,
      "step": 266
    },
    {
      "epoch": 0.5365365365365365,
      "grad_norm": 0.3699535131454468,
      "learning_rate": 4.580494389971628e-05,
      "loss": 0.9377,
      "step": 268
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.33457526564598083,
      "learning_rate": 4.570744506291138e-05,
      "loss": 0.9492,
      "step": 270
    },
    {
      "epoch": 0.5445445445445446,
      "grad_norm": 0.37723392248153687,
      "learning_rate": 4.56089324739071e-05,
      "loss": 0.9433,
      "step": 272
    },
    {
      "epoch": 0.5485485485485485,
      "grad_norm": 0.3375968039035797,
      "learning_rate": 4.5509410955478686e-05,
      "loss": 0.9699,
      "step": 274
    },
    {
      "epoch": 0.5525525525525525,
      "grad_norm": 0.36604395508766174,
      "learning_rate": 4.5408885379794494e-05,
      "loss": 0.8939,
      "step": 276
    },
    {
      "epoch": 0.5565565565565566,
      "grad_norm": 0.33874592185020447,
      "learning_rate": 4.5307360668177404e-05,
      "loss": 0.9053,
      "step": 278
    },
    {
      "epoch": 0.5605605605605606,
      "grad_norm": 0.3532886505126953,
      "learning_rate": 4.520484179086394e-05,
      "loss": 0.9273,
      "step": 280
    },
    {
      "epoch": 0.5645645645645646,
      "grad_norm": 0.3623044788837433,
      "learning_rate": 4.510133376676092e-05,
      "loss": 0.9356,
      "step": 282
    },
    {
      "epoch": 0.5685685685685685,
      "grad_norm": 0.31736573576927185,
      "learning_rate": 4.499684166319978e-05,
      "loss": 0.9171,
      "step": 284
    },
    {
      "epoch": 0.5725725725725725,
      "grad_norm": 0.335746705532074,
      "learning_rate": 4.489137059568847e-05,
      "loss": 0.9482,
      "step": 286
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.37591829895973206,
      "learning_rate": 4.478492572766102e-05,
      "loss": 0.9614,
      "step": 288
    },
    {
      "epoch": 0.5805805805805806,
      "grad_norm": 0.32530349493026733,
      "learning_rate": 4.4677512270224774e-05,
      "loss": 0.9871,
      "step": 290
    },
    {
      "epoch": 0.5845845845845846,
      "grad_norm": 0.36305058002471924,
      "learning_rate": 4.456913548190527e-05,
      "loss": 0.9783,
      "step": 292
    },
    {
      "epoch": 0.5885885885885885,
      "grad_norm": 0.34992191195487976,
      "learning_rate": 4.445980066838882e-05,
      "loss": 0.9204,
      "step": 294
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.357051819562912,
      "learning_rate": 4.4349513182262715e-05,
      "loss": 0.9342,
      "step": 296
    },
    {
      "epoch": 0.5965965965965966,
      "grad_norm": 0.6614818572998047,
      "learning_rate": 4.423827842275325e-05,
      "loss": 0.9105,
      "step": 298
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.3560963273048401,
      "learning_rate": 4.4126101835461346e-05,
      "loss": 0.9392,
      "step": 300
    },
    {
      "epoch": 0.6006006006006006,
      "eval_flock_task4_val_loss": 1.1696926355361938,
      "eval_flock_task4_val_runtime": 2.2897,
      "eval_flock_task4_val_samples_per_second": 25.331,
      "eval_flock_task4_val_steps_per_second": 25.331,
      "step": 300
    },
    {
      "epoch": 0.6046046046046046,
      "grad_norm": 0.35408785939216614,
      "learning_rate": 4.4012988912095995e-05,
      "loss": 0.9848,
      "step": 302
    },
    {
      "epoch": 0.6086086086086087,
      "grad_norm": 0.3559267520904541,
      "learning_rate": 4.3898945190205386e-05,
      "loss": 0.9635,
      "step": 304
    },
    {
      "epoch": 0.6126126126126126,
      "grad_norm": 0.3476458489894867,
      "learning_rate": 4.3783976252905804e-05,
      "loss": 0.9699,
      "step": 306
    },
    {
      "epoch": 0.6166166166166166,
      "grad_norm": 0.3224807381629944,
      "learning_rate": 4.3668087728608316e-05,
      "loss": 0.9391,
      "step": 308
    },
    {
      "epoch": 0.6206206206206206,
      "grad_norm": 0.3327246606349945,
      "learning_rate": 4.355128529074323e-05,
      "loss": 0.9049,
      "step": 310
    },
    {
      "epoch": 0.6246246246246246,
      "grad_norm": 0.3456214666366577,
      "learning_rate": 4.343357465748235e-05,
      "loss": 0.9336,
      "step": 312
    },
    {
      "epoch": 0.6286286286286287,
      "grad_norm": 0.36309632658958435,
      "learning_rate": 4.331496159145901e-05,
      "loss": 0.9568,
      "step": 314
    },
    {
      "epoch": 0.6326326326326326,
      "grad_norm": 0.31426164507865906,
      "learning_rate": 4.3195451899485994e-05,
      "loss": 0.9634,
      "step": 316
    },
    {
      "epoch": 0.6366366366366366,
      "grad_norm": 0.29084381461143494,
      "learning_rate": 4.307505143227122e-05,
      "loss": 0.9351,
      "step": 318
    },
    {
      "epoch": 0.6406406406406406,
      "grad_norm": 0.3159138560295105,
      "learning_rate": 4.295376608413137e-05,
      "loss": 0.9604,
      "step": 320
    },
    {
      "epoch": 0.6446446446446447,
      "grad_norm": 0.33817973732948303,
      "learning_rate": 4.2831601792703245e-05,
      "loss": 0.9504,
      "step": 322
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.3421194553375244,
      "learning_rate": 4.270856453865318e-05,
      "loss": 0.9784,
      "step": 324
    },
    {
      "epoch": 0.6526526526526526,
      "grad_norm": 0.3762097656726837,
      "learning_rate": 4.258466034538417e-05,
      "loss": 0.9177,
      "step": 326
    },
    {
      "epoch": 0.6566566566566566,
      "grad_norm": 0.3637877106666565,
      "learning_rate": 4.245989527874107e-05,
      "loss": 0.9737,
      "step": 328
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 0.399688184261322,
      "learning_rate": 4.233427544671351e-05,
      "loss": 0.9587,
      "step": 330
    },
    {
      "epoch": 0.6646646646646647,
      "grad_norm": 0.3639969527721405,
      "learning_rate": 4.2207806999137035e-05,
      "loss": 0.9308,
      "step": 332
    },
    {
      "epoch": 0.6686686686686687,
      "grad_norm": 0.390143483877182,
      "learning_rate": 4.208049612739192e-05,
      "loss": 0.9002,
      "step": 334
    },
    {
      "epoch": 0.6726726726726727,
      "grad_norm": 0.36150315403938293,
      "learning_rate": 4.1952349064100074e-05,
      "loss": 0.9214,
      "step": 336
    },
    {
      "epoch": 0.6766766766766766,
      "grad_norm": 0.36743301153182983,
      "learning_rate": 4.1823372082819975e-05,
      "loss": 0.9446,
      "step": 338
    },
    {
      "epoch": 0.6806806806806807,
      "grad_norm": 0.34222760796546936,
      "learning_rate": 4.1693571497739495e-05,
      "loss": 0.9083,
      "step": 340
    },
    {
      "epoch": 0.6846846846846847,
      "grad_norm": 0.31091299653053284,
      "learning_rate": 4.156295366336679e-05,
      "loss": 0.9626,
      "step": 342
    },
    {
      "epoch": 0.6886886886886887,
      "grad_norm": 0.3398517966270447,
      "learning_rate": 4.143152497421922e-05,
      "loss": 0.8785,
      "step": 344
    },
    {
      "epoch": 0.6926926926926927,
      "grad_norm": 0.3354012370109558,
      "learning_rate": 4.129929186451028e-05,
      "loss": 0.9608,
      "step": 346
    },
    {
      "epoch": 0.6966966966966966,
      "grad_norm": 0.3858669102191925,
      "learning_rate": 4.1166260807834644e-05,
      "loss": 0.9665,
      "step": 348
    },
    {
      "epoch": 0.7007007007007007,
      "grad_norm": 0.35795554518699646,
      "learning_rate": 4.103243831685121e-05,
      "loss": 0.9277,
      "step": 350
    },
    {
      "epoch": 0.7007007007007007,
      "eval_flock_task4_val_loss": 1.1536976099014282,
      "eval_flock_task4_val_runtime": 2.2912,
      "eval_flock_task4_val_samples_per_second": 25.314,
      "eval_flock_task4_val_steps_per_second": 25.314,
      "step": 350
    },
    {
      "epoch": 0.7047047047047047,
      "grad_norm": 0.3871535062789917,
      "learning_rate": 4.0897830942964255e-05,
      "loss": 0.9379,
      "step": 352
    },
    {
      "epoch": 0.7087087087087087,
      "grad_norm": 0.3559763431549072,
      "learning_rate": 4.076244527600276e-05,
      "loss": 0.9377,
      "step": 354
    },
    {
      "epoch": 0.7127127127127127,
      "grad_norm": 0.3114367425441742,
      "learning_rate": 4.0626287943897764e-05,
      "loss": 0.8784,
      "step": 356
    },
    {
      "epoch": 0.7167167167167167,
      "grad_norm": 0.3529565930366516,
      "learning_rate": 4.048936561235786e-05,
      "loss": 0.953,
      "step": 358
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.33330368995666504,
      "learning_rate": 4.035168498454292e-05,
      "loss": 0.9587,
      "step": 360
    },
    {
      "epoch": 0.7247247247247247,
      "grad_norm": 0.418038934469223,
      "learning_rate": 4.021325280073592e-05,
      "loss": 0.9108,
      "step": 362
    },
    {
      "epoch": 0.7287287287287287,
      "grad_norm": 0.373203307390213,
      "learning_rate": 4.007407583801295e-05,
      "loss": 0.9772,
      "step": 364
    },
    {
      "epoch": 0.7327327327327328,
      "grad_norm": 0.31042730808258057,
      "learning_rate": 3.9934160909911434e-05,
      "loss": 0.9174,
      "step": 366
    },
    {
      "epoch": 0.7367367367367368,
      "grad_norm": 0.3332262635231018,
      "learning_rate": 3.979351486609658e-05,
      "loss": 0.9127,
      "step": 368
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.32328566908836365,
      "learning_rate": 3.965214459202607e-05,
      "loss": 0.9197,
      "step": 370
    },
    {
      "epoch": 0.7447447447447447,
      "grad_norm": 0.3616783022880554,
      "learning_rate": 3.951005700861291e-05,
      "loss": 0.9017,
      "step": 372
    },
    {
      "epoch": 0.7487487487487487,
      "grad_norm": 0.4132612645626068,
      "learning_rate": 3.936725907188668e-05,
      "loss": 0.9353,
      "step": 374
    },
    {
      "epoch": 0.7527527527527528,
      "grad_norm": 0.34235623478889465,
      "learning_rate": 3.9223757772652956e-05,
      "loss": 0.9438,
      "step": 376
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.3544083833694458,
      "learning_rate": 3.9079560136151075e-05,
      "loss": 0.9663,
      "step": 378
    },
    {
      "epoch": 0.7607607607607607,
      "grad_norm": 0.37442663311958313,
      "learning_rate": 3.8934673221710215e-05,
      "loss": 0.9043,
      "step": 380
    },
    {
      "epoch": 0.7647647647647647,
      "grad_norm": 0.38071951270103455,
      "learning_rate": 3.878910412240381e-05,
      "loss": 0.9556,
      "step": 382
    },
    {
      "epoch": 0.7687687687687688,
      "grad_norm": 0.33478865027427673,
      "learning_rate": 3.864285996470226e-05,
      "loss": 0.8984,
      "step": 384
    },
    {
      "epoch": 0.7727727727727728,
      "grad_norm": 0.37500250339508057,
      "learning_rate": 3.8495947908124094e-05,
      "loss": 0.8947,
      "step": 386
    },
    {
      "epoch": 0.7767767767767768,
      "grad_norm": 0.3144890069961548,
      "learning_rate": 3.834837514488544e-05,
      "loss": 0.928,
      "step": 388
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 0.3349425494670868,
      "learning_rate": 3.8200148899547945e-05,
      "loss": 0.9221,
      "step": 390
    },
    {
      "epoch": 0.7847847847847848,
      "grad_norm": 0.4010365605354309,
      "learning_rate": 3.805127642866507e-05,
      "loss": 0.9071,
      "step": 392
    },
    {
      "epoch": 0.7887887887887888,
      "grad_norm": 0.4623183310031891,
      "learning_rate": 3.790176502042686e-05,
      "loss": 0.9169,
      "step": 394
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.35621941089630127,
      "learning_rate": 3.775162199430312e-05,
      "loss": 0.928,
      "step": 396
    },
    {
      "epoch": 0.7967967967967968,
      "grad_norm": 0.33506807684898376,
      "learning_rate": 3.76008547006851e-05,
      "loss": 0.8739,
      "step": 398
    },
    {
      "epoch": 0.8008008008008008,
      "grad_norm": 0.4462102949619293,
      "learning_rate": 3.744947052052562e-05,
      "loss": 0.8549,
      "step": 400
    },
    {
      "epoch": 0.8008008008008008,
      "eval_flock_task4_val_loss": 1.1560972929000854,
      "eval_flock_task4_val_runtime": 2.3054,
      "eval_flock_task4_val_samples_per_second": 25.159,
      "eval_flock_task4_val_steps_per_second": 25.159,
      "step": 400
    },
    {
      "epoch": 0.8048048048048048,
      "grad_norm": 0.39696791768074036,
      "learning_rate": 3.72974768649778e-05,
      "loss": 0.9826,
      "step": 402
    },
    {
      "epoch": 0.8088088088088088,
      "grad_norm": 0.33046942949295044,
      "learning_rate": 3.7144881175032174e-05,
      "loss": 0.9925,
      "step": 404
    },
    {
      "epoch": 0.8128128128128128,
      "grad_norm": 0.40008458495140076,
      "learning_rate": 3.69916909211524e-05,
      "loss": 0.8818,
      "step": 406
    },
    {
      "epoch": 0.8168168168168168,
      "grad_norm": 0.3182609975337982,
      "learning_rate": 3.683791360290961e-05,
      "loss": 0.9055,
      "step": 408
    },
    {
      "epoch": 0.8208208208208209,
      "grad_norm": 0.3375478684902191,
      "learning_rate": 3.6683556748615195e-05,
      "loss": 0.9267,
      "step": 410
    },
    {
      "epoch": 0.8248248248248248,
      "grad_norm": 0.35459277033805847,
      "learning_rate": 3.6528627914952266e-05,
      "loss": 0.954,
      "step": 412
    },
    {
      "epoch": 0.8288288288288288,
      "grad_norm": 0.31690555810928345,
      "learning_rate": 3.637313468660572e-05,
      "loss": 0.9145,
      "step": 414
    },
    {
      "epoch": 0.8328328328328328,
      "grad_norm": 0.35816216468811035,
      "learning_rate": 3.6217084675890935e-05,
      "loss": 0.879,
      "step": 416
    },
    {
      "epoch": 0.8368368368368369,
      "grad_norm": 0.36077073216438293,
      "learning_rate": 3.6060485522381065e-05,
      "loss": 0.9376,
      "step": 418
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.35410434007644653,
      "learning_rate": 3.590334489253306e-05,
      "loss": 0.9169,
      "step": 420
    },
    {
      "epoch": 0.8448448448448449,
      "grad_norm": 0.3886237144470215,
      "learning_rate": 3.5745670479312374e-05,
      "loss": 0.8846,
      "step": 422
    },
    {
      "epoch": 0.8488488488488488,
      "grad_norm": 0.33457881212234497,
      "learning_rate": 3.55874700018163e-05,
      "loss": 0.922,
      "step": 424
    },
    {
      "epoch": 0.8528528528528528,
      "grad_norm": 0.3439764082431793,
      "learning_rate": 3.5428751204896085e-05,
      "loss": 0.9225,
      "step": 426
    },
    {
      "epoch": 0.8568568568568569,
      "grad_norm": 0.3794129192829132,
      "learning_rate": 3.526952185877781e-05,
      "loss": 0.9177,
      "step": 428
    },
    {
      "epoch": 0.8608608608608609,
      "grad_norm": 0.36088061332702637,
      "learning_rate": 3.5109789758681946e-05,
      "loss": 0.9212,
      "step": 430
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.40673118829727173,
      "learning_rate": 3.494956272444177e-05,
      "loss": 0.9235,
      "step": 432
    },
    {
      "epoch": 0.8688688688688688,
      "grad_norm": 0.3603825271129608,
      "learning_rate": 3.4788848600120505e-05,
      "loss": 0.919,
      "step": 434
    },
    {
      "epoch": 0.8728728728728729,
      "grad_norm": 0.3395703136920929,
      "learning_rate": 3.4627655253627323e-05,
      "loss": 0.8724,
      "step": 436
    },
    {
      "epoch": 0.8768768768768769,
      "grad_norm": 0.3341948390007019,
      "learning_rate": 3.446599057633217e-05,
      "loss": 0.9189,
      "step": 438
    },
    {
      "epoch": 0.8808808808808809,
      "grad_norm": 0.342174768447876,
      "learning_rate": 3.430386248267943e-05,
      "loss": 0.9327,
      "step": 440
    },
    {
      "epoch": 0.8848848848848849,
      "grad_norm": 0.35033905506134033,
      "learning_rate": 3.4141278909800444e-05,
      "loss": 0.9197,
      "step": 442
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3870660960674286,
      "learning_rate": 3.397824781712499e-05,
      "loss": 0.863,
      "step": 444
    },
    {
      "epoch": 0.8928928928928929,
      "grad_norm": 0.3849852383136749,
      "learning_rate": 3.381477718599157e-05,
      "loss": 0.8746,
      "step": 446
    },
    {
      "epoch": 0.8968968968968969,
      "grad_norm": 0.3900209963321686,
      "learning_rate": 3.365087501925673e-05,
      "loss": 0.9194,
      "step": 448
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 0.36199262738227844,
      "learning_rate": 3.3486549340903195e-05,
      "loss": 0.886,
      "step": 450
    },
    {
      "epoch": 0.9009009009009009,
      "eval_flock_task4_val_loss": 1.151094913482666,
      "eval_flock_task4_val_runtime": 2.4214,
      "eval_flock_task4_val_samples_per_second": 23.953,
      "eval_flock_task4_val_steps_per_second": 23.953,
      "step": 450
    },
    {
      "epoch": 0.9049049049049049,
      "grad_norm": 0.33788204193115234,
      "learning_rate": 3.332180819564714e-05,
      "loss": 0.9225,
      "step": 452
    },
    {
      "epoch": 0.908908908908909,
      "grad_norm": 0.3792935311794281,
      "learning_rate": 3.3156659648544276e-05,
      "loss": 0.9141,
      "step": 454
    },
    {
      "epoch": 0.9129129129129129,
      "grad_norm": 0.33289849758148193,
      "learning_rate": 3.299111178459507e-05,
      "loss": 0.9296,
      "step": 456
    },
    {
      "epoch": 0.9169169169169169,
      "grad_norm": 0.35779908299446106,
      "learning_rate": 3.282517270834891e-05,
      "loss": 0.8576,
      "step": 458
    },
    {
      "epoch": 0.9209209209209209,
      "grad_norm": 0.38421431183815,
      "learning_rate": 3.2658850543507334e-05,
      "loss": 0.9252,
      "step": 460
    },
    {
      "epoch": 0.924924924924925,
      "grad_norm": 0.4044077396392822,
      "learning_rate": 3.2492153432526355e-05,
      "loss": 0.8938,
      "step": 462
    },
    {
      "epoch": 0.928928928928929,
      "grad_norm": 0.4189876616001129,
      "learning_rate": 3.2325089536217815e-05,
      "loss": 0.938,
      "step": 464
    },
    {
      "epoch": 0.9329329329329329,
      "grad_norm": 0.33194634318351746,
      "learning_rate": 3.215766703334988e-05,
      "loss": 0.8809,
      "step": 466
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.3266729712486267,
      "learning_rate": 3.1989894120246614e-05,
      "loss": 0.9338,
      "step": 468
    },
    {
      "epoch": 0.9409409409409409,
      "grad_norm": 0.3905945122241974,
      "learning_rate": 3.1821779010386755e-05,
      "loss": 0.9709,
      "step": 470
    },
    {
      "epoch": 0.944944944944945,
      "grad_norm": 0.3806445598602295,
      "learning_rate": 3.1653329934001584e-05,
      "loss": 0.9232,
      "step": 472
    },
    {
      "epoch": 0.948948948948949,
      "grad_norm": 0.34493544697761536,
      "learning_rate": 3.148455513767206e-05,
      "loss": 0.9446,
      "step": 474
    },
    {
      "epoch": 0.9529529529529529,
      "grad_norm": 0.34965747594833374,
      "learning_rate": 3.1315462883925025e-05,
      "loss": 0.932,
      "step": 476
    },
    {
      "epoch": 0.9569569569569569,
      "grad_norm": 0.34367701411247253,
      "learning_rate": 3.114606145082876e-05,
      "loss": 0.9061,
      "step": 478
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.36689406633377075,
      "learning_rate": 3.097635913158772e-05,
      "loss": 0.8817,
      "step": 480
    },
    {
      "epoch": 0.964964964964965,
      "grad_norm": 0.34466394782066345,
      "learning_rate": 3.080636423413649e-05,
      "loss": 0.9088,
      "step": 482
    },
    {
      "epoch": 0.968968968968969,
      "grad_norm": 0.3059948980808258,
      "learning_rate": 3.063608508073311e-05,
      "loss": 0.957,
      "step": 484
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.3226034641265869,
      "learning_rate": 3.0465530007551645e-05,
      "loss": 0.8844,
      "step": 486
    },
    {
      "epoch": 0.9769769769769769,
      "grad_norm": 0.3674728274345398,
      "learning_rate": 3.0294707364274067e-05,
      "loss": 0.9126,
      "step": 488
    },
    {
      "epoch": 0.980980980980981,
      "grad_norm": 0.3241788148880005,
      "learning_rate": 3.0123625513681463e-05,
      "loss": 0.8676,
      "step": 490
    },
    {
      "epoch": 0.984984984984985,
      "grad_norm": 0.3742011487483978,
      "learning_rate": 2.9952292831244676e-05,
      "loss": 0.9293,
      "step": 492
    },
    {
      "epoch": 0.988988988988989,
      "grad_norm": 0.4942300617694855,
      "learning_rate": 2.9780717704714266e-05,
      "loss": 0.9426,
      "step": 494
    },
    {
      "epoch": 0.992992992992993,
      "grad_norm": 0.34072035551071167,
      "learning_rate": 2.960890853370985e-05,
      "loss": 0.9089,
      "step": 496
    },
    {
      "epoch": 0.996996996996997,
      "grad_norm": 0.47447457909584045,
      "learning_rate": 2.9436873729308912e-05,
      "loss": 0.8594,
      "step": 498
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5046526193618774,
      "learning_rate": 2.9264621713635028e-05,
      "loss": 0.6843,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_flock_task4_val_loss": 1.1507720947265625,
      "eval_flock_task4_val_runtime": 2.3966,
      "eval_flock_task4_val_samples_per_second": 24.201,
      "eval_flock_task4_val_steps_per_second": 24.201,
      "step": 500
    },
    {
      "epoch": 1.004004004004004,
      "grad_norm": 0.36078399419784546,
      "learning_rate": 2.9092160919445567e-05,
      "loss": 0.8636,
      "step": 502
    },
    {
      "epoch": 1.008008008008008,
      "grad_norm": 0.3482002317905426,
      "learning_rate": 2.891949978971883e-05,
      "loss": 0.8479,
      "step": 504
    },
    {
      "epoch": 1.012012012012012,
      "grad_norm": 0.3719685673713684,
      "learning_rate": 2.874664677724072e-05,
      "loss": 0.8854,
      "step": 506
    },
    {
      "epoch": 1.016016016016016,
      "grad_norm": 0.3359503746032715,
      "learning_rate": 2.8573610344190975e-05,
      "loss": 0.8757,
      "step": 508
    },
    {
      "epoch": 1.02002002002002,
      "grad_norm": 0.5480461120605469,
      "learning_rate": 2.840039896172882e-05,
      "loss": 0.8581,
      "step": 510
    },
    {
      "epoch": 1.024024024024024,
      "grad_norm": 0.3680349588394165,
      "learning_rate": 2.822702110957831e-05,
      "loss": 0.9137,
      "step": 512
    },
    {
      "epoch": 1.028028028028028,
      "grad_norm": 0.3575070798397064,
      "learning_rate": 2.8053485275613178e-05,
      "loss": 0.8918,
      "step": 514
    },
    {
      "epoch": 1.032032032032032,
      "grad_norm": 0.4439910650253296,
      "learning_rate": 2.78797999554413e-05,
      "loss": 0.8673,
      "step": 516
    },
    {
      "epoch": 1.0360360360360361,
      "grad_norm": 0.40003103017807007,
      "learning_rate": 2.7705973651988776e-05,
      "loss": 0.8849,
      "step": 518
    },
    {
      "epoch": 1.04004004004004,
      "grad_norm": 0.38889795541763306,
      "learning_rate": 2.753201487508369e-05,
      "loss": 0.8631,
      "step": 520
    },
    {
      "epoch": 1.044044044044044,
      "grad_norm": 0.37320345640182495,
      "learning_rate": 2.7357932141039495e-05,
      "loss": 0.9151,
      "step": 522
    },
    {
      "epoch": 1.048048048048048,
      "grad_norm": 0.34984591603279114,
      "learning_rate": 2.718373397223804e-05,
      "loss": 0.8854,
      "step": 524
    },
    {
      "epoch": 1.052052052052052,
      "grad_norm": 0.3709803819656372,
      "learning_rate": 2.7009428896712442e-05,
      "loss": 0.889,
      "step": 526
    },
    {
      "epoch": 1.0560560560560561,
      "grad_norm": 0.4115319848060608,
      "learning_rate": 2.6835025447729495e-05,
      "loss": 0.9024,
      "step": 528
    },
    {
      "epoch": 1.06006006006006,
      "grad_norm": 0.3313678503036499,
      "learning_rate": 2.6660532163371992e-05,
      "loss": 0.8515,
      "step": 530
    },
    {
      "epoch": 1.064064064064064,
      "grad_norm": 0.3881412744522095,
      "learning_rate": 2.6485957586120663e-05,
      "loss": 0.8723,
      "step": 532
    },
    {
      "epoch": 1.068068068068068,
      "grad_norm": 0.4042016267776489,
      "learning_rate": 2.6311310262436036e-05,
      "loss": 0.8583,
      "step": 534
    },
    {
      "epoch": 1.072072072072072,
      "grad_norm": 0.37638312578201294,
      "learning_rate": 2.613659874233999e-05,
      "loss": 0.8764,
      "step": 536
    },
    {
      "epoch": 1.0760760760760761,
      "grad_norm": 0.3946394920349121,
      "learning_rate": 2.5961831578997215e-05,
      "loss": 0.89,
      "step": 538
    },
    {
      "epoch": 1.08008008008008,
      "grad_norm": 0.37551435828208923,
      "learning_rate": 2.5787017328296447e-05,
      "loss": 0.8913,
      "step": 540
    },
    {
      "epoch": 1.0840840840840842,
      "grad_norm": 0.4114207923412323,
      "learning_rate": 2.561216454843165e-05,
      "loss": 0.8973,
      "step": 542
    },
    {
      "epoch": 1.088088088088088,
      "grad_norm": 0.36333537101745605,
      "learning_rate": 2.5437281799483004e-05,
      "loss": 0.8764,
      "step": 544
    },
    {
      "epoch": 1.092092092092092,
      "grad_norm": 0.4394896328449249,
      "learning_rate": 2.526237764299786e-05,
      "loss": 0.93,
      "step": 546
    },
    {
      "epoch": 1.0960960960960962,
      "grad_norm": 0.37381502985954285,
      "learning_rate": 2.508746064157159e-05,
      "loss": 0.8433,
      "step": 548
    },
    {
      "epoch": 1.1001001001001,
      "grad_norm": 0.3822025656700134,
      "learning_rate": 2.4912539358428415e-05,
      "loss": 0.877,
      "step": 550
    },
    {
      "epoch": 1.1001001001001,
      "eval_flock_task4_val_loss": 1.1475247144699097,
      "eval_flock_task4_val_runtime": 2.41,
      "eval_flock_task4_val_samples_per_second": 24.067,
      "eval_flock_task4_val_steps_per_second": 24.067,
      "step": 550
    },
    {
      "epoch": 1.1041041041041042,
      "grad_norm": 0.49058809876441956,
      "learning_rate": 2.473762235700214e-05,
      "loss": 0.8725,
      "step": 552
    },
    {
      "epoch": 1.1081081081081081,
      "grad_norm": 0.3926384150981903,
      "learning_rate": 2.4562718200517002e-05,
      "loss": 0.8599,
      "step": 554
    },
    {
      "epoch": 1.112112112112112,
      "grad_norm": 0.39552003145217896,
      "learning_rate": 2.4387835451568355e-05,
      "loss": 0.8659,
      "step": 556
    },
    {
      "epoch": 1.1161161161161162,
      "grad_norm": 0.4861438274383545,
      "learning_rate": 2.421298267170356e-05,
      "loss": 0.8898,
      "step": 558
    },
    {
      "epoch": 1.12012012012012,
      "grad_norm": 0.418471097946167,
      "learning_rate": 2.4038168421002794e-05,
      "loss": 0.8401,
      "step": 560
    },
    {
      "epoch": 1.1241241241241242,
      "grad_norm": 0.3635142743587494,
      "learning_rate": 2.3863401257660018e-05,
      "loss": 0.8742,
      "step": 562
    },
    {
      "epoch": 1.1281281281281281,
      "grad_norm": 0.3907809257507324,
      "learning_rate": 2.3688689737563967e-05,
      "loss": 0.8774,
      "step": 564
    },
    {
      "epoch": 1.132132132132132,
      "grad_norm": 0.3826066553592682,
      "learning_rate": 2.3514042413879343e-05,
      "loss": 0.9037,
      "step": 566
    },
    {
      "epoch": 1.1361361361361362,
      "grad_norm": 0.36759504675865173,
      "learning_rate": 2.3339467836628017e-05,
      "loss": 0.8573,
      "step": 568
    },
    {
      "epoch": 1.14014014014014,
      "grad_norm": 0.3731608986854553,
      "learning_rate": 2.31649745522705e-05,
      "loss": 0.9056,
      "step": 570
    },
    {
      "epoch": 1.1441441441441442,
      "grad_norm": 0.42503395676612854,
      "learning_rate": 2.2990571103287567e-05,
      "loss": 0.8685,
      "step": 572
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 0.43720346689224243,
      "learning_rate": 2.2816266027761966e-05,
      "loss": 0.883,
      "step": 574
    },
    {
      "epoch": 1.1521521521521523,
      "grad_norm": 0.38943639397621155,
      "learning_rate": 2.2642067858960514e-05,
      "loss": 0.8981,
      "step": 576
    },
    {
      "epoch": 1.1561561561561562,
      "grad_norm": 0.43230053782463074,
      "learning_rate": 2.2467985124916314e-05,
      "loss": 0.8593,
      "step": 578
    },
    {
      "epoch": 1.16016016016016,
      "grad_norm": 0.4695190489292145,
      "learning_rate": 2.2294026348011223e-05,
      "loss": 0.8724,
      "step": 580
    },
    {
      "epoch": 1.1641641641641642,
      "grad_norm": 0.39060747623443604,
      "learning_rate": 2.2120200044558706e-05,
      "loss": 0.9046,
      "step": 582
    },
    {
      "epoch": 1.1681681681681682,
      "grad_norm": 0.3812834620475769,
      "learning_rate": 2.1946514724386828e-05,
      "loss": 0.8368,
      "step": 584
    },
    {
      "epoch": 1.1721721721721723,
      "grad_norm": 0.4360229969024658,
      "learning_rate": 2.1772978890421688e-05,
      "loss": 0.8587,
      "step": 586
    },
    {
      "epoch": 1.1761761761761762,
      "grad_norm": 0.4518442749977112,
      "learning_rate": 2.1599601038271186e-05,
      "loss": 0.8776,
      "step": 588
    },
    {
      "epoch": 1.1801801801801801,
      "grad_norm": 0.4748334586620331,
      "learning_rate": 2.142638965580903e-05,
      "loss": 0.8933,
      "step": 590
    },
    {
      "epoch": 1.1841841841841843,
      "grad_norm": 0.4352450966835022,
      "learning_rate": 2.125335322275928e-05,
      "loss": 0.8511,
      "step": 592
    },
    {
      "epoch": 1.1881881881881882,
      "grad_norm": 0.4232271611690521,
      "learning_rate": 2.108050021028118e-05,
      "loss": 0.8153,
      "step": 594
    },
    {
      "epoch": 1.1921921921921923,
      "grad_norm": 0.3999643325805664,
      "learning_rate": 2.0907839080554443e-05,
      "loss": 0.868,
      "step": 596
    },
    {
      "epoch": 1.1961961961961962,
      "grad_norm": 0.3707253336906433,
      "learning_rate": 2.073537828636497e-05,
      "loss": 0.882,
      "step": 598
    },
    {
      "epoch": 1.2002002002002001,
      "grad_norm": 0.44216448068618774,
      "learning_rate": 2.0563126270691097e-05,
      "loss": 0.8794,
      "step": 600
    },
    {
      "epoch": 1.2002002002002001,
      "eval_flock_task4_val_loss": 1.1478508710861206,
      "eval_flock_task4_val_runtime": 2.4198,
      "eval_flock_task4_val_samples_per_second": 23.969,
      "eval_flock_task4_val_steps_per_second": 23.969,
      "step": 600
    },
    {
      "epoch": 1.2042042042042043,
      "grad_norm": 0.4116131663322449,
      "learning_rate": 2.039109146629016e-05,
      "loss": 0.8466,
      "step": 602
    },
    {
      "epoch": 1.2082082082082082,
      "grad_norm": 0.36521586775779724,
      "learning_rate": 2.0219282295285737e-05,
      "loss": 0.8924,
      "step": 604
    },
    {
      "epoch": 1.2122122122122123,
      "grad_norm": 0.4010111391544342,
      "learning_rate": 2.004770716875533e-05,
      "loss": 0.8546,
      "step": 606
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 0.45376816391944885,
      "learning_rate": 1.9876374486318543e-05,
      "loss": 0.8457,
      "step": 608
    },
    {
      "epoch": 1.2202202202202201,
      "grad_norm": 0.4506365656852722,
      "learning_rate": 1.970529263572594e-05,
      "loss": 0.8564,
      "step": 610
    },
    {
      "epoch": 1.2242242242242243,
      "grad_norm": 0.4055129289627075,
      "learning_rate": 1.9534469992448358e-05,
      "loss": 0.8472,
      "step": 612
    },
    {
      "epoch": 1.2282282282282282,
      "grad_norm": 0.403263658285141,
      "learning_rate": 1.936391491926689e-05,
      "loss": 0.896,
      "step": 614
    },
    {
      "epoch": 1.2322322322322323,
      "grad_norm": 0.3937626779079437,
      "learning_rate": 1.9193635765863523e-05,
      "loss": 0.8931,
      "step": 616
    },
    {
      "epoch": 1.2362362362362362,
      "grad_norm": 0.42880845069885254,
      "learning_rate": 1.9023640868412297e-05,
      "loss": 0.8265,
      "step": 618
    },
    {
      "epoch": 1.2402402402402402,
      "grad_norm": 0.5050727128982544,
      "learning_rate": 1.885393854917124e-05,
      "loss": 0.8488,
      "step": 620
    },
    {
      "epoch": 1.2442442442442443,
      "grad_norm": 0.44161123037338257,
      "learning_rate": 1.868453711607498e-05,
      "loss": 0.845,
      "step": 622
    },
    {
      "epoch": 1.2482482482482482,
      "grad_norm": 0.42316916584968567,
      "learning_rate": 1.8515444862327946e-05,
      "loss": 0.9099,
      "step": 624
    },
    {
      "epoch": 1.2522522522522523,
      "grad_norm": 0.44850805401802063,
      "learning_rate": 1.834667006599841e-05,
      "loss": 0.8437,
      "step": 626
    },
    {
      "epoch": 1.2562562562562563,
      "grad_norm": 0.4694780707359314,
      "learning_rate": 1.8178220989613254e-05,
      "loss": 0.8875,
      "step": 628
    },
    {
      "epoch": 1.2602602602602602,
      "grad_norm": 0.4005432426929474,
      "learning_rate": 1.8010105879753396e-05,
      "loss": 0.8659,
      "step": 630
    },
    {
      "epoch": 1.2642642642642643,
      "grad_norm": 0.42025813460350037,
      "learning_rate": 1.784233296665012e-05,
      "loss": 0.8718,
      "step": 632
    },
    {
      "epoch": 1.2682682682682682,
      "grad_norm": 0.41626977920532227,
      "learning_rate": 1.7674910463782184e-05,
      "loss": 0.8716,
      "step": 634
    },
    {
      "epoch": 1.2722722722722724,
      "grad_norm": 0.458926260471344,
      "learning_rate": 1.7507846567473644e-05,
      "loss": 0.9085,
      "step": 636
    },
    {
      "epoch": 1.2762762762762763,
      "grad_norm": 0.45097580552101135,
      "learning_rate": 1.7341149456492672e-05,
      "loss": 0.9067,
      "step": 638
    },
    {
      "epoch": 1.2802802802802802,
      "grad_norm": 0.3684636652469635,
      "learning_rate": 1.71748272916511e-05,
      "loss": 0.8626,
      "step": 640
    },
    {
      "epoch": 1.2842842842842843,
      "grad_norm": 0.39824149012565613,
      "learning_rate": 1.7008888215404933e-05,
      "loss": 0.9234,
      "step": 642
    },
    {
      "epoch": 1.2882882882882882,
      "grad_norm": 0.37552574276924133,
      "learning_rate": 1.6843340351455726e-05,
      "loss": 0.826,
      "step": 644
    },
    {
      "epoch": 1.2922922922922924,
      "grad_norm": 0.44982481002807617,
      "learning_rate": 1.6678191804352872e-05,
      "loss": 0.8814,
      "step": 646
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.4010125994682312,
      "learning_rate": 1.6513450659096804e-05,
      "loss": 0.8905,
      "step": 648
    },
    {
      "epoch": 1.3003003003003002,
      "grad_norm": 0.43015238642692566,
      "learning_rate": 1.6349124980743276e-05,
      "loss": 0.8357,
      "step": 650
    },
    {
      "epoch": 1.3003003003003002,
      "eval_flock_task4_val_loss": 1.143893837928772,
      "eval_flock_task4_val_runtime": 2.291,
      "eval_flock_task4_val_samples_per_second": 25.317,
      "eval_flock_task4_val_steps_per_second": 25.317,
      "step": 650
    },
    {
      "epoch": 1.3043043043043043,
      "grad_norm": 0.44190534949302673,
      "learning_rate": 1.6185222814008433e-05,
      "loss": 0.8707,
      "step": 652
    },
    {
      "epoch": 1.3083083083083082,
      "grad_norm": 0.4301456809043884,
      "learning_rate": 1.602175218287501e-05,
      "loss": 0.8699,
      "step": 654
    },
    {
      "epoch": 1.3123123123123124,
      "grad_norm": 0.4133666455745697,
      "learning_rate": 1.5858721090199565e-05,
      "loss": 0.8277,
      "step": 656
    },
    {
      "epoch": 1.3163163163163163,
      "grad_norm": 0.459380179643631,
      "learning_rate": 1.569613751732058e-05,
      "loss": 0.8458,
      "step": 658
    },
    {
      "epoch": 1.3203203203203202,
      "grad_norm": 0.3874422311782837,
      "learning_rate": 1.5534009423667827e-05,
      "loss": 0.8508,
      "step": 660
    },
    {
      "epoch": 1.3243243243243243,
      "grad_norm": 0.5516605377197266,
      "learning_rate": 1.537234474637268e-05,
      "loss": 0.8989,
      "step": 662
    },
    {
      "epoch": 1.3283283283283283,
      "grad_norm": 0.38644006848335266,
      "learning_rate": 1.5211151399879506e-05,
      "loss": 0.8677,
      "step": 664
    },
    {
      "epoch": 1.3323323323323324,
      "grad_norm": 0.4062030017375946,
      "learning_rate": 1.5050437275558233e-05,
      "loss": 0.8896,
      "step": 666
    },
    {
      "epoch": 1.3363363363363363,
      "grad_norm": 0.43147289752960205,
      "learning_rate": 1.489021024131806e-05,
      "loss": 0.8782,
      "step": 668
    },
    {
      "epoch": 1.3403403403403402,
      "grad_norm": 0.35989537835121155,
      "learning_rate": 1.4730478141222192e-05,
      "loss": 0.9494,
      "step": 670
    },
    {
      "epoch": 1.3443443443443444,
      "grad_norm": 0.4030705988407135,
      "learning_rate": 1.457124879510392e-05,
      "loss": 0.8307,
      "step": 672
    },
    {
      "epoch": 1.3483483483483483,
      "grad_norm": 0.3988940715789795,
      "learning_rate": 1.441252999818371e-05,
      "loss": 0.8933,
      "step": 674
    },
    {
      "epoch": 1.3523523523523524,
      "grad_norm": 0.3888278603553772,
      "learning_rate": 1.4254329520687625e-05,
      "loss": 0.8324,
      "step": 676
    },
    {
      "epoch": 1.3563563563563563,
      "grad_norm": 0.3939126431941986,
      "learning_rate": 1.4096655107466945e-05,
      "loss": 0.89,
      "step": 678
    },
    {
      "epoch": 1.3603603603603602,
      "grad_norm": 0.4838270843029022,
      "learning_rate": 1.3939514477618942e-05,
      "loss": 0.8477,
      "step": 680
    },
    {
      "epoch": 1.3643643643643644,
      "grad_norm": 0.40554022789001465,
      "learning_rate": 1.3782915324109074e-05,
      "loss": 0.8645,
      "step": 682
    },
    {
      "epoch": 1.3683683683683685,
      "grad_norm": 0.40760108828544617,
      "learning_rate": 1.362686531339428e-05,
      "loss": 0.8567,
      "step": 684
    },
    {
      "epoch": 1.3723723723723724,
      "grad_norm": 0.3956020176410675,
      "learning_rate": 1.3471372085047742e-05,
      "loss": 0.8703,
      "step": 686
    },
    {
      "epoch": 1.3763763763763763,
      "grad_norm": 0.478240966796875,
      "learning_rate": 1.3316443251384807e-05,
      "loss": 0.8142,
      "step": 688
    },
    {
      "epoch": 1.3803803803803802,
      "grad_norm": 0.4959944188594818,
      "learning_rate": 1.316208639709039e-05,
      "loss": 0.8593,
      "step": 690
    },
    {
      "epoch": 1.3843843843843844,
      "grad_norm": 0.47035202383995056,
      "learning_rate": 1.3008309078847605e-05,
      "loss": 0.9078,
      "step": 692
    },
    {
      "epoch": 1.3883883883883885,
      "grad_norm": 0.44363516569137573,
      "learning_rate": 1.2855118824967833e-05,
      "loss": 0.8965,
      "step": 694
    },
    {
      "epoch": 1.3923923923923924,
      "grad_norm": 0.39717763662338257,
      "learning_rate": 1.2702523135022204e-05,
      "loss": 0.863,
      "step": 696
    },
    {
      "epoch": 1.3963963963963963,
      "grad_norm": 0.416452020406723,
      "learning_rate": 1.2550529479474383e-05,
      "loss": 0.8787,
      "step": 698
    },
    {
      "epoch": 1.4004004004004005,
      "grad_norm": 0.42090561985969543,
      "learning_rate": 1.2399145299314912e-05,
      "loss": 0.8709,
      "step": 700
    },
    {
      "epoch": 1.4004004004004005,
      "eval_flock_task4_val_loss": 1.1386691331863403,
      "eval_flock_task4_val_runtime": 2.2803,
      "eval_flock_task4_val_samples_per_second": 25.435,
      "eval_flock_task4_val_steps_per_second": 25.435,
      "step": 700
    },
    {
      "epoch": 1.4044044044044044,
      "grad_norm": 0.413644403219223,
      "learning_rate": 1.2248378005696889e-05,
      "loss": 0.8916,
      "step": 702
    },
    {
      "epoch": 1.4084084084084085,
      "grad_norm": 0.45839402079582214,
      "learning_rate": 1.209823497957314e-05,
      "loss": 0.8662,
      "step": 704
    },
    {
      "epoch": 1.4124124124124124,
      "grad_norm": 0.4414491653442383,
      "learning_rate": 1.1948723571334933e-05,
      "loss": 0.8382,
      "step": 706
    },
    {
      "epoch": 1.4164164164164164,
      "grad_norm": 0.43671172857284546,
      "learning_rate": 1.1799851100452066e-05,
      "loss": 0.8418,
      "step": 708
    },
    {
      "epoch": 1.4204204204204205,
      "grad_norm": 0.4703764021396637,
      "learning_rate": 1.1651624855114566e-05,
      "loss": 0.8407,
      "step": 710
    },
    {
      "epoch": 1.4244244244244244,
      "grad_norm": 0.4794108271598816,
      "learning_rate": 1.1504052091875916e-05,
      "loss": 0.8828,
      "step": 712
    },
    {
      "epoch": 1.4284284284284285,
      "grad_norm": 0.41678547859191895,
      "learning_rate": 1.1357140035297745e-05,
      "loss": 0.8714,
      "step": 714
    },
    {
      "epoch": 1.4324324324324325,
      "grad_norm": 0.4571875035762787,
      "learning_rate": 1.1210895877596194e-05,
      "loss": 0.8848,
      "step": 716
    },
    {
      "epoch": 1.4364364364364364,
      "grad_norm": 0.4822946786880493,
      "learning_rate": 1.1065326778289781e-05,
      "loss": 0.8514,
      "step": 718
    },
    {
      "epoch": 1.4404404404404405,
      "grad_norm": 0.392842561006546,
      "learning_rate": 1.092043986384893e-05,
      "loss": 0.842,
      "step": 720
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.43785953521728516,
      "learning_rate": 1.0776242227347045e-05,
      "loss": 0.8579,
      "step": 722
    },
    {
      "epoch": 1.4484484484484486,
      "grad_norm": 0.4331945776939392,
      "learning_rate": 1.0632740928113321e-05,
      "loss": 0.8866,
      "step": 724
    },
    {
      "epoch": 1.4524524524524525,
      "grad_norm": 0.3922359347343445,
      "learning_rate": 1.048994299138709e-05,
      "loss": 0.8631,
      "step": 726
    },
    {
      "epoch": 1.4564564564564564,
      "grad_norm": 0.46076324582099915,
      "learning_rate": 1.0347855407973934e-05,
      "loss": 0.8583,
      "step": 728
    },
    {
      "epoch": 1.4604604604604605,
      "grad_norm": 0.439680814743042,
      "learning_rate": 1.0206485133903424e-05,
      "loss": 0.8157,
      "step": 730
    },
    {
      "epoch": 1.4644644644644644,
      "grad_norm": 0.44809362292289734,
      "learning_rate": 1.0065839090088572e-05,
      "loss": 0.8127,
      "step": 732
    },
    {
      "epoch": 1.4684684684684686,
      "grad_norm": 0.46601828932762146,
      "learning_rate": 9.925924161987057e-06,
      "loss": 0.8641,
      "step": 734
    },
    {
      "epoch": 1.4724724724724725,
      "grad_norm": 0.4423384368419647,
      "learning_rate": 9.786747199264087e-06,
      "loss": 0.8645,
      "step": 736
    },
    {
      "epoch": 1.4764764764764764,
      "grad_norm": 0.4642850160598755,
      "learning_rate": 9.648315015457082e-06,
      "loss": 0.8303,
      "step": 738
    },
    {
      "epoch": 1.4804804804804805,
      "grad_norm": 0.4454893171787262,
      "learning_rate": 9.510634387642151e-06,
      "loss": 0.8334,
      "step": 740
    },
    {
      "epoch": 1.4844844844844844,
      "grad_norm": 0.5033170580863953,
      "learning_rate": 9.373712056102249e-06,
      "loss": 0.8668,
      "step": 742
    },
    {
      "epoch": 1.4884884884884886,
      "grad_norm": 0.45939940214157104,
      "learning_rate": 9.237554723997241e-06,
      "loss": 0.8321,
      "step": 744
    },
    {
      "epoch": 1.4924924924924925,
      "grad_norm": 0.42905375361442566,
      "learning_rate": 9.102169057035754e-06,
      "loss": 0.932,
      "step": 746
    },
    {
      "epoch": 1.4964964964964964,
      "grad_norm": 0.47114264965057373,
      "learning_rate": 8.967561683148798e-06,
      "loss": 0.8541,
      "step": 748
    },
    {
      "epoch": 1.5005005005005005,
      "grad_norm": 0.3895653188228607,
      "learning_rate": 8.833739192165352e-06,
      "loss": 0.8903,
      "step": 750
    },
    {
      "epoch": 1.5005005005005005,
      "eval_flock_task4_val_loss": 1.136841893196106,
      "eval_flock_task4_val_runtime": 2.2949,
      "eval_flock_task4_val_samples_per_second": 25.274,
      "eval_flock_task4_val_steps_per_second": 25.274,
      "step": 750
    },
    {
      "epoch": 1.5045045045045045,
      "grad_norm": 0.5534226894378662,
      "learning_rate": 8.700708135489721e-06,
      "loss": 0.8628,
      "step": 752
    },
    {
      "epoch": 1.5085085085085086,
      "grad_norm": 0.45723313093185425,
      "learning_rate": 8.56847502578078e-06,
      "loss": 0.8812,
      "step": 754
    },
    {
      "epoch": 1.5125125125125125,
      "grad_norm": 0.42593708634376526,
      "learning_rate": 8.43704633663321e-06,
      "loss": 0.8492,
      "step": 756
    },
    {
      "epoch": 1.5165165165165164,
      "grad_norm": 0.4144039452075958,
      "learning_rate": 8.306428502260511e-06,
      "loss": 0.8946,
      "step": 758
    },
    {
      "epoch": 1.5205205205205206,
      "grad_norm": 0.4269801080226898,
      "learning_rate": 8.176627917180024e-06,
      "loss": 0.8415,
      "step": 760
    },
    {
      "epoch": 1.5245245245245245,
      "grad_norm": 0.410341739654541,
      "learning_rate": 8.047650935899931e-06,
      "loss": 0.8318,
      "step": 762
    },
    {
      "epoch": 1.5285285285285286,
      "grad_norm": 0.4322713613510132,
      "learning_rate": 7.919503872608092e-06,
      "loss": 0.8473,
      "step": 764
    },
    {
      "epoch": 1.5325325325325325,
      "grad_norm": 0.5121660232543945,
      "learning_rate": 7.792193000862963e-06,
      "loss": 0.8559,
      "step": 766
    },
    {
      "epoch": 1.5365365365365364,
      "grad_norm": 0.4450767934322357,
      "learning_rate": 7.665724553286491e-06,
      "loss": 0.8338,
      "step": 768
    },
    {
      "epoch": 1.5405405405405406,
      "grad_norm": 0.4499673545360565,
      "learning_rate": 7.5401047212589444e-06,
      "loss": 0.9011,
      "step": 770
    },
    {
      "epoch": 1.5445445445445447,
      "grad_norm": 0.3775758445262909,
      "learning_rate": 7.415339654615824e-06,
      "loss": 0.8526,
      "step": 772
    },
    {
      "epoch": 1.5485485485485486,
      "grad_norm": 0.4253455102443695,
      "learning_rate": 7.291435461346827e-06,
      "loss": 0.8376,
      "step": 774
    },
    {
      "epoch": 1.5525525525525525,
      "grad_norm": 0.4507961869239807,
      "learning_rate": 7.1683982072967646e-06,
      "loss": 0.875,
      "step": 776
    },
    {
      "epoch": 1.5565565565565564,
      "grad_norm": 0.4244922697544098,
      "learning_rate": 7.0462339158686415e-06,
      "loss": 0.9,
      "step": 778
    },
    {
      "epoch": 1.5605605605605606,
      "grad_norm": 0.45657554268836975,
      "learning_rate": 6.924948567728786e-06,
      "loss": 0.8244,
      "step": 780
    },
    {
      "epoch": 1.5645645645645647,
      "grad_norm": 0.44866183400154114,
      "learning_rate": 6.804548100514013e-06,
      "loss": 0.849,
      "step": 782
    },
    {
      "epoch": 1.5685685685685686,
      "grad_norm": 0.4514263868331909,
      "learning_rate": 6.685038408540989e-06,
      "loss": 0.8307,
      "step": 784
    },
    {
      "epoch": 1.5725725725725725,
      "grad_norm": 0.4524141252040863,
      "learning_rate": 6.566425342517652e-06,
      "loss": 0.8082,
      "step": 786
    },
    {
      "epoch": 1.5765765765765765,
      "grad_norm": 0.5142974853515625,
      "learning_rate": 6.4487147092567675e-06,
      "loss": 0.8573,
      "step": 788
    },
    {
      "epoch": 1.5805805805805806,
      "grad_norm": 0.48223766684532166,
      "learning_rate": 6.331912271391688e-06,
      "loss": 0.8703,
      "step": 790
    },
    {
      "epoch": 1.5845845845845847,
      "grad_norm": 0.45007768273353577,
      "learning_rate": 6.216023747094207e-06,
      "loss": 0.8822,
      "step": 792
    },
    {
      "epoch": 1.5885885885885886,
      "grad_norm": 0.46107056736946106,
      "learning_rate": 6.101054809794615e-06,
      "loss": 0.8731,
      "step": 794
    },
    {
      "epoch": 1.5925925925925926,
      "grad_norm": 0.5555247664451599,
      "learning_rate": 5.987011087904007e-06,
      "loss": 0.7878,
      "step": 796
    },
    {
      "epoch": 1.5965965965965965,
      "grad_norm": 0.43157267570495605,
      "learning_rate": 5.873898164538657e-06,
      "loss": 0.8779,
      "step": 798
    },
    {
      "epoch": 1.6006006006006006,
      "grad_norm": 0.4325798451900482,
      "learning_rate": 5.7617215772467535e-06,
      "loss": 0.8346,
      "step": 800
    },
    {
      "epoch": 1.6006006006006006,
      "eval_flock_task4_val_loss": 1.1378659009933472,
      "eval_flock_task4_val_runtime": 2.3013,
      "eval_flock_task4_val_samples_per_second": 25.203,
      "eval_flock_task4_val_steps_per_second": 25.203,
      "step": 800
    },
    {
      "epoch": 1.6046046046046047,
      "grad_norm": 0.43533363938331604,
      "learning_rate": 5.650486817737291e-06,
      "loss": 0.8708,
      "step": 802
    },
    {
      "epoch": 1.6086086086086087,
      "grad_norm": 0.8679392337799072,
      "learning_rate": 5.54019933161119e-06,
      "loss": 0.8308,
      "step": 804
    },
    {
      "epoch": 1.6126126126126126,
      "grad_norm": 0.49564796686172485,
      "learning_rate": 5.430864518094731e-06,
      "loss": 0.8808,
      "step": 806
    },
    {
      "epoch": 1.6166166166166165,
      "grad_norm": 0.4227229356765747,
      "learning_rate": 5.322487729775233e-06,
      "loss": 0.9045,
      "step": 808
    },
    {
      "epoch": 1.6206206206206206,
      "grad_norm": 0.450801283121109,
      "learning_rate": 5.215074272338985e-06,
      "loss": 0.8726,
      "step": 810
    },
    {
      "epoch": 1.6246246246246248,
      "grad_norm": 0.4490666389465332,
      "learning_rate": 5.108629404311535e-06,
      "loss": 0.854,
      "step": 812
    },
    {
      "epoch": 1.6286286286286287,
      "grad_norm": 0.49601781368255615,
      "learning_rate": 5.003158336800218e-06,
      "loss": 0.9127,
      "step": 814
    },
    {
      "epoch": 1.6326326326326326,
      "grad_norm": 0.4565769135951996,
      "learning_rate": 4.898666233239083e-06,
      "loss": 0.8636,
      "step": 816
    },
    {
      "epoch": 1.6366366366366365,
      "grad_norm": 0.4938611090183258,
      "learning_rate": 4.795158209136066e-06,
      "loss": 0.8341,
      "step": 818
    },
    {
      "epoch": 1.6406406406406406,
      "grad_norm": 0.3954929709434509,
      "learning_rate": 4.692639331822604e-06,
      "loss": 0.8855,
      "step": 820
    },
    {
      "epoch": 1.6446446446446448,
      "grad_norm": 0.42091336846351624,
      "learning_rate": 4.5911146202055114e-06,
      "loss": 0.8929,
      "step": 822
    },
    {
      "epoch": 1.6486486486486487,
      "grad_norm": 0.49426716566085815,
      "learning_rate": 4.490589044521315e-06,
      "loss": 0.839,
      "step": 824
    },
    {
      "epoch": 1.6526526526526526,
      "grad_norm": 0.5828158259391785,
      "learning_rate": 4.39106752609291e-06,
      "loss": 0.8209,
      "step": 826
    },
    {
      "epoch": 1.6566566566566565,
      "grad_norm": 0.4805382788181305,
      "learning_rate": 4.292554937088622e-06,
      "loss": 0.8909,
      "step": 828
    },
    {
      "epoch": 1.6606606606606606,
      "grad_norm": 0.5196824669837952,
      "learning_rate": 4.195056100283726e-06,
      "loss": 0.8537,
      "step": 830
    },
    {
      "epoch": 1.6646646646646648,
      "grad_norm": 0.45226049423217773,
      "learning_rate": 4.098575788824297e-06,
      "loss": 0.8264,
      "step": 832
    },
    {
      "epoch": 1.6686686686686687,
      "grad_norm": 0.5464234352111816,
      "learning_rate": 4.003118725993554e-06,
      "loss": 0.832,
      "step": 834
    },
    {
      "epoch": 1.6726726726726726,
      "grad_norm": 0.5279391407966614,
      "learning_rate": 3.908689584980654e-06,
      "loss": 0.8355,
      "step": 836
    },
    {
      "epoch": 1.6766766766766765,
      "grad_norm": 0.5107043981552124,
      "learning_rate": 3.815292988651859e-06,
      "loss": 0.8848,
      "step": 838
    },
    {
      "epoch": 1.6806806806806807,
      "grad_norm": 0.49792614579200745,
      "learning_rate": 3.7229335093242585e-06,
      "loss": 0.8724,
      "step": 840
    },
    {
      "epoch": 1.6846846846846848,
      "grad_norm": 0.5087601542472839,
      "learning_rate": 3.6316156685419213e-06,
      "loss": 0.8495,
      "step": 842
    },
    {
      "epoch": 1.6886886886886887,
      "grad_norm": 0.4378841817378998,
      "learning_rate": 3.541343936854524e-06,
      "loss": 0.8915,
      "step": 844
    },
    {
      "epoch": 1.6926926926926926,
      "grad_norm": 0.47965216636657715,
      "learning_rate": 3.4521227335985145e-06,
      "loss": 0.7802,
      "step": 846
    },
    {
      "epoch": 1.6966966966966965,
      "grad_norm": 0.4828782379627228,
      "learning_rate": 3.363956426680728e-06,
      "loss": 0.8011,
      "step": 848
    },
    {
      "epoch": 1.7007007007007007,
      "grad_norm": 0.46208733320236206,
      "learning_rate": 3.276849332364587e-06,
      "loss": 0.8748,
      "step": 850
    },
    {
      "epoch": 1.7007007007007007,
      "eval_flock_task4_val_loss": 1.1365524530410767,
      "eval_flock_task4_val_runtime": 2.2775,
      "eval_flock_task4_val_samples_per_second": 25.466,
      "eval_flock_task4_val_steps_per_second": 25.466,
      "step": 850
    },
    {
      "epoch": 1.7047047047047048,
      "grad_norm": 0.38446688652038574,
      "learning_rate": 3.1908057150587643e-06,
      "loss": 0.8712,
      "step": 852
    },
    {
      "epoch": 1.7087087087087087,
      "grad_norm": 0.43955543637275696,
      "learning_rate": 3.105829787108444e-06,
      "loss": 0.8534,
      "step": 854
    },
    {
      "epoch": 1.7127127127127126,
      "grad_norm": 0.44339418411254883,
      "learning_rate": 3.0219257085890656e-06,
      "loss": 0.835,
      "step": 856
    },
    {
      "epoch": 1.7167167167167166,
      "grad_norm": 0.5061709880828857,
      "learning_rate": 2.939097587102704e-06,
      "loss": 0.8415,
      "step": 858
    },
    {
      "epoch": 1.7207207207207207,
      "grad_norm": 0.4325864315032959,
      "learning_rate": 2.8573494775769484e-06,
      "loss": 0.8284,
      "step": 860
    },
    {
      "epoch": 1.7247247247247248,
      "grad_norm": 0.46651405096054077,
      "learning_rate": 2.776685382066396e-06,
      "loss": 0.8204,
      "step": 862
    },
    {
      "epoch": 1.7287287287287287,
      "grad_norm": 0.46017175912857056,
      "learning_rate": 2.697109249556748e-06,
      "loss": 0.7886,
      "step": 864
    },
    {
      "epoch": 1.7327327327327327,
      "grad_norm": 0.45303404331207275,
      "learning_rate": 2.618624975771447e-06,
      "loss": 0.7975,
      "step": 866
    },
    {
      "epoch": 1.7367367367367368,
      "grad_norm": 0.4538724720478058,
      "learning_rate": 2.541236402980987e-06,
      "loss": 0.816,
      "step": 868
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 0.4861656725406647,
      "learning_rate": 2.464947319814806e-06,
      "loss": 0.762,
      "step": 870
    },
    {
      "epoch": 1.7447447447447448,
      "grad_norm": 0.5382648706436157,
      "learning_rate": 2.3897614610757983e-06,
      "loss": 0.8531,
      "step": 872
    },
    {
      "epoch": 1.7487487487487487,
      "grad_norm": 0.4602164328098297,
      "learning_rate": 2.3156825075574958e-06,
      "loss": 0.8246,
      "step": 874
    },
    {
      "epoch": 1.7527527527527527,
      "grad_norm": 0.517173707485199,
      "learning_rate": 2.242714085863842e-06,
      "loss": 0.8728,
      "step": 876
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 0.48782795667648315,
      "learning_rate": 2.1708597682316644e-06,
      "loss": 0.8758,
      "step": 878
    },
    {
      "epoch": 1.7607607607607607,
      "grad_norm": 0.40246081352233887,
      "learning_rate": 2.1001230723558083e-06,
      "loss": 0.8576,
      "step": 880
    },
    {
      "epoch": 1.7647647647647648,
      "grad_norm": 0.45257192850112915,
      "learning_rate": 2.0305074612168906e-06,
      "loss": 0.8405,
      "step": 882
    },
    {
      "epoch": 1.7687687687687688,
      "grad_norm": 0.49757951498031616,
      "learning_rate": 1.9620163429117905e-06,
      "loss": 0.7962,
      "step": 884
    },
    {
      "epoch": 1.7727727727727727,
      "grad_norm": 0.4517136514186859,
      "learning_rate": 1.894653070486807e-06,
      "loss": 0.8599,
      "step": 886
    },
    {
      "epoch": 1.7767767767767768,
      "grad_norm": 0.3954245448112488,
      "learning_rate": 1.828420941773476e-06,
      "loss": 0.8918,
      "step": 888
    },
    {
      "epoch": 1.7807807807807807,
      "grad_norm": 0.46916237473487854,
      "learning_rate": 1.763323199227157e-06,
      "loss": 0.8613,
      "step": 890
    },
    {
      "epoch": 1.7847847847847849,
      "grad_norm": 0.4551919102668762,
      "learning_rate": 1.6993630297682778e-06,
      "loss": 0.8169,
      "step": 892
    },
    {
      "epoch": 1.7887887887887888,
      "grad_norm": 0.5219541788101196,
      "learning_rate": 1.6365435646263222e-06,
      "loss": 0.8465,
      "step": 894
    },
    {
      "epoch": 1.7927927927927927,
      "grad_norm": 0.45977309346199036,
      "learning_rate": 1.5748678791865228e-06,
      "loss": 0.8893,
      "step": 896
    },
    {
      "epoch": 1.7967967967967968,
      "grad_norm": 0.5053537487983704,
      "learning_rate": 1.5143389928393398e-06,
      "loss": 0.8646,
      "step": 898
    },
    {
      "epoch": 1.800800800800801,
      "grad_norm": 0.5736296772956848,
      "learning_rate": 1.4549598688325893e-06,
      "loss": 0.8026,
      "step": 900
    },
    {
      "epoch": 1.800800800800801,
      "eval_flock_task4_val_loss": 1.1379015445709229,
      "eval_flock_task4_val_runtime": 2.2904,
      "eval_flock_task4_val_samples_per_second": 25.323,
      "eval_flock_task4_val_steps_per_second": 25.323,
      "step": 900
    },
    {
      "epoch": 1.8048048048048049,
      "grad_norm": 0.4098823070526123,
      "learning_rate": 1.3967334141264277e-06,
      "loss": 0.889,
      "step": 902
    },
    {
      "epoch": 1.8088088088088088,
      "grad_norm": 0.4983745217323303,
      "learning_rate": 1.3396624792510083e-06,
      "loss": 0.801,
      "step": 904
    },
    {
      "epoch": 1.8128128128128127,
      "grad_norm": 0.4158942997455597,
      "learning_rate": 1.2837498581669272e-06,
      "loss": 0.8228,
      "step": 906
    },
    {
      "epoch": 1.8168168168168168,
      "grad_norm": 0.46956199407577515,
      "learning_rate": 1.2289982881284718e-06,
      "loss": 0.8589,
      "step": 908
    },
    {
      "epoch": 1.820820820820821,
      "grad_norm": 0.38610410690307617,
      "learning_rate": 1.1754104495495883e-06,
      "loss": 0.8549,
      "step": 910
    },
    {
      "epoch": 1.8248248248248249,
      "grad_norm": 0.4316381812095642,
      "learning_rate": 1.1229889658726622e-06,
      "loss": 0.8648,
      "step": 912
    },
    {
      "epoch": 1.8288288288288288,
      "grad_norm": 0.4447328746318817,
      "learning_rate": 1.0717364034401074e-06,
      "loss": 0.8273,
      "step": 914
    },
    {
      "epoch": 1.8328328328328327,
      "grad_norm": 0.47008782625198364,
      "learning_rate": 1.0216552713686988e-06,
      "loss": 0.8811,
      "step": 916
    },
    {
      "epoch": 1.8368368368368369,
      "grad_norm": 0.41356533765792847,
      "learning_rate": 9.72748021426756e-07,
      "loss": 0.8253,
      "step": 918
    },
    {
      "epoch": 1.840840840840841,
      "grad_norm": 0.43283718824386597,
      "learning_rate": 9.250170479141146e-07,
      "loss": 0.8694,
      "step": 920
    },
    {
      "epoch": 1.844844844844845,
      "grad_norm": 0.46151700615882874,
      "learning_rate": 8.784646875448971e-07,
      "loss": 0.8889,
      "step": 922
    },
    {
      "epoch": 1.8488488488488488,
      "grad_norm": 0.4734440743923187,
      "learning_rate": 8.330932193331226e-07,
      "loss": 0.8338,
      "step": 924
    },
    {
      "epoch": 1.8528528528528527,
      "grad_norm": 0.44311681389808655,
      "learning_rate": 7.889048644811519e-07,
      "loss": 0.8679,
      "step": 926
    },
    {
      "epoch": 1.8568568568568569,
      "grad_norm": 0.5000930428504944,
      "learning_rate": 7.459017862709194e-07,
      "loss": 0.8324,
      "step": 928
    },
    {
      "epoch": 1.860860860860861,
      "grad_norm": 0.422635555267334,
      "learning_rate": 7.040860899580476e-07,
      "loss": 0.88,
      "step": 930
    },
    {
      "epoch": 1.864864864864865,
      "grad_norm": 0.4244588017463684,
      "learning_rate": 6.634598226687771e-07,
      "loss": 0.8555,
      "step": 932
    },
    {
      "epoch": 1.8688688688688688,
      "grad_norm": 1.2747561931610107,
      "learning_rate": 6.240249732997361e-07,
      "loss": 0.8798,
      "step": 934
    },
    {
      "epoch": 1.8728728728728727,
      "grad_norm": 0.4664041996002197,
      "learning_rate": 5.85783472420598e-07,
      "loss": 0.8003,
      "step": 936
    },
    {
      "epoch": 1.8768768768768769,
      "grad_norm": 0.5424234867095947,
      "learning_rate": 5.487371921795381e-07,
      "loss": 0.8488,
      "step": 938
    },
    {
      "epoch": 1.880880880880881,
      "grad_norm": 0.4183599352836609,
      "learning_rate": 5.12887946211607e-07,
      "loss": 0.8356,
      "step": 940
    },
    {
      "epoch": 1.884884884884885,
      "grad_norm": 0.5235341787338257,
      "learning_rate": 4.782374895499236e-07,
      "loss": 0.8021,
      "step": 942
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.4295443892478943,
      "learning_rate": 4.4478751853976597e-07,
      "loss": 0.8604,
      "step": 944
    },
    {
      "epoch": 1.8928928928928928,
      "grad_norm": 0.4572451114654541,
      "learning_rate": 4.1253967075552124e-07,
      "loss": 0.8838,
      "step": 946
    },
    {
      "epoch": 1.896896896896897,
      "grad_norm": 0.4556294083595276,
      "learning_rate": 3.814955249205221e-07,
      "loss": 0.8709,
      "step": 948
    },
    {
      "epoch": 1.900900900900901,
      "grad_norm": 0.4841032028198242,
      "learning_rate": 3.5165660082975005e-07,
      "loss": 0.8514,
      "step": 950
    },
    {
      "epoch": 1.900900900900901,
      "eval_flock_task4_val_loss": 1.1388740539550781,
      "eval_flock_task4_val_runtime": 2.3026,
      "eval_flock_task4_val_samples_per_second": 25.189,
      "eval_flock_task4_val_steps_per_second": 25.189,
      "step": 950
    },
    {
      "epoch": 1.904904904904905,
      "grad_norm": 0.4695403575897217,
      "learning_rate": 3.230243592754367e-07,
      "loss": 0.8065,
      "step": 952
    },
    {
      "epoch": 1.9089089089089089,
      "grad_norm": 0.5065103769302368,
      "learning_rate": 2.9560020197555714e-07,
      "loss": 0.8747,
      "step": 954
    },
    {
      "epoch": 1.9129129129129128,
      "grad_norm": 0.48485851287841797,
      "learning_rate": 2.6938547150518743e-07,
      "loss": 0.8536,
      "step": 956
    },
    {
      "epoch": 1.916916916916917,
      "grad_norm": 0.45243096351623535,
      "learning_rate": 2.443814512308018e-07,
      "loss": 0.8555,
      "step": 958
    },
    {
      "epoch": 1.920920920920921,
      "grad_norm": 0.4358191192150116,
      "learning_rate": 2.2058936524742835e-07,
      "loss": 0.8594,
      "step": 960
    },
    {
      "epoch": 1.924924924924925,
      "grad_norm": 0.4899273216724396,
      "learning_rate": 1.9801037831872482e-07,
      "loss": 0.8678,
      "step": 962
    },
    {
      "epoch": 1.9289289289289289,
      "grad_norm": 0.47123733162879944,
      "learning_rate": 1.766455958199631e-07,
      "loss": 0.9019,
      "step": 964
    },
    {
      "epoch": 1.9329329329329328,
      "grad_norm": 0.5304355025291443,
      "learning_rate": 1.564960636839058e-07,
      "loss": 0.8371,
      "step": 966
    },
    {
      "epoch": 1.936936936936937,
      "grad_norm": 0.4939720034599304,
      "learning_rate": 1.3756276834960557e-07,
      "loss": 0.8776,
      "step": 968
    },
    {
      "epoch": 1.940940940940941,
      "grad_norm": 0.4805956482887268,
      "learning_rate": 1.19846636714116e-07,
      "loss": 0.8481,
      "step": 970
    },
    {
      "epoch": 1.944944944944945,
      "grad_norm": 0.49638184905052185,
      "learning_rate": 1.0334853608710837e-07,
      "loss": 0.8513,
      "step": 972
    },
    {
      "epoch": 1.9489489489489489,
      "grad_norm": 0.4554474353790283,
      "learning_rate": 8.80692741484196e-08,
      "loss": 0.8635,
      "step": 974
    },
    {
      "epoch": 1.9529529529529528,
      "grad_norm": 0.4783639907836914,
      "learning_rate": 7.400959890850046e-08,
      "loss": 0.8719,
      "step": 976
    },
    {
      "epoch": 1.956956956956957,
      "grad_norm": 0.4808086156845093,
      "learning_rate": 6.117019867181162e-08,
      "loss": 0.878,
      "step": 978
    },
    {
      "epoch": 1.960960960960961,
      "grad_norm": 0.4793371260166168,
      "learning_rate": 4.955170200310888e-08,
      "loss": 0.85,
      "step": 980
    },
    {
      "epoch": 1.964964964964965,
      "grad_norm": 0.45383748412132263,
      "learning_rate": 3.9154677696687235e-08,
      "loss": 0.8224,
      "step": 982
    },
    {
      "epoch": 1.968968968968969,
      "grad_norm": 0.4468953609466553,
      "learning_rate": 2.997963474852261e-08,
      "loss": 0.8869,
      "step": 984
    },
    {
      "epoch": 1.972972972972973,
      "grad_norm": 0.46686744689941406,
      "learning_rate": 2.2027022331361224e-08,
      "loss": 0.8786,
      "step": 986
    },
    {
      "epoch": 1.976976976976977,
      "grad_norm": 0.3748922646045685,
      "learning_rate": 1.5297229772726074e-08,
      "loss": 0.9047,
      "step": 988
    },
    {
      "epoch": 1.980980980980981,
      "grad_norm": 0.4514774680137634,
      "learning_rate": 9.79058653586551e-09,
      "loss": 0.846,
      "step": 990
    },
    {
      "epoch": 1.984984984984985,
      "grad_norm": 0.4313613474369049,
      "learning_rate": 5.507362203607813e-09,
      "loss": 0.8178,
      "step": 992
    },
    {
      "epoch": 1.988988988988989,
      "grad_norm": 0.43718430399894714,
      "learning_rate": 2.4477664651800793e-09,
      "loss": 0.851,
      "step": 994
    },
    {
      "epoch": 1.992992992992993,
      "grad_norm": 0.4382748007774353,
      "learning_rate": 6.119491059303206e-10,
      "loss": 0.7938,
      "step": 996
    },
    {
      "epoch": 1.996996996996997,
      "grad_norm": 0.4784489572048187,
      "learning_rate": 0.0,
      "loss": 0.8333,
      "step": 998
    },
    {
      "epoch": 1.996996996996997,
      "step": 998,
      "total_flos": 2.4596562853380096e+17,
      "train_loss": 0.9170954039913858,
      "train_runtime": 1533.9501,
      "train_samples_per_second": 10.411,
      "train_steps_per_second": 0.651
    }
  ],
  "logging_steps": 2,
  "max_steps": 998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4596562853380096e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}