{
  "best_metric": 0.13911749422550201,
  "best_model_checkpoint": "limbxy_pose/checkpoint-1780",
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 1780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2808988764044944,
      "grad_norm": 4.863247798176859e-14,
      "learning_rate": 5e-06,
      "loss": 0.3282,
      "step": 25
    },
    {
      "epoch": 0.5617977528089888,
      "grad_norm": 80268.6796875,
      "learning_rate": 1e-05,
      "loss": 0.3192,
      "step": 50
    },
    {
      "epoch": 0.8426966292134831,
      "grad_norm": 1568863.75,
      "learning_rate": 1.5e-05,
      "loss": 0.2116,
      "step": 75
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.17222893238067627,
      "eval_rmse": 0.4150047302246094,
      "eval_runtime": 9.1184,
      "eval_samples_per_second": 109.668,
      "eval_steps_per_second": 1.755,
      "step": 89
    },
    {
      "epoch": 1.1235955056179776,
      "grad_norm": 1656748.25,
      "learning_rate": 2e-05,
      "loss": 0.1818,
      "step": 100
    },
    {
      "epoch": 1.404494382022472,
      "grad_norm": 1260438.5,
      "learning_rate": 2.5e-05,
      "loss": 0.1681,
      "step": 125
    },
    {
      "epoch": 1.6853932584269664,
      "grad_norm": 3767623.0,
      "learning_rate": 3e-05,
      "loss": 0.1607,
      "step": 150
    },
    {
      "epoch": 1.9662921348314608,
      "grad_norm": 718866.8125,
      "learning_rate": 3.5e-05,
      "loss": 0.154,
      "step": 175
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.16393612325191498,
      "eval_rmse": 0.4048902690410614,
      "eval_runtime": 8.9983,
      "eval_samples_per_second": 111.132,
      "eval_steps_per_second": 1.778,
      "step": 178
    },
    {
      "epoch": 2.247191011235955,
      "grad_norm": 1494838.0,
      "learning_rate": 4e-05,
      "loss": 0.1776,
      "step": 200
    },
    {
      "epoch": 2.5280898876404496,
      "grad_norm": 182619.0,
      "learning_rate": 4.5e-05,
      "loss": 0.1685,
      "step": 225
    },
    {
      "epoch": 2.808988764044944,
      "grad_norm": 568053.375,
      "learning_rate": 5e-05,
      "loss": 0.1667,
      "step": 250
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.14878585934638977,
      "eval_rmse": 0.3857277035713196,
      "eval_runtime": 9.1378,
      "eval_samples_per_second": 109.436,
      "eval_steps_per_second": 1.751,
      "step": 267
    },
    {
      "epoch": 3.0898876404494384,
      "grad_norm": 234025.9375,
      "learning_rate": 4.918300653594771e-05,
      "loss": 0.1701,
      "step": 275
    },
    {
      "epoch": 3.370786516853933,
      "grad_norm": 1965555.75,
      "learning_rate": 4.8366013071895424e-05,
      "loss": 0.1514,
      "step": 300
    },
    {
      "epoch": 3.6516853932584272,
      "grad_norm": 851152.4375,
      "learning_rate": 4.7549019607843135e-05,
      "loss": 0.1577,
      "step": 325
    },
    {
      "epoch": 3.932584269662921,
      "grad_norm": 746618.4375,
      "learning_rate": 4.673202614379085e-05,
      "loss": 0.1487,
      "step": 350
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.15289434790611267,
      "eval_rmse": 0.3910170793533325,
      "eval_runtime": 8.8946,
      "eval_samples_per_second": 112.428,
      "eval_steps_per_second": 1.799,
      "step": 356
    },
    {
      "epoch": 4.213483146067416,
      "grad_norm": 1243115.125,
      "learning_rate": 4.5915032679738564e-05,
      "loss": 0.1504,
      "step": 375
    },
    {
      "epoch": 4.49438202247191,
      "grad_norm": 1589738.0,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.1497,
      "step": 400
    },
    {
      "epoch": 4.775280898876405,
      "grad_norm": 2689456.25,
      "learning_rate": 4.4281045751633986e-05,
      "loss": 0.153,
      "step": 425
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.1420373022556305,
      "eval_rmse": 0.37687838077545166,
      "eval_runtime": 9.1741,
      "eval_samples_per_second": 109.002,
      "eval_steps_per_second": 1.744,
      "step": 445
    },
    {
      "epoch": 5.056179775280899,
      "grad_norm": 1829392.75,
      "learning_rate": 4.3464052287581704e-05,
      "loss": 0.148,
      "step": 450
    },
    {
      "epoch": 5.337078651685394,
      "grad_norm": 1871118.375,
      "learning_rate": 4.2647058823529415e-05,
      "loss": 0.1563,
      "step": 475
    },
    {
      "epoch": 5.617977528089888,
      "grad_norm": 407695.96875,
      "learning_rate": 4.1830065359477126e-05,
      "loss": 0.1614,
      "step": 500
    },
    {
      "epoch": 5.898876404494382,
      "grad_norm": 2876208.0,
      "learning_rate": 4.101307189542484e-05,
      "loss": 0.1516,
      "step": 525
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.1412646770477295,
      "eval_rmse": 0.37585192918777466,
      "eval_runtime": 9.4039,
      "eval_samples_per_second": 106.339,
      "eval_steps_per_second": 1.701,
      "step": 534
    },
    {
      "epoch": 6.179775280898877,
      "grad_norm": 1888194.125,
      "learning_rate": 4.0196078431372555e-05,
      "loss": 0.1484,
      "step": 550
    },
    {
      "epoch": 6.460674157303371,
      "grad_norm": 2303002.75,
      "learning_rate": 3.9379084967320266e-05,
      "loss": 0.1544,
      "step": 575
    },
    {
      "epoch": 6.741573033707866,
      "grad_norm": 3461513.0,
      "learning_rate": 3.8562091503267977e-05,
      "loss": 0.1492,
      "step": 600
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.14228275418281555,
      "eval_rmse": 0.3772038519382477,
      "eval_runtime": 9.0867,
      "eval_samples_per_second": 110.051,
      "eval_steps_per_second": 1.761,
      "step": 623
    },
    {
      "epoch": 7.022471910112359,
      "grad_norm": 1115296.0,
      "learning_rate": 3.774509803921569e-05,
      "loss": 0.1452,
      "step": 625
    },
    {
      "epoch": 7.303370786516854,
      "grad_norm": 951385.5,
      "learning_rate": 3.6928104575163405e-05,
      "loss": 0.1481,
      "step": 650
    },
    {
      "epoch": 7.584269662921348,
      "grad_norm": 1324887.875,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.1436,
      "step": 675
    },
    {
      "epoch": 7.865168539325842,
      "grad_norm": 1049904.875,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.1472,
      "step": 700
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.14021900296211243,
      "eval_rmse": 0.3744582533836365,
      "eval_runtime": 9.2311,
      "eval_samples_per_second": 108.33,
      "eval_steps_per_second": 1.733,
      "step": 712
    },
    {
      "epoch": 8.146067415730338,
      "grad_norm": 2260510.0,
      "learning_rate": 3.447712418300654e-05,
      "loss": 0.1457,
      "step": 725
    },
    {
      "epoch": 8.426966292134832,
      "grad_norm": 866467.125,
      "learning_rate": 3.366013071895425e-05,
      "loss": 0.1407,
      "step": 750
    },
    {
      "epoch": 8.707865168539326,
      "grad_norm": 1763516.375,
      "learning_rate": 3.284313725490196e-05,
      "loss": 0.1428,
      "step": 775
    },
    {
      "epoch": 8.98876404494382,
      "grad_norm": 1886526.5,
      "learning_rate": 3.202614379084967e-05,
      "loss": 0.1507,
      "step": 800
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.14308789372444153,
      "eval_rmse": 0.37826961278915405,
      "eval_runtime": 9.0525,
      "eval_samples_per_second": 110.466,
      "eval_steps_per_second": 1.767,
      "step": 801
    },
    {
      "epoch": 9.269662921348315,
      "grad_norm": 268722.6875,
      "learning_rate": 3.120915032679739e-05,
      "loss": 0.1452,
      "step": 825
    },
    {
      "epoch": 9.55056179775281,
      "grad_norm": 35291.34375,
      "learning_rate": 3.0392156862745097e-05,
      "loss": 0.1457,
      "step": 850
    },
    {
      "epoch": 9.831460674157304,
      "grad_norm": 3213099.0,
      "learning_rate": 2.957516339869281e-05,
      "loss": 0.1494,
      "step": 875
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.13986632227897644,
      "eval_rmse": 0.3739870488643646,
      "eval_runtime": 9.3282,
      "eval_samples_per_second": 107.201,
      "eval_steps_per_second": 1.715,
      "step": 890
    },
    {
      "epoch": 10.112359550561798,
      "grad_norm": 364516.15625,
      "learning_rate": 2.8758169934640522e-05,
      "loss": 0.1496,
      "step": 900
    },
    {
      "epoch": 10.393258426966293,
      "grad_norm": 646683.375,
      "learning_rate": 2.7941176470588236e-05,
      "loss": 0.1519,
      "step": 925
    },
    {
      "epoch": 10.674157303370787,
      "grad_norm": 157647.40625,
      "learning_rate": 2.7124183006535947e-05,
      "loss": 0.1564,
      "step": 950
    },
    {
      "epoch": 10.955056179775282,
      "grad_norm": 436840.03125,
      "learning_rate": 2.630718954248366e-05,
      "loss": 0.1483,
      "step": 975
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.1415373831987381,
      "eval_rmse": 0.37621453404426575,
      "eval_runtime": 9.0431,
      "eval_samples_per_second": 110.581,
      "eval_steps_per_second": 1.769,
      "step": 979
    },
    {
      "epoch": 11.235955056179776,
      "grad_norm": 1514792.0,
      "learning_rate": 2.5490196078431373e-05,
      "loss": 0.1415,
      "step": 1000
    },
    {
      "epoch": 11.51685393258427,
      "grad_norm": 611788.6875,
      "learning_rate": 2.4673202614379087e-05,
      "loss": 0.1462,
      "step": 1025
    },
    {
      "epoch": 11.797752808988765,
      "grad_norm": 1177116.5,
      "learning_rate": 2.38562091503268e-05,
      "loss": 0.1447,
      "step": 1050
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.14167071878910065,
      "eval_rmse": 0.3763917088508606,
      "eval_runtime": 9.3028,
      "eval_samples_per_second": 107.495,
      "eval_steps_per_second": 1.72,
      "step": 1068
    },
    {
      "epoch": 12.07865168539326,
      "grad_norm": 1233414.0,
      "learning_rate": 2.303921568627451e-05,
      "loss": 0.1433,
      "step": 1075
    },
    {
      "epoch": 12.359550561797754,
      "grad_norm": 323718.25,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.1409,
      "step": 1100
    },
    {
      "epoch": 12.640449438202246,
      "grad_norm": 1150212.0,
      "learning_rate": 2.1405228758169934e-05,
      "loss": 0.1427,
      "step": 1125
    },
    {
      "epoch": 12.921348314606742,
      "grad_norm": 845101.5625,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.1562,
      "step": 1150
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.14507122337818146,
      "eval_rmse": 0.380882203578949,
      "eval_runtime": 8.886,
      "eval_samples_per_second": 112.536,
      "eval_steps_per_second": 1.801,
      "step": 1157
    },
    {
      "epoch": 13.202247191011235,
      "grad_norm": 833533.0,
      "learning_rate": 1.977124183006536e-05,
      "loss": 0.1502,
      "step": 1175
    },
    {
      "epoch": 13.48314606741573,
      "grad_norm": 2828633.0,
      "learning_rate": 1.895424836601307e-05,
      "loss": 0.1541,
      "step": 1200
    },
    {
      "epoch": 13.764044943820224,
      "grad_norm": 195191.921875,
      "learning_rate": 1.8137254901960785e-05,
      "loss": 0.1444,
      "step": 1225
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.14213800430297852,
      "eval_rmse": 0.3770119547843933,
      "eval_runtime": 9.1277,
      "eval_samples_per_second": 109.556,
      "eval_steps_per_second": 1.753,
      "step": 1246
    },
    {
      "epoch": 14.044943820224718,
      "grad_norm": 976718.9375,
      "learning_rate": 1.7320261437908496e-05,
      "loss": 0.1433,
      "step": 1250
    },
    {
      "epoch": 14.325842696629213,
      "grad_norm": 240414.078125,
      "learning_rate": 1.650326797385621e-05,
      "loss": 0.1411,
      "step": 1275
    },
    {
      "epoch": 14.606741573033707,
      "grad_norm": 1395570.375,
      "learning_rate": 1.568627450980392e-05,
      "loss": 0.1427,
      "step": 1300
    },
    {
      "epoch": 14.887640449438202,
      "grad_norm": 69238.7109375,
      "learning_rate": 1.4869281045751634e-05,
      "loss": 0.1474,
      "step": 1325
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.13990294933319092,
      "eval_rmse": 0.3740360140800476,
      "eval_runtime": 9.2196,
      "eval_samples_per_second": 108.465,
      "eval_steps_per_second": 1.735,
      "step": 1335
    },
    {
      "epoch": 15.168539325842696,
      "grad_norm": 1121152.75,
      "learning_rate": 1.4052287581699347e-05,
      "loss": 0.141,
      "step": 1350
    },
    {
      "epoch": 15.44943820224719,
      "grad_norm": 321656.96875,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.1439,
      "step": 1375
    },
    {
      "epoch": 15.730337078651685,
      "grad_norm": 148007.78125,
      "learning_rate": 1.2418300653594772e-05,
      "loss": 0.1414,
      "step": 1400
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.14314845204353333,
      "eval_rmse": 0.3783496618270874,
      "eval_runtime": 9.1061,
      "eval_samples_per_second": 109.817,
      "eval_steps_per_second": 1.757,
      "step": 1424
    },
    {
      "epoch": 16.01123595505618,
      "grad_norm": 1851991.5,
      "learning_rate": 1.1601307189542485e-05,
      "loss": 0.1454,
      "step": 1425
    },
    {
      "epoch": 16.292134831460675,
      "grad_norm": 42276.51171875,
      "learning_rate": 1.0784313725490197e-05,
      "loss": 0.1427,
      "step": 1450
    },
    {
      "epoch": 16.573033707865168,
      "grad_norm": 302381.03125,
      "learning_rate": 9.96732026143791e-06,
      "loss": 0.1446,
      "step": 1475
    },
    {
      "epoch": 16.853932584269664,
      "grad_norm": 51647.3046875,
      "learning_rate": 9.150326797385621e-06,
      "loss": 0.1411,
      "step": 1500
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.13933230936527252,
      "eval_rmse": 0.37327244877815247,
      "eval_runtime": 9.0522,
      "eval_samples_per_second": 110.471,
      "eval_steps_per_second": 1.768,
      "step": 1513
    },
    {
      "epoch": 17.134831460674157,
      "grad_norm": 385612.03125,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.1421,
      "step": 1525
    },
    {
      "epoch": 17.415730337078653,
      "grad_norm": 76190.3203125,
      "learning_rate": 7.5163398692810456e-06,
      "loss": 0.1426,
      "step": 1550
    },
    {
      "epoch": 17.696629213483146,
      "grad_norm": 1091171.375,
      "learning_rate": 6.699346405228758e-06,
      "loss": 0.1391,
      "step": 1575
    },
    {
      "epoch": 17.97752808988764,
      "grad_norm": 344962.09375,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.1394,
      "step": 1600
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.13929913938045502,
      "eval_rmse": 0.3732280135154724,
      "eval_runtime": 9.0911,
      "eval_samples_per_second": 109.998,
      "eval_steps_per_second": 1.76,
      "step": 1602
    },
    {
      "epoch": 18.258426966292134,
      "grad_norm": 226082.828125,
      "learning_rate": 5.065359477124184e-06,
      "loss": 0.1391,
      "step": 1625
    },
    {
      "epoch": 18.53932584269663,
      "grad_norm": 3716.295654296875,
      "learning_rate": 4.2483660130718954e-06,
      "loss": 0.1385,
      "step": 1650
    },
    {
      "epoch": 18.820224719101123,
      "grad_norm": 57442.78515625,
      "learning_rate": 3.431372549019608e-06,
      "loss": 0.1427,
      "step": 1675
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.13926273584365845,
      "eval_rmse": 0.37317925691604614,
      "eval_runtime": 9.1349,
      "eval_samples_per_second": 109.471,
      "eval_steps_per_second": 1.752,
      "step": 1691
    },
    {
      "epoch": 19.10112359550562,
      "grad_norm": 204073.96875,
      "learning_rate": 2.6143790849673204e-06,
      "loss": 0.1406,
      "step": 1700
    },
    {
      "epoch": 19.382022471910112,
      "grad_norm": 7520.126953125,
      "learning_rate": 1.7973856209150326e-06,
      "loss": 0.1404,
      "step": 1725
    },
    {
      "epoch": 19.662921348314608,
      "grad_norm": 312753.4375,
      "learning_rate": 9.80392156862745e-07,
      "loss": 0.1402,
      "step": 1750
    },
    {
      "epoch": 19.9438202247191,
      "grad_norm": 339669.75,
      "learning_rate": 1.6339869281045752e-07,
      "loss": 0.139,
      "step": 1775
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.13911749422550201,
      "eval_rmse": 0.3729845881462097,
      "eval_runtime": 9.2284,
      "eval_samples_per_second": 108.361,
      "eval_steps_per_second": 1.734,
      "step": 1780
    },
    {
      "epoch": 20.0,
      "step": 1780,
      "total_flos": 0.0,
      "train_loss": 0.15459485087501867,
      "train_runtime": 3248.8153,
      "train_samples_per_second": 34.856,
      "train_steps_per_second": 0.548
    }
  ],
  "logging_steps": 25,
  "max_steps": 1780,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}