{
  "best_metric": 90.49664002544833,
  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-English-EWT/checkpoint-7500",
  "epoch": 25.510204081632654,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26,
      "learning_rate": 7.52e-05,
      "loss": 3.6373,
      "step": 100
    },
    {
      "epoch": 0.51,
      "learning_rate": 7.949530201342283e-05,
      "loss": 0.7868,
      "step": 200
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.895838926174497e-05,
      "loss": 0.6003,
      "step": 300
    },
    {
      "epoch": 1.02,
      "learning_rate": 7.842147651006712e-05,
      "loss": 0.4937,
      "step": 400
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.788456375838927e-05,
      "loss": 0.3314,
      "step": 500
    },
    {
      "epoch": 1.28,
      "eval_las": 88.67151775418506,
      "eval_loss": 0.4770449995994568,
      "eval_runtime": 12.8846,
      "eval_samples_per_second": 155.301,
      "eval_steps_per_second": 19.481,
      "eval_uas": 91.08513260964651,
      "step": 500
    },
    {
      "epoch": 1.53,
      "learning_rate": 7.734765100671142e-05,
      "loss": 0.3157,
      "step": 600
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.681073825503357e-05,
      "loss": 0.3354,
      "step": 700
    },
    {
      "epoch": 2.04,
      "learning_rate": 7.627382550335572e-05,
      "loss": 0.2813,
      "step": 800
    },
    {
      "epoch": 2.3,
      "learning_rate": 7.573691275167786e-05,
      "loss": 0.1771,
      "step": 900
    },
    {
      "epoch": 2.55,
      "learning_rate": 7.52e-05,
      "loss": 0.1868,
      "step": 1000
    },
    {
      "epoch": 2.55,
      "eval_las": 89.37532307447611,
      "eval_loss": 0.5148924589157104,
      "eval_runtime": 12.9189,
      "eval_samples_per_second": 154.889,
      "eval_steps_per_second": 19.429,
      "eval_uas": 91.68953039882301,
      "step": 1000
    },
    {
      "epoch": 2.81,
      "learning_rate": 7.466308724832215e-05,
      "loss": 0.18,
      "step": 1100
    },
    {
      "epoch": 3.06,
      "learning_rate": 7.41261744966443e-05,
      "loss": 0.1798,
      "step": 1200
    },
    {
      "epoch": 3.32,
      "learning_rate": 7.358926174496644e-05,
      "loss": 0.1099,
      "step": 1300
    },
    {
      "epoch": 3.57,
      "learning_rate": 7.305234899328859e-05,
      "loss": 0.1302,
      "step": 1400
    },
    {
      "epoch": 3.83,
      "learning_rate": 7.251543624161074e-05,
      "loss": 0.1241,
      "step": 1500
    },
    {
      "epoch": 3.83,
      "eval_las": 89.86440812755974,
      "eval_loss": 0.5785237550735474,
      "eval_runtime": 12.921,
      "eval_samples_per_second": 154.864,
      "eval_steps_per_second": 19.426,
      "eval_uas": 92.11499463199331,
      "step": 1500
    },
    {
      "epoch": 4.08,
      "learning_rate": 7.197852348993289e-05,
      "loss": 0.1088,
      "step": 1600
    },
    {
      "epoch": 4.34,
      "learning_rate": 7.144161073825504e-05,
      "loss": 0.086,
      "step": 1700
    },
    {
      "epoch": 4.59,
      "learning_rate": 7.090469798657718e-05,
      "loss": 0.0918,
      "step": 1800
    },
    {
      "epoch": 4.85,
      "learning_rate": 7.036778523489933e-05,
      "loss": 0.092,
      "step": 1900
    },
    {
      "epoch": 5.1,
      "learning_rate": 6.983087248322148e-05,
      "loss": 0.0802,
      "step": 2000
    },
    {
      "epoch": 5.1,
      "eval_las": 90.06322318978886,
      "eval_loss": 0.7516521215438843,
      "eval_runtime": 12.9274,
      "eval_samples_per_second": 154.787,
      "eval_steps_per_second": 19.416,
      "eval_uas": 92.23825997057537,
      "step": 2000
    },
    {
      "epoch": 5.36,
      "learning_rate": 6.929395973154363e-05,
      "loss": 0.0653,
      "step": 2100
    },
    {
      "epoch": 5.61,
      "learning_rate": 6.875704697986578e-05,
      "loss": 0.0647,
      "step": 2200
    },
    {
      "epoch": 5.87,
      "learning_rate": 6.822013422818793e-05,
      "loss": 0.0753,
      "step": 2300
    },
    {
      "epoch": 6.12,
      "learning_rate": 6.768322147651007e-05,
      "loss": 0.0639,
      "step": 2400
    },
    {
      "epoch": 6.38,
      "learning_rate": 6.714630872483222e-05,
      "loss": 0.0542,
      "step": 2500
    },
    {
      "epoch": 6.38,
      "eval_las": 90.0552705872997,
      "eval_loss": 0.7744932174682617,
      "eval_runtime": 12.9222,
      "eval_samples_per_second": 154.85,
      "eval_steps_per_second": 19.424,
      "eval_uas": 92.34164380293451,
      "step": 2500
    },
    {
      "epoch": 6.63,
      "learning_rate": 6.660939597315437e-05,
      "loss": 0.0525,
      "step": 2600
    },
    {
      "epoch": 6.89,
      "learning_rate": 6.607248322147652e-05,
      "loss": 0.0607,
      "step": 2700
    },
    {
      "epoch": 7.14,
      "learning_rate": 6.553557046979867e-05,
      "loss": 0.0499,
      "step": 2800
    },
    {
      "epoch": 7.4,
      "learning_rate": 6.499865771812081e-05,
      "loss": 0.0475,
      "step": 2900
    },
    {
      "epoch": 7.65,
      "learning_rate": 6.446174496644296e-05,
      "loss": 0.0488,
      "step": 3000
    },
    {
      "epoch": 7.65,
      "eval_las": 90.06322318978886,
      "eval_loss": 0.6991102695465088,
      "eval_runtime": 12.8997,
      "eval_samples_per_second": 155.119,
      "eval_steps_per_second": 19.458,
      "eval_uas": 92.27007038053203,
      "step": 3000
    },
    {
      "epoch": 7.91,
      "learning_rate": 6.392483221476511e-05,
      "loss": 0.0498,
      "step": 3100
    },
    {
      "epoch": 8.16,
      "learning_rate": 6.338791946308726e-05,
      "loss": 0.0452,
      "step": 3200
    },
    {
      "epoch": 8.42,
      "learning_rate": 6.28510067114094e-05,
      "loss": 0.0423,
      "step": 3300
    },
    {
      "epoch": 8.67,
      "learning_rate": 6.231409395973154e-05,
      "loss": 0.0434,
      "step": 3400
    },
    {
      "epoch": 8.93,
      "learning_rate": 6.177718120805369e-05,
      "loss": 0.0417,
      "step": 3500
    },
    {
      "epoch": 8.93,
      "eval_las": 90.22227523957214,
      "eval_loss": 0.8318419456481934,
      "eval_runtime": 12.8987,
      "eval_samples_per_second": 155.132,
      "eval_steps_per_second": 19.459,
      "eval_uas": 92.35357270666825,
      "step": 3500
    },
    {
      "epoch": 9.18,
      "learning_rate": 6.124026845637584e-05,
      "loss": 0.0391,
      "step": 3600
    },
    {
      "epoch": 9.44,
      "learning_rate": 6.070335570469799e-05,
      "loss": 0.0369,
      "step": 3700
    },
    {
      "epoch": 9.69,
      "learning_rate": 6.0166442953020136e-05,
      "loss": 0.0329,
      "step": 3800
    },
    {
      "epoch": 9.95,
      "learning_rate": 5.962953020134229e-05,
      "loss": 0.0329,
      "step": 3900
    },
    {
      "epoch": 10.2,
      "learning_rate": 5.909261744966444e-05,
      "loss": 0.0289,
      "step": 4000
    },
    {
      "epoch": 10.2,
      "eval_las": 90.11491510596844,
      "eval_loss": 0.9339661002159119,
      "eval_runtime": 12.8923,
      "eval_samples_per_second": 155.209,
      "eval_steps_per_second": 19.469,
      "eval_uas": 92.26211777804286,
      "step": 4000
    },
    {
      "epoch": 10.46,
      "learning_rate": 5.855570469798659e-05,
      "loss": 0.0311,
      "step": 4100
    },
    {
      "epoch": 10.71,
      "learning_rate": 5.8018791946308735e-05,
      "loss": 0.0294,
      "step": 4200
    },
    {
      "epoch": 10.97,
      "learning_rate": 5.7481879194630884e-05,
      "loss": 0.0312,
      "step": 4300
    },
    {
      "epoch": 11.22,
      "learning_rate": 5.694496644295303e-05,
      "loss": 0.0226,
      "step": 4400
    },
    {
      "epoch": 11.48,
      "learning_rate": 5.6408053691275166e-05,
      "loss": 0.0249,
      "step": 4500
    },
    {
      "epoch": 11.48,
      "eval_las": 90.21829893832756,
      "eval_loss": 0.850771963596344,
      "eval_runtime": 12.8981,
      "eval_samples_per_second": 155.139,
      "eval_steps_per_second": 19.46,
      "eval_uas": 92.34562010417909,
      "step": 4500
    },
    {
      "epoch": 11.73,
      "learning_rate": 5.5871140939597315e-05,
      "loss": 0.025,
      "step": 4600
    },
    {
      "epoch": 11.99,
      "learning_rate": 5.533422818791946e-05,
      "loss": 0.0297,
      "step": 4700
    },
    {
      "epoch": 12.24,
      "learning_rate": 5.479731543624161e-05,
      "loss": 0.022,
      "step": 4800
    },
    {
      "epoch": 12.5,
      "learning_rate": 5.426040268456376e-05,
      "loss": 0.0237,
      "step": 4900
    },
    {
      "epoch": 12.76,
      "learning_rate": 5.372348993288591e-05,
      "loss": 0.0244,
      "step": 5000
    },
    {
      "epoch": 12.76,
      "eval_las": 90.2779434569963,
      "eval_loss": 0.84713214635849,
      "eval_runtime": 12.9629,
      "eval_samples_per_second": 154.363,
      "eval_steps_per_second": 19.363,
      "eval_uas": 92.48876694898406,
      "step": 5000
    },
    {
      "epoch": 13.01,
      "learning_rate": 5.3186577181208056e-05,
      "loss": 0.0255,
      "step": 5100
    },
    {
      "epoch": 13.27,
      "learning_rate": 5.2649664429530204e-05,
      "loss": 0.0175,
      "step": 5200
    },
    {
      "epoch": 13.52,
      "learning_rate": 5.211275167785235e-05,
      "loss": 0.0285,
      "step": 5300
    },
    {
      "epoch": 13.78,
      "learning_rate": 5.15758389261745e-05,
      "loss": 0.0238,
      "step": 5400
    },
    {
      "epoch": 14.03,
      "learning_rate": 5.1038926174496656e-05,
      "loss": 0.0214,
      "step": 5500
    },
    {
      "epoch": 14.03,
      "eval_las": 89.99960236987555,
      "eval_loss": 0.9246010780334473,
      "eval_runtime": 12.9247,
      "eval_samples_per_second": 154.82,
      "eval_steps_per_second": 19.42,
      "eval_uas": 92.1627102469283,
      "step": 5500
    },
    {
      "epoch": 14.29,
      "learning_rate": 5.050201342281879e-05,
      "loss": 0.0179,
      "step": 5600
    },
    {
      "epoch": 14.54,
      "learning_rate": 4.996510067114094e-05,
      "loss": 0.0192,
      "step": 5700
    },
    {
      "epoch": 14.8,
      "learning_rate": 4.942818791946309e-05,
      "loss": 0.0218,
      "step": 5800
    },
    {
      "epoch": 15.05,
      "learning_rate": 4.8891275167785235e-05,
      "loss": 0.0215,
      "step": 5900
    },
    {
      "epoch": 15.31,
      "learning_rate": 4.835436241610738e-05,
      "loss": 0.0165,
      "step": 6000
    },
    {
      "epoch": 15.31,
      "eval_las": 89.90814744125015,
      "eval_loss": 1.003578782081604,
      "eval_runtime": 12.9261,
      "eval_samples_per_second": 154.803,
      "eval_steps_per_second": 19.418,
      "eval_uas": 92.17066284941747,
      "step": 6000
    },
    {
      "epoch": 15.56,
      "learning_rate": 4.781744966442953e-05,
      "loss": 0.0166,
      "step": 6100
    },
    {
      "epoch": 15.82,
      "learning_rate": 4.728053691275168e-05,
      "loss": 0.0184,
      "step": 6200
    },
    {
      "epoch": 16.07,
      "learning_rate": 4.674362416107383e-05,
      "loss": 0.0174,
      "step": 6300
    },
    {
      "epoch": 16.33,
      "learning_rate": 4.6206711409395976e-05,
      "loss": 0.0139,
      "step": 6400
    },
    {
      "epoch": 16.58,
      "learning_rate": 4.5669798657718125e-05,
      "loss": 0.015,
      "step": 6500
    },
    {
      "epoch": 16.58,
      "eval_las": 90.1904648296155,
      "eval_loss": 1.006374478340149,
      "eval_runtime": 12.9169,
      "eval_samples_per_second": 154.913,
      "eval_steps_per_second": 19.432,
      "eval_uas": 92.30585709173327,
      "step": 6500
    },
    {
      "epoch": 16.84,
      "learning_rate": 4.513288590604027e-05,
      "loss": 0.0166,
      "step": 6600
    },
    {
      "epoch": 17.09,
      "learning_rate": 4.459597315436242e-05,
      "loss": 0.0142,
      "step": 6700
    },
    {
      "epoch": 17.35,
      "learning_rate": 4.405906040268456e-05,
      "loss": 0.0144,
      "step": 6800
    },
    {
      "epoch": 17.6,
      "learning_rate": 4.352214765100671e-05,
      "loss": 0.0115,
      "step": 6900
    },
    {
      "epoch": 17.86,
      "learning_rate": 4.298523489932886e-05,
      "loss": 0.0135,
      "step": 7000
    },
    {
      "epoch": 17.86,
      "eval_las": 90.13479661219134,
      "eval_loss": 1.039555549621582,
      "eval_runtime": 12.9436,
      "eval_samples_per_second": 154.594,
      "eval_steps_per_second": 19.392,
      "eval_uas": 92.26211777804286,
      "step": 7000
    },
    {
      "epoch": 18.11,
      "learning_rate": 4.244832214765101e-05,
      "loss": 0.0117,
      "step": 7100
    },
    {
      "epoch": 18.37,
      "learning_rate": 4.1911409395973156e-05,
      "loss": 0.0137,
      "step": 7200
    },
    {
      "epoch": 18.62,
      "learning_rate": 4.1374496644295304e-05,
      "loss": 0.0107,
      "step": 7300
    },
    {
      "epoch": 18.88,
      "learning_rate": 4.083758389261745e-05,
      "loss": 0.0113,
      "step": 7400
    },
    {
      "epoch": 19.13,
      "learning_rate": 4.03006711409396e-05,
      "loss": 0.0118,
      "step": 7500
    },
    {
      "epoch": 19.13,
      "eval_las": 90.49664002544833,
      "eval_loss": 1.0788443088531494,
      "eval_runtime": 12.946,
      "eval_samples_per_second": 154.565,
      "eval_steps_per_second": 19.388,
      "eval_uas": 92.62793749254443,
      "step": 7500
    },
    {
      "epoch": 19.39,
      "learning_rate": 3.976375838926175e-05,
      "loss": 0.0192,
      "step": 7600
    },
    {
      "epoch": 19.64,
      "learning_rate": 3.92268456375839e-05,
      "loss": 0.0116,
      "step": 7700
    },
    {
      "epoch": 19.9,
      "learning_rate": 3.8689932885906045e-05,
      "loss": 0.0117,
      "step": 7800
    },
    {
      "epoch": 20.15,
      "learning_rate": 3.815302013422819e-05,
      "loss": 0.0142,
      "step": 7900
    },
    {
      "epoch": 20.41,
      "learning_rate": 3.761610738255034e-05,
      "loss": 0.0089,
      "step": 8000
    },
    {
      "epoch": 20.41,
      "eval_las": 90.34156427690961,
      "eval_loss": 1.065735936164856,
      "eval_runtime": 12.9533,
      "eval_samples_per_second": 154.478,
      "eval_steps_per_second": 19.377,
      "eval_uas": 92.4092409240924,
      "step": 8000
    },
    {
      "epoch": 20.66,
      "learning_rate": 3.707919463087249e-05,
      "loss": 0.0121,
      "step": 8100
    },
    {
      "epoch": 20.92,
      "learning_rate": 3.654228187919463e-05,
      "loss": 0.0112,
      "step": 8200
    },
    {
      "epoch": 21.17,
      "learning_rate": 3.600536912751678e-05,
      "loss": 0.0079,
      "step": 8300
    },
    {
      "epoch": 21.43,
      "learning_rate": 3.546845637583893e-05,
      "loss": 0.009,
      "step": 8400
    },
    {
      "epoch": 21.68,
      "learning_rate": 3.4931543624161076e-05,
      "loss": 0.0092,
      "step": 8500
    },
    {
      "epoch": 21.68,
      "eval_las": 90.38927989184461,
      "eval_loss": 1.0594043731689453,
      "eval_runtime": 12.978,
      "eval_samples_per_second": 154.184,
      "eval_steps_per_second": 19.34,
      "eval_uas": 92.49671955147322,
      "step": 8500
    },
    {
      "epoch": 21.94,
      "learning_rate": 3.4394630872483224e-05,
      "loss": 0.0064,
      "step": 8600
    },
    {
      "epoch": 22.19,
      "learning_rate": 3.385771812080537e-05,
      "loss": 0.0081,
      "step": 8700
    },
    {
      "epoch": 22.45,
      "learning_rate": 3.332080536912752e-05,
      "loss": 0.0079,
      "step": 8800
    },
    {
      "epoch": 22.7,
      "learning_rate": 3.278389261744967e-05,
      "loss": 0.0085,
      "step": 8900
    },
    {
      "epoch": 22.96,
      "learning_rate": 3.224697986577182e-05,
      "loss": 0.0089,
      "step": 9000
    },
    {
      "epoch": 22.96,
      "eval_las": 90.47675851922541,
      "eval_loss": 1.0339850187301636,
      "eval_runtime": 12.9806,
      "eval_samples_per_second": 154.153,
      "eval_steps_per_second": 19.337,
      "eval_uas": 92.54045886516363,
      "step": 9000
    },
    {
      "epoch": 23.21,
      "learning_rate": 3.1710067114093965e-05,
      "loss": 0.0068,
      "step": 9100
    },
    {
      "epoch": 23.47,
      "learning_rate": 3.1173154362416114e-05,
      "loss": 0.0047,
      "step": 9200
    },
    {
      "epoch": 23.72,
      "learning_rate": 3.0636241610738255e-05,
      "loss": 0.0064,
      "step": 9300
    },
    {
      "epoch": 23.98,
      "learning_rate": 3.0099328859060403e-05,
      "loss": 0.0071,
      "step": 9400
    },
    {
      "epoch": 24.23,
      "learning_rate": 2.956241610738255e-05,
      "loss": 0.0056,
      "step": 9500
    },
    {
      "epoch": 24.23,
      "eval_las": 90.49266372420375,
      "eval_loss": 1.0786528587341309,
      "eval_runtime": 12.983,
      "eval_samples_per_second": 154.125,
      "eval_steps_per_second": 19.333,
      "eval_uas": 92.57624557636487,
      "step": 9500
    },
    {
      "epoch": 24.49,
      "learning_rate": 2.90255033557047e-05,
      "loss": 0.0072,
      "step": 9600
    },
    {
      "epoch": 24.74,
      "learning_rate": 2.8488590604026848e-05,
      "loss": 0.0055,
      "step": 9700
    },
    {
      "epoch": 25.0,
      "learning_rate": 2.7951677852348996e-05,
      "loss": 0.0074,
      "step": 9800
    },
    {
      "epoch": 25.26,
      "learning_rate": 2.741476510067114e-05,
      "loss": 0.004,
      "step": 9900
    },
    {
      "epoch": 25.51,
      "learning_rate": 2.687785234899329e-05,
      "loss": 0.0045,
      "step": 10000
    },
    {
      "epoch": 25.51,
      "eval_las": 90.43301920553502,
      "eval_loss": 1.2013182640075684,
      "eval_runtime": 12.9849,
      "eval_samples_per_second": 154.102,
      "eval_steps_per_second": 19.33,
      "eval_uas": 92.4768380452503,
      "step": 10000
    },
    {
      "epoch": 25.51,
      "step": 10000,
      "total_flos": 5.34284250892032e+16,
      "train_loss": 0.1020653991997242,
      "train_runtime": 5461.7633,
      "train_samples_per_second": 87.884,
      "train_steps_per_second": 2.746
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 39,
  "total_flos": 5.34284250892032e+16,
  "trial_name": null,
  "trial_params": null
}