{
  "best_metric": 68.56690419635788,
  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-parsing-ud-Tamil-TTB/checkpoint-1500",
  "epoch": 307.6923076923077,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.69,
      "learning_rate": 7.680000000000001e-05,
      "loss": 2.8111,
      "step": 100
    },
    {
      "epoch": 15.38,
      "learning_rate": 7.948456375838927e-05,
      "loss": 0.2559,
      "step": 200
    },
    {
      "epoch": 23.08,
      "learning_rate": 7.894765100671142e-05,
      "loss": 0.1068,
      "step": 300
    },
    {
      "epoch": 30.77,
      "learning_rate": 7.841073825503357e-05,
      "loss": 0.0779,
      "step": 400
    },
    {
      "epoch": 38.46,
      "learning_rate": 7.78738255033557e-05,
      "loss": 0.056,
      "step": 500
    },
    {
      "epoch": 38.46,
      "eval_las": 67.2209026128266,
      "eval_loss": 4.200492858886719,
      "eval_runtime": 0.5418,
      "eval_samples_per_second": 147.645,
      "eval_steps_per_second": 18.456,
      "eval_uas": 78.4639746634996,
      "step": 500
    },
    {
      "epoch": 46.15,
      "learning_rate": 7.733691275167786e-05,
      "loss": 0.0501,
      "step": 600
    },
    {
      "epoch": 53.85,
      "learning_rate": 7.680000000000001e-05,
      "loss": 0.0416,
      "step": 700
    },
    {
      "epoch": 61.54,
      "learning_rate": 7.626308724832216e-05,
      "loss": 0.036,
      "step": 800
    },
    {
      "epoch": 69.23,
      "learning_rate": 7.57261744966443e-05,
      "loss": 0.0322,
      "step": 900
    },
    {
      "epoch": 76.92,
      "learning_rate": 7.518926174496645e-05,
      "loss": 0.0312,
      "step": 1000
    },
    {
      "epoch": 76.92,
      "eval_las": 66.0332541567696,
      "eval_loss": 5.273917198181152,
      "eval_runtime": 0.5321,
      "eval_samples_per_second": 150.34,
      "eval_steps_per_second": 18.793,
      "eval_uas": 76.72209026128266,
      "step": 1000
    },
    {
      "epoch": 84.62,
      "learning_rate": 7.46523489932886e-05,
      "loss": 0.0244,
      "step": 1100
    },
    {
      "epoch": 92.31,
      "learning_rate": 7.411543624161075e-05,
      "loss": 0.0265,
      "step": 1200
    },
    {
      "epoch": 100.0,
      "learning_rate": 7.35785234899329e-05,
      "loss": 0.021,
      "step": 1300
    },
    {
      "epoch": 107.69,
      "learning_rate": 7.304161073825505e-05,
      "loss": 0.0229,
      "step": 1400
    },
    {
      "epoch": 115.38,
      "learning_rate": 7.25046979865772e-05,
      "loss": 0.0168,
      "step": 1500
    },
    {
      "epoch": 115.38,
      "eval_las": 68.56690419635788,
      "eval_loss": 6.0272111892700195,
      "eval_runtime": 0.533,
      "eval_samples_per_second": 150.087,
      "eval_steps_per_second": 18.761,
      "eval_uas": 78.06809184481394,
      "step": 1500
    },
    {
      "epoch": 123.08,
      "learning_rate": 7.196778523489934e-05,
      "loss": 0.0195,
      "step": 1600
    },
    {
      "epoch": 130.77,
      "learning_rate": 7.143087248322148e-05,
      "loss": 0.0163,
      "step": 1700
    },
    {
      "epoch": 138.46,
      "learning_rate": 7.089395973154363e-05,
      "loss": 0.0133,
      "step": 1800
    },
    {
      "epoch": 146.15,
      "learning_rate": 7.035704697986578e-05,
      "loss": 0.0172,
      "step": 1900
    },
    {
      "epoch": 153.85,
      "learning_rate": 6.982013422818792e-05,
      "loss": 0.0135,
      "step": 2000
    },
    {
      "epoch": 153.85,
      "eval_las": 66.5083135391924,
      "eval_loss": 5.791055202484131,
      "eval_runtime": 0.5426,
      "eval_samples_per_second": 147.447,
      "eval_steps_per_second": 18.431,
      "eval_uas": 77.0387965162312,
      "step": 2000
    },
    {
      "epoch": 161.54,
      "learning_rate": 6.928322147651007e-05,
      "loss": 0.0131,
      "step": 2100
    },
    {
      "epoch": 169.23,
      "learning_rate": 6.874630872483222e-05,
      "loss": 0.0114,
      "step": 2200
    },
    {
      "epoch": 176.92,
      "learning_rate": 6.820939597315437e-05,
      "loss": 0.0117,
      "step": 2300
    },
    {
      "epoch": 184.62,
      "learning_rate": 6.767248322147652e-05,
      "loss": 0.0149,
      "step": 2400
    },
    {
      "epoch": 192.31,
      "learning_rate": 6.713557046979866e-05,
      "loss": 0.0093,
      "step": 2500
    },
    {
      "epoch": 192.31,
      "eval_las": 66.19160728424386,
      "eval_loss": 6.622511386871338,
      "eval_runtime": 0.5411,
      "eval_samples_per_second": 147.836,
      "eval_steps_per_second": 18.48,
      "eval_uas": 76.8012668250198,
      "step": 2500
    },
    {
      "epoch": 200.0,
      "learning_rate": 6.659865771812081e-05,
      "loss": 0.0145,
      "step": 2600
    },
    {
      "epoch": 207.69,
      "learning_rate": 6.606174496644296e-05,
      "loss": 0.0111,
      "step": 2700
    },
    {
      "epoch": 215.38,
      "learning_rate": 6.55248322147651e-05,
      "loss": 0.0091,
      "step": 2800
    },
    {
      "epoch": 223.08,
      "learning_rate": 6.498791946308724e-05,
      "loss": 0.01,
      "step": 2900
    },
    {
      "epoch": 230.77,
      "learning_rate": 6.445100671140939e-05,
      "loss": 0.01,
      "step": 3000
    },
    {
      "epoch": 230.77,
      "eval_las": 65.63737133808392,
      "eval_loss": 6.7730560302734375,
      "eval_runtime": 0.5346,
      "eval_samples_per_second": 149.632,
      "eval_steps_per_second": 18.704,
      "eval_uas": 77.0387965162312,
      "step": 3000
    },
    {
      "epoch": 238.46,
      "learning_rate": 6.391409395973154e-05,
      "loss": 0.0092,
      "step": 3100
    },
    {
      "epoch": 246.15,
      "learning_rate": 6.337718120805369e-05,
      "loss": 0.007,
      "step": 3200
    },
    {
      "epoch": 253.85,
      "learning_rate": 6.284026845637584e-05,
      "loss": 0.007,
      "step": 3300
    },
    {
      "epoch": 261.54,
      "learning_rate": 6.230335570469799e-05,
      "loss": 0.007,
      "step": 3400
    },
    {
      "epoch": 269.23,
      "learning_rate": 6.176644295302013e-05,
      "loss": 0.0061,
      "step": 3500
    },
    {
      "epoch": 269.23,
      "eval_las": 66.270783847981,
      "eval_loss": 6.5091376304626465,
      "eval_runtime": 0.5325,
      "eval_samples_per_second": 150.229,
      "eval_steps_per_second": 18.779,
      "eval_uas": 76.64291369754552,
      "step": 3500
    },
    {
      "epoch": 276.92,
      "learning_rate": 6.122953020134228e-05,
      "loss": 0.008,
      "step": 3600
    },
    {
      "epoch": 284.62,
      "learning_rate": 6.069261744966444e-05,
      "loss": 0.0092,
      "step": 3700
    },
    {
      "epoch": 292.31,
      "learning_rate": 6.0155704697986585e-05,
      "loss": 0.007,
      "step": 3800
    },
    {
      "epoch": 300.0,
      "learning_rate": 5.9618791946308734e-05,
      "loss": 0.0076,
      "step": 3900
    },
    {
      "epoch": 307.69,
      "learning_rate": 5.9081879194630875e-05,
      "loss": 0.0101,
      "step": 4000
    },
    {
      "epoch": 307.69,
      "eval_las": 66.7458432304038,
      "eval_loss": 7.320127010345459,
      "eval_runtime": 0.5431,
      "eval_samples_per_second": 147.315,
      "eval_steps_per_second": 18.414,
      "eval_uas": 76.40538400633412,
      "step": 4000
    },
    {
      "epoch": 307.69,
      "step": 4000,
      "total_flos": 2.0552849401921536e+16,
      "train_loss": 0.0970867464542389,
      "train_runtime": 2080.6987,
      "train_samples_per_second": 230.692,
      "train_steps_per_second": 7.209
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 1154,
  "total_flos": 2.0552849401921536e+16,
  "trial_name": null,
  "trial_params": null
}