{
  "best_metric": 18.92319873317498,
  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-base-finetuned-parsing-ud-Tamil-TTB/checkpoint-500",
  "epoch": 230.76923076923077,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.69,
      "learning_rate": 7.52e-05,
      "loss": 4.575,
      "step": 100
    },
    {
      "epoch": 15.38,
      "learning_rate": 7.949530201342283e-05,
      "loss": 2.7427,
      "step": 200
    },
    {
      "epoch": 23.08,
      "learning_rate": 7.895838926174497e-05,
      "loss": 1.7932,
      "step": 300
    },
    {
      "epoch": 30.77,
      "learning_rate": 7.842147651006712e-05,
      "loss": 1.1589,
      "step": 400
    },
    {
      "epoch": 38.46,
      "learning_rate": 7.788456375838927e-05,
      "loss": 0.787,
      "step": 500
    },
    {
      "epoch": 38.46,
      "eval_las": 18.92319873317498,
      "eval_loss": 8.03709888458252,
      "eval_runtime": 0.5456,
      "eval_samples_per_second": 146.634,
      "eval_steps_per_second": 18.329,
      "eval_uas": 36.18368962787015,
      "step": 500
    },
    {
      "epoch": 46.15,
      "learning_rate": 7.734765100671142e-05,
      "loss": 0.5851,
      "step": 600
    },
    {
      "epoch": 53.85,
      "learning_rate": 7.681073825503357e-05,
      "loss": 0.4576,
      "step": 700
    },
    {
      "epoch": 61.54,
      "learning_rate": 7.627382550335572e-05,
      "loss": 0.3946,
      "step": 800
    },
    {
      "epoch": 69.23,
      "learning_rate": 7.573691275167786e-05,
      "loss": 0.3746,
      "step": 900
    },
    {
      "epoch": 76.92,
      "learning_rate": 7.52e-05,
      "loss": 0.358,
      "step": 1000
    },
    {
      "epoch": 76.92,
      "eval_las": 16.943784639746635,
      "eval_loss": 11.071226119995117,
      "eval_runtime": 0.5411,
      "eval_samples_per_second": 147.855,
      "eval_steps_per_second": 18.482,
      "eval_uas": 33.966745843230406,
      "step": 1000
    },
    {
      "epoch": 84.62,
      "learning_rate": 7.466308724832215e-05,
      "loss": 0.3352,
      "step": 1100
    },
    {
      "epoch": 92.31,
      "learning_rate": 7.41261744966443e-05,
      "loss": 0.3213,
      "step": 1200
    },
    {
      "epoch": 100.0,
      "learning_rate": 7.358926174496644e-05,
      "loss": 0.322,
      "step": 1300
    },
    {
      "epoch": 107.69,
      "learning_rate": 7.305234899328859e-05,
      "loss": 0.3044,
      "step": 1400
    },
    {
      "epoch": 115.38,
      "learning_rate": 7.251543624161074e-05,
      "loss": 0.2942,
      "step": 1500
    },
    {
      "epoch": 115.38,
      "eval_las": 17.02296120348377,
      "eval_loss": 12.35420036315918,
      "eval_runtime": 0.542,
      "eval_samples_per_second": 147.589,
      "eval_steps_per_second": 18.449,
      "eval_uas": 34.837688044338876,
      "step": 1500
    },
    {
      "epoch": 123.08,
      "learning_rate": 7.197852348993289e-05,
      "loss": 0.3028,
      "step": 1600
    },
    {
      "epoch": 130.77,
      "learning_rate": 7.144161073825504e-05,
      "loss": 0.2954,
      "step": 1700
    },
    {
      "epoch": 138.46,
      "learning_rate": 7.090469798657718e-05,
      "loss": 0.2822,
      "step": 1800
    },
    {
      "epoch": 146.15,
      "learning_rate": 7.036778523489933e-05,
      "loss": 0.2814,
      "step": 1900
    },
    {
      "epoch": 153.85,
      "learning_rate": 6.983087248322148e-05,
      "loss": 0.2812,
      "step": 2000
    },
    {
      "epoch": 153.85,
      "eval_las": 17.81472684085511,
      "eval_loss": 13.284212112426758,
      "eval_runtime": 0.5416,
      "eval_samples_per_second": 147.703,
      "eval_steps_per_second": 18.463,
      "eval_uas": 36.57957244655582,
      "step": 2000
    },
    {
      "epoch": 161.54,
      "learning_rate": 6.929395973154363e-05,
      "loss": 0.2837,
      "step": 2100
    },
    {
      "epoch": 169.23,
      "learning_rate": 6.875704697986578e-05,
      "loss": 0.2887,
      "step": 2200
    },
    {
      "epoch": 176.92,
      "learning_rate": 6.822013422818793e-05,
      "loss": 0.278,
      "step": 2300
    },
    {
      "epoch": 184.62,
      "learning_rate": 6.768322147651007e-05,
      "loss": 0.2721,
      "step": 2400
    },
    {
      "epoch": 192.31,
      "learning_rate": 6.714630872483222e-05,
      "loss": 0.2727,
      "step": 2500
    },
    {
      "epoch": 192.31,
      "eval_las": 16.706254948535236,
      "eval_loss": 14.351984977722168,
      "eval_runtime": 0.5408,
      "eval_samples_per_second": 147.943,
      "eval_steps_per_second": 18.493,
      "eval_uas": 34.36262866191607,
      "step": 2500
    },
    {
      "epoch": 200.0,
      "learning_rate": 6.660939597315437e-05,
      "loss": 0.2718,
      "step": 2600
    },
    {
      "epoch": 207.69,
      "learning_rate": 6.607248322147652e-05,
      "loss": 0.264,
      "step": 2700
    },
    {
      "epoch": 215.38,
      "learning_rate": 6.553557046979867e-05,
      "loss": 0.2648,
      "step": 2800
    },
    {
      "epoch": 223.08,
      "learning_rate": 6.499865771812081e-05,
      "loss": 0.2699,
      "step": 2900
    },
    {
      "epoch": 230.77,
      "learning_rate": 6.446174496644296e-05,
      "loss": 0.2604,
      "step": 3000
    },
    {
      "epoch": 230.77,
      "eval_las": 17.339667458432302,
      "eval_loss": 14.176854133605957,
      "eval_runtime": 0.5399,
      "eval_samples_per_second": 148.179,
      "eval_steps_per_second": 18.522,
      "eval_uas": 34.04592240696754,
      "step": 3000
    },
    {
      "epoch": 230.77,
      "step": 3000,
      "total_flos": 1.541530495893504e+16,
      "train_loss": 0.6324253260294597,
      "train_runtime": 1509.7376,
      "train_samples_per_second": 317.936,
      "train_steps_per_second": 9.936
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 1154,
  "total_flos": 1.541530495893504e+16,
  "trial_name": null,
  "trial_params": null
}