{
  "best_global_step": 3960,
  "best_metric": 0.0027947870548814535,
  "best_model_checkpoint": "/content/drive/MyDrive/evo_CodeT5plus_frozenEnc/checkpoint-3960",
  "epoch": 18.0,
  "eval_steps": 500,
  "global_step": 3960,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.1201924085617065,
      "learning_rate": 5e-05,
      "loss": 0.508801997791637,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.031036050990223885,
      "eval_runtime": 16.9632,
      "eval_samples_per_second": 12.969,
      "eval_steps_per_second": 6.485,
      "step": 220
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.11240009218454361,
      "learning_rate": 5e-05,
      "loss": 0.1055341200395064,
      "step": 440
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.022242471575737,
      "eval_runtime": 17.2794,
      "eval_samples_per_second": 12.732,
      "eval_steps_per_second": 6.366,
      "step": 440
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7675652503967285,
      "learning_rate": 5e-05,
      "loss": 0.06234081441705877,
      "step": 660
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.01632743328809738,
      "eval_runtime": 17.1769,
      "eval_samples_per_second": 12.808,
      "eval_steps_per_second": 6.404,
      "step": 660
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.07149142771959305,
      "learning_rate": 5e-05,
      "loss": 0.04255591739307751,
      "step": 880
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.00789650809019804,
      "eval_runtime": 17.0577,
      "eval_samples_per_second": 12.897,
      "eval_steps_per_second": 6.449,
      "step": 880
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.41593658924102783,
      "learning_rate": 5e-05,
      "loss": 0.03280660672621293,
      "step": 1100
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.010357110761106014,
      "eval_runtime": 16.9345,
      "eval_samples_per_second": 12.991,
      "eval_steps_per_second": 6.496,
      "step": 1100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0010334457037970424,
      "learning_rate": 5e-05,
      "loss": 0.024871245297518642,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.006158643402159214,
      "eval_runtime": 17.2443,
      "eval_samples_per_second": 12.758,
      "eval_steps_per_second": 6.379,
      "step": 1320
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.1123638153076172,
      "learning_rate": 5e-05,
      "loss": 0.02346384958787398,
      "step": 1540
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.007988177239894867,
      "eval_runtime": 16.944,
      "eval_samples_per_second": 12.984,
      "eval_steps_per_second": 6.492,
      "step": 1540
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.02058124728500843,
      "learning_rate": 5e-05,
      "loss": 0.018623479929837313,
      "step": 1760
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.0052207051776349545,
      "eval_runtime": 17.0998,
      "eval_samples_per_second": 12.866,
      "eval_steps_per_second": 6.433,
      "step": 1760
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.010896311141550541,
      "learning_rate": 5e-05,
      "loss": 0.0202510573647239,
      "step": 1980
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.010862304829061031,
      "eval_runtime": 16.5148,
      "eval_samples_per_second": 13.321,
      "eval_steps_per_second": 6.661,
      "step": 1980
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.00067019002744928,
      "learning_rate": 5e-05,
      "loss": 0.018236663124778053,
      "step": 2200
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.003377651795744896,
      "eval_runtime": 16.608,
      "eval_samples_per_second": 13.247,
      "eval_steps_per_second": 6.623,
      "step": 2200
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.001838264986872673,
      "learning_rate": 5e-05,
      "loss": 0.01725634444843639,
      "step": 2420
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.012781262397766113,
      "eval_runtime": 16.5932,
      "eval_samples_per_second": 13.258,
      "eval_steps_per_second": 6.629,
      "step": 2420
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.0013156271306797862,
      "learning_rate": 5e-05,
      "loss": 0.00876567309552973,
      "step": 2640
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.005950805265456438,
      "eval_runtime": 16.5031,
      "eval_samples_per_second": 13.331,
      "eval_steps_per_second": 6.665,
      "step": 2640
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.010019246488809586,
      "learning_rate": 5e-05,
      "loss": 0.011685315045443448,
      "step": 2860
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.0038430262356996536,
      "eval_runtime": 16.4244,
      "eval_samples_per_second": 13.395,
      "eval_steps_per_second": 6.697,
      "step": 2860
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.007604538928717375,
      "learning_rate": 5e-05,
      "loss": 0.007304735075343739,
      "step": 3080
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.006216138135641813,
      "eval_runtime": 16.422,
      "eval_samples_per_second": 13.397,
      "eval_steps_per_second": 6.698,
      "step": 3080
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.00034067651722580194,
      "learning_rate": 5e-05,
      "loss": 0.0061811084097081965,
      "step": 3300
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.003704946953803301,
      "eval_runtime": 16.6472,
      "eval_samples_per_second": 13.215,
      "eval_steps_per_second": 6.608,
      "step": 3300
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.00039539029239676893,
      "learning_rate": 5e-05,
      "loss": 0.005046481435949152,
      "step": 3520
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.0054435427300632,
      "eval_runtime": 16.5747,
      "eval_samples_per_second": 13.273,
      "eval_steps_per_second": 6.637,
      "step": 3520
    },
    {
      "epoch": 17.0,
      "grad_norm": 0.0006793063948862255,
      "learning_rate": 5e-05,
      "loss": 0.005749529600143433,
      "step": 3740
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.004094177391380072,
      "eval_runtime": 16.5162,
      "eval_samples_per_second": 13.32,
      "eval_steps_per_second": 6.66,
      "step": 3740
    },
    {
      "epoch": 18.0,
      "grad_norm": 0.0004089501453563571,
      "learning_rate": 5e-05,
      "loss": 0.004834394563328136,
      "step": 3960
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.0027947870548814535,
      "eval_runtime": 16.4672,
      "eval_samples_per_second": 13.36,
      "eval_steps_per_second": 6.68,
      "step": 3960
    }
  ],
  "logging_steps": 500,
  "max_steps": 4400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.84867909490688e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}