{
  "best_global_step": 1760,
  "best_metric": 0.004073738120496273,
  "best_model_checkpoint": "/content/drive/MyDrive/evo_ablation_DirectEvolution_CodeT5base_FullFT/checkpoint-1760",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 1980,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0355877876281738,
      "learning_rate": 4.991027181875014e-05,
      "loss": 1.8348119562322442,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.03580193594098091,
      "eval_runtime": 3.039,
      "eval_samples_per_second": 72.392,
      "eval_steps_per_second": 18.098,
      "step": 220
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07191833108663559,
      "learning_rate": 4.925493631367695e-05,
      "loss": 0.08348724191839045,
      "step": 440
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.019032808020710945,
      "eval_runtime": 3.0215,
      "eval_samples_per_second": 72.811,
      "eval_steps_per_second": 18.203,
      "step": 440
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5394785404205322,
      "learning_rate": 4.79727833666922e-05,
      "loss": 0.04584090492942117,
      "step": 660
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.012234838679432869,
      "eval_runtime": 3.0514,
      "eval_samples_per_second": 72.098,
      "eval_steps_per_second": 18.024,
      "step": 660
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.1377420276403427,
      "learning_rate": 4.610819813755038e-05,
      "loss": 0.025517858158458362,
      "step": 880
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.00837874785065651,
      "eval_runtime": 3.0383,
      "eval_samples_per_second": 72.409,
      "eval_steps_per_second": 18.102,
      "step": 880
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.66103595495224,
      "learning_rate": 4.3692257202498335e-05,
      "loss": 0.017070700905539773,
      "step": 1100
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.006502046715468168,
      "eval_runtime": 3.2267,
      "eval_samples_per_second": 68.182,
      "eval_steps_per_second": 17.045,
      "step": 1100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.002123212441802025,
      "learning_rate": 4.079444088124431e-05,
      "loss": 0.012019785967740145,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.00527948047965765,
      "eval_runtime": 3.1399,
      "eval_samples_per_second": 70.066,
      "eval_steps_per_second": 17.516,
      "step": 1320
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03506750613451004,
      "learning_rate": 3.7489453172552035e-05,
      "loss": 0.008358093283393167,
      "step": 1540
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.004877733998000622,
      "eval_runtime": 3.0578,
      "eval_samples_per_second": 71.948,
      "eval_steps_per_second": 17.987,
      "step": 1540
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0033804229460656643,
      "learning_rate": 3.386249471384405e-05,
      "loss": 0.007093059474771673,
      "step": 1760
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.004073738120496273,
      "eval_runtime": 3.0231,
      "eval_samples_per_second": 72.772,
      "eval_steps_per_second": 18.193,
      "step": 1760
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.0007005213410593569,
      "learning_rate": 3.0007066358928138e-05,
      "loss": 0.004284547404809431,
      "step": 1980
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.005608182400465012,
      "eval_runtime": 3.0645,
      "eval_samples_per_second": 71.789,
      "eval_steps_per_second": 17.947,
      "step": 1980
    }
  ],
  "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3589231990763520.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}