{
  "best_metric": 0.37704405188560486,
  "best_model_checkpoint": "text_go3_aug\\checkpoint-600",
  "epoch": 12.834224598930481,
  "global_step": 2400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6,
      "learning_rate": 6e-07,
      "loss": 0.2199,
      "step": 300
    },
    {
      "epoch": 1.6,
      "eval_accuracy": 0.8704156479217604,
      "eval_loss": 0.3835061192512512,
      "eval_runtime": 13.2805,
      "eval_samples_per_second": 400.362,
      "eval_steps_per_second": 1.581,
      "step": 300
    },
    {
      "epoch": 3.21,
      "learning_rate": 9.804305283757338e-07,
      "loss": 0.2115,
      "step": 600
    },
    {
      "epoch": 3.21,
      "eval_accuracy": 0.8726725597141245,
      "eval_loss": 0.37704405188560486,
      "eval_runtime": 5.9909,
      "eval_samples_per_second": 887.511,
      "eval_steps_per_second": 3.505,
      "step": 600
    },
    {
      "epoch": 4.81,
      "learning_rate": 9.217221135029354e-07,
      "loss": 0.2059,
      "step": 900
    },
    {
      "epoch": 4.81,
      "eval_accuracy": 0.8751175474891856,
      "eval_loss": 0.37850409746170044,
      "eval_runtime": 5.7996,
      "eval_samples_per_second": 916.787,
      "eval_steps_per_second": 3.621,
      "step": 900
    },
    {
      "epoch": 6.42,
      "learning_rate": 8.63013698630137e-07,
      "loss": 0.2025,
      "step": 1200
    },
    {
      "epoch": 6.42,
      "eval_accuracy": 0.8751175474891856,
      "eval_loss": 0.3802962303161621,
      "eval_runtime": 5.6716,
      "eval_samples_per_second": 937.483,
      "eval_steps_per_second": 3.703,
      "step": 1200
    },
    {
      "epoch": 8.02,
      "learning_rate": 8.043052837573385e-07,
      "loss": 0.2035,
      "step": 1500
    },
    {
      "epoch": 8.02,
      "eval_accuracy": 0.8749294715064886,
      "eval_loss": 0.379294753074646,
      "eval_runtime": 5.6111,
      "eval_samples_per_second": 947.593,
      "eval_steps_per_second": 3.743,
      "step": 1500
    },
    {
      "epoch": 9.63,
      "learning_rate": 7.455968688845401e-07,
      "loss": 0.1956,
      "step": 1800
    },
    {
      "epoch": 9.63,
      "eval_accuracy": 0.8756817754372767,
      "eval_loss": 0.37750834226608276,
      "eval_runtime": 5.916,
      "eval_samples_per_second": 898.751,
      "eval_steps_per_second": 3.55,
      "step": 1800
    },
    {
      "epoch": 11.23,
      "learning_rate": 6.868884540117417e-07,
      "loss": 0.1979,
      "step": 2100
    },
    {
      "epoch": 11.23,
      "eval_accuracy": 0.8769983073161557,
      "eval_loss": 0.37952980399131775,
      "eval_runtime": 5.8097,
      "eval_samples_per_second": 915.188,
      "eval_steps_per_second": 3.615,
      "step": 2100
    },
    {
      "epoch": 12.83,
      "learning_rate": 6.281800391389432e-07,
      "loss": 0.1939,
      "step": 2400
    },
    {
      "epoch": 12.83,
      "eval_accuracy": 0.8768102313334587,
      "eval_loss": 0.37845009565353394,
      "eval_runtime": 5.7511,
      "eval_samples_per_second": 924.522,
      "eval_steps_per_second": 3.651,
      "step": 2400
    }
  ],
  "max_steps": 5610,
  "num_train_epochs": 30,
  "total_flos": 1.8243640989395136e+16,
  "trial_name": null,
  "trial_params": null
}