{
  "best_metric": 2.1534345149993896,
  "best_model_checkpoint": "gpt2-open-instruct-v1-Anthropic/hh-rlhf/checkpoint-30000",
  "epoch": 4.0,
  "global_step": 30000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.009867224080267559,
      "loss": 2.4868,
      "step": 500
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0097,
      "loss": 2.3663,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.009532775919732442,
      "loss": 2.3524,
      "step": 1500
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.009365551839464883,
      "loss": 2.3374,
      "step": 2000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.009198327759197324,
      "loss": 2.3286,
      "step": 2500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.009031103678929767,
      "loss": 2.3082,
      "step": 3000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.008863879598662208,
      "loss": 2.3161,
      "step": 3500
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00869665551839465,
      "loss": 2.308,
      "step": 4000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00852943143812709,
      "loss": 2.3175,
      "step": 4500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.008362541806020068,
      "loss": 2.3023,
      "step": 5000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.008195317725752507,
      "loss": 2.3155,
      "step": 5500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00802809364548495,
      "loss": 2.314,
      "step": 6000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.007860869565217391,
      "loss": 2.2981,
      "step": 6500
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.007693645484949833,
      "loss": 2.3153,
      "step": 7000
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.007526755852842809,
      "loss": 2.3108,
      "step": 7500
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.1798622608184814,
      "eval_runtime": 12.4843,
      "eval_samples_per_second": 40.05,
      "eval_steps_per_second": 40.05,
      "step": 7500
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.007359531772575251,
      "loss": 2.2738,
      "step": 8000
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.007192307692307692,
      "loss": 2.2885,
      "step": 8500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.007025083612040134,
      "loss": 2.313,
      "step": 9000
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.006858193979933111,
      "loss": 2.2854,
      "step": 9500
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.006690969899665552,
      "loss": 2.2524,
      "step": 10000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.006523745819397994,
      "loss": 2.2767,
      "step": 10500
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.006356521739130435,
      "loss": 2.2627,
      "step": 11000
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.006189297658862877,
      "loss": 2.2779,
      "step": 11500
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0060224080267558535,
      "loss": 2.2778,
      "step": 12000
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.005855183946488294,
      "loss": 2.2588,
      "step": 12500
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.005687959866220735,
      "loss": 2.296,
      "step": 13000
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.005520735785953177,
      "loss": 2.2451,
      "step": 13500
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0053538461538461535,
      "loss": 2.2831,
      "step": 14000
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.005186622073578596,
      "loss": 2.2801,
      "step": 14500
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.005019397993311037,
      "loss": 2.265,
      "step": 15000
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.1632304191589355,
      "eval_runtime": 12.092,
      "eval_samples_per_second": 41.35,
      "eval_steps_per_second": 41.35,
      "step": 15000
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.004852173913043478,
      "loss": 2.2483,
      "step": 15500
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00468494983277592,
      "loss": 2.2928,
      "step": 16000
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.004518060200668896,
      "loss": 2.2555,
      "step": 16500
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.004350836120401338,
      "loss": 2.2761,
      "step": 17000
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00418361204013378,
      "loss": 2.2515,
      "step": 17500
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.004016387959866221,
      "loss": 2.2636,
      "step": 18000
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.003849498327759197,
      "loss": 2.2569,
      "step": 18500
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.003682274247491639,
      "loss": 2.2728,
      "step": 19000
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0035150501672240805,
      "loss": 2.2561,
      "step": 19500
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0033478260869565218,
      "loss": 2.2396,
      "step": 20000
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0031809364548494984,
      "loss": 2.2601,
      "step": 20500
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00301371237458194,
      "loss": 2.2609,
      "step": 21000
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.002846488294314381,
      "loss": 2.2654,
      "step": 21500
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0026792642140468226,
      "loss": 2.2381,
      "step": 22000
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0025123745819397992,
      "loss": 2.2507,
      "step": 22500
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.156663179397583,
      "eval_runtime": 12.0987,
      "eval_samples_per_second": 41.327,
      "eval_steps_per_second": 41.327,
      "step": 22500
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.002345150501672241,
      "loss": 2.2693,
      "step": 23000
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.002177926421404682,
      "loss": 2.2605,
      "step": 23500
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.002010702341137124,
      "loss": 2.2272,
      "step": 24000
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0018434782608695653,
      "loss": 2.2394,
      "step": 24500
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0016765886287625417,
      "loss": 2.231,
      "step": 25000
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0015093645484949834,
      "loss": 2.225,
      "step": 25500
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0013421404682274248,
      "loss": 2.2503,
      "step": 26000
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0011749163879598663,
      "loss": 2.2597,
      "step": 26500
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.001008026755852843,
      "loss": 2.228,
      "step": 27000
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0008408026755852843,
      "loss": 2.2338,
      "step": 27500
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0006735785953177258,
      "loss": 2.2478,
      "step": 28000
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0005063545150501672,
      "loss": 2.2672,
      "step": 28500
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0003391304347826087,
      "loss": 2.2513,
      "step": 29000
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001722408026755853,
      "loss": 2.2776,
      "step": 29500
    },
    {
      "epoch": 4.0,
      "learning_rate": 5.016722408026756e-06,
      "loss": 2.2519,
      "step": 30000
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.1534345149993896,
      "eval_runtime": 11.8174,
      "eval_samples_per_second": 42.31,
      "eval_steps_per_second": 42.31,
      "step": 30000
    }
  ],
  "max_steps": 30000,
  "num_train_epochs": 4,
  "total_flos": 3.135504384e+16,
  "trial_name": null,
  "trial_params": null
}