{
  "best_metric": 1.8454276323318481,
  "best_model_checkpoint": "/home/llmadmin/lawrence/autoWSB/data/tunned_v4/checkpoint-1000",
  "epoch": 2.9994666666666667,
  "global_step": 4218,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 8.333333333333333e-05,
      "loss": 1.9887,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.7819,
      "step": 200
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00025,
      "loss": 1.7572,
      "step": 300
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00024400444104134763,
      "loss": 3.1654,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00023762618683001533,
      "loss": 2.402,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.0042166709899902,
      "eval_runtime": 1078.6167,
      "eval_samples_per_second": 23.178,
      "eval_steps_per_second": 0.579,
      "step": 500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000231247932618683,
      "loss": 1.9543,
      "step": 600
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002248696784073507,
      "loss": 1.905,
      "step": 700
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00021849142419601836,
      "loss": 1.8835,
      "step": 800
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00021211316998468607,
      "loss": 1.8628,
      "step": 900
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00020573491577335375,
      "loss": 1.8463,
      "step": 1000
    },
    {
      "epoch": 0.71,
      "eval_loss": 1.8454276323318481,
      "eval_runtime": 1080.8608,
      "eval_samples_per_second": 23.13,
      "eval_steps_per_second": 0.578,
      "step": 1000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019935666156202145,
      "loss": 1.8654,
      "step": 1100
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019297840735068913,
      "loss": 1.8511,
      "step": 1200
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018660015313935684,
      "loss": 1.8424,
      "step": 1300
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001802218989280245,
      "loss": 1.8579,
      "step": 1400
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00017843598774885147,
      "loss": 23.4765,
      "step": 1500
    },
    {
      "epoch": 1.07,
      "eval_loss": 10.320993423461914,
      "eval_runtime": 1165.3618,
      "eval_samples_per_second": 21.453,
      "eval_steps_per_second": 0.536,
      "step": 1500
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00017767059724349159,
      "loss": 26.8324,
      "step": 1600
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00017129234303215926,
      "loss": 33.5803,
      "step": 1700
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00016491408882082697,
      "loss": 75831.04,
      "step": 1800
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00015853583460949465,
      "loss": 112434.02,
      "step": 1900
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00015215758039816232,
      "loss": 9892.82,
      "step": 2000
    },
    {
      "epoch": 1.42,
      "eval_loss": 10.320993423461914,
      "eval_runtime": 1166.8445,
      "eval_samples_per_second": 21.425,
      "eval_steps_per_second": 0.536,
      "step": 2000
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00014577932618683,
      "loss": 9040.6219,
      "step": 2100
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001394010719754977,
      "loss": 2015.4547,
      "step": 2200
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001330228177641654,
      "loss": 16854.6437,
      "step": 2300
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001266445635528331,
      "loss": 795.047,
      "step": 2400
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00012026630934150074,
      "loss": 38857.9575,
      "step": 2500
    },
    {
      "epoch": 1.78,
      "eval_loss": 10.320993423461914,
      "eval_runtime": 1167.9826,
      "eval_samples_per_second": 21.404,
      "eval_steps_per_second": 0.535,
      "step": 2500
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00011388805513016846,
      "loss": 185.0979,
      "step": 2600
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00010750980091883614,
      "loss": 12796.2138,
      "step": 2700
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00010113154670750384,
      "loss": 14625.28,
      "step": 2800
    },
    {
      "epoch": 2.06,
      "learning_rate": 9.475329249617151e-05,
      "loss": 271.5516,
      "step": 2900
    },
    {
      "epoch": 2.13,
      "learning_rate": 8.837503828483921e-05,
      "loss": 5358.3219,
      "step": 3000
    },
    {
      "epoch": 2.13,
      "eval_loss": 10.320993423461914,
      "eval_runtime": 1167.2296,
      "eval_samples_per_second": 21.418,
      "eval_steps_per_second": 0.535,
      "step": 3000
    },
    {
      "epoch": 2.2,
      "learning_rate": 8.199678407350689e-05,
      "loss": 106711.13,
      "step": 3100
    },
    {
      "epoch": 2.28,
      "learning_rate": 7.561852986217458e-05,
      "loss": 141536.53,
      "step": 3200
    },
    {
      "epoch": 2.35,
      "learning_rate": 6.924027565084226e-05,
      "loss": 784.2875,
      "step": 3300
    },
    {
      "epoch": 2.42,
      "learning_rate": 6.286202143950997e-05,
      "loss": 95102.5,
      "step": 3400
    },
    {
      "epoch": 2.49,
      "learning_rate": 5.648376722817764e-05,
      "loss": 2327.5258,
      "step": 3500
    },
    {
      "epoch": 2.49,
      "eval_loss": 10.320993423461914,
      "eval_runtime": 1166.8332,
      "eval_samples_per_second": 21.426,
      "eval_steps_per_second": 0.536,
      "step": 3500
    },
    {
      "epoch": 2.56,
      "learning_rate": 5.010551301684534e-05,
      "loss": 59017.795,
      "step": 3600
    },
    {
      "epoch": 2.63,
      "learning_rate": 4.3727258805513014e-05,
      "loss": 680382.64,
      "step": 3700
    },
    {
      "epoch": 2.7,
      "learning_rate": 3.734900459418072e-05,
      "loss": 1483.1705,
      "step": 3800
    },
    {
      "epoch": 2.77,
      "learning_rate": 3.097075038284839e-05,
      "loss": 30906.0775,
      "step": 3900
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.459249617151609e-05,
      "loss": 46132.635,
      "step": 4000
    },
    {
      "epoch": 2.84,
      "eval_loss": 10.320993423461914,
      "eval_runtime": 1166.5367,
      "eval_samples_per_second": 21.431,
      "eval_steps_per_second": 0.536,
      "step": 4000
    },
    {
      "epoch": 2.92,
      "learning_rate": 1.8214241960183767e-05,
      "loss": 31202.95,
      "step": 4100
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.1835987748851469e-05,
      "loss": 2477.5823,
      "step": 4200
    },
    {
      "epoch": 3.0,
      "step": 4218,
      "total_flos": 2.7466670484779696e+19,
      "train_loss": 35493.948473290504,
      "train_runtime": 121039.6951,
      "train_samples_per_second": 5.577,
      "train_steps_per_second": 0.035
    }
  ],
  "max_steps": 4218,
  "num_train_epochs": 3,
  "total_flos": 2.7466670484779696e+19,
  "trial_name": null,
  "trial_params": null
}