{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 4040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 13.334685325622559,
      "learning_rate": 5.7178217821782184e-06,
      "loss": 2.6835,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.5441126823425293,
      "learning_rate": 1.1584158415841584e-05,
      "loss": 2.3047,
      "step": 160
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.4855196475982666,
      "learning_rate": 1.7524752475247524e-05,
      "loss": 2.0103,
      "step": 240
    },
    {
      "epoch": 0.79,
      "grad_norm": 2.429617166519165,
      "learning_rate": 2.3465346534653467e-05,
      "loss": 1.7695,
      "step": 320
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.6394236087799072,
      "learning_rate": 2.9405940594059407e-05,
      "loss": 1.7141,
      "step": 400
    },
    {
      "epoch": 1.19,
      "grad_norm": 4.821674823760986,
      "learning_rate": 2.9405940594059407e-05,
      "loss": 1.6202,
      "step": 480
    },
    {
      "epoch": 1.39,
      "grad_norm": 1.7676095962524414,
      "learning_rate": 2.8745874587458746e-05,
      "loss": 1.5316,
      "step": 560
    },
    {
      "epoch": 1.58,
      "grad_norm": 1.9537432193756104,
      "learning_rate": 2.8085808580858088e-05,
      "loss": 1.5497,
      "step": 640
    },
    {
      "epoch": 1.78,
      "grad_norm": 1.6451698541641235,
      "learning_rate": 2.7425742574257424e-05,
      "loss": 1.5092,
      "step": 720
    },
    {
      "epoch": 1.98,
      "grad_norm": 1.8162490129470825,
      "learning_rate": 2.6765676567656766e-05,
      "loss": 1.4958,
      "step": 800
    },
    {
      "epoch": 2.18,
      "grad_norm": 1.7349311113357544,
      "learning_rate": 2.610561056105611e-05,
      "loss": 1.4255,
      "step": 880
    },
    {
      "epoch": 2.38,
      "grad_norm": 2.0465753078460693,
      "learning_rate": 2.5445544554455447e-05,
      "loss": 1.4322,
      "step": 960
    },
    {
      "epoch": 2.57,
      "grad_norm": 2.079873561859131,
      "learning_rate": 2.4785478547854786e-05,
      "loss": 1.391,
      "step": 1040
    },
    {
      "epoch": 2.77,
      "grad_norm": 1.8764556646347046,
      "learning_rate": 2.4125412541254125e-05,
      "loss": 1.4254,
      "step": 1120
    },
    {
      "epoch": 2.97,
      "grad_norm": 2.345323324203491,
      "learning_rate": 2.3465346534653467e-05,
      "loss": 1.4177,
      "step": 1200
    },
    {
      "epoch": 3.17,
      "grad_norm": 2.4153122901916504,
      "learning_rate": 2.2805280528052803e-05,
      "loss": 1.31,
      "step": 1280
    },
    {
      "epoch": 3.37,
      "grad_norm": 2.362084150314331,
      "learning_rate": 2.2145214521452145e-05,
      "loss": 1.2966,
      "step": 1360
    },
    {
      "epoch": 3.56,
      "grad_norm": 2.2319586277008057,
      "learning_rate": 2.1485148514851487e-05,
      "loss": 1.3684,
      "step": 1440
    },
    {
      "epoch": 3.76,
      "grad_norm": 2.043566942214966,
      "learning_rate": 2.0825082508250826e-05,
      "loss": 1.392,
      "step": 1520
    },
    {
      "epoch": 3.96,
      "grad_norm": 2.2719879150390625,
      "learning_rate": 2.0165016501650165e-05,
      "loss": 1.3083,
      "step": 1600
    },
    {
      "epoch": 4.16,
      "grad_norm": 2.6207830905914307,
      "learning_rate": 1.9504950495049504e-05,
      "loss": 1.252,
      "step": 1680
    },
    {
      "epoch": 4.36,
      "grad_norm": 2.797555446624756,
      "learning_rate": 1.8844884488448846e-05,
      "loss": 1.2673,
      "step": 1760
    },
    {
      "epoch": 4.55,
      "grad_norm": 2.4675941467285156,
      "learning_rate": 1.8184818481848185e-05,
      "loss": 1.2311,
      "step": 1840
    },
    {
      "epoch": 4.75,
      "grad_norm": 2.450917959213257,
      "learning_rate": 1.7524752475247524e-05,
      "loss": 1.2466,
      "step": 1920
    },
    {
      "epoch": 4.95,
      "grad_norm": 2.9076478481292725,
      "learning_rate": 1.6864686468646866e-05,
      "loss": 1.3578,
      "step": 2000
    },
    {
      "epoch": 5.15,
      "grad_norm": 2.909982681274414,
      "learning_rate": 1.6204620462046205e-05,
      "loss": 1.2384,
      "step": 2080
    },
    {
      "epoch": 5.35,
      "grad_norm": 2.7267675399780273,
      "learning_rate": 1.5544554455445548e-05,
      "loss": 1.1951,
      "step": 2160
    },
    {
      "epoch": 5.54,
      "grad_norm": 3.54055118560791,
      "learning_rate": 1.4884488448844885e-05,
      "loss": 1.2141,
      "step": 2240
    },
    {
      "epoch": 5.74,
      "grad_norm": 2.72868275642395,
      "learning_rate": 1.4224422442244225e-05,
      "loss": 1.2374,
      "step": 2320
    },
    {
      "epoch": 5.94,
      "grad_norm": 2.7000038623809814,
      "learning_rate": 1.3564356435643564e-05,
      "loss": 1.2645,
      "step": 2400
    },
    {
      "epoch": 6.14,
      "grad_norm": 3.291171073913574,
      "learning_rate": 1.2904290429042905e-05,
      "loss": 1.1701,
      "step": 2480
    },
    {
      "epoch": 6.34,
      "grad_norm": 2.9283392429351807,
      "learning_rate": 1.2244224422442244e-05,
      "loss": 1.1559,
      "step": 2560
    },
    {
      "epoch": 6.53,
      "grad_norm": 3.4444239139556885,
      "learning_rate": 1.1584158415841584e-05,
      "loss": 1.1984,
      "step": 2640
    },
    {
      "epoch": 6.73,
      "grad_norm": 3.4505791664123535,
      "learning_rate": 1.0924092409240923e-05,
      "loss": 1.1956,
      "step": 2720
    },
    {
      "epoch": 6.93,
      "grad_norm": 3.7554521560668945,
      "learning_rate": 1.0264026402640264e-05,
      "loss": 1.1743,
      "step": 2800
    },
    {
      "epoch": 7.13,
      "grad_norm": 3.4612154960632324,
      "learning_rate": 9.603960396039604e-06,
      "loss": 1.1505,
      "step": 2880
    },
    {
      "epoch": 7.33,
      "grad_norm": 3.5600943565368652,
      "learning_rate": 8.943894389438945e-06,
      "loss": 1.1334,
      "step": 2960
    },
    {
      "epoch": 7.52,
      "grad_norm": 3.4435224533081055,
      "learning_rate": 8.283828382838284e-06,
      "loss": 1.1477,
      "step": 3040
    },
    {
      "epoch": 7.72,
      "grad_norm": 3.559251546859741,
      "learning_rate": 7.6237623762376246e-06,
      "loss": 1.1525,
      "step": 3120
    },
    {
      "epoch": 7.92,
      "grad_norm": 4.093379497528076,
      "learning_rate": 6.9636963696369635e-06,
      "loss": 1.1258,
      "step": 3200
    },
    {
      "epoch": 8.12,
      "grad_norm": 3.836825370788574,
      "learning_rate": 6.303630363036304e-06,
      "loss": 1.092,
      "step": 3280
    },
    {
      "epoch": 8.32,
      "grad_norm": 3.719158411026001,
      "learning_rate": 5.643564356435644e-06,
      "loss": 1.1118,
      "step": 3360
    },
    {
      "epoch": 8.51,
      "grad_norm": 4.2379374504089355,
      "learning_rate": 4.9834983498349835e-06,
      "loss": 1.1066,
      "step": 3440
    },
    {
      "epoch": 8.71,
      "grad_norm": 4.96703577041626,
      "learning_rate": 4.323432343234323e-06,
      "loss": 1.1161,
      "step": 3520
    },
    {
      "epoch": 8.91,
      "grad_norm": 9.020540237426758,
      "learning_rate": 3.6633663366336635e-06,
      "loss": 1.129,
      "step": 3600
    },
    {
      "epoch": 9.11,
      "grad_norm": 3.624774217605591,
      "learning_rate": 3.003300330033003e-06,
      "loss": 1.097,
      "step": 3680
    },
    {
      "epoch": 9.31,
      "grad_norm": 3.6332197189331055,
      "learning_rate": 2.3432343234323434e-06,
      "loss": 1.074,
      "step": 3760
    },
    {
      "epoch": 9.5,
      "grad_norm": 4.2010579109191895,
      "learning_rate": 1.683168316831683e-06,
      "loss": 1.0808,
      "step": 3840
    },
    {
      "epoch": 9.7,
      "grad_norm": 3.434506416320801,
      "learning_rate": 1.023102310231023e-06,
      "loss": 1.0774,
      "step": 3920
    },
    {
      "epoch": 9.9,
      "grad_norm": 4.213884353637695,
      "learning_rate": 3.63036303630363e-07,
      "loss": 1.1134,
      "step": 4000
    }
  ],
  "logging_steps": 80,
  "max_steps": 4040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 9.936130988310528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}