{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 40.0,
  "eval_steps": 500,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 3.7084410190582275,
      "learning_rate": 9.984893239410646e-05,
      "loss": 2.8145,
      "step": 100
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.862682342529297,
      "learning_rate": 9.939054496480722e-05,
      "loss": 2.0914,
      "step": 200
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.9071481227874756,
      "learning_rate": 9.862764840177711e-05,
      "loss": 1.931,
      "step": 300
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.2915053367614746,
      "learning_rate": 9.756494621601604e-05,
      "loss": 1.7925,
      "step": 400
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.6224589347839355,
      "learning_rate": 9.620899031988359e-05,
      "loss": 1.6613,
      "step": 500
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.952088832855225,
      "learning_rate": 9.45681406323805e-05,
      "loss": 1.5279,
      "step": 600
    },
    {
      "epoch": 7.0,
      "grad_norm": 10.756989479064941,
      "learning_rate": 9.265251353746812e-05,
      "loss": 1.3985,
      "step": 700
    },
    {
      "epoch": 8.0,
      "grad_norm": 7.803109645843506,
      "learning_rate": 9.047391951319722e-05,
      "loss": 1.2695,
      "step": 800
    },
    {
      "epoch": 9.0,
      "grad_norm": 7.662687301635742,
      "learning_rate": 8.804579031618346e-05,
      "loss": 1.1485,
      "step": 900
    },
    {
      "epoch": 10.0,
      "grad_norm": 12.890942573547363,
      "learning_rate": 8.54108314553238e-05,
      "loss": 1.0421,
      "step": 1000
    },
    {
      "epoch": 11.0,
      "grad_norm": 11.642329216003418,
      "learning_rate": 8.253208447561882e-05,
      "loss": 0.9218,
      "step": 1100
    },
    {
      "epoch": 12.0,
      "grad_norm": 10.444331169128418,
      "learning_rate": 7.945276637710582e-05,
      "loss": 0.8349,
      "step": 1200
    },
    {
      "epoch": 13.0,
      "grad_norm": 12.028226852416992,
      "learning_rate": 7.619186217983924e-05,
      "loss": 0.7391,
      "step": 1300
    },
    {
      "epoch": 14.0,
      "grad_norm": 13.66382122039795,
      "learning_rate": 7.2769476442556e-05,
      "loss": 0.6468,
      "step": 1400
    },
    {
      "epoch": 15.0,
      "grad_norm": 20.563343048095703,
      "learning_rate": 6.920670931138513e-05,
      "loss": 0.5789,
      "step": 1500
    },
    {
      "epoch": 16.0,
      "grad_norm": Infinity,
      "learning_rate": 6.556285043239972e-05,
      "loss": 0.5189,
      "step": 1600
    },
    {
      "epoch": 17.0,
      "grad_norm": 14.84958267211914,
      "learning_rate": 6.178679031907088e-05,
      "loss": 0.4609,
      "step": 1700
    },
    {
      "epoch": 18.0,
      "grad_norm": 10.033011436462402,
      "learning_rate": 5.7938060723919484e-05,
      "loss": 0.412,
      "step": 1800
    },
    {
      "epoch": 19.0,
      "grad_norm": 10.275761604309082,
      "learning_rate": 5.404039034473205e-05,
      "loss": 0.365,
      "step": 1900
    },
    {
      "epoch": 20.0,
      "grad_norm": 21.667903900146484,
      "learning_rate": 5.011780961550321e-05,
      "loss": 0.3297,
      "step": 2000
    },
    {
      "epoch": 21.0,
      "grad_norm": 15.773643493652344,
      "learning_rate": 4.619450255081913e-05,
      "loss": 0.2924,
      "step": 2100
    },
    {
      "epoch": 22.0,
      "grad_norm": 8.906744956970215,
      "learning_rate": 4.229465764336555e-05,
      "loss": 0.2637,
      "step": 2200
    },
    {
      "epoch": 23.0,
      "grad_norm": 7.449186325073242,
      "learning_rate": 3.848052866617049e-05,
      "loss": 0.2479,
      "step": 2300
    },
    {
      "epoch": 24.0,
      "grad_norm": 15.881937980651855,
      "learning_rate": 3.4736008447197823e-05,
      "loss": 0.2266,
      "step": 2400
    },
    {
      "epoch": 25.0,
      "grad_norm": 9.639005661010742,
      "learning_rate": 3.104737877380828e-05,
      "loss": 0.1991,
      "step": 2500
    },
    {
      "epoch": 26.0,
      "grad_norm": 94.2000961303711,
      "learning_rate": 2.7475598312664285e-05,
      "loss": 0.1865,
      "step": 2600
    },
    {
      "epoch": 27.0,
      "grad_norm": 6.111320972442627,
      "learning_rate": 2.404268827804637e-05,
      "loss": 0.1715,
      "step": 2700
    },
    {
      "epoch": 28.0,
      "grad_norm": 9.6605806350708,
      "learning_rate": 2.0769813701876333e-05,
      "loss": 0.1607,
      "step": 2800
    },
    {
      "epoch": 29.0,
      "grad_norm": 4.928094863891602,
      "learning_rate": 1.7677152944257513e-05,
      "loss": 0.1465,
      "step": 2900
    },
    {
      "epoch": 30.0,
      "grad_norm": 6.157331943511963,
      "learning_rate": 1.4783773287174684e-05,
      "loss": 0.1411,
      "step": 3000
    },
    {
      "epoch": 31.0,
      "grad_norm": 9.299696922302246,
      "learning_rate": 1.2107513378360164e-05,
      "loss": 0.1338,
      "step": 3100
    },
    {
      "epoch": 32.0,
      "grad_norm": 3.8831334114074707,
      "learning_rate": 9.664873250098511e-06,
      "loss": 0.1273,
      "step": 3200
    },
    {
      "epoch": 33.0,
      "grad_norm": 5.329362869262695,
      "learning_rate": 7.470912591040696e-06,
      "loss": 0.1222,
      "step": 3300
    },
    {
      "epoch": 34.0,
      "grad_norm": 6.742835521697998,
      "learning_rate": 5.539157898215786e-06,
      "loss": 0.1175,
      "step": 3400
    },
    {
      "epoch": 35.0,
      "grad_norm": 3.8493688106536865,
      "learning_rate": 3.881519081678658e-06,
      "loss": 0.1162,
      "step": 3500
    },
    {
      "epoch": 36.0,
      "grad_norm": 6.8995041847229,
      "learning_rate": 2.5082160359541142e-06,
      "loss": 0.1136,
      "step": 3600
    },
    {
      "epoch": 37.0,
      "grad_norm": 2.0875461101531982,
      "learning_rate": 1.4277156309886575e-06,
      "loss": 0.1131,
      "step": 3700
    },
    {
      "epoch": 38.0,
      "grad_norm": 4.801537036895752,
      "learning_rate": 6.466795110817214e-07,
      "loss": 0.1097,
      "step": 3800
    },
    {
      "epoch": 39.0,
      "grad_norm": 3.8173491954803467,
      "learning_rate": 1.6992302363341704e-07,
      "loss": 0.1082,
      "step": 3900
    },
    {
      "epoch": 40.0,
      "grad_norm": 9.46168041229248,
      "learning_rate": 3.8553092647219956e-10,
      "loss": 0.1102,
      "step": 4000
    }
  ],
  "logging_steps": 500,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 615486789058560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}