{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013020303535826179,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006510151767913089,
      "grad_norm": 17.231752395629883,
      "learning_rate": 1e-05,
      "loss": 44.8594,
      "step": 1
    },
    {
      "epoch": 0.0006510151767913089,
      "eval_loss": 2.7306196689605713,
      "eval_runtime": 22.5604,
      "eval_samples_per_second": 114.714,
      "eval_steps_per_second": 57.357,
      "step": 1
    },
    {
      "epoch": 0.0013020303535826179,
      "grad_norm": 25.99519920349121,
      "learning_rate": 2e-05,
      "loss": 48.9219,
      "step": 2
    },
    {
      "epoch": 0.001953045530373927,
      "grad_norm": 25.249834060668945,
      "learning_rate": 3e-05,
      "loss": 43.4375,
      "step": 3
    },
    {
      "epoch": 0.0026040607071652357,
      "grad_norm": 21.748672485351562,
      "learning_rate": 4e-05,
      "loss": 47.7812,
      "step": 4
    },
    {
      "epoch": 0.0032550758839565447,
      "grad_norm": 31.247392654418945,
      "learning_rate": 5e-05,
      "loss": 49.4531,
      "step": 5
    },
    {
      "epoch": 0.0032550758839565447,
      "eval_loss": 2.716805934906006,
      "eval_runtime": 11.3368,
      "eval_samples_per_second": 228.283,
      "eval_steps_per_second": 114.141,
      "step": 5
    },
    {
      "epoch": 0.003906091060747854,
      "grad_norm": 15.069538116455078,
      "learning_rate": 6e-05,
      "loss": 43.7188,
      "step": 6
    },
    {
      "epoch": 0.004557106237539163,
      "grad_norm": 23.0030460357666,
      "learning_rate": 7e-05,
      "loss": 45.2891,
      "step": 7
    },
    {
      "epoch": 0.005208121414330471,
      "grad_norm": 25.9981689453125,
      "learning_rate": 8e-05,
      "loss": 48.8125,
      "step": 8
    },
    {
      "epoch": 0.005859136591121781,
      "grad_norm": 13.974116325378418,
      "learning_rate": 9e-05,
      "loss": 44.5156,
      "step": 9
    },
    {
      "epoch": 0.0065101517679130895,
      "grad_norm": 27.361398696899414,
      "learning_rate": 0.0001,
      "loss": 47.6875,
      "step": 10
    },
    {
      "epoch": 0.0065101517679130895,
      "eval_loss": 2.6825039386749268,
      "eval_runtime": 11.3339,
      "eval_samples_per_second": 228.341,
      "eval_steps_per_second": 114.17,
      "step": 10
    },
    {
      "epoch": 0.007161166944704398,
      "grad_norm": 16.357383728027344,
      "learning_rate": 9.755282581475769e-05,
      "loss": 42.9062,
      "step": 11
    },
    {
      "epoch": 0.007812182121495708,
      "grad_norm": 15.48184585571289,
      "learning_rate": 9.045084971874738e-05,
      "loss": 44.2656,
      "step": 12
    },
    {
      "epoch": 0.008463197298287017,
      "grad_norm": 15.607367515563965,
      "learning_rate": 7.938926261462366e-05,
      "loss": 45.2188,
      "step": 13
    },
    {
      "epoch": 0.009114212475078326,
      "grad_norm": 15.278877258300781,
      "learning_rate": 6.545084971874738e-05,
      "loss": 43.9609,
      "step": 14
    },
    {
      "epoch": 0.009765227651869634,
      "grad_norm": 17.62762451171875,
      "learning_rate": 5e-05,
      "loss": 45.7188,
      "step": 15
    },
    {
      "epoch": 0.009765227651869634,
      "eval_loss": 2.6543149948120117,
      "eval_runtime": 11.2253,
      "eval_samples_per_second": 230.55,
      "eval_steps_per_second": 115.275,
      "step": 15
    },
    {
      "epoch": 0.010416242828660943,
      "grad_norm": 16.40966033935547,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.2578,
      "step": 16
    },
    {
      "epoch": 0.011067258005452251,
      "grad_norm": 15.669730186462402,
      "learning_rate": 2.061073738537635e-05,
      "loss": 44.1328,
      "step": 17
    },
    {
      "epoch": 0.011718273182243562,
      "grad_norm": 16.64231300354004,
      "learning_rate": 9.549150281252633e-06,
      "loss": 44.6562,
      "step": 18
    },
    {
      "epoch": 0.01236928835903487,
      "grad_norm": 15.17128849029541,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.8594,
      "step": 19
    },
    {
      "epoch": 0.013020303535826179,
      "grad_norm": 17.088932037353516,
      "learning_rate": 0.0,
      "loss": 45.0234,
      "step": 20
    },
    {
      "epoch": 0.013020303535826179,
      "eval_loss": 2.647012710571289,
      "eval_runtime": 16.1732,
      "eval_samples_per_second": 160.017,
      "eval_steps_per_second": 80.009,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 171959044276224.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}