{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.61111111111111,
  "eval_steps": 1,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 1.6399296522140503,
      "eval_runtime": 32.6961,
      "eval_samples_per_second": 1.285,
      "eval_steps_per_second": 0.642,
      "step": 1
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 1.6282259225845337,
      "eval_runtime": 33.1979,
      "eval_samples_per_second": 1.265,
      "eval_steps_per_second": 0.633,
      "step": 2
    },
    {
      "epoch": 1.2222222222222223,
      "eval_loss": 1.5775563716888428,
      "eval_runtime": 33.3023,
      "eval_samples_per_second": 1.261,
      "eval_steps_per_second": 0.631,
      "step": 3
    },
    {
      "epoch": 1.6666666666666665,
      "eval_loss": 1.4133661985397339,
      "eval_runtime": 33.3356,
      "eval_samples_per_second": 1.26,
      "eval_steps_per_second": 0.63,
      "step": 4
    },
    {
      "epoch": 2.111111111111111,
      "eval_loss": 1.0690102577209473,
      "eval_runtime": 33.3402,
      "eval_samples_per_second": 1.26,
      "eval_steps_per_second": 0.63,
      "step": 5
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 1.21875,
      "learning_rate": 0.00012,
      "loss": 1.2956,
      "step": 6
    },
    {
      "epoch": 2.4444444444444446,
      "eval_loss": 0.7333933711051941,
      "eval_runtime": 33.3584,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 6
    },
    {
      "epoch": 2.888888888888889,
      "eval_loss": 0.46304765343666077,
      "eval_runtime": 33.3638,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 7
    },
    {
      "epoch": 3.2222222222222223,
      "eval_loss": 0.33892586827278137,
      "eval_runtime": 33.354,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 8
    },
    {
      "epoch": 3.6666666666666665,
      "eval_loss": 0.3081058859825134,
      "eval_runtime": 33.3492,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 9
    },
    {
      "epoch": 4.111111111111111,
      "eval_loss": 0.25422048568725586,
      "eval_runtime": 33.35,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 10
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 0.20887801051139832,
      "eval_runtime": 33.3499,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 11
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 0.67578125,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.3391,
      "step": 12
    },
    {
      "epoch": 4.888888888888889,
      "eval_loss": 0.1926366090774536,
      "eval_runtime": 33.3565,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 12
    },
    {
      "epoch": 5.222222222222222,
      "eval_loss": 0.20367372035980225,
      "eval_runtime": 33.3799,
      "eval_samples_per_second": 1.258,
      "eval_steps_per_second": 0.629,
      "step": 13
    },
    {
      "epoch": 5.666666666666667,
      "eval_loss": 0.2034320831298828,
      "eval_runtime": 33.3724,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 14
    },
    {
      "epoch": 6.111111111111111,
      "eval_loss": 0.18845374882221222,
      "eval_runtime": 33.3553,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 15
    },
    {
      "epoch": 6.444444444444445,
      "eval_loss": 0.18130186200141907,
      "eval_runtime": 33.3671,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 16
    },
    {
      "epoch": 6.888888888888889,
      "eval_loss": 0.18147918581962585,
      "eval_runtime": 33.3574,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 17
    },
    {
      "epoch": 7.166666666666667,
      "grad_norm": 0.287109375,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.1772,
      "step": 18
    },
    {
      "epoch": 7.166666666666667,
      "eval_loss": 0.1814892441034317,
      "eval_runtime": 33.362,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 18
    },
    {
      "epoch": 7.611111111111111,
      "eval_loss": 0.18450787663459778,
      "eval_runtime": 33.3689,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 19
    },
    {
      "epoch": 8.055555555555555,
      "eval_loss": 0.18693938851356506,
      "eval_runtime": 33.3701,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 20
    },
    {
      "epoch": 8.38888888888889,
      "eval_loss": 0.18996506929397583,
      "eval_runtime": 33.3472,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 21
    },
    {
      "epoch": 8.833333333333334,
      "eval_loss": 0.19113004207611084,
      "eval_runtime": 33.3691,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 22
    },
    {
      "epoch": 9.166666666666666,
      "eval_loss": 0.19181369245052338,
      "eval_runtime": 33.3709,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 23
    },
    {
      "epoch": 9.61111111111111,
      "grad_norm": 0.14453125,
      "learning_rate": 0.0,
      "loss": 0.1513,
      "step": 24
    },
    {
      "epoch": 9.61111111111111,
      "eval_loss": 0.19259721040725708,
      "eval_runtime": 33.3581,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 24
    }
  ],
  "logging_steps": 6,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4211499113735782e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}