{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05644402634054563,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018814675446848542,
      "eval_loss": 11.94036865234375,
      "eval_runtime": 3.3357,
      "eval_samples_per_second": 67.153,
      "eval_steps_per_second": 33.576,
      "step": 1
    },
    {
      "epoch": 0.005644402634054563,
      "grad_norm": 0.2863217890262604,
      "learning_rate": 3e-05,
      "loss": 11.9358,
      "step": 3
    },
    {
      "epoch": 0.00940733772342427,
      "eval_loss": 11.93970775604248,
      "eval_runtime": 3.277,
      "eval_samples_per_second": 68.356,
      "eval_steps_per_second": 34.178,
      "step": 5
    },
    {
      "epoch": 0.011288805268109126,
      "grad_norm": 0.2686111032962799,
      "learning_rate": 6e-05,
      "loss": 11.9345,
      "step": 6
    },
    {
      "epoch": 0.016933207902163686,
      "grad_norm": 0.20651701092720032,
      "learning_rate": 9e-05,
      "loss": 11.9359,
      "step": 9
    },
    {
      "epoch": 0.01881467544684854,
      "eval_loss": 11.937393188476562,
      "eval_runtime": 3.3512,
      "eval_samples_per_second": 66.842,
      "eval_steps_per_second": 33.421,
      "step": 10
    },
    {
      "epoch": 0.022577610536218252,
      "grad_norm": 0.25992536544799805,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9336,
      "step": 12
    },
    {
      "epoch": 0.028222013170272814,
      "grad_norm": 0.2817200720310211,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9332,
      "step": 15
    },
    {
      "epoch": 0.028222013170272814,
      "eval_loss": 11.933990478515625,
      "eval_runtime": 3.3961,
      "eval_samples_per_second": 65.958,
      "eval_steps_per_second": 32.979,
      "step": 15
    },
    {
      "epoch": 0.03386641580432737,
      "grad_norm": 0.2507167160511017,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9318,
      "step": 18
    },
    {
      "epoch": 0.03762935089369708,
      "eval_loss": 11.93133544921875,
      "eval_runtime": 3.3024,
      "eval_samples_per_second": 67.83,
      "eval_steps_per_second": 33.915,
      "step": 20
    },
    {
      "epoch": 0.03951081843838194,
      "grad_norm": 0.22199992835521698,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 11.9307,
      "step": 21
    },
    {
      "epoch": 0.045155221072436504,
      "grad_norm": 0.26525187492370605,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.9266,
      "step": 24
    },
    {
      "epoch": 0.047036688617121354,
      "eval_loss": 11.929987907409668,
      "eval_runtime": 3.369,
      "eval_samples_per_second": 66.489,
      "eval_steps_per_second": 33.245,
      "step": 25
    },
    {
      "epoch": 0.05079962370649106,
      "grad_norm": 0.2282623052597046,
      "learning_rate": 5.449673790581611e-06,
      "loss": 11.9327,
      "step": 27
    },
    {
      "epoch": 0.05644402634054563,
      "grad_norm": 0.2645018398761749,
      "learning_rate": 0.0,
      "loss": 11.9229,
      "step": 30
    },
    {
      "epoch": 0.05644402634054563,
      "eval_loss": 11.929728507995605,
      "eval_runtime": 3.3494,
      "eval_samples_per_second": 66.877,
      "eval_steps_per_second": 33.439,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7617081507840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}