{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8682719966786276,
  "eval_steps": 7000,
  "global_step": 63000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2075857774087364,
      "grad_norm": 6.259258952923119e-05,
      "learning_rate": 9.958482297312883e-06,
      "loss": 0.015,
      "step": 7000
    },
    {
      "epoch": 0.2075857774087364,
      "eval_loss": 0.005288162734359503,
      "eval_runtime": 299.0787,
      "eval_samples_per_second": 225.496,
      "eval_steps_per_second": 28.19,
      "step": 7000
    },
    {
      "epoch": 0.4151715548174728,
      "grad_norm": 0.0349661149084568,
      "learning_rate": 8.805542283803155e-06,
      "loss": 0.0059,
      "step": 14000
    },
    {
      "epoch": 0.4151715548174728,
      "eval_loss": 0.004213849548250437,
      "eval_runtime": 305.6778,
      "eval_samples_per_second": 220.628,
      "eval_steps_per_second": 27.581,
      "step": 14000
    },
    {
      "epoch": 0.6227573322262092,
      "grad_norm": 0.0007877133903093636,
      "learning_rate": 7.652767023081867e-06,
      "loss": 0.0041,
      "step": 21000
    },
    {
      "epoch": 0.6227573322262092,
      "eval_loss": 0.0033566548954695463,
      "eval_runtime": 304.5219,
      "eval_samples_per_second": 221.465,
      "eval_steps_per_second": 27.686,
      "step": 21000
    },
    {
      "epoch": 0.8303431096349456,
      "grad_norm": 0.006591067183762789,
      "learning_rate": 6.50015651514902e-06,
      "loss": 0.0038,
      "step": 28000
    },
    {
      "epoch": 0.8303431096349456,
      "eval_loss": 0.003017185255885124,
      "eval_runtime": 310.7502,
      "eval_samples_per_second": 217.026,
      "eval_steps_per_second": 27.131,
      "step": 28000
    },
    {
      "epoch": 1.037928887043682,
      "grad_norm": 6.050535012036562e-05,
      "learning_rate": 5.3470517488508496e-06,
      "loss": 0.0028,
      "step": 35000
    },
    {
      "epoch": 1.037928887043682,
      "eval_loss": 0.00263745104894042,
      "eval_runtime": 318.0582,
      "eval_samples_per_second": 212.04,
      "eval_steps_per_second": 26.508,
      "step": 35000
    },
    {
      "epoch": 1.2455146644524184,
      "grad_norm": 0.0005422074464149773,
      "learning_rate": 4.194276488129561e-06,
      "loss": 0.0023,
      "step": 42000
    },
    {
      "epoch": 1.2455146644524184,
      "eval_loss": 0.002334447344765067,
      "eval_runtime": 308.969,
      "eval_samples_per_second": 218.278,
      "eval_steps_per_second": 27.288,
      "step": 42000
    },
    {
      "epoch": 1.4531004418611548,
      "grad_norm": 4.648882895708084e-05,
      "learning_rate": 3.041501227408274e-06,
      "loss": 0.0011,
      "step": 49000
    },
    {
      "epoch": 1.4531004418611548,
      "eval_loss": 0.0022575457114726305,
      "eval_runtime": 293.5363,
      "eval_samples_per_second": 229.753,
      "eval_steps_per_second": 28.722,
      "step": 49000
    },
    {
      "epoch": 1.6606862192698912,
      "grad_norm": 5.3200383263174444e-05,
      "learning_rate": 1.8890554722638682e-06,
      "loss": 0.0008,
      "step": 56000
    },
    {
      "epoch": 1.6606862192698912,
      "eval_loss": 0.0020312555134296417,
      "eval_runtime": 311.6551,
      "eval_samples_per_second": 216.396,
      "eval_steps_per_second": 27.052,
      "step": 56000
    },
    {
      "epoch": 1.8682719966786276,
      "grad_norm": 7.308552449103445e-05,
      "learning_rate": 7.359507059656985e-07,
      "loss": 0.0007,
      "step": 63000
    },
    {
      "epoch": 1.8682719966786276,
      "eval_loss": 0.00200638803653419,
      "eval_runtime": 310.1684,
      "eval_samples_per_second": 217.433,
      "eval_steps_per_second": 27.182,
      "step": 63000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 67442,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}