{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01176401388153638,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002352802776307276,
      "eval_loss": 9.940110206604004,
      "eval_runtime": 112.3066,
      "eval_samples_per_second": 15.939,
      "eval_steps_per_second": 7.969,
      "step": 1
    },
    {
      "epoch": 0.001176401388153638,
      "grad_norm": 84.26264190673828,
      "learning_rate": 5e-05,
      "loss": 39.911,
      "step": 5
    },
    {
      "epoch": 0.002352802776307276,
      "grad_norm": 91.40861511230469,
      "learning_rate": 0.0001,
      "loss": 26.6323,
      "step": 10
    },
    {
      "epoch": 0.002352802776307276,
      "eval_loss": 2.8446736335754395,
      "eval_runtime": 112.7933,
      "eval_samples_per_second": 15.87,
      "eval_steps_per_second": 7.935,
      "step": 10
    },
    {
      "epoch": 0.0035292041644609143,
      "grad_norm": 56.89608383178711,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.8756,
      "step": 15
    },
    {
      "epoch": 0.004705605552614552,
      "grad_norm": 71.20320129394531,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.0662,
      "step": 20
    },
    {
      "epoch": 0.004705605552614552,
      "eval_loss": 0.3466031849384308,
      "eval_runtime": 112.4854,
      "eval_samples_per_second": 15.913,
      "eval_steps_per_second": 7.957,
      "step": 20
    },
    {
      "epoch": 0.00588200694076819,
      "grad_norm": 16.495267868041992,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9863,
      "step": 25
    },
    {
      "epoch": 0.0070584083289218285,
      "grad_norm": 21.18825340270996,
      "learning_rate": 5e-05,
      "loss": 1.1181,
      "step": 30
    },
    {
      "epoch": 0.0070584083289218285,
      "eval_loss": 0.3385402262210846,
      "eval_runtime": 112.5232,
      "eval_samples_per_second": 15.908,
      "eval_steps_per_second": 7.954,
      "step": 30
    },
    {
      "epoch": 0.008234809717075466,
      "grad_norm": 6.755566596984863,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9769,
      "step": 35
    },
    {
      "epoch": 0.009411211105229104,
      "grad_norm": 16.23630142211914,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.084,
      "step": 40
    },
    {
      "epoch": 0.009411211105229104,
      "eval_loss": 0.23241721093654633,
      "eval_runtime": 112.5922,
      "eval_samples_per_second": 15.898,
      "eval_steps_per_second": 7.949,
      "step": 40
    },
    {
      "epoch": 0.010587612493382742,
      "grad_norm": 5.550320148468018,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9626,
      "step": 45
    },
    {
      "epoch": 0.01176401388153638,
      "grad_norm": 34.21563720703125,
      "learning_rate": 0.0,
      "loss": 1.0023,
      "step": 50
    },
    {
      "epoch": 0.01176401388153638,
      "eval_loss": 0.2757435441017151,
      "eval_runtime": 112.4167,
      "eval_samples_per_second": 15.923,
      "eval_steps_per_second": 7.961,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8763348929740800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}