{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12004801920768307,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024009603841536613,
      "eval_loss": 1.4358983039855957,
      "eval_runtime": 13.5379,
      "eval_samples_per_second": 13.001,
      "eval_steps_per_second": 6.5,
      "step": 1
    },
    {
      "epoch": 0.012004801920768308,
      "grad_norm": 15.937287330627441,
      "learning_rate": 5e-05,
      "loss": 6.0666,
      "step": 5
    },
    {
      "epoch": 0.024009603841536616,
      "grad_norm": 11.59009838104248,
      "learning_rate": 0.0001,
      "loss": 5.4448,
      "step": 10
    },
    {
      "epoch": 0.024009603841536616,
      "eval_loss": 1.3160247802734375,
      "eval_runtime": 13.6666,
      "eval_samples_per_second": 12.878,
      "eval_steps_per_second": 6.439,
      "step": 10
    },
    {
      "epoch": 0.03601440576230492,
      "grad_norm": 7.118363857269287,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.4109,
      "step": 15
    },
    {
      "epoch": 0.04801920768307323,
      "grad_norm": 7.1571221351623535,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.235,
      "step": 20
    },
    {
      "epoch": 0.04801920768307323,
      "eval_loss": 1.2547309398651123,
      "eval_runtime": 13.7282,
      "eval_samples_per_second": 12.82,
      "eval_steps_per_second": 6.41,
      "step": 20
    },
    {
      "epoch": 0.060024009603841535,
      "grad_norm": 6.3883891105651855,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.8792,
      "step": 25
    },
    {
      "epoch": 0.07202881152460984,
      "grad_norm": 8.490561485290527,
      "learning_rate": 5e-05,
      "loss": 5.1044,
      "step": 30
    },
    {
      "epoch": 0.07202881152460984,
      "eval_loss": 1.2332581281661987,
      "eval_runtime": 13.8173,
      "eval_samples_per_second": 12.738,
      "eval_steps_per_second": 6.369,
      "step": 30
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 7.227184772491455,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.9676,
      "step": 35
    },
    {
      "epoch": 0.09603841536614646,
      "grad_norm": 6.193565845489502,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 4.9788,
      "step": 40
    },
    {
      "epoch": 0.09603841536614646,
      "eval_loss": 1.2202028036117554,
      "eval_runtime": 13.884,
      "eval_samples_per_second": 12.676,
      "eval_steps_per_second": 6.338,
      "step": 40
    },
    {
      "epoch": 0.10804321728691477,
      "grad_norm": 7.4627366065979,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.1128,
      "step": 45
    },
    {
      "epoch": 0.12004801920768307,
      "grad_norm": 5.629809856414795,
      "learning_rate": 0.0,
      "loss": 4.637,
      "step": 50
    },
    {
      "epoch": 0.12004801920768307,
      "eval_loss": 1.217408299446106,
      "eval_runtime": 13.7389,
      "eval_samples_per_second": 12.81,
      "eval_steps_per_second": 6.405,
      "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": 1.1129465925009408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}