{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000885696445257317,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.771392890514634e-05,
      "eval_loss": 10.875212669372559,
      "eval_runtime": 1587.4066,
      "eval_samples_per_second": 14.974,
      "eval_steps_per_second": 7.487,
      "step": 1
    },
    {
      "epoch": 8.85696445257317e-05,
      "grad_norm": 10.146245002746582,
      "learning_rate": 5e-05,
      "loss": 9.9397,
      "step": 5
    },
    {
      "epoch": 0.0001771392890514634,
      "grad_norm": 16.552648544311523,
      "learning_rate": 0.0001,
      "loss": 10.5492,
      "step": 10
    },
    {
      "epoch": 0.0001771392890514634,
      "eval_loss": 8.176838874816895,
      "eval_runtime": 1588.7522,
      "eval_samples_per_second": 14.961,
      "eval_steps_per_second": 7.481,
      "step": 10
    },
    {
      "epoch": 0.00026570893357719507,
      "grad_norm": 20.21416473388672,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.6639,
      "step": 15
    },
    {
      "epoch": 0.0003542785781029268,
      "grad_norm": 12.341681480407715,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.4964,
      "step": 20
    },
    {
      "epoch": 0.0003542785781029268,
      "eval_loss": 2.387244701385498,
      "eval_runtime": 1594.7076,
      "eval_samples_per_second": 14.906,
      "eval_steps_per_second": 7.453,
      "step": 20
    },
    {
      "epoch": 0.0004428482226286585,
      "grad_norm": 11.880754470825195,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.833,
      "step": 25
    },
    {
      "epoch": 0.0005314178671543901,
      "grad_norm": 11.601590156555176,
      "learning_rate": 5e-05,
      "loss": 1.6242,
      "step": 30
    },
    {
      "epoch": 0.0005314178671543901,
      "eval_loss": 1.7157038450241089,
      "eval_runtime": 1595.6324,
      "eval_samples_per_second": 14.897,
      "eval_steps_per_second": 7.448,
      "step": 30
    },
    {
      "epoch": 0.0006199875116801219,
      "grad_norm": 20.013578414916992,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6083,
      "step": 35
    },
    {
      "epoch": 0.0007085571562058535,
      "grad_norm": 7.160251140594482,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4506,
      "step": 40
    },
    {
      "epoch": 0.0007085571562058535,
      "eval_loss": 1.5205236673355103,
      "eval_runtime": 1600.3605,
      "eval_samples_per_second": 14.853,
      "eval_steps_per_second": 7.426,
      "step": 40
    },
    {
      "epoch": 0.0007971268007315853,
      "grad_norm": 9.940959930419922,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.1803,
      "step": 45
    },
    {
      "epoch": 0.000885696445257317,
      "grad_norm": 10.175341606140137,
      "learning_rate": 0.0,
      "loss": 1.3866,
      "step": 50
    },
    {
      "epoch": 0.000885696445257317,
      "eval_loss": 1.4981493949890137,
      "eval_runtime": 1604.4754,
      "eval_samples_per_second": 14.815,
      "eval_steps_per_second": 7.407,
      "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": 9386538559340544.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}