{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000811191193708401,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6223823874168022e-05,
      "eval_loss": 11.932548522949219,
      "eval_runtime": 232.3563,
      "eval_samples_per_second": 111.695,
      "eval_steps_per_second": 55.85,
      "step": 1
    },
    {
      "epoch": 8.111911937084011e-05,
      "grad_norm": 0.016159748658537865,
      "learning_rate": 5e-05,
      "loss": 11.9312,
      "step": 5
    },
    {
      "epoch": 0.00016223823874168022,
      "grad_norm": 0.013233560137450695,
      "learning_rate": 0.0001,
      "loss": 11.9326,
      "step": 10
    },
    {
      "epoch": 0.00016223823874168022,
      "eval_loss": 11.932516098022461,
      "eval_runtime": 236.8859,
      "eval_samples_per_second": 109.559,
      "eval_steps_per_second": 54.782,
      "step": 10
    },
    {
      "epoch": 0.00024335735811252033,
      "grad_norm": 0.009878978133201599,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9322,
      "step": 15
    },
    {
      "epoch": 0.00032447647748336044,
      "grad_norm": 0.015007059089839458,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9334,
      "step": 20
    },
    {
      "epoch": 0.00032447647748336044,
      "eval_loss": 11.932459831237793,
      "eval_runtime": 234.0158,
      "eval_samples_per_second": 110.903,
      "eval_steps_per_second": 55.454,
      "step": 20
    },
    {
      "epoch": 0.0004055955968542005,
      "grad_norm": 0.011904916726052761,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9332,
      "step": 25
    },
    {
      "epoch": 0.00048671471622504066,
      "grad_norm": 0.016311276704072952,
      "learning_rate": 5e-05,
      "loss": 11.9314,
      "step": 30
    },
    {
      "epoch": 0.00048671471622504066,
      "eval_loss": 11.932413101196289,
      "eval_runtime": 236.2597,
      "eval_samples_per_second": 109.849,
      "eval_steps_per_second": 54.927,
      "step": 30
    },
    {
      "epoch": 0.0005678338355958808,
      "grad_norm": 0.012984448112547398,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.932,
      "step": 35
    },
    {
      "epoch": 0.0006489529549667209,
      "grad_norm": 0.0169618409126997,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9312,
      "step": 40
    },
    {
      "epoch": 0.0006489529549667209,
      "eval_loss": 11.93238639831543,
      "eval_runtime": 235.5856,
      "eval_samples_per_second": 110.164,
      "eval_steps_per_second": 55.084,
      "step": 40
    },
    {
      "epoch": 0.000730072074337561,
      "grad_norm": 0.02265729382634163,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9316,
      "step": 45
    },
    {
      "epoch": 0.000811191193708401,
      "grad_norm": 0.009908193722367287,
      "learning_rate": 0.0,
      "loss": 11.9326,
      "step": 50
    },
    {
      "epoch": 0.000811191193708401,
      "eval_loss": 11.932382583618164,
      "eval_runtime": 235.7842,
      "eval_samples_per_second": 110.071,
      "eval_steps_per_second": 55.038,
      "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": 5937610752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}