{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0410958904109589,
  "eval_steps": 6,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016438356164383563,
      "grad_norm": 18.2674560546875,
      "learning_rate": 1e-05,
      "loss": 7.2877,
      "step": 1
    },
    {
      "epoch": 0.0016438356164383563,
      "eval_loss": 7.202574729919434,
      "eval_runtime": 400.2611,
      "eval_samples_per_second": 1.921,
      "eval_steps_per_second": 0.482,
      "step": 1
    },
    {
      "epoch": 0.0032876712328767125,
      "grad_norm": 17.67232894897461,
      "learning_rate": 2e-05,
      "loss": 7.1103,
      "step": 2
    },
    {
      "epoch": 0.004931506849315068,
      "grad_norm": 18.076366424560547,
      "learning_rate": 3e-05,
      "loss": 6.7461,
      "step": 3
    },
    {
      "epoch": 0.006575342465753425,
      "grad_norm": 16.23063850402832,
      "learning_rate": 4e-05,
      "loss": 6.8808,
      "step": 4
    },
    {
      "epoch": 0.00821917808219178,
      "grad_norm": 15.608308792114258,
      "learning_rate": 5e-05,
      "loss": 6.2408,
      "step": 5
    },
    {
      "epoch": 0.009863013698630137,
      "grad_norm": 15.950782775878906,
      "learning_rate": 6e-05,
      "loss": 5.2182,
      "step": 6
    },
    {
      "epoch": 0.009863013698630137,
      "eval_loss": 3.6735994815826416,
      "eval_runtime": 401.6303,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.481,
      "step": 6
    },
    {
      "epoch": 0.011506849315068493,
      "grad_norm": 17.16571044921875,
      "learning_rate": 7e-05,
      "loss": 3.5523,
      "step": 7
    },
    {
      "epoch": 0.01315068493150685,
      "grad_norm": 15.576335906982422,
      "learning_rate": 8e-05,
      "loss": 2.116,
      "step": 8
    },
    {
      "epoch": 0.014794520547945205,
      "grad_norm": 8.430649757385254,
      "learning_rate": 9e-05,
      "loss": 1.4004,
      "step": 9
    },
    {
      "epoch": 0.01643835616438356,
      "grad_norm": 4.160114288330078,
      "learning_rate": 0.0001,
      "loss": 0.9875,
      "step": 10
    },
    {
      "epoch": 0.01808219178082192,
      "grad_norm": 4.697726726531982,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.8455,
      "step": 11
    },
    {
      "epoch": 0.019726027397260273,
      "grad_norm": 3.292222499847412,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.7364,
      "step": 12
    },
    {
      "epoch": 0.019726027397260273,
      "eval_loss": 0.734883189201355,
      "eval_runtime": 401.7356,
      "eval_samples_per_second": 1.914,
      "eval_steps_per_second": 0.48,
      "step": 12
    },
    {
      "epoch": 0.021369863013698632,
      "grad_norm": 3.199315071105957,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.7187,
      "step": 13
    },
    {
      "epoch": 0.023013698630136987,
      "grad_norm": 3.5907278060913086,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7173,
      "step": 14
    },
    {
      "epoch": 0.024657534246575342,
      "grad_norm": 9.821634292602539,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9381,
      "step": 15
    },
    {
      "epoch": 0.0263013698630137,
      "grad_norm": 3.7522168159484863,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.744,
      "step": 16
    },
    {
      "epoch": 0.027945205479452055,
      "grad_norm": 2.0294668674468994,
      "learning_rate": 9.263200821770461e-05,
      "loss": 0.6902,
      "step": 17
    },
    {
      "epoch": 0.02958904109589041,
      "grad_norm": 2.3452353477478027,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.729,
      "step": 18
    },
    {
      "epoch": 0.02958904109589041,
      "eval_loss": 0.7356500029563904,
      "eval_runtime": 401.8552,
      "eval_samples_per_second": 1.914,
      "eval_steps_per_second": 0.48,
      "step": 18
    },
    {
      "epoch": 0.03123287671232877,
      "grad_norm": 3.9628705978393555,
      "learning_rate": 8.802029828000156e-05,
      "loss": 0.7545,
      "step": 19
    },
    {
      "epoch": 0.03287671232876712,
      "grad_norm": 1.9698278903961182,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6791,
      "step": 20
    },
    {
      "epoch": 0.03452054794520548,
      "grad_norm": 1.0390818119049072,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.6828,
      "step": 21
    },
    {
      "epoch": 0.03616438356164384,
      "grad_norm": 3.9402551651000977,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7803,
      "step": 22
    },
    {
      "epoch": 0.03780821917808219,
      "grad_norm": 6.37379264831543,
      "learning_rate": 7.612492823579745e-05,
      "loss": 0.883,
      "step": 23
    },
    {
      "epoch": 0.03945205479452055,
      "grad_norm": 3.2149131298065186,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.7417,
      "step": 24
    },
    {
      "epoch": 0.03945205479452055,
      "eval_loss": 0.7024959921836853,
      "eval_runtime": 401.4676,
      "eval_samples_per_second": 1.915,
      "eval_steps_per_second": 0.481,
      "step": 24
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 2.5781383514404297,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7425,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.119015678246912e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}