{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8682719966786276,
  "eval_steps": 7000,
  "global_step": 63000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2075857774087364,
      "grad_norm": 0.007890098728239536,
      "learning_rate": 9.958647050101323e-06,
      "loss": 0.012,
      "step": 7000
    },
    {
      "epoch": 0.2075857774087364,
      "eval_loss": 0.005739695392549038,
      "eval_runtime": 412.7277,
      "eval_samples_per_second": 163.403,
      "eval_steps_per_second": 20.428,
      "step": 7000
    },
    {
      "epoch": 0.4151715548174728,
      "grad_norm": 0.07381915301084518,
      "learning_rate": 8.805871789380036e-06,
      "loss": 0.0044,
      "step": 14000
    },
    {
      "epoch": 0.4151715548174728,
      "eval_loss": 0.003970430698245764,
      "eval_runtime": 417.73,
      "eval_samples_per_second": 161.446,
      "eval_steps_per_second": 20.183,
      "step": 14000
    },
    {
      "epoch": 0.6227573322262092,
      "grad_norm": 0.01579739712178707,
      "learning_rate": 7.653096528658748e-06,
      "loss": 0.0038,
      "step": 21000
    },
    {
      "epoch": 0.6227573322262092,
      "eval_loss": 0.004011470824480057,
      "eval_runtime": 416.5579,
      "eval_samples_per_second": 161.901,
      "eval_steps_per_second": 20.24,
      "step": 21000
    },
    {
      "epoch": 0.8303431096349456,
      "grad_norm": 0.024147002026438713,
      "learning_rate": 6.500321267937461e-06,
      "loss": 0.0033,
      "step": 28000
    },
    {
      "epoch": 0.8303431096349456,
      "eval_loss": 0.0028445960488170385,
      "eval_runtime": 416.8518,
      "eval_samples_per_second": 161.787,
      "eval_steps_per_second": 20.225,
      "step": 28000
    },
    {
      "epoch": 1.037928887043682,
      "grad_norm": 0.00019609538139775395,
      "learning_rate": 5.347381254427731e-06,
      "loss": 0.002,
      "step": 35000
    },
    {
      "epoch": 1.037928887043682,
      "eval_loss": 0.002484912285581231,
      "eval_runtime": 415.7525,
      "eval_samples_per_second": 162.214,
      "eval_steps_per_second": 20.279,
      "step": 35000
    },
    {
      "epoch": 1.2455146644524184,
      "grad_norm": 0.008880384266376495,
      "learning_rate": 4.194276488129561e-06,
      "loss": 0.0012,
      "step": 42000
    },
    {
      "epoch": 1.2455146644524184,
      "eval_loss": 0.0021632197313010693,
      "eval_runtime": 408.105,
      "eval_samples_per_second": 165.254,
      "eval_steps_per_second": 20.659,
      "step": 42000
    },
    {
      "epoch": 1.4531004418611548,
      "grad_norm": 0.003053226973861456,
      "learning_rate": 3.0413364746198333e-06,
      "loss": 0.0008,
      "step": 49000
    },
    {
      "epoch": 1.4531004418611548,
      "eval_loss": 0.002097294433042407,
      "eval_runtime": 407.9995,
      "eval_samples_per_second": 165.297,
      "eval_steps_per_second": 20.664,
      "step": 49000
    },
    {
      "epoch": 1.6606862192698912,
      "grad_norm": 0.00016563042299821973,
      "learning_rate": 1.8883964611101043e-06,
      "loss": 0.0005,
      "step": 56000
    },
    {
      "epoch": 1.6606862192698912,
      "eval_loss": 0.0021241051144897938,
      "eval_runtime": 407.4084,
      "eval_samples_per_second": 165.537,
      "eval_steps_per_second": 20.694,
      "step": 56000
    },
    {
      "epoch": 1.8682719966786276,
      "grad_norm": 0.0011578386183828115,
      "learning_rate": 7.354564476003758e-07,
      "loss": 0.0004,
      "step": 63000
    },
    {
      "epoch": 1.8682719966786276,
      "eval_loss": 0.001993535552173853,
      "eval_runtime": 406.6423,
      "eval_samples_per_second": 165.848,
      "eval_steps_per_second": 20.733,
      "step": 63000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 67442,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}