{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015670910871694416,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015670910871694416,
      "grad_norm": 0.017084021121263504,
      "learning_rate": 2e-05,
      "loss": 10.3817,
      "step": 1
    },
    {
      "epoch": 0.00015670910871694416,
      "eval_loss": 10.377445220947266,
      "eval_runtime": 16.8743,
      "eval_samples_per_second": 159.236,
      "eval_steps_per_second": 79.648,
      "step": 1
    },
    {
      "epoch": 0.0003134182174338883,
      "grad_norm": 0.016867632046341896,
      "learning_rate": 4e-05,
      "loss": 10.3794,
      "step": 2
    },
    {
      "epoch": 0.0004701273261508325,
      "grad_norm": 0.03566126897931099,
      "learning_rate": 6e-05,
      "loss": 10.3702,
      "step": 3
    },
    {
      "epoch": 0.0004701273261508325,
      "eval_loss": 10.377437591552734,
      "eval_runtime": 16.9608,
      "eval_samples_per_second": 158.424,
      "eval_steps_per_second": 79.241,
      "step": 3
    },
    {
      "epoch": 0.0006268364348677766,
      "grad_norm": 0.023006998002529144,
      "learning_rate": 8e-05,
      "loss": 10.3757,
      "step": 4
    },
    {
      "epoch": 0.0007835455435847208,
      "grad_norm": 0.02287760190665722,
      "learning_rate": 0.0001,
      "loss": 10.3744,
      "step": 5
    },
    {
      "epoch": 0.000940254652301665,
      "grad_norm": 0.02409427799284458,
      "learning_rate": 0.00012,
      "loss": 10.3829,
      "step": 6
    },
    {
      "epoch": 0.000940254652301665,
      "eval_loss": 10.377397537231445,
      "eval_runtime": 17.0744,
      "eval_samples_per_second": 157.37,
      "eval_steps_per_second": 78.714,
      "step": 6
    },
    {
      "epoch": 0.0010969637610186093,
      "grad_norm": 0.018140584230422974,
      "learning_rate": 0.00014,
      "loss": 10.3776,
      "step": 7
    },
    {
      "epoch": 0.0012536728697355533,
      "grad_norm": 0.022324591875076294,
      "learning_rate": 0.00016,
      "loss": 10.3753,
      "step": 8
    },
    {
      "epoch": 0.0014103819784524975,
      "grad_norm": 0.025807922706007957,
      "learning_rate": 0.00018,
      "loss": 10.382,
      "step": 9
    },
    {
      "epoch": 0.0014103819784524975,
      "eval_loss": 10.37732982635498,
      "eval_runtime": 17.0006,
      "eval_samples_per_second": 158.053,
      "eval_steps_per_second": 79.056,
      "step": 9
    },
    {
      "epoch": 0.0015670910871694416,
      "grad_norm": 0.01946774125099182,
      "learning_rate": 0.0002,
      "loss": 10.3783,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 164869079040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}