{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006877224352251431,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.877224352251431e-05,
      "grad_norm": 0.0463884212076664,
      "learning_rate": 2e-05,
      "loss": 10.3683,
      "step": 1
    },
    {
      "epoch": 6.877224352251431e-05,
      "eval_loss": 10.368851661682129,
      "eval_runtime": 16.2788,
      "eval_samples_per_second": 376.134,
      "eval_steps_per_second": 188.098,
      "step": 1
    },
    {
      "epoch": 0.00013754448704502863,
      "grad_norm": 0.03955372795462608,
      "learning_rate": 4e-05,
      "loss": 10.3762,
      "step": 2
    },
    {
      "epoch": 0.00020631673056754294,
      "grad_norm": 0.041240863502025604,
      "learning_rate": 6e-05,
      "loss": 10.3685,
      "step": 3
    },
    {
      "epoch": 0.00020631673056754294,
      "eval_loss": 10.368825912475586,
      "eval_runtime": 16.0842,
      "eval_samples_per_second": 380.683,
      "eval_steps_per_second": 190.373,
      "step": 3
    },
    {
      "epoch": 0.00027508897409005725,
      "grad_norm": 0.03528662770986557,
      "learning_rate": 8e-05,
      "loss": 10.3814,
      "step": 4
    },
    {
      "epoch": 0.00034386121761257156,
      "grad_norm": 0.04171079769730568,
      "learning_rate": 0.0001,
      "loss": 10.3704,
      "step": 5
    },
    {
      "epoch": 0.0004126334611350859,
      "grad_norm": 0.041729431599378586,
      "learning_rate": 0.00012,
      "loss": 10.3627,
      "step": 6
    },
    {
      "epoch": 0.0004126334611350859,
      "eval_loss": 10.368712425231934,
      "eval_runtime": 16.1964,
      "eval_samples_per_second": 378.048,
      "eval_steps_per_second": 189.055,
      "step": 6
    },
    {
      "epoch": 0.0004814057046576002,
      "grad_norm": 0.034311771392822266,
      "learning_rate": 0.00014,
      "loss": 10.3716,
      "step": 7
    },
    {
      "epoch": 0.0005501779481801145,
      "grad_norm": 0.03152099996805191,
      "learning_rate": 0.00016,
      "loss": 10.3777,
      "step": 8
    },
    {
      "epoch": 0.0006189501917026289,
      "grad_norm": 0.03747215494513512,
      "learning_rate": 0.00018,
      "loss": 10.3646,
      "step": 9
    },
    {
      "epoch": 0.0006189501917026289,
      "eval_loss": 10.368529319763184,
      "eval_runtime": 16.3372,
      "eval_samples_per_second": 374.789,
      "eval_steps_per_second": 187.425,
      "step": 9
    },
    {
      "epoch": 0.0006877224352251431,
      "grad_norm": 0.04311435669660568,
      "learning_rate": 0.0002,
      "loss": 10.3634,
      "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": 135774535680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}