{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004968326915911067,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004968326915911067,
      "grad_norm": 8.897107124328613,
      "learning_rate": 2e-05,
      "loss": 13.4967,
      "step": 1
    },
    {
      "epoch": 0.0004968326915911067,
      "eval_loss": 4.478808879852295,
      "eval_runtime": 9.642,
      "eval_samples_per_second": 87.949,
      "eval_steps_per_second": 43.974,
      "step": 1
    },
    {
      "epoch": 0.0009936653831822133,
      "grad_norm": 13.745929718017578,
      "learning_rate": 4e-05,
      "loss": 18.8801,
      "step": 2
    },
    {
      "epoch": 0.0014904980747733202,
      "grad_norm": 10.752406120300293,
      "learning_rate": 6e-05,
      "loss": 16.3086,
      "step": 3
    },
    {
      "epoch": 0.0014904980747733202,
      "eval_loss": 4.450636863708496,
      "eval_runtime": 9.8753,
      "eval_samples_per_second": 85.871,
      "eval_steps_per_second": 42.935,
      "step": 3
    },
    {
      "epoch": 0.0019873307663644266,
      "grad_norm": 14.035537719726562,
      "learning_rate": 8e-05,
      "loss": 19.2806,
      "step": 4
    },
    {
      "epoch": 0.0024841634579555335,
      "grad_norm": 10.670316696166992,
      "learning_rate": 0.0001,
      "loss": 13.925,
      "step": 5
    },
    {
      "epoch": 0.0029809961495466403,
      "grad_norm": 12.22524356842041,
      "learning_rate": 0.00012,
      "loss": 18.4843,
      "step": 6
    },
    {
      "epoch": 0.0029809961495466403,
      "eval_loss": 4.24907922744751,
      "eval_runtime": 9.7856,
      "eval_samples_per_second": 86.658,
      "eval_steps_per_second": 43.329,
      "step": 6
    },
    {
      "epoch": 0.0034778288411377468,
      "grad_norm": 10.040848731994629,
      "learning_rate": 0.00014,
      "loss": 16.4169,
      "step": 7
    },
    {
      "epoch": 0.003974661532728853,
      "grad_norm": 17.642581939697266,
      "learning_rate": 0.00016,
      "loss": 20.6224,
      "step": 8
    },
    {
      "epoch": 0.0044714942243199605,
      "grad_norm": 17.910484313964844,
      "learning_rate": 0.00018,
      "loss": 18.6167,
      "step": 9
    },
    {
      "epoch": 0.0044714942243199605,
      "eval_loss": 3.810196876525879,
      "eval_runtime": 9.7781,
      "eval_samples_per_second": 86.724,
      "eval_steps_per_second": 43.362,
      "step": 9
    },
    {
      "epoch": 0.004968326915911067,
      "grad_norm": 13.06505298614502,
      "learning_rate": 0.0002,
      "loss": 16.2331,
      "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": 75069652992000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}