{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014825796886582653,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014825796886582654,
      "grad_norm": 0.8024897575378418,
      "learning_rate": 2e-05,
      "loss": 1.4327,
      "step": 1
    },
    {
      "epoch": 0.00014825796886582654,
      "eval_loss": 1.423957109451294,
      "eval_runtime": 63.9424,
      "eval_samples_per_second": 44.415,
      "eval_steps_per_second": 22.208,
      "step": 1
    },
    {
      "epoch": 0.0002965159377316531,
      "grad_norm": 0.6338537335395813,
      "learning_rate": 4e-05,
      "loss": 1.3985,
      "step": 2
    },
    {
      "epoch": 0.00044477390659747963,
      "grad_norm": 0.7848641276359558,
      "learning_rate": 6e-05,
      "loss": 1.461,
      "step": 3
    },
    {
      "epoch": 0.00044477390659747963,
      "eval_loss": 1.4189410209655762,
      "eval_runtime": 62.7655,
      "eval_samples_per_second": 45.248,
      "eval_steps_per_second": 22.624,
      "step": 3
    },
    {
      "epoch": 0.0005930318754633062,
      "grad_norm": 0.7131264209747314,
      "learning_rate": 8e-05,
      "loss": 1.3658,
      "step": 4
    },
    {
      "epoch": 0.0007412898443291327,
      "grad_norm": 0.7118561267852783,
      "learning_rate": 0.0001,
      "loss": 1.5296,
      "step": 5
    },
    {
      "epoch": 0.0008895478131949593,
      "grad_norm": 0.776576578617096,
      "learning_rate": 0.00012,
      "loss": 1.3735,
      "step": 6
    },
    {
      "epoch": 0.0008895478131949593,
      "eval_loss": 1.362064003944397,
      "eval_runtime": 62.878,
      "eval_samples_per_second": 45.167,
      "eval_steps_per_second": 22.583,
      "step": 6
    },
    {
      "epoch": 0.0010378057820607859,
      "grad_norm": 0.6471361517906189,
      "learning_rate": 0.00014,
      "loss": 1.3516,
      "step": 7
    },
    {
      "epoch": 0.0011860637509266123,
      "grad_norm": 0.6238671541213989,
      "learning_rate": 0.00016,
      "loss": 1.4295,
      "step": 8
    },
    {
      "epoch": 0.0013343217197924388,
      "grad_norm": 0.7230969071388245,
      "learning_rate": 0.00018,
      "loss": 1.2367,
      "step": 9
    },
    {
      "epoch": 0.0013343217197924388,
      "eval_loss": 1.3056071996688843,
      "eval_runtime": 62.7943,
      "eval_samples_per_second": 45.227,
      "eval_steps_per_second": 22.614,
      "step": 9
    },
    {
      "epoch": 0.0014825796886582653,
      "grad_norm": 0.8463790416717529,
      "learning_rate": 0.0002,
      "loss": 1.4213,
      "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": 155816786657280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}