{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005685856432125089,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005685856432125089,
      "grad_norm": 1.5823501348495483,
      "learning_rate": 2e-05,
      "loss": 0.9626,
      "step": 1
    },
    {
      "epoch": 0.0005685856432125089,
      "eval_loss": 1.1186397075653076,
      "eval_runtime": 40.6256,
      "eval_samples_per_second": 18.24,
      "eval_steps_per_second": 9.132,
      "step": 1
    },
    {
      "epoch": 0.0011371712864250178,
      "grad_norm": 1.7835773229599,
      "learning_rate": 4e-05,
      "loss": 1.0313,
      "step": 2
    },
    {
      "epoch": 0.0017057569296375266,
      "grad_norm": 1.660274624824524,
      "learning_rate": 6e-05,
      "loss": 1.144,
      "step": 3
    },
    {
      "epoch": 0.0017057569296375266,
      "eval_loss": 1.1061285734176636,
      "eval_runtime": 38.2357,
      "eval_samples_per_second": 19.38,
      "eval_steps_per_second": 9.703,
      "step": 3
    },
    {
      "epoch": 0.0022743425728500356,
      "grad_norm": 1.2570874691009521,
      "learning_rate": 8e-05,
      "loss": 0.7521,
      "step": 4
    },
    {
      "epoch": 0.0028429282160625444,
      "grad_norm": 2.45873761177063,
      "learning_rate": 0.0001,
      "loss": 1.2302,
      "step": 5
    },
    {
      "epoch": 0.003411513859275053,
      "grad_norm": 2.0134787559509277,
      "learning_rate": 0.00012,
      "loss": 1.0774,
      "step": 6
    },
    {
      "epoch": 0.003411513859275053,
      "eval_loss": 0.9874036908149719,
      "eval_runtime": 38.1771,
      "eval_samples_per_second": 19.41,
      "eval_steps_per_second": 9.718,
      "step": 6
    },
    {
      "epoch": 0.003980099502487562,
      "grad_norm": 1.5424729585647583,
      "learning_rate": 0.00014,
      "loss": 0.8746,
      "step": 7
    },
    {
      "epoch": 0.004548685145700071,
      "grad_norm": 1.2669204473495483,
      "learning_rate": 0.00016,
      "loss": 0.8404,
      "step": 8
    },
    {
      "epoch": 0.00511727078891258,
      "grad_norm": 1.3752027750015259,
      "learning_rate": 0.00018,
      "loss": 0.7102,
      "step": 9
    },
    {
      "epoch": 0.00511727078891258,
      "eval_loss": 0.9485008120536804,
      "eval_runtime": 38.0929,
      "eval_samples_per_second": 19.452,
      "eval_steps_per_second": 9.739,
      "step": 9
    },
    {
      "epoch": 0.005685856432125089,
      "grad_norm": 1.452796459197998,
      "learning_rate": 0.0002,
      "loss": 0.8366,
      "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": 3329215646662656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}