{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006838905775075988,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007598784194528875,
      "grad_norm": 3.105186700820923,
      "learning_rate": 2e-05,
      "loss": 9.0112,
      "step": 1
    },
    {
      "epoch": 0.0007598784194528875,
      "eval_loss": 8.610201835632324,
      "eval_runtime": 4.1922,
      "eval_samples_per_second": 132.389,
      "eval_steps_per_second": 66.314,
      "step": 1
    },
    {
      "epoch": 0.001519756838905775,
      "grad_norm": 2.8080806732177734,
      "learning_rate": 4e-05,
      "loss": 8.5327,
      "step": 2
    },
    {
      "epoch": 0.0022796352583586625,
      "grad_norm": 3.564710855484009,
      "learning_rate": 6e-05,
      "loss": 8.4969,
      "step": 3
    },
    {
      "epoch": 0.0022796352583586625,
      "eval_loss": 8.608213424682617,
      "eval_runtime": 4.2073,
      "eval_samples_per_second": 131.915,
      "eval_steps_per_second": 66.076,
      "step": 3
    },
    {
      "epoch": 0.00303951367781155,
      "grad_norm": 3.1519551277160645,
      "learning_rate": 8e-05,
      "loss": 8.383,
      "step": 4
    },
    {
      "epoch": 0.003799392097264438,
      "grad_norm": 3.0586771965026855,
      "learning_rate": 0.0001,
      "loss": 8.5196,
      "step": 5
    },
    {
      "epoch": 0.004559270516717325,
      "grad_norm": 2.610563039779663,
      "learning_rate": 0.00012,
      "loss": 8.6136,
      "step": 6
    },
    {
      "epoch": 0.004559270516717325,
      "eval_loss": 8.571167945861816,
      "eval_runtime": 4.3244,
      "eval_samples_per_second": 128.341,
      "eval_steps_per_second": 64.286,
      "step": 6
    },
    {
      "epoch": 0.005319148936170213,
      "grad_norm": 3.2952821254730225,
      "learning_rate": 0.00014,
      "loss": 8.6017,
      "step": 7
    },
    {
      "epoch": 0.0060790273556231,
      "grad_norm": 2.317990779876709,
      "learning_rate": 0.00016,
      "loss": 7.7968,
      "step": 8
    },
    {
      "epoch": 0.006838905775075988,
      "grad_norm": 2.775648593902588,
      "learning_rate": 0.00018,
      "loss": 8.2047,
      "step": 9
    },
    {
      "epoch": 0.006838905775075988,
      "eval_loss": 8.484367370605469,
      "eval_runtime": 4.3445,
      "eval_samples_per_second": 127.748,
      "eval_steps_per_second": 63.989,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1130884890624.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}