{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11214953271028037,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 1.2704600095748901,
      "learning_rate": 2e-05,
      "loss": 2.2598,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 2.2257795333862305,
      "eval_runtime": 0.9227,
      "eval_samples_per_second": 98.625,
      "eval_steps_per_second": 13.005,
      "step": 1
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 1.3961941003799438,
      "learning_rate": 4e-05,
      "loss": 2.262,
      "step": 2
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 1.301194429397583,
      "learning_rate": 6e-05,
      "loss": 2.2203,
      "step": 3
    },
    {
      "epoch": 0.056074766355140186,
      "eval_loss": 2.207164764404297,
      "eval_runtime": 0.9897,
      "eval_samples_per_second": 91.95,
      "eval_steps_per_second": 12.125,
      "step": 3
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 1.3056365251541138,
      "learning_rate": 8e-05,
      "loss": 2.1908,
      "step": 4
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.2624163627624512,
      "learning_rate": 0.0001,
      "loss": 2.1388,
      "step": 5
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 1.3537291288375854,
      "learning_rate": 0.00012,
      "loss": 2.1188,
      "step": 6
    },
    {
      "epoch": 0.11214953271028037,
      "eval_loss": 1.8779184818267822,
      "eval_runtime": 0.9893,
      "eval_samples_per_second": 91.989,
      "eval_steps_per_second": 12.13,
      "step": 6
    }
  ],
  "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": 4438954195550208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}