{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024891101431238332,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002489110143123833,
      "grad_norm": 2.9824841022491455,
      "learning_rate": 2e-05,
      "loss": 8.6277,
      "step": 1
    },
    {
      "epoch": 0.002489110143123833,
      "eval_loss": 2.0778281688690186,
      "eval_runtime": 3.1837,
      "eval_samples_per_second": 53.397,
      "eval_steps_per_second": 26.698,
      "step": 1
    },
    {
      "epoch": 0.004978220286247666,
      "grad_norm": 3.3361434936523438,
      "learning_rate": 4e-05,
      "loss": 8.487,
      "step": 2
    },
    {
      "epoch": 0.0074673304293715,
      "grad_norm": 2.8599517345428467,
      "learning_rate": 6e-05,
      "loss": 8.6255,
      "step": 3
    },
    {
      "epoch": 0.0074673304293715,
      "eval_loss": 2.0739619731903076,
      "eval_runtime": 2.1151,
      "eval_samples_per_second": 80.376,
      "eval_steps_per_second": 40.188,
      "step": 3
    },
    {
      "epoch": 0.009956440572495333,
      "grad_norm": 2.838259220123291,
      "learning_rate": 8e-05,
      "loss": 8.2522,
      "step": 4
    },
    {
      "epoch": 0.012445550715619166,
      "grad_norm": 2.586542844772339,
      "learning_rate": 0.0001,
      "loss": 8.4279,
      "step": 5
    },
    {
      "epoch": 0.014934660858743,
      "grad_norm": 2.7397217750549316,
      "learning_rate": 0.00012,
      "loss": 8.4247,
      "step": 6
    },
    {
      "epoch": 0.014934660858743,
      "eval_loss": 2.0526249408721924,
      "eval_runtime": 2.216,
      "eval_samples_per_second": 76.715,
      "eval_steps_per_second": 38.358,
      "step": 6
    },
    {
      "epoch": 0.017423771001866834,
      "grad_norm": 2.8856303691864014,
      "learning_rate": 0.00014,
      "loss": 8.5952,
      "step": 7
    },
    {
      "epoch": 0.019912881144990666,
      "grad_norm": 2.9074909687042236,
      "learning_rate": 0.00016,
      "loss": 8.666,
      "step": 8
    },
    {
      "epoch": 0.0224019912881145,
      "grad_norm": 2.4418694972991943,
      "learning_rate": 0.00018,
      "loss": 8.263,
      "step": 9
    },
    {
      "epoch": 0.0224019912881145,
      "eval_loss": 2.0184924602508545,
      "eval_runtime": 2.165,
      "eval_samples_per_second": 78.521,
      "eval_steps_per_second": 39.26,
      "step": 9
    },
    {
      "epoch": 0.024891101431238332,
      "grad_norm": 2.5304298400878906,
      "learning_rate": 0.0002,
      "loss": 8.087,
      "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": 24944676175872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}