{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015829046299960427,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015829046299960427,
      "grad_norm": 1.2222102880477905,
      "learning_rate": 2e-05,
      "loss": 10.0117,
      "step": 1
    },
    {
      "epoch": 0.0015829046299960427,
      "eval_loss": 2.706019878387451,
      "eval_runtime": 4.6987,
      "eval_samples_per_second": 56.825,
      "eval_steps_per_second": 28.519,
      "step": 1
    },
    {
      "epoch": 0.0031658092599920855,
      "grad_norm": 1.0556036233901978,
      "learning_rate": 4e-05,
      "loss": 9.2419,
      "step": 2
    },
    {
      "epoch": 0.004748713889988128,
      "grad_norm": 1.3151988983154297,
      "learning_rate": 6e-05,
      "loss": 10.9533,
      "step": 3
    },
    {
      "epoch": 0.004748713889988128,
      "eval_loss": 2.705254554748535,
      "eval_runtime": 4.6989,
      "eval_samples_per_second": 56.821,
      "eval_steps_per_second": 28.517,
      "step": 3
    },
    {
      "epoch": 0.006331618519984171,
      "grad_norm": 1.1604503393173218,
      "learning_rate": 8e-05,
      "loss": 10.0903,
      "step": 4
    },
    {
      "epoch": 0.007914523149980214,
      "grad_norm": 1.1817126274108887,
      "learning_rate": 0.0001,
      "loss": 11.4336,
      "step": 5
    },
    {
      "epoch": 0.009497427779976256,
      "grad_norm": 1.3432368040084839,
      "learning_rate": 0.00012,
      "loss": 10.6907,
      "step": 6
    },
    {
      "epoch": 0.009497427779976256,
      "eval_loss": 2.689335584640503,
      "eval_runtime": 4.7614,
      "eval_samples_per_second": 56.076,
      "eval_steps_per_second": 28.143,
      "step": 6
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 1.7751564979553223,
      "learning_rate": 0.00014,
      "loss": 10.5266,
      "step": 7
    },
    {
      "epoch": 0.012663237039968342,
      "grad_norm": 1.837289571762085,
      "learning_rate": 0.00016,
      "loss": 10.3167,
      "step": 8
    },
    {
      "epoch": 0.014246141669964385,
      "grad_norm": 1.6653811931610107,
      "learning_rate": 0.00018,
      "loss": 9.206,
      "step": 9
    },
    {
      "epoch": 0.014246141669964385,
      "eval_loss": 2.5799317359924316,
      "eval_runtime": 4.7712,
      "eval_samples_per_second": 55.961,
      "eval_steps_per_second": 28.085,
      "step": 9
    },
    {
      "epoch": 0.015829046299960427,
      "grad_norm": 2.1507608890533447,
      "learning_rate": 0.0002,
      "loss": 10.3633,
      "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": 298729403842560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}