{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01088139281828074,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001088139281828074,
      "grad_norm": 0.1605968475341797,
      "learning_rate": 2e-05,
      "loss": 0.2178,
      "step": 1
    },
    {
      "epoch": 0.001088139281828074,
      "eval_loss": 0.2808469533920288,
      "eval_runtime": 20.8433,
      "eval_samples_per_second": 18.567,
      "eval_steps_per_second": 9.308,
      "step": 1
    },
    {
      "epoch": 0.002176278563656148,
      "grad_norm": 0.1751880645751953,
      "learning_rate": 4e-05,
      "loss": 0.2729,
      "step": 2
    },
    {
      "epoch": 0.003264417845484222,
      "grad_norm": 0.14018131792545319,
      "learning_rate": 6e-05,
      "loss": 0.2357,
      "step": 3
    },
    {
      "epoch": 0.003264417845484222,
      "eval_loss": 0.27992600202560425,
      "eval_runtime": 20.9269,
      "eval_samples_per_second": 18.493,
      "eval_steps_per_second": 9.27,
      "step": 3
    },
    {
      "epoch": 0.004352557127312296,
      "grad_norm": 0.17276977002620697,
      "learning_rate": 8e-05,
      "loss": 0.2035,
      "step": 4
    },
    {
      "epoch": 0.00544069640914037,
      "grad_norm": 0.14943687617778778,
      "learning_rate": 0.0001,
      "loss": 0.2743,
      "step": 5
    },
    {
      "epoch": 0.006528835690968444,
      "grad_norm": 0.2077263444662094,
      "learning_rate": 0.00012,
      "loss": 0.2739,
      "step": 6
    },
    {
      "epoch": 0.006528835690968444,
      "eval_loss": 0.2667318284511566,
      "eval_runtime": 20.8615,
      "eval_samples_per_second": 18.551,
      "eval_steps_per_second": 9.299,
      "step": 6
    },
    {
      "epoch": 0.007616974972796518,
      "grad_norm": 0.21373873949050903,
      "learning_rate": 0.00014,
      "loss": 0.233,
      "step": 7
    },
    {
      "epoch": 0.008705114254624592,
      "grad_norm": 0.19470500946044922,
      "learning_rate": 0.00016,
      "loss": 0.2478,
      "step": 8
    },
    {
      "epoch": 0.009793253536452665,
      "grad_norm": 0.16962379217147827,
      "learning_rate": 0.00018,
      "loss": 0.2129,
      "step": 9
    },
    {
      "epoch": 0.009793253536452665,
      "eval_loss": 0.23116014897823334,
      "eval_runtime": 20.8869,
      "eval_samples_per_second": 18.528,
      "eval_steps_per_second": 9.288,
      "step": 9
    },
    {
      "epoch": 0.01088139281828074,
      "grad_norm": 0.17300285398960114,
      "learning_rate": 0.0002,
      "loss": 0.1476,
      "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": 1558092463472640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}