{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005775700664686885,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9252335548956284e-05,
      "eval_loss": NaN,
      "eval_runtime": 1441.3033,
      "eval_samples_per_second": 15.174,
      "eval_steps_per_second": 7.588,
      "step": 1
    },
    {
      "epoch": 5.775700664686885e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0001155140132937377,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00015401868439165027,
      "eval_loss": NaN,
      "eval_runtime": 1438.4986,
      "eval_samples_per_second": 15.204,
      "eval_steps_per_second": 7.602,
      "step": 8
    },
    {
      "epoch": 0.00017327101994060655,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002310280265874754,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00028878503323434427,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00030803736878330055,
      "eval_loss": NaN,
      "eval_runtime": 1438.5057,
      "eval_samples_per_second": 15.204,
      "eval_steps_per_second": 7.602,
      "step": 16
    },
    {
      "epoch": 0.0003465420398812131,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00040429904652808195,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0004620560531749508,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0004620560531749508,
      "eval_loss": NaN,
      "eval_runtime": 1437.8595,
      "eval_samples_per_second": 15.211,
      "eval_steps_per_second": 7.606,
      "step": 24
    },
    {
      "epoch": 0.0005198130598218196,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0005775700664686885,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3075763372752896e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}