{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03325020781379884,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011083402604599613,
      "eval_loss": 0.7769315242767334,
      "eval_runtime": 24.7753,
      "eval_samples_per_second": 15.338,
      "eval_steps_per_second": 7.669,
      "step": 1
    },
    {
      "epoch": 0.0033250207813798837,
      "grad_norm": 0.5615259408950806,
      "learning_rate": 6e-05,
      "loss": 0.8129,
      "step": 3
    },
    {
      "epoch": 0.006650041562759767,
      "grad_norm": 0.5169650912284851,
      "learning_rate": 0.00012,
      "loss": 0.7443,
      "step": 6
    },
    {
      "epoch": 0.00886672208367969,
      "eval_loss": 0.6080591082572937,
      "eval_runtime": 23.2808,
      "eval_samples_per_second": 16.322,
      "eval_steps_per_second": 8.161,
      "step": 8
    },
    {
      "epoch": 0.00997506234413965,
      "grad_norm": 0.47779959440231323,
      "learning_rate": 0.00018,
      "loss": 0.6185,
      "step": 9
    },
    {
      "epoch": 0.013300083125519535,
      "grad_norm": 0.59880530834198,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.5892,
      "step": 12
    },
    {
      "epoch": 0.01662510390689942,
      "grad_norm": 0.8566116690635681,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.5471,
      "step": 15
    },
    {
      "epoch": 0.01773344416735938,
      "eval_loss": 0.5450372099876404,
      "eval_runtime": 23.4062,
      "eval_samples_per_second": 16.235,
      "eval_steps_per_second": 8.117,
      "step": 16
    },
    {
      "epoch": 0.0199501246882793,
      "grad_norm": 0.35130101442337036,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5379,
      "step": 18
    },
    {
      "epoch": 0.023275145469659187,
      "grad_norm": 0.43810561299324036,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.496,
      "step": 21
    },
    {
      "epoch": 0.02660016625103907,
      "grad_norm": 0.3642444908618927,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.5328,
      "step": 24
    },
    {
      "epoch": 0.02660016625103907,
      "eval_loss": 0.5327214002609253,
      "eval_runtime": 23.4926,
      "eval_samples_per_second": 16.175,
      "eval_steps_per_second": 8.088,
      "step": 24
    },
    {
      "epoch": 0.029925187032418952,
      "grad_norm": 0.30899062752723694,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.5391,
      "step": 27
    },
    {
      "epoch": 0.03325020781379884,
      "grad_norm": 0.3484113812446594,
      "learning_rate": 0.0,
      "loss": 0.4985,
      "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": 1.1591988805632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}