{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025236593059936908,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008412197686645636,
      "eval_loss": 2.659315586090088,
      "eval_runtime": 16.9175,
      "eval_samples_per_second": 29.614,
      "eval_steps_per_second": 14.837,
      "step": 1
    },
    {
      "epoch": 0.002523659305993691,
      "grad_norm": 4.930280685424805,
      "learning_rate": 6e-05,
      "loss": 9.9892,
      "step": 3
    },
    {
      "epoch": 0.005047318611987382,
      "grad_norm": 5.0327959060668945,
      "learning_rate": 0.00012,
      "loss": 9.9225,
      "step": 6
    },
    {
      "epoch": 0.0067297581493165086,
      "eval_loss": 2.0016512870788574,
      "eval_runtime": 16.5545,
      "eval_samples_per_second": 30.264,
      "eval_steps_per_second": 15.162,
      "step": 8
    },
    {
      "epoch": 0.007570977917981073,
      "grad_norm": 5.421952247619629,
      "learning_rate": 0.00018,
      "loss": 8.6682,
      "step": 9
    },
    {
      "epoch": 0.010094637223974764,
      "grad_norm": 6.393758296966553,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.8927,
      "step": 12
    },
    {
      "epoch": 0.012618296529968454,
      "grad_norm": 7.1155009269714355,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.266,
      "step": 15
    },
    {
      "epoch": 0.013459516298633017,
      "eval_loss": 1.5018607378005981,
      "eval_runtime": 16.5596,
      "eval_samples_per_second": 30.254,
      "eval_steps_per_second": 15.157,
      "step": 16
    },
    {
      "epoch": 0.015141955835962145,
      "grad_norm": 5.386624813079834,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.5651,
      "step": 18
    },
    {
      "epoch": 0.017665615141955835,
      "grad_norm": 5.273889541625977,
      "learning_rate": 8.435655349597689e-05,
      "loss": 5.653,
      "step": 21
    },
    {
      "epoch": 0.02018927444794953,
      "grad_norm": 5.292482852935791,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.9318,
      "step": 24
    },
    {
      "epoch": 0.02018927444794953,
      "eval_loss": 1.4570142030715942,
      "eval_runtime": 16.5884,
      "eval_samples_per_second": 30.202,
      "eval_steps_per_second": 15.131,
      "step": 24
    },
    {
      "epoch": 0.022712933753943218,
      "grad_norm": 4.244992256164551,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 6.0213,
      "step": 27
    },
    {
      "epoch": 0.025236593059936908,
      "grad_norm": 4.878582954406738,
      "learning_rate": 0.0,
      "loss": 6.3151,
      "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": 1800711343964160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}