{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9928057553956835,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014388489208633094,
      "grad_norm": 3.479528102297347e+19,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 2.7998,
      "step": 1
    },
    {
      "epoch": 0.07194244604316546,
      "grad_norm": 24.423364424826083,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 2.7188,
      "step": 5
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 13.819600450408876,
      "learning_rate": 1.9884683243281117e-05,
      "loss": 2.3561,
      "step": 10
    },
    {
      "epoch": 0.2158273381294964,
      "grad_norm": 5.30012638056683,
      "learning_rate": 1.918957811620231e-05,
      "loss": 2.1327,
      "step": 15
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 5.03426919288419,
      "learning_rate": 1.7907757369376984e-05,
      "loss": 1.9799,
      "step": 20
    },
    {
      "epoch": 0.3597122302158273,
      "grad_norm": 3.9429760994685155,
      "learning_rate": 1.612105982547663e-05,
      "loss": 1.8584,
      "step": 25
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 2.0220604553339685,
      "learning_rate": 1.3943558551133186e-05,
      "loss": 1.7667,
      "step": 30
    },
    {
      "epoch": 0.5035971223021583,
      "grad_norm": 3.1848301524617004,
      "learning_rate": 1.1514277775045768e-05,
      "loss": 1.7095,
      "step": 35
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 2.3172187772965414,
      "learning_rate": 8.98831678012568e-06,
      "loss": 1.6791,
      "step": 40
    },
    {
      "epoch": 0.6474820143884892,
      "grad_norm": 2.045331863386451,
      "learning_rate": 6.526947471551799e-06,
      "loss": 1.6488,
      "step": 45
    },
    {
      "epoch": 0.7194244604316546,
      "grad_norm": 1.7461420545505917,
      "learning_rate": 4.287317849052075e-06,
      "loss": 1.6196,
      "step": 50
    },
    {
      "epoch": 0.7913669064748201,
      "grad_norm": 1.672072301802694,
      "learning_rate": 2.4124187730720916e-06,
      "loss": 1.6049,
      "step": 55
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 1.5544447809209505,
      "learning_rate": 1.0219546042925842e-06,
      "loss": 1.605,
      "step": 60
    },
    {
      "epoch": 0.935251798561151,
      "grad_norm": 1.5327804816345267,
      "learning_rate": 2.0470058747505516e-07,
      "loss": 1.5919,
      "step": 65
    },
    {
      "epoch": 0.9928057553956835,
      "eval_loss": 1.5895432233810425,
      "eval_runtime": 21.544,
      "eval_samples_per_second": 44.328,
      "eval_steps_per_second": 0.696,
      "step": 69
    },
    {
      "epoch": 0.9928057553956835,
      "step": 69,
      "total_flos": 57579405312000.0,
      "train_loss": 1.8519639035929805,
      "train_runtime": 1562.6462,
      "train_samples_per_second": 11.37,
      "train_steps_per_second": 0.044
    }
  ],
  "logging_steps": 5,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 57579405312000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}