{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0041928721174003,
  "eval_steps": 500,
  "global_step": 239,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 0.023019764572381973,
      "learning_rate": 0.000233974358974359,
      "loss": 11.9301,
      "step": 20
    },
    {
      "epoch": 0.33542976939203356,
      "grad_norm": 0.05555475503206253,
      "learning_rate": 0.0002126068376068376,
      "loss": 11.9266,
      "step": 40
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 0.04104316607117653,
      "learning_rate": 0.00019123931623931623,
      "loss": 11.9229,
      "step": 60
    },
    {
      "epoch": 0.6708595387840671,
      "grad_norm": 0.0416753776371479,
      "learning_rate": 0.0001698717948717949,
      "loss": 11.9211,
      "step": 80
    },
    {
      "epoch": 0.8385744234800838,
      "grad_norm": 0.04827936738729477,
      "learning_rate": 0.0001485042735042735,
      "loss": 11.9211,
      "step": 100
    },
    {
      "epoch": 0.9979035639412998,
      "eval_loss": 11.919425964355469,
      "eval_runtime": 0.4166,
      "eval_samples_per_second": 242.468,
      "eval_steps_per_second": 62.417,
      "step": 119
    },
    {
      "epoch": 1.0062893081761006,
      "grad_norm": 0.11942638456821442,
      "learning_rate": 0.00012713675213675213,
      "loss": 12.3702,
      "step": 120
    },
    {
      "epoch": 1.1740041928721174,
      "grad_norm": 0.059040140360593796,
      "learning_rate": 0.00010576923076923077,
      "loss": 11.8371,
      "step": 140
    },
    {
      "epoch": 1.3417190775681342,
      "grad_norm": 0.06853944063186646,
      "learning_rate": 8.440170940170941e-05,
      "loss": 12.0029,
      "step": 160
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.030212825164198875,
      "learning_rate": 6.303418803418804e-05,
      "loss": 11.9184,
      "step": 180
    },
    {
      "epoch": 1.6771488469601676,
      "grad_norm": 0.034588687121868134,
      "learning_rate": 4.1666666666666665e-05,
      "loss": 11.9407,
      "step": 200
    },
    {
      "epoch": 1.8448637316561844,
      "grad_norm": 0.0361829474568367,
      "learning_rate": 2.02991452991453e-05,
      "loss": 11.8561,
      "step": 220
    },
    {
      "epoch": 1.9958071278825997,
      "eval_loss": 11.917513847351074,
      "eval_runtime": 0.4181,
      "eval_samples_per_second": 241.592,
      "eval_steps_per_second": 62.192,
      "step": 238
    },
    {
      "epoch": 2.0041928721174003,
      "eval_loss": 11.917852401733398,
      "eval_runtime": 0.4182,
      "eval_samples_per_second": 241.517,
      "eval_steps_per_second": 62.173,
      "step": 239
    }
  ],
  "logging_steps": 20,
  "max_steps": 239,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 269012385792.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}