{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18570102135561745,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003714020427112349,
      "eval_loss": 2.625425100326538,
      "eval_runtime": 11.9889,
      "eval_samples_per_second": 9.509,
      "eval_steps_per_second": 4.754,
      "step": 1
    },
    {
      "epoch": 0.018570102135561744,
      "grad_norm": 0.3816036283969879,
      "learning_rate": 5e-05,
      "loss": 2.7497,
      "step": 5
    },
    {
      "epoch": 0.03714020427112349,
      "grad_norm": 0.574531614780426,
      "learning_rate": 0.0001,
      "loss": 2.6056,
      "step": 10
    },
    {
      "epoch": 0.03714020427112349,
      "eval_loss": 2.5287303924560547,
      "eval_runtime": 12.1391,
      "eval_samples_per_second": 9.391,
      "eval_steps_per_second": 4.696,
      "step": 10
    },
    {
      "epoch": 0.055710306406685235,
      "grad_norm": 0.32838571071624756,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.487,
      "step": 15
    },
    {
      "epoch": 0.07428040854224698,
      "grad_norm": 0.2884520888328552,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.434,
      "step": 20
    },
    {
      "epoch": 0.07428040854224698,
      "eval_loss": 2.443124294281006,
      "eval_runtime": 12.2351,
      "eval_samples_per_second": 9.317,
      "eval_steps_per_second": 4.659,
      "step": 20
    },
    {
      "epoch": 0.09285051067780872,
      "grad_norm": 0.27789685130119324,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.511,
      "step": 25
    },
    {
      "epoch": 0.11142061281337047,
      "grad_norm": 0.2861422896385193,
      "learning_rate": 5e-05,
      "loss": 2.4991,
      "step": 30
    },
    {
      "epoch": 0.11142061281337047,
      "eval_loss": 2.4089643955230713,
      "eval_runtime": 12.3034,
      "eval_samples_per_second": 9.266,
      "eval_steps_per_second": 4.633,
      "step": 30
    },
    {
      "epoch": 0.12999071494893222,
      "grad_norm": 0.26488766074180603,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.4306,
      "step": 35
    },
    {
      "epoch": 0.14856081708449395,
      "grad_norm": 0.2455853372812271,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.4061,
      "step": 40
    },
    {
      "epoch": 0.14856081708449395,
      "eval_loss": 2.3940765857696533,
      "eval_runtime": 12.3681,
      "eval_samples_per_second": 9.217,
      "eval_steps_per_second": 4.609,
      "step": 40
    },
    {
      "epoch": 0.1671309192200557,
      "grad_norm": 0.2584855258464813,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.4314,
      "step": 45
    },
    {
      "epoch": 0.18570102135561745,
      "grad_norm": 0.24273546040058136,
      "learning_rate": 0.0,
      "loss": 2.3304,
      "step": 50
    },
    {
      "epoch": 0.18570102135561745,
      "eval_loss": 2.3918755054473877,
      "eval_runtime": 12.2602,
      "eval_samples_per_second": 9.298,
      "eval_steps_per_second": 4.649,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6246613030731776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}