{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022471121098276044,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011235560549138022,
      "grad_norm": 12.907438278198242,
      "learning_rate": 1e-05,
      "loss": 9.6293,
      "step": 1
    },
    {
      "epoch": 0.00011235560549138022,
      "eval_loss": 0.549656867980957,
      "eval_runtime": 678.5992,
      "eval_samples_per_second": 22.09,
      "eval_steps_per_second": 11.045,
      "step": 1
    },
    {
      "epoch": 0.00022471121098276045,
      "grad_norm": 11.824499130249023,
      "learning_rate": 2e-05,
      "loss": 9.7717,
      "step": 2
    },
    {
      "epoch": 0.00033706681647414064,
      "grad_norm": 11.416561126708984,
      "learning_rate": 3e-05,
      "loss": 10.3236,
      "step": 3
    },
    {
      "epoch": 0.0004494224219655209,
      "grad_norm": 10.089188575744629,
      "learning_rate": 4e-05,
      "loss": 8.6999,
      "step": 4
    },
    {
      "epoch": 0.0005617780274569011,
      "grad_norm": 11.472464561462402,
      "learning_rate": 5e-05,
      "loss": 9.7988,
      "step": 5
    },
    {
      "epoch": 0.0005617780274569011,
      "eval_loss": 0.5387327671051025,
      "eval_runtime": 593.7409,
      "eval_samples_per_second": 25.247,
      "eval_steps_per_second": 12.623,
      "step": 5
    },
    {
      "epoch": 0.0006741336329482813,
      "grad_norm": 9.719332695007324,
      "learning_rate": 6e-05,
      "loss": 8.2278,
      "step": 6
    },
    {
      "epoch": 0.0007864892384396615,
      "grad_norm": 11.081488609313965,
      "learning_rate": 7e-05,
      "loss": 8.9019,
      "step": 7
    },
    {
      "epoch": 0.0008988448439310418,
      "grad_norm": 9.865341186523438,
      "learning_rate": 8e-05,
      "loss": 8.5421,
      "step": 8
    },
    {
      "epoch": 0.0010112004494224219,
      "grad_norm": 8.71439266204834,
      "learning_rate": 9e-05,
      "loss": 8.4593,
      "step": 9
    },
    {
      "epoch": 0.0011235560549138022,
      "grad_norm": 9.529187202453613,
      "learning_rate": 0.0001,
      "loss": 8.2528,
      "step": 10
    },
    {
      "epoch": 0.0011235560549138022,
      "eval_loss": 0.5102785229682922,
      "eval_runtime": 725.2331,
      "eval_samples_per_second": 20.669,
      "eval_steps_per_second": 10.335,
      "step": 10
    },
    {
      "epoch": 0.0012359116604051825,
      "grad_norm": 9.459853172302246,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.5236,
      "step": 11
    },
    {
      "epoch": 0.0013482672658965626,
      "grad_norm": 9.357318878173828,
      "learning_rate": 9.045084971874738e-05,
      "loss": 8.5885,
      "step": 12
    },
    {
      "epoch": 0.0014606228713879429,
      "grad_norm": 8.91463565826416,
      "learning_rate": 7.938926261462366e-05,
      "loss": 7.9383,
      "step": 13
    },
    {
      "epoch": 0.001572978476879323,
      "grad_norm": 8.66787052154541,
      "learning_rate": 6.545084971874738e-05,
      "loss": 7.472,
      "step": 14
    },
    {
      "epoch": 0.0016853340823707033,
      "grad_norm": 8.063846588134766,
      "learning_rate": 5e-05,
      "loss": 7.9145,
      "step": 15
    },
    {
      "epoch": 0.0016853340823707033,
      "eval_loss": 0.4864272177219391,
      "eval_runtime": 593.7636,
      "eval_samples_per_second": 25.246,
      "eval_steps_per_second": 12.623,
      "step": 15
    },
    {
      "epoch": 0.0017976896878620836,
      "grad_norm": 9.519815444946289,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 8.389,
      "step": 16
    },
    {
      "epoch": 0.0019100452933534637,
      "grad_norm": 9.816612243652344,
      "learning_rate": 2.061073738537635e-05,
      "loss": 8.4567,
      "step": 17
    },
    {
      "epoch": 0.0020224008988448438,
      "grad_norm": 7.924627780914307,
      "learning_rate": 9.549150281252633e-06,
      "loss": 7.5395,
      "step": 18
    },
    {
      "epoch": 0.002134756504336224,
      "grad_norm": 9.166494369506836,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 8.6007,
      "step": 19
    },
    {
      "epoch": 0.0022471121098276044,
      "grad_norm": 9.202842712402344,
      "learning_rate": 0.0,
      "loss": 7.9256,
      "step": 20
    },
    {
      "epoch": 0.0022471121098276044,
      "eval_loss": 0.4830845594406128,
      "eval_runtime": 604.6011,
      "eval_samples_per_second": 24.793,
      "eval_steps_per_second": 12.397,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5720458653466624e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}