{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0033685156074556477,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011228385358185493,
      "eval_loss": 11.5,
      "eval_runtime": 24.0004,
      "eval_samples_per_second": 156.247,
      "eval_steps_per_second": 78.124,
      "step": 1
    },
    {
      "epoch": 0.00033685156074556477,
      "grad_norm": 1.953316132130567e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0005614192679092747,
      "eval_loss": 11.5,
      "eval_runtime": 24.2609,
      "eval_samples_per_second": 154.57,
      "eval_steps_per_second": 77.285,
      "step": 5
    },
    {
      "epoch": 0.0006737031214911295,
      "grad_norm": 1.4230739907361567e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0010105546822366943,
      "grad_norm": 1.824189348553773e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0011228385358185494,
      "eval_loss": 11.5,
      "eval_runtime": 24.2682,
      "eval_samples_per_second": 154.523,
      "eval_steps_per_second": 77.262,
      "step": 10
    },
    {
      "epoch": 0.001347406242982259,
      "grad_norm": 1.678512489888817e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0016842578037278239,
      "grad_norm": 1.1590057511057239e-05,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0016842578037278239,
      "eval_loss": 11.5,
      "eval_runtime": 24.371,
      "eval_samples_per_second": 153.871,
      "eval_steps_per_second": 76.936,
      "step": 15
    },
    {
      "epoch": 0.0020211093644733886,
      "grad_norm": 1.3804982700094115e-05,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0022456770716370988,
      "eval_loss": 11.5,
      "eval_runtime": 24.0385,
      "eval_samples_per_second": 156.0,
      "eval_steps_per_second": 78.0,
      "step": 20
    },
    {
      "epoch": 0.0023579609252189536,
      "grad_norm": 1.6708543626009487e-05,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 1.7559348634677008e-05,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.002807096339546373,
      "eval_loss": 11.5,
      "eval_runtime": 24.4035,
      "eval_samples_per_second": 153.667,
      "eval_steps_per_second": 76.833,
      "step": 25
    },
    {
      "epoch": 0.003031664046710083,
      "grad_norm": 2.3784989025443792e-05,
      "learning_rate": 5.449673790581611e-06,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.0033685156074556477,
      "grad_norm": 1.8421775166643783e-05,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.0033685156074556477,
      "eval_loss": 11.5,
      "eval_runtime": 24.2838,
      "eval_samples_per_second": 154.424,
      "eval_steps_per_second": 77.212,
      "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": 1206856679424.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}