{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0039670732916790635,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00039670732916790636,
      "grad_norm": 21.452529907226562,
      "learning_rate": 2e-05,
      "loss": 16.5819,
      "step": 1
    },
    {
      "epoch": 0.00039670732916790636,
      "eval_loss": 3.460477352142334,
      "eval_runtime": 7.6942,
      "eval_samples_per_second": 138.026,
      "eval_steps_per_second": 69.013,
      "step": 1
    },
    {
      "epoch": 0.0007934146583358127,
      "grad_norm": 22.006479263305664,
      "learning_rate": 4e-05,
      "loss": 16.1027,
      "step": 2
    },
    {
      "epoch": 0.0011901219875037191,
      "grad_norm": 23.007572174072266,
      "learning_rate": 6e-05,
      "loss": 14.9943,
      "step": 3
    },
    {
      "epoch": 0.0011901219875037191,
      "eval_loss": 3.436659812927246,
      "eval_runtime": 6.9478,
      "eval_samples_per_second": 152.853,
      "eval_steps_per_second": 76.427,
      "step": 3
    },
    {
      "epoch": 0.0015868293166716254,
      "grad_norm": 23.50531578063965,
      "learning_rate": 8e-05,
      "loss": 15.688,
      "step": 4
    },
    {
      "epoch": 0.0019835366458395317,
      "grad_norm": 19.6435489654541,
      "learning_rate": 0.0001,
      "loss": 13.3793,
      "step": 5
    },
    {
      "epoch": 0.0023802439750074383,
      "grad_norm": 16.59267807006836,
      "learning_rate": 0.00012,
      "loss": 13.8399,
      "step": 6
    },
    {
      "epoch": 0.0023802439750074383,
      "eval_loss": 3.2900075912475586,
      "eval_runtime": 7.0966,
      "eval_samples_per_second": 149.649,
      "eval_steps_per_second": 74.825,
      "step": 6
    },
    {
      "epoch": 0.002776951304175345,
      "grad_norm": 16.987205505371094,
      "learning_rate": 0.00014,
      "loss": 14.3672,
      "step": 7
    },
    {
      "epoch": 0.003173658633343251,
      "grad_norm": 15.192695617675781,
      "learning_rate": 0.00016,
      "loss": 11.0621,
      "step": 8
    },
    {
      "epoch": 0.0035703659625111574,
      "grad_norm": 21.766023635864258,
      "learning_rate": 0.00018,
      "loss": 12.1704,
      "step": 9
    },
    {
      "epoch": 0.0035703659625111574,
      "eval_loss": 3.023158550262451,
      "eval_runtime": 6.9939,
      "eval_samples_per_second": 151.847,
      "eval_steps_per_second": 75.924,
      "step": 9
    },
    {
      "epoch": 0.0039670732916790635,
      "grad_norm": 16.854900360107422,
      "learning_rate": 0.0002,
      "loss": 13.1797,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 27067627339776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}