{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.049672300793377026,
  "eval_steps": 9,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013797861331493618,
      "eval_loss": 0.7372766733169556,
      "eval_runtime": 168.7844,
      "eval_samples_per_second": 7.234,
      "eval_steps_per_second": 0.906,
      "step": 1
    },
    {
      "epoch": 0.004139358399448086,
      "grad_norm": 33.24546432495117,
      "learning_rate": 1.5e-05,
      "loss": 3.0101,
      "step": 3
    },
    {
      "epoch": 0.008278716798896172,
      "grad_norm": 17.34926986694336,
      "learning_rate": 3e-05,
      "loss": 2.2218,
      "step": 6
    },
    {
      "epoch": 0.012418075198344257,
      "grad_norm": 5.28987979888916,
      "learning_rate": 4.5e-05,
      "loss": 1.4942,
      "step": 9
    },
    {
      "epoch": 0.012418075198344257,
      "eval_loss": 0.26399311423301697,
      "eval_runtime": 170.9677,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 0.895,
      "step": 9
    },
    {
      "epoch": 0.016557433597792343,
      "grad_norm": 4.505770683288574,
      "learning_rate": 4.993910125649561e-05,
      "loss": 1.0678,
      "step": 12
    },
    {
      "epoch": 0.020696791997240428,
      "grad_norm": 3.744687795639038,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.7375,
      "step": 15
    },
    {
      "epoch": 0.024836150396688513,
      "grad_norm": 3.299644708633423,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 0.9198,
      "step": 18
    },
    {
      "epoch": 0.024836150396688513,
      "eval_loss": 0.21940629184246063,
      "eval_runtime": 170.9547,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 0.895,
      "step": 18
    },
    {
      "epoch": 0.028975508796136598,
      "grad_norm": 2.6757843494415283,
      "learning_rate": 4.817959636416969e-05,
      "loss": 0.8649,
      "step": 21
    },
    {
      "epoch": 0.03311486719558469,
      "grad_norm": 3.3077943325042725,
      "learning_rate": 4.707368982147318e-05,
      "loss": 0.8514,
      "step": 24
    },
    {
      "epoch": 0.03725422559503277,
      "grad_norm": 3.4696767330169678,
      "learning_rate": 4.572593931387604e-05,
      "loss": 0.7777,
      "step": 27
    },
    {
      "epoch": 0.03725422559503277,
      "eval_loss": 0.20136968791484833,
      "eval_runtime": 171.0507,
      "eval_samples_per_second": 7.138,
      "eval_steps_per_second": 0.894,
      "step": 27
    },
    {
      "epoch": 0.041393583994480856,
      "grad_norm": 2.9004974365234375,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.664,
      "step": 30
    },
    {
      "epoch": 0.04553294239392894,
      "grad_norm": 2.8733339309692383,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 0.5927,
      "step": 33
    },
    {
      "epoch": 0.049672300793377026,
      "grad_norm": 3.473083019256592,
      "learning_rate": 4.039153688314145e-05,
      "loss": 0.6759,
      "step": 36
    },
    {
      "epoch": 0.049672300793377026,
      "eval_loss": 0.19248369336128235,
      "eval_runtime": 170.9492,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 0.895,
      "step": 36
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0125064781011354e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}