{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.1929763555526733,
      "learning_rate": 5e-05,
      "loss": 0.842,
      "step": 1
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.5904757380485535,
      "learning_rate": 0.00019948693233918952,
      "loss": 0.7602,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.35242587327957153,
      "learning_rate": 0.00018207634412072764,
      "loss": 0.5166,
      "step": 10
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.23204153776168823,
      "learning_rate": 0.00014403941515576344,
      "loss": 0.3699,
      "step": 15
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.21575891971588135,
      "learning_rate": 9.493508311612874e-05,
      "loss": 0.2784,
      "step": 20
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.27512410283088684,
      "learning_rate": 4.710359896730379e-05,
      "loss": 0.222,
      "step": 25
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3192328214645386,
      "learning_rate": 1.2565338385541792e-05,
      "loss": 0.1813,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11489653587341309,
      "learning_rate": 0.0,
      "loss": 0.1727,
      "step": 35
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.1722353994846344,
      "eval_runtime": 11.0271,
      "eval_samples_per_second": 5.623,
      "eval_steps_per_second": 0.363,
      "step": 35
    },
    {
      "epoch": 1.0,
      "step": 35,
      "total_flos": 5.19321114598441e+16,
      "train_loss": 0.3596490706716265,
      "train_runtime": 336.8523,
      "train_samples_per_second": 1.657,
      "train_steps_per_second": 0.104
    }
  ],
  "logging_steps": 5,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.19321114598441e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}