{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03508771929824561,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 2.8504276275634766,
      "learning_rate": 1e-05,
      "loss": 17.487,
      "step": 1
    },
    {
      "epoch": 0.007017543859649123,
      "eval_loss": 1.1553192138671875,
      "eval_runtime": 95.7389,
      "eval_samples_per_second": 2.507,
      "eval_steps_per_second": 1.253,
      "step": 1
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 3.5421972274780273,
      "learning_rate": 2e-05,
      "loss": 19.4668,
      "step": 2
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 3.372083902359009,
      "learning_rate": 3e-05,
      "loss": 17.2781,
      "step": 3
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 2.8809428215026855,
      "learning_rate": 4e-05,
      "loss": 16.4683,
      "step": 4
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 3.473324775695801,
      "learning_rate": 5e-05,
      "loss": 19.2854,
      "step": 5
    },
    {
      "epoch": 0.03508771929824561,
      "eval_loss": 1.127090573310852,
      "eval_runtime": 8.9521,
      "eval_samples_per_second": 26.809,
      "eval_steps_per_second": 13.405,
      "step": 5
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5374872498733056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}