{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03269069572506287,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008382229673093043,
      "eval_loss": 10.376425743103027,
      "eval_runtime": 6.0687,
      "eval_samples_per_second": 82.885,
      "eval_steps_per_second": 41.525,
      "step": 1
    },
    {
      "epoch": 0.004191114836546521,
      "grad_norm": 3.966305732727051,
      "learning_rate": 5e-05,
      "loss": 10.3163,
      "step": 5
    },
    {
      "epoch": 0.008382229673093043,
      "grad_norm": 3.3468010425567627,
      "learning_rate": 0.0001,
      "loss": 9.9714,
      "step": 10
    },
    {
      "epoch": 0.008382229673093043,
      "eval_loss": 10.273557662963867,
      "eval_runtime": 6.0619,
      "eval_samples_per_second": 82.978,
      "eval_steps_per_second": 41.571,
      "step": 10
    },
    {
      "epoch": 0.012573344509639563,
      "grad_norm": 4.065016269683838,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.2311,
      "step": 15
    },
    {
      "epoch": 0.016764459346186086,
      "grad_norm": 3.4927356243133545,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.0962,
      "step": 20
    },
    {
      "epoch": 0.016764459346186086,
      "eval_loss": 9.986302375793457,
      "eval_runtime": 6.1887,
      "eval_samples_per_second": 81.278,
      "eval_steps_per_second": 40.72,
      "step": 20
    },
    {
      "epoch": 0.020955574182732608,
      "grad_norm": 3.271510601043701,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.1087,
      "step": 25
    },
    {
      "epoch": 0.025146689019279127,
      "grad_norm": 4.116062641143799,
      "learning_rate": 5e-05,
      "loss": 9.708,
      "step": 30
    },
    {
      "epoch": 0.025146689019279127,
      "eval_loss": 9.775476455688477,
      "eval_runtime": 6.1738,
      "eval_samples_per_second": 81.473,
      "eval_steps_per_second": 40.818,
      "step": 30
    },
    {
      "epoch": 0.02933780385582565,
      "grad_norm": 3.193754196166992,
      "learning_rate": 3.086582838174551e-05,
      "loss": 9.8981,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4294084657152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}