{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009233610341643583,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018467220683287165,
      "grad_norm": 27.030624389648438,
      "learning_rate": 1e-05,
      "loss": 80.3012,
      "step": 1
    },
    {
      "epoch": 0.0018467220683287165,
      "eval_loss": 4.9485955238342285,
      "eval_runtime": 263.3149,
      "eval_samples_per_second": 3.464,
      "eval_steps_per_second": 1.732,
      "step": 1
    },
    {
      "epoch": 0.003693444136657433,
      "grad_norm": 26.34075164794922,
      "learning_rate": 2e-05,
      "loss": 76.2596,
      "step": 2
    },
    {
      "epoch": 0.003693444136657433,
      "eval_loss": 4.890717029571533,
      "eval_runtime": 249.3503,
      "eval_samples_per_second": 3.658,
      "eval_steps_per_second": 1.829,
      "step": 2
    },
    {
      "epoch": 0.00554016620498615,
      "grad_norm": 26.259929656982422,
      "learning_rate": 3e-05,
      "loss": 81.1513,
      "step": 3
    },
    {
      "epoch": 0.007386888273314866,
      "grad_norm": 30.05765151977539,
      "learning_rate": 4e-05,
      "loss": 83.1307,
      "step": 4
    },
    {
      "epoch": 0.007386888273314866,
      "eval_loss": 4.852306842803955,
      "eval_runtime": 216.9209,
      "eval_samples_per_second": 4.204,
      "eval_steps_per_second": 2.102,
      "step": 4
    },
    {
      "epoch": 0.009233610341643583,
      "grad_norm": 31.968595504760742,
      "learning_rate": 5e-05,
      "loss": 87.738,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3257498484080640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}