{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00021917808219178083,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.383561643835617e-05,
      "grad_norm": 234.98072814941406,
      "learning_rate": 1e-05,
      "loss": 92.0373,
      "step": 1
    },
    {
      "epoch": 4.383561643835617e-05,
      "eval_loss": 5.466329097747803,
      "eval_runtime": 6387.8948,
      "eval_samples_per_second": 6.015,
      "eval_steps_per_second": 3.007,
      "step": 1
    },
    {
      "epoch": 8.767123287671233e-05,
      "grad_norm": 229.7847137451172,
      "learning_rate": 2e-05,
      "loss": 91.5059,
      "step": 2
    },
    {
      "epoch": 8.767123287671233e-05,
      "eval_loss": 5.301162242889404,
      "eval_runtime": 4405.215,
      "eval_samples_per_second": 8.722,
      "eval_steps_per_second": 4.361,
      "step": 2
    },
    {
      "epoch": 0.00013150684931506848,
      "grad_norm": 179.3043212890625,
      "learning_rate": 3e-05,
      "loss": 74.5113,
      "step": 3
    },
    {
      "epoch": 0.00017534246575342467,
      "grad_norm": 249.5963134765625,
      "learning_rate": 4e-05,
      "loss": 92.2301,
      "step": 4
    },
    {
      "epoch": 0.00017534246575342467,
      "eval_loss": 4.798212051391602,
      "eval_runtime": 6858.1012,
      "eval_samples_per_second": 5.602,
      "eval_steps_per_second": 2.801,
      "step": 4
    },
    {
      "epoch": 0.00021917808219178083,
      "grad_norm": 211.14576721191406,
      "learning_rate": 5e-05,
      "loss": 73.736,
      "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": 3549156316545024.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}