{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.032180209171359615,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006436041834271922,
      "grad_norm": 20.479650497436523,
      "learning_rate": 1e-05,
      "loss": 12.6767,
      "step": 1
    },
    {
      "epoch": 0.006436041834271922,
      "eval_loss": 12.668194770812988,
      "eval_runtime": 18.4992,
      "eval_samples_per_second": 14.163,
      "eval_steps_per_second": 7.081,
      "step": 1
    },
    {
      "epoch": 0.012872083668543845,
      "grad_norm": 21.03908920288086,
      "learning_rate": 2e-05,
      "loss": 12.6971,
      "step": 2
    },
    {
      "epoch": 0.012872083668543845,
      "eval_loss": 12.647562026977539,
      "eval_runtime": 1.0077,
      "eval_samples_per_second": 259.993,
      "eval_steps_per_second": 129.996,
      "step": 2
    },
    {
      "epoch": 0.019308125502815767,
      "grad_norm": 21.503442764282227,
      "learning_rate": 3e-05,
      "loss": 12.6708,
      "step": 3
    },
    {
      "epoch": 0.02574416733708769,
      "grad_norm": 22.437776565551758,
      "learning_rate": 4e-05,
      "loss": 12.6861,
      "step": 4
    },
    {
      "epoch": 0.02574416733708769,
      "eval_loss": 12.580215454101562,
      "eval_runtime": 1.0736,
      "eval_samples_per_second": 244.046,
      "eval_steps_per_second": 122.023,
      "step": 4
    },
    {
      "epoch": 0.032180209171359615,
      "grad_norm": 19.842269897460938,
      "learning_rate": 5e-05,
      "loss": 12.6079,
      "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": 2622341775360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}