{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011927836588638736,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023855673177277472,
      "grad_norm": 1.2481120824813843,
      "learning_rate": 1e-05,
      "loss": 0.9265,
      "step": 1
    },
    {
      "epoch": 0.0023855673177277472,
      "eval_loss": 0.9870346188545227,
      "eval_runtime": 65.0919,
      "eval_samples_per_second": 10.846,
      "eval_steps_per_second": 5.423,
      "step": 1
    },
    {
      "epoch": 0.0047711346354554944,
      "grad_norm": 1.427655577659607,
      "learning_rate": 2e-05,
      "loss": 1.0298,
      "step": 2
    },
    {
      "epoch": 0.0047711346354554944,
      "eval_loss": 0.9387862086296082,
      "eval_runtime": 16.6543,
      "eval_samples_per_second": 42.392,
      "eval_steps_per_second": 21.196,
      "step": 2
    },
    {
      "epoch": 0.007156701953183241,
      "grad_norm": 1.2481718063354492,
      "learning_rate": 3e-05,
      "loss": 0.9639,
      "step": 3
    },
    {
      "epoch": 0.009542269270910989,
      "grad_norm": 1.2510924339294434,
      "learning_rate": 4e-05,
      "loss": 0.9506,
      "step": 4
    },
    {
      "epoch": 0.009542269270910989,
      "eval_loss": 0.8984954953193665,
      "eval_runtime": 16.8324,
      "eval_samples_per_second": 41.943,
      "eval_steps_per_second": 20.971,
      "step": 4
    },
    {
      "epoch": 0.011927836588638736,
      "grad_norm": 1.215053677558899,
      "learning_rate": 5e-05,
      "loss": 0.8298,
      "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": 3295645846732800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}