{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.027164685908319185,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005432937181663837,
      "grad_norm": 70.13006591796875,
      "learning_rate": 1e-05,
      "loss": 52.5351,
      "step": 1
    },
    {
      "epoch": 0.005432937181663837,
      "eval_loss": 3.50217866897583,
      "eval_runtime": 27.5515,
      "eval_samples_per_second": 11.252,
      "eval_steps_per_second": 5.626,
      "step": 1
    },
    {
      "epoch": 0.010865874363327675,
      "grad_norm": 80.5508041381836,
      "learning_rate": 2e-05,
      "loss": 56.9291,
      "step": 2
    },
    {
      "epoch": 0.010865874363327675,
      "eval_loss": 3.4603018760681152,
      "eval_runtime": 21.0457,
      "eval_samples_per_second": 14.73,
      "eval_steps_per_second": 7.365,
      "step": 2
    },
    {
      "epoch": 0.01629881154499151,
      "grad_norm": 67.22582244873047,
      "learning_rate": 3e-05,
      "loss": 50.0485,
      "step": 3
    },
    {
      "epoch": 0.02173174872665535,
      "grad_norm": 92.59852600097656,
      "learning_rate": 4e-05,
      "loss": 58.5185,
      "step": 4
    },
    {
      "epoch": 0.02173174872665535,
      "eval_loss": 3.3412952423095703,
      "eval_runtime": 20.998,
      "eval_samples_per_second": 14.763,
      "eval_steps_per_second": 7.382,
      "step": 4
    },
    {
      "epoch": 0.027164685908319185,
      "grad_norm": 96.22347259521484,
      "learning_rate": 5e-05,
      "loss": 55.5185,
      "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": 3505339571896320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}