{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0028194826249383236,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005638965249876648,
      "grad_norm": 1.2278774976730347,
      "learning_rate": 1e-05,
      "loss": 20.2417,
      "step": 1
    },
    {
      "epoch": 0.0005638965249876648,
      "eval_loss": 1.259517788887024,
      "eval_runtime": 153.5327,
      "eval_samples_per_second": 19.455,
      "eval_steps_per_second": 9.731,
      "step": 1
    },
    {
      "epoch": 0.0011277930499753296,
      "grad_norm": 3.8106093406677246,
      "learning_rate": 2e-05,
      "loss": 20.6244,
      "step": 2
    },
    {
      "epoch": 0.0011277930499753296,
      "eval_loss": NaN,
      "eval_runtime": 126.3874,
      "eval_samples_per_second": 23.634,
      "eval_steps_per_second": 11.821,
      "step": 2
    },
    {
      "epoch": 0.0016916895749629942,
      "grad_norm": 1.428214430809021,
      "learning_rate": 3e-05,
      "loss": 20.1576,
      "step": 3
    },
    {
      "epoch": 0.0022555860999506593,
      "grad_norm": 1.7558352947235107,
      "learning_rate": 4e-05,
      "loss": 19.9871,
      "step": 4
    },
    {
      "epoch": 0.0022555860999506593,
      "eval_loss": NaN,
      "eval_runtime": 126.3963,
      "eval_samples_per_second": 23.632,
      "eval_steps_per_second": 11.82,
      "step": 4
    },
    {
      "epoch": 0.0028194826249383236,
      "grad_norm": 1.4141714572906494,
      "learning_rate": 5e-05,
      "loss": 20.1202,
      "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": 4519779146661888.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}