{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032512395350727465,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006502479070145493,
      "grad_norm": 38.074520111083984,
      "learning_rate": 1e-05,
      "loss": 17.5389,
      "step": 1
    },
    {
      "epoch": 0.0006502479070145493,
      "eval_loss": 1.0618399381637573,
      "eval_runtime": 460.4304,
      "eval_samples_per_second": 5.627,
      "eval_steps_per_second": 2.815,
      "step": 1
    },
    {
      "epoch": 0.0013004958140290985,
      "grad_norm": 22.84642791748047,
      "learning_rate": 2e-05,
      "loss": 15.412,
      "step": 2
    },
    {
      "epoch": 0.0013004958140290985,
      "eval_loss": 1.0530256032943726,
      "eval_runtime": 235.1279,
      "eval_samples_per_second": 11.02,
      "eval_steps_per_second": 5.512,
      "step": 2
    },
    {
      "epoch": 0.001950743721043648,
      "grad_norm": 20.80272102355957,
      "learning_rate": 3e-05,
      "loss": 15.7976,
      "step": 3
    },
    {
      "epoch": 0.002600991628058197,
      "grad_norm": 29.789457321166992,
      "learning_rate": 4e-05,
      "loss": 16.4979,
      "step": 4
    },
    {
      "epoch": 0.002600991628058197,
      "eval_loss": 1.0309265851974487,
      "eval_runtime": 234.912,
      "eval_samples_per_second": 11.03,
      "eval_steps_per_second": 5.517,
      "step": 4
    },
    {
      "epoch": 0.0032512395350727465,
      "grad_norm": 14.433426856994629,
      "learning_rate": 5e-05,
      "loss": 14.9313,
      "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": 3592977188388864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}