{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032265870775187544,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032265870775187547,
      "eval_loss": 4.1613311767578125,
      "eval_runtime": 23.9151,
      "eval_samples_per_second": 54.568,
      "eval_steps_per_second": 27.305,
      "step": 1
    },
    {
      "epoch": 0.0009679761232556264,
      "grad_norm": 1.7457234859466553,
      "learning_rate": 6e-05,
      "loss": 3.516,
      "step": 3
    },
    {
      "epoch": 0.0019359522465112527,
      "grad_norm": 1.6416014432907104,
      "learning_rate": 0.00012,
      "loss": 3.6706,
      "step": 6
    },
    {
      "epoch": 0.0025812696620150038,
      "eval_loss": 3.9660162925720215,
      "eval_runtime": 22.7709,
      "eval_samples_per_second": 57.31,
      "eval_steps_per_second": 28.677,
      "step": 8
    },
    {
      "epoch": 0.002903928369766879,
      "grad_norm": 1.9313857555389404,
      "learning_rate": 0.00018,
      "loss": 3.9218,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 527551495667712.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}