{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009467231544815507,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.467231544815507e-05,
      "grad_norm": 27.603601455688477,
      "learning_rate": 2e-05,
      "loss": 7.7285,
      "step": 1
    },
    {
      "epoch": 9.467231544815507e-05,
      "eval_loss": 7.354588985443115,
      "eval_runtime": 76.9802,
      "eval_samples_per_second": 57.781,
      "eval_steps_per_second": 28.891,
      "step": 1
    },
    {
      "epoch": 0.00018934463089631014,
      "grad_norm": 49.91172409057617,
      "learning_rate": 4e-05,
      "loss": 7.4189,
      "step": 2
    },
    {
      "epoch": 0.0002840169463444652,
      "grad_norm": 54.60095977783203,
      "learning_rate": 6e-05,
      "loss": 8.3787,
      "step": 3
    },
    {
      "epoch": 0.0002840169463444652,
      "eval_loss": 7.160763263702393,
      "eval_runtime": 76.6118,
      "eval_samples_per_second": 58.059,
      "eval_steps_per_second": 29.029,
      "step": 3
    },
    {
      "epoch": 0.0003786892617926203,
      "grad_norm": 31.0164794921875,
      "learning_rate": 8e-05,
      "loss": 7.9694,
      "step": 4
    },
    {
      "epoch": 0.00047336157724077536,
      "grad_norm": 38.51640701293945,
      "learning_rate": 0.0001,
      "loss": 7.2194,
      "step": 5
    },
    {
      "epoch": 0.0005680338926889304,
      "grad_norm": 22.034116744995117,
      "learning_rate": 0.00012,
      "loss": 5.5011,
      "step": 6
    },
    {
      "epoch": 0.0005680338926889304,
      "eval_loss": 5.140564441680908,
      "eval_runtime": 76.6566,
      "eval_samples_per_second": 58.025,
      "eval_steps_per_second": 29.013,
      "step": 6
    },
    {
      "epoch": 0.0006627062081370855,
      "grad_norm": 33.167362213134766,
      "learning_rate": 0.00014,
      "loss": 5.0429,
      "step": 7
    },
    {
      "epoch": 0.0007573785235852406,
      "grad_norm": 32.992427825927734,
      "learning_rate": 0.00016,
      "loss": 3.8519,
      "step": 8
    },
    {
      "epoch": 0.0008520508390333956,
      "grad_norm": 170.6376953125,
      "learning_rate": 0.00018,
      "loss": 3.9001,
      "step": 9
    },
    {
      "epoch": 0.0008520508390333956,
      "eval_loss": 2.894521474838257,
      "eval_runtime": 76.6298,
      "eval_samples_per_second": 58.045,
      "eval_steps_per_second": 29.023,
      "step": 9
    },
    {
      "epoch": 0.0009467231544815507,
      "grad_norm": 82.27149963378906,
      "learning_rate": 0.0002,
      "loss": 2.7972,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 255791978250240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}