{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 100,
  "global_step": 88,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.2645957469940186,
      "learning_rate": 0.00017727272727272728,
      "loss": 0.5609,
      "step": 10
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 3.18221116065979,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.8267,
      "step": 20
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 3.1673595905303955,
      "learning_rate": 0.0001318181818181818,
      "loss": 0.5182,
      "step": 30
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.5910093784332275,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.2435,
      "step": 40
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 3.6887409687042236,
      "learning_rate": 8.636363636363637e-05,
      "loss": 0.2545,
      "step": 50
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.7244749665260315,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.1302,
      "step": 60
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.1487322300672531,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.0252,
      "step": 70
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.1414584219455719,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.0192,
      "step": 80
    },
    {
      "epoch": 4.0,
      "step": 88,
      "total_flos": 2.7277180344336384e+16,
      "train_loss": 0.29457727345553314,
      "train_runtime": 29.6451,
      "train_samples_per_second": 11.874,
      "train_steps_per_second": 2.968
    }
  ],
  "logging_steps": 10,
  "max_steps": 88,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.7277180344336384e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}