{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9953488372093023,
  "eval_steps": 500,
  "global_step": 107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009302325581395349,
      "grad_norm": 0.33000171184539795,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.2009,
      "mean_token_accuracy": 0.673521239310503,
      "step": 1
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.3065112829208374,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.1539,
      "mean_token_accuracy": 0.6822087187319994,
      "step": 5
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.3443320393562317,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.1184,
      "mean_token_accuracy": 0.6890031665563583,
      "step": 10
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.23821508884429932,
      "learning_rate": 0.00019914448613738106,
      "loss": 1.0085,
      "mean_token_accuracy": 0.709736293554306,
      "step": 15
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.1719299852848053,
      "learning_rate": 0.0001956940335732209,
      "loss": 0.9457,
      "mean_token_accuracy": 0.7221233680844307,
      "step": 20
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.15530090034008026,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.9069,
      "mean_token_accuracy": 0.7291829422116279,
      "step": 25
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.1351461559534073,
      "learning_rate": 0.00018128466845916154,
      "loss": 0.8542,
      "mean_token_accuracy": 0.7403964079916477,
      "step": 30
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.12998437881469727,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.8219,
      "mean_token_accuracy": 0.7473064973950386,
      "step": 35
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.1579654961824417,
      "learning_rate": 0.00015824776968678024,
      "loss": 0.7689,
      "mean_token_accuracy": 0.7591808065772057,
      "step": 40
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.13961397111415863,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.7605,
      "mean_token_accuracy": 0.7607541777193546,
      "step": 45
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.15156981348991394,
      "learning_rate": 0.00012902846772544624,
      "loss": 0.7466,
      "mean_token_accuracy": 0.7628601484000683,
      "step": 50
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.1230233684182167,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.7338,
      "mean_token_accuracy": 0.7658133447170258,
      "step": 55
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.1458376795053482,
      "learning_rate": 9.67280917178224e-05,
      "loss": 0.7271,
      "mean_token_accuracy": 0.7671422854065895,
      "step": 60
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.1341293305158615,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.7137,
      "mean_token_accuracy": 0.7699349835515022,
      "step": 65
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.13247253000736237,
      "learning_rate": 6.477499520787665e-05,
      "loss": 0.6963,
      "mean_token_accuracy": 0.7752044893801212,
      "step": 70
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.12003805488348007,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.6957,
      "mean_token_accuracy": 0.774368204921484,
      "step": 75
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.11840014159679413,
      "learning_rate": 3.6560671583635467e-05,
      "loss": 0.6922,
      "mean_token_accuracy": 0.7757050350308419,
      "step": 80
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.13812483847141266,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.6854,
      "mean_token_accuracy": 0.777467641979456,
      "step": 85
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.12007566541433334,
      "learning_rate": 1.5079781847342123e-05,
      "loss": 0.6774,
      "mean_token_accuracy": 0.7794982820749283,
      "step": 90
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.11563662439584732,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.6787,
      "mean_token_accuracy": 0.7794713638722897,
      "step": 95
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.11361019313335419,
      "learning_rate": 2.612302072266637e-06,
      "loss": 0.6715,
      "mean_token_accuracy": 0.7792891427874565,
      "step": 100
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.11059077084064484,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.6896,
      "mean_token_accuracy": 0.7759934611618519,
      "step": 105
    },
    {
      "epoch": 0.9953488372093023,
      "mean_token_accuracy": 0.7779956627637148,
      "step": 107,
      "total_flos": 3.0828954034110464e+16,
      "train_loss": 0.7957682988353979,
      "train_runtime": 1817.9416,
      "train_samples_per_second": 0.946,
      "train_steps_per_second": 0.059
    }
  ],
  "logging_steps": 5,
  "max_steps": 107,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.0828954034110464e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}