{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9964841788046208,
  "eval_steps": 1000,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04018081366147665,
      "grad_norm": 3.9855914370792176,
      "learning_rate": 6.923076923076923e-06,
      "loss": 1.528,
      "step": 10
    },
    {
      "epoch": 0.0803616273229533,
      "grad_norm": 1.1009387233386336,
      "learning_rate": 9.983924160137627e-06,
      "loss": 0.7997,
      "step": 20
    },
    {
      "epoch": 0.12054244098442994,
      "grad_norm": 0.8531122977437774,
      "learning_rate": 9.886057021922984e-06,
      "loss": 0.6384,
      "step": 30
    },
    {
      "epoch": 0.1607232546459066,
      "grad_norm": 0.8536491315382806,
      "learning_rate": 9.700998080399287e-06,
      "loss": 0.626,
      "step": 40
    },
    {
      "epoch": 0.20090406830738322,
      "grad_norm": 0.8012093869333087,
      "learning_rate": 9.432049716762151e-06,
      "loss": 0.5725,
      "step": 50
    },
    {
      "epoch": 0.24108488196885988,
      "grad_norm": 0.7591296330983313,
      "learning_rate": 9.08401132093219e-06,
      "loss": 0.5478,
      "step": 60
    },
    {
      "epoch": 0.2812656956303365,
      "grad_norm": 0.7482379362816577,
      "learning_rate": 8.663093646328166e-06,
      "loss": 0.547,
      "step": 70
    },
    {
      "epoch": 0.3214465092918132,
      "grad_norm": 0.739024551349721,
      "learning_rate": 8.17680797882512e-06,
      "loss": 0.5588,
      "step": 80
    },
    {
      "epoch": 0.3616273229532898,
      "grad_norm": 0.7393951361302983,
      "learning_rate": 7.633832097679959e-06,
      "loss": 0.508,
      "step": 90
    },
    {
      "epoch": 0.40180813661476644,
      "grad_norm": 0.7515531494396616,
      "learning_rate": 7.04385542035506e-06,
      "loss": 0.5226,
      "step": 100
    },
    {
      "epoch": 0.4419889502762431,
      "grad_norm": 0.7192941297373309,
      "learning_rate": 6.41740609463409e-06,
      "loss": 0.5259,
      "step": 110
    },
    {
      "epoch": 0.48216976393771976,
      "grad_norm": 0.7491496835437959,
      "learning_rate": 5.765663123575401e-06,
      "loss": 0.5236,
      "step": 120
    },
    {
      "epoch": 0.5223505775991963,
      "grad_norm": 0.6913958034624077,
      "learning_rate": 5.1002568759376134e-06,
      "loss": 0.4932,
      "step": 130
    },
    {
      "epoch": 0.562531391260673,
      "grad_norm": 0.7500711845802256,
      "learning_rate": 4.433061541973591e-06,
      "loss": 0.4862,
      "step": 140
    },
    {
      "epoch": 0.6027122049221497,
      "grad_norm": 0.6913808839000353,
      "learning_rate": 3.77598323822407e-06,
      "loss": 0.5015,
      "step": 150
    },
    {
      "epoch": 0.6428930185836264,
      "grad_norm": 0.6642782125575131,
      "learning_rate": 3.1407475425859348e-06,
      "loss": 0.5478,
      "step": 160
    },
    {
      "epoch": 0.683073832245103,
      "grad_norm": 0.6488024479264766,
      "learning_rate": 2.5386902510968627e-06,
      "loss": 0.4814,
      "step": 170
    },
    {
      "epoch": 0.7232546459065796,
      "grad_norm": 0.7186636113633829,
      "learning_rate": 1.9805550903864775e-06,
      "loss": 0.5066,
      "step": 180
    },
    {
      "epoch": 0.7634354595680563,
      "grad_norm": 0.6368854640125701,
      "learning_rate": 1.4763019956201252e-06,
      "loss": 0.4917,
      "step": 190
    },
    {
      "epoch": 0.8036162732295329,
      "grad_norm": 0.8130162452154214,
      "learning_rate": 1.0349293752198842e-06,
      "loss": 0.4796,
      "step": 200
    },
    {
      "epoch": 0.8437970868910095,
      "grad_norm": 0.7305985326066481,
      "learning_rate": 6.643135340531137e-07,
      "loss": 0.5084,
      "step": 210
    },
    {
      "epoch": 0.8839779005524862,
      "grad_norm": 0.7027540145976225,
      "learning_rate": 3.710681205854838e-07,
      "loss": 0.4863,
      "step": 220
    },
    {
      "epoch": 0.9241587142139628,
      "grad_norm": 0.6411791844623818,
      "learning_rate": 1.6042610616743782e-07,
      "loss": 0.4763,
      "step": 230
    },
    {
      "epoch": 0.9643395278754395,
      "grad_norm": 0.6768334011228406,
      "learning_rate": 3.6146402536468285e-08,
      "loss": 0.4711,
      "step": 240
    },
    {
      "epoch": 0.9964841788046208,
      "step": 248,
      "total_flos": 790927692005376.0,
      "train_loss": 0.5734609403917866,
      "train_runtime": 14466.4063,
      "train_samples_per_second": 2.202,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 248,
  "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": 790927692005376.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}