{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 0.03611391115633824,
      "learning_rate": 0.0,
      "loss": 0.1775,
      "num_tokens": 756225.0,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.035872818263133606,
      "learning_rate": 5e-05,
      "loss": 0.1765,
      "num_tokens": 1483390.0,
      "step": 2
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.03915901096677451,
      "learning_rate": 0.0001,
      "loss": 0.1806,
      "num_tokens": 2209300.0,
      "step": 3
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.036205560159263704,
      "learning_rate": 9.984630218530014e-05,
      "loss": 0.1635,
      "num_tokens": 2984177.0,
      "step": 4
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.02680440059976215,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.1674,
      "num_tokens": 3753109.0,
      "step": 5
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.026262738280192953,
      "learning_rate": 9.862301196726987e-05,
      "loss": 0.1689,
      "num_tokens": 4469538.0,
      "step": 6
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.0424737010568047,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.1712,
      "num_tokens": 5211764.0,
      "step": 7
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.0333944365217068,
      "learning_rate": 9.620979969947759e-05,
      "loss": 0.1549,
      "num_tokens": 5991810.0,
      "step": 8
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.028498133402257736,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.1546,
      "num_tokens": 6739218.0,
      "step": 9
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.018380894351295054,
      "learning_rate": 9.267249152181379e-05,
      "loss": 0.1547,
      "num_tokens": 7509565.0,
      "step": 10
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.01398479297990615,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.1456,
      "num_tokens": 8264071.0,
      "step": 11
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.02288922386851858,
      "learning_rate": 8.810757598029093e-05,
      "loss": 0.1515,
      "num_tokens": 8995157.0,
      "step": 12
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.01639983702617964,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.1513,
      "num_tokens": 9738011.0,
      "step": 13
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.017539251111415122,
      "learning_rate": 8.263957207103507e-05,
      "loss": 0.1577,
      "num_tokens": 10510599.0,
      "step": 14
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.01564027560200894,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.1495,
      "num_tokens": 11258986.0,
      "step": 15
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.01477374574495207,
      "learning_rate": 7.641763268666831e-05,
      "loss": 0.1439,
      "num_tokens": 12004651.0,
      "step": 16
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.01581085629651005,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.1548,
      "num_tokens": 12720028.0,
      "step": 17
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.017050020743555896,
      "learning_rate": 6.961147611421075e-05,
      "loss": 0.1389,
      "num_tokens": 13471910.0,
      "step": 18
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.01657365889734436,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.1409,
      "num_tokens": 14256829.0,
      "step": 19
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.017278692031308423,
      "learning_rate": 6.240675656263303e-05,
      "loss": 0.138,
      "num_tokens": 15011843.0,
      "step": 20
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.01428176044310885,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.1283,
      "num_tokens": 15735208.0,
      "step": 21
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.01499874953620338,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.1394,
      "num_tokens": 16472251.0,
      "step": 22
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.015634439749128978,
      "learning_rate": 5.128392945374505e-05,
      "loss": 0.136,
      "num_tokens": 17217444.0,
      "step": 23
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.016546311554517055,
      "learning_rate": 4.7593243437366975e-05,
      "loss": 0.1305,
      "num_tokens": 17994169.0,
      "step": 24
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.017548942190792314,
      "learning_rate": 4.395315307866405e-05,
      "loss": 0.1345,
      "num_tokens": 18771682.0,
      "step": 25
    },
    {
      "epoch": 5.2,
      "grad_norm": 0.0152813105228742,
      "learning_rate": 4.0388523885789256e-05,
      "loss": 0.1355,
      "num_tokens": 19526237.0,
      "step": 26
    },
    {
      "epoch": 5.4,
      "grad_norm": 0.01647103229085855,
      "learning_rate": 3.692370589061639e-05,
      "loss": 0.1246,
      "num_tokens": 20228353.0,
      "step": 27
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.015380646551294024,
      "learning_rate": 3.358236731333169e-05,
      "loss": 0.1177,
      "num_tokens": 21052939.0,
      "step": 28
    },
    {
      "epoch": 5.8,
      "grad_norm": 0.01775161513408205,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.1229,
      "num_tokens": 21802988.0,
      "step": 29
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.016290142632997433,
      "learning_rate": 2.736042792896495e-05,
      "loss": 0.1274,
      "num_tokens": 22534050.0,
      "step": 30
    },
    {
      "epoch": 6.2,
      "grad_norm": 0.016350803725219853,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.1203,
      "num_tokens": 23285521.0,
      "step": 31
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.01737465421484033,
      "learning_rate": 2.189242401970908e-05,
      "loss": 0.1227,
      "num_tokens": 24010248.0,
      "step": 32
    },
    {
      "epoch": 6.6,
      "grad_norm": 0.016284427710037876,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.1201,
      "num_tokens": 24773039.0,
      "step": 33
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.016910802013508405,
      "learning_rate": 1.7327508478186218e-05,
      "loss": 0.1197,
      "num_tokens": 25513022.0,
      "step": 34
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.017565799087890962,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.1166,
      "num_tokens": 26298224.0,
      "step": 35
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.01603571844512917,
      "learning_rate": 1.3790200300522413e-05,
      "loss": 0.124,
      "num_tokens": 26998867.0,
      "step": 36
    },
    {
      "epoch": 7.4,
      "grad_norm": 0.019226664942621104,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 0.1149,
      "num_tokens": 27748781.0,
      "step": 37
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.01722863782520172,
      "learning_rate": 1.1376988032730134e-05,
      "loss": 0.1167,
      "num_tokens": 28555376.0,
      "step": 38
    },
    {
      "epoch": 7.8,
      "grad_norm": 0.01661843313975511,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 0.1178,
      "num_tokens": 29318862.0,
      "step": 39
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.015837386464072713,
      "learning_rate": 1.0153697814699859e-05,
      "loss": 0.1096,
      "num_tokens": 30051707.0,
      "step": 40
    },
    {
      "epoch": 8.0,
      "step": 40,
      "total_flos": 146178451963904.0,
      "train_loss": 0.0,
      "train_runtime": 4.8816,
      "train_samples_per_second": 1042.287,
      "train_steps_per_second": 8.194
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 146178451963904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}