{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9280742459396751,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02320185614849188,
      "grad_norm": 29.851993456423653,
      "learning_rate": 5e-07,
      "loss": 1.6448,
      "step": 5
    },
    {
      "epoch": 0.04640371229698376,
      "grad_norm": 14.665681394229273,
      "learning_rate": 1e-06,
      "loss": 1.5147,
      "step": 10
    },
    {
      "epoch": 0.06960556844547564,
      "grad_norm": 7.818944779433003,
      "learning_rate": 9.998470286265414e-07,
      "loss": 1.2888,
      "step": 15
    },
    {
      "epoch": 0.09280742459396751,
      "grad_norm": 6.011350341653904,
      "learning_rate": 9.993882081071305e-07,
      "loss": 1.2291,
      "step": 20
    },
    {
      "epoch": 0.11600928074245939,
      "grad_norm": 5.834488035843988,
      "learning_rate": 9.986238191873872e-07,
      "loss": 1.1827,
      "step": 25
    },
    {
      "epoch": 0.13921113689095127,
      "grad_norm": 4.944851583820086,
      "learning_rate": 9.975543295858033e-07,
      "loss": 1.1637,
      "step": 30
    },
    {
      "epoch": 0.16241299303944315,
      "grad_norm": 5.051276519398371,
      "learning_rate": 9.961803937075514e-07,
      "loss": 1.1448,
      "step": 35
    },
    {
      "epoch": 0.18561484918793503,
      "grad_norm": 5.008630441799495,
      "learning_rate": 9.945028522440653e-07,
      "loss": 1.1539,
      "step": 40
    },
    {
      "epoch": 0.2088167053364269,
      "grad_norm": 4.527889171881266,
      "learning_rate": 9.925227316586314e-07,
      "loss": 1.1302,
      "step": 45
    },
    {
      "epoch": 0.23201856148491878,
      "grad_norm": 4.665448898349117,
      "learning_rate": 9.902412435583125e-07,
      "loss": 1.1315,
      "step": 50
    },
    {
      "epoch": 0.23201856148491878,
      "eval_loss": 1.1243596076965332,
      "eval_runtime": 107.3706,
      "eval_samples_per_second": 57.083,
      "eval_steps_per_second": 0.894,
      "step": 50
    },
    {
      "epoch": 0.2552204176334107,
      "grad_norm": 4.780072580854242,
      "learning_rate": 9.876597839525813e-07,
      "loss": 1.1184,
      "step": 55
    },
    {
      "epoch": 0.27842227378190254,
      "grad_norm": 4.698899616021614,
      "learning_rate": 9.847799323991233e-07,
      "loss": 1.1112,
      "step": 60
    },
    {
      "epoch": 0.30162412993039445,
      "grad_norm": 4.798544900134018,
      "learning_rate": 9.816034510373285e-07,
      "loss": 1.1022,
      "step": 65
    },
    {
      "epoch": 0.3248259860788863,
      "grad_norm": 4.7554420584590105,
      "learning_rate": 9.781322835100637e-07,
      "loss": 1.1109,
      "step": 70
    },
    {
      "epoch": 0.3480278422273782,
      "grad_norm": 4.715791460597178,
      "learning_rate": 9.743685537743856e-07,
      "loss": 1.1044,
      "step": 75
    },
    {
      "epoch": 0.37122969837587005,
      "grad_norm": 4.781446446456838,
      "learning_rate": 9.70314564801922e-07,
      "loss": 1.0982,
      "step": 80
    },
    {
      "epoch": 0.39443155452436196,
      "grad_norm": 4.616375479434296,
      "learning_rate": 9.659727971697173e-07,
      "loss": 1.0798,
      "step": 85
    },
    {
      "epoch": 0.4176334106728538,
      "grad_norm": 4.81678899141071,
      "learning_rate": 9.613459075424033e-07,
      "loss": 1.0925,
      "step": 90
    },
    {
      "epoch": 0.4408352668213457,
      "grad_norm": 4.804913673447656,
      "learning_rate": 9.564367270466245e-07,
      "loss": 1.0726,
      "step": 95
    },
    {
      "epoch": 0.46403712296983757,
      "grad_norm": 5.428814841421836,
      "learning_rate": 9.51248259538713e-07,
      "loss": 1.0732,
      "step": 100
    },
    {
      "epoch": 0.46403712296983757,
      "eval_loss": 1.079745888710022,
      "eval_runtime": 106.1023,
      "eval_samples_per_second": 57.765,
      "eval_steps_per_second": 0.905,
      "step": 100
    },
    {
      "epoch": 0.4872389791183295,
      "grad_norm": 4.842120094208203,
      "learning_rate": 9.457836797666721e-07,
      "loss": 1.0596,
      "step": 105
    },
    {
      "epoch": 0.5104408352668214,
      "grad_norm": 5.09946277444771,
      "learning_rate": 9.400463314275941e-07,
      "loss": 1.0699,
      "step": 110
    },
    {
      "epoch": 0.5336426914153132,
      "grad_norm": 4.86963572334168,
      "learning_rate": 9.340397251217008e-07,
      "loss": 1.0653,
      "step": 115
    },
    {
      "epoch": 0.5568445475638051,
      "grad_norm": 4.762779682097982,
      "learning_rate": 9.27767536204258e-07,
      "loss": 1.0729,
      "step": 120
    },
    {
      "epoch": 0.580046403712297,
      "grad_norm": 4.737687820279848,
      "learning_rate": 9.212336025366787e-07,
      "loss": 1.0709,
      "step": 125
    },
    {
      "epoch": 0.6032482598607889,
      "grad_norm": 4.782611230029462,
      "learning_rate": 9.144419221381918e-07,
      "loss": 1.0579,
      "step": 130
    },
    {
      "epoch": 0.6264501160092807,
      "grad_norm": 4.991569479884324,
      "learning_rate": 9.073966507395121e-07,
      "loss": 1.0554,
      "step": 135
    },
    {
      "epoch": 0.6496519721577726,
      "grad_norm": 5.008963657772678,
      "learning_rate": 9.001020992400085e-07,
      "loss": 1.043,
      "step": 140
    },
    {
      "epoch": 0.6728538283062645,
      "grad_norm": 5.0207483196868985,
      "learning_rate": 8.925627310699274e-07,
      "loss": 1.0531,
      "step": 145
    },
    {
      "epoch": 0.6960556844547564,
      "grad_norm": 5.288716673563479,
      "learning_rate": 8.84783159459285e-07,
      "loss": 1.0352,
      "step": 150
    },
    {
      "epoch": 0.6960556844547564,
      "eval_loss": 1.054144263267517,
      "eval_runtime": 106.0227,
      "eval_samples_per_second": 57.808,
      "eval_steps_per_second": 0.905,
      "step": 150
    },
    {
      "epoch": 0.7192575406032483,
      "grad_norm": 5.04033042010659,
      "learning_rate": 8.767681446150976e-07,
      "loss": 1.0565,
      "step": 155
    },
    {
      "epoch": 0.7424593967517401,
      "grad_norm": 4.8573560396750395,
      "learning_rate": 8.68522590808682e-07,
      "loss": 1.0409,
      "step": 160
    },
    {
      "epoch": 0.765661252900232,
      "grad_norm": 4.8296712724118125,
      "learning_rate": 8.600515433748001e-07,
      "loss": 1.0531,
      "step": 165
    },
    {
      "epoch": 0.7888631090487239,
      "grad_norm": 5.039044240861594,
      "learning_rate": 8.51360185624495e-07,
      "loss": 1.0321,
      "step": 170
    },
    {
      "epoch": 0.8120649651972158,
      "grad_norm": 4.944895975035593,
      "learning_rate": 8.424538356734956e-07,
      "loss": 1.0366,
      "step": 175
    },
    {
      "epoch": 0.8352668213457076,
      "grad_norm": 5.568497060519676,
      "learning_rate": 8.333379431881397e-07,
      "loss": 1.0454,
      "step": 180
    },
    {
      "epoch": 0.8584686774941995,
      "grad_norm": 4.984582777418547,
      "learning_rate": 8.240180860508026e-07,
      "loss": 1.0368,
      "step": 185
    },
    {
      "epoch": 0.8816705336426914,
      "grad_norm": 5.7520355685162,
      "learning_rate": 8.144999669468713e-07,
      "loss": 1.0288,
      "step": 190
    },
    {
      "epoch": 0.9048723897911833,
      "grad_norm": 5.580835397673134,
      "learning_rate": 8.047894098753539e-07,
      "loss": 1.0323,
      "step": 195
    },
    {
      "epoch": 0.9280742459396751,
      "grad_norm": 4.941555770840273,
      "learning_rate": 7.948923565852597e-07,
      "loss": 1.0347,
      "step": 200
    },
    {
      "epoch": 0.9280742459396751,
      "eval_loss": 1.0315721035003662,
      "eval_runtime": 106.1537,
      "eval_samples_per_second": 57.737,
      "eval_steps_per_second": 0.904,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1179056703799296.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}