{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06281900274833137,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012563800549666275,
      "grad_norm": 0.061941880732774734,
      "learning_rate": 5e-05,
      "loss": 10.3793,
      "step": 1
    },
    {
      "epoch": 0.0012563800549666275,
      "eval_loss": 10.377693176269531,
      "eval_runtime": 0.1105,
      "eval_samples_per_second": 452.476,
      "eval_steps_per_second": 117.644,
      "step": 1
    },
    {
      "epoch": 0.002512760109933255,
      "grad_norm": 0.06490458548069,
      "learning_rate": 0.0001,
      "loss": 10.3791,
      "step": 2
    },
    {
      "epoch": 0.003769140164899882,
      "grad_norm": 0.05616064369678497,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3777,
      "step": 3
    },
    {
      "epoch": 0.00502552021986651,
      "grad_norm": 0.07075366377830505,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3793,
      "step": 4
    },
    {
      "epoch": 0.006281900274833137,
      "grad_norm": 0.07972919940948486,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3785,
      "step": 5
    },
    {
      "epoch": 0.007538280329799764,
      "grad_norm": 0.08161884546279907,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3753,
      "step": 6
    },
    {
      "epoch": 0.008794660384766392,
      "grad_norm": 0.07617795467376709,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3779,
      "step": 7
    },
    {
      "epoch": 0.01005104043973302,
      "grad_norm": 0.08107949048280716,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3801,
      "step": 8
    },
    {
      "epoch": 0.011307420494699646,
      "grad_norm": 0.09238782525062561,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3781,
      "step": 9
    },
    {
      "epoch": 0.012563800549666274,
      "grad_norm": 0.10267684608697891,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3811,
      "step": 10
    },
    {
      "epoch": 0.0138201806046329,
      "grad_norm": 0.1072874367237091,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3822,
      "step": 11
    },
    {
      "epoch": 0.015076560659599529,
      "grad_norm": 0.142090305685997,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3748,
      "step": 12
    },
    {
      "epoch": 0.016332940714566157,
      "grad_norm": 0.08328002691268921,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.375,
      "step": 13
    },
    {
      "epoch": 0.017589320769532783,
      "grad_norm": 0.06633290648460388,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3765,
      "step": 14
    },
    {
      "epoch": 0.01884570082449941,
      "grad_norm": 0.06674735248088837,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3743,
      "step": 15
    },
    {
      "epoch": 0.02010208087946604,
      "grad_norm": 0.07032306492328644,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3757,
      "step": 16
    },
    {
      "epoch": 0.021358460934432666,
      "grad_norm": 0.07050874829292297,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3727,
      "step": 17
    },
    {
      "epoch": 0.022614840989399292,
      "grad_norm": 0.07946357131004333,
      "learning_rate": 7.75e-05,
      "loss": 10.3729,
      "step": 18
    },
    {
      "epoch": 0.023871221044365922,
      "grad_norm": 0.08008846640586853,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.3761,
      "step": 19
    },
    {
      "epoch": 0.02512760109933255,
      "grad_norm": 0.08792636543512344,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3767,
      "step": 20
    },
    {
      "epoch": 0.026383981154299175,
      "grad_norm": 0.1040104404091835,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3768,
      "step": 21
    },
    {
      "epoch": 0.0276403612092658,
      "grad_norm": 0.10459451377391815,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.3733,
      "step": 22
    },
    {
      "epoch": 0.02889674126423243,
      "grad_norm": 0.128785640001297,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3714,
      "step": 23
    },
    {
      "epoch": 0.030153121319199058,
      "grad_norm": 0.14887204766273499,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3727,
      "step": 24
    },
    {
      "epoch": 0.031409501374165684,
      "grad_norm": 0.17993320524692535,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3705,
      "step": 25
    },
    {
      "epoch": 0.031409501374165684,
      "eval_loss": 10.371550559997559,
      "eval_runtime": 0.1128,
      "eval_samples_per_second": 443.339,
      "eval_steps_per_second": 115.268,
      "step": 25
    },
    {
      "epoch": 0.032665881429132314,
      "grad_norm": 0.07941242307424545,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3757,
      "step": 26
    },
    {
      "epoch": 0.03392226148409894,
      "grad_norm": 0.08044446259737015,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.3728,
      "step": 27
    },
    {
      "epoch": 0.03517864153906557,
      "grad_norm": 0.08249679952859879,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3723,
      "step": 28
    },
    {
      "epoch": 0.036435021594032196,
      "grad_norm": 0.08098943531513214,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.3699,
      "step": 29
    },
    {
      "epoch": 0.03769140164899882,
      "grad_norm": 0.08017662167549133,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3701,
      "step": 30
    },
    {
      "epoch": 0.03894778170396545,
      "grad_norm": 0.1113213524222374,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3705,
      "step": 31
    },
    {
      "epoch": 0.04020416175893208,
      "grad_norm": 0.09690547734498978,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.3709,
      "step": 32
    },
    {
      "epoch": 0.0414605418138987,
      "grad_norm": 0.11658542603254318,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.3703,
      "step": 33
    },
    {
      "epoch": 0.04271692186886533,
      "grad_norm": 0.1213645190000534,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.3702,
      "step": 34
    },
    {
      "epoch": 0.04397330192383196,
      "grad_norm": 0.1535189151763916,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.371,
      "step": 35
    },
    {
      "epoch": 0.045229681978798585,
      "grad_norm": 0.1568264365196228,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3716,
      "step": 36
    },
    {
      "epoch": 0.046486062033765214,
      "grad_norm": 0.16247683763504028,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.37,
      "step": 37
    },
    {
      "epoch": 0.047742442088731844,
      "grad_norm": 0.09954192489385605,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3715,
      "step": 38
    },
    {
      "epoch": 0.04899882214369847,
      "grad_norm": 0.07307647168636322,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.372,
      "step": 39
    },
    {
      "epoch": 0.0502552021986651,
      "grad_norm": 0.08242448419332504,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.3705,
      "step": 40
    },
    {
      "epoch": 0.05151158225363173,
      "grad_norm": 0.10652370005846024,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3715,
      "step": 41
    },
    {
      "epoch": 0.05276796230859835,
      "grad_norm": 0.08008083701133728,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3667,
      "step": 42
    },
    {
      "epoch": 0.05402434236356498,
      "grad_norm": 0.09826371818780899,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.3691,
      "step": 43
    },
    {
      "epoch": 0.0552807224185316,
      "grad_norm": 0.10542301088571548,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3723,
      "step": 44
    },
    {
      "epoch": 0.05653710247349823,
      "grad_norm": 0.11045415699481964,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.3693,
      "step": 45
    },
    {
      "epoch": 0.05779348252846486,
      "grad_norm": 0.12850798666477203,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.3701,
      "step": 46
    },
    {
      "epoch": 0.059049862583431485,
      "grad_norm": 0.13147960603237152,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.3681,
      "step": 47
    },
    {
      "epoch": 0.060306242638398115,
      "grad_norm": 0.17121492326259613,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3689,
      "step": 48
    },
    {
      "epoch": 0.061562622693364745,
      "grad_norm": 0.18566985428333282,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.3713,
      "step": 49
    },
    {
      "epoch": 0.06281900274833137,
      "grad_norm": 0.20494161546230316,
      "learning_rate": 1e-05,
      "loss": 10.3626,
      "step": 50
    },
    {
      "epoch": 0.06281900274833137,
      "eval_loss": 10.368329048156738,
      "eval_runtime": 0.0997,
      "eval_samples_per_second": 501.26,
      "eval_steps_per_second": 130.328,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 42768059596800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}