{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4536366770079283,
  "eval_steps": 500,
  "global_step": 2109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006894174422612892,
      "grad_norm": 6.479256629943848,
      "learning_rate": 0.0,
      "loss": 1.6632,
      "step": 1
    },
    {
      "epoch": 0.03447087211306446,
      "grad_norm": 3.2223708629608154,
      "learning_rate": 1.9999434046461045e-05,
      "loss": 1.4496,
      "step": 50
    },
    {
      "epoch": 0.06894174422612892,
      "grad_norm": 3.344071388244629,
      "learning_rate": 1.996249692618611e-05,
      "loss": 1.2491,
      "step": 100
    },
    {
      "epoch": 0.10341261633919338,
      "grad_norm": 3.0401906967163086,
      "learning_rate": 1.9868053167196865e-05,
      "loss": 1.1876,
      "step": 150
    },
    {
      "epoch": 0.13788348845225784,
      "grad_norm": 3.164588689804077,
      "learning_rate": 1.971664792831919e-05,
      "loss": 1.1607,
      "step": 200
    },
    {
      "epoch": 0.1723543605653223,
      "grad_norm": 2.982455253601074,
      "learning_rate": 1.9509155167802316e-05,
      "loss": 1.1297,
      "step": 250
    },
    {
      "epoch": 0.20682523267838676,
      "grad_norm": 3.021336793899536,
      "learning_rate": 1.9246772598559302e-05,
      "loss": 1.1096,
      "step": 300
    },
    {
      "epoch": 0.24129610479145122,
      "grad_norm": 2.949462652206421,
      "learning_rate": 1.8931014774594656e-05,
      "loss": 1.1004,
      "step": 350
    },
    {
      "epoch": 0.2757669769045157,
      "grad_norm": 2.738522529602051,
      "learning_rate": 1.8563704348526337e-05,
      "loss": 1.0608,
      "step": 400
    },
    {
      "epoch": 0.31023784901758017,
      "grad_norm": 3.002688407897949,
      "learning_rate": 1.8146961550666525e-05,
      "loss": 1.0632,
      "step": 450
    },
    {
      "epoch": 0.3447087211306446,
      "grad_norm": 2.8380253314971924,
      "learning_rate": 1.7683191950391142e-05,
      "loss": 1.0549,
      "step": 500
    },
    {
      "epoch": 0.3791795932437091,
      "grad_norm": 2.875920295715332,
      "learning_rate": 1.717507257044331e-05,
      "loss": 1.0378,
      "step": 550
    },
    {
      "epoch": 0.4136504653567735,
      "grad_norm": 2.8477611541748047,
      "learning_rate": 1.6625536434323358e-05,
      "loss": 1.0359,
      "step": 600
    },
    {
      "epoch": 0.448121337469838,
      "grad_norm": 2.6955602169036865,
      "learning_rate": 1.6037755635962587e-05,
      "loss": 1.017,
      "step": 650
    },
    {
      "epoch": 0.48259220958290244,
      "grad_norm": 2.665055751800537,
      "learning_rate": 1.5415123029408046e-05,
      "loss": 1.0066,
      "step": 700
    },
    {
      "epoch": 0.5170630816959669,
      "grad_norm": 2.7886996269226074,
      "learning_rate": 1.4761232644210963e-05,
      "loss": 1.0003,
      "step": 750
    },
    {
      "epoch": 0.5515339538090314,
      "grad_norm": 2.561713218688965,
      "learning_rate": 1.4079858939567557e-05,
      "loss": 0.9959,
      "step": 800
    },
    {
      "epoch": 0.5860048259220958,
      "grad_norm": 2.623467206954956,
      "learning_rate": 1.3374935016963595e-05,
      "loss": 0.9915,
      "step": 850
    },
    {
      "epoch": 0.6204756980351603,
      "grad_norm": 2.6682498455047607,
      "learning_rate": 1.2650529917086232e-05,
      "loss": 0.9738,
      "step": 900
    },
    {
      "epoch": 0.6549465701482248,
      "grad_norm": 2.6951420307159424,
      "learning_rate": 1.1910825132052356e-05,
      "loss": 0.9785,
      "step": 950
    },
    {
      "epoch": 0.6894174422612892,
      "grad_norm": 2.6426846981048584,
      "learning_rate": 1.1160090468532266e-05,
      "loss": 0.9806,
      "step": 1000
    },
    {
      "epoch": 0.7238883143743536,
      "grad_norm": 2.6905856132507324,
      "learning_rate": 1.0402659401094154e-05,
      "loss": 0.9568,
      "step": 1050
    },
    {
      "epoch": 0.7583591864874182,
      "grad_norm": 2.618277072906494,
      "learning_rate": 9.642904058037667e-06,
      "loss": 0.9653,
      "step": 1100
    },
    {
      "epoch": 0.7928300586004826,
      "grad_norm": 2.5803515911102295,
      "learning_rate": 8.885209984106072e-06,
      "loss": 0.9566,
      "step": 1150
    },
    {
      "epoch": 0.827300930713547,
      "grad_norm": 2.7561099529266357,
      "learning_rate": 8.133950825754511e-06,
      "loss": 0.9571,
      "step": 1200
    },
    {
      "epoch": 0.8617718028266115,
      "grad_norm": 2.651911735534668,
      "learning_rate": 7.393463085098886e-06,
      "loss": 0.9485,
      "step": 1250
    },
    {
      "epoch": 0.896242674939676,
      "grad_norm": 2.649693250656128,
      "learning_rate": 6.6680210882734805e-06,
      "loss": 0.9471,
      "step": 1300
    },
    {
      "epoch": 0.9307135470527405,
      "grad_norm": 2.6041650772094727,
      "learning_rate": 5.961812312687689e-06,
      "loss": 0.9349,
      "step": 1350
    },
    {
      "epoch": 0.9651844191658049,
      "grad_norm": 2.6525392532348633,
      "learning_rate": 5.278913215600714e-06,
      "loss": 0.9344,
      "step": 1400
    },
    {
      "epoch": 0.9996552912788693,
      "grad_norm": 2.6537036895751953,
      "learning_rate": 4.623265703539146e-06,
      "loss": 0.9174,
      "step": 1450
    },
    {
      "epoch": 1.033781454670803,
      "grad_norm": 2.5499179363250732,
      "learning_rate": 3.998654378383361e-06,
      "loss": 0.7982,
      "step": 1500
    },
    {
      "epoch": 1.0682523267838677,
      "grad_norm": 2.596992254257202,
      "learning_rate": 3.408684691465355e-06,
      "loss": 0.786,
      "step": 1550
    },
    {
      "epoch": 1.1027231988969322,
      "grad_norm": 2.550497531890869,
      "learning_rate": 2.85676213177945e-06,
      "loss": 0.7988,
      "step": 1600
    },
    {
      "epoch": 1.1371940710099966,
      "grad_norm": 2.5404860973358154,
      "learning_rate": 2.3460725684379002e-06,
      "loss": 0.7874,
      "step": 1650
    },
    {
      "epoch": 1.171664943123061,
      "grad_norm": 2.6311583518981934,
      "learning_rate": 1.8795638608410016e-06,
      "loss": 0.7965,
      "step": 1700
    },
    {
      "epoch": 1.2061358152361255,
      "grad_norm": 2.623417615890503,
      "learning_rate": 1.4599288427134283e-06,
      "loss": 0.7922,
      "step": 1750
    },
    {
      "epoch": 1.2406066873491899,
      "grad_norm": 2.5811400413513184,
      "learning_rate": 1.0895897782283305e-06,
      "loss": 0.7915,
      "step": 1800
    },
    {
      "epoch": 1.2750775594622543,
      "grad_norm": 2.5747768878936768,
      "learning_rate": 7.706843799431985e-07,
      "loss": 0.7884,
      "step": 1850
    },
    {
      "epoch": 1.309548431575319,
      "grad_norm": 2.675109624862671,
      "learning_rate": 5.050534692564358e-07,
      "loss": 0.786,
      "step": 1900
    },
    {
      "epoch": 1.3440193036883832,
      "grad_norm": 2.594230890274048,
      "learning_rate": 2.94230350612239e-07,
      "loss": 0.7751,
      "step": 1950
    },
    {
      "epoch": 1.3784901758014478,
      "grad_norm": 2.5236330032348633,
      "learning_rate": 1.3943196078924247e-07,
      "loss": 0.7861,
      "step": 2000
    },
    {
      "epoch": 1.4129610479145123,
      "grad_norm": 2.671135902404785,
      "learning_rate": 4.155184436196669e-08,
      "loss": 0.7872,
      "step": 2050
    },
    {
      "epoch": 1.4474319200275767,
      "grad_norm": 2.5242528915405273,
      "learning_rate": 1.154995882924892e-09,
      "loss": 0.7975,
      "step": 2100
    },
    {
      "epoch": 1.4536366770079283,
      "step": 2109,
      "total_flos": 7.41829675403182e+16,
      "train_loss": 0.9605129250082827,
      "train_runtime": 2747.171,
      "train_samples_per_second": 6.142,
      "train_steps_per_second": 0.768
    }
  ],
  "logging_steps": 50,
  "max_steps": 2109,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 7.41829675403182e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}