{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0049808238282611945,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.961647656522389e-05,
      "grad_norm": 0.3748319745063782,
      "learning_rate": 1e-05,
      "loss": 1.6077,
      "step": 1
    },
    {
      "epoch": 9.961647656522389e-05,
      "eval_loss": 1.0737049579620361,
      "eval_runtime": 1789.5077,
      "eval_samples_per_second": 4.724,
      "eval_steps_per_second": 0.591,
      "step": 1
    },
    {
      "epoch": 0.00019923295313044778,
      "grad_norm": 0.47770676016807556,
      "learning_rate": 2e-05,
      "loss": 2.0602,
      "step": 2
    },
    {
      "epoch": 0.0002988494296956717,
      "grad_norm": 0.4726722538471222,
      "learning_rate": 3e-05,
      "loss": 2.2152,
      "step": 3
    },
    {
      "epoch": 0.00039846590626089557,
      "grad_norm": 0.509148359298706,
      "learning_rate": 4e-05,
      "loss": 2.2219,
      "step": 4
    },
    {
      "epoch": 0.0004980823828261194,
      "grad_norm": 0.6239567399024963,
      "learning_rate": 5e-05,
      "loss": 2.3138,
      "step": 5
    },
    {
      "epoch": 0.0005976988593913434,
      "grad_norm": 0.5875715017318726,
      "learning_rate": 6e-05,
      "loss": 2.3489,
      "step": 6
    },
    {
      "epoch": 0.0006973153359565673,
      "grad_norm": 0.47263002395629883,
      "learning_rate": 7e-05,
      "loss": 1.813,
      "step": 7
    },
    {
      "epoch": 0.0007969318125217911,
      "grad_norm": 0.5967614054679871,
      "learning_rate": 8e-05,
      "loss": 2.1826,
      "step": 8
    },
    {
      "epoch": 0.000896548289087015,
      "grad_norm": 0.750761866569519,
      "learning_rate": 9e-05,
      "loss": 2.2517,
      "step": 9
    },
    {
      "epoch": 0.000896548289087015,
      "eval_loss": 1.023254632949829,
      "eval_runtime": 1791.5954,
      "eval_samples_per_second": 4.719,
      "eval_steps_per_second": 0.59,
      "step": 9
    },
    {
      "epoch": 0.0009961647656522388,
      "grad_norm": 0.7320921421051025,
      "learning_rate": 0.0001,
      "loss": 2.3192,
      "step": 10
    },
    {
      "epoch": 0.0010957812422174628,
      "grad_norm": 0.6750331521034241,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9599,
      "step": 11
    },
    {
      "epoch": 0.0011953977187826868,
      "grad_norm": 0.7737115025520325,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.0029,
      "step": 12
    },
    {
      "epoch": 0.0012950141953479105,
      "grad_norm": 0.7610511183738708,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.983,
      "step": 13
    },
    {
      "epoch": 0.0013946306719131345,
      "grad_norm": 0.739033043384552,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.0262,
      "step": 14
    },
    {
      "epoch": 0.0014942471484783583,
      "grad_norm": 1.2172285318374634,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.9857,
      "step": 15
    },
    {
      "epoch": 0.0015938636250435823,
      "grad_norm": 1.3501102924346924,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.0328,
      "step": 16
    },
    {
      "epoch": 0.001693480101608806,
      "grad_norm": 1.155712366104126,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.8468,
      "step": 17
    },
    {
      "epoch": 0.00179309657817403,
      "grad_norm": 0.8886969089508057,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7503,
      "step": 18
    },
    {
      "epoch": 0.00179309657817403,
      "eval_loss": 0.855793833732605,
      "eval_runtime": 1791.6889,
      "eval_samples_per_second": 4.718,
      "eval_steps_per_second": 0.59,
      "step": 18
    },
    {
      "epoch": 0.0018927130547392538,
      "grad_norm": 0.7103469967842102,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5929,
      "step": 19
    },
    {
      "epoch": 0.0019923295313044776,
      "grad_norm": 0.7840328812599182,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5679,
      "step": 20
    },
    {
      "epoch": 0.0020919460078697018,
      "grad_norm": 0.91854327917099,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.5348,
      "step": 21
    },
    {
      "epoch": 0.0021915624844349255,
      "grad_norm": 0.937053918838501,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6614,
      "step": 22
    },
    {
      "epoch": 0.0022911789610001493,
      "grad_norm": 0.7176125049591064,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.42,
      "step": 23
    },
    {
      "epoch": 0.0023907954375653735,
      "grad_norm": 0.6584264636039734,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4349,
      "step": 24
    },
    {
      "epoch": 0.0024904119141305973,
      "grad_norm": 0.8029303550720215,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5511,
      "step": 25
    },
    {
      "epoch": 0.002590028390695821,
      "grad_norm": 0.7229349613189697,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5875,
      "step": 26
    },
    {
      "epoch": 0.002689644867261045,
      "grad_norm": 0.7011633515357971,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.4422,
      "step": 27
    },
    {
      "epoch": 0.002689644867261045,
      "eval_loss": 0.8157444596290588,
      "eval_runtime": 1793.0592,
      "eval_samples_per_second": 4.715,
      "eval_steps_per_second": 0.589,
      "step": 27
    },
    {
      "epoch": 0.002789261343826269,
      "grad_norm": 0.7655370235443115,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4044,
      "step": 28
    },
    {
      "epoch": 0.002888877820391493,
      "grad_norm": 0.7056297659873962,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.2278,
      "step": 29
    },
    {
      "epoch": 0.0029884942969567166,
      "grad_norm": 0.8524144291877747,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7044,
      "step": 30
    },
    {
      "epoch": 0.0030881107735219403,
      "grad_norm": 0.8623614311218262,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.407,
      "step": 31
    },
    {
      "epoch": 0.0031877272500871645,
      "grad_norm": 0.6192923188209534,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.2924,
      "step": 32
    },
    {
      "epoch": 0.0032873437266523883,
      "grad_norm": 0.751940906047821,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4389,
      "step": 33
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 0.8193197846412659,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.6467,
      "step": 34
    },
    {
      "epoch": 0.0034865766797828363,
      "grad_norm": 0.9100502729415894,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8511,
      "step": 35
    },
    {
      "epoch": 0.00358619315634806,
      "grad_norm": 0.6470741629600525,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7999,
      "step": 36
    },
    {
      "epoch": 0.00358619315634806,
      "eval_loss": 0.7980929017066956,
      "eval_runtime": 1792.1871,
      "eval_samples_per_second": 4.717,
      "eval_steps_per_second": 0.59,
      "step": 36
    },
    {
      "epoch": 0.003685809632913284,
      "grad_norm": 0.677931010723114,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5122,
      "step": 37
    },
    {
      "epoch": 0.0037854261094785076,
      "grad_norm": 0.762718677520752,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.6601,
      "step": 38
    },
    {
      "epoch": 0.0038850425860437318,
      "grad_norm": 0.9628387689590454,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.8207,
      "step": 39
    },
    {
      "epoch": 0.003984659062608955,
      "grad_norm": 0.7539001107215881,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5463,
      "step": 40
    },
    {
      "epoch": 0.004084275539174179,
      "grad_norm": 0.8410975337028503,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.6561,
      "step": 41
    },
    {
      "epoch": 0.0041838920157394035,
      "grad_norm": 0.7135648727416992,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.7115,
      "step": 42
    },
    {
      "epoch": 0.004283508492304627,
      "grad_norm": 0.6998557448387146,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.4507,
      "step": 43
    },
    {
      "epoch": 0.004383124968869851,
      "grad_norm": 0.7283175587654114,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6081,
      "step": 44
    },
    {
      "epoch": 0.004482741445435075,
      "grad_norm": 0.8036450147628784,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5691,
      "step": 45
    },
    {
      "epoch": 0.004482741445435075,
      "eval_loss": 0.7816627025604248,
      "eval_runtime": 1792.2297,
      "eval_samples_per_second": 4.717,
      "eval_steps_per_second": 0.59,
      "step": 45
    },
    {
      "epoch": 0.004582357922000299,
      "grad_norm": 0.8214872479438782,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6442,
      "step": 46
    },
    {
      "epoch": 0.004681974398565523,
      "grad_norm": 0.7427443861961365,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.4082,
      "step": 47
    },
    {
      "epoch": 0.004781590875130747,
      "grad_norm": 0.5892370939254761,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.3837,
      "step": 48
    },
    {
      "epoch": 0.00488120735169597,
      "grad_norm": 0.8555832505226135,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.8097,
      "step": 49
    },
    {
      "epoch": 0.0049808238282611945,
      "grad_norm": 0.7236791849136353,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.6533,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.411308261965824e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}