{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 200.0,
  "global_step": 370,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005405405405405406,
      "grad_norm": 3.1680717633202877,
      "learning_rate": 1.5789473684210526e-06,
      "loss": 0.6688475608825684,
      "step": 1,
      "token_acc": 0.8242903529904682
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.8549251728609573,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 0.8109264373779297,
      "step": 10,
      "token_acc": 0.7761103592601787
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.9484813990147456,
      "learning_rate": 2.9999399180697783e-05,
      "loss": 0.6205739498138427,
      "step": 20,
      "token_acc": 0.8202673243249641
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.183614904613414,
      "learning_rate": 2.9927359084964877e-05,
      "loss": 0.6088469982147217,
      "step": 30,
      "token_acc": 0.8198438348312171
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.2353384024615621,
      "learning_rate": 2.973581606123497e-05,
      "loss": 0.739194393157959,
      "step": 40,
      "token_acc": 0.7898660420316513
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.3432923315535181,
      "learning_rate": 2.942630353226844e-05,
      "loss": 0.6011062622070312,
      "step": 50,
      "token_acc": 0.8247190588471379
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 1.168183989145606,
      "learning_rate": 2.900129934114876e-05,
      "loss": 0.6731441020965576,
      "step": 60,
      "token_acc": 0.8113857485368042
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 1.2344777400050695,
      "learning_rate": 2.8464205914585212e-05,
      "loss": 0.6012222290039062,
      "step": 70,
      "token_acc": 0.8260620662270369
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.16232118124639,
      "learning_rate": 2.7819323024340304e-05,
      "loss": 0.6182085990905761,
      "step": 80,
      "token_acc": 0.8235405045953511
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 0.9498735816994268,
      "learning_rate": 2.7071813364843832e-05,
      "loss": 0.59684157371521,
      "step": 90,
      "token_acc": 0.8311607063059382
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.8108342228004247,
      "learning_rate": 2.6227661222566516e-05,
      "loss": 0.6133281230926514,
      "step": 100,
      "token_acc": 0.8260576887809151
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 1.2084724906810802,
      "learning_rate": 2.5293624568031008e-05,
      "loss": 0.5700843811035157,
      "step": 110,
      "token_acc": 0.8353099803946354
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.1407595512042275,
      "learning_rate": 2.4277180953993826e-05,
      "loss": 0.585970115661621,
      "step": 120,
      "token_acc": 0.8267323572461026
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 1.230613842801466,
      "learning_rate": 2.318646765291757e-05,
      "loss": 0.6366302967071533,
      "step": 130,
      "token_acc": 0.8218803207769427
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 1.2394471459646628,
      "learning_rate": 2.2030216512970554e-05,
      "loss": 0.5958713531494141,
      "step": 140,
      "token_acc": 0.8305702226808576
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 1.1136999131785847,
      "learning_rate": 2.0817684054072827e-05,
      "loss": 0.7051344871520996,
      "step": 150,
      "token_acc": 0.7948495053253495
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.953872013030958,
      "learning_rate": 1.9558577363613704e-05,
      "loss": 0.5482869148254395,
      "step": 160,
      "token_acc": 0.8431717927114541
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 1.1211814795042592,
      "learning_rate": 1.826297638509251e-05,
      "loss": 0.6120530128479004,
      "step": 170,
      "token_acc": 0.825810897386503
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 1.0724707419323103,
      "learning_rate": 1.694125322181083e-05,
      "loss": 0.6729551792144776,
      "step": 180,
      "token_acc": 0.809713255234503
    },
    {
      "epoch": 1.027027027027027,
      "grad_norm": 0.9017702538446655,
      "learning_rate": 1.5603989101641228e-05,
      "loss": 0.49294071197509765,
      "step": 190,
      "token_acc": 0.8595634401529221
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.8357826808926182,
      "learning_rate": 1.4261889667621828e-05,
      "loss": 0.30256004333496095,
      "step": 200,
      "token_acc": 0.9047140790097637
    },
    {
      "epoch": 1.135135135135135,
      "grad_norm": 1.3306024060830839,
      "learning_rate": 1.2925699272529006e-05,
      "loss": 0.28004865646362304,
      "step": 210,
      "token_acc": 0.9124356333016044
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 1.0315509694012732,
      "learning_rate": 1.1606114963554171e-05,
      "loss": 0.28960094451904295,
      "step": 220,
      "token_acc": 0.9050426736039798
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 0.897647555480616,
      "learning_rate": 1.0313700845691636e-05,
      "loss": 0.24299814701080322,
      "step": 230,
      "token_acc": 0.9234494029347422
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 1.0238680932300175,
      "learning_rate": 9.058803509412647e-06,
      "loss": 0.2083221435546875,
      "step": 240,
      "token_acc": 0.9324800906289405
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 0.8507949565744011,
      "learning_rate": 7.851469199680382e-06,
      "loss": 0.27800228595733645,
      "step": 250,
      "token_acc": 0.9101957597480809
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.9239797828529825,
      "learning_rate": 6.701363389420296e-06,
      "loss": 0.257454514503479,
      "step": 260,
      "token_acc": 0.9200535757981635
    },
    {
      "epoch": 1.4594594594594594,
      "grad_norm": 0.8289302773930988,
      "learning_rate": 5.617693401310837e-06,
      "loss": 0.2699479103088379,
      "step": 270,
      "token_acc": 0.9118848637175058
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 1.4264660137512906,
      "learning_rate": 4.609134697356009e-06,
      "loss": 0.25818724632263185,
      "step": 280,
      "token_acc": 0.9165730954889045
    },
    {
      "epoch": 1.5675675675675675,
      "grad_norm": 0.6809121084776086,
      "learning_rate": 3.683761426338148e-06,
      "loss": 0.2499394655227661,
      "step": 290,
      "token_acc": 0.9210303247829308
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.7911442310830548,
      "learning_rate": 2.848981785162503e-06,
      "loss": 0.2243581771850586,
      "step": 300,
      "token_acc": 0.9255768284539416
    },
    {
      "epoch": 1.6756756756756757,
      "grad_norm": 0.8302748471075124,
      "learning_rate": 2.1114787115667476e-06,
      "loss": 0.2524730205535889,
      "step": 310,
      "token_acc": 0.9196754182044243
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.7652465806020483,
      "learning_rate": 1.4771563829877598e-06,
      "loss": 0.21740343570709228,
      "step": 320,
      "token_acc": 0.9257807174001964
    },
    {
      "epoch": 1.7837837837837838,
      "grad_norm": 0.6723695635268157,
      "learning_rate": 9.51092949895927e-07,
      "loss": 0.29862112998962403,
      "step": 330,
      "token_acc": 0.9064944202025343
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 0.7836833639138061,
      "learning_rate": 5.374998819965654e-07,
      "loss": 0.2673323154449463,
      "step": 340,
      "token_acc": 0.9137580442481246
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 0.8148712923768102,
      "learning_rate": 2.3968825275764774e-07,
      "loss": 0.2481457471847534,
      "step": 350,
      "token_acc": 0.9221015450205239
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 1.055375940725962,
      "learning_rate": 6.00422321775751e-08,
      "loss": 0.2384178876876831,
      "step": 360,
      "token_acc": 0.9246336357292394
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9495217159079454,
      "learning_rate": 0.0,
      "loss": 0.22227826118469238,
      "step": 370,
      "token_acc": 0.9248096999252118
    }
  ],
  "logging_steps": 10,
  "max_steps": 370,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 163536917889024.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}