{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999973634949511,
  "eval_steps": 500,
  "global_step": 9482,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02109204039125735,
      "grad_norm": 0.40668317675590515,
      "learning_rate": 4.994568013593584e-05,
      "loss": 0.947,
      "num_input_tokens_seen": 44211392,
      "step": 200
    },
    {
      "epoch": 0.0421840807825147,
      "grad_norm": 0.5519078373908997,
      "learning_rate": 4.9781866145835606e-05,
      "loss": 0.7951,
      "num_input_tokens_seen": 88542848,
      "step": 400
    },
    {
      "epoch": 0.06327612117377204,
      "grad_norm": 0.7488412857055664,
      "learning_rate": 4.950927569562368e-05,
      "loss": 0.7381,
      "num_input_tokens_seen": 132711296,
      "step": 600
    },
    {
      "epoch": 0.0843681615650294,
      "grad_norm": 0.8657649159431458,
      "learning_rate": 4.912910528212802e-05,
      "loss": 0.706,
      "num_input_tokens_seen": 177102464,
      "step": 800
    },
    {
      "epoch": 0.10546020195628675,
      "grad_norm": 0.835016131401062,
      "learning_rate": 4.864302360905221e-05,
      "loss": 0.6805,
      "num_input_tokens_seen": 221189952,
      "step": 1000
    },
    {
      "epoch": 0.12655224234754409,
      "grad_norm": 0.8248361945152283,
      "learning_rate": 4.8053164262439e-05,
      "loss": 0.6578,
      "num_input_tokens_seen": 265373568,
      "step": 1200
    },
    {
      "epoch": 0.14764428273880145,
      "grad_norm": 0.9251222014427185,
      "learning_rate": 4.736211634559929e-05,
      "loss": 0.645,
      "num_input_tokens_seen": 309590976,
      "step": 1400
    },
    {
      "epoch": 0.1687363231300588,
      "grad_norm": 1.0570456981658936,
      "learning_rate": 4.657291311461312e-05,
      "loss": 0.6295,
      "num_input_tokens_seen": 353823104,
      "step": 1600
    },
    {
      "epoch": 0.18982836352131616,
      "grad_norm": 0.8825539350509644,
      "learning_rate": 4.5689018664285547e-05,
      "loss": 0.6153,
      "num_input_tokens_seen": 397997888,
      "step": 1800
    },
    {
      "epoch": 0.2109204039125735,
      "grad_norm": 0.9760900735855103,
      "learning_rate": 4.471431272299751e-05,
      "loss": 0.6042,
      "num_input_tokens_seen": 442188672,
      "step": 2000
    },
    {
      "epoch": 0.23201244430383083,
      "grad_norm": 0.95518559217453,
      "learning_rate": 4.365307362319256e-05,
      "loss": 0.5945,
      "num_input_tokens_seen": 486364032,
      "step": 2200
    },
    {
      "epoch": 0.25310448469508817,
      "grad_norm": 0.9054489135742188,
      "learning_rate": 4.2509959522247934e-05,
      "loss": 0.5865,
      "num_input_tokens_seen": 530501120,
      "step": 2400
    },
    {
      "epoch": 0.27419652508634557,
      "grad_norm": 1.0242657661437988,
      "learning_rate": 4.128998795615841e-05,
      "loss": 0.58,
      "num_input_tokens_seen": 574837120,
      "step": 2600
    },
    {
      "epoch": 0.2952885654776029,
      "grad_norm": 1.1412681341171265,
      "learning_rate": 3.999851381577905e-05,
      "loss": 0.5707,
      "num_input_tokens_seen": 618964480,
      "step": 2800
    },
    {
      "epoch": 0.31638060586886024,
      "grad_norm": 1.0616246461868286,
      "learning_rate": 3.864120584229707e-05,
      "loss": 0.5639,
      "num_input_tokens_seen": 663315776,
      "step": 3000
    },
    {
      "epoch": 0.3374726462601176,
      "grad_norm": 1.0734329223632812,
      "learning_rate": 3.722402174510236e-05,
      "loss": 0.5597,
      "num_input_tokens_seen": 707722240,
      "step": 3200
    },
    {
      "epoch": 0.3585646866513749,
      "grad_norm": 1.0842781066894531,
      "learning_rate": 3.5753182051273594e-05,
      "loss": 0.5533,
      "num_input_tokens_seen": 751884864,
      "step": 3400
    },
    {
      "epoch": 0.3796567270426323,
      "grad_norm": 1.0658433437347412,
      "learning_rate": 3.423514280146341e-05,
      "loss": 0.5442,
      "num_input_tokens_seen": 796284224,
      "step": 3600
    },
    {
      "epoch": 0.40074876743388965,
      "grad_norm": 1.0794566869735718,
      "learning_rate": 3.267656721203064e-05,
      "loss": 0.542,
      "num_input_tokens_seen": 840569728,
      "step": 3800
    },
    {
      "epoch": 0.421840807825147,
      "grad_norm": 1.2425159215927124,
      "learning_rate": 3.108429642780421e-05,
      "loss": 0.5361,
      "num_input_tokens_seen": 884788608,
      "step": 4000
    },
    {
      "epoch": 0.44293284821640433,
      "grad_norm": 1.080336332321167,
      "learning_rate": 2.9465319493855552e-05,
      "loss": 0.531,
      "num_input_tokens_seen": 929015680,
      "step": 4200
    },
    {
      "epoch": 0.46402488860766167,
      "grad_norm": 1.1406266689300537,
      "learning_rate": 2.7826742678084e-05,
      "loss": 0.5287,
      "num_input_tokens_seen": 973320448,
      "step": 4400
    },
    {
      "epoch": 0.485116928998919,
      "grad_norm": 1.081685185432434,
      "learning_rate": 2.6175758279269303e-05,
      "loss": 0.521,
      "num_input_tokens_seen": 1017647040,
      "step": 4600
    },
    {
      "epoch": 0.5062089693901763,
      "grad_norm": 1.0887905359268188,
      "learning_rate": 2.451961305750393e-05,
      "loss": 0.5184,
      "num_input_tokens_seen": 1061997888,
      "step": 4800
    },
    {
      "epoch": 0.5273010097814337,
      "grad_norm": 1.0519535541534424,
      "learning_rate": 2.2865576425575215e-05,
      "loss": 0.5141,
      "num_input_tokens_seen": 1106436416,
      "step": 5000
    },
    {
      "epoch": 0.5483930501726911,
      "grad_norm": 1.1306272745132446,
      "learning_rate": 2.122090854091672e-05,
      "loss": 0.5101,
      "num_input_tokens_seen": 1150734720,
      "step": 5200
    },
    {
      "epoch": 0.5694850905639485,
      "grad_norm": 1.2493129968643188,
      "learning_rate": 1.9592828438184685e-05,
      "loss": 0.5068,
      "num_input_tokens_seen": 1195030080,
      "step": 5400
    },
    {
      "epoch": 0.5905771309552058,
      "grad_norm": 1.1448969841003418,
      "learning_rate": 1.7988482342336927e-05,
      "loss": 0.5012,
      "num_input_tokens_seen": 1239434432,
      "step": 5600
    },
    {
      "epoch": 0.6116691713464631,
      "grad_norm": 1.1951446533203125,
      "learning_rate": 1.6414912301299696e-05,
      "loss": 0.5006,
      "num_input_tokens_seen": 1283707776,
      "step": 5800
    },
    {
      "epoch": 0.6327612117377205,
      "grad_norm": 1.19136381149292,
      "learning_rate": 1.4879025275904534e-05,
      "loss": 0.4975,
      "num_input_tokens_seen": 1327901312,
      "step": 6000
    },
    {
      "epoch": 0.6538532521289778,
      "grad_norm": 1.2069401741027832,
      "learning_rate": 1.3387562822770727e-05,
      "loss": 0.4938,
      "num_input_tokens_seen": 1372311040,
      "step": 6200
    },
    {
      "epoch": 0.6749452925202352,
      "grad_norm": 1.2452600002288818,
      "learning_rate": 1.194707150320592e-05,
      "loss": 0.4925,
      "num_input_tokens_seen": 1416523904,
      "step": 6400
    },
    {
      "epoch": 0.6960373329114925,
      "grad_norm": 1.3586419820785522,
      "learning_rate": 1.0563874148010725e-05,
      "loss": 0.4888,
      "num_input_tokens_seen": 1460803456,
      "step": 6600
    },
    {
      "epoch": 0.7171293733027498,
      "grad_norm": 1.186355471611023,
      "learning_rate": 9.244042104316522e-06,
      "loss": 0.4858,
      "num_input_tokens_seen": 1505213888,
      "step": 6800
    },
    {
      "epoch": 0.7382214136940072,
      "grad_norm": 1.15864896774292,
      "learning_rate": 7.993368586274711e-06,
      "loss": 0.4834,
      "num_input_tokens_seen": 1549483328,
      "step": 7000
    },
    {
      "epoch": 0.7593134540852646,
      "grad_norm": 1.2812916040420532,
      "learning_rate": 6.817343246571176e-06,
      "loss": 0.483,
      "num_input_tokens_seen": 1593631168,
      "step": 7200
    },
    {
      "epoch": 0.780405494476522,
      "grad_norm": 1.3027392625808716,
      "learning_rate": 5.7211280803801945e-06,
      "loss": 0.4826,
      "num_input_tokens_seen": 1637873600,
      "step": 7400
    },
    {
      "epoch": 0.8014975348677793,
      "grad_norm": 1.2680199146270752,
      "learning_rate": 4.7095347675243015e-06,
      "loss": 0.4799,
      "num_input_tokens_seen": 1682312384,
      "step": 7600
    },
    {
      "epoch": 0.8225895752590366,
      "grad_norm": 1.323339819908142,
      "learning_rate": 3.7870035522933416e-06,
      "loss": 0.4776,
      "num_input_tokens_seen": 1726473216,
      "step": 7800
    },
    {
      "epoch": 0.843681615650294,
      "grad_norm": 1.3831522464752197,
      "learning_rate": 2.9575837536265804e-06,
      "loss": 0.4783,
      "num_input_tokens_seen": 1770914880,
      "step": 8000
    },
    {
      "epoch": 0.8647736560415513,
      "grad_norm": 1.3245904445648193,
      "learning_rate": 2.2249159912059698e-06,
      "loss": 0.4757,
      "num_input_tokens_seen": 1815006528,
      "step": 8200
    },
    {
      "epoch": 0.8858656964328087,
      "grad_norm": 1.2998374700546265,
      "learning_rate": 1.592216205476227e-06,
      "loss": 0.4747,
      "num_input_tokens_seen": 1859331136,
      "step": 8400
    },
    {
      "epoch": 0.906957736824066,
      "grad_norm": 1.2577829360961914,
      "learning_rate": 1.0622615417338333e-06,
      "loss": 0.474,
      "num_input_tokens_seen": 1903616448,
      "step": 8600
    },
    {
      "epoch": 0.9280497772153233,
      "grad_norm": 1.3561482429504395,
      "learning_rate": 6.373781602446283e-07,
      "loss": 0.4727,
      "num_input_tokens_seen": 1947822592,
      "step": 8800
    },
    {
      "epoch": 0.9491418176065807,
      "grad_norm": 1.2875652313232422,
      "learning_rate": 3.194310258956973e-07,
      "loss": 0.473,
      "num_input_tokens_seen": 1992285376,
      "step": 9000
    },
    {
      "epoch": 0.970233857997838,
      "grad_norm": 1.2597335577011108,
      "learning_rate": 1.0981572219854463e-07,
      "loss": 0.475,
      "num_input_tokens_seen": 2036784768,
      "step": 9200
    },
    {
      "epoch": 0.9913258983890955,
      "grad_norm": 1.3087178468704224,
      "learning_rate": 9.452325574654808e-09,
      "loss": 0.4727,
      "num_input_tokens_seen": 2080910400,
      "step": 9400
    },
    {
      "epoch": 0.999973634949511,
      "num_input_tokens_seen": 2098994560,
      "step": 9482,
      "total_flos": 4.036532744878576e+20,
      "train_loss": 0.5513084518635382,
      "train_runtime": 186000.3322,
      "train_samples_per_second": 13.051,
      "train_steps_per_second": 0.051
    }
  ],
  "logging_steps": 200,
  "max_steps": 9482,
  "num_input_tokens_seen": 2098994560,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.036532744878576e+20,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}