{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9964699949571356,
  "eval_steps": 500,
  "global_step": 247,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004034291477559254,
      "grad_norm": 0.10618364810943604,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8761,
      "mean_token_accuracy": 0.7515642121434212,
      "step": 1
    },
    {
      "epoch": 0.020171457387796268,
      "grad_norm": 0.1208970844745636,
      "learning_rate": 4e-05,
      "loss": 0.9213,
      "mean_token_accuracy": 0.7374346107244492,
      "step": 5
    },
    {
      "epoch": 0.040342914775592535,
      "grad_norm": 0.09196259081363678,
      "learning_rate": 8e-05,
      "loss": 0.8914,
      "mean_token_accuracy": 0.7460352770984173,
      "step": 10
    },
    {
      "epoch": 0.060514372163388806,
      "grad_norm": 0.10933861136436462,
      "learning_rate": 0.00012,
      "loss": 0.8602,
      "mean_token_accuracy": 0.7503265753388405,
      "step": 15
    },
    {
      "epoch": 0.08068582955118507,
      "grad_norm": 0.11680758744478226,
      "learning_rate": 0.00016,
      "loss": 0.8439,
      "mean_token_accuracy": 0.7499923676252365,
      "step": 20
    },
    {
      "epoch": 0.10085728693898134,
      "grad_norm": 0.0951286181807518,
      "learning_rate": 0.0002,
      "loss": 0.7772,
      "mean_token_accuracy": 0.7655725114047527,
      "step": 25
    },
    {
      "epoch": 0.12102874432677761,
      "grad_norm": 0.08053945004940033,
      "learning_rate": 0.00019974977965945,
      "loss": 0.7238,
      "mean_token_accuracy": 0.7779346205294132,
      "step": 30
    },
    {
      "epoch": 0.14120020171457387,
      "grad_norm": 0.08780888468027115,
      "learning_rate": 0.00019900037084217637,
      "loss": 0.6863,
      "mean_token_accuracy": 0.7845150113105774,
      "step": 35
    },
    {
      "epoch": 0.16137165910237014,
      "grad_norm": 0.08427116274833679,
      "learning_rate": 0.00019775552389476864,
      "loss": 0.6315,
      "mean_token_accuracy": 0.7988936014473438,
      "step": 40
    },
    {
      "epoch": 0.1815431164901664,
      "grad_norm": 0.08954589813947678,
      "learning_rate": 0.00019602146853776894,
      "loss": 0.617,
      "mean_token_accuracy": 0.8002350099384785,
      "step": 45
    },
    {
      "epoch": 0.20171457387796268,
      "grad_norm": 0.09293227642774582,
      "learning_rate": 0.0001938068826896166,
      "loss": 0.5883,
      "mean_token_accuracy": 0.8079691044986248,
      "step": 50
    },
    {
      "epoch": 0.22188603126575895,
      "grad_norm": 0.09921843558549881,
      "learning_rate": 0.0001911228490388136,
      "loss": 0.5817,
      "mean_token_accuracy": 0.8088557526469231,
      "step": 55
    },
    {
      "epoch": 0.24205748865355523,
      "grad_norm": 0.11710495501756668,
      "learning_rate": 0.00018798279958164295,
      "loss": 0.5737,
      "mean_token_accuracy": 0.809910261631012,
      "step": 60
    },
    {
      "epoch": 0.2622289460413515,
      "grad_norm": 0.10755322873592377,
      "learning_rate": 0.00018440244840299506,
      "loss": 0.567,
      "mean_token_accuracy": 0.8104779615998268,
      "step": 65
    },
    {
      "epoch": 0.28240040342914774,
      "grad_norm": 0.12730592489242554,
      "learning_rate": 0.00018039971303669407,
      "loss": 0.5546,
      "mean_token_accuracy": 0.8143862128257752,
      "step": 70
    },
    {
      "epoch": 0.30257186081694404,
      "grad_norm": 0.12127107381820679,
      "learning_rate": 0.00017599462479886974,
      "loss": 0.5522,
      "mean_token_accuracy": 0.8144258864223957,
      "step": 75
    },
    {
      "epoch": 0.3227433182047403,
      "grad_norm": 0.11108188331127167,
      "learning_rate": 0.00017120922854310257,
      "loss": 0.5305,
      "mean_token_accuracy": 0.8214686810970306,
      "step": 80
    },
    {
      "epoch": 0.3429147755925366,
      "grad_norm": 0.11264903098344803,
      "learning_rate": 0.00016606747233900815,
      "loss": 0.5398,
      "mean_token_accuracy": 0.8181388042867184,
      "step": 85
    },
    {
      "epoch": 0.3630862329803328,
      "grad_norm": 0.1377757340669632,
      "learning_rate": 0.00016059508762635482,
      "loss": 0.532,
      "mean_token_accuracy": 0.8195081010460854,
      "step": 90
    },
    {
      "epoch": 0.3832576903681291,
      "grad_norm": 0.12057465314865112,
      "learning_rate": 0.00015481946044447099,
      "loss": 0.5238,
      "mean_token_accuracy": 0.8215388789772987,
      "step": 95
    },
    {
      "epoch": 0.40342914775592537,
      "grad_norm": 0.11411843448877335,
      "learning_rate": 0.00014876949438136347,
      "loss": 0.5285,
      "mean_token_accuracy": 0.819812896847725,
      "step": 100
    },
    {
      "epoch": 0.4236006051437216,
      "grad_norm": 0.12218334525823593,
      "learning_rate": 0.0001424754659284048,
      "loss": 0.5178,
      "mean_token_accuracy": 0.8232251830399037,
      "step": 105
    },
    {
      "epoch": 0.4437720625315179,
      "grad_norm": 0.12559793889522552,
      "learning_rate": 0.0001359688729644536,
      "loss": 0.5269,
      "mean_token_accuracy": 0.8201104834675789,
      "step": 110
    },
    {
      "epoch": 0.46394351991931415,
      "grad_norm": 0.14769871532917023,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.5203,
      "mean_token_accuracy": 0.8221889816224575,
      "step": 115
    },
    {
      "epoch": 0.48411497730711045,
      "grad_norm": 0.1480661779642105,
      "learning_rate": 0.00012244914086375724,
      "loss": 0.523,
      "mean_token_accuracy": 0.8210825860500336,
      "step": 120
    },
    {
      "epoch": 0.5042864346949067,
      "grad_norm": 0.14564430713653564,
      "learning_rate": 0.00011550365996641979,
      "loss": 0.5074,
      "mean_token_accuracy": 0.8264268651604653,
      "step": 125
    },
    {
      "epoch": 0.524457892082703,
      "grad_norm": 0.13270238041877747,
      "learning_rate": 0.00010848059244755093,
      "loss": 0.5092,
      "mean_token_accuracy": 0.8253403089940547,
      "step": 130
    },
    {
      "epoch": 0.5446293494704992,
      "grad_norm": 0.11992616951465607,
      "learning_rate": 0.00010141508459407623,
      "loss": 0.5012,
      "mean_token_accuracy": 0.8276812911033631,
      "step": 135
    },
    {
      "epoch": 0.5648008068582955,
      "grad_norm": 0.14025390148162842,
      "learning_rate": 9.434249508162076e-05,
      "loss": 0.5128,
      "mean_token_accuracy": 0.8234357766807079,
      "step": 140
    },
    {
      "epoch": 0.5849722642460918,
      "grad_norm": 0.11215393245220184,
      "learning_rate": 8.729821802531212e-05,
      "loss": 0.5133,
      "mean_token_accuracy": 0.8236173823475837,
      "step": 145
    },
    {
      "epoch": 0.6051437216338881,
      "grad_norm": 0.11705436557531357,
      "learning_rate": 8.031750585322947e-05,
      "loss": 0.5053,
      "mean_token_accuracy": 0.8257141962647438,
      "step": 150
    },
    {
      "epoch": 0.6253151790216843,
      "grad_norm": 0.12025938928127289,
      "learning_rate": 7.343529288891239e-05,
      "loss": 0.4955,
      "mean_token_accuracy": 0.8292319044470787,
      "step": 155
    },
    {
      "epoch": 0.6454866364094806,
      "grad_norm": 0.11226729303598404,
      "learning_rate": 6.668602052579424e-05,
      "loss": 0.4939,
      "mean_token_accuracy": 0.8295842953026294,
      "step": 160
    },
    {
      "epoch": 0.6656580937972768,
      "grad_norm": 0.10537487268447876,
      "learning_rate": 6.010346486845837e-05,
      "loss": 0.4907,
      "mean_token_accuracy": 0.8306830637156963,
      "step": 165
    },
    {
      "epoch": 0.6858295511850732,
      "grad_norm": 0.1326971799135208,
      "learning_rate": 5.372056770327013e-05,
      "loss": 0.4994,
      "mean_token_accuracy": 0.8274142310023308,
      "step": 170
    },
    {
      "epoch": 0.7060010085728694,
      "grad_norm": 0.0996076837182045,
      "learning_rate": 4.756927164427685e-05,
      "loss": 0.4973,
      "mean_token_accuracy": 0.8285726100206375,
      "step": 175
    },
    {
      "epoch": 0.7261724659606656,
      "grad_norm": 0.10915440320968628,
      "learning_rate": 4.168036027937267e-05,
      "loss": 0.4987,
      "mean_token_accuracy": 0.8276034623384476,
      "step": 180
    },
    {
      "epoch": 0.7463439233484619,
      "grad_norm": 0.10033515840768814,
      "learning_rate": 3.6083304116701535e-05,
      "loss": 0.4946,
      "mean_token_accuracy": 0.8296850137412548,
      "step": 185
    },
    {
      "epoch": 0.7665153807362582,
      "grad_norm": 0.10720834881067276,
      "learning_rate": 3.080611310224539e-05,
      "loss": 0.4952,
      "mean_token_accuracy": 0.8289067208766937,
      "step": 190
    },
    {
      "epoch": 0.7866868381240545,
      "grad_norm": 0.11353600770235062,
      "learning_rate": 2.587519644666001e-05,
      "loss": 0.4978,
      "mean_token_accuracy": 0.8272387310862541,
      "step": 195
    },
    {
      "epoch": 0.8068582955118507,
      "grad_norm": 0.09966889768838882,
      "learning_rate": 2.1315230462840985e-05,
      "loss": 0.4993,
      "mean_token_accuracy": 0.8278293192386628,
      "step": 200
    },
    {
      "epoch": 0.827029752899647,
      "grad_norm": 0.10758362710475922,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 0.5055,
      "mean_token_accuracy": 0.8247546002268791,
      "step": 205
    },
    {
      "epoch": 0.8472012102874432,
      "grad_norm": 0.09960389137268066,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.4822,
      "mean_token_accuracy": 0.8327905587852001,
      "step": 210
    },
    {
      "epoch": 0.8673726676752396,
      "grad_norm": 0.10244999825954437,
      "learning_rate": 1.0079278510416313e-05,
      "loss": 0.4894,
      "mean_token_accuracy": 0.8305548712611198,
      "step": 215
    },
    {
      "epoch": 0.8875441250630358,
      "grad_norm": 0.09608753025531769,
      "learning_rate": 7.211097270349066e-06,
      "loss": 0.4998,
      "mean_token_accuracy": 0.8276750639081001,
      "step": 220
    },
    {
      "epoch": 0.9077155824508321,
      "grad_norm": 0.09114421159029007,
      "learning_rate": 4.807269447087348e-06,
      "loss": 0.4985,
      "mean_token_accuracy": 0.827449332177639,
      "step": 225
    },
    {
      "epoch": 0.9278870398386283,
      "grad_norm": 0.09354618191719055,
      "learning_rate": 2.8798247729623806e-06,
      "loss": 0.493,
      "mean_token_accuracy": 0.8297582663595676,
      "step": 230
    },
    {
      "epoch": 0.9480584972264247,
      "grad_norm": 0.09092767536640167,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 0.4887,
      "mean_token_accuracy": 0.8308509282767773,
      "step": 235
    },
    {
      "epoch": 0.9682299546142209,
      "grad_norm": 0.09328487515449524,
      "learning_rate": 4.902354549733978e-07,
      "loss": 0.4923,
      "mean_token_accuracy": 0.8295751377940178,
      "step": 240
    },
    {
      "epoch": 0.9884014120020171,
      "grad_norm": 0.09508884698152542,
      "learning_rate": 4.0049288167842705e-08,
      "loss": 0.5046,
      "mean_token_accuracy": 0.825819493830204,
      "step": 245
    },
    {
      "epoch": 0.9964699949571356,
      "mean_token_accuracy": 0.825654674321413,
      "step": 247,
      "total_flos": 2.5792410000818176e+17,
      "train_loss": 0.5621715438993353,
      "train_runtime": 8702.0895,
      "train_samples_per_second": 0.456,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 5,
  "max_steps": 247,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5792410000818176e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}