{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 532,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018819101387908727,
      "grad_norm": 119.85382415184827,
      "learning_rate": 8.333333333333333e-07,
      "loss": 3.7563,
      "step": 10
    },
    {
      "epoch": 0.037638202775817454,
      "grad_norm": 33.81891320175042,
      "learning_rate": 1.7592592592592594e-06,
      "loss": 3.0,
      "step": 20
    },
    {
      "epoch": 0.056457304163726185,
      "grad_norm": 11.708086861495808,
      "learning_rate": 2.6851851851851856e-06,
      "loss": 1.9966,
      "step": 30
    },
    {
      "epoch": 0.07527640555163491,
      "grad_norm": 11.971367057507148,
      "learning_rate": 3.6111111111111115e-06,
      "loss": 1.6552,
      "step": 40
    },
    {
      "epoch": 0.09409550693954363,
      "grad_norm": 23.209165550861357,
      "learning_rate": 4.537037037037038e-06,
      "loss": 1.4811,
      "step": 50
    },
    {
      "epoch": 0.11291460832745237,
      "grad_norm": 9.899478278575582,
      "learning_rate": 4.998650245168965e-06,
      "loss": 1.3785,
      "step": 60
    },
    {
      "epoch": 0.13173370971536108,
      "grad_norm": 8.96121751266139,
      "learning_rate": 4.987860949769804e-06,
      "loss": 1.2907,
      "step": 70
    },
    {
      "epoch": 0.15055281110326982,
      "grad_norm": 7.298252173607856,
      "learning_rate": 4.9663289476829e-06,
      "loss": 1.2165,
      "step": 80
    },
    {
      "epoch": 0.16937191249117856,
      "grad_norm": 4.002757463166737,
      "learning_rate": 4.934147215158732e-06,
      "loss": 1.1604,
      "step": 90
    },
    {
      "epoch": 0.18819101387908727,
      "grad_norm": 3.6552314011131473,
      "learning_rate": 4.891454714510784e-06,
      "loss": 1.1411,
      "step": 100
    },
    {
      "epoch": 0.207010115266996,
      "grad_norm": 4.688923092060107,
      "learning_rate": 4.838435794069406e-06,
      "loss": 1.1315,
      "step": 110
    },
    {
      "epoch": 0.22582921665490474,
      "grad_norm": 4.575073558083306,
      "learning_rate": 4.775319392156593e-06,
      "loss": 1.1167,
      "step": 120
    },
    {
      "epoch": 0.24464831804281345,
      "grad_norm": 3.851078841596319,
      "learning_rate": 4.70237804851899e-06,
      "loss": 1.1103,
      "step": 130
    },
    {
      "epoch": 0.26346741943072216,
      "grad_norm": 3.2193694749710215,
      "learning_rate": 4.619926727487774e-06,
      "loss": 1.1076,
      "step": 140
    },
    {
      "epoch": 0.2822865208186309,
      "grad_norm": 2.8438246971893637,
      "learning_rate": 4.528321457947091e-06,
      "loss": 1.0984,
      "step": 150
    },
    {
      "epoch": 0.30110562220653964,
      "grad_norm": 3.0947911049743686,
      "learning_rate": 4.427957795983715e-06,
      "loss": 1.0917,
      "step": 160
    },
    {
      "epoch": 0.31992472359444835,
      "grad_norm": 4.227096537902385,
      "learning_rate": 4.319269116856291e-06,
      "loss": 1.0883,
      "step": 170
    },
    {
      "epoch": 0.3387438249823571,
      "grad_norm": 3.3099714841544965,
      "learning_rate": 4.2027247436595245e-06,
      "loss": 1.0899,
      "step": 180
    },
    {
      "epoch": 0.3575629263702658,
      "grad_norm": 3.074228439753722,
      "learning_rate": 4.078827920763835e-06,
      "loss": 1.0809,
      "step": 190
    },
    {
      "epoch": 0.37638202775817453,
      "grad_norm": 3.9331955228691893,
      "learning_rate": 3.948113640781265e-06,
      "loss": 1.0803,
      "step": 200
    },
    {
      "epoch": 0.3952011291460833,
      "grad_norm": 3.1687316695184595,
      "learning_rate": 3.8111463344409026e-06,
      "loss": 1.0752,
      "step": 210
    },
    {
      "epoch": 0.414020230533992,
      "grad_norm": 3.1086870103207263,
      "learning_rate": 3.668517433349069e-06,
      "loss": 1.0801,
      "step": 220
    },
    {
      "epoch": 0.4328393319219007,
      "grad_norm": 3.569818521101058,
      "learning_rate": 3.520842816158374e-06,
      "loss": 1.0737,
      "step": 230
    },
    {
      "epoch": 0.4516584333098095,
      "grad_norm": 2.821249949263903,
      "learning_rate": 3.368760149173219e-06,
      "loss": 1.0578,
      "step": 240
    },
    {
      "epoch": 0.4704775346977182,
      "grad_norm": 3.3886861570744524,
      "learning_rate": 3.212926132875141e-06,
      "loss": 1.07,
      "step": 250
    },
    {
      "epoch": 0.4892966360856269,
      "grad_norm": 3.1106639034791805,
      "learning_rate": 3.054013666257638e-06,
      "loss": 1.0513,
      "step": 260
    },
    {
      "epoch": 0.5081157374735357,
      "grad_norm": 3.2421734605805144,
      "learning_rate": 2.8927089412150176e-06,
      "loss": 1.059,
      "step": 270
    },
    {
      "epoch": 0.5269348388614443,
      "grad_norm": 2.8138590739611065,
      "learning_rate": 2.729708479531844e-06,
      "loss": 1.059,
      "step": 280
    },
    {
      "epoch": 0.5457539402493531,
      "grad_norm": 3.085937678600229,
      "learning_rate": 2.5657161252674047e-06,
      "loss": 1.0506,
      "step": 290
    },
    {
      "epoch": 0.5645730416372619,
      "grad_norm": 2.5910896828670555,
      "learning_rate": 2.4014400055222337e-06,
      "loss": 1.0458,
      "step": 300
    },
    {
      "epoch": 0.5833921430251705,
      "grad_norm": 2.711615583893317,
      "learning_rate": 2.2375894727102552e-06,
      "loss": 1.0489,
      "step": 310
    },
    {
      "epoch": 0.6022112444130793,
      "grad_norm": 2.8163698166832067,
      "learning_rate": 2.0748720415399542e-06,
      "loss": 1.0492,
      "step": 320
    },
    {
      "epoch": 0.621030345800988,
      "grad_norm": 2.396874440884708,
      "learning_rate": 1.913990333930858e-06,
      "loss": 1.0448,
      "step": 330
    },
    {
      "epoch": 0.6398494471888967,
      "grad_norm": 2.537957050013955,
      "learning_rate": 1.7556390450573213e-06,
      "loss": 1.0396,
      "step": 340
    },
    {
      "epoch": 0.6586685485768055,
      "grad_norm": 2.6769709470166068,
      "learning_rate": 1.600501943620384e-06,
      "loss": 1.0483,
      "step": 350
    },
    {
      "epoch": 0.6774876499647142,
      "grad_norm": 2.6349913820783066,
      "learning_rate": 1.4492489193006884e-06,
      "loss": 1.0441,
      "step": 360
    },
    {
      "epoch": 0.6963067513526229,
      "grad_norm": 2.496611917295113,
      "learning_rate": 1.302533090141689e-06,
      "loss": 1.0413,
      "step": 370
    },
    {
      "epoch": 0.7151258527405316,
      "grad_norm": 2.4335057884143807,
      "learning_rate": 1.1609879823536233e-06,
      "loss": 1.0397,
      "step": 380
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 2.2916566931708533,
      "learning_rate": 1.0252247947159846e-06,
      "loss": 1.0288,
      "step": 390
    },
    {
      "epoch": 0.7527640555163491,
      "grad_norm": 2.597561005712493,
      "learning_rate": 8.95829759390954e-07,
      "loss": 1.0419,
      "step": 400
    },
    {
      "epoch": 0.7715831569042578,
      "grad_norm": 2.40328918066519,
      "learning_rate": 7.733616105439077e-07,
      "loss": 1.0387,
      "step": 410
    },
    {
      "epoch": 0.7904022582921666,
      "grad_norm": 2.3994734100827197,
      "learning_rate": 6.58349171701651e-07,
      "loss": 1.036,
      "step": 420
    },
    {
      "epoch": 0.8092213596800752,
      "grad_norm": 2.2299325222354267,
      "learning_rate": 5.51289072266255e-07,
      "loss": 1.0345,
      "step": 430
    },
    {
      "epoch": 0.828040461067984,
      "grad_norm": 1.9175406133141235,
      "learning_rate": 4.5264360304473065e-07,
      "loss": 1.033,
      "step": 440
    },
    {
      "epoch": 0.8468595624558928,
      "grad_norm": 2.147736712406261,
      "learning_rate": 3.6283872005444087e-07,
      "loss": 1.0334,
      "step": 450
    },
    {
      "epoch": 0.8656786638438014,
      "grad_norm": 1.9503396710553103,
      "learning_rate": 2.8226220522394735e-07,
      "loss": 1.0358,
      "step": 460
    },
    {
      "epoch": 0.8844977652317102,
      "grad_norm": 2.205405844751076,
      "learning_rate": 2.1126199193144904e-07,
      "loss": 1.0429,
      "step": 470
    },
    {
      "epoch": 0.903316866619619,
      "grad_norm": 1.9900450300171217,
      "learning_rate": 1.5014466261124128e-07,
      "loss": 1.0368,
      "step": 480
    },
    {
      "epoch": 0.9221359680075276,
      "grad_norm": 2.0904507985722534,
      "learning_rate": 9.917412491559337e-08,
      "loss": 1.0237,
      "step": 490
    },
    {
      "epoch": 0.9409550693954364,
      "grad_norm": 2.186757730889461,
      "learning_rate": 5.8570472148445633e-08,
      "loss": 1.0242,
      "step": 500
    },
    {
      "epoch": 0.9597741707833451,
      "grad_norm": 2.2178555824642445,
      "learning_rate": 2.8509032891635146e-08,
      "loss": 1.0294,
      "step": 510
    },
    {
      "epoch": 0.9785932721712538,
      "grad_norm": 1.9581112450691653,
      "learning_rate": 9.119613927399684e-09,
      "loss": 1.0281,
      "step": 520
    },
    {
      "epoch": 0.9974123735591626,
      "grad_norm": 1.908843408243316,
      "learning_rate": 4.859397262726995e-10,
      "loss": 1.0255,
      "step": 530
    },
    {
      "epoch": 1.0,
      "step": 532,
      "total_flos": 8.800004805943624e+17,
      "train_loss": 1.198594591671363,
      "train_runtime": 17174.361,
      "train_samples_per_second": 15.841,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 532,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.800004805943624e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}