{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991532599491956,
  "eval_steps": 500,
  "global_step": 295,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01693480101608806,
      "grad_norm": 11.07681941986084,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.8357,
      "step": 5
    },
    {
      "epoch": 0.03386960203217612,
      "grad_norm": 4.368485450744629,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.6208,
      "step": 10
    },
    {
      "epoch": 0.05080440304826418,
      "grad_norm": 2.597416877746582,
      "learning_rate": 1e-05,
      "loss": 1.2437,
      "step": 15
    },
    {
      "epoch": 0.06773920406435224,
      "grad_norm": 2.159755229949951,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.9804,
      "step": 20
    },
    {
      "epoch": 0.0846740050804403,
      "grad_norm": 1.7200169563293457,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8607,
      "step": 25
    },
    {
      "epoch": 0.10160880609652836,
      "grad_norm": 1.2486546039581299,
      "learning_rate": 2e-05,
      "loss": 0.7869,
      "step": 30
    },
    {
      "epoch": 0.11854360711261643,
      "grad_norm": 1.2447178363800049,
      "learning_rate": 1.9982437317643218e-05,
      "loss": 0.7324,
      "step": 35
    },
    {
      "epoch": 0.1354784081287045,
      "grad_norm": 1.129758358001709,
      "learning_rate": 1.992981096013517e-05,
      "loss": 0.7058,
      "step": 40
    },
    {
      "epoch": 0.15241320914479256,
      "grad_norm": 0.9256328344345093,
      "learning_rate": 1.984230577947597e-05,
      "loss": 0.6845,
      "step": 45
    },
    {
      "epoch": 0.1693480101608806,
      "grad_norm": 0.9811558723449707,
      "learning_rate": 1.972022914080411e-05,
      "loss": 0.6698,
      "step": 50
    },
    {
      "epoch": 0.18628281117696868,
      "grad_norm": 1.0069135427474976,
      "learning_rate": 1.9564009842765225e-05,
      "loss": 0.6393,
      "step": 55
    },
    {
      "epoch": 0.20321761219305673,
      "grad_norm": 0.9143001437187195,
      "learning_rate": 1.9374196611341212e-05,
      "loss": 0.6321,
      "step": 60
    },
    {
      "epoch": 0.2201524132091448,
      "grad_norm": 0.9945001006126404,
      "learning_rate": 1.9151456172430186e-05,
      "loss": 0.6286,
      "step": 65
    },
    {
      "epoch": 0.23708721422523285,
      "grad_norm": 0.9755650758743286,
      "learning_rate": 1.8896570909947477e-05,
      "loss": 0.6178,
      "step": 70
    },
    {
      "epoch": 0.2540220152413209,
      "grad_norm": 0.9144276976585388,
      "learning_rate": 1.8610436117673557e-05,
      "loss": 0.6204,
      "step": 75
    },
    {
      "epoch": 0.270956816257409,
      "grad_norm": 0.9252317547798157,
      "learning_rate": 1.829405685450202e-05,
      "loss": 0.6124,
      "step": 80
    },
    {
      "epoch": 0.28789161727349705,
      "grad_norm": 0.7833272218704224,
      "learning_rate": 1.7948544414133534e-05,
      "loss": 0.5958,
      "step": 85
    },
    {
      "epoch": 0.3048264182895851,
      "grad_norm": 0.8833147883415222,
      "learning_rate": 1.7575112421616203e-05,
      "loss": 0.6049,
      "step": 90
    },
    {
      "epoch": 0.32176121930567314,
      "grad_norm": 0.8253676295280457,
      "learning_rate": 1.717507257044331e-05,
      "loss": 0.5905,
      "step": 95
    },
    {
      "epoch": 0.3386960203217612,
      "grad_norm": 0.800396740436554,
      "learning_rate": 1.6749830015182106e-05,
      "loss": 0.5698,
      "step": 100
    },
    {
      "epoch": 0.3556308213378493,
      "grad_norm": 0.9177567362785339,
      "learning_rate": 1.6300878435817115e-05,
      "loss": 0.5787,
      "step": 105
    },
    {
      "epoch": 0.37256562235393736,
      "grad_norm": 0.8931817412376404,
      "learning_rate": 1.5829794791144723e-05,
      "loss": 0.5748,
      "step": 110
    },
    {
      "epoch": 0.3895004233700254,
      "grad_norm": 1.0776097774505615,
      "learning_rate": 1.533823377964791e-05,
      "loss": 0.5693,
      "step": 115
    },
    {
      "epoch": 0.40643522438611346,
      "grad_norm": 0.9571148157119751,
      "learning_rate": 1.482792202730745e-05,
      "loss": 0.5795,
      "step": 120
    },
    {
      "epoch": 0.42337002540220153,
      "grad_norm": 0.9276224970817566,
      "learning_rate": 1.4300652022765207e-05,
      "loss": 0.5744,
      "step": 125
    },
    {
      "epoch": 0.4403048264182896,
      "grad_norm": 0.8562670350074768,
      "learning_rate": 1.3758275821142382e-05,
      "loss": 0.574,
      "step": 130
    },
    {
      "epoch": 0.4572396274343776,
      "grad_norm": 0.987328827381134,
      "learning_rate": 1.3202698538628376e-05,
      "loss": 0.5612,
      "step": 135
    },
    {
      "epoch": 0.4741744284504657,
      "grad_norm": 0.7609542012214661,
      "learning_rate": 1.2635871660690677e-05,
      "loss": 0.5608,
      "step": 140
    },
    {
      "epoch": 0.4911092294665538,
      "grad_norm": 0.752984881401062,
      "learning_rate": 1.2059786187410984e-05,
      "loss": 0.5462,
      "step": 145
    },
    {
      "epoch": 0.5080440304826418,
      "grad_norm": 0.7577420473098755,
      "learning_rate": 1.1476465640024814e-05,
      "loss": 0.5565,
      "step": 150
    },
    {
      "epoch": 0.5249788314987299,
      "grad_norm": 0.7515721321105957,
      "learning_rate": 1.0887958953229349e-05,
      "loss": 0.5475,
      "step": 155
    },
    {
      "epoch": 0.541913632514818,
      "grad_norm": 0.7427639961242676,
      "learning_rate": 1.0296333278225599e-05,
      "loss": 0.5561,
      "step": 160
    },
    {
      "epoch": 0.558848433530906,
      "grad_norm": 0.8810573816299438,
      "learning_rate": 9.703666721774403e-06,
      "loss": 0.5391,
      "step": 165
    },
    {
      "epoch": 0.5757832345469941,
      "grad_norm": 0.7623007297515869,
      "learning_rate": 9.112041046770653e-06,
      "loss": 0.5504,
      "step": 170
    },
    {
      "epoch": 0.5927180355630821,
      "grad_norm": 0.7749871015548706,
      "learning_rate": 8.52353435997519e-06,
      "loss": 0.5442,
      "step": 175
    },
    {
      "epoch": 0.6096528365791702,
      "grad_norm": 0.731037974357605,
      "learning_rate": 7.940213812589018e-06,
      "loss": 0.5504,
      "step": 180
    },
    {
      "epoch": 0.6265876375952583,
      "grad_norm": 0.6718469262123108,
      "learning_rate": 7.364128339309326e-06,
      "loss": 0.5461,
      "step": 185
    },
    {
      "epoch": 0.6435224386113463,
      "grad_norm": 0.7169979214668274,
      "learning_rate": 6.797301461371626e-06,
      "loss": 0.5387,
      "step": 190
    },
    {
      "epoch": 0.6604572396274344,
      "grad_norm": 0.6952066421508789,
      "learning_rate": 6.241724178857621e-06,
      "loss": 0.5391,
      "step": 195
    },
    {
      "epoch": 0.6773920406435224,
      "grad_norm": 0.7324413657188416,
      "learning_rate": 5.699347977234799e-06,
      "loss": 0.5351,
      "step": 200
    },
    {
      "epoch": 0.6943268416596104,
      "grad_norm": 0.7053231596946716,
      "learning_rate": 5.172077972692553e-06,
      "loss": 0.5393,
      "step": 205
    },
    {
      "epoch": 0.7112616426756986,
      "grad_norm": 0.6486250758171082,
      "learning_rate": 4.661766220352098e-06,
      "loss": 0.5311,
      "step": 210
    },
    {
      "epoch": 0.7281964436917866,
      "grad_norm": 0.6176902055740356,
      "learning_rate": 4.170205208855281e-06,
      "loss": 0.5342,
      "step": 215
    },
    {
      "epoch": 0.7451312447078747,
      "grad_norm": 0.6902855634689331,
      "learning_rate": 3.6991215641828903e-06,
      "loss": 0.526,
      "step": 220
    },
    {
      "epoch": 0.7620660457239627,
      "grad_norm": 0.6924082636833191,
      "learning_rate": 3.250169984817897e-06,
      "loss": 0.5393,
      "step": 225
    },
    {
      "epoch": 0.7790008467400508,
      "grad_norm": 0.6927950978279114,
      "learning_rate": 2.8249274295566863e-06,
      "loss": 0.5372,
      "step": 230
    },
    {
      "epoch": 0.7959356477561389,
      "grad_norm": 0.6544324159622192,
      "learning_rate": 2.424887578383799e-06,
      "loss": 0.53,
      "step": 235
    },
    {
      "epoch": 0.8128704487722269,
      "grad_norm": 0.6218433976173401,
      "learning_rate": 2.0514555858664663e-06,
      "loss": 0.5383,
      "step": 240
    },
    {
      "epoch": 0.8298052497883149,
      "grad_norm": 0.6293333172798157,
      "learning_rate": 1.7059431454979825e-06,
      "loss": 0.5242,
      "step": 245
    },
    {
      "epoch": 0.8467400508044031,
      "grad_norm": 0.6629937291145325,
      "learning_rate": 1.3895638823264447e-06,
      "loss": 0.5283,
      "step": 250
    },
    {
      "epoch": 0.8636748518204911,
      "grad_norm": 0.6638931632041931,
      "learning_rate": 1.1034290900525279e-06,
      "loss": 0.5346,
      "step": 255
    },
    {
      "epoch": 0.8806096528365792,
      "grad_norm": 0.6154753565788269,
      "learning_rate": 8.485438275698154e-07,
      "loss": 0.5286,
      "step": 260
    },
    {
      "epoch": 0.8975444538526672,
      "grad_norm": 0.5576867461204529,
      "learning_rate": 6.258033886587911e-07,
      "loss": 0.5197,
      "step": 265
    },
    {
      "epoch": 0.9144792548687553,
      "grad_norm": 0.5925081372261047,
      "learning_rate": 4.359901572347758e-07,
      "loss": 0.5272,
      "step": 270
    },
    {
      "epoch": 0.9314140558848434,
      "grad_norm": 0.8894816040992737,
      "learning_rate": 2.7977085919589253e-07,
      "loss": 0.5229,
      "step": 275
    },
    {
      "epoch": 0.9483488569009314,
      "grad_norm": 0.613675057888031,
      "learning_rate": 1.5769422052403172e-07,
      "loss": 0.5336,
      "step": 280
    },
    {
      "epoch": 0.9652836579170194,
      "grad_norm": 0.5702030658721924,
      "learning_rate": 7.018903986483083e-08,
      "loss": 0.5295,
      "step": 285
    },
    {
      "epoch": 0.9822184589331076,
      "grad_norm": 0.6007622480392456,
      "learning_rate": 1.7562682356786488e-08,
      "loss": 0.5357,
      "step": 290
    },
    {
      "epoch": 0.9991532599491956,
      "grad_norm": 0.5643032193183899,
      "learning_rate": 0.0,
      "loss": 0.5246,
      "step": 295
    },
    {
      "epoch": 0.9991532599491956,
      "step": 295,
      "total_flos": 8.380405739893555e+17,
      "train_loss": 0.6345516301817813,
      "train_runtime": 3216.2267,
      "train_samples_per_second": 11.745,
      "train_steps_per_second": 0.092
    }
  ],
  "logging_steps": 5,
  "max_steps": 295,
  "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": 8.380405739893555e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}