{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 398,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01256281407035176,
      "grad_norm": 21.75,
      "learning_rate": 9.999999999999999e-06,
      "loss": 2.8925046920776367,
      "step": 5
    },
    {
      "epoch": 0.02512562814070352,
      "grad_norm": 8.0625,
      "learning_rate": 2.25e-05,
      "loss": 2.448771286010742,
      "step": 10
    },
    {
      "epoch": 0.03768844221105527,
      "grad_norm": 3.96875,
      "learning_rate": 2.9998012821858358e-05,
      "loss": 2.0705329895019533,
      "step": 15
    },
    {
      "epoch": 0.05025125628140704,
      "grad_norm": 2.78125,
      "learning_rate": 2.997566311404217e-05,
      "loss": 1.9264299392700195,
      "step": 20
    },
    {
      "epoch": 0.06281407035175879,
      "grad_norm": 2.734375,
      "learning_rate": 2.9928516855555942e-05,
      "loss": 1.7724725723266601,
      "step": 25
    },
    {
      "epoch": 0.07537688442211055,
      "grad_norm": 2.59375,
      "learning_rate": 2.985665211069496e-05,
      "loss": 1.7452875137329102,
      "step": 30
    },
    {
      "epoch": 0.08793969849246232,
      "grad_norm": 2.15625,
      "learning_rate": 2.9760187872372847e-05,
      "loss": 1.6443361282348632,
      "step": 35
    },
    {
      "epoch": 0.10050251256281408,
      "grad_norm": 4.15625,
      "learning_rate": 2.9639283865094298e-05,
      "loss": 1.6196260452270508,
      "step": 40
    },
    {
      "epoch": 0.11306532663316583,
      "grad_norm": 2.390625,
      "learning_rate": 2.9494140280484873e-05,
      "loss": 1.6696979522705078,
      "step": 45
    },
    {
      "epoch": 0.12562814070351758,
      "grad_norm": 2.296875,
      "learning_rate": 2.932499744581575e-05,
      "loss": 1.5513226509094238,
      "step": 50
    },
    {
      "epoch": 0.13819095477386933,
      "grad_norm": 2.1875,
      "learning_rate": 2.913213542607226e-05,
      "loss": 1.5566128730773925,
      "step": 55
    },
    {
      "epoch": 0.1507537688442211,
      "grad_norm": 2.640625,
      "learning_rate": 2.8915873560225136e-05,
      "loss": 1.5669374465942383,
      "step": 60
    },
    {
      "epoch": 0.16331658291457288,
      "grad_norm": 2.625,
      "learning_rate": 2.8676569932472298e-05,
      "loss": 1.5305331230163575,
      "step": 65
    },
    {
      "epoch": 0.17587939698492464,
      "grad_norm": 2.09375,
      "learning_rate": 2.841462077932666e-05,
      "loss": 1.575944995880127,
      "step": 70
    },
    {
      "epoch": 0.1884422110552764,
      "grad_norm": 2.421875,
      "learning_rate": 2.8130459833531793e-05,
      "loss": 1.5058233261108398,
      "step": 75
    },
    {
      "epoch": 0.20100502512562815,
      "grad_norm": 2.875,
      "learning_rate": 2.7824557605891595e-05,
      "loss": 1.502994918823242,
      "step": 80
    },
    {
      "epoch": 0.2135678391959799,
      "grad_norm": 2.234375,
      "learning_rate": 2.749742060620333e-05,
      "loss": 1.511138916015625,
      "step": 85
    },
    {
      "epoch": 0.22613065326633167,
      "grad_norm": 2.46875,
      "learning_rate": 2.714959050458384e-05,
      "loss": 1.5119872093200684,
      "step": 90
    },
    {
      "epoch": 0.23869346733668342,
      "grad_norm": 2.203125,
      "learning_rate": 2.6781643234577683e-05,
      "loss": 1.5344759941101074,
      "step": 95
    },
    {
      "epoch": 0.25125628140703515,
      "grad_norm": 2.203125,
      "learning_rate": 2.639418803953223e-05,
      "loss": 1.494624137878418,
      "step": 100
    },
    {
      "epoch": 0.2638190954773869,
      "grad_norm": 2.3125,
      "learning_rate": 2.598786646381871e-05,
      "loss": 1.4727994918823242,
      "step": 105
    },
    {
      "epoch": 0.27638190954773867,
      "grad_norm": 2.59375,
      "learning_rate": 2.5563351290569583e-05,
      "loss": 1.4636452674865723,
      "step": 110
    },
    {
      "epoch": 0.2889447236180904,
      "grad_norm": 2.234375,
      "learning_rate": 2.5121345427691065e-05,
      "loss": 1.526972484588623,
      "step": 115
    },
    {
      "epoch": 0.3015075376884422,
      "grad_norm": 2.125,
      "learning_rate": 2.4662580743995365e-05,
      "loss": 1.4123519897460937,
      "step": 120
    },
    {
      "epoch": 0.314070351758794,
      "grad_norm": 2.09375,
      "learning_rate": 2.4187816857379752e-05,
      "loss": 1.440127468109131,
      "step": 125
    },
    {
      "epoch": 0.32663316582914576,
      "grad_norm": 2.859375,
      "learning_rate": 2.3697839877058963e-05,
      "loss": 1.4384952545166017,
      "step": 130
    },
    {
      "epoch": 0.3391959798994975,
      "grad_norm": 2.578125,
      "learning_rate": 2.319346110193356e-05,
      "loss": 1.4032865524291993,
      "step": 135
    },
    {
      "epoch": 0.35175879396984927,
      "grad_norm": 2.46875,
      "learning_rate": 2.267551567724948e-05,
      "loss": 1.4081149101257324,
      "step": 140
    },
    {
      "epoch": 0.36432160804020103,
      "grad_norm": 2.28125,
      "learning_rate": 2.2144861211772998e-05,
      "loss": 1.4147528648376464,
      "step": 145
    },
    {
      "epoch": 0.3768844221105528,
      "grad_norm": 3.046875,
      "learning_rate": 2.160237635777088e-05,
      "loss": 1.3809213638305664,
      "step": 150
    },
    {
      "epoch": 0.38944723618090454,
      "grad_norm": 2.546875,
      "learning_rate": 2.104895935614689e-05,
      "loss": 1.443575954437256,
      "step": 155
    },
    {
      "epoch": 0.4020100502512563,
      "grad_norm": 2.1875,
      "learning_rate": 2.0485526549143637e-05,
      "loss": 1.4132374763488769,
      "step": 160
    },
    {
      "epoch": 0.41457286432160806,
      "grad_norm": 2.3125,
      "learning_rate": 1.99130108630724e-05,
      "loss": 1.4260528564453125,
      "step": 165
    },
    {
      "epoch": 0.4271356783919598,
      "grad_norm": 2.40625,
      "learning_rate": 1.933236026358324e-05,
      "loss": 1.4127822875976563,
      "step": 170
    },
    {
      "epoch": 0.4396984924623116,
      "grad_norm": 2.1875,
      "learning_rate": 1.8744536186033133e-05,
      "loss": 1.3749101638793946,
      "step": 175
    },
    {
      "epoch": 0.45226130653266333,
      "grad_norm": 2.84375,
      "learning_rate": 1.8150511943551052e-05,
      "loss": 1.3645042419433593,
      "step": 180
    },
    {
      "epoch": 0.4648241206030151,
      "grad_norm": 3.125,
      "learning_rate": 1.7551271115436e-05,
      "loss": 1.3747994422912597,
      "step": 185
    },
    {
      "epoch": 0.47738693467336685,
      "grad_norm": 2.203125,
      "learning_rate": 1.694780591855643e-05,
      "loss": 1.356684684753418,
      "step": 190
    },
    {
      "epoch": 0.4899497487437186,
      "grad_norm": 2.203125,
      "learning_rate": 1.6341115564447624e-05,
      "loss": 1.3736384391784668,
      "step": 195
    },
    {
      "epoch": 0.5025125628140703,
      "grad_norm": 2.34375,
      "learning_rate": 1.5732204604827395e-05,
      "loss": 1.3433109283447267,
      "step": 200
    },
    {
      "epoch": 0.5150753768844221,
      "grad_norm": 2.703125,
      "learning_rate": 1.5122081268269593e-05,
      "loss": 1.4066362380981445,
      "step": 205
    },
    {
      "epoch": 0.5276381909547738,
      "grad_norm": 2.515625,
      "learning_rate": 1.4511755790789445e-05,
      "loss": 1.382357692718506,
      "step": 210
    },
    {
      "epoch": 0.5402010050251256,
      "grad_norm": 3.5,
      "learning_rate": 1.3902238743105087e-05,
      "loss": 1.4047765731811523,
      "step": 215
    },
    {
      "epoch": 0.5527638190954773,
      "grad_norm": 2.3125,
      "learning_rate": 1.32945393573448e-05,
      "loss": 1.3828323364257813,
      "step": 220
    },
    {
      "epoch": 0.5653266331658291,
      "grad_norm": 1.9921875,
      "learning_rate": 1.2689663855970765e-05,
      "loss": 1.4413321495056153,
      "step": 225
    },
    {
      "epoch": 0.5778894472361809,
      "grad_norm": 2.109375,
      "learning_rate": 1.2088613785686083e-05,
      "loss": 1.3303167343139648,
      "step": 230
    },
    {
      "epoch": 0.5904522613065326,
      "grad_norm": 2.21875,
      "learning_rate": 1.1492384359083988e-05,
      "loss": 1.3269375801086425,
      "step": 235
    },
    {
      "epoch": 0.6030150753768844,
      "grad_norm": 2.109375,
      "learning_rate": 1.0901962806784941e-05,
      "loss": 1.3969734191894532,
      "step": 240
    },
    {
      "epoch": 0.6155778894472361,
      "grad_norm": 2.109375,
      "learning_rate": 1.0318326742790171e-05,
      "loss": 1.3942330360412598,
      "step": 245
    },
    {
      "epoch": 0.628140703517588,
      "grad_norm": 2.25,
      "learning_rate": 9.742442545758419e-06,
      "loss": 1.3573790550231934,
      "step": 250
    },
    {
      "epoch": 0.6407035175879398,
      "grad_norm": 2.234375,
      "learning_rate": 9.175263758885932e-06,
      "loss": 1.3188179016113282,
      "step": 255
    },
    {
      "epoch": 0.6532663316582915,
      "grad_norm": 2.125,
      "learning_rate": 8.617729511039368e-06,
      "loss": 1.3902714729309082,
      "step": 260
    },
    {
      "epoch": 0.6658291457286433,
      "grad_norm": 2.53125,
      "learning_rate": 8.070762961755747e-06,
      "loss": 1.3327635765075683,
      "step": 265
    },
    {
      "epoch": 0.678391959798995,
      "grad_norm": 2.140625,
      "learning_rate": 7.535269772684295e-06,
      "loss": 1.4243352890014649,
      "step": 270
    },
    {
      "epoch": 0.6909547738693468,
      "grad_norm": 2.421875,
      "learning_rate": 7.012136608001107e-06,
      "loss": 1.3524487495422364,
      "step": 275
    },
    {
      "epoch": 0.7035175879396985,
      "grad_norm": 1.859375,
      "learning_rate": 6.5022296662795675e-06,
      "loss": 1.4379519462585448,
      "step": 280
    },
    {
      "epoch": 0.7160804020100503,
      "grad_norm": 2.515625,
      "learning_rate": 6.006393246247647e-06,
      "loss": 1.3775064468383789,
      "step": 285
    },
    {
      "epoch": 0.7286432160804021,
      "grad_norm": 2.21875,
      "learning_rate": 5.525448348806584e-06,
      "loss": 1.3395397186279296,
      "step": 290
    },
    {
      "epoch": 0.7412060301507538,
      "grad_norm": 2.515625,
      "learning_rate": 5.060191317625973e-06,
      "loss": 1.3216740608215332,
      "step": 295
    },
    {
      "epoch": 0.7537688442211056,
      "grad_norm": 2.09375,
      "learning_rate": 4.611392520566028e-06,
      "loss": 1.367293930053711,
      "step": 300
    },
    {
      "epoch": 0.7663316582914573,
      "grad_norm": 1.796875,
      "learning_rate": 4.179795074110265e-06,
      "loss": 1.3515189170837403,
      "step": 305
    },
    {
      "epoch": 0.7788944723618091,
      "grad_norm": 2.078125,
      "learning_rate": 3.766113612920868e-06,
      "loss": 1.3384337425231934,
      "step": 310
    },
    {
      "epoch": 0.7914572864321608,
      "grad_norm": 2.390625,
      "learning_rate": 3.3710331065537868e-06,
      "loss": 1.3583839416503907,
      "step": 315
    },
    {
      "epoch": 0.8040201005025126,
      "grad_norm": 2.3125,
      "learning_rate": 2.9952077252932014e-06,
      "loss": 1.3483553886413575,
      "step": 320
    },
    {
      "epoch": 0.8165829145728644,
      "grad_norm": 2.09375,
      "learning_rate": 2.6392597569829623e-06,
      "loss": 1.365108108520508,
      "step": 325
    },
    {
      "epoch": 0.8291457286432161,
      "grad_norm": 2.0625,
      "learning_rate": 2.3037785766487252e-06,
      "loss": 1.3631028175354003,
      "step": 330
    },
    {
      "epoch": 0.8417085427135679,
      "grad_norm": 2.609375,
      "learning_rate": 1.98931967061679e-06,
      "loss": 1.3902606964111328,
      "step": 335
    },
    {
      "epoch": 0.8542713567839196,
      "grad_norm": 1.890625,
      "learning_rate": 1.6964037167454605e-06,
      "loss": 1.405683994293213,
      "step": 340
    },
    {
      "epoch": 0.8668341708542714,
      "grad_norm": 2.6875,
      "learning_rate": 1.4255157222919812e-06,
      "loss": 1.4000654220581055,
      "step": 345
    },
    {
      "epoch": 0.8793969849246231,
      "grad_norm": 1.828125,
      "learning_rate": 1.1771042208424232e-06,
      "loss": 1.388939380645752,
      "step": 350
    },
    {
      "epoch": 0.8919597989949749,
      "grad_norm": 2.359375,
      "learning_rate": 9.515805296343461e-07,
      "loss": 1.383950424194336,
      "step": 355
    },
    {
      "epoch": 0.9045226130653267,
      "grad_norm": 2.53125,
      "learning_rate": 7.493180685019057e-07,
      "loss": 1.3533215522766113,
      "step": 360
    },
    {
      "epoch": 0.9170854271356784,
      "grad_norm": 2.1875,
      "learning_rate": 5.706517415710688e-07,
      "loss": 1.3400803565979005,
      "step": 365
    },
    {
      "epoch": 0.9296482412060302,
      "grad_norm": 2.515625,
      "learning_rate": 4.1587738272880093e-07,
      "loss": 1.40626220703125,
      "step": 370
    },
    {
      "epoch": 0.9422110552763819,
      "grad_norm": 1.953125,
      "learning_rate": 2.8525126578428927e-07,
      "loss": 1.3951802253723145,
      "step": 375
    },
    {
      "epoch": 0.9547738693467337,
      "grad_norm": 2.078125,
      "learning_rate": 1.7898968013340567e-07,
      "loss": 1.3679948806762696,
      "step": 380
    },
    {
      "epoch": 0.9673366834170855,
      "grad_norm": 2.40625,
      "learning_rate": 9.726857262890576e-08,
      "loss": 1.378611946105957,
      "step": 385
    },
    {
      "epoch": 0.9798994974874372,
      "grad_norm": 2.265625,
      "learning_rate": 4.0223256249426465e-08,
      "loss": 1.344498634338379,
      "step": 390
    },
    {
      "epoch": 0.992462311557789,
      "grad_norm": 2.453125,
      "learning_rate": 7.948186049637207e-09,
      "loss": 1.359067726135254,
      "step": 395
    },
    {
      "epoch": 1.0,
      "step": 398,
      "total_flos": 1.9165347193492685e+17,
      "train_loss": 1.4728496278350676,
      "train_runtime": 3210.9735,
      "train_samples_per_second": 0.496,
      "train_steps_per_second": 0.124
    }
  ],
  "logging_steps": 5,
  "max_steps": 398,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9165347193492685e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}