{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 394,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025380710659898477,
      "grad_norm": 1.8291217999671763,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.4159851551055908,
      "step": 10
    },
    {
      "epoch": 0.050761421319796954,
      "grad_norm": 1.6007748773654842,
      "learning_rate": 4.995858485682857e-06,
      "loss": 0.35700695514678954,
      "step": 20
    },
    {
      "epoch": 0.07614213197969544,
      "grad_norm": 1.5703851925337782,
      "learning_rate": 4.975606543367983e-06,
      "loss": 0.3234694957733154,
      "step": 30
    },
    {
      "epoch": 0.10152284263959391,
      "grad_norm": 1.4126270514736947,
      "learning_rate": 4.938620212537733e-06,
      "loss": 0.3106333017349243,
      "step": 40
    },
    {
      "epoch": 0.12690355329949238,
      "grad_norm": 1.4523222284806365,
      "learning_rate": 4.88514951015523e-06,
      "loss": 0.2907158136367798,
      "step": 50
    },
    {
      "epoch": 0.15228426395939088,
      "grad_norm": 1.4245940516947615,
      "learning_rate": 4.815555882796169e-06,
      "loss": 0.28935024738311765,
      "step": 60
    },
    {
      "epoch": 0.17766497461928935,
      "grad_norm": 1.4326576791215673,
      "learning_rate": 4.730309763373866e-06,
      "loss": 0.27973968982696534,
      "step": 70
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 1.3417742117513098,
      "learning_rate": 4.629987391148012e-06,
      "loss": 0.27466156482696535,
      "step": 80
    },
    {
      "epoch": 0.22842639593908629,
      "grad_norm": 1.4098788972536733,
      "learning_rate": 4.515266916512945e-06,
      "loss": 0.2743204116821289,
      "step": 90
    },
    {
      "epoch": 0.25380710659898476,
      "grad_norm": 1.4505892408446934,
      "learning_rate": 4.3869238168959485e-06,
      "loss": 0.26970345973968507,
      "step": 100
    },
    {
      "epoch": 0.27918781725888325,
      "grad_norm": 1.3693356575199105,
      "learning_rate": 4.245825654752781e-06,
      "loss": 0.2528782844543457,
      "step": 110
    },
    {
      "epoch": 0.30456852791878175,
      "grad_norm": 1.4119308585018628,
      "learning_rate": 4.092926213094897e-06,
      "loss": 0.2709981441497803,
      "step": 120
    },
    {
      "epoch": 0.3299492385786802,
      "grad_norm": 1.2896260197827607,
      "learning_rate": 3.929259048190492e-06,
      "loss": 0.2611530780792236,
      "step": 130
    },
    {
      "epoch": 0.3553299492385787,
      "grad_norm": 1.2552219232154451,
      "learning_rate": 3.7559305030212746e-06,
      "loss": 0.26369991302490237,
      "step": 140
    },
    {
      "epoch": 0.38071065989847713,
      "grad_norm": 1.2259393296995453,
      "learning_rate": 3.5741122287219665e-06,
      "loss": 0.2534872770309448,
      "step": 150
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 1.292717843077142,
      "learning_rate": 3.385033264555482e-06,
      "loss": 0.24978070259094237,
      "step": 160
    },
    {
      "epoch": 0.43147208121827413,
      "grad_norm": 1.3993012441121058,
      "learning_rate": 3.1899717299608384e-06,
      "loss": 0.2548422336578369,
      "step": 170
    },
    {
      "epoch": 0.45685279187817257,
      "grad_norm": 1.306729282222898,
      "learning_rate": 2.9902461848332128e-06,
      "loss": 0.2472081661224365,
      "step": 180
    },
    {
      "epoch": 0.48223350253807107,
      "grad_norm": 1.328781150018071,
      "learning_rate": 2.7872067164381113e-06,
      "loss": 0.25132601261138915,
      "step": 190
    },
    {
      "epoch": 0.5076142131979695,
      "grad_norm": 1.2163742646511995,
      "learning_rate": 2.5822258132096038e-06,
      "loss": 0.24532461166381836,
      "step": 200
    },
    {
      "epoch": 0.5329949238578681,
      "grad_norm": 1.2627775111774209,
      "learning_rate": 2.376689087123087e-06,
      "loss": 0.24561314582824706,
      "step": 210
    },
    {
      "epoch": 0.5583756345177665,
      "grad_norm": 1.2836814124431382,
      "learning_rate": 2.1719859073566813e-06,
      "loss": 0.23798489570617676,
      "step": 220
    },
    {
      "epoch": 0.583756345177665,
      "grad_norm": 1.2980057773033666,
      "learning_rate": 1.969500008555023e-06,
      "loss": 0.23232407569885255,
      "step": 230
    },
    {
      "epoch": 0.6091370558375635,
      "grad_norm": 1.223401499162475,
      "learning_rate": 1.7706001371808763e-06,
      "loss": 0.2399765968322754,
      "step": 240
    },
    {
      "epoch": 0.6345177664974619,
      "grad_norm": 1.1891124244205362,
      "learning_rate": 1.5766307991825514e-06,
      "loss": 0.2318518877029419,
      "step": 250
    },
    {
      "epoch": 0.6598984771573604,
      "grad_norm": 1.30587831950529,
      "learning_rate": 1.3889031715202272e-06,
      "loss": 0.23593788146972655,
      "step": 260
    },
    {
      "epoch": 0.6852791878172588,
      "grad_norm": 1.1784663873376826,
      "learning_rate": 1.2086862389866577e-06,
      "loss": 0.22989363670349122,
      "step": 270
    },
    {
      "epoch": 0.7106598984771574,
      "grad_norm": 1.2366732391489947,
      "learning_rate": 1.037198216234791e-06,
      "loss": 0.22706074714660646,
      "step": 280
    },
    {
      "epoch": 0.7360406091370558,
      "grad_norm": 1.3193385141675646,
      "learning_rate": 8.75598312996944e-07,
      "loss": 0.22869620323181153,
      "step": 290
    },
    {
      "epoch": 0.7614213197969543,
      "grad_norm": 1.2340874172254008,
      "learning_rate": 7.249788981602801e-07,
      "loss": 0.22583470344543458,
      "step": 300
    },
    {
      "epoch": 0.7868020304568528,
      "grad_norm": 1.2687910418829957,
      "learning_rate": 5.863581156671755e-07,
      "loss": 0.22786765098571776,
      "step": 310
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 1.2940273846110892,
      "learning_rate": 4.6067300215487663e-07,
      "loss": 0.22640743255615234,
      "step": 320
    },
    {
      "epoch": 0.8375634517766497,
      "grad_norm": 1.2649715981594793,
      "learning_rate": 3.487731528572255e-07,
      "loss": 0.2247671127319336,
      "step": 330
    },
    {
      "epoch": 0.8629441624365483,
      "grad_norm": 1.2255865117192781,
      "learning_rate": 2.514149785851311e-07,
      "loss": 0.22807893753051758,
      "step": 340
    },
    {
      "epoch": 0.8883248730964467,
      "grad_norm": 1.1670836264810733,
      "learning_rate": 1.6925659260694894e-07,
      "loss": 0.21738579273223876,
      "step": 350
    },
    {
      "epoch": 0.9137055837563451,
      "grad_norm": 1.2918462011993423,
      "learning_rate": 1.0285336199198858e-07,
      "loss": 0.2203979015350342,
      "step": 360
    },
    {
      "epoch": 0.9390862944162437,
      "grad_norm": 1.3093873490646804,
      "learning_rate": 5.265415348879005e-08,
      "loss": 0.22320880889892578,
      "step": 370
    },
    {
      "epoch": 0.9644670050761421,
      "grad_norm": 1.1814867509953966,
      "learning_rate": 1.899829931495012e-08,
      "loss": 0.22281956672668457,
      "step": 380
    },
    {
      "epoch": 0.9898477157360406,
      "grad_norm": 1.2460294855428804,
      "learning_rate": 2.1133033688858217e-09,
      "loss": 0.22592899799346924,
      "step": 390
    },
    {
      "epoch": 1.0,
      "step": 394,
      "total_flos": 147320576409600.0,
      "train_loss": 0.25529243710077354,
      "train_runtime": 2644.3362,
      "train_samples_per_second": 19.068,
      "train_steps_per_second": 0.149
    }
  ],
  "logging_steps": 10,
  "max_steps": 394,
  "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": 147320576409600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}