{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6992522542335606,
  "eval_steps": 500,
  "global_step": 30906,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027490653177919506,
      "grad_norm": 7.844790935516357,
      "learning_rate": 1.98e-05,
      "loss": 3.3532,
      "step": 500
    },
    {
      "epoch": 0.05498130635583901,
      "grad_norm": 7.924389362335205,
      "learning_rate": 1.9816883693400415e-05,
      "loss": 2.6056,
      "step": 1000
    },
    {
      "epoch": 0.08247195953375852,
      "grad_norm": 7.497577667236328,
      "learning_rate": 1.963191772713821e-05,
      "loss": 2.5447,
      "step": 1500
    },
    {
      "epoch": 0.10996261271167802,
      "grad_norm": 6.73529577255249,
      "learning_rate": 1.9446951760876e-05,
      "loss": 2.4492,
      "step": 2000
    },
    {
      "epoch": 0.13745326588959753,
      "grad_norm": 6.306326866149902,
      "learning_rate": 1.9261985794613793e-05,
      "loss": 2.4463,
      "step": 2500
    },
    {
      "epoch": 0.16494391906751704,
      "grad_norm": 5.651560306549072,
      "learning_rate": 1.9077019828351584e-05,
      "loss": 2.3291,
      "step": 3000
    },
    {
      "epoch": 0.19243457224543656,
      "grad_norm": 4.0863471031188965,
      "learning_rate": 1.8892053862089378e-05,
      "loss": 2.3461,
      "step": 3500
    },
    {
      "epoch": 0.21992522542335605,
      "grad_norm": 4.746509075164795,
      "learning_rate": 1.8707087895827168e-05,
      "loss": 2.2806,
      "step": 4000
    },
    {
      "epoch": 0.24741587860127556,
      "grad_norm": 4.339619159698486,
      "learning_rate": 1.8522121929564962e-05,
      "loss": 2.2746,
      "step": 4500
    },
    {
      "epoch": 0.27490653177919505,
      "grad_norm": 4.018620014190674,
      "learning_rate": 1.8337155963302752e-05,
      "loss": 2.2403,
      "step": 5000
    },
    {
      "epoch": 0.3023971849571146,
      "grad_norm": 4.380566120147705,
      "learning_rate": 1.8152189997040546e-05,
      "loss": 2.226,
      "step": 5500
    },
    {
      "epoch": 0.3298878381350341,
      "grad_norm": 4.302157402038574,
      "learning_rate": 1.796722403077834e-05,
      "loss": 2.2119,
      "step": 6000
    },
    {
      "epoch": 0.3573784913129536,
      "grad_norm": 4.434130668640137,
      "learning_rate": 1.778225806451613e-05,
      "loss": 2.2138,
      "step": 6500
    },
    {
      "epoch": 0.3848691444908731,
      "grad_norm": 3.770848035812378,
      "learning_rate": 1.759729209825392e-05,
      "loss": 2.2103,
      "step": 7000
    },
    {
      "epoch": 0.4123597976687926,
      "grad_norm": 2.9288535118103027,
      "learning_rate": 1.7412326131991715e-05,
      "loss": 2.1397,
      "step": 7500
    },
    {
      "epoch": 0.4398504508467121,
      "grad_norm": 3.2082479000091553,
      "learning_rate": 1.722736016572951e-05,
      "loss": 2.2021,
      "step": 8000
    },
    {
      "epoch": 0.46734110402463164,
      "grad_norm": 3.6131439208984375,
      "learning_rate": 1.70423941994673e-05,
      "loss": 2.2106,
      "step": 8500
    },
    {
      "epoch": 0.4948317572025511,
      "grad_norm": 2.992415189743042,
      "learning_rate": 1.6857798165137616e-05,
      "loss": 2.1246,
      "step": 9000
    },
    {
      "epoch": 0.5223224103804707,
      "grad_norm": 3.4553306102752686,
      "learning_rate": 1.667283219887541e-05,
      "loss": 2.0973,
      "step": 9500
    },
    {
      "epoch": 0.5498130635583901,
      "grad_norm": 2.82578182220459,
      "learning_rate": 1.64878662326132e-05,
      "loss": 2.1257,
      "step": 10000
    },
    {
      "epoch": 0.5773037167363096,
      "grad_norm": 2.674267292022705,
      "learning_rate": 1.630290026635099e-05,
      "loss": 2.13,
      "step": 10500
    },
    {
      "epoch": 0.6047943699142292,
      "grad_norm": 3.27205491065979,
      "learning_rate": 1.6117934300088784e-05,
      "loss": 2.1855,
      "step": 11000
    },
    {
      "epoch": 0.6322850230921486,
      "grad_norm": 3.042849540710449,
      "learning_rate": 1.5932968333826578e-05,
      "loss": 2.1532,
      "step": 11500
    },
    {
      "epoch": 0.6597756762700682,
      "grad_norm": 3.618957042694092,
      "learning_rate": 1.5748372299496894e-05,
      "loss": 2.1202,
      "step": 12000
    },
    {
      "epoch": 0.6872663294479877,
      "grad_norm": 3.6390328407287598,
      "learning_rate": 1.5563406333234685e-05,
      "loss": 2.0902,
      "step": 12500
    },
    {
      "epoch": 0.7147569826259071,
      "grad_norm": 3.3778562545776367,
      "learning_rate": 1.537844036697248e-05,
      "loss": 2.0536,
      "step": 13000
    },
    {
      "epoch": 0.7422476358038267,
      "grad_norm": 2.8149023056030273,
      "learning_rate": 1.519347440071027e-05,
      "loss": 2.1065,
      "step": 13500
    },
    {
      "epoch": 0.7697382889817462,
      "grad_norm": 2.860196590423584,
      "learning_rate": 1.5008508434448063e-05,
      "loss": 2.0705,
      "step": 14000
    },
    {
      "epoch": 0.7972289421596657,
      "grad_norm": 3.2587316036224365,
      "learning_rate": 1.4823542468185853e-05,
      "loss": 2.1082,
      "step": 14500
    },
    {
      "epoch": 0.8247195953375852,
      "grad_norm": 2.4807844161987305,
      "learning_rate": 1.4638576501923647e-05,
      "loss": 2.0576,
      "step": 15000
    },
    {
      "epoch": 0.8522102485155048,
      "grad_norm": 3.040374755859375,
      "learning_rate": 1.445361053566144e-05,
      "loss": 2.0694,
      "step": 15500
    },
    {
      "epoch": 0.8797009016934242,
      "grad_norm": 3.2850606441497803,
      "learning_rate": 1.4269014501331757e-05,
      "loss": 2.081,
      "step": 16000
    },
    {
      "epoch": 0.9071915548713437,
      "grad_norm": 3.131565570831299,
      "learning_rate": 1.4084048535069548e-05,
      "loss": 2.0567,
      "step": 16500
    },
    {
      "epoch": 0.9346822080492633,
      "grad_norm": 2.221071481704712,
      "learning_rate": 1.389908256880734e-05,
      "loss": 2.0758,
      "step": 17000
    },
    {
      "epoch": 0.9621728612271827,
      "grad_norm": 2.6275980472564697,
      "learning_rate": 1.3714116602545134e-05,
      "loss": 2.0495,
      "step": 17500
    },
    {
      "epoch": 0.9896635144051023,
      "grad_norm": 3.2267441749572754,
      "learning_rate": 1.3529150636282926e-05,
      "loss": 2.0287,
      "step": 18000
    },
    {
      "epoch": 1.0171541675830218,
      "grad_norm": 3.0593459606170654,
      "learning_rate": 1.334455460195324e-05,
      "loss": 2.0028,
      "step": 18500
    },
    {
      "epoch": 1.0446448207609413,
      "grad_norm": 2.9170665740966797,
      "learning_rate": 1.3159588635691035e-05,
      "loss": 1.9644,
      "step": 19000
    },
    {
      "epoch": 1.0721354739388609,
      "grad_norm": 3.075544834136963,
      "learning_rate": 1.2974622669428827e-05,
      "loss": 1.9723,
      "step": 19500
    },
    {
      "epoch": 1.0996261271167802,
      "grad_norm": 2.9603986740112305,
      "learning_rate": 1.2789656703166617e-05,
      "loss": 1.997,
      "step": 20000
    },
    {
      "epoch": 1.1271167802946997,
      "grad_norm": 2.951988458633423,
      "learning_rate": 1.2605060668836935e-05,
      "loss": 1.9418,
      "step": 20500
    },
    {
      "epoch": 1.1546074334726193,
      "grad_norm": 3.427750587463379,
      "learning_rate": 1.2420094702574727e-05,
      "loss": 1.9553,
      "step": 21000
    },
    {
      "epoch": 1.1820980866505388,
      "grad_norm": 2.6535024642944336,
      "learning_rate": 1.223512873631252e-05,
      "loss": 2.0072,
      "step": 21500
    },
    {
      "epoch": 1.2095887398284584,
      "grad_norm": 2.9090585708618164,
      "learning_rate": 1.2050162770050312e-05,
      "loss": 1.9705,
      "step": 22000
    },
    {
      "epoch": 1.237079393006378,
      "grad_norm": 3.2485570907592773,
      "learning_rate": 1.1865196803788104e-05,
      "loss": 1.9543,
      "step": 22500
    },
    {
      "epoch": 1.2645700461842972,
      "grad_norm": 3.0418505668640137,
      "learning_rate": 1.168060076945842e-05,
      "loss": 2.0092,
      "step": 23000
    },
    {
      "epoch": 1.2920606993622168,
      "grad_norm": 3.1117002964019775,
      "learning_rate": 1.1495634803196214e-05,
      "loss": 1.9702,
      "step": 23500
    },
    {
      "epoch": 1.3195513525401363,
      "grad_norm": 2.928476095199585,
      "learning_rate": 1.1310668836934005e-05,
      "loss": 1.9813,
      "step": 24000
    },
    {
      "epoch": 1.3470420057180559,
      "grad_norm": 3.026412010192871,
      "learning_rate": 1.1125702870671797e-05,
      "loss": 1.9192,
      "step": 24500
    },
    {
      "epoch": 1.3745326588959754,
      "grad_norm": 3.093477249145508,
      "learning_rate": 1.094073690440959e-05,
      "loss": 1.9387,
      "step": 25000
    },
    {
      "epoch": 1.402023312073895,
      "grad_norm": 2.920074701309204,
      "learning_rate": 1.0756140870079905e-05,
      "loss": 1.9651,
      "step": 25500
    },
    {
      "epoch": 1.4295139652518145,
      "grad_norm": 2.5337624549865723,
      "learning_rate": 1.0571174903817697e-05,
      "loss": 1.9262,
      "step": 26000
    },
    {
      "epoch": 1.4570046184297338,
      "grad_norm": 2.506801128387451,
      "learning_rate": 1.0386208937555491e-05,
      "loss": 1.9542,
      "step": 26500
    },
    {
      "epoch": 1.4844952716076534,
      "grad_norm": 2.7995145320892334,
      "learning_rate": 1.0201242971293283e-05,
      "loss": 1.9609,
      "step": 27000
    },
    {
      "epoch": 1.511985924785573,
      "grad_norm": 4.121292591094971,
      "learning_rate": 1.0016646936963598e-05,
      "loss": 1.9317,
      "step": 27500
    },
    {
      "epoch": 1.5394765779634925,
      "grad_norm": 2.802678346633911,
      "learning_rate": 9.831680970701392e-06,
      "loss": 1.9519,
      "step": 28000
    },
    {
      "epoch": 1.5669672311414118,
      "grad_norm": 2.965937852859497,
      "learning_rate": 9.646715004439184e-06,
      "loss": 1.9401,
      "step": 28500
    },
    {
      "epoch": 1.5944578843193313,
      "grad_norm": 2.364539861679077,
      "learning_rate": 9.461749038176976e-06,
      "loss": 1.9686,
      "step": 29000
    },
    {
      "epoch": 1.6219485374972509,
      "grad_norm": 2.8087072372436523,
      "learning_rate": 9.276783071914768e-06,
      "loss": 1.9046,
      "step": 29500
    },
    {
      "epoch": 1.6494391906751704,
      "grad_norm": 3.0667874813079834,
      "learning_rate": 9.092187037585085e-06,
      "loss": 1.8992,
      "step": 30000
    },
    {
      "epoch": 1.67692984385309,
      "grad_norm": 2.4543378353118896,
      "learning_rate": 8.907221071322877e-06,
      "loss": 1.8936,
      "step": 30500
    }
  ],
  "logging_steps": 500,
  "max_steps": 54564,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1818,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8075360894976000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}