{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6996921046844073,
  "eval_steps": 500,
  "global_step": 12726,
  "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
    }
  ],
  "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": 3325202399232000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}