{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 475,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10614101592115238,
      "grad_norm": 6.5291595458984375,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.3263,
      "step": 10
    },
    {
      "epoch": 0.21228203184230476,
      "grad_norm": 1.4655342102050781,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 1.1625,
      "step": 20
    },
    {
      "epoch": 0.31842304776345715,
      "grad_norm": 1.383467197418213,
      "learning_rate": 2.4166666666666667e-05,
      "loss": 1.0477,
      "step": 30
    },
    {
      "epoch": 0.4245640636846095,
      "grad_norm": 1.4785548448562622,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 1.0062,
      "step": 40
    },
    {
      "epoch": 0.530705079605762,
      "grad_norm": 1.4572118520736694,
      "learning_rate": 3.999945869500297e-05,
      "loss": 1.0003,
      "step": 50
    },
    {
      "epoch": 0.6368460955269143,
      "grad_norm": 1.7819571495056152,
      "learning_rate": 3.9934537542218075e-05,
      "loss": 0.9682,
      "step": 60
    },
    {
      "epoch": 0.7429871114480667,
      "grad_norm": 1.0432629585266113,
      "learning_rate": 3.9761757921821544e-05,
      "loss": 0.9887,
      "step": 70
    },
    {
      "epoch": 0.849128127369219,
      "grad_norm": 2.0072572231292725,
      "learning_rate": 3.948205468093744e-05,
      "loss": 0.9882,
      "step": 80
    },
    {
      "epoch": 0.9552691432903715,
      "grad_norm": 1.6535046100616455,
      "learning_rate": 3.909694119116433e-05,
      "loss": 0.9592,
      "step": 90
    },
    {
      "epoch": 1.0530705079605762,
      "grad_norm": 1.6055387258529663,
      "learning_rate": 3.860850116027705e-05,
      "loss": 0.9474,
      "step": 100
    },
    {
      "epoch": 1.1592115238817287,
      "grad_norm": 1.1085819005966187,
      "learning_rate": 3.801937735804838e-05,
      "loss": 0.9273,
      "step": 110
    },
    {
      "epoch": 1.265352539802881,
      "grad_norm": 1.5138670206069946,
      "learning_rate": 3.7332757317191726e-05,
      "loss": 0.8991,
      "step": 120
    },
    {
      "epoch": 1.3714935557240333,
      "grad_norm": 1.4127428531646729,
      "learning_rate": 3.6552356086791176e-05,
      "loss": 0.9057,
      "step": 130
    },
    {
      "epoch": 1.4776345716451857,
      "grad_norm": 0.9714298844337463,
      "learning_rate": 3.568239613153421e-05,
      "loss": 0.8885,
      "step": 140
    },
    {
      "epoch": 1.5837755875663382,
      "grad_norm": 0.8646650910377502,
      "learning_rate": 3.472758448550471e-05,
      "loss": 0.9101,
      "step": 150
    },
    {
      "epoch": 1.6899166034874904,
      "grad_norm": 0.6955054402351379,
      "learning_rate": 3.3693087284148765e-05,
      "loss": 0.9119,
      "step": 160
    },
    {
      "epoch": 1.7960576194086428,
      "grad_norm": 0.8518441915512085,
      "learning_rate": 3.258450181221154e-05,
      "loss": 0.88,
      "step": 170
    },
    {
      "epoch": 1.9021986353297953,
      "grad_norm": 0.9373747110366821,
      "learning_rate": 3.140782621888343e-05,
      "loss": 0.8962,
      "step": 180
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5835213661193848,
      "learning_rate": 3.0169427064015813e-05,
      "loss": 0.9049,
      "step": 190
    },
    {
      "epoch": 2.1061410159211524,
      "grad_norm": 0.4349837601184845,
      "learning_rate": 2.887600487100196e-05,
      "loss": 0.8462,
      "step": 200
    },
    {
      "epoch": 2.212282031842305,
      "grad_norm": 0.40261805057525635,
      "learning_rate": 2.7534557872703705e-05,
      "loss": 0.8301,
      "step": 210
    },
    {
      "epoch": 2.3184230477634573,
      "grad_norm": 0.3540641665458679,
      "learning_rate": 2.615234414658145e-05,
      "loss": 0.8281,
      "step": 220
    },
    {
      "epoch": 2.4245640636846097,
      "grad_norm": 0.3487437069416046,
      "learning_rate": 2.4736842343900386e-05,
      "loss": 0.8388,
      "step": 230
    },
    {
      "epoch": 2.530705079605762,
      "grad_norm": 0.5164170265197754,
      "learning_rate": 2.3295711225492847e-05,
      "loss": 0.8335,
      "step": 240
    },
    {
      "epoch": 2.636846095526914,
      "grad_norm": 0.34246334433555603,
      "learning_rate": 2.1836748223013785e-05,
      "loss": 0.8491,
      "step": 250
    },
    {
      "epoch": 2.7429871114480666,
      "grad_norm": 0.4085201621055603,
      "learning_rate": 2.0367847249899443e-05,
      "loss": 0.8155,
      "step": 260
    },
    {
      "epoch": 2.849128127369219,
      "grad_norm": 0.3134537637233734,
      "learning_rate": 1.8896955990298364e-05,
      "loss": 0.823,
      "step": 270
    },
    {
      "epoch": 2.9552691432903715,
      "grad_norm": 0.3039611279964447,
      "learning_rate": 1.743203289706898e-05,
      "loss": 0.8266,
      "step": 280
    },
    {
      "epoch": 3.053070507960576,
      "grad_norm": 0.24728739261627197,
      "learning_rate": 1.5981004131511497e-05,
      "loss": 0.7984,
      "step": 290
    },
    {
      "epoch": 3.1592115238817287,
      "grad_norm": 0.20878377556800842,
      "learning_rate": 1.455172067781763e-05,
      "loss": 0.7883,
      "step": 300
    },
    {
      "epoch": 3.265352539802881,
      "grad_norm": 0.1705101877450943,
      "learning_rate": 1.3151915864276115e-05,
      "loss": 0.7863,
      "step": 310
    },
    {
      "epoch": 3.3714935557240335,
      "grad_norm": 0.15946735441684723,
      "learning_rate": 1.1789163521071099e-05,
      "loss": 0.7712,
      "step": 320
    },
    {
      "epoch": 3.4776345716451855,
      "grad_norm": 0.19221286475658417,
      "learning_rate": 1.0470837001066219e-05,
      "loss": 0.7943,
      "step": 330
    },
    {
      "epoch": 3.583775587566338,
      "grad_norm": 0.19959454238414764,
      "learning_rate": 9.204069285297936e-06,
      "loss": 0.7896,
      "step": 340
    },
    {
      "epoch": 3.6899166034874904,
      "grad_norm": 0.13320986926555634,
      "learning_rate": 7.995714389032638e-06,
      "loss": 0.7797,
      "step": 350
    },
    {
      "epoch": 3.796057619408643,
      "grad_norm": 0.16105031967163086,
      "learning_rate": 6.852310277205116e-06,
      "loss": 0.801,
      "step": 360
    },
    {
      "epoch": 3.9021986353297953,
      "grad_norm": 0.1884138584136963,
      "learning_rate": 5.780043489889415e-06,
      "loss": 0.7722,
      "step": 370
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.16600456833839417,
      "learning_rate": 4.784715669200672e-06,
      "loss": 0.7575,
      "step": 380
    },
    {
      "epoch": 4.106141015921152,
      "grad_norm": 0.08295275270938873,
      "learning_rate": 3.8717121687385575e-06,
      "loss": 0.7798,
      "step": 390
    },
    {
      "epoch": 4.212282031842305,
      "grad_norm": 0.10298614203929901,
      "learning_rate": 3.0459729154151095e-06,
      "loss": 0.7812,
      "step": 400
    },
    {
      "epoch": 4.318423047763457,
      "grad_norm": 0.09198899567127228,
      "learning_rate": 2.311965681322943e-06,
      "loss": 0.7591,
      "step": 410
    },
    {
      "epoch": 4.42456406368461,
      "grad_norm": 0.08718331158161163,
      "learning_rate": 1.6736619102599073e-06,
      "loss": 0.7507,
      "step": 420
    },
    {
      "epoch": 4.530705079605762,
      "grad_norm": 0.09788376837968826,
      "learning_rate": 1.1345152297040273e-06,
      "loss": 0.7636,
      "step": 430
    },
    {
      "epoch": 4.636846095526915,
      "grad_norm": 0.07903146743774414,
      "learning_rate": 6.974427645025427e-07,
      "loss": 0.746,
      "step": 440
    },
    {
      "epoch": 4.742987111448067,
      "grad_norm": 0.08080583065748215,
      "learning_rate": 3.648093533798092e-07,
      "loss": 0.7581,
      "step": 450
    },
    {
      "epoch": 4.8491281273692195,
      "grad_norm": 0.07727949321269989,
      "learning_rate": 1.3841475366273228e-07,
      "loss": 0.7594,
      "step": 460
    },
    {
      "epoch": 4.955269143290371,
      "grad_norm": 0.0837486982345581,
      "learning_rate": 1.948390345430484e-08,
      "loss": 0.7481,
      "step": 470
    },
    {
      "epoch": 5.0,
      "step": 475,
      "total_flos": 3.54463086751976e+19,
      "train_loss": 0.865001671439723,
      "train_runtime": 46695.3235,
      "train_samples_per_second": 1.271,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 10,
  "max_steps": 475,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.54463086751976e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}