{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 10000,
  "global_step": 735,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13646055437100213,
      "grad_norm": 0.14500385522842407,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.1268,
      "step": 20
    },
    {
      "epoch": 0.27292110874200426,
      "grad_norm": 0.06265528500080109,
      "learning_rate": 0.000234,
      "loss": 0.0282,
      "step": 40
    },
    {
      "epoch": 0.4093816631130064,
      "grad_norm": 0.03309512510895729,
      "learning_rate": 0.00029987223755234907,
      "loss": 0.0157,
      "step": 60
    },
    {
      "epoch": 0.5458422174840085,
      "grad_norm": 0.03388677537441254,
      "learning_rate": 0.00029867524500941253,
      "loss": 0.0125,
      "step": 80
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.038252197206020355,
      "learning_rate": 0.00029622824461983995,
      "loss": 0.0128,
      "step": 100
    },
    {
      "epoch": 0.8187633262260128,
      "grad_norm": 0.06330293416976929,
      "learning_rate": 0.00029255180988050044,
      "loss": 0.0112,
      "step": 120
    },
    {
      "epoch": 0.9552238805970149,
      "grad_norm": 0.03660163655877113,
      "learning_rate": 0.0002876768509289324,
      "loss": 0.0106,
      "step": 140
    },
    {
      "epoch": 1.0886993603411514,
      "grad_norm": 0.028105631470680237,
      "learning_rate": 0.0002816443546620542,
      "loss": 0.0085,
      "step": 160
    },
    {
      "epoch": 1.2251599147121535,
      "grad_norm": 0.04313601925969124,
      "learning_rate": 0.00027450504013311436,
      "loss": 0.007,
      "step": 180
    },
    {
      "epoch": 1.3616204690831557,
      "grad_norm": 0.03731823340058327,
      "learning_rate": 0.00026631893212418224,
      "loss": 0.0056,
      "step": 200
    },
    {
      "epoch": 1.4980810234541577,
      "grad_norm": 0.02299409918487072,
      "learning_rate": 0.00025715485647942525,
      "loss": 0.0075,
      "step": 220
    },
    {
      "epoch": 1.63454157782516,
      "grad_norm": 0.03759332001209259,
      "learning_rate": 0.00024708986144223035,
      "loss": 0.0063,
      "step": 240
    },
    {
      "epoch": 1.7710021321961622,
      "grad_norm": 0.013533813878893852,
      "learning_rate": 0.00023620856986135804,
      "loss": 0.0052,
      "step": 260
    },
    {
      "epoch": 1.9074626865671642,
      "grad_norm": 0.0647633746266365,
      "learning_rate": 0.00022460246771254522,
      "loss": 0.0045,
      "step": 280
    },
    {
      "epoch": 2.0409381663113004,
      "grad_norm": 0.022289317101240158,
      "learning_rate": 0.0002123691349174121,
      "loss": 0.003,
      "step": 300
    },
    {
      "epoch": 2.177398720682303,
      "grad_norm": 0.040852464735507965,
      "learning_rate": 0.00019961142492666903,
      "loss": 0.0028,
      "step": 320
    },
    {
      "epoch": 2.313859275053305,
      "grad_norm": 0.04412081092596054,
      "learning_rate": 0.00018643659996539272,
      "loss": 0.0029,
      "step": 340
    },
    {
      "epoch": 2.450319829424307,
      "grad_norm": 0.047590937465429306,
      "learning_rate": 0.00017295542921091727,
      "loss": 0.0025,
      "step": 360
    },
    {
      "epoch": 2.5867803837953094,
      "grad_norm": 0.032162390649318695,
      "learning_rate": 0.00015928125748553563,
      "loss": 0.002,
      "step": 380
    },
    {
      "epoch": 2.7232409381663114,
      "grad_norm": 0.02574550174176693,
      "learning_rate": 0.00014552905229410626,
      "loss": 0.0014,
      "step": 400
    },
    {
      "epoch": 2.8597014925373134,
      "grad_norm": 0.014707539230585098,
      "learning_rate": 0.000131814437218731,
      "loss": 0.0012,
      "step": 420
    },
    {
      "epoch": 2.9961620469083154,
      "grad_norm": 0.04477572441101074,
      "learning_rate": 0.0001182527197973709,
      "loss": 0.0011,
      "step": 440
    },
    {
      "epoch": 3.129637526652452,
      "grad_norm": 0.012851215898990631,
      "learning_rate": 0.00010495792205964832,
      "loss": 0.0008,
      "step": 460
    },
    {
      "epoch": 3.266098081023454,
      "grad_norm": 0.02783357724547386,
      "learning_rate": 9.204182187073868e-05,
      "loss": 0.0007,
      "step": 480
    },
    {
      "epoch": 3.402558635394456,
      "grad_norm": 0.004735818598419428,
      "learning_rate": 7.961301314338808e-05,
      "loss": 0.0004,
      "step": 500
    },
    {
      "epoch": 3.539019189765458,
      "grad_norm": 0.003670594422146678,
      "learning_rate": 6.777599281945507e-05,
      "loss": 0.0004,
      "step": 520
    },
    {
      "epoch": 3.6754797441364606,
      "grad_norm": 0.013839378952980042,
      "learning_rate": 5.66302822973053e-05,
      "loss": 0.0004,
      "step": 540
    },
    {
      "epoch": 3.8119402985074626,
      "grad_norm": 0.00302703189663589,
      "learning_rate": 4.626959069178253e-05,
      "loss": 0.0004,
      "step": 560
    },
    {
      "epoch": 3.948400852878465,
      "grad_norm": 0.026532089337706566,
      "learning_rate": 3.6781026961763353e-05,
      "loss": 0.0004,
      "step": 580
    },
    {
      "epoch": 4.081876332622601,
      "grad_norm": 0.001038851565681398,
      "learning_rate": 2.8244367529442822e-05,
      "loss": 0.0002,
      "step": 600
    },
    {
      "epoch": 4.218336886993604,
      "grad_norm": 0.0008404534310102463,
      "learning_rate": 2.0731385548944725e-05,
      "loss": 0.0002,
      "step": 620
    },
    {
      "epoch": 4.354797441364606,
      "grad_norm": 0.0016892015701159835,
      "learning_rate": 1.4305247463523778e-05,
      "loss": 0.0002,
      "step": 640
    },
    {
      "epoch": 4.491257995735608,
      "grad_norm": 0.002141030738130212,
      "learning_rate": 9.019981924888797e-06,
      "loss": 0.0001,
      "step": 660
    },
    {
      "epoch": 4.62771855010661,
      "grad_norm": 0.0017192725790664554,
      "learning_rate": 4.920025539782397e-06,
      "loss": 0.0002,
      "step": 680
    },
    {
      "epoch": 4.764179104477612,
      "grad_norm": 0.002778939437121153,
      "learning_rate": 2.0398492630157303e-06,
      "loss": 0.0002,
      "step": 700
    },
    {
      "epoch": 4.900639658848614,
      "grad_norm": 0.002974987495690584,
      "learning_rate": 4.036685781107329e-07,
      "loss": 0.0001,
      "step": 720
    }
  ],
  "logging_steps": 20,
  "max_steps": 735,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8319121075920896e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}