{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 490,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04094165813715456,
      "grad_norm": 7.529000759124756,
      "learning_rate": 9.000000000000001e-07,
      "loss": 6.639524841308594,
      "step": 10
    },
    {
      "epoch": 0.08188331627430911,
      "grad_norm": 7.1427388191223145,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 6.582770538330078,
      "step": 20
    },
    {
      "epoch": 0.12282497441146366,
      "grad_norm": 6.251121997833252,
      "learning_rate": 2.9e-06,
      "loss": 6.114261245727539,
      "step": 30
    },
    {
      "epoch": 0.16376663254861823,
      "grad_norm": 7.014133453369141,
      "learning_rate": 3.900000000000001e-06,
      "loss": 6.333962631225586,
      "step": 40
    },
    {
      "epoch": 0.2047082906857728,
      "grad_norm": 7.072969913482666,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 6.248543930053711,
      "step": 50
    },
    {
      "epoch": 0.24564994882292732,
      "grad_norm": 5.674424171447754,
      "learning_rate": 5.9e-06,
      "loss": 5.6220745086669925,
      "step": 60
    },
    {
      "epoch": 0.2865916069600819,
      "grad_norm": 5.3739800453186035,
      "learning_rate": 6.9e-06,
      "loss": 5.0251930236816404,
      "step": 70
    },
    {
      "epoch": 0.32753326509723646,
      "grad_norm": 6.372293472290039,
      "learning_rate": 7.9e-06,
      "loss": 5.033017349243164,
      "step": 80
    },
    {
      "epoch": 0.368474923234391,
      "grad_norm": 7.22106409072876,
      "learning_rate": 8.900000000000001e-06,
      "loss": 3.514456939697266,
      "step": 90
    },
    {
      "epoch": 0.4094165813715456,
      "grad_norm": 4.990958213806152,
      "learning_rate": 9.9e-06,
      "loss": 2.256962776184082,
      "step": 100
    },
    {
      "epoch": 0.4503582395087001,
      "grad_norm": 3.2661993503570557,
      "learning_rate": 9.76923076923077e-06,
      "loss": 2.0482555389404298,
      "step": 110
    },
    {
      "epoch": 0.49129989764585463,
      "grad_norm": 2.997323513031006,
      "learning_rate": 9.512820512820514e-06,
      "loss": 1.6077747344970703,
      "step": 120
    },
    {
      "epoch": 0.5322415557830092,
      "grad_norm": 2.422741413116455,
      "learning_rate": 9.256410256410257e-06,
      "loss": 1.538028621673584,
      "step": 130
    },
    {
      "epoch": 0.5731832139201638,
      "grad_norm": 2.4594290256500244,
      "learning_rate": 9e-06,
      "loss": 1.5614049911499024,
      "step": 140
    },
    {
      "epoch": 0.6141248720573184,
      "grad_norm": 2.7256577014923096,
      "learning_rate": 8.743589743589743e-06,
      "loss": 1.7180768966674804,
      "step": 150
    },
    {
      "epoch": 0.6550665301944729,
      "grad_norm": 2.6614902019500732,
      "learning_rate": 8.487179487179488e-06,
      "loss": 1.6412044525146485,
      "step": 160
    },
    {
      "epoch": 0.6960081883316275,
      "grad_norm": 2.1517934799194336,
      "learning_rate": 8.230769230769232e-06,
      "loss": 1.729467010498047,
      "step": 170
    },
    {
      "epoch": 0.736949846468782,
      "grad_norm": 2.4588229656219482,
      "learning_rate": 7.974358974358975e-06,
      "loss": 1.305363941192627,
      "step": 180
    },
    {
      "epoch": 0.7778915046059366,
      "grad_norm": 2.5282061100006104,
      "learning_rate": 7.717948717948718e-06,
      "loss": 1.4986873626708985,
      "step": 190
    },
    {
      "epoch": 0.8188331627430911,
      "grad_norm": 3.699396848678589,
      "learning_rate": 7.461538461538462e-06,
      "loss": 1.5059691429138184,
      "step": 200
    },
    {
      "epoch": 0.8597748208802457,
      "grad_norm": 2.2632241249084473,
      "learning_rate": 7.205128205128206e-06,
      "loss": 1.4249659538269044,
      "step": 210
    },
    {
      "epoch": 0.9007164790174002,
      "grad_norm": 1.6525421142578125,
      "learning_rate": 6.948717948717949e-06,
      "loss": 1.2684237480163574,
      "step": 220
    },
    {
      "epoch": 0.9416581371545547,
      "grad_norm": 4.144842624664307,
      "learning_rate": 6.692307692307692e-06,
      "loss": 1.3331901550292968,
      "step": 230
    },
    {
      "epoch": 0.9825997952917093,
      "grad_norm": 4.287148475646973,
      "learning_rate": 6.435897435897437e-06,
      "loss": 1.3455743789672852,
      "step": 240
    },
    {
      "epoch": 1.0204708290685773,
      "grad_norm": 1.7868481874465942,
      "learning_rate": 6.17948717948718e-06,
      "loss": 1.2180957794189453,
      "step": 250
    },
    {
      "epoch": 1.0614124872057318,
      "grad_norm": 3.4123318195343018,
      "learning_rate": 5.923076923076924e-06,
      "loss": 1.0844655990600587,
      "step": 260
    },
    {
      "epoch": 1.1023541453428864,
      "grad_norm": 2.9107143878936768,
      "learning_rate": 5.666666666666667e-06,
      "loss": 1.2759632110595702,
      "step": 270
    },
    {
      "epoch": 1.143295803480041,
      "grad_norm": 2.166071653366089,
      "learning_rate": 5.41025641025641e-06,
      "loss": 1.2902444839477538,
      "step": 280
    },
    {
      "epoch": 1.1842374616171956,
      "grad_norm": 3.7286741733551025,
      "learning_rate": 5.1538461538461534e-06,
      "loss": 1.1132170677185058,
      "step": 290
    },
    {
      "epoch": 1.22517911975435,
      "grad_norm": 3.644495964050293,
      "learning_rate": 4.8974358974358975e-06,
      "loss": 1.3006702423095704,
      "step": 300
    },
    {
      "epoch": 1.2661207778915047,
      "grad_norm": 2.9774715900421143,
      "learning_rate": 4.641025641025642e-06,
      "loss": 1.3277738571166993,
      "step": 310
    },
    {
      "epoch": 1.3070624360286591,
      "grad_norm": 3.5428693294525146,
      "learning_rate": 4.384615384615385e-06,
      "loss": 1.2050466537475586,
      "step": 320
    },
    {
      "epoch": 1.3480040941658138,
      "grad_norm": 2.9129176139831543,
      "learning_rate": 4.128205128205128e-06,
      "loss": 1.0705522537231444,
      "step": 330
    },
    {
      "epoch": 1.3889457523029682,
      "grad_norm": 3.6323633193969727,
      "learning_rate": 3.871794871794872e-06,
      "loss": 1.1811490058898926,
      "step": 340
    },
    {
      "epoch": 1.429887410440123,
      "grad_norm": 2.344156265258789,
      "learning_rate": 3.6153846153846156e-06,
      "loss": 1.2702527046203613,
      "step": 350
    },
    {
      "epoch": 1.4708290685772774,
      "grad_norm": 2.93733286857605,
      "learning_rate": 3.358974358974359e-06,
      "loss": 1.2678390502929688,
      "step": 360
    },
    {
      "epoch": 1.511770726714432,
      "grad_norm": 3.3147552013397217,
      "learning_rate": 3.102564102564103e-06,
      "loss": 0.975819206237793,
      "step": 370
    },
    {
      "epoch": 1.5527123848515865,
      "grad_norm": 3.5217061042785645,
      "learning_rate": 2.846153846153846e-06,
      "loss": 1.5488268852233886,
      "step": 380
    },
    {
      "epoch": 1.593654042988741,
      "grad_norm": 2.5279595851898193,
      "learning_rate": 2.5897435897435903e-06,
      "loss": 1.1411288261413575,
      "step": 390
    },
    {
      "epoch": 1.6345957011258956,
      "grad_norm": 2.848078489303589,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 1.1716268539428711,
      "step": 400
    },
    {
      "epoch": 1.6755373592630503,
      "grad_norm": 2.8351571559906006,
      "learning_rate": 2.0769230769230773e-06,
      "loss": 1.139915370941162,
      "step": 410
    },
    {
      "epoch": 1.7164790174002047,
      "grad_norm": 5.1406707763671875,
      "learning_rate": 1.8205128205128205e-06,
      "loss": 1.016810417175293,
      "step": 420
    },
    {
      "epoch": 1.7574206755373591,
      "grad_norm": 2.3416874408721924,
      "learning_rate": 1.5641025641025642e-06,
      "loss": 1.0270769119262695,
      "step": 430
    },
    {
      "epoch": 1.7983623336745138,
      "grad_norm": 2.4181466102600098,
      "learning_rate": 1.307692307692308e-06,
      "loss": 1.2266251564025878,
      "step": 440
    },
    {
      "epoch": 1.8393039918116685,
      "grad_norm": 2.907052755355835,
      "learning_rate": 1.0512820512820514e-06,
      "loss": 1.1883393287658692,
      "step": 450
    },
    {
      "epoch": 1.880245649948823,
      "grad_norm": 2.765097141265869,
      "learning_rate": 7.948717948717949e-07,
      "loss": 1.2259196281433105,
      "step": 460
    },
    {
      "epoch": 1.9211873080859774,
      "grad_norm": 3.7463090419769287,
      "learning_rate": 5.384615384615386e-07,
      "loss": 1.016909694671631,
      "step": 470
    },
    {
      "epoch": 1.962128966223132,
      "grad_norm": 3.9370245933532715,
      "learning_rate": 2.820512820512821e-07,
      "loss": 1.1455986976623536,
      "step": 480
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.772556304931641,
      "learning_rate": 2.5641025641025643e-08,
      "loss": 1.0747014999389648,
      "step": 490
    }
  ],
  "logging_steps": 10,
  "max_steps": 490,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4297687441485824e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}