{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 396,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025252525252525255,
      "grad_norm": 32.43943786621094,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.9259,
      "step": 1
    },
    {
      "epoch": 0.012626262626262626,
      "grad_norm": 18.802860260009766,
      "learning_rate": 2.5e-06,
      "loss": 0.8543,
      "step": 5
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 11.966745376586914,
      "learning_rate": 5e-06,
      "loss": 0.6558,
      "step": 10
    },
    {
      "epoch": 0.03787878787878788,
      "grad_norm": 4.041635990142822,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.5411,
      "step": 15
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.9634244441986084,
      "learning_rate": 1e-05,
      "loss": 0.5026,
      "step": 20
    },
    {
      "epoch": 0.06313131313131314,
      "grad_norm": 4.437589168548584,
      "learning_rate": 1.25e-05,
      "loss": 0.4873,
      "step": 25
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 3.071434497833252,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.4655,
      "step": 30
    },
    {
      "epoch": 0.08838383838383838,
      "grad_norm": 2.649683713912964,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.4277,
      "step": 35
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.9353753328323364,
      "learning_rate": 2e-05,
      "loss": 0.4123,
      "step": 40
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 1.7575881481170654,
      "learning_rate": 1.9990267166335665e-05,
      "loss": 0.3856,
      "step": 45
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 1.685341715812683,
      "learning_rate": 1.9961087610952893e-05,
      "loss": 0.3652,
      "step": 50
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.361409068107605,
      "learning_rate": 1.9912518133803466e-05,
      "loss": 0.3402,
      "step": 55
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.4926209449768066,
      "learning_rate": 1.9844653278615836e-05,
      "loss": 0.3274,
      "step": 60
    },
    {
      "epoch": 0.16414141414141414,
      "grad_norm": 1.358234167098999,
      "learning_rate": 1.9757625148859444e-05,
      "loss": 0.3158,
      "step": 65
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 1.3026068210601807,
      "learning_rate": 1.9651603150596497e-05,
      "loss": 0.3039,
      "step": 70
    },
    {
      "epoch": 0.1893939393939394,
      "grad_norm": 1.4417624473571777,
      "learning_rate": 1.9526793662721768e-05,
      "loss": 0.2947,
      "step": 75
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.306173324584961,
      "learning_rate": 1.9383439635232296e-05,
      "loss": 0.2866,
      "step": 80
    },
    {
      "epoch": 0.21464646464646464,
      "grad_norm": 1.3218271732330322,
      "learning_rate": 1.922182011630902e-05,
      "loss": 0.2807,
      "step": 85
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.3361605405807495,
      "learning_rate": 1.904224970913085e-05,
      "loss": 0.2705,
      "step": 90
    },
    {
      "epoch": 0.2398989898989899,
      "grad_norm": 1.2049956321716309,
      "learning_rate": 1.8845077959478615e-05,
      "loss": 0.2647,
      "step": 95
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 1.0850019454956055,
      "learning_rate": 1.8630688675320844e-05,
      "loss": 0.2558,
      "step": 100
    },
    {
      "epoch": 0.26515151515151514,
      "grad_norm": 1.0417327880859375,
      "learning_rate": 1.839949917970596e-05,
      "loss": 0.2519,
      "step": 105
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.1492786407470703,
      "learning_rate": 1.815195949841512e-05,
      "loss": 0.2491,
      "step": 110
    },
    {
      "epoch": 0.2904040404040404,
      "grad_norm": 1.007467269897461,
      "learning_rate": 1.788855148395699e-05,
      "loss": 0.2399,
      "step": 115
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.9345642924308777,
      "learning_rate": 1.7609787877609678e-05,
      "loss": 0.2389,
      "step": 120
    },
    {
      "epoch": 0.31565656565656564,
      "grad_norm": 0.907543957233429,
      "learning_rate": 1.731621131133564e-05,
      "loss": 0.2398,
      "step": 125
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 0.9041042923927307,
      "learning_rate": 1.700839325151233e-05,
      "loss": 0.2342,
      "step": 130
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.9225403070449829,
      "learning_rate": 1.668693288653478e-05,
      "loss": 0.2311,
      "step": 135
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 0.8411688208580017,
      "learning_rate": 1.6352455960455385e-05,
      "loss": 0.2281,
      "step": 140
    },
    {
      "epoch": 0.3661616161616162,
      "grad_norm": 0.8488685488700867,
      "learning_rate": 1.600561355493137e-05,
      "loss": 0.2218,
      "step": 145
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 0.8601275086402893,
      "learning_rate": 1.5647080821850868e-05,
      "loss": 0.2223,
      "step": 150
    },
    {
      "epoch": 0.39141414141414144,
      "grad_norm": 0.8070423007011414,
      "learning_rate": 1.5277555669104743e-05,
      "loss": 0.2153,
      "step": 155
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.8097870945930481,
      "learning_rate": 1.4897757402062285e-05,
      "loss": 0.2162,
      "step": 160
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.8055990934371948,
      "learning_rate": 1.4508425323395319e-05,
      "loss": 0.2134,
      "step": 165
    },
    {
      "epoch": 0.4292929292929293,
      "grad_norm": 0.8727415800094604,
      "learning_rate": 1.411031729397622e-05,
      "loss": 0.2115,
      "step": 170
    },
    {
      "epoch": 0.44191919191919193,
      "grad_norm": 0.79546058177948,
      "learning_rate": 1.370420825765114e-05,
      "loss": 0.2123,
      "step": 175
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.7648718953132629,
      "learning_rate": 1.32908887327601e-05,
      "loss": 0.2101,
      "step": 180
    },
    {
      "epoch": 0.4671717171717172,
      "grad_norm": 0.7550036311149597,
      "learning_rate": 1.2871163273340309e-05,
      "loss": 0.2027,
      "step": 185
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 0.7257375121116638,
      "learning_rate": 1.2445848903008001e-05,
      "loss": 0.202,
      "step": 190
    },
    {
      "epoch": 0.49242424242424243,
      "grad_norm": 0.7294561266899109,
      "learning_rate": 1.201577352456748e-05,
      "loss": 0.2022,
      "step": 195
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 0.7660893797874451,
      "learning_rate": 1.1581774308443042e-05,
      "loss": 0.1997,
      "step": 200
    },
    {
      "epoch": 0.5176767676767676,
      "grad_norm": 0.7221814393997192,
      "learning_rate": 1.1144696063070884e-05,
      "loss": 0.1963,
      "step": 205
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 0.6848293542861938,
      "learning_rate": 1.070538959042311e-05,
      "loss": 0.1957,
      "step": 210
    },
    {
      "epoch": 0.5429292929292929,
      "grad_norm": 0.6825312972068787,
      "learning_rate": 1.026471002986491e-05,
      "loss": 0.1951,
      "step": 215
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.6754021644592285,
      "learning_rate": 9.823515193568715e-06,
      "loss": 0.1902,
      "step": 220
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.6493006348609924,
      "learning_rate": 9.382663896725578e-06,
      "loss": 0.1892,
      "step": 225
    },
    {
      "epoch": 0.5808080808080808,
      "grad_norm": 0.6259664297103882,
      "learning_rate": 8.943014285804072e-06,
      "loss": 0.1919,
      "step": 230
    },
    {
      "epoch": 0.5934343434343434,
      "grad_norm": 0.6426423192024231,
      "learning_rate": 8.505422168110936e-06,
      "loss": 0.1871,
      "step": 235
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.6354442834854126,
      "learning_rate": 8.070739345905032e-06,
      "loss": 0.1852,
      "step": 240
    },
    {
      "epoch": 0.6186868686868687,
      "grad_norm": 0.6016388535499573,
      "learning_rate": 7.639811958307421e-06,
      "loss": 0.1856,
      "step": 245
    },
    {
      "epoch": 0.6313131313131313,
      "grad_norm": 0.6031273007392883,
      "learning_rate": 7.213478834235079e-06,
      "loss": 0.1854,
      "step": 250
    },
    {
      "epoch": 0.6439393939393939,
      "grad_norm": 0.6175743937492371,
      "learning_rate": 6.792569859564445e-06,
      "loss": 0.183,
      "step": 255
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 0.6094260215759277,
      "learning_rate": 6.3779043617031775e-06,
      "loss": 0.1829,
      "step": 260
    },
    {
      "epoch": 0.6691919191919192,
      "grad_norm": 0.5978714227676392,
      "learning_rate": 5.9702895147146765e-06,
      "loss": 0.1824,
      "step": 265
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.5708032846450806,
      "learning_rate": 5.570518768099918e-06,
      "loss": 0.1785,
      "step": 270
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 0.5738463401794434,
      "learning_rate": 5.179370302295037e-06,
      "loss": 0.1816,
      "step": 275
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 0.5719105005264282,
      "learning_rate": 4.797605513891179e-06,
      "loss": 0.1758,
      "step": 280
    },
    {
      "epoch": 0.7196969696969697,
      "grad_norm": 0.5968112945556641,
      "learning_rate": 4.425967533525229e-06,
      "loss": 0.1779,
      "step": 285
    },
    {
      "epoch": 0.7323232323232324,
      "grad_norm": 0.5471134781837463,
      "learning_rate": 4.0651797793264356e-06,
      "loss": 0.1751,
      "step": 290
    },
    {
      "epoch": 0.7449494949494949,
      "grad_norm": 0.5474812984466553,
      "learning_rate": 3.7159445487347546e-06,
      "loss": 0.1769,
      "step": 295
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.5562990307807922,
      "learning_rate": 3.378941651431996e-06,
      "loss": 0.1744,
      "step": 300
    },
    {
      "epoch": 0.7702020202020202,
      "grad_norm": 0.5516139268875122,
      "learning_rate": 3.054827086046931e-06,
      "loss": 0.1718,
      "step": 305
    },
    {
      "epoch": 0.7828282828282829,
      "grad_norm": 0.5370557308197021,
      "learning_rate": 2.7442317632101743e-06,
      "loss": 0.171,
      "step": 310
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.5318647623062134,
      "learning_rate": 2.447760277444543e-06,
      "loss": 0.1714,
      "step": 315
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.5430074334144592,
      "learning_rate": 2.165989730281475e-06,
      "loss": 0.1727,
      "step": 320
    },
    {
      "epoch": 0.8207070707070707,
      "grad_norm": 0.575107216835022,
      "learning_rate": 1.8994686068943792e-06,
      "loss": 0.1695,
      "step": 325
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.566429615020752,
      "learning_rate": 1.6487157084356454e-06,
      "loss": 0.1718,
      "step": 330
    },
    {
      "epoch": 0.8459595959595959,
      "grad_norm": 0.5522480607032776,
      "learning_rate": 1.414219142155585e-06,
      "loss": 0.1694,
      "step": 335
    },
    {
      "epoch": 0.8585858585858586,
      "grad_norm": 0.5301287174224854,
      "learning_rate": 1.196435371269089e-06,
      "loss": 0.1695,
      "step": 340
    },
    {
      "epoch": 0.8712121212121212,
      "grad_norm": 0.5381254553794861,
      "learning_rate": 9.957883264195224e-07,
      "loss": 0.1709,
      "step": 345
    },
    {
      "epoch": 0.8838383838383839,
      "grad_norm": 0.52545166015625,
      "learning_rate": 8.126685804694401e-07,
      "loss": 0.1686,
      "step": 350
    },
    {
      "epoch": 0.8964646464646465,
      "grad_norm": 0.5226617455482483,
      "learning_rate": 6.47432588224437e-07,
      "loss": 0.1674,
      "step": 355
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.5346973538398743,
      "learning_rate": 5.004019925700921e-07,
      "loss": 0.1692,
      "step": 360
    },
    {
      "epoch": 0.9217171717171717,
      "grad_norm": 0.5276767015457153,
      "learning_rate": 3.7186299837261855e-07,
      "loss": 0.1699,
      "step": 365
    },
    {
      "epoch": 0.9343434343434344,
      "grad_norm": 0.5401973128318787,
      "learning_rate": 2.620658153619959e-07,
      "loss": 0.1684,
      "step": 370
    },
    {
      "epoch": 0.946969696969697,
      "grad_norm": 0.5313433408737183,
      "learning_rate": 1.7122417108203727e-07,
      "loss": 0.1691,
      "step": 375
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 0.5390282273292542,
      "learning_rate": 9.951489485545696e-08,
      "loss": 0.169,
      "step": 380
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 0.5103330016136169,
      "learning_rate": 4.7077573573793836e-08,
      "loss": 0.1653,
      "step": 385
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 0.5155799388885498,
      "learning_rate": 1.4014279982216272e-08,
      "loss": 0.1668,
      "step": 390
    },
    {
      "epoch": 0.9974747474747475,
      "grad_norm": 0.5293468832969666,
      "learning_rate": 3.893739881088987e-10,
      "loss": 0.1711,
      "step": 395
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.12780985236167908,
      "eval_runtime": 1.3224,
      "eval_samples_per_second": 0.756,
      "eval_steps_per_second": 0.756,
      "step": 396
    },
    {
      "epoch": 1.0,
      "step": 396,
      "total_flos": 165828687298560.0,
      "train_loss": 0.24546745942548068,
      "train_runtime": 6726.335,
      "train_samples_per_second": 7.533,
      "train_steps_per_second": 0.059
    }
  ],
  "logging_steps": 5,
  "max_steps": 396,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 165828687298560.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}