{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3367003367003367,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003367003367003367,
      "grad_norm": 190.2997283935547,
      "learning_rate": 6.711409395973154e-07,
      "loss": 13.9272,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 196.5933074951172,
      "learning_rate": 1.3422818791946309e-06,
      "loss": 14.3753,
      "step": 2
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 198.02767944335938,
      "learning_rate": 2.013422818791946e-06,
      "loss": 14.4143,
      "step": 3
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 186.30801391601562,
      "learning_rate": 2.6845637583892617e-06,
      "loss": 13.7729,
      "step": 4
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 129.32237243652344,
      "learning_rate": 3.3557046979865773e-06,
      "loss": 11.4082,
      "step": 5
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 123.9930191040039,
      "learning_rate": 4.026845637583892e-06,
      "loss": 11.5581,
      "step": 6
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 102.4565658569336,
      "learning_rate": 4.697986577181209e-06,
      "loss": 9.8311,
      "step": 7
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 98.7117919921875,
      "learning_rate": 5.3691275167785235e-06,
      "loss": 9.825,
      "step": 8
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 121.9065170288086,
      "learning_rate": 6.04026845637584e-06,
      "loss": 8.5157,
      "step": 9
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 93.352294921875,
      "learning_rate": 6.7114093959731546e-06,
      "loss": 7.6328,
      "step": 10
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 108.89420318603516,
      "learning_rate": 7.382550335570471e-06,
      "loss": 7.1598,
      "step": 11
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 191.65274047851562,
      "learning_rate": 8.053691275167785e-06,
      "loss": 6.237,
      "step": 12
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 150.62646484375,
      "learning_rate": 8.724832214765101e-06,
      "loss": 5.7063,
      "step": 13
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 185.48080444335938,
      "learning_rate": 9.395973154362418e-06,
      "loss": 5.093,
      "step": 14
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 1576.556640625,
      "learning_rate": 1.006711409395973e-05,
      "loss": 8.3575,
      "step": 15
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 441.4505310058594,
      "learning_rate": 1.0738255033557047e-05,
      "loss": 4.679,
      "step": 16
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 499.8016357421875,
      "learning_rate": 1.1409395973154363e-05,
      "loss": 3.1432,
      "step": 17
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 472.59747314453125,
      "learning_rate": 1.208053691275168e-05,
      "loss": 2.9237,
      "step": 18
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 506.6687927246094,
      "learning_rate": 1.2751677852348994e-05,
      "loss": 2.6882,
      "step": 19
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 494.16949462890625,
      "learning_rate": 1.3422818791946309e-05,
      "loss": 2.4807,
      "step": 20
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 463.3478698730469,
      "learning_rate": 1.4093959731543624e-05,
      "loss": 2.2508,
      "step": 21
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 422.92401123046875,
      "learning_rate": 1.4765100671140942e-05,
      "loss": 1.9202,
      "step": 22
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 417.1321105957031,
      "learning_rate": 1.5436241610738255e-05,
      "loss": 1.6106,
      "step": 23
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 360.2781677246094,
      "learning_rate": 1.610738255033557e-05,
      "loss": 1.2741,
      "step": 24
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 297.3291015625,
      "learning_rate": 1.6778523489932888e-05,
      "loss": 1.0282,
      "step": 25
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 195.75958251953125,
      "learning_rate": 1.7449664429530202e-05,
      "loss": 0.799,
      "step": 26
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 116.36829376220703,
      "learning_rate": 1.8120805369127517e-05,
      "loss": 0.6593,
      "step": 27
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 70.56578063964844,
      "learning_rate": 1.8791946308724835e-05,
      "loss": 0.5787,
      "step": 28
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 45.22296905517578,
      "learning_rate": 1.946308724832215e-05,
      "loss": 0.5196,
      "step": 29
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 20.37734603881836,
      "learning_rate": 2.013422818791946e-05,
      "loss": 0.4681,
      "step": 30
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 7.735367298126221,
      "learning_rate": 2.080536912751678e-05,
      "loss": 0.4318,
      "step": 31
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 4.360243797302246,
      "learning_rate": 2.1476510067114094e-05,
      "loss": 0.4276,
      "step": 32
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 4.440345287322998,
      "learning_rate": 2.2147651006711412e-05,
      "loss": 0.4463,
      "step": 33
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 26.992700576782227,
      "learning_rate": 2.2818791946308727e-05,
      "loss": 0.4394,
      "step": 34
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 33.81399917602539,
      "learning_rate": 2.348993288590604e-05,
      "loss": 0.6005,
      "step": 35
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 7.8905029296875,
      "learning_rate": 2.416107382550336e-05,
      "loss": 0.4963,
      "step": 36
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 2.6311209201812744,
      "learning_rate": 2.4832214765100674e-05,
      "loss": 0.39,
      "step": 37
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 2.389883041381836,
      "learning_rate": 2.550335570469799e-05,
      "loss": 0.3782,
      "step": 38
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 2.070525646209717,
      "learning_rate": 2.6174496644295304e-05,
      "loss": 0.3592,
      "step": 39
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 5.955089569091797,
      "learning_rate": 2.6845637583892618e-05,
      "loss": 0.3777,
      "step": 40
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 6.50673770904541,
      "learning_rate": 2.7516778523489933e-05,
      "loss": 0.389,
      "step": 41
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 2.0794308185577393,
      "learning_rate": 2.8187919463087248e-05,
      "loss": 0.3618,
      "step": 42
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 1.5477614402770996,
      "learning_rate": 2.885906040268457e-05,
      "loss": 0.3593,
      "step": 43
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 10.740438461303711,
      "learning_rate": 2.9530201342281884e-05,
      "loss": 0.3805,
      "step": 44
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 2.993213176727295,
      "learning_rate": 3.02013422818792e-05,
      "loss": 0.3673,
      "step": 45
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 17.512208938598633,
      "learning_rate": 3.087248322147651e-05,
      "loss": 0.3922,
      "step": 46
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 2.5222012996673584,
      "learning_rate": 3.1543624161073825e-05,
      "loss": 0.3873,
      "step": 47
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.8730729222297668,
      "learning_rate": 3.221476510067114e-05,
      "loss": 0.3593,
      "step": 48
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 0.8050268292427063,
      "learning_rate": 3.288590604026846e-05,
      "loss": 0.3491,
      "step": 49
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.7536938190460205,
      "learning_rate": 3.3557046979865775e-05,
      "loss": 0.3469,
      "step": 50
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 0.9090268015861511,
      "learning_rate": 3.422818791946309e-05,
      "loss": 0.3663,
      "step": 51
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 0.8775368928909302,
      "learning_rate": 3.4899328859060405e-05,
      "loss": 0.3489,
      "step": 52
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 0.5326427221298218,
      "learning_rate": 3.557046979865772e-05,
      "loss": 0.3466,
      "step": 53
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.561137318611145,
      "learning_rate": 3.6241610738255034e-05,
      "loss": 0.3393,
      "step": 54
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.8053128123283386,
      "learning_rate": 3.6912751677852356e-05,
      "loss": 0.352,
      "step": 55
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 0.5964087843894958,
      "learning_rate": 3.758389261744967e-05,
      "loss": 0.3507,
      "step": 56
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 0.5998376607894897,
      "learning_rate": 3.8255033557046985e-05,
      "loss": 0.3504,
      "step": 57
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 1.2634875774383545,
      "learning_rate": 3.89261744966443e-05,
      "loss": 0.337,
      "step": 58
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 0.5703901648521423,
      "learning_rate": 3.959731543624161e-05,
      "loss": 0.3408,
      "step": 59
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.7656762003898621,
      "learning_rate": 4.026845637583892e-05,
      "loss": 0.3206,
      "step": 60
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 0.6210582852363586,
      "learning_rate": 4.0939597315436244e-05,
      "loss": 0.354,
      "step": 61
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 0.6622840166091919,
      "learning_rate": 4.161073825503356e-05,
      "loss": 0.3439,
      "step": 62
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 0.46426376700401306,
      "learning_rate": 4.228187919463087e-05,
      "loss": 0.3434,
      "step": 63
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 0.38662126660346985,
      "learning_rate": 4.295302013422819e-05,
      "loss": 0.3362,
      "step": 64
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 0.5812459588050842,
      "learning_rate": 4.36241610738255e-05,
      "loss": 0.323,
      "step": 65
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.626932680606842,
      "learning_rate": 4.4295302013422824e-05,
      "loss": 0.3427,
      "step": 66
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 0.5491658449172974,
      "learning_rate": 4.496644295302014e-05,
      "loss": 0.3406,
      "step": 67
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 0.4023520052433014,
      "learning_rate": 4.5637583892617453e-05,
      "loss": 0.3328,
      "step": 68
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 0.478535532951355,
      "learning_rate": 4.630872483221477e-05,
      "loss": 0.3402,
      "step": 69
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 0.44869011640548706,
      "learning_rate": 4.697986577181208e-05,
      "loss": 0.3516,
      "step": 70
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 0.4810108244419098,
      "learning_rate": 4.76510067114094e-05,
      "loss": 0.3411,
      "step": 71
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.3956281542778015,
      "learning_rate": 4.832214765100672e-05,
      "loss": 0.3395,
      "step": 72
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 0.40301939845085144,
      "learning_rate": 4.8993288590604034e-05,
      "loss": 0.3217,
      "step": 73
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 0.44550034403800964,
      "learning_rate": 4.966442953020135e-05,
      "loss": 0.3257,
      "step": 74
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 0.5890341997146606,
      "learning_rate": 5.033557046979866e-05,
      "loss": 0.3335,
      "step": 75
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 0.8096022009849548,
      "learning_rate": 5.100671140939598e-05,
      "loss": 0.3421,
      "step": 76
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.6044747829437256,
      "learning_rate": 5.167785234899329e-05,
      "loss": 0.3266,
      "step": 77
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 0.5191451907157898,
      "learning_rate": 5.234899328859061e-05,
      "loss": 0.331,
      "step": 78
    },
    {
      "epoch": 0.265993265993266,
      "grad_norm": 1.0799261331558228,
      "learning_rate": 5.302013422818792e-05,
      "loss": 0.3243,
      "step": 79
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 5.513405799865723,
      "learning_rate": 5.3691275167785237e-05,
      "loss": 0.379,
      "step": 80
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.673650860786438,
      "learning_rate": 5.436241610738255e-05,
      "loss": 0.3482,
      "step": 81
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 1.1485897302627563,
      "learning_rate": 5.5033557046979866e-05,
      "loss": 0.3351,
      "step": 82
    },
    {
      "epoch": 0.27946127946127947,
      "grad_norm": 0.5018780827522278,
      "learning_rate": 5.570469798657718e-05,
      "loss": 0.3077,
      "step": 83
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 4.367802619934082,
      "learning_rate": 5.6375838926174495e-05,
      "loss": 0.3284,
      "step": 84
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 33.46516036987305,
      "learning_rate": 5.704697986577181e-05,
      "loss": 1.0651,
      "step": 85
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 91.36512756347656,
      "learning_rate": 5.771812080536914e-05,
      "loss": 1.7174,
      "step": 86
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 9.666085243225098,
      "learning_rate": 5.838926174496645e-05,
      "loss": 0.5601,
      "step": 87
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 8.608613967895508,
      "learning_rate": 5.906040268456377e-05,
      "loss": 0.3865,
      "step": 88
    },
    {
      "epoch": 0.2996632996632997,
      "grad_norm": 3.025059223175049,
      "learning_rate": 5.973154362416108e-05,
      "loss": 0.358,
      "step": 89
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 9.862916946411133,
      "learning_rate": 6.04026845637584e-05,
      "loss": 0.4464,
      "step": 90
    },
    {
      "epoch": 0.3063973063973064,
      "grad_norm": 11.05635929107666,
      "learning_rate": 6.107382550335571e-05,
      "loss": 0.3977,
      "step": 91
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 1.0226973295211792,
      "learning_rate": 6.174496644295302e-05,
      "loss": 0.3206,
      "step": 92
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 1.007895827293396,
      "learning_rate": 6.241610738255034e-05,
      "loss": 0.3355,
      "step": 93
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 1.5956454277038574,
      "learning_rate": 6.308724832214765e-05,
      "loss": 0.3408,
      "step": 94
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 21.75948715209961,
      "learning_rate": 6.375838926174497e-05,
      "loss": 0.4627,
      "step": 95
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 5.754608154296875,
      "learning_rate": 6.442953020134228e-05,
      "loss": 0.3818,
      "step": 96
    },
    {
      "epoch": 0.3265993265993266,
      "grad_norm": 3.1888318061828613,
      "learning_rate": 6.51006711409396e-05,
      "loss": 0.3713,
      "step": 97
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 4.586446762084961,
      "learning_rate": 6.577181208053692e-05,
      "loss": 0.3394,
      "step": 98
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.9332061409950256,
      "learning_rate": 6.644295302013423e-05,
      "loss": 0.3267,
      "step": 99
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 4.119638442993164,
      "learning_rate": 6.711409395973155e-05,
      "loss": 0.3825,
      "step": 100
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.16432031989097595,
      "eval_runtime": 33.0116,
      "eval_samples_per_second": 30.292,
      "eval_steps_per_second": 1.908,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 1485,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3367497566715904e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}