{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 110,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 2.043996572494507,
      "learning_rate": 1e-05,
      "loss": 2.9697265625,
      "step": 1
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 2.0926244258880615,
      "learning_rate": 9.997960964140946e-06,
      "loss": 3.10546875,
      "step": 2
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 1.8654357194900513,
      "learning_rate": 9.991845519630679e-06,
      "loss": 2.8662109375,
      "step": 3
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 1.915582299232483,
      "learning_rate": 9.981658654313458e-06,
      "loss": 2.935546875,
      "step": 4
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.7176072597503662,
      "learning_rate": 9.96740867674275e-06,
      "loss": 2.75,
      "step": 5
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.507042407989502,
      "learning_rate": 9.949107209404664e-06,
      "loss": 2.47265625,
      "step": 6
    },
    {
      "epoch": 0.12727272727272726,
      "grad_norm": 1.3875086307525635,
      "learning_rate": 9.926769179238467e-06,
      "loss": 2.419921875,
      "step": 7
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 1.1929569244384766,
      "learning_rate": 9.900412805461968e-06,
      "loss": 2.2275390625,
      "step": 8
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.9290140867233276,
      "learning_rate": 9.870059584711668e-06,
      "loss": 2.0986328125,
      "step": 9
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.7955628633499146,
      "learning_rate": 9.835734273509787e-06,
      "loss": 2.060546875,
      "step": 10
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.747456431388855,
      "learning_rate": 9.797464868072489e-06,
      "loss": 2.001953125,
      "step": 11
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.6845131516456604,
      "learning_rate": 9.755282581475769e-06,
      "loss": 1.9140625,
      "step": 12
    },
    {
      "epoch": 0.23636363636363636,
      "grad_norm": 0.5947973728179932,
      "learning_rate": 9.709221818197626e-06,
      "loss": 1.8671875,
      "step": 13
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.5244090557098389,
      "learning_rate": 9.659320146057263e-06,
      "loss": 1.8232421875,
      "step": 14
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.5063930749893188,
      "learning_rate": 9.60561826557425e-06,
      "loss": 1.8232421875,
      "step": 15
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.44349098205566406,
      "learning_rate": 9.548159976772593e-06,
      "loss": 1.8076171875,
      "step": 16
    },
    {
      "epoch": 0.3090909090909091,
      "grad_norm": 0.35866260528564453,
      "learning_rate": 9.486992143456792e-06,
      "loss": 1.677734375,
      "step": 17
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.35987231135368347,
      "learning_rate": 9.422164654989073e-06,
      "loss": 1.6611328125,
      "step": 18
    },
    {
      "epoch": 0.34545454545454546,
      "grad_norm": 0.3307989835739136,
      "learning_rate": 9.353730385598887e-06,
      "loss": 1.6337890625,
      "step": 19
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.3848985731601715,
      "learning_rate": 9.281745151257946e-06,
      "loss": 1.615234375,
      "step": 20
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.349418044090271,
      "learning_rate": 9.206267664155906e-06,
      "loss": 1.5546875,
      "step": 21
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.35031673312187195,
      "learning_rate": 9.12735948481387e-06,
      "loss": 1.57421875,
      "step": 22
    },
    {
      "epoch": 0.41818181818181815,
      "grad_norm": 0.3336755633354187,
      "learning_rate": 9.045084971874738e-06,
      "loss": 1.50439453125,
      "step": 23
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.34189310669898987,
      "learning_rate": 8.959511229611377e-06,
      "loss": 1.482421875,
      "step": 24
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.3576221764087677,
      "learning_rate": 8.870708053195414e-06,
      "loss": 1.4765625,
      "step": 25
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.36254608631134033,
      "learning_rate": 8.778747871771293e-06,
      "loss": 1.4287109375,
      "step": 26
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.4230624735355377,
      "learning_rate": 8.683705689382025e-06,
      "loss": 1.3896484375,
      "step": 27
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.40722933411598206,
      "learning_rate": 8.585659023794818e-06,
      "loss": 1.372314453125,
      "step": 28
    },
    {
      "epoch": 0.5272727272727272,
      "grad_norm": 0.4091890752315521,
      "learning_rate": 8.48468784327647e-06,
      "loss": 1.30517578125,
      "step": 29
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.3111860156059265,
      "learning_rate": 8.380874501370098e-06,
      "loss": 1.2509765625,
      "step": 30
    },
    {
      "epoch": 0.5636363636363636,
      "grad_norm": 0.203084334731102,
      "learning_rate": 8.274303669726427e-06,
      "loss": 1.30908203125,
      "step": 31
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.17557428777217865,
      "learning_rate": 8.165062269044353e-06,
      "loss": 1.32470703125,
      "step": 32
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.15492086112499237,
      "learning_rate": 8.053239398177191e-06,
      "loss": 1.220703125,
      "step": 33
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 0.20500344038009644,
      "learning_rate": 7.938926261462366e-06,
      "loss": 1.19970703125,
      "step": 34
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.1662224531173706,
      "learning_rate": 7.822216094333847e-06,
      "loss": 1.2255859375,
      "step": 35
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.17929084599018097,
      "learning_rate": 7.703204087277989e-06,
      "loss": 1.25146484375,
      "step": 36
    },
    {
      "epoch": 0.6727272727272727,
      "grad_norm": 0.18725869059562683,
      "learning_rate": 7.5819873081948105e-06,
      "loss": 1.24365234375,
      "step": 37
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 0.2386845201253891,
      "learning_rate": 7.45866462322802e-06,
      "loss": 1.27587890625,
      "step": 38
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.20446960628032684,
      "learning_rate": 7.333336616128369e-06,
      "loss": 1.203125,
      "step": 39
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.20624497532844543,
      "learning_rate": 7.206105506216107e-06,
      "loss": 1.25830078125,
      "step": 40
    },
    {
      "epoch": 0.7454545454545455,
      "grad_norm": 0.21159856021404266,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 1.1845703125,
      "step": 41
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.20678693056106567,
      "learning_rate": 6.946350531586959e-06,
      "loss": 1.19091796875,
      "step": 42
    },
    {
      "epoch": 0.7818181818181819,
      "grad_norm": 0.20037050545215607,
      "learning_rate": 6.814038526753205e-06,
      "loss": 1.204833984375,
      "step": 43
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.17004463076591492,
      "learning_rate": 6.680246966077151e-06,
      "loss": 1.2080078125,
      "step": 44
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.1704520583152771,
      "learning_rate": 6.545084971874738e-06,
      "loss": 1.15478515625,
      "step": 45
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 0.25000882148742676,
      "learning_rate": 6.408662784207149e-06,
      "loss": 1.1953125,
      "step": 46
    },
    {
      "epoch": 0.8545454545454545,
      "grad_norm": 0.26687896251678467,
      "learning_rate": 6.271091670967437e-06,
      "loss": 1.1884765625,
      "step": 47
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.11884502321481705,
      "learning_rate": 6.132483837128823e-06,
      "loss": 1.1826171875,
      "step": 48
    },
    {
      "epoch": 0.8909090909090909,
      "grad_norm": 0.11220335960388184,
      "learning_rate": 5.9929523332287275e-06,
      "loss": 1.17822265625,
      "step": 49
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.11708816140890121,
      "learning_rate": 5.85261096316312e-06,
      "loss": 1.17919921875,
      "step": 50
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.13113504648208618,
      "learning_rate": 5.711574191366427e-06,
      "loss": 1.248046875,
      "step": 51
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.1367698758840561,
      "learning_rate": 5.569957049452703e-06,
      "loss": 1.15576171875,
      "step": 52
    },
    {
      "epoch": 0.9636363636363636,
      "grad_norm": 0.12517711520195007,
      "learning_rate": 5.4278750423942e-06,
      "loss": 1.1552734375,
      "step": 53
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.11927603930234909,
      "learning_rate": 5.285444054313841e-06,
      "loss": 1.2119140625,
      "step": 54
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11289802938699722,
      "learning_rate": 5.142780253968481e-06,
      "loss": 1.18212890625,
      "step": 55
    },
    {
      "epoch": 1.018181818181818,
      "grad_norm": 0.09079399704933167,
      "learning_rate": 5e-06,
      "loss": 1.16162109375,
      "step": 56
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 0.09751984477043152,
      "learning_rate": 4.85721974603152e-06,
      "loss": 1.1767578125,
      "step": 57
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 0.09680410474538803,
      "learning_rate": 4.71455594568616e-06,
      "loss": 1.19873046875,
      "step": 58
    },
    {
      "epoch": 1.0727272727272728,
      "grad_norm": 0.08057751506567001,
      "learning_rate": 4.572124957605803e-06,
      "loss": 1.16455078125,
      "step": 59
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.0873107761144638,
      "learning_rate": 4.430042950547298e-06,
      "loss": 1.1708984375,
      "step": 60
    },
    {
      "epoch": 1.1090909090909091,
      "grad_norm": 0.08605661243200302,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 1.1630859375,
      "step": 61
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 0.08335281908512115,
      "learning_rate": 4.147389036836881e-06,
      "loss": 1.13671875,
      "step": 62
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 0.09709643572568893,
      "learning_rate": 4.007047666771274e-06,
      "loss": 1.123046875,
      "step": 63
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 0.07813747227191925,
      "learning_rate": 3.867516162871177e-06,
      "loss": 1.14697265625,
      "step": 64
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.07940645515918732,
      "learning_rate": 3.7289083290325668e-06,
      "loss": 1.185546875,
      "step": 65
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.0847330167889595,
      "learning_rate": 3.5913372157928515e-06,
      "loss": 1.14892578125,
      "step": 66
    },
    {
      "epoch": 1.2181818181818183,
      "grad_norm": 0.0767209529876709,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 1.1279296875,
      "step": 67
    },
    {
      "epoch": 1.2363636363636363,
      "grad_norm": 0.07237398624420166,
      "learning_rate": 3.319753033922849e-06,
      "loss": 1.16357421875,
      "step": 68
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 0.06874033063650131,
      "learning_rate": 3.1859614732467957e-06,
      "loss": 1.1767578125,
      "step": 69
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.06955976039171219,
      "learning_rate": 3.053649468413043e-06,
      "loss": 1.165283203125,
      "step": 70
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 0.0963461771607399,
      "learning_rate": 2.9229249349905686e-06,
      "loss": 1.19482421875,
      "step": 71
    },
    {
      "epoch": 1.309090909090909,
      "grad_norm": 0.10361190140247345,
      "learning_rate": 2.7938944937838924e-06,
      "loss": 1.169921875,
      "step": 72
    },
    {
      "epoch": 1.3272727272727272,
      "grad_norm": 0.0700468048453331,
      "learning_rate": 2.6666633838716317e-06,
      "loss": 1.14697265625,
      "step": 73
    },
    {
      "epoch": 1.3454545454545455,
      "grad_norm": 0.08605919778347015,
      "learning_rate": 2.5413353767719805e-06,
      "loss": 1.18701171875,
      "step": 74
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.07441291958093643,
      "learning_rate": 2.418012691805191e-06,
      "loss": 1.125,
      "step": 75
    },
    {
      "epoch": 1.3818181818181818,
      "grad_norm": 0.07339707762002945,
      "learning_rate": 2.296795912722014e-06,
      "loss": 1.13427734375,
      "step": 76
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.07407637685537338,
      "learning_rate": 2.1777839056661555e-06,
      "loss": 1.16650390625,
      "step": 77
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 0.07568876445293427,
      "learning_rate": 2.061073738537635e-06,
      "loss": 1.15478515625,
      "step": 78
    },
    {
      "epoch": 1.4363636363636363,
      "grad_norm": 0.062244512140750885,
      "learning_rate": 1.946760601822809e-06,
      "loss": 1.15087890625,
      "step": 79
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.06542546302080154,
      "learning_rate": 1.8349377309556487e-06,
      "loss": 1.164794921875,
      "step": 80
    },
    {
      "epoch": 1.4727272727272727,
      "grad_norm": 0.06182748079299927,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 1.158203125,
      "step": 81
    },
    {
      "epoch": 1.490909090909091,
      "grad_norm": 0.0789041593670845,
      "learning_rate": 1.6191254986299044e-06,
      "loss": 1.13427734375,
      "step": 82
    },
    {
      "epoch": 1.509090909090909,
      "grad_norm": 0.0626092255115509,
      "learning_rate": 1.5153121567235334e-06,
      "loss": 1.147705078125,
      "step": 83
    },
    {
      "epoch": 1.5272727272727273,
      "grad_norm": 0.072810098528862,
      "learning_rate": 1.4143409762051829e-06,
      "loss": 1.1201171875,
      "step": 84
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.07056964188814163,
      "learning_rate": 1.3162943106179748e-06,
      "loss": 1.0986328125,
      "step": 85
    },
    {
      "epoch": 1.5636363636363635,
      "grad_norm": 0.06387604773044586,
      "learning_rate": 1.2212521282287093e-06,
      "loss": 1.1708984375,
      "step": 86
    },
    {
      "epoch": 1.5818181818181818,
      "grad_norm": 0.0639725774526596,
      "learning_rate": 1.1292919468045876e-06,
      "loss": 1.1875,
      "step": 87
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.05896006152033806,
      "learning_rate": 1.0404887703886252e-06,
      "loss": 1.111328125,
      "step": 88
    },
    {
      "epoch": 1.6181818181818182,
      "grad_norm": 0.12896744906902313,
      "learning_rate": 9.549150281252633e-07,
      "loss": 1.101806640625,
      "step": 89
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.08080096542835236,
      "learning_rate": 8.7264051518613e-07,
      "loss": 1.1220703125,
      "step": 90
    },
    {
      "epoch": 1.6545454545454545,
      "grad_norm": 0.06684555858373642,
      "learning_rate": 7.937323358440935e-07,
      "loss": 1.14306640625,
      "step": 91
    },
    {
      "epoch": 1.6727272727272728,
      "grad_norm": 0.05942356213927269,
      "learning_rate": 7.182548487420555e-07,
      "loss": 1.14013671875,
      "step": 92
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 0.07880666106939316,
      "learning_rate": 6.462696144011149e-07,
      "loss": 1.173828125,
      "step": 93
    },
    {
      "epoch": 1.709090909090909,
      "grad_norm": 0.06027885526418686,
      "learning_rate": 5.778353450109286e-07,
      "loss": 1.11279296875,
      "step": 94
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.0611584335565567,
      "learning_rate": 5.130078565432089e-07,
      "loss": 1.17431640625,
      "step": 95
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 0.0627589002251625,
      "learning_rate": 4.5184002322740784e-07,
      "loss": 1.1083984375,
      "step": 96
    },
    {
      "epoch": 1.7636363636363637,
      "grad_norm": 0.061538759618997574,
      "learning_rate": 3.9438173442575e-07,
      "loss": 1.1259765625,
      "step": 97
    },
    {
      "epoch": 1.7818181818181817,
      "grad_norm": 0.06338467448949814,
      "learning_rate": 3.406798539427386e-07,
      "loss": 1.1396484375,
      "step": 98
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.06770215928554535,
      "learning_rate": 2.9077818180237693e-07,
      "loss": 1.15087890625,
      "step": 99
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.061797644942998886,
      "learning_rate": 2.447174185242324e-07,
      "loss": 1.10302734375,
      "step": 100
    },
    {
      "epoch": 1.8363636363636364,
      "grad_norm": 0.06173209846019745,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 1.14208984375,
      "step": 101
    },
    {
      "epoch": 1.8545454545454545,
      "grad_norm": 0.06665000319480896,
      "learning_rate": 1.6426572649021477e-07,
      "loss": 1.1396484375,
      "step": 102
    },
    {
      "epoch": 1.8727272727272726,
      "grad_norm": 0.06044939532876015,
      "learning_rate": 1.2994041528833267e-07,
      "loss": 1.13916015625,
      "step": 103
    },
    {
      "epoch": 1.8909090909090909,
      "grad_norm": 0.06250400841236115,
      "learning_rate": 9.958719453803278e-08,
      "loss": 1.14013671875,
      "step": 104
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.059070732444524765,
      "learning_rate": 7.32308207615351e-08,
      "loss": 1.1396484375,
      "step": 105
    },
    {
      "epoch": 1.9272727272727272,
      "grad_norm": 0.06301233917474747,
      "learning_rate": 5.089279059533658e-08,
      "loss": 1.212890625,
      "step": 106
    },
    {
      "epoch": 1.9454545454545453,
      "grad_norm": 0.059316884726285934,
      "learning_rate": 3.25913232572489e-08,
      "loss": 1.119140625,
      "step": 107
    },
    {
      "epoch": 1.9636363636363636,
      "grad_norm": 0.05868269130587578,
      "learning_rate": 1.834134568654333e-08,
      "loss": 1.12255859375,
      "step": 108
    },
    {
      "epoch": 1.981818181818182,
      "grad_norm": 0.0642366111278534,
      "learning_rate": 8.15448036932176e-09,
      "loss": 1.1806640625,
      "step": 109
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.06383895128965378,
      "learning_rate": 2.0390358590538507e-09,
      "loss": 1.15185546875,
      "step": 110
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.192138671875,
      "eval_runtime": 1.9189,
      "eval_samples_per_second": 5.211,
      "eval_steps_per_second": 0.521,
      "step": 110
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5003689757670113e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}