{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4783147459727384,
  "eval_steps": 42,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004956629491945477,
      "eval_loss": 11.9326810836792,
      "eval_runtime": 1.7783,
      "eval_samples_per_second": 191.195,
      "eval_steps_per_second": 24.181,
      "step": 1
    },
    {
      "epoch": 0.01486988847583643,
      "grad_norm": 0.021911758929491043,
      "learning_rate": 3e-05,
      "loss": 11.9334,
      "step": 3
    },
    {
      "epoch": 0.02973977695167286,
      "grad_norm": 0.023962631821632385,
      "learning_rate": 6e-05,
      "loss": 11.9313,
      "step": 6
    },
    {
      "epoch": 0.04460966542750929,
      "grad_norm": 0.03333725035190582,
      "learning_rate": 9e-05,
      "loss": 11.9339,
      "step": 9
    },
    {
      "epoch": 0.05947955390334572,
      "grad_norm": 0.033243514597415924,
      "learning_rate": 9.999588943391597e-05,
      "loss": 11.9306,
      "step": 12
    },
    {
      "epoch": 0.07434944237918216,
      "grad_norm": 0.04458344355225563,
      "learning_rate": 9.99743108100344e-05,
      "loss": 11.9308,
      "step": 15
    },
    {
      "epoch": 0.08921933085501858,
      "grad_norm": 0.052610304206609726,
      "learning_rate": 9.993424445916923e-05,
      "loss": 11.9319,
      "step": 18
    },
    {
      "epoch": 0.10408921933085502,
      "grad_norm": 0.07262662053108215,
      "learning_rate": 9.987570520365104e-05,
      "loss": 11.9302,
      "step": 21
    },
    {
      "epoch": 0.11895910780669144,
      "grad_norm": 0.058128416538238525,
      "learning_rate": 9.979871469976196e-05,
      "loss": 11.93,
      "step": 24
    },
    {
      "epoch": 0.13382899628252787,
      "grad_norm": 0.0720035582780838,
      "learning_rate": 9.970330142972401e-05,
      "loss": 11.9281,
      "step": 27
    },
    {
      "epoch": 0.14869888475836432,
      "grad_norm": 0.09731002151966095,
      "learning_rate": 9.95895006911623e-05,
      "loss": 11.9291,
      "step": 30
    },
    {
      "epoch": 0.16356877323420074,
      "grad_norm": 0.12672215700149536,
      "learning_rate": 9.945735458404681e-05,
      "loss": 11.9264,
      "step": 33
    },
    {
      "epoch": 0.17843866171003717,
      "grad_norm": 0.1286524087190628,
      "learning_rate": 9.930691199511775e-05,
      "loss": 11.9261,
      "step": 36
    },
    {
      "epoch": 0.19330855018587362,
      "grad_norm": 0.07290291041135788,
      "learning_rate": 9.91382285798002e-05,
      "loss": 11.9238,
      "step": 39
    },
    {
      "epoch": 0.20817843866171004,
      "grad_norm": 0.10860157757997513,
      "learning_rate": 9.895136674161465e-05,
      "loss": 11.9245,
      "step": 42
    },
    {
      "epoch": 0.20817843866171004,
      "eval_loss": 11.923065185546875,
      "eval_runtime": 1.7832,
      "eval_samples_per_second": 190.666,
      "eval_steps_per_second": 24.114,
      "step": 42
    },
    {
      "epoch": 0.22304832713754646,
      "grad_norm": 0.05279519036412239,
      "learning_rate": 9.874639560909117e-05,
      "loss": 11.9242,
      "step": 45
    },
    {
      "epoch": 0.2379182156133829,
      "grad_norm": 0.04096081852912903,
      "learning_rate": 9.852339101019574e-05,
      "loss": 11.9223,
      "step": 48
    },
    {
      "epoch": 0.2527881040892193,
      "grad_norm": 0.058863602578639984,
      "learning_rate": 9.828243544427796e-05,
      "loss": 11.9211,
      "step": 51
    },
    {
      "epoch": 0.26765799256505574,
      "grad_norm": 0.042531974613666534,
      "learning_rate": 9.802361805155097e-05,
      "loss": 11.9209,
      "step": 54
    },
    {
      "epoch": 0.2825278810408922,
      "grad_norm": 0.032496560364961624,
      "learning_rate": 9.774703458011453e-05,
      "loss": 11.9219,
      "step": 57
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 0.047955676913261414,
      "learning_rate": 9.745278735053343e-05,
      "loss": 11.9211,
      "step": 60
    },
    {
      "epoch": 0.31226765799256506,
      "grad_norm": 0.046965163201093674,
      "learning_rate": 9.714098521798465e-05,
      "loss": 11.9214,
      "step": 63
    },
    {
      "epoch": 0.3271375464684015,
      "grad_norm": 0.0456559844315052,
      "learning_rate": 9.681174353198687e-05,
      "loss": 11.9209,
      "step": 66
    },
    {
      "epoch": 0.3420074349442379,
      "grad_norm": 0.03221632167696953,
      "learning_rate": 9.64651840937276e-05,
      "loss": 11.9206,
      "step": 69
    },
    {
      "epoch": 0.35687732342007433,
      "grad_norm": 0.04287073761224747,
      "learning_rate": 9.610143511100354e-05,
      "loss": 11.9213,
      "step": 72
    },
    {
      "epoch": 0.37174721189591076,
      "grad_norm": 0.02795012667775154,
      "learning_rate": 9.572063115079063e-05,
      "loss": 11.9218,
      "step": 75
    },
    {
      "epoch": 0.38661710037174724,
      "grad_norm": 0.04518656060099602,
      "learning_rate": 9.53229130894619e-05,
      "loss": 11.9199,
      "step": 78
    },
    {
      "epoch": 0.40148698884758366,
      "grad_norm": 0.04366651177406311,
      "learning_rate": 9.490842806067095e-05,
      "loss": 11.9215,
      "step": 81
    },
    {
      "epoch": 0.4163568773234201,
      "grad_norm": 0.03678198903799057,
      "learning_rate": 9.44773294009206e-05,
      "loss": 11.9213,
      "step": 84
    },
    {
      "epoch": 0.4163568773234201,
      "eval_loss": 11.920437812805176,
      "eval_runtime": 1.7948,
      "eval_samples_per_second": 189.431,
      "eval_steps_per_second": 23.957,
      "step": 84
    },
    {
      "epoch": 0.4312267657992565,
      "grad_norm": 0.023460518568754196,
      "learning_rate": 9.40297765928369e-05,
      "loss": 11.9217,
      "step": 87
    },
    {
      "epoch": 0.44609665427509293,
      "grad_norm": 0.024318113923072815,
      "learning_rate": 9.356593520616948e-05,
      "loss": 11.9213,
      "step": 90
    },
    {
      "epoch": 0.46096654275092935,
      "grad_norm": 0.049881741404533386,
      "learning_rate": 9.308597683653975e-05,
      "loss": 11.9201,
      "step": 93
    },
    {
      "epoch": 0.4758364312267658,
      "grad_norm": 0.04094057157635689,
      "learning_rate": 9.259007904196023e-05,
      "loss": 11.9212,
      "step": 96
    },
    {
      "epoch": 0.49070631970260226,
      "grad_norm": 0.027084438130259514,
      "learning_rate": 9.207842527714767e-05,
      "loss": 11.9202,
      "step": 99
    },
    {
      "epoch": 0.5055762081784386,
      "grad_norm": 0.039569973945617676,
      "learning_rate": 9.155120482565521e-05,
      "loss": 11.9205,
      "step": 102
    },
    {
      "epoch": 0.5204460966542751,
      "grad_norm": 0.0342690534889698,
      "learning_rate": 9.10086127298478e-05,
      "loss": 11.9208,
      "step": 105
    },
    {
      "epoch": 0.5353159851301115,
      "grad_norm": 0.040326882153749466,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9197,
      "step": 108
    },
    {
      "epoch": 0.550185873605948,
      "grad_norm": 0.04327003285288811,
      "learning_rate": 8.987812213377424e-05,
      "loss": 11.92,
      "step": 111
    },
    {
      "epoch": 0.5650557620817844,
      "grad_norm": 0.036849964410066605,
      "learning_rate": 8.929064185241213e-05,
      "loss": 11.9206,
      "step": 114
    },
    {
      "epoch": 0.5799256505576208,
      "grad_norm": 0.031241154298186302,
      "learning_rate": 8.868862620982534e-05,
      "loss": 11.9197,
      "step": 117
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 0.03847566619515419,
      "learning_rate": 8.807229791845673e-05,
      "loss": 11.9206,
      "step": 120
    },
    {
      "epoch": 0.6096654275092936,
      "grad_norm": 0.028667431324720383,
      "learning_rate": 8.744188498563641e-05,
      "loss": 11.9187,
      "step": 123
    },
    {
      "epoch": 0.6245353159851301,
      "grad_norm": 0.033852025866508484,
      "learning_rate": 8.679762062923175e-05,
      "loss": 11.9202,
      "step": 126
    },
    {
      "epoch": 0.6245353159851301,
      "eval_loss": 11.91907024383545,
      "eval_runtime": 1.7852,
      "eval_samples_per_second": 190.457,
      "eval_steps_per_second": 24.087,
      "step": 126
    },
    {
      "epoch": 0.6394052044609665,
      "grad_norm": 0.02974875643849373,
      "learning_rate": 8.613974319136958e-05,
      "loss": 11.9185,
      "step": 129
    },
    {
      "epoch": 0.654275092936803,
      "grad_norm": 0.03015587106347084,
      "learning_rate": 8.54684960502629e-05,
      "loss": 11.9188,
      "step": 132
    },
    {
      "epoch": 0.6691449814126395,
      "grad_norm": 0.03938285633921623,
      "learning_rate": 8.478412753017433e-05,
      "loss": 11.9191,
      "step": 135
    },
    {
      "epoch": 0.6840148698884758,
      "grad_norm": 0.03826509043574333,
      "learning_rate": 8.408689080954998e-05,
      "loss": 11.9189,
      "step": 138
    },
    {
      "epoch": 0.6988847583643123,
      "grad_norm": 0.03719158098101616,
      "learning_rate": 8.33770438273574e-05,
      "loss": 11.9192,
      "step": 141
    },
    {
      "epoch": 0.7137546468401487,
      "grad_norm": 0.029518159106373787,
      "learning_rate": 8.265484918766243e-05,
      "loss": 11.9173,
      "step": 144
    },
    {
      "epoch": 0.7286245353159851,
      "grad_norm": 0.036953601986169815,
      "learning_rate": 8.192057406248028e-05,
      "loss": 11.9192,
      "step": 147
    },
    {
      "epoch": 0.7434944237918215,
      "grad_norm": 0.029631230980157852,
      "learning_rate": 8.117449009293668e-05,
      "loss": 11.9204,
      "step": 150
    },
    {
      "epoch": 0.758364312267658,
      "grad_norm": 0.045844074338674545,
      "learning_rate": 8.041687328877567e-05,
      "loss": 11.9189,
      "step": 153
    },
    {
      "epoch": 0.7732342007434945,
      "grad_norm": 0.03137771785259247,
      "learning_rate": 7.964800392625129e-05,
      "loss": 11.9176,
      "step": 156
    },
    {
      "epoch": 0.7881040892193308,
      "grad_norm": 0.04033302888274193,
      "learning_rate": 7.886816644444098e-05,
      "loss": 11.9179,
      "step": 159
    },
    {
      "epoch": 0.8029739776951673,
      "grad_norm": 0.05383464694023132,
      "learning_rate": 7.807764934001874e-05,
      "loss": 11.9192,
      "step": 162
    },
    {
      "epoch": 0.8178438661710037,
      "grad_norm": 0.04305844381451607,
      "learning_rate": 7.727674506052743e-05,
      "loss": 11.9175,
      "step": 165
    },
    {
      "epoch": 0.8327137546468402,
      "grad_norm": 0.04624446481466293,
      "learning_rate": 7.646574989618938e-05,
      "loss": 11.9179,
      "step": 168
    },
    {
      "epoch": 0.8327137546468402,
      "eval_loss": 11.916953086853027,
      "eval_runtime": 1.7891,
      "eval_samples_per_second": 190.043,
      "eval_steps_per_second": 24.035,
      "step": 168
    },
    {
      "epoch": 0.8475836431226765,
      "grad_norm": 0.04116937518119812,
      "learning_rate": 7.564496387029532e-05,
      "loss": 11.9188,
      "step": 171
    },
    {
      "epoch": 0.862453531598513,
      "grad_norm": 0.047030821442604065,
      "learning_rate": 7.481469062821252e-05,
      "loss": 11.9165,
      "step": 174
    },
    {
      "epoch": 0.8773234200743495,
      "grad_norm": 0.04179559275507927,
      "learning_rate": 7.39752373250527e-05,
      "loss": 11.9173,
      "step": 177
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 0.035439781844615936,
      "learning_rate": 7.312691451204178e-05,
      "loss": 11.9156,
      "step": 180
    },
    {
      "epoch": 0.9070631970260223,
      "grad_norm": 0.034943871200084686,
      "learning_rate": 7.227003602163295e-05,
      "loss": 11.9169,
      "step": 183
    },
    {
      "epoch": 0.9219330855018587,
      "grad_norm": 0.05772566422820091,
      "learning_rate": 7.14049188514063e-05,
      "loss": 11.9182,
      "step": 186
    },
    {
      "epoch": 0.9368029739776952,
      "grad_norm": 0.03869827464222908,
      "learning_rate": 7.05318830467969e-05,
      "loss": 11.9158,
      "step": 189
    },
    {
      "epoch": 0.9516728624535316,
      "grad_norm": 0.04426341503858566,
      "learning_rate": 6.965125158269619e-05,
      "loss": 11.9162,
      "step": 192
    },
    {
      "epoch": 0.966542750929368,
      "grad_norm": 0.03408205881714821,
      "learning_rate": 6.876335024396872e-05,
      "loss": 11.917,
      "step": 195
    },
    {
      "epoch": 0.9814126394052045,
      "grad_norm": 0.05809081718325615,
      "learning_rate": 6.786850750493006e-05,
      "loss": 11.9167,
      "step": 198
    },
    {
      "epoch": 0.9962825278810409,
      "grad_norm": 0.04577980935573578,
      "learning_rate": 6.696705440782938e-05,
      "loss": 11.9165,
      "step": 201
    },
    {
      "epoch": 1.0111524163568772,
      "grad_norm": 0.057778336107730865,
      "learning_rate": 6.605932444038229e-05,
      "loss": 12.9382,
      "step": 204
    },
    {
      "epoch": 1.0260223048327137,
      "grad_norm": 0.04783137887716293,
      "learning_rate": 6.514565341239861e-05,
      "loss": 11.9452,
      "step": 207
    },
    {
      "epoch": 1.0408921933085502,
      "grad_norm": 0.0524618998169899,
      "learning_rate": 6.422637933155162e-05,
      "loss": 12.2734,
      "step": 210
    },
    {
      "epoch": 1.0408921933085502,
      "eval_loss": 11.91499137878418,
      "eval_runtime": 1.7898,
      "eval_samples_per_second": 189.967,
      "eval_steps_per_second": 24.025,
      "step": 210
    },
    {
      "epoch": 1.0557620817843867,
      "grad_norm": 0.05849219486117363,
      "learning_rate": 6.330184227833376e-05,
      "loss": 11.5033,
      "step": 213
    },
    {
      "epoch": 1.070631970260223,
      "grad_norm": 0.033805862069129944,
      "learning_rate": 6.237238428024572e-05,
      "loss": 11.9935,
      "step": 216
    },
    {
      "epoch": 1.0855018587360594,
      "grad_norm": 0.03404450789093971,
      "learning_rate": 6.143834918526527e-05,
      "loss": 11.5313,
      "step": 219
    },
    {
      "epoch": 1.100371747211896,
      "grad_norm": 0.04725867882370949,
      "learning_rate": 6.0500082534642464e-05,
      "loss": 12.2978,
      "step": 222
    },
    {
      "epoch": 1.1152416356877324,
      "grad_norm": 0.03899763897061348,
      "learning_rate": 5.955793143506863e-05,
      "loss": 11.65,
      "step": 225
    },
    {
      "epoch": 1.1301115241635689,
      "grad_norm": 0.04015621915459633,
      "learning_rate": 5.861224443026595e-05,
      "loss": 11.884,
      "step": 228
    },
    {
      "epoch": 1.1449814126394051,
      "grad_norm": 0.036584775894880295,
      "learning_rate": 5.766337137204579e-05,
      "loss": 12.0427,
      "step": 231
    },
    {
      "epoch": 1.1598513011152416,
      "grad_norm": 0.03569253534078598,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 12.0982,
      "step": 234
    },
    {
      "epoch": 1.174721189591078,
      "grad_norm": 0.03620843589305878,
      "learning_rate": 5.575747226605298e-05,
      "loss": 11.5985,
      "step": 237
    },
    {
      "epoch": 1.1895910780669146,
      "grad_norm": 0.04758467897772789,
      "learning_rate": 5.480115129538409e-05,
      "loss": 11.9431,
      "step": 240
    },
    {
      "epoch": 1.2044609665427508,
      "grad_norm": 0.05280792713165283,
      "learning_rate": 5.384305416466584e-05,
      "loss": 12.3327,
      "step": 243
    },
    {
      "epoch": 1.2193308550185873,
      "grad_norm": 0.04065597429871559,
      "learning_rate": 5.288353531676873e-05,
      "loss": 11.808,
      "step": 246
    },
    {
      "epoch": 1.2342007434944238,
      "grad_norm": 0.054324232041835785,
      "learning_rate": 5.192294972051992e-05,
      "loss": 11.9609,
      "step": 249
    },
    {
      "epoch": 1.2490706319702602,
      "grad_norm": 0.05009124055504799,
      "learning_rate": 5.0961652739384356e-05,
      "loss": 11.8481,
      "step": 252
    },
    {
      "epoch": 1.2490706319702602,
      "eval_loss": 11.913633346557617,
      "eval_runtime": 1.7911,
      "eval_samples_per_second": 189.827,
      "eval_steps_per_second": 24.008,
      "step": 252
    },
    {
      "epoch": 1.2639405204460967,
      "grad_norm": 0.04657704755663872,
      "learning_rate": 5e-05,
      "loss": 11.8575,
      "step": 255
    },
    {
      "epoch": 1.2788104089219332,
      "grad_norm": 0.0462481752038002,
      "learning_rate": 4.903834726061565e-05,
      "loss": 11.8051,
      "step": 258
    },
    {
      "epoch": 1.2936802973977695,
      "grad_norm": 0.04893633350729942,
      "learning_rate": 4.807705027948008e-05,
      "loss": 12.0714,
      "step": 261
    },
    {
      "epoch": 1.308550185873606,
      "grad_norm": 0.04405223950743675,
      "learning_rate": 4.711646468323129e-05,
      "loss": 12.0378,
      "step": 264
    },
    {
      "epoch": 1.3234200743494424,
      "grad_norm": 0.03830258920788765,
      "learning_rate": 4.6156945835334184e-05,
      "loss": 11.4953,
      "step": 267
    },
    {
      "epoch": 1.3382899628252787,
      "grad_norm": 0.05353306978940964,
      "learning_rate": 4.5198848704615914e-05,
      "loss": 11.9302,
      "step": 270
    },
    {
      "epoch": 1.3531598513011152,
      "grad_norm": 0.04591304063796997,
      "learning_rate": 4.424252773394704e-05,
      "loss": 11.8904,
      "step": 273
    },
    {
      "epoch": 1.3680297397769516,
      "grad_norm": 0.06073668599128723,
      "learning_rate": 4.328833670911724e-05,
      "loss": 11.887,
      "step": 276
    },
    {
      "epoch": 1.3828996282527881,
      "grad_norm": 0.05969596654176712,
      "learning_rate": 4.23366286279542e-05,
      "loss": 12.2583,
      "step": 279
    },
    {
      "epoch": 1.3977695167286246,
      "grad_norm": 0.05688675865530968,
      "learning_rate": 4.138775556973406e-05,
      "loss": 11.9721,
      "step": 282
    },
    {
      "epoch": 1.412639405204461,
      "grad_norm": 0.044570520520210266,
      "learning_rate": 4.04420685649314e-05,
      "loss": 11.8229,
      "step": 285
    },
    {
      "epoch": 1.4275092936802973,
      "grad_norm": 0.0395139679312706,
      "learning_rate": 3.9499917465357534e-05,
      "loss": 12.044,
      "step": 288
    },
    {
      "epoch": 1.4423791821561338,
      "grad_norm": 0.04410000145435333,
      "learning_rate": 3.856165081473474e-05,
      "loss": 11.6002,
      "step": 291
    },
    {
      "epoch": 1.4572490706319703,
      "grad_norm": 0.03875131905078888,
      "learning_rate": 3.762761571975429e-05,
      "loss": 12.0345,
      "step": 294
    },
    {
      "epoch": 1.4572490706319703,
      "eval_loss": 11.912762641906738,
      "eval_runtime": 1.7821,
      "eval_samples_per_second": 190.782,
      "eval_steps_per_second": 24.128,
      "step": 294
    },
    {
      "epoch": 1.4721189591078068,
      "grad_norm": 0.03900081291794777,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 11.957,
      "step": 297
    },
    {
      "epoch": 1.486988847583643,
      "grad_norm": 0.05851195752620697,
      "learning_rate": 3.5773620668448384e-05,
      "loss": 12.2009,
      "step": 300
    },
    {
      "epoch": 1.5018587360594795,
      "grad_norm": 0.040698371827602386,
      "learning_rate": 3.48543465876014e-05,
      "loss": 11.5507,
      "step": 303
    },
    {
      "epoch": 1.516728624535316,
      "grad_norm": 0.051156215369701385,
      "learning_rate": 3.3940675559617724e-05,
      "loss": 11.9339,
      "step": 306
    },
    {
      "epoch": 1.5315985130111525,
      "grad_norm": 0.04702401161193848,
      "learning_rate": 3.303294559217063e-05,
      "loss": 11.9592,
      "step": 309
    },
    {
      "epoch": 1.546468401486989,
      "grad_norm": 0.052173860371112823,
      "learning_rate": 3.213149249506997e-05,
      "loss": 12.1149,
      "step": 312
    },
    {
      "epoch": 1.5613382899628254,
      "grad_norm": 0.04223547503352165,
      "learning_rate": 3.12366497560313e-05,
      "loss": 11.7891,
      "step": 315
    },
    {
      "epoch": 1.5762081784386617,
      "grad_norm": 0.04051812365651131,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 11.88,
      "step": 318
    },
    {
      "epoch": 1.5910780669144982,
      "grad_norm": 0.04893014580011368,
      "learning_rate": 2.9468116953203107e-05,
      "loss": 12.0515,
      "step": 321
    },
    {
      "epoch": 1.6059479553903344,
      "grad_norm": 0.034630462527275085,
      "learning_rate": 2.8595081148593738e-05,
      "loss": 11.7524,
      "step": 324
    },
    {
      "epoch": 1.620817843866171,
      "grad_norm": 0.04877002164721489,
      "learning_rate": 2.772996397836704e-05,
      "loss": 12.0419,
      "step": 327
    },
    {
      "epoch": 1.6356877323420074,
      "grad_norm": 0.04910058155655861,
      "learning_rate": 2.687308548795825e-05,
      "loss": 11.8161,
      "step": 330
    },
    {
      "epoch": 1.6505576208178439,
      "grad_norm": 0.07067956030368805,
      "learning_rate": 2.6024762674947313e-05,
      "loss": 12.0154,
      "step": 333
    },
    {
      "epoch": 1.6654275092936803,
      "grad_norm": 0.05364261567592621,
      "learning_rate": 2.5185309371787513e-05,
      "loss": 11.6038,
      "step": 336
    },
    {
      "epoch": 1.6654275092936803,
      "eval_loss": 11.912201881408691,
      "eval_runtime": 1.7828,
      "eval_samples_per_second": 190.715,
      "eval_steps_per_second": 24.12,
      "step": 336
    },
    {
      "epoch": 1.6802973977695168,
      "grad_norm": 0.05523364245891571,
      "learning_rate": 2.43550361297047e-05,
      "loss": 12.134,
      "step": 339
    },
    {
      "epoch": 1.6951672862453533,
      "grad_norm": 0.048208702355623245,
      "learning_rate": 2.353425010381063e-05,
      "loss": 11.7113,
      "step": 342
    },
    {
      "epoch": 1.7100371747211895,
      "grad_norm": 0.05443693697452545,
      "learning_rate": 2.272325493947257e-05,
      "loss": 12.0261,
      "step": 345
    },
    {
      "epoch": 1.724907063197026,
      "grad_norm": 0.04431464150547981,
      "learning_rate": 2.192235065998126e-05,
      "loss": 11.7941,
      "step": 348
    },
    {
      "epoch": 1.7397769516728625,
      "grad_norm": 0.051699794828891754,
      "learning_rate": 2.1131833555559037e-05,
      "loss": 11.828,
      "step": 351
    },
    {
      "epoch": 1.7546468401486988,
      "grad_norm": 0.05203912407159805,
      "learning_rate": 2.0351996073748713e-05,
      "loss": 12.2296,
      "step": 354
    },
    {
      "epoch": 1.7695167286245352,
      "grad_norm": 0.0487595833837986,
      "learning_rate": 1.9583126711224343e-05,
      "loss": 12.0436,
      "step": 357
    },
    {
      "epoch": 1.7843866171003717,
      "grad_norm": 0.052862875163555145,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 12.0195,
      "step": 360
    },
    {
      "epoch": 1.7992565055762082,
      "grad_norm": 0.0489225871860981,
      "learning_rate": 1.807942593751973e-05,
      "loss": 11.4072,
      "step": 363
    },
    {
      "epoch": 1.8141263940520447,
      "grad_norm": 0.0481363870203495,
      "learning_rate": 1.7345150812337564e-05,
      "loss": 12.0078,
      "step": 366
    },
    {
      "epoch": 1.8289962825278812,
      "grad_norm": 0.04153072461485863,
      "learning_rate": 1.66229561726426e-05,
      "loss": 12.0028,
      "step": 369
    },
    {
      "epoch": 1.8438661710037176,
      "grad_norm": 0.036744702607393265,
      "learning_rate": 1.5913109190450032e-05,
      "loss": 11.5179,
      "step": 372
    },
    {
      "epoch": 1.858736059479554,
      "grad_norm": 0.047882892191410065,
      "learning_rate": 1.5215872469825682e-05,
      "loss": 12.3708,
      "step": 375
    },
    {
      "epoch": 1.8736059479553904,
      "grad_norm": 0.04179394617676735,
      "learning_rate": 1.4531503949737108e-05,
      "loss": 11.7007,
      "step": 378
    },
    {
      "epoch": 1.8736059479553904,
      "eval_loss": 11.911933898925781,
      "eval_runtime": 1.7796,
      "eval_samples_per_second": 191.052,
      "eval_steps_per_second": 24.162,
      "step": 378
    },
    {
      "epoch": 1.8884758364312266,
      "grad_norm": 0.05014241859316826,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 11.9337,
      "step": 381
    },
    {
      "epoch": 1.903345724907063,
      "grad_norm": 0.04191575199365616,
      "learning_rate": 1.3202379370768252e-05,
      "loss": 11.9915,
      "step": 384
    },
    {
      "epoch": 1.9182156133828996,
      "grad_norm": 0.05335910990834236,
      "learning_rate": 1.2558115014363592e-05,
      "loss": 12.4018,
      "step": 387
    },
    {
      "epoch": 1.933085501858736,
      "grad_norm": 0.04739459604024887,
      "learning_rate": 1.1927702081543279e-05,
      "loss": 11.3111,
      "step": 390
    },
    {
      "epoch": 1.9479553903345725,
      "grad_norm": 0.05000464618206024,
      "learning_rate": 1.1311373790174657e-05,
      "loss": 11.9361,
      "step": 393
    },
    {
      "epoch": 1.962825278810409,
      "grad_norm": 0.05147460475564003,
      "learning_rate": 1.0709358147587884e-05,
      "loss": 12.0779,
      "step": 396
    },
    {
      "epoch": 1.9776951672862455,
      "grad_norm": 0.050420261919498444,
      "learning_rate": 1.0121877866225781e-05,
      "loss": 12.0052,
      "step": 399
    },
    {
      "epoch": 1.9925650557620818,
      "grad_norm": 0.052469439804553986,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.1211,
      "step": 402
    },
    {
      "epoch": 2.007434944237918,
      "grad_norm": 0.06131839007139206,
      "learning_rate": 8.991387270152201e-06,
      "loss": 13.1191,
      "step": 405
    },
    {
      "epoch": 2.0223048327137545,
      "grad_norm": 0.03518624231219292,
      "learning_rate": 8.448795174344804e-06,
      "loss": 11.1255,
      "step": 408
    },
    {
      "epoch": 2.037174721189591,
      "grad_norm": 0.04108744114637375,
      "learning_rate": 7.921574722852343e-06,
      "loss": 12.2408,
      "step": 411
    },
    {
      "epoch": 2.0520446096654275,
      "grad_norm": 0.04392145946621895,
      "learning_rate": 7.409920958039795e-06,
      "loss": 12.0512,
      "step": 414
    },
    {
      "epoch": 2.066914498141264,
      "grad_norm": 0.05916118621826172,
      "learning_rate": 6.9140231634602485e-06,
      "loss": 12.0364,
      "step": 417
    },
    {
      "epoch": 2.0817843866171004,
      "grad_norm": 0.04456472024321556,
      "learning_rate": 6.43406479383053e-06,
      "loss": 11.2393,
      "step": 420
    },
    {
      "epoch": 2.0817843866171004,
      "eval_loss": 11.911803245544434,
      "eval_runtime": 1.785,
      "eval_samples_per_second": 190.476,
      "eval_steps_per_second": 24.09,
      "step": 420
    },
    {
      "epoch": 2.096654275092937,
      "grad_norm": 0.044985052198171616,
      "learning_rate": 5.9702234071631e-06,
      "loss": 12.1785,
      "step": 423
    },
    {
      "epoch": 2.1115241635687734,
      "grad_norm": 0.04410139098763466,
      "learning_rate": 5.5226705990794155e-06,
      "loss": 12.1236,
      "step": 426
    },
    {
      "epoch": 2.12639405204461,
      "grad_norm": 0.05194435641169548,
      "learning_rate": 5.091571939329048e-06,
      "loss": 11.6732,
      "step": 429
    },
    {
      "epoch": 2.141263940520446,
      "grad_norm": 0.05501653999090195,
      "learning_rate": 4.677086910538092e-06,
      "loss": 12.3777,
      "step": 432
    },
    {
      "epoch": 2.1561338289962824,
      "grad_norm": 0.04983314871788025,
      "learning_rate": 4.279368849209381e-06,
      "loss": 11.8892,
      "step": 435
    },
    {
      "epoch": 2.171003717472119,
      "grad_norm": 0.03725075721740723,
      "learning_rate": 3.898564888996476e-06,
      "loss": 11.2909,
      "step": 438
    },
    {
      "epoch": 2.1858736059479553,
      "grad_norm": 0.05022915452718735,
      "learning_rate": 3.534815906272404e-06,
      "loss": 12.1708,
      "step": 441
    },
    {
      "epoch": 2.200743494423792,
      "grad_norm": 0.04059191420674324,
      "learning_rate": 3.18825646801314e-06,
      "loss": 12.0311,
      "step": 444
    },
    {
      "epoch": 2.2156133828996283,
      "grad_norm": 0.056071698665618896,
      "learning_rate": 2.8590147820153513e-06,
      "loss": 11.767,
      "step": 447
    },
    {
      "epoch": 2.2304832713754648,
      "grad_norm": 0.0420910008251667,
      "learning_rate": 2.547212649466568e-06,
      "loss": 11.9581,
      "step": 450
    },
    {
      "epoch": 2.2453531598513012,
      "grad_norm": 0.05278888717293739,
      "learning_rate": 2.2529654198854835e-06,
      "loss": 12.2002,
      "step": 453
    },
    {
      "epoch": 2.2602230483271377,
      "grad_norm": 0.05625374615192413,
      "learning_rate": 1.9763819484490355e-06,
      "loss": 11.4997,
      "step": 456
    },
    {
      "epoch": 2.2750929368029738,
      "grad_norm": 0.03911924734711647,
      "learning_rate": 1.7175645557220566e-06,
      "loss": 11.6504,
      "step": 459
    },
    {
      "epoch": 2.2899628252788102,
      "grad_norm": 0.054204318672418594,
      "learning_rate": 1.4766089898042678e-06,
      "loss": 12.3732,
      "step": 462
    },
    {
      "epoch": 2.2899628252788102,
      "eval_loss": 11.911750793457031,
      "eval_runtime": 1.7787,
      "eval_samples_per_second": 191.152,
      "eval_steps_per_second": 24.175,
      "step": 462
    },
    {
      "epoch": 2.3048327137546467,
      "grad_norm": 0.04429741948843002,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 11.539,
      "step": 465
    },
    {
      "epoch": 2.319702602230483,
      "grad_norm": 0.04356589540839195,
      "learning_rate": 1.0486332583853563e-06,
      "loss": 12.4901,
      "step": 468
    },
    {
      "epoch": 2.3345724907063197,
      "grad_norm": 0.04233817383646965,
      "learning_rate": 8.617714201998084e-07,
      "loss": 11.4907,
      "step": 471
    },
    {
      "epoch": 2.349442379182156,
      "grad_norm": 0.0563838854432106,
      "learning_rate": 6.93088004882253e-07,
      "loss": 12.2563,
      "step": 474
    },
    {
      "epoch": 2.3643122676579926,
      "grad_norm": 0.05499923229217529,
      "learning_rate": 5.426454159531913e-07,
      "loss": 11.8555,
      "step": 477
    },
    {
      "epoch": 2.379182156133829,
      "grad_norm": 0.044174499809741974,
      "learning_rate": 4.104993088376974e-07,
      "loss": 11.8189,
      "step": 480
    },
    {
      "epoch": 2.3940520446096656,
      "grad_norm": 0.05212130397558212,
      "learning_rate": 2.966985702759828e-07,
      "loss": 12.3588,
      "step": 483
    },
    {
      "epoch": 2.4089219330855016,
      "grad_norm": 0.05286373570561409,
      "learning_rate": 2.012853002380466e-07,
      "loss": 11.2934,
      "step": 486
    },
    {
      "epoch": 2.423791821561338,
      "grad_norm": 0.04788150638341904,
      "learning_rate": 1.2429479634897267e-07,
      "loss": 11.9583,
      "step": 489
    },
    {
      "epoch": 2.4386617100371746,
      "grad_norm": 0.045176565647125244,
      "learning_rate": 6.575554083078084e-08,
      "loss": 11.6715,
      "step": 492
    },
    {
      "epoch": 2.453531598513011,
      "grad_norm": 0.038598958402872086,
      "learning_rate": 2.568918996560532e-08,
      "loss": 12.1975,
      "step": 495
    },
    {
      "epoch": 2.4684014869888475,
      "grad_norm": 0.04955305531620979,
      "learning_rate": 4.110566084036816e-09,
      "loss": 12.0849,
      "step": 498
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2410414080000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}