{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10481081647626035,
  "eval_steps": 42,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002096216329525207,
      "eval_loss": 1.4208108186721802,
      "eval_runtime": 163.5996,
      "eval_samples_per_second": 49.114,
      "eval_steps_per_second": 6.143,
      "step": 1
    },
    {
      "epoch": 0.0006288648988575621,
      "grad_norm": 0.39683395624160767,
      "learning_rate": 3e-05,
      "loss": 1.4354,
      "step": 3
    },
    {
      "epoch": 0.0012577297977151242,
      "grad_norm": 0.4367702305316925,
      "learning_rate": 6e-05,
      "loss": 1.4342,
      "step": 6
    },
    {
      "epoch": 0.0018865946965726864,
      "grad_norm": 0.37110769748687744,
      "learning_rate": 9e-05,
      "loss": 1.3479,
      "step": 9
    },
    {
      "epoch": 0.0025154595954302483,
      "grad_norm": 0.36730247735977173,
      "learning_rate": 9.999588943391597e-05,
      "loss": 1.361,
      "step": 12
    },
    {
      "epoch": 0.0031443244942878103,
      "grad_norm": 0.35089993476867676,
      "learning_rate": 9.99743108100344e-05,
      "loss": 1.2814,
      "step": 15
    },
    {
      "epoch": 0.0037731893931453727,
      "grad_norm": 0.38672298192977905,
      "learning_rate": 9.993424445916923e-05,
      "loss": 1.3016,
      "step": 18
    },
    {
      "epoch": 0.004402054292002935,
      "grad_norm": 0.321205198764801,
      "learning_rate": 9.987570520365104e-05,
      "loss": 1.2163,
      "step": 21
    },
    {
      "epoch": 0.005030919190860497,
      "grad_norm": 0.3282659649848938,
      "learning_rate": 9.979871469976196e-05,
      "loss": 1.2312,
      "step": 24
    },
    {
      "epoch": 0.005659784089718059,
      "grad_norm": 0.3265891373157501,
      "learning_rate": 9.970330142972401e-05,
      "loss": 1.2505,
      "step": 27
    },
    {
      "epoch": 0.006288648988575621,
      "grad_norm": 0.3450949192047119,
      "learning_rate": 9.95895006911623e-05,
      "loss": 1.1982,
      "step": 30
    },
    {
      "epoch": 0.0069175138874331835,
      "grad_norm": 0.3153296411037445,
      "learning_rate": 9.945735458404681e-05,
      "loss": 1.1669,
      "step": 33
    },
    {
      "epoch": 0.0075463787862907455,
      "grad_norm": 0.3419332802295685,
      "learning_rate": 9.930691199511775e-05,
      "loss": 1.2492,
      "step": 36
    },
    {
      "epoch": 0.008175243685148307,
      "grad_norm": 0.2867058515548706,
      "learning_rate": 9.91382285798002e-05,
      "loss": 1.1652,
      "step": 39
    },
    {
      "epoch": 0.00880410858400587,
      "grad_norm": 0.3220820426940918,
      "learning_rate": 9.895136674161465e-05,
      "loss": 1.1996,
      "step": 42
    },
    {
      "epoch": 0.00880410858400587,
      "eval_loss": 1.1905547380447388,
      "eval_runtime": 165.0006,
      "eval_samples_per_second": 48.697,
      "eval_steps_per_second": 6.091,
      "step": 42
    },
    {
      "epoch": 0.009432973482863432,
      "grad_norm": 0.30218949913978577,
      "learning_rate": 9.874639560909117e-05,
      "loss": 1.1916,
      "step": 45
    },
    {
      "epoch": 0.010061838381720993,
      "grad_norm": 0.3343711197376251,
      "learning_rate": 9.852339101019574e-05,
      "loss": 1.1487,
      "step": 48
    },
    {
      "epoch": 0.010690703280578556,
      "grad_norm": 0.3268805146217346,
      "learning_rate": 9.828243544427796e-05,
      "loss": 1.1781,
      "step": 51
    },
    {
      "epoch": 0.011319568179436117,
      "grad_norm": 0.34138286113739014,
      "learning_rate": 9.802361805155097e-05,
      "loss": 1.1215,
      "step": 54
    },
    {
      "epoch": 0.01194843307829368,
      "grad_norm": 0.3412030339241028,
      "learning_rate": 9.774703458011453e-05,
      "loss": 1.2044,
      "step": 57
    },
    {
      "epoch": 0.012577297977151241,
      "grad_norm": 0.3168179392814636,
      "learning_rate": 9.745278735053343e-05,
      "loss": 1.1087,
      "step": 60
    },
    {
      "epoch": 0.013206162876008804,
      "grad_norm": 0.3409186005592346,
      "learning_rate": 9.714098521798465e-05,
      "loss": 1.2062,
      "step": 63
    },
    {
      "epoch": 0.013835027774866367,
      "grad_norm": 0.29721856117248535,
      "learning_rate": 9.681174353198687e-05,
      "loss": 1.1158,
      "step": 66
    },
    {
      "epoch": 0.014463892673723928,
      "grad_norm": 0.3369769752025604,
      "learning_rate": 9.64651840937276e-05,
      "loss": 1.1834,
      "step": 69
    },
    {
      "epoch": 0.015092757572581491,
      "grad_norm": 0.31268638372421265,
      "learning_rate": 9.610143511100354e-05,
      "loss": 1.1367,
      "step": 72
    },
    {
      "epoch": 0.015721622471439052,
      "grad_norm": 0.333360493183136,
      "learning_rate": 9.572063115079063e-05,
      "loss": 1.1805,
      "step": 75
    },
    {
      "epoch": 0.016350487370296613,
      "grad_norm": 0.2951726019382477,
      "learning_rate": 9.53229130894619e-05,
      "loss": 1.1459,
      "step": 78
    },
    {
      "epoch": 0.016979352269154178,
      "grad_norm": 0.36082521080970764,
      "learning_rate": 9.490842806067095e-05,
      "loss": 1.17,
      "step": 81
    },
    {
      "epoch": 0.01760821716801174,
      "grad_norm": 0.33050239086151123,
      "learning_rate": 9.44773294009206e-05,
      "loss": 1.1611,
      "step": 84
    },
    {
      "epoch": 0.01760821716801174,
      "eval_loss": 1.147385835647583,
      "eval_runtime": 165.0588,
      "eval_samples_per_second": 48.68,
      "eval_steps_per_second": 6.089,
      "step": 84
    },
    {
      "epoch": 0.0182370820668693,
      "grad_norm": 0.3466218411922455,
      "learning_rate": 9.40297765928369e-05,
      "loss": 1.181,
      "step": 87
    },
    {
      "epoch": 0.018865946965726865,
      "grad_norm": 0.3219515085220337,
      "learning_rate": 9.356593520616948e-05,
      "loss": 1.1236,
      "step": 90
    },
    {
      "epoch": 0.019494811864584426,
      "grad_norm": 0.35251516103744507,
      "learning_rate": 9.308597683653975e-05,
      "loss": 1.1749,
      "step": 93
    },
    {
      "epoch": 0.020123676763441987,
      "grad_norm": 0.3366820514202118,
      "learning_rate": 9.259007904196023e-05,
      "loss": 1.1411,
      "step": 96
    },
    {
      "epoch": 0.020752541662299548,
      "grad_norm": 0.3501774072647095,
      "learning_rate": 9.207842527714767e-05,
      "loss": 1.122,
      "step": 99
    },
    {
      "epoch": 0.021381406561157112,
      "grad_norm": 0.3260366916656494,
      "learning_rate": 9.155120482565521e-05,
      "loss": 1.1032,
      "step": 102
    },
    {
      "epoch": 0.022010271460014674,
      "grad_norm": 0.3130464255809784,
      "learning_rate": 9.10086127298478e-05,
      "loss": 1.1025,
      "step": 105
    },
    {
      "epoch": 0.022639136358872235,
      "grad_norm": 0.3319336473941803,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1279,
      "step": 108
    },
    {
      "epoch": 0.0232680012577298,
      "grad_norm": 0.3683924973011017,
      "learning_rate": 8.987812213377424e-05,
      "loss": 1.1384,
      "step": 111
    },
    {
      "epoch": 0.02389686615658736,
      "grad_norm": 0.3043256998062134,
      "learning_rate": 8.929064185241213e-05,
      "loss": 1.106,
      "step": 114
    },
    {
      "epoch": 0.02452573105544492,
      "grad_norm": 0.3852984607219696,
      "learning_rate": 8.868862620982534e-05,
      "loss": 1.123,
      "step": 117
    },
    {
      "epoch": 0.025154595954302483,
      "grad_norm": 0.36246711015701294,
      "learning_rate": 8.807229791845673e-05,
      "loss": 1.1248,
      "step": 120
    },
    {
      "epoch": 0.025783460853160047,
      "grad_norm": 0.3592873215675354,
      "learning_rate": 8.744188498563641e-05,
      "loss": 1.0983,
      "step": 123
    },
    {
      "epoch": 0.02641232575201761,
      "grad_norm": 0.3461982309818268,
      "learning_rate": 8.679762062923175e-05,
      "loss": 1.1211,
      "step": 126
    },
    {
      "epoch": 0.02641232575201761,
      "eval_loss": 1.1246975660324097,
      "eval_runtime": 165.051,
      "eval_samples_per_second": 48.682,
      "eval_steps_per_second": 6.089,
      "step": 126
    },
    {
      "epoch": 0.02704119065087517,
      "grad_norm": 0.3487012982368469,
      "learning_rate": 8.613974319136958e-05,
      "loss": 1.1212,
      "step": 129
    },
    {
      "epoch": 0.027670055549732734,
      "grad_norm": 0.37176796793937683,
      "learning_rate": 8.54684960502629e-05,
      "loss": 1.0707,
      "step": 132
    },
    {
      "epoch": 0.028298920448590295,
      "grad_norm": 0.3854920268058777,
      "learning_rate": 8.478412753017433e-05,
      "loss": 1.1204,
      "step": 135
    },
    {
      "epoch": 0.028927785347447856,
      "grad_norm": 0.3561486303806305,
      "learning_rate": 8.408689080954998e-05,
      "loss": 1.1238,
      "step": 138
    },
    {
      "epoch": 0.029556650246305417,
      "grad_norm": 0.35637167096138,
      "learning_rate": 8.33770438273574e-05,
      "loss": 1.1415,
      "step": 141
    },
    {
      "epoch": 0.030185515145162982,
      "grad_norm": 0.37608301639556885,
      "learning_rate": 8.265484918766243e-05,
      "loss": 1.1374,
      "step": 144
    },
    {
      "epoch": 0.030814380044020543,
      "grad_norm": 0.3702179789543152,
      "learning_rate": 8.192057406248028e-05,
      "loss": 1.1001,
      "step": 147
    },
    {
      "epoch": 0.031443244942878104,
      "grad_norm": 0.35054582357406616,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.122,
      "step": 150
    },
    {
      "epoch": 0.03207210984173567,
      "grad_norm": 0.35157763957977295,
      "learning_rate": 8.041687328877567e-05,
      "loss": 1.1126,
      "step": 153
    },
    {
      "epoch": 0.032700974740593226,
      "grad_norm": 0.3567587435245514,
      "learning_rate": 7.964800392625129e-05,
      "loss": 1.1196,
      "step": 156
    },
    {
      "epoch": 0.03332983963945079,
      "grad_norm": 0.33376169204711914,
      "learning_rate": 7.886816644444098e-05,
      "loss": 1.1269,
      "step": 159
    },
    {
      "epoch": 0.033958704538308356,
      "grad_norm": 0.33005964756011963,
      "learning_rate": 7.807764934001874e-05,
      "loss": 1.0881,
      "step": 162
    },
    {
      "epoch": 0.03458756943716591,
      "grad_norm": 0.3465365171432495,
      "learning_rate": 7.727674506052743e-05,
      "loss": 1.0912,
      "step": 165
    },
    {
      "epoch": 0.03521643433602348,
      "grad_norm": 0.3523496985435486,
      "learning_rate": 7.646574989618938e-05,
      "loss": 1.0962,
      "step": 168
    },
    {
      "epoch": 0.03521643433602348,
      "eval_loss": 1.1077728271484375,
      "eval_runtime": 165.0063,
      "eval_samples_per_second": 48.695,
      "eval_steps_per_second": 6.091,
      "step": 168
    },
    {
      "epoch": 0.03584529923488104,
      "grad_norm": 0.3241373300552368,
      "learning_rate": 7.564496387029532e-05,
      "loss": 1.1243,
      "step": 171
    },
    {
      "epoch": 0.0364741641337386,
      "grad_norm": 0.33574438095092773,
      "learning_rate": 7.481469062821252e-05,
      "loss": 1.1031,
      "step": 174
    },
    {
      "epoch": 0.037103029032596165,
      "grad_norm": 0.38013267517089844,
      "learning_rate": 7.39752373250527e-05,
      "loss": 1.1191,
      "step": 177
    },
    {
      "epoch": 0.03773189393145373,
      "grad_norm": 0.35769525170326233,
      "learning_rate": 7.312691451204178e-05,
      "loss": 1.0992,
      "step": 180
    },
    {
      "epoch": 0.03836075883031129,
      "grad_norm": 0.32820338010787964,
      "learning_rate": 7.227003602163295e-05,
      "loss": 1.0621,
      "step": 183
    },
    {
      "epoch": 0.03898962372916885,
      "grad_norm": 0.32962238788604736,
      "learning_rate": 7.14049188514063e-05,
      "loss": 1.0828,
      "step": 186
    },
    {
      "epoch": 0.03961848862802641,
      "grad_norm": 0.34197545051574707,
      "learning_rate": 7.05318830467969e-05,
      "loss": 1.1168,
      "step": 189
    },
    {
      "epoch": 0.040247353526883974,
      "grad_norm": 0.37021368741989136,
      "learning_rate": 6.965125158269619e-05,
      "loss": 1.1374,
      "step": 192
    },
    {
      "epoch": 0.04087621842574154,
      "grad_norm": 0.3301369547843933,
      "learning_rate": 6.876335024396872e-05,
      "loss": 1.054,
      "step": 195
    },
    {
      "epoch": 0.041505083324599096,
      "grad_norm": 0.35479190945625305,
      "learning_rate": 6.786850750493006e-05,
      "loss": 1.0923,
      "step": 198
    },
    {
      "epoch": 0.04213394822345666,
      "grad_norm": 0.35211730003356934,
      "learning_rate": 6.696705440782938e-05,
      "loss": 1.1124,
      "step": 201
    },
    {
      "epoch": 0.042762813122314225,
      "grad_norm": 0.4026525616645813,
      "learning_rate": 6.605932444038229e-05,
      "loss": 1.1229,
      "step": 204
    },
    {
      "epoch": 0.04339167802117178,
      "grad_norm": 0.40407177805900574,
      "learning_rate": 6.514565341239861e-05,
      "loss": 1.066,
      "step": 207
    },
    {
      "epoch": 0.04402054292002935,
      "grad_norm": 0.3534255027770996,
      "learning_rate": 6.422637933155162e-05,
      "loss": 1.0462,
      "step": 210
    },
    {
      "epoch": 0.04402054292002935,
      "eval_loss": 1.0946003198623657,
      "eval_runtime": 165.0602,
      "eval_samples_per_second": 48.679,
      "eval_steps_per_second": 6.089,
      "step": 210
    },
    {
      "epoch": 0.04464940781888691,
      "grad_norm": 0.3846144676208496,
      "learning_rate": 6.330184227833376e-05,
      "loss": 1.0922,
      "step": 213
    },
    {
      "epoch": 0.04527827271774447,
      "grad_norm": 0.37346020340919495,
      "learning_rate": 6.237238428024572e-05,
      "loss": 1.0727,
      "step": 216
    },
    {
      "epoch": 0.045907137616602034,
      "grad_norm": 0.3563274145126343,
      "learning_rate": 6.143834918526527e-05,
      "loss": 1.144,
      "step": 219
    },
    {
      "epoch": 0.0465360025154596,
      "grad_norm": 0.3684130907058716,
      "learning_rate": 6.0500082534642464e-05,
      "loss": 1.0526,
      "step": 222
    },
    {
      "epoch": 0.047164867414317156,
      "grad_norm": 0.37623313069343567,
      "learning_rate": 5.955793143506863e-05,
      "loss": 1.0694,
      "step": 225
    },
    {
      "epoch": 0.04779373231317472,
      "grad_norm": 0.335705429315567,
      "learning_rate": 5.861224443026595e-05,
      "loss": 1.0766,
      "step": 228
    },
    {
      "epoch": 0.04842259721203228,
      "grad_norm": 0.35654446482658386,
      "learning_rate": 5.766337137204579e-05,
      "loss": 1.091,
      "step": 231
    },
    {
      "epoch": 0.04905146211088984,
      "grad_norm": 0.33855140209198,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 1.0715,
      "step": 234
    },
    {
      "epoch": 0.04968032700974741,
      "grad_norm": 0.3658079206943512,
      "learning_rate": 5.575747226605298e-05,
      "loss": 1.0915,
      "step": 237
    },
    {
      "epoch": 0.050309191908604965,
      "grad_norm": 0.3918761610984802,
      "learning_rate": 5.480115129538409e-05,
      "loss": 1.073,
      "step": 240
    },
    {
      "epoch": 0.05093805680746253,
      "grad_norm": 0.37080520391464233,
      "learning_rate": 5.384305416466584e-05,
      "loss": 1.0234,
      "step": 243
    },
    {
      "epoch": 0.051566921706320094,
      "grad_norm": 0.315390020608902,
      "learning_rate": 5.288353531676873e-05,
      "loss": 1.0456,
      "step": 246
    },
    {
      "epoch": 0.05219578660517765,
      "grad_norm": 0.34985366463661194,
      "learning_rate": 5.192294972051992e-05,
      "loss": 1.0505,
      "step": 249
    },
    {
      "epoch": 0.05282465150403522,
      "grad_norm": 0.35391372442245483,
      "learning_rate": 5.0961652739384356e-05,
      "loss": 1.0728,
      "step": 252
    },
    {
      "epoch": 0.05282465150403522,
      "eval_loss": 1.0837104320526123,
      "eval_runtime": 164.9887,
      "eval_samples_per_second": 48.7,
      "eval_steps_per_second": 6.091,
      "step": 252
    },
    {
      "epoch": 0.05345351640289278,
      "grad_norm": 0.36929386854171753,
      "learning_rate": 5e-05,
      "loss": 1.0279,
      "step": 255
    },
    {
      "epoch": 0.05408238130175034,
      "grad_norm": 0.34936413168907166,
      "learning_rate": 4.903834726061565e-05,
      "loss": 1.0564,
      "step": 258
    },
    {
      "epoch": 0.0547112462006079,
      "grad_norm": 0.33937400579452515,
      "learning_rate": 4.807705027948008e-05,
      "loss": 1.0349,
      "step": 261
    },
    {
      "epoch": 0.05534011109946547,
      "grad_norm": 0.3877185583114624,
      "learning_rate": 4.711646468323129e-05,
      "loss": 1.0518,
      "step": 264
    },
    {
      "epoch": 0.055968975998323026,
      "grad_norm": 0.36920610070228577,
      "learning_rate": 4.6156945835334184e-05,
      "loss": 1.0907,
      "step": 267
    },
    {
      "epoch": 0.05659784089718059,
      "grad_norm": 0.3572535216808319,
      "learning_rate": 4.5198848704615914e-05,
      "loss": 1.0811,
      "step": 270
    },
    {
      "epoch": 0.05722670579603815,
      "grad_norm": 0.3565980792045593,
      "learning_rate": 4.424252773394704e-05,
      "loss": 1.0598,
      "step": 273
    },
    {
      "epoch": 0.05785557069489571,
      "grad_norm": 0.3740125298500061,
      "learning_rate": 4.328833670911724e-05,
      "loss": 1.0403,
      "step": 276
    },
    {
      "epoch": 0.05848443559375328,
      "grad_norm": 0.382012277841568,
      "learning_rate": 4.23366286279542e-05,
      "loss": 1.0877,
      "step": 279
    },
    {
      "epoch": 0.059113300492610835,
      "grad_norm": 0.359355092048645,
      "learning_rate": 4.138775556973406e-05,
      "loss": 1.0644,
      "step": 282
    },
    {
      "epoch": 0.0597421653914684,
      "grad_norm": 0.35905787348747253,
      "learning_rate": 4.04420685649314e-05,
      "loss": 1.0783,
      "step": 285
    },
    {
      "epoch": 0.060371030290325964,
      "grad_norm": 0.4150475263595581,
      "learning_rate": 3.9499917465357534e-05,
      "loss": 1.0996,
      "step": 288
    },
    {
      "epoch": 0.06099989518918352,
      "grad_norm": 0.3718733489513397,
      "learning_rate": 3.856165081473474e-05,
      "loss": 1.0191,
      "step": 291
    },
    {
      "epoch": 0.061628760088041086,
      "grad_norm": 0.36830800771713257,
      "learning_rate": 3.762761571975429e-05,
      "loss": 1.1456,
      "step": 294
    },
    {
      "epoch": 0.061628760088041086,
      "eval_loss": 1.0759488344192505,
      "eval_runtime": 164.9861,
      "eval_samples_per_second": 48.701,
      "eval_steps_per_second": 6.091,
      "step": 294
    },
    {
      "epoch": 0.06225762498689865,
      "grad_norm": 0.36433523893356323,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 1.0619,
      "step": 297
    },
    {
      "epoch": 0.06288648988575621,
      "grad_norm": 0.382252961397171,
      "learning_rate": 3.5773620668448384e-05,
      "loss": 1.0544,
      "step": 300
    },
    {
      "epoch": 0.06351535478461377,
      "grad_norm": 0.4051714539527893,
      "learning_rate": 3.48543465876014e-05,
      "loss": 0.9961,
      "step": 303
    },
    {
      "epoch": 0.06414421968347134,
      "grad_norm": 0.34751641750335693,
      "learning_rate": 3.3940675559617724e-05,
      "loss": 1.0396,
      "step": 306
    },
    {
      "epoch": 0.0647730845823289,
      "grad_norm": 0.38340121507644653,
      "learning_rate": 3.303294559217063e-05,
      "loss": 1.0916,
      "step": 309
    },
    {
      "epoch": 0.06540194948118645,
      "grad_norm": 0.41020599007606506,
      "learning_rate": 3.213149249506997e-05,
      "loss": 1.0738,
      "step": 312
    },
    {
      "epoch": 0.06603081438004402,
      "grad_norm": 0.3864920735359192,
      "learning_rate": 3.12366497560313e-05,
      "loss": 1.0936,
      "step": 315
    },
    {
      "epoch": 0.06665967927890158,
      "grad_norm": 0.35983094573020935,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 1.1001,
      "step": 318
    },
    {
      "epoch": 0.06728854417775915,
      "grad_norm": 0.39053815603256226,
      "learning_rate": 2.9468116953203107e-05,
      "loss": 1.0366,
      "step": 321
    },
    {
      "epoch": 0.06791740907661671,
      "grad_norm": 0.3519478142261505,
      "learning_rate": 2.8595081148593738e-05,
      "loss": 1.044,
      "step": 324
    },
    {
      "epoch": 0.06854627397547428,
      "grad_norm": 0.37353023886680603,
      "learning_rate": 2.772996397836704e-05,
      "loss": 1.0449,
      "step": 327
    },
    {
      "epoch": 0.06917513887433183,
      "grad_norm": 0.357658714056015,
      "learning_rate": 2.687308548795825e-05,
      "loss": 1.0519,
      "step": 330
    },
    {
      "epoch": 0.06980400377318939,
      "grad_norm": 0.40195825695991516,
      "learning_rate": 2.6024762674947313e-05,
      "loss": 1.0915,
      "step": 333
    },
    {
      "epoch": 0.07043286867204696,
      "grad_norm": 0.3929975628852844,
      "learning_rate": 2.5185309371787513e-05,
      "loss": 1.0375,
      "step": 336
    },
    {
      "epoch": 0.07043286867204696,
      "eval_loss": 1.0703336000442505,
      "eval_runtime": 165.0152,
      "eval_samples_per_second": 48.692,
      "eval_steps_per_second": 6.09,
      "step": 336
    },
    {
      "epoch": 0.07106173357090452,
      "grad_norm": 0.4022517502307892,
      "learning_rate": 2.43550361297047e-05,
      "loss": 1.0749,
      "step": 339
    },
    {
      "epoch": 0.07169059846976208,
      "grad_norm": 0.35164332389831543,
      "learning_rate": 2.353425010381063e-05,
      "loss": 1.0352,
      "step": 342
    },
    {
      "epoch": 0.07231946336861964,
      "grad_norm": 0.40566059947013855,
      "learning_rate": 2.272325493947257e-05,
      "loss": 1.0625,
      "step": 345
    },
    {
      "epoch": 0.0729483282674772,
      "grad_norm": 0.37188711762428284,
      "learning_rate": 2.192235065998126e-05,
      "loss": 1.072,
      "step": 348
    },
    {
      "epoch": 0.07357719316633476,
      "grad_norm": 0.3737729489803314,
      "learning_rate": 2.1131833555559037e-05,
      "loss": 1.0546,
      "step": 351
    },
    {
      "epoch": 0.07420605806519233,
      "grad_norm": 0.35681530833244324,
      "learning_rate": 2.0351996073748713e-05,
      "loss": 1.0669,
      "step": 354
    },
    {
      "epoch": 0.0748349229640499,
      "grad_norm": 0.3745366334915161,
      "learning_rate": 1.9583126711224343e-05,
      "loss": 1.0731,
      "step": 357
    },
    {
      "epoch": 0.07546378786290746,
      "grad_norm": 0.3998556137084961,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 1.1069,
      "step": 360
    },
    {
      "epoch": 0.07609265276176501,
      "grad_norm": 0.4358106255531311,
      "learning_rate": 1.807942593751973e-05,
      "loss": 1.0876,
      "step": 363
    },
    {
      "epoch": 0.07672151766062257,
      "grad_norm": 0.3841058313846588,
      "learning_rate": 1.7345150812337564e-05,
      "loss": 1.0822,
      "step": 366
    },
    {
      "epoch": 0.07735038255948014,
      "grad_norm": 0.4276648759841919,
      "learning_rate": 1.66229561726426e-05,
      "loss": 1.0894,
      "step": 369
    },
    {
      "epoch": 0.0779792474583377,
      "grad_norm": 0.40756258368492126,
      "learning_rate": 1.5913109190450032e-05,
      "loss": 1.0673,
      "step": 372
    },
    {
      "epoch": 0.07860811235719527,
      "grad_norm": 0.34232285618782043,
      "learning_rate": 1.5215872469825682e-05,
      "loss": 1.0659,
      "step": 375
    },
    {
      "epoch": 0.07923697725605282,
      "grad_norm": 0.35964226722717285,
      "learning_rate": 1.4531503949737108e-05,
      "loss": 1.0067,
      "step": 378
    },
    {
      "epoch": 0.07923697725605282,
      "eval_loss": 1.0661753416061401,
      "eval_runtime": 165.0357,
      "eval_samples_per_second": 48.686,
      "eval_steps_per_second": 6.09,
      "step": 378
    },
    {
      "epoch": 0.07986584215491038,
      "grad_norm": 0.3825712203979492,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 1.1019,
      "step": 381
    },
    {
      "epoch": 0.08049470705376795,
      "grad_norm": 0.39544931054115295,
      "learning_rate": 1.3202379370768252e-05,
      "loss": 1.0646,
      "step": 384
    },
    {
      "epoch": 0.08112357195262551,
      "grad_norm": 0.3967124819755554,
      "learning_rate": 1.2558115014363592e-05,
      "loss": 1.0394,
      "step": 387
    },
    {
      "epoch": 0.08175243685148308,
      "grad_norm": 0.39682498574256897,
      "learning_rate": 1.1927702081543279e-05,
      "loss": 1.0968,
      "step": 390
    },
    {
      "epoch": 0.08238130175034064,
      "grad_norm": 0.3636738359928131,
      "learning_rate": 1.1311373790174657e-05,
      "loss": 1.031,
      "step": 393
    },
    {
      "epoch": 0.08301016664919819,
      "grad_norm": 0.32566869258880615,
      "learning_rate": 1.0709358147587884e-05,
      "loss": 1.094,
      "step": 396
    },
    {
      "epoch": 0.08363903154805576,
      "grad_norm": 0.38560715317726135,
      "learning_rate": 1.0121877866225781e-05,
      "loss": 1.1144,
      "step": 399
    },
    {
      "epoch": 0.08426789644691332,
      "grad_norm": 0.32941296696662903,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0141,
      "step": 402
    },
    {
      "epoch": 0.08489676134577089,
      "grad_norm": 0.36348846554756165,
      "learning_rate": 8.991387270152201e-06,
      "loss": 1.043,
      "step": 405
    },
    {
      "epoch": 0.08552562624462845,
      "grad_norm": 0.37229597568511963,
      "learning_rate": 8.448795174344804e-06,
      "loss": 1.077,
      "step": 408
    },
    {
      "epoch": 0.08615449114348601,
      "grad_norm": 0.3720276653766632,
      "learning_rate": 7.921574722852343e-06,
      "loss": 0.9869,
      "step": 411
    },
    {
      "epoch": 0.08678335604234357,
      "grad_norm": 0.3702375590801239,
      "learning_rate": 7.409920958039795e-06,
      "loss": 0.9772,
      "step": 414
    },
    {
      "epoch": 0.08741222094120113,
      "grad_norm": 0.37576282024383545,
      "learning_rate": 6.9140231634602485e-06,
      "loss": 1.0302,
      "step": 417
    },
    {
      "epoch": 0.0880410858400587,
      "grad_norm": 0.39544618129730225,
      "learning_rate": 6.43406479383053e-06,
      "loss": 1.0528,
      "step": 420
    },
    {
      "epoch": 0.0880410858400587,
      "eval_loss": 1.0637660026550293,
      "eval_runtime": 165.1277,
      "eval_samples_per_second": 48.659,
      "eval_steps_per_second": 6.086,
      "step": 420
    },
    {
      "epoch": 0.08866995073891626,
      "grad_norm": 0.4187450110912323,
      "learning_rate": 5.9702234071631e-06,
      "loss": 1.0578,
      "step": 423
    },
    {
      "epoch": 0.08929881563777382,
      "grad_norm": 0.3692411780357361,
      "learning_rate": 5.5226705990794155e-06,
      "loss": 1.0522,
      "step": 426
    },
    {
      "epoch": 0.08992768053663137,
      "grad_norm": 0.4078660309314728,
      "learning_rate": 5.091571939329048e-06,
      "loss": 1.0434,
      "step": 429
    },
    {
      "epoch": 0.09055654543548894,
      "grad_norm": 0.4134742319583893,
      "learning_rate": 4.677086910538092e-06,
      "loss": 1.074,
      "step": 432
    },
    {
      "epoch": 0.0911854103343465,
      "grad_norm": 0.36238303780555725,
      "learning_rate": 4.279368849209381e-06,
      "loss": 1.0455,
      "step": 435
    },
    {
      "epoch": 0.09181427523320407,
      "grad_norm": 0.4054090976715088,
      "learning_rate": 3.898564888996476e-06,
      "loss": 1.0706,
      "step": 438
    },
    {
      "epoch": 0.09244314013206163,
      "grad_norm": 0.3747381567955017,
      "learning_rate": 3.534815906272404e-06,
      "loss": 1.0354,
      "step": 441
    },
    {
      "epoch": 0.0930720050309192,
      "grad_norm": 0.3801961839199066,
      "learning_rate": 3.18825646801314e-06,
      "loss": 1.0818,
      "step": 444
    },
    {
      "epoch": 0.09370086992977675,
      "grad_norm": 0.3710772395133972,
      "learning_rate": 2.8590147820153513e-06,
      "loss": 1.0605,
      "step": 447
    },
    {
      "epoch": 0.09432973482863431,
      "grad_norm": 0.3717288672924042,
      "learning_rate": 2.547212649466568e-06,
      "loss": 1.0153,
      "step": 450
    },
    {
      "epoch": 0.09495859972749188,
      "grad_norm": 0.370351105928421,
      "learning_rate": 2.2529654198854835e-06,
      "loss": 1.037,
      "step": 453
    },
    {
      "epoch": 0.09558746462634944,
      "grad_norm": 0.38800954818725586,
      "learning_rate": 1.9763819484490355e-06,
      "loss": 1.0668,
      "step": 456
    },
    {
      "epoch": 0.096216329525207,
      "grad_norm": 0.39085131883621216,
      "learning_rate": 1.7175645557220566e-06,
      "loss": 1.0601,
      "step": 459
    },
    {
      "epoch": 0.09684519442406456,
      "grad_norm": 0.38424739241600037,
      "learning_rate": 1.4766089898042678e-06,
      "loss": 1.0742,
      "step": 462
    },
    {
      "epoch": 0.09684519442406456,
      "eval_loss": 1.0629161596298218,
      "eval_runtime": 165.0993,
      "eval_samples_per_second": 48.668,
      "eval_steps_per_second": 6.087,
      "step": 462
    },
    {
      "epoch": 0.09747405932292212,
      "grad_norm": 0.34824374318122864,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 1.0597,
      "step": 465
    },
    {
      "epoch": 0.09810292422177969,
      "grad_norm": 0.3800143599510193,
      "learning_rate": 1.0486332583853563e-06,
      "loss": 1.0733,
      "step": 468
    },
    {
      "epoch": 0.09873178912063725,
      "grad_norm": 0.39402127265930176,
      "learning_rate": 8.617714201998084e-07,
      "loss": 1.0444,
      "step": 471
    },
    {
      "epoch": 0.09936065401949482,
      "grad_norm": 0.3665209114551544,
      "learning_rate": 6.93088004882253e-07,
      "loss": 1.0652,
      "step": 474
    },
    {
      "epoch": 0.09998951891835238,
      "grad_norm": 0.3840101659297943,
      "learning_rate": 5.426454159531913e-07,
      "loss": 1.0667,
      "step": 477
    },
    {
      "epoch": 0.10061838381720993,
      "grad_norm": 0.40634945034980774,
      "learning_rate": 4.104993088376974e-07,
      "loss": 1.024,
      "step": 480
    },
    {
      "epoch": 0.1012472487160675,
      "grad_norm": 0.4399307370185852,
      "learning_rate": 2.966985702759828e-07,
      "loss": 1.0763,
      "step": 483
    },
    {
      "epoch": 0.10187611361492506,
      "grad_norm": 0.3584943115711212,
      "learning_rate": 2.012853002380466e-07,
      "loss": 1.0044,
      "step": 486
    },
    {
      "epoch": 0.10250497851378262,
      "grad_norm": 0.3854651153087616,
      "learning_rate": 1.2429479634897267e-07,
      "loss": 1.0373,
      "step": 489
    },
    {
      "epoch": 0.10313384341264019,
      "grad_norm": 0.3579770028591156,
      "learning_rate": 6.575554083078084e-08,
      "loss": 1.0518,
      "step": 492
    },
    {
      "epoch": 0.10376270831149775,
      "grad_norm": 0.38003799319267273,
      "learning_rate": 2.568918996560532e-08,
      "loss": 1.1002,
      "step": 495
    },
    {
      "epoch": 0.1043915732103553,
      "grad_norm": 0.35773521661758423,
      "learning_rate": 4.110566084036816e-09,
      "loss": 1.062,
      "step": 498
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.06657392623616e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}