{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5719187875321704,
  "eval_steps": 42,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001143837575064341,
      "eval_loss": NaN,
      "eval_runtime": 102.4879,
      "eval_samples_per_second": 14.372,
      "eval_steps_per_second": 3.6,
      "step": 1
    },
    {
      "epoch": 0.0034315127251930227,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006863025450386045,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010294538175579068,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.01372605090077209,
      "grad_norm": NaN,
      "learning_rate": 9.999588943391597e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.017157563625965114,
      "grad_norm": NaN,
      "learning_rate": 9.99743108100344e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.020589076351158135,
      "grad_norm": NaN,
      "learning_rate": 9.993424445916923e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.024020589076351156,
      "grad_norm": NaN,
      "learning_rate": 9.987570520365104e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.02745210180154418,
      "grad_norm": NaN,
      "learning_rate": 9.979871469976196e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.030883614526737203,
      "grad_norm": NaN,
      "learning_rate": 9.970330142972401e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.03431512725193023,
      "grad_norm": NaN,
      "learning_rate": 9.95895006911623e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03774663997712325,
      "grad_norm": NaN,
      "learning_rate": 9.945735458404681e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.04117815270231627,
      "grad_norm": NaN,
      "learning_rate": 9.930691199511775e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.04460966542750929,
      "grad_norm": NaN,
      "learning_rate": 9.91382285798002e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.04804117815270231,
      "grad_norm": NaN,
      "learning_rate": 9.895136674161465e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.04804117815270231,
      "eval_loss": NaN,
      "eval_runtime": 102.5032,
      "eval_samples_per_second": 14.37,
      "eval_steps_per_second": 3.6,
      "step": 42
    },
    {
      "epoch": 0.05147269087789534,
      "grad_norm": NaN,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.05490420360308836,
      "grad_norm": NaN,
      "learning_rate": 9.852339101019574e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.058335716328281384,
      "grad_norm": NaN,
      "learning_rate": 9.828243544427796e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.061767229053474405,
      "grad_norm": NaN,
      "learning_rate": 9.802361805155097e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.06519874177866743,
      "grad_norm": NaN,
      "learning_rate": 9.774703458011453e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.06863025450386046,
      "grad_norm": NaN,
      "learning_rate": 9.745278735053343e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.07206176722905347,
      "grad_norm": NaN,
      "learning_rate": 9.714098521798465e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.0754932799542465,
      "grad_norm": NaN,
      "learning_rate": 9.681174353198687e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.07892479267943953,
      "grad_norm": NaN,
      "learning_rate": 9.64651840937276e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.08235630540463254,
      "grad_norm": NaN,
      "learning_rate": 9.610143511100354e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.08578781812982557,
      "grad_norm": NaN,
      "learning_rate": 9.572063115079063e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.08921933085501858,
      "grad_norm": NaN,
      "learning_rate": 9.53229130894619e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.09265084358021161,
      "grad_norm": NaN,
      "learning_rate": 9.490842806067095e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.09608235630540463,
      "grad_norm": NaN,
      "learning_rate": 9.44773294009206e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.09608235630540463,
      "eval_loss": NaN,
      "eval_runtime": 102.5365,
      "eval_samples_per_second": 14.366,
      "eval_steps_per_second": 3.599,
      "step": 84
    },
    {
      "epoch": 0.09951386903059765,
      "grad_norm": NaN,
      "learning_rate": 9.40297765928369e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.10294538175579068,
      "grad_norm": NaN,
      "learning_rate": 9.356593520616948e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.1063768944809837,
      "grad_norm": NaN,
      "learning_rate": 9.308597683653975e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.10980840720617673,
      "grad_norm": NaN,
      "learning_rate": 9.259007904196023e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.11323991993136974,
      "grad_norm": NaN,
      "learning_rate": 9.207842527714767e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.11667143265656277,
      "grad_norm": NaN,
      "learning_rate": 9.155120482565521e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.1201029453817558,
      "grad_norm": NaN,
      "learning_rate": 9.10086127298478e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.12353445810694881,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.12696597083214184,
      "grad_norm": NaN,
      "learning_rate": 8.987812213377424e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.13039748355733485,
      "grad_norm": NaN,
      "learning_rate": 8.929064185241213e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.13382899628252787,
      "grad_norm": NaN,
      "learning_rate": 8.868862620982534e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.1372605090077209,
      "grad_norm": NaN,
      "learning_rate": 8.807229791845673e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.14069202173291392,
      "grad_norm": NaN,
      "learning_rate": 8.744188498563641e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.14412353445810694,
      "grad_norm": NaN,
      "learning_rate": 8.679762062923175e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.14412353445810694,
      "eval_loss": NaN,
      "eval_runtime": 102.4791,
      "eval_samples_per_second": 14.374,
      "eval_steps_per_second": 3.601,
      "step": 126
    },
    {
      "epoch": 0.14755504718329998,
      "grad_norm": NaN,
      "learning_rate": 8.613974319136958e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.150986559908493,
      "grad_norm": NaN,
      "learning_rate": 8.54684960502629e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.154418072633686,
      "grad_norm": NaN,
      "learning_rate": 8.478412753017433e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.15784958535887905,
      "grad_norm": NaN,
      "learning_rate": 8.408689080954998e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.16128109808407207,
      "grad_norm": NaN,
      "learning_rate": 8.33770438273574e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.16471261080926508,
      "grad_norm": NaN,
      "learning_rate": 8.265484918766243e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.1681441235344581,
      "grad_norm": NaN,
      "learning_rate": 8.192057406248028e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.17157563625965114,
      "grad_norm": NaN,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.17500714898484415,
      "grad_norm": NaN,
      "learning_rate": 8.041687328877567e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.17843866171003717,
      "grad_norm": NaN,
      "learning_rate": 7.964800392625129e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.1818701744352302,
      "grad_norm": NaN,
      "learning_rate": 7.886816644444098e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.18530168716042322,
      "grad_norm": NaN,
      "learning_rate": 7.807764934001874e-05,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.18873319988561624,
      "grad_norm": NaN,
      "learning_rate": 7.727674506052743e-05,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.19216471261080925,
      "grad_norm": NaN,
      "learning_rate": 7.646574989618938e-05,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.19216471261080925,
      "eval_loss": NaN,
      "eval_runtime": 102.4359,
      "eval_samples_per_second": 14.38,
      "eval_steps_per_second": 3.602,
      "step": 168
    },
    {
      "epoch": 0.1955962253360023,
      "grad_norm": NaN,
      "learning_rate": 7.564496387029532e-05,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.1990277380611953,
      "grad_norm": NaN,
      "learning_rate": 7.481469062821252e-05,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.20245925078638832,
      "grad_norm": NaN,
      "learning_rate": 7.39752373250527e-05,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.20589076351158137,
      "grad_norm": NaN,
      "learning_rate": 7.312691451204178e-05,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.20932227623677438,
      "grad_norm": NaN,
      "learning_rate": 7.227003602163295e-05,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.2127537889619674,
      "grad_norm": NaN,
      "learning_rate": 7.14049188514063e-05,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.21618530168716044,
      "grad_norm": NaN,
      "learning_rate": 7.05318830467969e-05,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.21961681441235345,
      "grad_norm": NaN,
      "learning_rate": 6.965125158269619e-05,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.22304832713754646,
      "grad_norm": NaN,
      "learning_rate": 6.876335024396872e-05,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.22647983986273948,
      "grad_norm": NaN,
      "learning_rate": 6.786850750493006e-05,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.22991135258793252,
      "grad_norm": NaN,
      "learning_rate": 6.696705440782938e-05,
      "loss": 0.0,
      "step": 201
    },
    {
      "epoch": 0.23334286531312554,
      "grad_norm": NaN,
      "learning_rate": 6.605932444038229e-05,
      "loss": 0.0,
      "step": 204
    },
    {
      "epoch": 0.23677437803831855,
      "grad_norm": NaN,
      "learning_rate": 6.514565341239861e-05,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 0.2402058907635116,
      "grad_norm": NaN,
      "learning_rate": 6.422637933155162e-05,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.2402058907635116,
      "eval_loss": NaN,
      "eval_runtime": 102.4571,
      "eval_samples_per_second": 14.377,
      "eval_steps_per_second": 3.602,
      "step": 210
    },
    {
      "epoch": 0.2436374034887046,
      "grad_norm": NaN,
      "learning_rate": 6.330184227833376e-05,
      "loss": 0.0,
      "step": 213
    },
    {
      "epoch": 0.24706891621389762,
      "grad_norm": NaN,
      "learning_rate": 6.237238428024572e-05,
      "loss": 0.0,
      "step": 216
    },
    {
      "epoch": 0.25050042893909064,
      "grad_norm": NaN,
      "learning_rate": 6.143834918526527e-05,
      "loss": 0.0,
      "step": 219
    },
    {
      "epoch": 0.2539319416642837,
      "grad_norm": NaN,
      "learning_rate": 6.0500082534642464e-05,
      "loss": 0.0,
      "step": 222
    },
    {
      "epoch": 0.2573634543894767,
      "grad_norm": NaN,
      "learning_rate": 5.955793143506863e-05,
      "loss": 0.0,
      "step": 225
    },
    {
      "epoch": 0.2607949671146697,
      "grad_norm": NaN,
      "learning_rate": 5.861224443026595e-05,
      "loss": 0.0,
      "step": 228
    },
    {
      "epoch": 0.26422647983986275,
      "grad_norm": NaN,
      "learning_rate": 5.766337137204579e-05,
      "loss": 0.0,
      "step": 231
    },
    {
      "epoch": 0.26765799256505574,
      "grad_norm": NaN,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 0.0,
      "step": 234
    },
    {
      "epoch": 0.2710895052902488,
      "grad_norm": NaN,
      "learning_rate": 5.575747226605298e-05,
      "loss": 0.0,
      "step": 237
    },
    {
      "epoch": 0.2745210180154418,
      "grad_norm": NaN,
      "learning_rate": 5.480115129538409e-05,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.2779525307406348,
      "grad_norm": NaN,
      "learning_rate": 5.384305416466584e-05,
      "loss": 0.0,
      "step": 243
    },
    {
      "epoch": 0.28138404346582785,
      "grad_norm": NaN,
      "learning_rate": 5.288353531676873e-05,
      "loss": 0.0,
      "step": 246
    },
    {
      "epoch": 0.2848155561910209,
      "grad_norm": NaN,
      "learning_rate": 5.192294972051992e-05,
      "loss": 0.0,
      "step": 249
    },
    {
      "epoch": 0.2882470689162139,
      "grad_norm": NaN,
      "learning_rate": 5.0961652739384356e-05,
      "loss": 0.0,
      "step": 252
    },
    {
      "epoch": 0.2882470689162139,
      "eval_loss": NaN,
      "eval_runtime": 102.4897,
      "eval_samples_per_second": 14.372,
      "eval_steps_per_second": 3.6,
      "step": 252
    },
    {
      "epoch": 0.2916785816414069,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 255
    },
    {
      "epoch": 0.29511009436659996,
      "grad_norm": NaN,
      "learning_rate": 4.903834726061565e-05,
      "loss": 0.0,
      "step": 258
    },
    {
      "epoch": 0.29854160709179295,
      "grad_norm": NaN,
      "learning_rate": 4.807705027948008e-05,
      "loss": 0.0,
      "step": 261
    },
    {
      "epoch": 0.301973119816986,
      "grad_norm": NaN,
      "learning_rate": 4.711646468323129e-05,
      "loss": 0.0,
      "step": 264
    },
    {
      "epoch": 0.30540463254217903,
      "grad_norm": NaN,
      "learning_rate": 4.6156945835334184e-05,
      "loss": 0.0,
      "step": 267
    },
    {
      "epoch": 0.308836145267372,
      "grad_norm": NaN,
      "learning_rate": 4.5198848704615914e-05,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.31226765799256506,
      "grad_norm": NaN,
      "learning_rate": 4.424252773394704e-05,
      "loss": 0.0,
      "step": 273
    },
    {
      "epoch": 0.3156991707177581,
      "grad_norm": NaN,
      "learning_rate": 4.328833670911724e-05,
      "loss": 0.0,
      "step": 276
    },
    {
      "epoch": 0.3191306834429511,
      "grad_norm": NaN,
      "learning_rate": 4.23366286279542e-05,
      "loss": 0.0,
      "step": 279
    },
    {
      "epoch": 0.32256219616814413,
      "grad_norm": NaN,
      "learning_rate": 4.138775556973406e-05,
      "loss": 0.0,
      "step": 282
    },
    {
      "epoch": 0.3259937088933371,
      "grad_norm": NaN,
      "learning_rate": 4.04420685649314e-05,
      "loss": 0.0,
      "step": 285
    },
    {
      "epoch": 0.32942522161853016,
      "grad_norm": NaN,
      "learning_rate": 3.9499917465357534e-05,
      "loss": 0.0,
      "step": 288
    },
    {
      "epoch": 0.3328567343437232,
      "grad_norm": NaN,
      "learning_rate": 3.856165081473474e-05,
      "loss": 0.0,
      "step": 291
    },
    {
      "epoch": 0.3362882470689162,
      "grad_norm": NaN,
      "learning_rate": 3.762761571975429e-05,
      "loss": 0.0,
      "step": 294
    },
    {
      "epoch": 0.3362882470689162,
      "eval_loss": NaN,
      "eval_runtime": 102.4532,
      "eval_samples_per_second": 14.377,
      "eval_steps_per_second": 3.602,
      "step": 294
    },
    {
      "epoch": 0.33971975979410923,
      "grad_norm": NaN,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 0.0,
      "step": 297
    },
    {
      "epoch": 0.3431512725193023,
      "grad_norm": NaN,
      "learning_rate": 3.5773620668448384e-05,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.34658278524449526,
      "grad_norm": NaN,
      "learning_rate": 3.48543465876014e-05,
      "loss": 0.0,
      "step": 303
    },
    {
      "epoch": 0.3500142979696883,
      "grad_norm": NaN,
      "learning_rate": 3.3940675559617724e-05,
      "loss": 0.0,
      "step": 306
    },
    {
      "epoch": 0.35344581069488135,
      "grad_norm": NaN,
      "learning_rate": 3.303294559217063e-05,
      "loss": 0.0,
      "step": 309
    },
    {
      "epoch": 0.35687732342007433,
      "grad_norm": NaN,
      "learning_rate": 3.213149249506997e-05,
      "loss": 0.0,
      "step": 312
    },
    {
      "epoch": 0.3603088361452674,
      "grad_norm": NaN,
      "learning_rate": 3.12366497560313e-05,
      "loss": 0.0,
      "step": 315
    },
    {
      "epoch": 0.3637403488704604,
      "grad_norm": NaN,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 0.0,
      "step": 318
    },
    {
      "epoch": 0.3671718615956534,
      "grad_norm": NaN,
      "learning_rate": 2.9468116953203107e-05,
      "loss": 0.0,
      "step": 321
    },
    {
      "epoch": 0.37060337432084645,
      "grad_norm": NaN,
      "learning_rate": 2.8595081148593738e-05,
      "loss": 0.0,
      "step": 324
    },
    {
      "epoch": 0.3740348870460395,
      "grad_norm": NaN,
      "learning_rate": 2.772996397836704e-05,
      "loss": 0.0,
      "step": 327
    },
    {
      "epoch": 0.3774663997712325,
      "grad_norm": NaN,
      "learning_rate": 2.687308548795825e-05,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.3808979124964255,
      "grad_norm": NaN,
      "learning_rate": 2.6024762674947313e-05,
      "loss": 0.0,
      "step": 333
    },
    {
      "epoch": 0.3843294252216185,
      "grad_norm": NaN,
      "learning_rate": 2.5185309371787513e-05,
      "loss": 0.0,
      "step": 336
    },
    {
      "epoch": 0.3843294252216185,
      "eval_loss": NaN,
      "eval_runtime": 102.4557,
      "eval_samples_per_second": 14.377,
      "eval_steps_per_second": 3.602,
      "step": 336
    },
    {
      "epoch": 0.38776093794681155,
      "grad_norm": NaN,
      "learning_rate": 2.43550361297047e-05,
      "loss": 0.0,
      "step": 339
    },
    {
      "epoch": 0.3911924506720046,
      "grad_norm": NaN,
      "learning_rate": 2.353425010381063e-05,
      "loss": 0.0,
      "step": 342
    },
    {
      "epoch": 0.3946239633971976,
      "grad_norm": NaN,
      "learning_rate": 2.272325493947257e-05,
      "loss": 0.0,
      "step": 345
    },
    {
      "epoch": 0.3980554761223906,
      "grad_norm": NaN,
      "learning_rate": 2.192235065998126e-05,
      "loss": 0.0,
      "step": 348
    },
    {
      "epoch": 0.40148698884758366,
      "grad_norm": NaN,
      "learning_rate": 2.1131833555559037e-05,
      "loss": 0.0,
      "step": 351
    },
    {
      "epoch": 0.40491850157277665,
      "grad_norm": NaN,
      "learning_rate": 2.0351996073748713e-05,
      "loss": 0.0,
      "step": 354
    },
    {
      "epoch": 0.4083500142979697,
      "grad_norm": NaN,
      "learning_rate": 1.9583126711224343e-05,
      "loss": 0.0,
      "step": 357
    },
    {
      "epoch": 0.41178152702316273,
      "grad_norm": NaN,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.4152130397483557,
      "grad_norm": NaN,
      "learning_rate": 1.807942593751973e-05,
      "loss": 0.0,
      "step": 363
    },
    {
      "epoch": 0.41864455247354876,
      "grad_norm": NaN,
      "learning_rate": 1.7345150812337564e-05,
      "loss": 0.0,
      "step": 366
    },
    {
      "epoch": 0.4220760651987418,
      "grad_norm": NaN,
      "learning_rate": 1.66229561726426e-05,
      "loss": 0.0,
      "step": 369
    },
    {
      "epoch": 0.4255075779239348,
      "grad_norm": NaN,
      "learning_rate": 1.5913109190450032e-05,
      "loss": 0.0,
      "step": 372
    },
    {
      "epoch": 0.42893909064912783,
      "grad_norm": NaN,
      "learning_rate": 1.5215872469825682e-05,
      "loss": 0.0,
      "step": 375
    },
    {
      "epoch": 0.43237060337432087,
      "grad_norm": NaN,
      "learning_rate": 1.4531503949737108e-05,
      "loss": 0.0,
      "step": 378
    },
    {
      "epoch": 0.43237060337432087,
      "eval_loss": NaN,
      "eval_runtime": 102.4156,
      "eval_samples_per_second": 14.383,
      "eval_steps_per_second": 3.603,
      "step": 378
    },
    {
      "epoch": 0.43580211609951386,
      "grad_norm": NaN,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 0.0,
      "step": 381
    },
    {
      "epoch": 0.4392336288247069,
      "grad_norm": NaN,
      "learning_rate": 1.3202379370768252e-05,
      "loss": 0.0,
      "step": 384
    },
    {
      "epoch": 0.4426651415498999,
      "grad_norm": NaN,
      "learning_rate": 1.2558115014363592e-05,
      "loss": 0.0,
      "step": 387
    },
    {
      "epoch": 0.44609665427509293,
      "grad_norm": NaN,
      "learning_rate": 1.1927702081543279e-05,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.44952816700028597,
      "grad_norm": NaN,
      "learning_rate": 1.1311373790174657e-05,
      "loss": 0.0,
      "step": 393
    },
    {
      "epoch": 0.45295967972547896,
      "grad_norm": NaN,
      "learning_rate": 1.0709358147587884e-05,
      "loss": 0.0,
      "step": 396
    },
    {
      "epoch": 0.456391192450672,
      "grad_norm": NaN,
      "learning_rate": 1.0121877866225781e-05,
      "loss": 0.0,
      "step": 399
    },
    {
      "epoch": 0.45982270517586504,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 402
    },
    {
      "epoch": 0.46325421790105803,
      "grad_norm": NaN,
      "learning_rate": 8.991387270152201e-06,
      "loss": 0.0,
      "step": 405
    },
    {
      "epoch": 0.46668573062625107,
      "grad_norm": NaN,
      "learning_rate": 8.448795174344804e-06,
      "loss": 0.0,
      "step": 408
    },
    {
      "epoch": 0.4701172433514441,
      "grad_norm": NaN,
      "learning_rate": 7.921574722852343e-06,
      "loss": 0.0,
      "step": 411
    },
    {
      "epoch": 0.4735487560766371,
      "grad_norm": NaN,
      "learning_rate": 7.409920958039795e-06,
      "loss": 0.0,
      "step": 414
    },
    {
      "epoch": 0.47698026880183014,
      "grad_norm": NaN,
      "learning_rate": 6.9140231634602485e-06,
      "loss": 0.0,
      "step": 417
    },
    {
      "epoch": 0.4804117815270232,
      "grad_norm": NaN,
      "learning_rate": 6.43406479383053e-06,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.4804117815270232,
      "eval_loss": NaN,
      "eval_runtime": 102.4101,
      "eval_samples_per_second": 14.383,
      "eval_steps_per_second": 3.603,
      "step": 420
    },
    {
      "epoch": 0.48384329425221617,
      "grad_norm": NaN,
      "learning_rate": 5.9702234071631e-06,
      "loss": 0.0,
      "step": 423
    },
    {
      "epoch": 0.4872748069774092,
      "grad_norm": NaN,
      "learning_rate": 5.5226705990794155e-06,
      "loss": 0.0,
      "step": 426
    },
    {
      "epoch": 0.49070631970260226,
      "grad_norm": NaN,
      "learning_rate": 5.091571939329048e-06,
      "loss": 0.0,
      "step": 429
    },
    {
      "epoch": 0.49413783242779524,
      "grad_norm": NaN,
      "learning_rate": 4.677086910538092e-06,
      "loss": 0.0,
      "step": 432
    },
    {
      "epoch": 0.4975693451529883,
      "grad_norm": NaN,
      "learning_rate": 4.279368849209381e-06,
      "loss": 0.0,
      "step": 435
    },
    {
      "epoch": 0.5010008578781813,
      "grad_norm": NaN,
      "learning_rate": 3.898564888996476e-06,
      "loss": 0.0,
      "step": 438
    },
    {
      "epoch": 0.5044323706033743,
      "grad_norm": NaN,
      "learning_rate": 3.534815906272404e-06,
      "loss": 0.0,
      "step": 441
    },
    {
      "epoch": 0.5078638833285674,
      "grad_norm": NaN,
      "learning_rate": 3.18825646801314e-06,
      "loss": 0.0,
      "step": 444
    },
    {
      "epoch": 0.5112953960537604,
      "grad_norm": NaN,
      "learning_rate": 2.8590147820153513e-06,
      "loss": 0.0,
      "step": 447
    },
    {
      "epoch": 0.5147269087789534,
      "grad_norm": NaN,
      "learning_rate": 2.547212649466568e-06,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.5181584215041464,
      "grad_norm": NaN,
      "learning_rate": 2.2529654198854835e-06,
      "loss": 0.0,
      "step": 453
    },
    {
      "epoch": 0.5215899342293394,
      "grad_norm": NaN,
      "learning_rate": 1.9763819484490355e-06,
      "loss": 0.0,
      "step": 456
    },
    {
      "epoch": 0.5250214469545325,
      "grad_norm": NaN,
      "learning_rate": 1.7175645557220566e-06,
      "loss": 0.0,
      "step": 459
    },
    {
      "epoch": 0.5284529596797255,
      "grad_norm": NaN,
      "learning_rate": 1.4766089898042678e-06,
      "loss": 0.0,
      "step": 462
    },
    {
      "epoch": 0.5284529596797255,
      "eval_loss": NaN,
      "eval_runtime": 102.5202,
      "eval_samples_per_second": 14.368,
      "eval_steps_per_second": 3.599,
      "step": 462
    },
    {
      "epoch": 0.5318844724049185,
      "grad_norm": NaN,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0,
      "step": 465
    },
    {
      "epoch": 0.5353159851301115,
      "grad_norm": NaN,
      "learning_rate": 1.0486332583853563e-06,
      "loss": 0.0,
      "step": 468
    },
    {
      "epoch": 0.5387474978553045,
      "grad_norm": NaN,
      "learning_rate": 8.617714201998084e-07,
      "loss": 0.0,
      "step": 471
    },
    {
      "epoch": 0.5421790105804976,
      "grad_norm": NaN,
      "learning_rate": 6.93088004882253e-07,
      "loss": 0.0,
      "step": 474
    },
    {
      "epoch": 0.5456105233056906,
      "grad_norm": NaN,
      "learning_rate": 5.426454159531913e-07,
      "loss": 0.0,
      "step": 477
    },
    {
      "epoch": 0.5490420360308836,
      "grad_norm": NaN,
      "learning_rate": 4.104993088376974e-07,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 0.5524735487560767,
      "grad_norm": NaN,
      "learning_rate": 2.966985702759828e-07,
      "loss": 0.0,
      "step": 483
    },
    {
      "epoch": 0.5559050614812696,
      "grad_norm": NaN,
      "learning_rate": 2.012853002380466e-07,
      "loss": 0.0,
      "step": 486
    },
    {
      "epoch": 0.5593365742064627,
      "grad_norm": NaN,
      "learning_rate": 1.2429479634897267e-07,
      "loss": 0.0,
      "step": 489
    },
    {
      "epoch": 0.5627680869316557,
      "grad_norm": NaN,
      "learning_rate": 6.575554083078084e-08,
      "loss": 0.0,
      "step": 492
    },
    {
      "epoch": 0.5661995996568487,
      "grad_norm": NaN,
      "learning_rate": 2.568918996560532e-08,
      "loss": 0.0,
      "step": 495
    },
    {
      "epoch": 0.5696311123820418,
      "grad_norm": NaN,
      "learning_rate": 4.110566084036816e-09,
      "loss": 0.0,
      "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": 7.1094434267136e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}