{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.43149946062567424,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002157497303128371,
      "eval_loss": 0.23401260375976562,
      "eval_runtime": 15.1427,
      "eval_samples_per_second": 51.576,
      "eval_steps_per_second": 6.472,
      "step": 1
    },
    {
      "epoch": 0.006472491909385114,
      "grad_norm": 0.3756199777126312,
      "learning_rate": 3e-05,
      "loss": 0.1908,
      "step": 3
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 0.5128735303878784,
      "learning_rate": 6e-05,
      "loss": 0.2163,
      "step": 6
    },
    {
      "epoch": 0.019417475728155338,
      "grad_norm": 0.7347843050956726,
      "learning_rate": 9e-05,
      "loss": 0.139,
      "step": 9
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 0.21246007084846497,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.053,
      "step": 12
    },
    {
      "epoch": 0.032362459546925564,
      "grad_norm": 0.31107938289642334,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0425,
      "step": 15
    },
    {
      "epoch": 0.036677454153182305,
      "eval_loss": 0.009197796694934368,
      "eval_runtime": 15.204,
      "eval_samples_per_second": 51.368,
      "eval_steps_per_second": 6.446,
      "step": 17
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 0.42941978573799133,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0104,
      "step": 18
    },
    {
      "epoch": 0.045307443365695796,
      "grad_norm": 0.16689348220825195,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0053,
      "step": 21
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 0.1845988631248474,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0032,
      "step": 24
    },
    {
      "epoch": 0.05825242718446602,
      "grad_norm": 0.2645643949508667,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0052,
      "step": 27
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 0.019420228898525238,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0056,
      "step": 30
    },
    {
      "epoch": 0.07119741100323625,
      "grad_norm": 0.054533425718545914,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0043,
      "step": 33
    },
    {
      "epoch": 0.07335490830636461,
      "eval_loss": 0.004006265662610531,
      "eval_runtime": 15.2337,
      "eval_samples_per_second": 51.268,
      "eval_steps_per_second": 6.433,
      "step": 34
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 0.05752410367131233,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0031,
      "step": 36
    },
    {
      "epoch": 0.08414239482200647,
      "grad_norm": 0.059737678617239,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.001,
      "step": 39
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": 0.1771877408027649,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0028,
      "step": 42
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": 0.252778559923172,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0025,
      "step": 45
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 0.010936114937067032,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0021,
      "step": 48
    },
    {
      "epoch": 0.11003236245954692,
      "grad_norm": 0.2493264079093933,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0026,
      "step": 51
    },
    {
      "epoch": 0.11003236245954692,
      "eval_loss": 0.002514491556212306,
      "eval_runtime": 15.3305,
      "eval_samples_per_second": 50.944,
      "eval_steps_per_second": 6.392,
      "step": 51
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 0.26944953203201294,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.001,
      "step": 54
    },
    {
      "epoch": 0.12297734627831715,
      "grad_norm": 0.044158048927783966,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0008,
      "step": 57
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 0.009304636158049107,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0017,
      "step": 60
    },
    {
      "epoch": 0.13592233009708737,
      "grad_norm": 0.004074821714311838,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0019,
      "step": 63
    },
    {
      "epoch": 0.1423948220064725,
      "grad_norm": 0.03731223940849304,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0006,
      "step": 66
    },
    {
      "epoch": 0.14670981661272922,
      "eval_loss": 0.0016004251083359122,
      "eval_runtime": 15.3506,
      "eval_samples_per_second": 50.878,
      "eval_steps_per_second": 6.384,
      "step": 68
    },
    {
      "epoch": 0.1488673139158576,
      "grad_norm": 0.03484257683157921,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0004,
      "step": 69
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": 0.03455309569835663,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0016,
      "step": 72
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": 0.011528185568749905,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0004,
      "step": 75
    },
    {
      "epoch": 0.16828478964401294,
      "grad_norm": 0.03166678920388222,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0024,
      "step": 78
    },
    {
      "epoch": 0.17475728155339806,
      "grad_norm": 0.0032140235416591167,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0002,
      "step": 81
    },
    {
      "epoch": 0.18122977346278318,
      "grad_norm": 0.0027989039663225412,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0001,
      "step": 84
    },
    {
      "epoch": 0.18338727076591155,
      "eval_loss": 0.0013614986091852188,
      "eval_runtime": 15.3471,
      "eval_samples_per_second": 50.889,
      "eval_steps_per_second": 6.386,
      "step": 85
    },
    {
      "epoch": 0.18770226537216828,
      "grad_norm": 0.005217652302235365,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0002,
      "step": 87
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.2677434980869293,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0004,
      "step": 90
    },
    {
      "epoch": 0.20064724919093851,
      "grad_norm": 0.0085700498893857,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0003,
      "step": 93
    },
    {
      "epoch": 0.20711974110032363,
      "grad_norm": 0.0022312181536108255,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0004,
      "step": 96
    },
    {
      "epoch": 0.21359223300970873,
      "grad_norm": 0.008560556918382645,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0026,
      "step": 99
    },
    {
      "epoch": 0.22006472491909385,
      "grad_norm": 0.004689795430749655,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0002,
      "step": 102
    },
    {
      "epoch": 0.22006472491909385,
      "eval_loss": 0.0012459141435101628,
      "eval_runtime": 15.286,
      "eval_samples_per_second": 51.093,
      "eval_steps_per_second": 6.411,
      "step": 102
    },
    {
      "epoch": 0.22653721682847897,
      "grad_norm": 0.007451518904417753,
      "learning_rate": 5e-05,
      "loss": 0.0003,
      "step": 105
    },
    {
      "epoch": 0.23300970873786409,
      "grad_norm": 0.0017845184775069356,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0002,
      "step": 108
    },
    {
      "epoch": 0.23948220064724918,
      "grad_norm": 0.0030623022466897964,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.001,
      "step": 111
    },
    {
      "epoch": 0.2459546925566343,
      "grad_norm": 0.09107693284749985,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0005,
      "step": 114
    },
    {
      "epoch": 0.2524271844660194,
      "grad_norm": 0.002830550307407975,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0009,
      "step": 117
    },
    {
      "epoch": 0.25674217907227614,
      "eval_loss": 0.0011964853620156646,
      "eval_runtime": 15.3143,
      "eval_samples_per_second": 50.998,
      "eval_steps_per_second": 6.399,
      "step": 119
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.004851281642913818,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0008,
      "step": 120
    },
    {
      "epoch": 0.26537216828478966,
      "grad_norm": 0.0022969194687902927,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0003,
      "step": 123
    },
    {
      "epoch": 0.27184466019417475,
      "grad_norm": 0.002009553834795952,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0008,
      "step": 126
    },
    {
      "epoch": 0.2783171521035599,
      "grad_norm": 0.019238989800214767,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.001,
      "step": 129
    },
    {
      "epoch": 0.284789644012945,
      "grad_norm": 0.0018951981328427792,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0001,
      "step": 132
    },
    {
      "epoch": 0.2912621359223301,
      "grad_norm": 0.0017350999405607581,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0001,
      "step": 135
    },
    {
      "epoch": 0.29341963322545844,
      "eval_loss": 0.00118519167881459,
      "eval_runtime": 15.2967,
      "eval_samples_per_second": 51.057,
      "eval_steps_per_second": 6.407,
      "step": 136
    },
    {
      "epoch": 0.2977346278317152,
      "grad_norm": 0.012939455918967724,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0005,
      "step": 138
    },
    {
      "epoch": 0.3042071197411003,
      "grad_norm": 0.006930975709110498,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0022,
      "step": 141
    },
    {
      "epoch": 0.3106796116504854,
      "grad_norm": 0.04907749965786934,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0004,
      "step": 144
    },
    {
      "epoch": 0.31715210355987056,
      "grad_norm": 0.001971936086192727,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0001,
      "step": 147
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.014784353785216808,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0002,
      "step": 150
    },
    {
      "epoch": 0.3300970873786408,
      "grad_norm": 0.014250230975449085,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0002,
      "step": 153
    },
    {
      "epoch": 0.3300970873786408,
      "eval_loss": 0.0011580369900912046,
      "eval_runtime": 15.3831,
      "eval_samples_per_second": 50.77,
      "eval_steps_per_second": 6.371,
      "step": 153
    },
    {
      "epoch": 0.3365695792880259,
      "grad_norm": 0.0075296154245734215,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0003,
      "step": 156
    },
    {
      "epoch": 0.343042071197411,
      "grad_norm": 0.0026120678521692753,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0001,
      "step": 159
    },
    {
      "epoch": 0.34951456310679613,
      "grad_norm": 0.009413421154022217,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0001,
      "step": 162
    },
    {
      "epoch": 0.3559870550161812,
      "grad_norm": 0.0064108408987522125,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0004,
      "step": 165
    },
    {
      "epoch": 0.36245954692556637,
      "grad_norm": 0.019446568563580513,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0002,
      "step": 168
    },
    {
      "epoch": 0.3667745415318231,
      "eval_loss": 0.0011426601558923721,
      "eval_runtime": 15.322,
      "eval_samples_per_second": 50.972,
      "eval_steps_per_second": 6.396,
      "step": 170
    },
    {
      "epoch": 0.36893203883495146,
      "grad_norm": 0.058607444167137146,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0053,
      "step": 171
    },
    {
      "epoch": 0.37540453074433655,
      "grad_norm": 0.0422167032957077,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0003,
      "step": 174
    },
    {
      "epoch": 0.3818770226537217,
      "grad_norm": 0.005847129505127668,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0028,
      "step": 177
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.019291536882519722,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 0.3948220064724919,
      "grad_norm": 0.03592485189437866,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0005,
      "step": 183
    },
    {
      "epoch": 0.40129449838187703,
      "grad_norm": 0.05044146999716759,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.001,
      "step": 186
    },
    {
      "epoch": 0.4034519956850054,
      "eval_loss": 0.0011317983735352755,
      "eval_runtime": 15.3194,
      "eval_samples_per_second": 50.981,
      "eval_steps_per_second": 6.397,
      "step": 187
    },
    {
      "epoch": 0.4077669902912621,
      "grad_norm": 0.00613233121111989,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0001,
      "step": 189
    },
    {
      "epoch": 0.41423948220064727,
      "grad_norm": 0.0022430219687521458,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0014,
      "step": 192
    },
    {
      "epoch": 0.42071197411003236,
      "grad_norm": 0.05681368708610535,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0012,
      "step": 195
    },
    {
      "epoch": 0.42718446601941745,
      "grad_norm": 0.0026419395580887794,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0002,
      "step": 198
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.895083342495744e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}