{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 231,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 4.101644677095025,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4313,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.13728275895118713,
      "step": 5,
      "valid_targets_mean": 14623.7,
      "valid_targets_min": 8472
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.4454499538073753,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.3895,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.12719786167144775,
      "step": 10,
      "valid_targets_mean": 13794.9,
      "valid_targets_min": 8012
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.5038065535865701,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.3418,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10844413936138153,
      "step": 15,
      "valid_targets_mean": 13961.8,
      "valid_targets_min": 7669
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.41739277046604123,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 0.3153,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.10475271940231323,
      "step": 20,
      "valid_targets_mean": 13416.8,
      "valid_targets_min": 8687
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.33255764844488456,
      "learning_rate": 4e-05,
      "loss": 0.2946,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0998668372631073,
      "step": 25,
      "valid_targets_mean": 14083.4,
      "valid_targets_min": 6271
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.24004137696165997,
      "learning_rate": 3.994244399375679e-05,
      "loss": 0.2711,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.09284907579421997,
      "step": 30,
      "valid_targets_mean": 14132.5,
      "valid_targets_min": 5776
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.1967596430894074,
      "learning_rate": 3.977010724441261e-05,
      "loss": 0.2525,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.08178113400936127,
      "step": 35,
      "valid_targets_mean": 13705.5,
      "valid_targets_min": 6252
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.1734645093560045,
      "learning_rate": 3.9483981653469586e-05,
      "loss": 0.2416,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07989491522312164,
      "step": 40,
      "valid_targets_mean": 13126.1,
      "valid_targets_min": 3159
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.14595289141638512,
      "learning_rate": 3.908571404555758e-05,
      "loss": 0.2317,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07932181656360626,
      "step": 45,
      "valid_targets_mean": 14597.3,
      "valid_targets_min": 6419
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.12986441353280917,
      "learning_rate": 3.8577596689969346e-05,
      "loss": 0.2282,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07134190946817398,
      "step": 50,
      "valid_targets_mean": 14610.6,
      "valid_targets_min": 9878
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.12387431430113442,
      "learning_rate": 3.7962554107273926e-05,
      "loss": 0.2185,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07062166929244995,
      "step": 55,
      "valid_targets_mean": 14205.5,
      "valid_targets_min": 8994
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.12267549383494643,
      "learning_rate": 3.724412623694427e-05,
      "loss": 0.2129,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0706438273191452,
      "step": 60,
      "valid_targets_mean": 14081.0,
      "valid_targets_min": 7128
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 0.13132589101740186,
      "learning_rate": 3.642644806287938e-05,
      "loss": 0.2075,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06862840801477432,
      "step": 65,
      "valid_targets_mean": 13509.2,
      "valid_targets_min": 6997
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 0.12677199044727938,
      "learning_rate": 3.55142258140884e-05,
      "loss": 0.206,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06504399329423904,
      "step": 70,
      "valid_targets_mean": 13193.5,
      "valid_targets_min": 3186
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.12762593759862736,
      "learning_rate": 3.451270987751598e-05,
      "loss": 0.206,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07134096324443817,
      "step": 75,
      "valid_targets_mean": 14511.4,
      "valid_targets_min": 5311
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.13192592609992332,
      "learning_rate": 3.342766457891194e-05,
      "loss": 0.1969,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.07061142474412918,
      "step": 80,
      "valid_targets_mean": 14961.1,
      "valid_targets_min": 9318
    },
    {
      "epoch": 2.5757575757575757,
      "grad_norm": 0.13179397065972617,
      "learning_rate": 3.226533500567433e-05,
      "loss": 0.1944,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06371868401765823,
      "step": 85,
      "valid_targets_mean": 14331.9,
      "valid_targets_min": 8629
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.1328210848350246,
      "learning_rate": 3.1032411062620544e-05,
      "loss": 0.1965,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06617560237646103,
      "step": 90,
      "valid_targets_mean": 14391.3,
      "valid_targets_min": 9017
    },
    {
      "epoch": 2.878787878787879,
      "grad_norm": 0.12863302635004717,
      "learning_rate": 2.973598896756697e-05,
      "loss": 0.192,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.054877690970897675,
      "step": 95,
      "valid_targets_mean": 14151.3,
      "valid_targets_min": 6828
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 0.12536418590701268,
      "learning_rate": 2.8383530408333285e-05,
      "loss": 0.1911,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06761929392814636,
      "step": 100,
      "valid_targets_mean": 13563.6,
      "valid_targets_min": 5230
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.1333475753151719,
      "learning_rate": 2.6982819596247373e-05,
      "loss": 0.1887,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06502775102853775,
      "step": 105,
      "valid_targets_mean": 13841.5,
      "valid_targets_min": 7737
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.132217993667279,
      "learning_rate": 2.554191846333378e-05,
      "loss": 0.1847,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06282747536897659,
      "step": 110,
      "valid_targets_mean": 13982.2,
      "valid_targets_min": 6906
    },
    {
      "epoch": 3.484848484848485,
      "grad_norm": 0.1436057374223123,
      "learning_rate": 2.4069120261052682e-05,
      "loss": 0.1857,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06083241477608681,
      "step": 115,
      "valid_targets_mean": 14595.4,
      "valid_targets_min": 7001
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.12244006139108565,
      "learning_rate": 2.2572901827656626e-05,
      "loss": 0.1867,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06318728625774384,
      "step": 120,
      "valid_targets_mean": 14134.8,
      "valid_targets_min": 4539
    },
    {
      "epoch": 3.787878787878788,
      "grad_norm": 0.11988143398274238,
      "learning_rate": 2.1061874798894992e-05,
      "loss": 0.1845,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.056565746665000916,
      "step": 125,
      "valid_targets_mean": 13645.1,
      "valid_targets_min": 6953
    },
    {
      "epoch": 3.9393939393939394,
      "grad_norm": 0.11973237571725541,
      "learning_rate": 1.9544736042877886e-05,
      "loss": 0.1823,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06245823949575424,
      "step": 130,
      "valid_targets_mean": 14213.2,
      "valid_targets_min": 7309
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 0.12095919425002426,
      "learning_rate": 1.8030217604376628e-05,
      "loss": 0.1826,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06537604331970215,
      "step": 135,
      "valid_targets_mean": 14312.2,
      "valid_targets_min": 4618
    },
    {
      "epoch": 4.242424242424242,
      "grad_norm": 0.13130755282071463,
      "learning_rate": 1.6527036446661396e-05,
      "loss": 0.1834,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06200536713004112,
      "step": 140,
      "valid_targets_mean": 13995.9,
      "valid_targets_min": 3159
    },
    {
      "epoch": 4.393939393939394,
      "grad_norm": 0.12849185934902171,
      "learning_rate": 1.5043844280142005e-05,
      "loss": 0.1806,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06337574869394302,
      "step": 145,
      "valid_targets_mean": 14415.2,
      "valid_targets_min": 7395
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.11717509615507843,
      "learning_rate": 1.358917776657806e-05,
      "loss": 0.1778,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05878318101167679,
      "step": 150,
      "valid_targets_mean": 13608.7,
      "valid_targets_min": 4237
    },
    {
      "epoch": 4.696969696969697,
      "grad_norm": 0.11445364177176875,
      "learning_rate": 1.2171409385463218e-05,
      "loss": 0.1763,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05898250639438629,
      "step": 155,
      "valid_targets_mean": 13554.9,
      "valid_targets_min": 6402
    },
    {
      "epoch": 4.848484848484849,
      "grad_norm": 0.12374376070955681,
      "learning_rate": 1.0798699245376959e-05,
      "loss": 0.1777,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0593249574303627,
      "step": 160,
      "valid_targets_mean": 14594.9,
      "valid_targets_min": 7248
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.12668564763351842,
      "learning_rate": 9.478948117658577e-06,
      "loss": 0.1781,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.058884840458631516,
      "step": 165,
      "valid_targets_mean": 13341.7,
      "valid_targets_min": 4728
    },
    {
      "epoch": 5.151515151515151,
      "grad_norm": 0.1277080409655682,
      "learning_rate": 8.219751962722726e-06,
      "loss": 0.1799,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.059690214693546295,
      "step": 170,
      "valid_targets_mean": 14140.9,
      "valid_targets_min": 5241
    },
    {
      "epoch": 5.303030303030303,
      "grad_norm": 0.12129503849947158,
      "learning_rate": 7.028358210744881e-06,
      "loss": 0.1719,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05800726264715195,
      "step": 175,
      "valid_targets_mean": 13437.8,
      "valid_targets_min": 3456
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.12508479858740726,
      "learning_rate": 5.911624048347757e-06,
      "loss": 0.1778,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.0543239489197731,
      "step": 180,
      "valid_targets_mean": 13450.3,
      "valid_targets_min": 8527
    },
    {
      "epoch": 5.606060606060606,
      "grad_norm": 0.11850280030919257,
      "learning_rate": 4.875976951373633e-06,
      "loss": 0.1766,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05465681105852127,
      "step": 185,
      "valid_targets_mean": 14527.5,
      "valid_targets_min": 6291
    },
    {
      "epoch": 5.757575757575758,
      "grad_norm": 0.1259060690244162,
      "learning_rate": 3.927377690900436e-06,
      "loss": 0.1751,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.06268830597400665,
      "step": 190,
      "valid_targets_mean": 15079.5,
      "valid_targets_min": 5311
    },
    {
      "epoch": 5.909090909090909,
      "grad_norm": 0.14573628407483133,
      "learning_rate": 3.071286025423983e-06,
      "loss": 0.1757,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.056300319731235504,
      "step": 195,
      "valid_targets_mean": 13432.3,
      "valid_targets_min": 4391
    },
    {
      "epoch": 6.0606060606060606,
      "grad_norm": 0.1202999097496865,
      "learning_rate": 2.312629276668554e-06,
      "loss": 0.1741,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05936381220817566,
      "step": 200,
      "valid_targets_mean": 14715.9,
      "valid_targets_min": 8912
    },
    {
      "epoch": 6.212121212121212,
      "grad_norm": 0.1180038599779071,
      "learning_rate": 1.6557739698909436e-06,
      "loss": 0.176,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.058680810034275055,
      "step": 205,
      "valid_targets_mean": 13863.8,
      "valid_targets_min": 5335
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.11530000691449392,
      "learning_rate": 1.1045007019049182e-06,
      "loss": 0.1749,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05926910787820816,
      "step": 210,
      "valid_targets_mean": 13876.2,
      "valid_targets_min": 4510
    },
    {
      "epoch": 6.515151515151516,
      "grad_norm": 0.10947627448010318,
      "learning_rate": 6.619823814758786e-07,
      "loss": 0.172,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.04738888889551163,
      "step": 215,
      "valid_targets_mean": 13260.7,
      "valid_targets_min": 2975
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.11639605353220038,
      "learning_rate": 3.307659673251595e-07,
      "loss": 0.1755,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.05408981069922447,
      "step": 220,
      "valid_targets_mean": 13885.9,
      "valid_targets_min": 4618
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 0.11887366873653407,
      "learning_rate": 1.1275780885282806e-07,
      "loss": 0.1759,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.060421451926231384,
      "step": 225,
      "valid_targets_mean": 13998.0,
      "valid_targets_min": 7669
    },
    {
      "epoch": 6.96969696969697,
      "grad_norm": 0.11790553258946189,
      "learning_rate": 9.212673951897177e-09,
      "loss": 0.1756,
      "loss_nan_ranks": 0,
      "loss_rank_avg": 0.061030447483062744,
      "step": 230,
      "valid_targets_mean": 14301.2,
      "valid_targets_min": 7992
    },
    {
      "epoch": 7.0,
      "step": 231,
      "total_flos": 1.7948424939556045e+18,
      "train_loss": 0.0,
      "train_runtime": 4.778,
      "train_samples_per_second": 4629.543,
      "train_steps_per_second": 48.346
    }
  ],
  "logging_steps": 5,
  "max_steps": 231,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7948424939556045e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}