{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1916320664324497,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025550942190993293,
      "grad_norm": 1.53200364112854,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7561,
      "step": 1
    },
    {
      "epoch": 0.0025550942190993293,
      "eval_loss": 1.2268282175064087,
      "eval_runtime": 14.1514,
      "eval_samples_per_second": 23.319,
      "eval_steps_per_second": 11.66,
      "step": 1
    },
    {
      "epoch": 0.005110188438198659,
      "grad_norm": 1.9359681606292725,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8051,
      "step": 2
    },
    {
      "epoch": 0.0076652826572979876,
      "grad_norm": 1.9072275161743164,
      "learning_rate": 0.0001,
      "loss": 0.7167,
      "step": 3
    },
    {
      "epoch": 0.010220376876397317,
      "grad_norm": 1.9421987533569336,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.6961,
      "step": 4
    },
    {
      "epoch": 0.012775471095496647,
      "grad_norm": 1.5934714078903198,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.6662,
      "step": 5
    },
    {
      "epoch": 0.015330565314595975,
      "grad_norm": 1.5324499607086182,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.5733,
      "step": 6
    },
    {
      "epoch": 0.017885659533695305,
      "grad_norm": 1.2407643795013428,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4593,
      "step": 7
    },
    {
      "epoch": 0.020440753752794635,
      "grad_norm": 1.2209930419921875,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.4631,
      "step": 8
    },
    {
      "epoch": 0.022995847971893964,
      "grad_norm": 1.2211153507232666,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.3791,
      "step": 9
    },
    {
      "epoch": 0.025550942190993294,
      "grad_norm": 1.0290553569793701,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.2189,
      "step": 10
    },
    {
      "epoch": 0.02810603641009262,
      "grad_norm": 1.0332614183425903,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2729,
      "step": 11
    },
    {
      "epoch": 0.03066113062919195,
      "grad_norm": 1.0011751651763916,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1428,
      "step": 12
    },
    {
      "epoch": 0.03321622484829128,
      "grad_norm": 0.949007511138916,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.1634,
      "step": 13
    },
    {
      "epoch": 0.03577131906739061,
      "grad_norm": 0.9039943814277649,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.1082,
      "step": 14
    },
    {
      "epoch": 0.03832641328648994,
      "grad_norm": 1.1624059677124023,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2475,
      "step": 15
    },
    {
      "epoch": 0.04088150750558927,
      "grad_norm": 0.852632999420166,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.1442,
      "step": 16
    },
    {
      "epoch": 0.0434366017246886,
      "grad_norm": 1.9482204914093018,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.2423,
      "step": 17
    },
    {
      "epoch": 0.04599169594378793,
      "grad_norm": 2.1159651279449463,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1545,
      "step": 18
    },
    {
      "epoch": 0.04854679016288726,
      "grad_norm": 0.93006432056427,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1337,
      "step": 19
    },
    {
      "epoch": 0.05110188438198659,
      "grad_norm": 1.2222368717193604,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.1912,
      "step": 20
    },
    {
      "epoch": 0.05365697860108592,
      "grad_norm": 1.0246840715408325,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1101,
      "step": 21
    },
    {
      "epoch": 0.05621207282018524,
      "grad_norm": 1.29256010055542,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0949,
      "step": 22
    },
    {
      "epoch": 0.05876716703928457,
      "grad_norm": 1.2891842126846313,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0922,
      "step": 23
    },
    {
      "epoch": 0.0613222612583839,
      "grad_norm": 0.9216324687004089,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.1193,
      "step": 24
    },
    {
      "epoch": 0.06387735547748323,
      "grad_norm": 1.4697248935699463,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.1848,
      "step": 25
    },
    {
      "epoch": 0.06387735547748323,
      "eval_loss": 0.1296844184398651,
      "eval_runtime": 14.115,
      "eval_samples_per_second": 23.379,
      "eval_steps_per_second": 11.69,
      "step": 25
    },
    {
      "epoch": 0.06643244969658256,
      "grad_norm": 1.4003750085830688,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.2388,
      "step": 26
    },
    {
      "epoch": 0.06898754391568189,
      "grad_norm": 0.7332248091697693,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1133,
      "step": 27
    },
    {
      "epoch": 0.07154263813478122,
      "grad_norm": 1.1896603107452393,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.2283,
      "step": 28
    },
    {
      "epoch": 0.07409773235388055,
      "grad_norm": 1.1134674549102783,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0962,
      "step": 29
    },
    {
      "epoch": 0.07665282657297988,
      "grad_norm": 0.8824465274810791,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1033,
      "step": 30
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 1.149545669555664,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0992,
      "step": 31
    },
    {
      "epoch": 0.08176301501117854,
      "grad_norm": 1.4859205484390259,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.1449,
      "step": 32
    },
    {
      "epoch": 0.08431810923027787,
      "grad_norm": 1.4090569019317627,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1599,
      "step": 33
    },
    {
      "epoch": 0.0868732034493772,
      "grad_norm": 0.9273414611816406,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0869,
      "step": 34
    },
    {
      "epoch": 0.08942829766847653,
      "grad_norm": 1.5829126834869385,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0687,
      "step": 35
    },
    {
      "epoch": 0.09198339188757586,
      "grad_norm": 0.9160271883010864,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0965,
      "step": 36
    },
    {
      "epoch": 0.09453848610667519,
      "grad_norm": 0.6371787786483765,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0343,
      "step": 37
    },
    {
      "epoch": 0.09709358032577452,
      "grad_norm": 1.1970824003219604,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0713,
      "step": 38
    },
    {
      "epoch": 0.09964867454487385,
      "grad_norm": 1.2046923637390137,
      "learning_rate": 5e-05,
      "loss": 0.0583,
      "step": 39
    },
    {
      "epoch": 0.10220376876397318,
      "grad_norm": 0.6077913045883179,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0248,
      "step": 40
    },
    {
      "epoch": 0.1047588629830725,
      "grad_norm": 0.13593098521232605,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0041,
      "step": 41
    },
    {
      "epoch": 0.10731395720217184,
      "grad_norm": 0.3258521854877472,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0045,
      "step": 42
    },
    {
      "epoch": 0.10986905142127117,
      "grad_norm": 0.13207238912582397,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.005,
      "step": 43
    },
    {
      "epoch": 0.11242414564037048,
      "grad_norm": 0.12057414650917053,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0018,
      "step": 44
    },
    {
      "epoch": 0.11497923985946981,
      "grad_norm": 0.40026429295539856,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0105,
      "step": 45
    },
    {
      "epoch": 0.11753433407856914,
      "grad_norm": 0.13764841854572296,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0017,
      "step": 46
    },
    {
      "epoch": 0.12008942829766847,
      "grad_norm": 1.6517468690872192,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.055,
      "step": 47
    },
    {
      "epoch": 0.1226445225167678,
      "grad_norm": 0.8555214405059814,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0113,
      "step": 48
    },
    {
      "epoch": 0.12519961673586713,
      "grad_norm": 0.9184969663619995,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0174,
      "step": 49
    },
    {
      "epoch": 0.12775471095496646,
      "grad_norm": 4.27571964263916,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.1238,
      "step": 50
    },
    {
      "epoch": 0.12775471095496646,
      "eval_loss": 0.08126296103000641,
      "eval_runtime": 14.1157,
      "eval_samples_per_second": 23.378,
      "eval_steps_per_second": 11.689,
      "step": 50
    },
    {
      "epoch": 0.1303098051740658,
      "grad_norm": 1.1723414659500122,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0801,
      "step": 51
    },
    {
      "epoch": 0.13286489939316512,
      "grad_norm": 0.8172379732131958,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.1024,
      "step": 52
    },
    {
      "epoch": 0.13541999361226445,
      "grad_norm": 0.9060799479484558,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.1177,
      "step": 53
    },
    {
      "epoch": 0.13797508783136378,
      "grad_norm": 0.5991807579994202,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0704,
      "step": 54
    },
    {
      "epoch": 0.1405301820504631,
      "grad_norm": 0.703624427318573,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0954,
      "step": 55
    },
    {
      "epoch": 0.14308527626956244,
      "grad_norm": 0.7881723642349243,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.0788,
      "step": 56
    },
    {
      "epoch": 0.14564037048866177,
      "grad_norm": 0.9600244164466858,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0974,
      "step": 57
    },
    {
      "epoch": 0.1481954647077611,
      "grad_norm": 0.8376311659812927,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.0588,
      "step": 58
    },
    {
      "epoch": 0.15075055892686043,
      "grad_norm": 0.936733603477478,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1407,
      "step": 59
    },
    {
      "epoch": 0.15330565314595976,
      "grad_norm": 0.8105266690254211,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0863,
      "step": 60
    },
    {
      "epoch": 0.1558607473650591,
      "grad_norm": 0.4721161723136902,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0296,
      "step": 61
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.5724545121192932,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0688,
      "step": 62
    },
    {
      "epoch": 0.16097093580325775,
      "grad_norm": 1.028909683227539,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0995,
      "step": 63
    },
    {
      "epoch": 0.16352603002235708,
      "grad_norm": 0.7372393608093262,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0972,
      "step": 64
    },
    {
      "epoch": 0.1660811242414564,
      "grad_norm": 1.3419673442840576,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.1088,
      "step": 65
    },
    {
      "epoch": 0.16863621846055574,
      "grad_norm": 0.7063865661621094,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0701,
      "step": 66
    },
    {
      "epoch": 0.17119131267965507,
      "grad_norm": 0.628400444984436,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0733,
      "step": 67
    },
    {
      "epoch": 0.1737464068987544,
      "grad_norm": 1.4911381006240845,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.1276,
      "step": 68
    },
    {
      "epoch": 0.17630150111785373,
      "grad_norm": 0.7579659223556519,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0869,
      "step": 69
    },
    {
      "epoch": 0.17885659533695306,
      "grad_norm": 0.3117106258869171,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0235,
      "step": 70
    },
    {
      "epoch": 0.18141168955605239,
      "grad_norm": 1.2181602716445923,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0903,
      "step": 71
    },
    {
      "epoch": 0.18396678377515172,
      "grad_norm": 0.6046707034111023,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.03,
      "step": 72
    },
    {
      "epoch": 0.18652187799425105,
      "grad_norm": 0.4396168291568756,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0308,
      "step": 73
    },
    {
      "epoch": 0.18907697221335037,
      "grad_norm": 0.7448429465293884,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0689,
      "step": 74
    },
    {
      "epoch": 0.1916320664324497,
      "grad_norm": 0.9112486839294434,
      "learning_rate": 0.0,
      "loss": 0.0907,
      "step": 75
    },
    {
      "epoch": 0.1916320664324497,
      "eval_loss": 0.06476715207099915,
      "eval_runtime": 14.1155,
      "eval_samples_per_second": 23.379,
      "eval_steps_per_second": 11.689,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.98663066353664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}