{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6012024048096193,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 2.307159185409546,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 6.425,
      "step": 1
    },
    {
      "epoch": 0.008016032064128256,
      "eval_loss": 1.1576390266418457,
      "eval_runtime": 10.012,
      "eval_samples_per_second": 10.487,
      "eval_steps_per_second": 5.294,
      "step": 1
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 2.5824155807495117,
      "learning_rate": 6.666666666666667e-05,
      "loss": 6.4417,
      "step": 2
    },
    {
      "epoch": 0.02404809619238477,
      "grad_norm": 3.396984577178955,
      "learning_rate": 0.0001,
      "loss": 8.1689,
      "step": 3
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 2.59348726272583,
      "learning_rate": 9.99524110790929e-05,
      "loss": 7.313,
      "step": 4
    },
    {
      "epoch": 0.04008016032064128,
      "grad_norm": 2.7657885551452637,
      "learning_rate": 9.980973490458728e-05,
      "loss": 8.3049,
      "step": 5
    },
    {
      "epoch": 0.04809619238476954,
      "grad_norm": 2.9509098529815674,
      "learning_rate": 9.957224306869053e-05,
      "loss": 7.3503,
      "step": 6
    },
    {
      "epoch": 0.056112224448897796,
      "grad_norm": 2.893247604370117,
      "learning_rate": 9.924038765061042e-05,
      "loss": 6.8023,
      "step": 7
    },
    {
      "epoch": 0.06412825651302605,
      "grad_norm": 2.8917412757873535,
      "learning_rate": 9.881480035599667e-05,
      "loss": 7.3582,
      "step": 8
    },
    {
      "epoch": 0.07214428857715431,
      "grad_norm": 3.6936254501342773,
      "learning_rate": 9.829629131445342e-05,
      "loss": 7.792,
      "step": 9
    },
    {
      "epoch": 0.08016032064128256,
      "grad_norm": 3.8342223167419434,
      "learning_rate": 9.768584753741134e-05,
      "loss": 7.6313,
      "step": 10
    },
    {
      "epoch": 0.08817635270541083,
      "grad_norm": 3.553842544555664,
      "learning_rate": 9.698463103929542e-05,
      "loss": 7.9785,
      "step": 11
    },
    {
      "epoch": 0.09619238476953908,
      "grad_norm": 3.0366082191467285,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.9767,
      "step": 12
    },
    {
      "epoch": 0.10420841683366733,
      "grad_norm": 3.304401159286499,
      "learning_rate": 9.53153893518325e-05,
      "loss": 7.4045,
      "step": 13
    },
    {
      "epoch": 0.11222444889779559,
      "grad_norm": 3.1661627292633057,
      "learning_rate": 9.435054165891109e-05,
      "loss": 7.6905,
      "step": 14
    },
    {
      "epoch": 0.12024048096192384,
      "grad_norm": 3.185795545578003,
      "learning_rate": 9.330127018922194e-05,
      "loss": 7.6014,
      "step": 15
    },
    {
      "epoch": 0.1282565130260521,
      "grad_norm": 3.3107285499572754,
      "learning_rate": 9.21695722906443e-05,
      "loss": 7.9431,
      "step": 16
    },
    {
      "epoch": 0.13627254509018036,
      "grad_norm": 2.93304181098938,
      "learning_rate": 9.09576022144496e-05,
      "loss": 7.275,
      "step": 17
    },
    {
      "epoch": 0.14428857715430862,
      "grad_norm": 3.08390212059021,
      "learning_rate": 8.966766701456177e-05,
      "loss": 7.9457,
      "step": 18
    },
    {
      "epoch": 0.1523046092184369,
      "grad_norm": 3.381080150604248,
      "learning_rate": 8.83022221559489e-05,
      "loss": 8.2009,
      "step": 19
    },
    {
      "epoch": 0.16032064128256512,
      "grad_norm": 5.137476444244385,
      "learning_rate": 8.68638668405062e-05,
      "loss": 8.2093,
      "step": 20
    },
    {
      "epoch": 0.1683366733466934,
      "grad_norm": 3.8344078063964844,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.4002,
      "step": 21
    },
    {
      "epoch": 0.17635270541082165,
      "grad_norm": 3.9177253246307373,
      "learning_rate": 8.377951038078302e-05,
      "loss": 8.1867,
      "step": 22
    },
    {
      "epoch": 0.1843687374749499,
      "grad_norm": 5.506999492645264,
      "learning_rate": 8.213938048432697e-05,
      "loss": 8.3518,
      "step": 23
    },
    {
      "epoch": 0.19238476953907815,
      "grad_norm": 4.127420902252197,
      "learning_rate": 8.043807145043604e-05,
      "loss": 8.9159,
      "step": 24
    },
    {
      "epoch": 0.20040080160320642,
      "grad_norm": 4.1928229331970215,
      "learning_rate": 7.86788218175523e-05,
      "loss": 8.2144,
      "step": 25
    },
    {
      "epoch": 0.20040080160320642,
      "eval_loss": 0.9458172917366028,
      "eval_runtime": 10.0465,
      "eval_samples_per_second": 10.451,
      "eval_steps_per_second": 5.275,
      "step": 25
    },
    {
      "epoch": 0.20841683366733466,
      "grad_norm": 4.462054252624512,
      "learning_rate": 7.68649804173412e-05,
      "loss": 8.5793,
      "step": 26
    },
    {
      "epoch": 0.21643286573146292,
      "grad_norm": 4.8768463134765625,
      "learning_rate": 7.500000000000001e-05,
      "loss": 8.9825,
      "step": 27
    },
    {
      "epoch": 0.22444889779559118,
      "grad_norm": 4.757332801818848,
      "learning_rate": 7.308743066175172e-05,
      "loss": 8.4356,
      "step": 28
    },
    {
      "epoch": 0.23246492985971945,
      "grad_norm": 4.838624477386475,
      "learning_rate": 7.113091308703498e-05,
      "loss": 8.3826,
      "step": 29
    },
    {
      "epoch": 0.24048096192384769,
      "grad_norm": 5.770003318786621,
      "learning_rate": 6.91341716182545e-05,
      "loss": 8.4361,
      "step": 30
    },
    {
      "epoch": 0.24849699398797595,
      "grad_norm": 7.8174028396606445,
      "learning_rate": 6.710100716628344e-05,
      "loss": 8.9972,
      "step": 31
    },
    {
      "epoch": 0.2565130260521042,
      "grad_norm": 2.0084359645843506,
      "learning_rate": 6.503528997521366e-05,
      "loss": 5.4369,
      "step": 32
    },
    {
      "epoch": 0.26452905811623245,
      "grad_norm": 2.1963016986846924,
      "learning_rate": 6.294095225512603e-05,
      "loss": 6.623,
      "step": 33
    },
    {
      "epoch": 0.2725450901803607,
      "grad_norm": 2.6279807090759277,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 6.992,
      "step": 34
    },
    {
      "epoch": 0.280561122244489,
      "grad_norm": 2.3220574855804443,
      "learning_rate": 5.868240888334653e-05,
      "loss": 7.2082,
      "step": 35
    },
    {
      "epoch": 0.28857715430861725,
      "grad_norm": 2.368709087371826,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 7.3801,
      "step": 36
    },
    {
      "epoch": 0.2965931863727455,
      "grad_norm": 2.547515869140625,
      "learning_rate": 5.435778713738292e-05,
      "loss": 7.3293,
      "step": 37
    },
    {
      "epoch": 0.3046092184368738,
      "grad_norm": 2.321802854537964,
      "learning_rate": 5.218096936826681e-05,
      "loss": 6.902,
      "step": 38
    },
    {
      "epoch": 0.312625250501002,
      "grad_norm": 2.3677818775177,
      "learning_rate": 5e-05,
      "loss": 7.6134,
      "step": 39
    },
    {
      "epoch": 0.32064128256513025,
      "grad_norm": 2.6523196697235107,
      "learning_rate": 4.781903063173321e-05,
      "loss": 6.538,
      "step": 40
    },
    {
      "epoch": 0.3286573146292585,
      "grad_norm": 2.4183263778686523,
      "learning_rate": 4.564221286261709e-05,
      "loss": 7.0564,
      "step": 41
    },
    {
      "epoch": 0.3366733466933868,
      "grad_norm": 2.484513282775879,
      "learning_rate": 4.347369038899744e-05,
      "loss": 7.5796,
      "step": 42
    },
    {
      "epoch": 0.34468937875751504,
      "grad_norm": 2.533151149749756,
      "learning_rate": 4.131759111665349e-05,
      "loss": 6.9521,
      "step": 43
    },
    {
      "epoch": 0.3527054108216433,
      "grad_norm": 2.687480926513672,
      "learning_rate": 3.917801930309486e-05,
      "loss": 7.8218,
      "step": 44
    },
    {
      "epoch": 0.36072144288577157,
      "grad_norm": 2.9025418758392334,
      "learning_rate": 3.705904774487396e-05,
      "loss": 8.115,
      "step": 45
    },
    {
      "epoch": 0.3687374749498998,
      "grad_norm": 3.0086724758148193,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 7.9331,
      "step": 46
    },
    {
      "epoch": 0.37675350701402804,
      "grad_norm": 3.0804407596588135,
      "learning_rate": 3.289899283371657e-05,
      "loss": 7.3887,
      "step": 47
    },
    {
      "epoch": 0.3847695390781563,
      "grad_norm": 2.9071097373962402,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.5355,
      "step": 48
    },
    {
      "epoch": 0.3927855711422846,
      "grad_norm": 3.1507182121276855,
      "learning_rate": 2.886908691296504e-05,
      "loss": 8.1586,
      "step": 49
    },
    {
      "epoch": 0.40080160320641284,
      "grad_norm": 3.268674850463867,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 7.529,
      "step": 50
    },
    {
      "epoch": 0.40080160320641284,
      "eval_loss": 0.9151780009269714,
      "eval_runtime": 10.0555,
      "eval_samples_per_second": 10.442,
      "eval_steps_per_second": 5.271,
      "step": 50
    },
    {
      "epoch": 0.4088176352705411,
      "grad_norm": 3.3615987300872803,
      "learning_rate": 2.500000000000001e-05,
      "loss": 7.638,
      "step": 51
    },
    {
      "epoch": 0.4168336673346693,
      "grad_norm": 3.4315879344940186,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 7.6535,
      "step": 52
    },
    {
      "epoch": 0.4248496993987976,
      "grad_norm": 3.4674675464630127,
      "learning_rate": 2.132117818244771e-05,
      "loss": 7.576,
      "step": 53
    },
    {
      "epoch": 0.43286573146292584,
      "grad_norm": 4.074899196624756,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 8.2586,
      "step": 54
    },
    {
      "epoch": 0.4408817635270541,
      "grad_norm": 3.7496204376220703,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 8.2481,
      "step": 55
    },
    {
      "epoch": 0.44889779559118237,
      "grad_norm": 4.384031295776367,
      "learning_rate": 1.622048961921699e-05,
      "loss": 8.9745,
      "step": 56
    },
    {
      "epoch": 0.45691382765531063,
      "grad_norm": 4.619762897491455,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 8.3918,
      "step": 57
    },
    {
      "epoch": 0.4649298597194389,
      "grad_norm": 4.338256359100342,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 7.4605,
      "step": 58
    },
    {
      "epoch": 0.4729458917835671,
      "grad_norm": 4.962979316711426,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 8.278,
      "step": 59
    },
    {
      "epoch": 0.48096192384769537,
      "grad_norm": 5.241549968719482,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 8.4689,
      "step": 60
    },
    {
      "epoch": 0.48897795591182364,
      "grad_norm": 5.300624847412109,
      "learning_rate": 9.042397785550405e-06,
      "loss": 9.2895,
      "step": 61
    },
    {
      "epoch": 0.4969939879759519,
      "grad_norm": 6.585608005523682,
      "learning_rate": 7.830427709355725e-06,
      "loss": 7.982,
      "step": 62
    },
    {
      "epoch": 0.5050100200400801,
      "grad_norm": 1.4862316846847534,
      "learning_rate": 6.698729810778065e-06,
      "loss": 5.5931,
      "step": 63
    },
    {
      "epoch": 0.5130260521042084,
      "grad_norm": 1.845563530921936,
      "learning_rate": 5.649458341088915e-06,
      "loss": 6.426,
      "step": 64
    },
    {
      "epoch": 0.5210420841683366,
      "grad_norm": 1.8862559795379639,
      "learning_rate": 4.684610648167503e-06,
      "loss": 6.5485,
      "step": 65
    },
    {
      "epoch": 0.5290581162324649,
      "grad_norm": 1.9703049659729004,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 7.2592,
      "step": 66
    },
    {
      "epoch": 0.5370741482965932,
      "grad_norm": 1.9892781972885132,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 6.0312,
      "step": 67
    },
    {
      "epoch": 0.5450901803607214,
      "grad_norm": 2.151519775390625,
      "learning_rate": 2.314152462588659e-06,
      "loss": 6.933,
      "step": 68
    },
    {
      "epoch": 0.5531062124248497,
      "grad_norm": 2.203801155090332,
      "learning_rate": 1.70370868554659e-06,
      "loss": 6.3505,
      "step": 69
    },
    {
      "epoch": 0.561122244488978,
      "grad_norm": 2.3427622318267822,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 6.4348,
      "step": 70
    },
    {
      "epoch": 0.5691382765531062,
      "grad_norm": 2.671212911605835,
      "learning_rate": 7.596123493895991e-07,
      "loss": 7.2945,
      "step": 71
    },
    {
      "epoch": 0.5771543086172345,
      "grad_norm": 2.542541742324829,
      "learning_rate": 4.277569313094809e-07,
      "loss": 7.3814,
      "step": 72
    },
    {
      "epoch": 0.5851703406813628,
      "grad_norm": 2.441311836242676,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 6.5333,
      "step": 73
    },
    {
      "epoch": 0.593186372745491,
      "grad_norm": 2.626361608505249,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 6.1486,
      "step": 74
    },
    {
      "epoch": 0.6012024048096193,
      "grad_norm": 2.8685286045074463,
      "learning_rate": 0.0,
      "loss": 7.3685,
      "step": 75
    },
    {
      "epoch": 0.6012024048096193,
      "eval_loss": 0.9051383137702942,
      "eval_runtime": 10.0437,
      "eval_samples_per_second": 10.454,
      "eval_steps_per_second": 5.277,
      "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": 9.893690859533107e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}