{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2849002849002849,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003798670465337132,
      "grad_norm": 5.763856410980225,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3805,
      "step": 1
    },
    {
      "epoch": 0.003798670465337132,
      "eval_loss": 1.6539767980575562,
      "eval_runtime": 46.0435,
      "eval_samples_per_second": 4.822,
      "eval_steps_per_second": 2.411,
      "step": 1
    },
    {
      "epoch": 0.007597340930674264,
      "grad_norm": 10.064556121826172,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.3331,
      "step": 2
    },
    {
      "epoch": 0.011396011396011397,
      "grad_norm": 4.493223190307617,
      "learning_rate": 0.0001,
      "loss": 1.2743,
      "step": 3
    },
    {
      "epoch": 0.015194681861348529,
      "grad_norm": 2.946624755859375,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.8182,
      "step": 4
    },
    {
      "epoch": 0.01899335232668566,
      "grad_norm": 2.3877036571502686,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.4942,
      "step": 5
    },
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 2.079784631729126,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.3639,
      "step": 6
    },
    {
      "epoch": 0.026590693257359924,
      "grad_norm": 2.2234725952148438,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2986,
      "step": 7
    },
    {
      "epoch": 0.030389363722697058,
      "grad_norm": 2.4654929637908936,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.3149,
      "step": 8
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 1.5854908227920532,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2439,
      "step": 9
    },
    {
      "epoch": 0.03798670465337132,
      "grad_norm": 1.5591164827346802,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.2072,
      "step": 10
    },
    {
      "epoch": 0.04178537511870845,
      "grad_norm": 1.7570960521697998,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2455,
      "step": 11
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 1.3588300943374634,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2317,
      "step": 12
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 1.2992509603500366,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.2435,
      "step": 13
    },
    {
      "epoch": 0.05318138651471985,
      "grad_norm": 1.2096527814865112,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.1905,
      "step": 14
    },
    {
      "epoch": 0.05698005698005698,
      "grad_norm": 1.542781114578247,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2319,
      "step": 15
    },
    {
      "epoch": 0.060778727445394115,
      "grad_norm": 1.497053861618042,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.2579,
      "step": 16
    },
    {
      "epoch": 0.06457739791073125,
      "grad_norm": 0.8226407766342163,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.1359,
      "step": 17
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.5668431520462036,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.196,
      "step": 18
    },
    {
      "epoch": 0.0721747388414055,
      "grad_norm": 0.9736147522926331,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.147,
      "step": 19
    },
    {
      "epoch": 0.07597340930674264,
      "grad_norm": 1.0604015588760376,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.157,
      "step": 20
    },
    {
      "epoch": 0.07977207977207977,
      "grad_norm": 1.4285651445388794,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1586,
      "step": 21
    },
    {
      "epoch": 0.0835707502374169,
      "grad_norm": 1.30019211769104,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.1612,
      "step": 22
    },
    {
      "epoch": 0.08736942070275404,
      "grad_norm": 1.120355248451233,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1544,
      "step": 23
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 1.0541555881500244,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.177,
      "step": 24
    },
    {
      "epoch": 0.0949667616334283,
      "grad_norm": 4.731549263000488,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.1304,
      "step": 25
    },
    {
      "epoch": 0.0949667616334283,
      "eval_loss": 0.13617277145385742,
      "eval_runtime": 46.0992,
      "eval_samples_per_second": 4.816,
      "eval_steps_per_second": 2.408,
      "step": 25
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 1.1956746578216553,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.1458,
      "step": 26
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 1.324112057685852,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.163,
      "step": 27
    },
    {
      "epoch": 0.1063627730294397,
      "grad_norm": 0.8233721256256104,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.1269,
      "step": 28
    },
    {
      "epoch": 0.11016144349477683,
      "grad_norm": 1.525368332862854,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.1434,
      "step": 29
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 0.9574621319770813,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1332,
      "step": 30
    },
    {
      "epoch": 0.1177587844254511,
      "grad_norm": 1.4583760499954224,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1763,
      "step": 31
    },
    {
      "epoch": 0.12155745489078823,
      "grad_norm": 1.0511687994003296,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.1497,
      "step": 32
    },
    {
      "epoch": 0.12535612535612536,
      "grad_norm": 1.6222001314163208,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1879,
      "step": 33
    },
    {
      "epoch": 0.1291547958214625,
      "grad_norm": 0.9461656212806702,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.1369,
      "step": 34
    },
    {
      "epoch": 0.13295346628679963,
      "grad_norm": 1.5839506387710571,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.1875,
      "step": 35
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.9987668395042419,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1665,
      "step": 36
    },
    {
      "epoch": 0.14055080721747387,
      "grad_norm": 1.055713176727295,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.1277,
      "step": 37
    },
    {
      "epoch": 0.144349477682811,
      "grad_norm": 1.4075400829315186,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.1546,
      "step": 38
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.492407202720642,
      "learning_rate": 5e-05,
      "loss": 0.1452,
      "step": 39
    },
    {
      "epoch": 0.15194681861348527,
      "grad_norm": 1.1356338262557983,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.2063,
      "step": 40
    },
    {
      "epoch": 0.1557454890788224,
      "grad_norm": 0.7817217707633972,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.1271,
      "step": 41
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 1.0964385271072388,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.1298,
      "step": 42
    },
    {
      "epoch": 0.16334283000949668,
      "grad_norm": 0.8101369738578796,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1566,
      "step": 43
    },
    {
      "epoch": 0.1671415004748338,
      "grad_norm": 0.8687131404876709,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.1348,
      "step": 44
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 1.1124910116195679,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.1794,
      "step": 45
    },
    {
      "epoch": 0.17473884140550808,
      "grad_norm": 0.9842135310173035,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.1326,
      "step": 46
    },
    {
      "epoch": 0.1785375118708452,
      "grad_norm": 0.8552569150924683,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1088,
      "step": 47
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 0.7058787941932678,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1296,
      "step": 48
    },
    {
      "epoch": 0.18613485280151948,
      "grad_norm": 0.9564892053604126,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.1502,
      "step": 49
    },
    {
      "epoch": 0.1899335232668566,
      "grad_norm": 0.9216586351394653,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.1617,
      "step": 50
    },
    {
      "epoch": 0.1899335232668566,
      "eval_loss": 0.11469363421201706,
      "eval_runtime": 46.0987,
      "eval_samples_per_second": 4.816,
      "eval_steps_per_second": 2.408,
      "step": 50
    },
    {
      "epoch": 0.19373219373219372,
      "grad_norm": 1.5434670448303223,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1701,
      "step": 51
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.7094946503639221,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.106,
      "step": 52
    },
    {
      "epoch": 0.201329534662868,
      "grad_norm": 0.6739745140075684,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0905,
      "step": 53
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 1.323537826538086,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.1193,
      "step": 54
    },
    {
      "epoch": 0.20892687559354226,
      "grad_norm": 0.6400057673454285,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0969,
      "step": 55
    },
    {
      "epoch": 0.2127255460588794,
      "grad_norm": 0.5726168155670166,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.1037,
      "step": 56
    },
    {
      "epoch": 0.21652421652421652,
      "grad_norm": 0.9324626326560974,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.086,
      "step": 57
    },
    {
      "epoch": 0.22032288698955366,
      "grad_norm": 0.8309210538864136,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.1208,
      "step": 58
    },
    {
      "epoch": 0.2241215574548908,
      "grad_norm": 0.8675907850265503,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1326,
      "step": 59
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.6248118877410889,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1048,
      "step": 60
    },
    {
      "epoch": 0.23171889838556506,
      "grad_norm": 0.7150914072990417,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.1132,
      "step": 61
    },
    {
      "epoch": 0.2355175688509022,
      "grad_norm": 0.5807145833969116,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.1046,
      "step": 62
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.7972524762153625,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1191,
      "step": 63
    },
    {
      "epoch": 0.24311490978157646,
      "grad_norm": 0.5663894414901733,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.1081,
      "step": 64
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.2583680152893066,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.1063,
      "step": 65
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.5461013317108154,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1087,
      "step": 66
    },
    {
      "epoch": 0.25451092117758783,
      "grad_norm": 0.8133847117424011,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1474,
      "step": 67
    },
    {
      "epoch": 0.258309591642925,
      "grad_norm": 0.7079008221626282,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.141,
      "step": 68
    },
    {
      "epoch": 0.2621082621082621,
      "grad_norm": 0.49465906620025635,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0914,
      "step": 69
    },
    {
      "epoch": 0.26590693257359926,
      "grad_norm": 0.7780298590660095,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.1402,
      "step": 70
    },
    {
      "epoch": 0.26970560303893637,
      "grad_norm": 1.1167643070220947,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1814,
      "step": 71
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.5520243048667908,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.092,
      "step": 72
    },
    {
      "epoch": 0.27730294396961064,
      "grad_norm": 0.5053026676177979,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0918,
      "step": 73
    },
    {
      "epoch": 0.28110161443494774,
      "grad_norm": 0.7503936290740967,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.1032,
      "step": 74
    },
    {
      "epoch": 0.2849002849002849,
      "grad_norm": 0.8561326265335083,
      "learning_rate": 0.0,
      "loss": 0.1271,
      "step": 75
    },
    {
      "epoch": 0.2849002849002849,
      "eval_loss": 0.10664498805999756,
      "eval_runtime": 46.0966,
      "eval_samples_per_second": 4.816,
      "eval_steps_per_second": 2.408,
      "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": 1.24338409832448e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}