{
  "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": 4.665867328643799,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.5552,
      "step": 1
    },
    {
      "epoch": 0.003798670465337132,
      "eval_loss": 1.9311774969100952,
      "eval_runtime": 55.3181,
      "eval_samples_per_second": 4.013,
      "eval_steps_per_second": 2.007,
      "step": 1
    },
    {
      "epoch": 0.007597340930674264,
      "grad_norm": 5.30722188949585,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.686,
      "step": 2
    },
    {
      "epoch": 0.011396011396011397,
      "grad_norm": 4.190699577331543,
      "learning_rate": 0.0001,
      "loss": 1.5167,
      "step": 3
    },
    {
      "epoch": 0.015194681861348529,
      "grad_norm": 3.806157112121582,
      "learning_rate": 9.99524110790929e-05,
      "loss": 1.3334,
      "step": 4
    },
    {
      "epoch": 0.01899335232668566,
      "grad_norm": 3.4110376834869385,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.16,
      "step": 5
    },
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 3.0708816051483154,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.8534,
      "step": 6
    },
    {
      "epoch": 0.026590693257359924,
      "grad_norm": 3.6232693195343018,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7034,
      "step": 7
    },
    {
      "epoch": 0.030389363722697058,
      "grad_norm": 4.736238956451416,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.5525,
      "step": 8
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 3.348017692565918,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4894,
      "step": 9
    },
    {
      "epoch": 0.03798670465337132,
      "grad_norm": 2.443892240524292,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.3534,
      "step": 10
    },
    {
      "epoch": 0.04178537511870845,
      "grad_norm": 2.586397886276245,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4916,
      "step": 11
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 3.266211986541748,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5123,
      "step": 12
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 2.3014657497406006,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.2928,
      "step": 13
    },
    {
      "epoch": 0.05318138651471985,
      "grad_norm": 1.9256023168563843,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.3083,
      "step": 14
    },
    {
      "epoch": 0.05698005698005698,
      "grad_norm": 1.6575430631637573,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2892,
      "step": 15
    },
    {
      "epoch": 0.060778727445394115,
      "grad_norm": 1.5955344438552856,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.325,
      "step": 16
    },
    {
      "epoch": 0.06457739791073125,
      "grad_norm": 1.7478339672088623,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.3174,
      "step": 17
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.6537673473358154,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.2674,
      "step": 18
    },
    {
      "epoch": 0.0721747388414055,
      "grad_norm": 1.9351404905319214,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2489,
      "step": 19
    },
    {
      "epoch": 0.07597340930674264,
      "grad_norm": 1.7359018325805664,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.2896,
      "step": 20
    },
    {
      "epoch": 0.07977207977207977,
      "grad_norm": 1.5246787071228027,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1862,
      "step": 21
    },
    {
      "epoch": 0.0835707502374169,
      "grad_norm": 2.1828513145446777,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.2575,
      "step": 22
    },
    {
      "epoch": 0.08736942070275404,
      "grad_norm": 1.5045286417007446,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2036,
      "step": 23
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 2.245671510696411,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.27,
      "step": 24
    },
    {
      "epoch": 0.0949667616334283,
      "grad_norm": 2.924475908279419,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.2836,
      "step": 25
    },
    {
      "epoch": 0.0949667616334283,
      "eval_loss": 0.19420784711837769,
      "eval_runtime": 56.1543,
      "eval_samples_per_second": 3.953,
      "eval_steps_per_second": 1.977,
      "step": 25
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 2.044268846511841,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.1934,
      "step": 26
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 2.4309701919555664,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2114,
      "step": 27
    },
    {
      "epoch": 0.1063627730294397,
      "grad_norm": 1.493461012840271,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.1577,
      "step": 28
    },
    {
      "epoch": 0.11016144349477683,
      "grad_norm": 1.7502208948135376,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.2512,
      "step": 29
    },
    {
      "epoch": 0.11396011396011396,
      "grad_norm": 1.5487176179885864,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.2177,
      "step": 30
    },
    {
      "epoch": 0.1177587844254511,
      "grad_norm": 1.3351069688796997,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1698,
      "step": 31
    },
    {
      "epoch": 0.12155745489078823,
      "grad_norm": 1.4412907361984253,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.21,
      "step": 32
    },
    {
      "epoch": 0.12535612535612536,
      "grad_norm": 1.621321678161621,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1952,
      "step": 33
    },
    {
      "epoch": 0.1291547958214625,
      "grad_norm": 1.1219773292541504,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.1465,
      "step": 34
    },
    {
      "epoch": 0.13295346628679963,
      "grad_norm": 1.6503297090530396,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.238,
      "step": 35
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 1.3077759742736816,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1917,
      "step": 36
    },
    {
      "epoch": 0.14055080721747387,
      "grad_norm": 1.59805428981781,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.1985,
      "step": 37
    },
    {
      "epoch": 0.144349477682811,
      "grad_norm": 1.5772435665130615,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.227,
      "step": 38
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.5069894790649414,
      "learning_rate": 5e-05,
      "loss": 0.2056,
      "step": 39
    },
    {
      "epoch": 0.15194681861348527,
      "grad_norm": 1.4937382936477661,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.2006,
      "step": 40
    },
    {
      "epoch": 0.1557454890788224,
      "grad_norm": 2.5350654125213623,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.2203,
      "step": 41
    },
    {
      "epoch": 0.15954415954415954,
      "grad_norm": 1.570905089378357,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.2555,
      "step": 42
    },
    {
      "epoch": 0.16334283000949668,
      "grad_norm": 1.4732633829116821,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1532,
      "step": 43
    },
    {
      "epoch": 0.1671415004748338,
      "grad_norm": 2.052095413208008,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.2438,
      "step": 44
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 1.493403673171997,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.182,
      "step": 45
    },
    {
      "epoch": 0.17473884140550808,
      "grad_norm": 1.1273841857910156,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.1675,
      "step": 46
    },
    {
      "epoch": 0.1785375118708452,
      "grad_norm": 1.939112901687622,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1654,
      "step": 47
    },
    {
      "epoch": 0.18233618233618235,
      "grad_norm": 1.0533381700515747,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.135,
      "step": 48
    },
    {
      "epoch": 0.18613485280151948,
      "grad_norm": 1.7359578609466553,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.2186,
      "step": 49
    },
    {
      "epoch": 0.1899335232668566,
      "grad_norm": 2.2593016624450684,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.2618,
      "step": 50
    },
    {
      "epoch": 0.1899335232668566,
      "eval_loss": 0.15622515976428986,
      "eval_runtime": 56.1714,
      "eval_samples_per_second": 3.952,
      "eval_steps_per_second": 1.976,
      "step": 50
    },
    {
      "epoch": 0.19373219373219372,
      "grad_norm": 1.0411734580993652,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1466,
      "step": 51
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 1.2727152109146118,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.1484,
      "step": 52
    },
    {
      "epoch": 0.201329534662868,
      "grad_norm": 1.522938847541809,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.1559,
      "step": 53
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 1.072451114654541,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.1234,
      "step": 54
    },
    {
      "epoch": 0.20892687559354226,
      "grad_norm": 2.466201066970825,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1619,
      "step": 55
    },
    {
      "epoch": 0.2127255460588794,
      "grad_norm": 2.4038662910461426,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.1967,
      "step": 56
    },
    {
      "epoch": 0.21652421652421652,
      "grad_norm": 2.5965778827667236,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2216,
      "step": 57
    },
    {
      "epoch": 0.22032288698955366,
      "grad_norm": 1.1259628534317017,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.1716,
      "step": 58
    },
    {
      "epoch": 0.2241215574548908,
      "grad_norm": 1.1792726516723633,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1462,
      "step": 59
    },
    {
      "epoch": 0.22792022792022792,
      "grad_norm": 0.8546663522720337,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1117,
      "step": 60
    },
    {
      "epoch": 0.23171889838556506,
      "grad_norm": 0.9426295161247253,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.1341,
      "step": 61
    },
    {
      "epoch": 0.2355175688509022,
      "grad_norm": 1.6098453998565674,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.167,
      "step": 62
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 1.1398288011550903,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1675,
      "step": 63
    },
    {
      "epoch": 0.24311490978157646,
      "grad_norm": 1.3635776042938232,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.1591,
      "step": 64
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.1154038906097412,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.1559,
      "step": 65
    },
    {
      "epoch": 0.25071225071225073,
      "grad_norm": 0.870740532875061,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1289,
      "step": 66
    },
    {
      "epoch": 0.25451092117758783,
      "grad_norm": 1.1247227191925049,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1535,
      "step": 67
    },
    {
      "epoch": 0.258309591642925,
      "grad_norm": 1.1654616594314575,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.1626,
      "step": 68
    },
    {
      "epoch": 0.2621082621082621,
      "grad_norm": 1.496175765991211,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.1781,
      "step": 69
    },
    {
      "epoch": 0.26590693257359926,
      "grad_norm": 2.098728895187378,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.1563,
      "step": 70
    },
    {
      "epoch": 0.26970560303893637,
      "grad_norm": 0.9920639991760254,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1556,
      "step": 71
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 1.3341926336288452,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.2277,
      "step": 72
    },
    {
      "epoch": 0.27730294396961064,
      "grad_norm": 1.2077915668487549,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.1837,
      "step": 73
    },
    {
      "epoch": 0.28110161443494774,
      "grad_norm": 0.9270416498184204,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.1284,
      "step": 74
    },
    {
      "epoch": 0.2849002849002849,
      "grad_norm": 1.1907814741134644,
      "learning_rate": 0.0,
      "loss": 0.2088,
      "step": 75
    },
    {
      "epoch": 0.2849002849002849,
      "eval_loss": 0.14623484015464783,
      "eval_runtime": 56.166,
      "eval_samples_per_second": 3.953,
      "eval_steps_per_second": 1.976,
      "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": 1.119015678246912e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}