{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13711151736745886,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018281535648994515,
      "grad_norm": 2.1625711917877197,
      "learning_rate": 1e-05,
      "loss": 2.0061,
      "step": 1
    },
    {
      "epoch": 0.0018281535648994515,
      "eval_loss": 1.9399960041046143,
      "eval_runtime": 64.9097,
      "eval_samples_per_second": 7.102,
      "eval_steps_per_second": 0.894,
      "step": 1
    },
    {
      "epoch": 0.003656307129798903,
      "grad_norm": 2.010770082473755,
      "learning_rate": 2e-05,
      "loss": 1.9237,
      "step": 2
    },
    {
      "epoch": 0.005484460694698354,
      "grad_norm": 2.0491600036621094,
      "learning_rate": 3e-05,
      "loss": 2.0086,
      "step": 3
    },
    {
      "epoch": 0.007312614259597806,
      "grad_norm": 1.9856997728347778,
      "learning_rate": 4e-05,
      "loss": 1.8546,
      "step": 4
    },
    {
      "epoch": 0.009140767824497258,
      "grad_norm": 1.999695897102356,
      "learning_rate": 5e-05,
      "loss": 1.7567,
      "step": 5
    },
    {
      "epoch": 0.010968921389396709,
      "grad_norm": 2.1339967250823975,
      "learning_rate": 6e-05,
      "loss": 1.6694,
      "step": 6
    },
    {
      "epoch": 0.012797074954296161,
      "grad_norm": 2.18298602104187,
      "learning_rate": 7e-05,
      "loss": 1.7307,
      "step": 7
    },
    {
      "epoch": 0.014625228519195612,
      "grad_norm": 1.8223989009857178,
      "learning_rate": 8e-05,
      "loss": 1.399,
      "step": 8
    },
    {
      "epoch": 0.016453382084095063,
      "grad_norm": 1.704209804534912,
      "learning_rate": 9e-05,
      "loss": 1.3331,
      "step": 9
    },
    {
      "epoch": 0.016453382084095063,
      "eval_loss": 1.2653414011001587,
      "eval_runtime": 65.9311,
      "eval_samples_per_second": 6.992,
      "eval_steps_per_second": 0.88,
      "step": 9
    },
    {
      "epoch": 0.018281535648994516,
      "grad_norm": 1.8971141576766968,
      "learning_rate": 0.0001,
      "loss": 1.3892,
      "step": 10
    },
    {
      "epoch": 0.02010968921389397,
      "grad_norm": 2.0571422576904297,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.1854,
      "step": 11
    },
    {
      "epoch": 0.021937842778793418,
      "grad_norm": 2.0925815105438232,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1601,
      "step": 12
    },
    {
      "epoch": 0.02376599634369287,
      "grad_norm": 1.8084160089492798,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.0377,
      "step": 13
    },
    {
      "epoch": 0.025594149908592323,
      "grad_norm": 1.7532470226287842,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.0497,
      "step": 14
    },
    {
      "epoch": 0.027422303473491772,
      "grad_norm": 1.5659563541412354,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.9577,
      "step": 15
    },
    {
      "epoch": 0.029250457038391225,
      "grad_norm": 1.5059962272644043,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9969,
      "step": 16
    },
    {
      "epoch": 0.031078610603290677,
      "grad_norm": 1.6406954526901245,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.9157,
      "step": 17
    },
    {
      "epoch": 0.03290676416819013,
      "grad_norm": 1.520993709564209,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9165,
      "step": 18
    },
    {
      "epoch": 0.03290676416819013,
      "eval_loss": 0.9396372437477112,
      "eval_runtime": 65.9735,
      "eval_samples_per_second": 6.988,
      "eval_steps_per_second": 0.879,
      "step": 18
    },
    {
      "epoch": 0.03473491773308958,
      "grad_norm": 1.4247767925262451,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8283,
      "step": 19
    },
    {
      "epoch": 0.03656307129798903,
      "grad_norm": 1.5920847654342651,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0668,
      "step": 20
    },
    {
      "epoch": 0.038391224862888484,
      "grad_norm": 1.451392650604248,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.9108,
      "step": 21
    },
    {
      "epoch": 0.04021937842778794,
      "grad_norm": 1.4005733728408813,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8867,
      "step": 22
    },
    {
      "epoch": 0.04204753199268738,
      "grad_norm": 1.284644365310669,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.8585,
      "step": 23
    },
    {
      "epoch": 0.043875685557586835,
      "grad_norm": 1.3989516496658325,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6688,
      "step": 24
    },
    {
      "epoch": 0.04570383912248629,
      "grad_norm": 1.6957075595855713,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7847,
      "step": 25
    },
    {
      "epoch": 0.04753199268738574,
      "grad_norm": 1.3463910818099976,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.7988,
      "step": 26
    },
    {
      "epoch": 0.04936014625228519,
      "grad_norm": 1.4402669668197632,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7279,
      "step": 27
    },
    {
      "epoch": 0.04936014625228519,
      "eval_loss": 0.8090941309928894,
      "eval_runtime": 65.9062,
      "eval_samples_per_second": 6.995,
      "eval_steps_per_second": 0.88,
      "step": 27
    },
    {
      "epoch": 0.051188299817184646,
      "grad_norm": 1.5752246379852295,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.784,
      "step": 28
    },
    {
      "epoch": 0.05301645338208409,
      "grad_norm": 1.5713309049606323,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8821,
      "step": 29
    },
    {
      "epoch": 0.054844606946983544,
      "grad_norm": 1.5881538391113281,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7659,
      "step": 30
    },
    {
      "epoch": 0.056672760511883,
      "grad_norm": 1.4045054912567139,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8434,
      "step": 31
    },
    {
      "epoch": 0.05850091407678245,
      "grad_norm": 1.3920577764511108,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7623,
      "step": 32
    },
    {
      "epoch": 0.0603290676416819,
      "grad_norm": 1.535837173461914,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.8262,
      "step": 33
    },
    {
      "epoch": 0.062157221206581355,
      "grad_norm": 1.3267228603363037,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7212,
      "step": 34
    },
    {
      "epoch": 0.06398537477148081,
      "grad_norm": 1.2633198499679565,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6503,
      "step": 35
    },
    {
      "epoch": 0.06581352833638025,
      "grad_norm": 1.4025475978851318,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7201,
      "step": 36
    },
    {
      "epoch": 0.06581352833638025,
      "eval_loss": 0.7338544130325317,
      "eval_runtime": 65.937,
      "eval_samples_per_second": 6.992,
      "eval_steps_per_second": 0.88,
      "step": 36
    },
    {
      "epoch": 0.06764168190127971,
      "grad_norm": 1.480459213256836,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7089,
      "step": 37
    },
    {
      "epoch": 0.06946983546617916,
      "grad_norm": 1.4058476686477661,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.7587,
      "step": 38
    },
    {
      "epoch": 0.0712979890310786,
      "grad_norm": 1.5269132852554321,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7869,
      "step": 39
    },
    {
      "epoch": 0.07312614259597806,
      "grad_norm": 1.5104089975357056,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7055,
      "step": 40
    },
    {
      "epoch": 0.07495429616087751,
      "grad_norm": 1.5070502758026123,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.677,
      "step": 41
    },
    {
      "epoch": 0.07678244972577697,
      "grad_norm": 1.4173520803451538,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.6873,
      "step": 42
    },
    {
      "epoch": 0.07861060329067641,
      "grad_norm": 1.5242536067962646,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.707,
      "step": 43
    },
    {
      "epoch": 0.08043875685557587,
      "grad_norm": 1.484297752380371,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6689,
      "step": 44
    },
    {
      "epoch": 0.08226691042047532,
      "grad_norm": 1.4110380411148071,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.7221,
      "step": 45
    },
    {
      "epoch": 0.08226691042047532,
      "eval_loss": 0.6858494281768799,
      "eval_runtime": 65.9822,
      "eval_samples_per_second": 6.987,
      "eval_steps_per_second": 0.879,
      "step": 45
    },
    {
      "epoch": 0.08409506398537477,
      "grad_norm": 1.623942494392395,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6482,
      "step": 46
    },
    {
      "epoch": 0.08592321755027423,
      "grad_norm": 1.4406014680862427,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.6407,
      "step": 47
    },
    {
      "epoch": 0.08775137111517367,
      "grad_norm": 1.2649809122085571,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5991,
      "step": 48
    },
    {
      "epoch": 0.08957952468007313,
      "grad_norm": 1.4061084985733032,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.6766,
      "step": 49
    },
    {
      "epoch": 0.09140767824497258,
      "grad_norm": 1.412961483001709,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.685,
      "step": 50
    },
    {
      "epoch": 0.09323583180987204,
      "grad_norm": 1.3918739557266235,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.6061,
      "step": 51
    },
    {
      "epoch": 0.09506398537477148,
      "grad_norm": 1.3472814559936523,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6214,
      "step": 52
    },
    {
      "epoch": 0.09689213893967093,
      "grad_norm": 1.3871572017669678,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.6313,
      "step": 53
    },
    {
      "epoch": 0.09872029250457039,
      "grad_norm": 1.3942546844482422,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.6416,
      "step": 54
    },
    {
      "epoch": 0.09872029250457039,
      "eval_loss": 0.6498388648033142,
      "eval_runtime": 65.8779,
      "eval_samples_per_second": 6.998,
      "eval_steps_per_second": 0.88,
      "step": 54
    },
    {
      "epoch": 0.10054844606946983,
      "grad_norm": 1.36981201171875,
      "learning_rate": 5e-05,
      "loss": 0.6073,
      "step": 55
    },
    {
      "epoch": 0.10237659963436929,
      "grad_norm": 1.2767627239227295,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.6272,
      "step": 56
    },
    {
      "epoch": 0.10420475319926874,
      "grad_norm": 1.4287116527557373,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.6646,
      "step": 57
    },
    {
      "epoch": 0.10603290676416818,
      "grad_norm": 1.3621071577072144,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7029,
      "step": 58
    },
    {
      "epoch": 0.10786106032906764,
      "grad_norm": 1.4007452726364136,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.6084,
      "step": 59
    },
    {
      "epoch": 0.10968921389396709,
      "grad_norm": 1.3651444911956787,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.6416,
      "step": 60
    },
    {
      "epoch": 0.11151736745886655,
      "grad_norm": 1.371893286705017,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.64,
      "step": 61
    },
    {
      "epoch": 0.113345521023766,
      "grad_norm": 1.320582628250122,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5838,
      "step": 62
    },
    {
      "epoch": 0.11517367458866545,
      "grad_norm": 1.489526391029358,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.743,
      "step": 63
    },
    {
      "epoch": 0.11517367458866545,
      "eval_loss": 0.632634162902832,
      "eval_runtime": 65.9467,
      "eval_samples_per_second": 6.99,
      "eval_steps_per_second": 0.879,
      "step": 63
    },
    {
      "epoch": 0.1170018281535649,
      "grad_norm": 1.4206615686416626,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6447,
      "step": 64
    },
    {
      "epoch": 0.11882998171846434,
      "grad_norm": 1.3722271919250488,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.6066,
      "step": 65
    },
    {
      "epoch": 0.1206581352833638,
      "grad_norm": 1.4413255453109741,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.567,
      "step": 66
    },
    {
      "epoch": 0.12248628884826325,
      "grad_norm": 1.2582032680511475,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.5628,
      "step": 67
    },
    {
      "epoch": 0.12431444241316271,
      "grad_norm": 1.5137399435043335,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.615,
      "step": 68
    },
    {
      "epoch": 0.12614259597806216,
      "grad_norm": 1.4835834503173828,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.6619,
      "step": 69
    },
    {
      "epoch": 0.12797074954296161,
      "grad_norm": 1.2490266561508179,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.5641,
      "step": 70
    },
    {
      "epoch": 0.12979890310786105,
      "grad_norm": 1.3015044927597046,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5771,
      "step": 71
    },
    {
      "epoch": 0.1316270566727605,
      "grad_norm": 1.284609317779541,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5642,
      "step": 72
    },
    {
      "epoch": 0.1316270566727605,
      "eval_loss": 0.610695481300354,
      "eval_runtime": 65.8956,
      "eval_samples_per_second": 6.996,
      "eval_steps_per_second": 0.88,
      "step": 72
    },
    {
      "epoch": 0.13345521023765997,
      "grad_norm": 1.3459687232971191,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6421,
      "step": 73
    },
    {
      "epoch": 0.13528336380255943,
      "grad_norm": 1.2567322254180908,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.5645,
      "step": 74
    },
    {
      "epoch": 0.13711151736745886,
      "grad_norm": 1.2956007719039917,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.5018,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.75170771156992e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}