{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009752291788570315,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001300305571809375,
      "grad_norm": 1.6780084371566772,
      "learning_rate": 1e-05,
      "loss": 2.9304,
      "step": 1
    },
    {
      "epoch": 0.0001300305571809375,
      "eval_loss": 2.9824275970458984,
      "eval_runtime": 794.147,
      "eval_samples_per_second": 8.156,
      "eval_steps_per_second": 1.02,
      "step": 1
    },
    {
      "epoch": 0.000260061114361875,
      "grad_norm": 1.5127434730529785,
      "learning_rate": 2e-05,
      "loss": 2.6721,
      "step": 2
    },
    {
      "epoch": 0.0003900916715428126,
      "grad_norm": 1.4549626111984253,
      "learning_rate": 3e-05,
      "loss": 3.0495,
      "step": 3
    },
    {
      "epoch": 0.00052012222872375,
      "grad_norm": 1.4239425659179688,
      "learning_rate": 4e-05,
      "loss": 2.848,
      "step": 4
    },
    {
      "epoch": 0.0006501527859046876,
      "grad_norm": 1.7163941860198975,
      "learning_rate": 5e-05,
      "loss": 2.9877,
      "step": 5
    },
    {
      "epoch": 0.0007801833430856252,
      "grad_norm": 1.7513028383255005,
      "learning_rate": 6e-05,
      "loss": 3.1093,
      "step": 6
    },
    {
      "epoch": 0.0009102139002665627,
      "grad_norm": 2.0409626960754395,
      "learning_rate": 7e-05,
      "loss": 2.9148,
      "step": 7
    },
    {
      "epoch": 0.0010402444574475,
      "grad_norm": 1.8178987503051758,
      "learning_rate": 8e-05,
      "loss": 2.5652,
      "step": 8
    },
    {
      "epoch": 0.0011702750146284377,
      "grad_norm": 1.719016432762146,
      "learning_rate": 9e-05,
      "loss": 2.6372,
      "step": 9
    },
    {
      "epoch": 0.0011702750146284377,
      "eval_loss": 2.53609037399292,
      "eval_runtime": 798.3055,
      "eval_samples_per_second": 8.113,
      "eval_steps_per_second": 1.015,
      "step": 9
    },
    {
      "epoch": 0.001300305571809375,
      "grad_norm": 1.8005650043487549,
      "learning_rate": 0.0001,
      "loss": 2.6104,
      "step": 10
    },
    {
      "epoch": 0.0014303361289903127,
      "grad_norm": 2.23337984085083,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.5353,
      "step": 11
    },
    {
      "epoch": 0.0015603666861712503,
      "grad_norm": 2.304137706756592,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4463,
      "step": 12
    },
    {
      "epoch": 0.0016903972433521877,
      "grad_norm": 2.395646333694458,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.2376,
      "step": 13
    },
    {
      "epoch": 0.0018204278005331254,
      "grad_norm": 2.0669045448303223,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.2355,
      "step": 14
    },
    {
      "epoch": 0.0019504583577140628,
      "grad_norm": 1.8650434017181396,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.1997,
      "step": 15
    },
    {
      "epoch": 0.002080488914895,
      "grad_norm": 1.7368872165679932,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.2981,
      "step": 16
    },
    {
      "epoch": 0.002210519472075938,
      "grad_norm": 1.7989248037338257,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.1886,
      "step": 17
    },
    {
      "epoch": 0.0023405500292568754,
      "grad_norm": 2.1002037525177,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0913,
      "step": 18
    },
    {
      "epoch": 0.0023405500292568754,
      "eval_loss": 2.1949336528778076,
      "eval_runtime": 798.1959,
      "eval_samples_per_second": 8.115,
      "eval_steps_per_second": 1.015,
      "step": 18
    },
    {
      "epoch": 0.002470580586437813,
      "grad_norm": 2.0304739475250244,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1125,
      "step": 19
    },
    {
      "epoch": 0.00260061114361875,
      "grad_norm": 1.8570281267166138,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.0389,
      "step": 20
    },
    {
      "epoch": 0.002730641700799688,
      "grad_norm": 1.9962009191513062,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2157,
      "step": 21
    },
    {
      "epoch": 0.0028606722579806254,
      "grad_norm": 1.610560655593872,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.0864,
      "step": 22
    },
    {
      "epoch": 0.002990702815161563,
      "grad_norm": 1.5690929889678955,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.0661,
      "step": 23
    },
    {
      "epoch": 0.0031207333723425007,
      "grad_norm": 1.4237191677093506,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.1762,
      "step": 24
    },
    {
      "epoch": 0.003250763929523438,
      "grad_norm": 1.434701919555664,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.3499,
      "step": 25
    },
    {
      "epoch": 0.0033807944867043755,
      "grad_norm": 1.446837067604065,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.1251,
      "step": 26
    },
    {
      "epoch": 0.003510825043885313,
      "grad_norm": 1.3660688400268555,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.2792,
      "step": 27
    },
    {
      "epoch": 0.003510825043885313,
      "eval_loss": 2.0874953269958496,
      "eval_runtime": 798.6075,
      "eval_samples_per_second": 8.11,
      "eval_steps_per_second": 1.014,
      "step": 27
    },
    {
      "epoch": 0.0036408556010662507,
      "grad_norm": 1.325317144393921,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0105,
      "step": 28
    },
    {
      "epoch": 0.003770886158247188,
      "grad_norm": 1.1957124471664429,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.922,
      "step": 29
    },
    {
      "epoch": 0.0039009167154281255,
      "grad_norm": 1.3279383182525635,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.2541,
      "step": 30
    },
    {
      "epoch": 0.004030947272609063,
      "grad_norm": 1.3062236309051514,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.1241,
      "step": 31
    },
    {
      "epoch": 0.00416097782979,
      "grad_norm": 1.2911529541015625,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.0332,
      "step": 32
    },
    {
      "epoch": 0.004291008386970939,
      "grad_norm": 1.3375964164733887,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.2418,
      "step": 33
    },
    {
      "epoch": 0.004421038944151876,
      "grad_norm": 1.2575992345809937,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.006,
      "step": 34
    },
    {
      "epoch": 0.004551069501332813,
      "grad_norm": 1.4063093662261963,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.1193,
      "step": 35
    },
    {
      "epoch": 0.004681100058513751,
      "grad_norm": 1.3179113864898682,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0329,
      "step": 36
    },
    {
      "epoch": 0.004681100058513751,
      "eval_loss": 2.035128116607666,
      "eval_runtime": 799.1613,
      "eval_samples_per_second": 8.105,
      "eval_steps_per_second": 1.014,
      "step": 36
    },
    {
      "epoch": 0.004811130615694688,
      "grad_norm": 1.2613023519515991,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.9313,
      "step": 37
    },
    {
      "epoch": 0.004941161172875626,
      "grad_norm": 1.3515223264694214,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.0788,
      "step": 38
    },
    {
      "epoch": 0.005071191730056563,
      "grad_norm": 1.2660778760910034,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.1036,
      "step": 39
    },
    {
      "epoch": 0.0052012222872375,
      "grad_norm": 1.326257348060608,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9786,
      "step": 40
    },
    {
      "epoch": 0.005331252844418439,
      "grad_norm": 1.3134316205978394,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.9815,
      "step": 41
    },
    {
      "epoch": 0.005461283401599376,
      "grad_norm": 1.205758810043335,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.7983,
      "step": 42
    },
    {
      "epoch": 0.0055913139587803135,
      "grad_norm": 1.2276418209075928,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.9806,
      "step": 43
    },
    {
      "epoch": 0.005721344515961251,
      "grad_norm": 1.2819576263427734,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.1088,
      "step": 44
    },
    {
      "epoch": 0.005851375073142188,
      "grad_norm": 1.5112415552139282,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.1042,
      "step": 45
    },
    {
      "epoch": 0.005851375073142188,
      "eval_loss": 2.016366481781006,
      "eval_runtime": 798.8661,
      "eval_samples_per_second": 8.108,
      "eval_steps_per_second": 1.014,
      "step": 45
    },
    {
      "epoch": 0.005981405630323126,
      "grad_norm": 1.3770538568496704,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9961,
      "step": 46
    },
    {
      "epoch": 0.006111436187504063,
      "grad_norm": 1.2575160264968872,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.9696,
      "step": 47
    },
    {
      "epoch": 0.006241466744685001,
      "grad_norm": 1.291962742805481,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.9734,
      "step": 48
    },
    {
      "epoch": 0.006371497301865939,
      "grad_norm": 1.3372758626937866,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.9297,
      "step": 49
    },
    {
      "epoch": 0.006501527859046876,
      "grad_norm": 1.4221460819244385,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.0235,
      "step": 50
    },
    {
      "epoch": 0.006631558416227814,
      "grad_norm": 1.375552773475647,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.154,
      "step": 51
    },
    {
      "epoch": 0.006761588973408751,
      "grad_norm": 1.2784361839294434,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.8162,
      "step": 52
    },
    {
      "epoch": 0.006891619530589688,
      "grad_norm": 1.276304841041565,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8764,
      "step": 53
    },
    {
      "epoch": 0.007021650087770626,
      "grad_norm": 1.410377860069275,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.0339,
      "step": 54
    },
    {
      "epoch": 0.007021650087770626,
      "eval_loss": 2.003307342529297,
      "eval_runtime": 797.8815,
      "eval_samples_per_second": 8.118,
      "eval_steps_per_second": 1.015,
      "step": 54
    },
    {
      "epoch": 0.007151680644951564,
      "grad_norm": 1.4492992162704468,
      "learning_rate": 5e-05,
      "loss": 1.9981,
      "step": 55
    },
    {
      "epoch": 0.0072817112021325014,
      "grad_norm": 1.2912863492965698,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.9296,
      "step": 56
    },
    {
      "epoch": 0.007411741759313439,
      "grad_norm": 1.4446409940719604,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.1402,
      "step": 57
    },
    {
      "epoch": 0.007541772316494376,
      "grad_norm": 1.3119258880615234,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.1206,
      "step": 58
    },
    {
      "epoch": 0.007671802873675314,
      "grad_norm": 1.3505756855010986,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.9904,
      "step": 59
    },
    {
      "epoch": 0.007801833430856251,
      "grad_norm": 1.1748305559158325,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.8244,
      "step": 60
    },
    {
      "epoch": 0.00793186398803719,
      "grad_norm": 1.4007622003555298,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.7583,
      "step": 61
    },
    {
      "epoch": 0.008061894545218126,
      "grad_norm": 1.347882628440857,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.7797,
      "step": 62
    },
    {
      "epoch": 0.008191925102399064,
      "grad_norm": 1.238471508026123,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.0858,
      "step": 63
    },
    {
      "epoch": 0.008191925102399064,
      "eval_loss": 1.9927431344985962,
      "eval_runtime": 798.194,
      "eval_samples_per_second": 8.115,
      "eval_steps_per_second": 1.015,
      "step": 63
    },
    {
      "epoch": 0.00832195565958,
      "grad_norm": 1.262229323387146,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9837,
      "step": 64
    },
    {
      "epoch": 0.008451986216760939,
      "grad_norm": 1.2074021100997925,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.7543,
      "step": 65
    },
    {
      "epoch": 0.008582016773941877,
      "grad_norm": 1.2249289751052856,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8353,
      "step": 66
    },
    {
      "epoch": 0.008712047331122814,
      "grad_norm": 1.2845371961593628,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.1002,
      "step": 67
    },
    {
      "epoch": 0.008842077888303752,
      "grad_norm": 1.6088101863861084,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.0395,
      "step": 68
    },
    {
      "epoch": 0.008972108445484689,
      "grad_norm": 1.3388179540634155,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.0359,
      "step": 69
    },
    {
      "epoch": 0.009102139002665627,
      "grad_norm": 1.3151459693908691,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.9293,
      "step": 70
    },
    {
      "epoch": 0.009232169559846563,
      "grad_norm": 1.2528445720672607,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.1133,
      "step": 71
    },
    {
      "epoch": 0.009362200117027502,
      "grad_norm": 1.1626242399215698,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.9243,
      "step": 72
    },
    {
      "epoch": 0.009362200117027502,
      "eval_loss": 1.9879481792449951,
      "eval_runtime": 798.4744,
      "eval_samples_per_second": 8.112,
      "eval_steps_per_second": 1.014,
      "step": 72
    },
    {
      "epoch": 0.009492230674208438,
      "grad_norm": 1.1865943670272827,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1736,
      "step": 73
    },
    {
      "epoch": 0.009622261231389376,
      "grad_norm": 1.312575101852417,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.9773,
      "step": 74
    },
    {
      "epoch": 0.009752291788570315,
      "grad_norm": 1.3586748838424683,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.0381,
      "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": 5.56415462670336e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}