{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 278,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03597122302158273,
      "grad_norm": 0.09922864826944784,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.9273451805114746,
      "step": 5
    },
    {
      "epoch": 0.07194244604316546,
      "grad_norm": 0.09775713327362429,
      "learning_rate": 0.0001,
      "loss": 0.879729175567627,
      "step": 10
    },
    {
      "epoch": 0.1079136690647482,
      "grad_norm": 0.06962031038398203,
      "learning_rate": 9.991477798614638e-05,
      "loss": 0.8456396102905274,
      "step": 15
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 0.07512256866077939,
      "learning_rate": 9.965940245625131e-05,
      "loss": 0.8059403419494628,
      "step": 20
    },
    {
      "epoch": 0.17985611510791366,
      "grad_norm": 0.06345996636264109,
      "learning_rate": 9.923474395499265e-05,
      "loss": 0.7759585857391358,
      "step": 25
    },
    {
      "epoch": 0.2158273381294964,
      "grad_norm": 0.06004270955330792,
      "learning_rate": 9.864225009247751e-05,
      "loss": 0.7483164310455322,
      "step": 30
    },
    {
      "epoch": 0.2517985611510791,
      "grad_norm": 0.07437488371254487,
      "learning_rate": 9.788394060951229e-05,
      "loss": 0.8478424072265625,
      "step": 35
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.07975161331683868,
      "learning_rate": 9.696240049254743e-05,
      "loss": 0.8275875091552735,
      "step": 40
    },
    {
      "epoch": 0.3237410071942446,
      "grad_norm": 0.056110204238877824,
      "learning_rate": 9.588077116176756e-05,
      "loss": 0.745372200012207,
      "step": 45
    },
    {
      "epoch": 0.3597122302158273,
      "grad_norm": 0.07311021819090241,
      "learning_rate": 9.464273976236517e-05,
      "loss": 0.8448892593383789,
      "step": 50
    },
    {
      "epoch": 0.39568345323741005,
      "grad_norm": 0.06206181655606858,
      "learning_rate": 9.325252659550309e-05,
      "loss": 0.803032398223877,
      "step": 55
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 0.07330787459721261,
      "learning_rate": 9.171487073181198e-05,
      "loss": 0.7427041053771972,
      "step": 60
    },
    {
      "epoch": 0.4676258992805755,
      "grad_norm": 0.06690776136899469,
      "learning_rate": 9.003501385646449e-05,
      "loss": 0.845458984375,
      "step": 65
    },
    {
      "epoch": 0.5035971223021583,
      "grad_norm": 0.06724649328703676,
      "learning_rate": 8.821868240089676e-05,
      "loss": 0.7568838119506835,
      "step": 70
    },
    {
      "epoch": 0.539568345323741,
      "grad_norm": 0.07423296624528276,
      "learning_rate": 8.62720680220876e-05,
      "loss": 0.8067834854125977,
      "step": 75
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.06821297058376587,
      "learning_rate": 8.420180649593929e-05,
      "loss": 0.8216766357421875,
      "step": 80
    },
    {
      "epoch": 0.6115107913669064,
      "grad_norm": 0.0845331853669141,
      "learning_rate": 8.201495509671037e-05,
      "loss": 0.7999070167541504,
      "step": 85
    },
    {
      "epoch": 0.6474820143884892,
      "grad_norm": 0.08940520339956634,
      "learning_rate": 7.971896853961042e-05,
      "loss": 0.7463856220245362,
      "step": 90
    },
    {
      "epoch": 0.6834532374100719,
      "grad_norm": 0.0739578639152744,
      "learning_rate": 7.732167356856655e-05,
      "loss": 0.7730668067932129,
      "step": 95
    },
    {
      "epoch": 0.7194244604316546,
      "grad_norm": 0.0695624845552875,
      "learning_rate": 7.483124227578811e-05,
      "loss": 0.732236385345459,
      "step": 100
    },
    {
      "epoch": 0.7553956834532374,
      "grad_norm": 0.08718202167856036,
      "learning_rate": 7.225616424408045e-05,
      "loss": 0.8057218551635742,
      "step": 105
    },
    {
      "epoch": 0.7913669064748201,
      "grad_norm": 0.06252924097123615,
      "learning_rate": 6.960521760687129e-05,
      "loss": 0.7559296131134033,
      "step": 110
    },
    {
      "epoch": 0.8273381294964028,
      "grad_norm": 0.0683171512398649,
      "learning_rate": 6.688743912460229e-05,
      "loss": 0.798275089263916,
      "step": 115
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 0.06946370954099755,
      "learning_rate": 6.411209337949214e-05,
      "loss": 0.7671150684356689,
      "step": 120
    },
    {
      "epoch": 0.8992805755395683,
      "grad_norm": 0.06965417114125676,
      "learning_rate": 6.128864119368234e-05,
      "loss": 0.6539465904235839,
      "step": 125
    },
    {
      "epoch": 0.935251798561151,
      "grad_norm": 0.06667373525748503,
      "learning_rate": 5.8426707378424675e-05,
      "loss": 0.8279660224914551,
      "step": 130
    },
    {
      "epoch": 0.9712230215827338,
      "grad_norm": 0.06288374976421086,
      "learning_rate": 5.553604792424922e-05,
      "loss": 0.8029556274414062,
      "step": 135
    },
    {
      "epoch": 1.0071942446043165,
      "grad_norm": 0.07572492394881657,
      "learning_rate": 5.262651674395799e-05,
      "loss": 0.7947874069213867,
      "step": 140
    },
    {
      "epoch": 1.0431654676258992,
      "grad_norm": 0.07014160285000554,
      "learning_rate": 4.9708032081813144e-05,
      "loss": 0.7853281021118164,
      "step": 145
    },
    {
      "epoch": 1.079136690647482,
      "grad_norm": 0.07147065892903694,
      "learning_rate": 4.679054270342703e-05,
      "loss": 0.7561178207397461,
      "step": 150
    },
    {
      "epoch": 1.1151079136690647,
      "grad_norm": 0.08320440539524798,
      "learning_rate": 4.3883993981608576e-05,
      "loss": 0.6941920757293701,
      "step": 155
    },
    {
      "epoch": 1.1510791366906474,
      "grad_norm": 0.09370719660499001,
      "learning_rate": 4.0998293993775237e-05,
      "loss": 0.7089109420776367,
      "step": 160
    },
    {
      "epoch": 1.1870503597122302,
      "grad_norm": 0.09052205189656633,
      "learning_rate": 3.814327974650067e-05,
      "loss": 0.7286513328552247,
      "step": 165
    },
    {
      "epoch": 1.223021582733813,
      "grad_norm": 0.08062290558666846,
      "learning_rate": 3.532868364233416e-05,
      "loss": 0.7593664169311524,
      "step": 170
    },
    {
      "epoch": 1.2589928057553956,
      "grad_norm": 0.09623790985860192,
      "learning_rate": 3.2564100303203035e-05,
      "loss": 0.8009302139282226,
      "step": 175
    },
    {
      "epoch": 1.2949640287769784,
      "grad_norm": 0.13362882285179445,
      "learning_rate": 2.9858953863492334e-05,
      "loss": 0.7465702533721924,
      "step": 180
    },
    {
      "epoch": 1.330935251798561,
      "grad_norm": 0.08708298515845442,
      "learning_rate": 2.722246584429652e-05,
      "loss": 0.7011271476745605,
      "step": 185
    },
    {
      "epoch": 1.3669064748201438,
      "grad_norm": 0.09765847620975966,
      "learning_rate": 2.4663623718355444e-05,
      "loss": 0.6933589935302734,
      "step": 190
    },
    {
      "epoch": 1.4028776978417266,
      "grad_norm": 0.11061497330176863,
      "learning_rate": 2.219115027283339e-05,
      "loss": 0.6514883041381836,
      "step": 195
    },
    {
      "epoch": 1.4388489208633093,
      "grad_norm": 0.13003536918832742,
      "learning_rate": 1.9813473874379395e-05,
      "loss": 0.7087651252746582,
      "step": 200
    },
    {
      "epoch": 1.474820143884892,
      "grad_norm": 0.12215362417494327,
      "learning_rate": 1.7538699737832236e-05,
      "loss": 0.6702914714813233,
      "step": 205
    },
    {
      "epoch": 1.5107913669064748,
      "grad_norm": 0.10495077293191406,
      "learning_rate": 1.5374582296511053e-05,
      "loss": 0.7487486839294434,
      "step": 210
    },
    {
      "epoch": 1.5467625899280577,
      "grad_norm": 0.13424475386206883,
      "learning_rate": 1.332849876827842e-05,
      "loss": 0.7264563560485839,
      "step": 215
    },
    {
      "epoch": 1.5827338129496402,
      "grad_norm": 0.12241730701789537,
      "learning_rate": 1.1407424007485929e-05,
      "loss": 0.6742488861083984,
      "step": 220
    },
    {
      "epoch": 1.6187050359712232,
      "grad_norm": 0.10964031951322462,
      "learning_rate": 9.61790672852868e-06,
      "loss": 0.7405488967895508,
      "step": 225
    },
    {
      "epoch": 1.6546762589928057,
      "grad_norm": 0.11177149802046989,
      "learning_rate": 7.966047182060226e-06,
      "loss": 0.7087203979492187,
      "step": 230
    },
    {
      "epoch": 1.6906474820143886,
      "grad_norm": 0.1218003930872436,
      "learning_rate": 6.4574763599666856e-06,
      "loss": 0.705730390548706,
      "step": 235
    },
    {
      "epoch": 1.7266187050359711,
      "grad_norm": 0.10471844065341074,
      "learning_rate": 5.097336799988067e-06,
      "loss": 0.6330158710479736,
      "step": 240
    },
    {
      "epoch": 1.762589928057554,
      "grad_norm": 0.1036431593783518,
      "learning_rate": 3.890265055421283e-06,
      "loss": 0.6806740760803223,
      "step": 245
    },
    {
      "epoch": 1.7985611510791366,
      "grad_norm": 0.10616735376524208,
      "learning_rate": 2.840375889663871e-06,
      "loss": 0.7142208099365235,
      "step": 250
    },
    {
      "epoch": 1.8345323741007196,
      "grad_norm": 0.11988724859801742,
      "learning_rate": 1.9512482494769613e-06,
      "loss": 0.7671703338623047,
      "step": 255
    },
    {
      "epoch": 1.870503597122302,
      "grad_norm": 0.11871032303539183,
      "learning_rate": 1.2259130647833627e-06,
      "loss": 0.7068417072296143,
      "step": 260
    },
    {
      "epoch": 1.906474820143885,
      "grad_norm": 0.11598204652847133,
      "learning_rate": 6.668429165893997e-07,
      "loss": 0.6564496994018555,
      "step": 265
    },
    {
      "epoch": 1.9424460431654675,
      "grad_norm": 0.11993913393449739,
      "learning_rate": 2.7594360825166644e-07,
      "loss": 0.727387523651123,
      "step": 270
    },
    {
      "epoch": 1.9784172661870505,
      "grad_norm": 0.10081443145587521,
      "learning_rate": 5.454766882097007e-08,
      "loss": 0.7604126453399658,
      "step": 275
    },
    {
      "epoch": 2.0,
      "step": 278,
      "total_flos": 1037690204061696.0,
      "train_loss": 0.7568303492429446,
      "train_runtime": 5056.394,
      "train_samples_per_second": 0.439,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 5,
  "max_steps": 278,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1037690204061696.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}