{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 405,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.062402496099843996,
      "grad_norm": 6.869942132743882,
      "learning_rate": 3.902439024390244e-06,
      "loss": 1.5427,
      "step": 5
    },
    {
      "epoch": 0.12480499219968799,
      "grad_norm": 2.2309980970590986,
      "learning_rate": 8.78048780487805e-06,
      "loss": 1.3696,
      "step": 10
    },
    {
      "epoch": 0.187207488299532,
      "grad_norm": 1.1712750441166022,
      "learning_rate": 1.3658536585365855e-05,
      "loss": 1.2251,
      "step": 15
    },
    {
      "epoch": 0.24960998439937598,
      "grad_norm": 0.7551475721853925,
      "learning_rate": 1.8536585365853663e-05,
      "loss": 1.1254,
      "step": 20
    },
    {
      "epoch": 0.31201248049922,
      "grad_norm": 0.5573252986994611,
      "learning_rate": 2.3414634146341463e-05,
      "loss": 1.0861,
      "step": 25
    },
    {
      "epoch": 0.374414976599064,
      "grad_norm": 0.49960708728057857,
      "learning_rate": 2.829268292682927e-05,
      "loss": 1.0432,
      "step": 30
    },
    {
      "epoch": 0.43681747269890797,
      "grad_norm": 0.39316668250138564,
      "learning_rate": 3.3170731707317074e-05,
      "loss": 1.0154,
      "step": 35
    },
    {
      "epoch": 0.49921996879875197,
      "grad_norm": 0.42122486085711186,
      "learning_rate": 3.804878048780488e-05,
      "loss": 1.0176,
      "step": 40
    },
    {
      "epoch": 0.5616224648985959,
      "grad_norm": 0.3831326031640791,
      "learning_rate": 3.9993296289909065e-05,
      "loss": 1.0053,
      "step": 45
    },
    {
      "epoch": 0.62402496099844,
      "grad_norm": 0.3676595223485485,
      "learning_rate": 3.995234544602496e-05,
      "loss": 0.9786,
      "step": 50
    },
    {
      "epoch": 0.6864274570982839,
      "grad_norm": 0.382981845809094,
      "learning_rate": 3.9874244197864856e-05,
      "loss": 0.9687,
      "step": 55
    },
    {
      "epoch": 0.748829953198128,
      "grad_norm": 0.37479902064460385,
      "learning_rate": 3.9759137966574936e-05,
      "loss": 0.972,
      "step": 60
    },
    {
      "epoch": 0.8112324492979719,
      "grad_norm": 0.3426748881307313,
      "learning_rate": 3.960724107497947e-05,
      "loss": 0.9656,
      "step": 65
    },
    {
      "epoch": 0.8736349453978159,
      "grad_norm": 0.3607591872728085,
      "learning_rate": 3.9418836348521045e-05,
      "loss": 0.9594,
      "step": 70
    },
    {
      "epoch": 0.9360374414976599,
      "grad_norm": 0.3594265854927335,
      "learning_rate": 3.9194274588651754e-05,
      "loss": 0.9615,
      "step": 75
    },
    {
      "epoch": 0.9984399375975039,
      "grad_norm": 0.3720800209880234,
      "learning_rate": 3.8933973919656125e-05,
      "loss": 0.9639,
      "step": 80
    },
    {
      "epoch": 1.0499219968798752,
      "grad_norm": 0.5258116655668951,
      "learning_rate": 3.863841901012174e-05,
      "loss": 0.8615,
      "step": 85
    },
    {
      "epoch": 1.1123244929797191,
      "grad_norm": 0.422076372848612,
      "learning_rate": 3.830816017050733e-05,
      "loss": 0.8412,
      "step": 90
    },
    {
      "epoch": 1.1747269890795633,
      "grad_norm": 0.40949374854248716,
      "learning_rate": 3.7943812328488464e-05,
      "loss": 0.8315,
      "step": 95
    },
    {
      "epoch": 1.2371294851794072,
      "grad_norm": 0.3859478245144761,
      "learning_rate": 3.754605388398884e-05,
      "loss": 0.8236,
      "step": 100
    },
    {
      "epoch": 1.2995319812792512,
      "grad_norm": 0.4199418012141264,
      "learning_rate": 3.711562544602895e-05,
      "loss": 0.819,
      "step": 105
    },
    {
      "epoch": 1.3619344773790951,
      "grad_norm": 0.36315222403141173,
      "learning_rate": 3.6653328453744125e-05,
      "loss": 0.8186,
      "step": 110
    },
    {
      "epoch": 1.424336973478939,
      "grad_norm": 0.34642163847533863,
      "learning_rate": 3.6160023684139535e-05,
      "loss": 0.8224,
      "step": 115
    },
    {
      "epoch": 1.4867394695787832,
      "grad_norm": 0.3832216534097729,
      "learning_rate": 3.56366296493606e-05,
      "loss": 0.8413,
      "step": 120
    },
    {
      "epoch": 1.5491419656786272,
      "grad_norm": 0.3640063532707868,
      "learning_rate": 3.5084120886463144e-05,
      "loss": 0.8306,
      "step": 125
    },
    {
      "epoch": 1.611544461778471,
      "grad_norm": 0.3781925264117484,
      "learning_rate": 3.450352614286753e-05,
      "loss": 0.8199,
      "step": 130
    },
    {
      "epoch": 1.6739469578783153,
      "grad_norm": 0.37501346026864435,
      "learning_rate": 3.389592646087545e-05,
      "loss": 0.818,
      "step": 135
    },
    {
      "epoch": 1.7363494539781592,
      "grad_norm": 0.44359139615127,
      "learning_rate": 3.326245316481591e-05,
      "loss": 0.8215,
      "step": 140
    },
    {
      "epoch": 1.7987519500780031,
      "grad_norm": 0.36830915734892566,
      "learning_rate": 3.260428575456828e-05,
      "loss": 0.8335,
      "step": 145
    },
    {
      "epoch": 1.861154446177847,
      "grad_norm": 0.46153371532253307,
      "learning_rate": 3.192264970938451e-05,
      "loss": 0.8156,
      "step": 150
    },
    {
      "epoch": 1.923556942277691,
      "grad_norm": 0.34743016078129174,
      "learning_rate": 3.121881420609979e-05,
      "loss": 0.8173,
      "step": 155
    },
    {
      "epoch": 1.985959438377535,
      "grad_norm": 0.3759188970823807,
      "learning_rate": 3.049408975598016e-05,
      "loss": 0.8279,
      "step": 160
    },
    {
      "epoch": 2.0374414976599065,
      "grad_norm": 1.0057028929904333,
      "learning_rate": 2.97498257646072e-05,
      "loss": 0.7147,
      "step": 165
    },
    {
      "epoch": 2.0998439937597504,
      "grad_norm": 0.536294518765238,
      "learning_rate": 2.898740801934323e-05,
      "loss": 0.6542,
      "step": 170
    },
    {
      "epoch": 2.1622464898595943,
      "grad_norm": 0.42898484325049463,
      "learning_rate": 2.820825610905514e-05,
      "loss": 0.665,
      "step": 175
    },
    {
      "epoch": 2.2246489859594383,
      "grad_norm": 0.41828314302839964,
      "learning_rate": 2.7413820780901358e-05,
      "loss": 0.658,
      "step": 180
    },
    {
      "epoch": 2.287051482059282,
      "grad_norm": 0.3907402968243733,
      "learning_rate": 2.6605581239103347e-05,
      "loss": 0.6498,
      "step": 185
    },
    {
      "epoch": 2.3494539781591266,
      "grad_norm": 0.3990350855125441,
      "learning_rate": 2.5785042390731358e-05,
      "loss": 0.6594,
      "step": 190
    },
    {
      "epoch": 2.4118564742589705,
      "grad_norm": 0.38037771730038994,
      "learning_rate": 2.4953732043632523e-05,
      "loss": 0.6655,
      "step": 195
    },
    {
      "epoch": 2.4742589703588145,
      "grad_norm": 0.3604432455607804,
      "learning_rate": 2.4113198061718733e-05,
      "loss": 0.6394,
      "step": 200
    },
    {
      "epoch": 2.5366614664586584,
      "grad_norm": 0.3572233192776154,
      "learning_rate": 2.3265005482910992e-05,
      "loss": 0.6544,
      "step": 205
    },
    {
      "epoch": 2.5990639625585024,
      "grad_norm": 0.3507611257883115,
      "learning_rate": 2.2410733605106462e-05,
      "loss": 0.6484,
      "step": 210
    },
    {
      "epoch": 2.6614664586583463,
      "grad_norm": 0.3510892253492551,
      "learning_rate": 2.155197304559413e-05,
      "loss": 0.6627,
      "step": 215
    },
    {
      "epoch": 2.7238689547581902,
      "grad_norm": 0.3735092568001957,
      "learning_rate": 2.0690322779394166e-05,
      "loss": 0.6471,
      "step": 220
    },
    {
      "epoch": 2.786271450858034,
      "grad_norm": 0.37169089248562637,
      "learning_rate": 1.9827387162035624e-05,
      "loss": 0.6588,
      "step": 225
    },
    {
      "epoch": 2.848673946957878,
      "grad_norm": 0.34864036644035284,
      "learning_rate": 1.896477294231581e-05,
      "loss": 0.6592,
      "step": 230
    },
    {
      "epoch": 2.9110764430577225,
      "grad_norm": 0.3557390648460663,
      "learning_rate": 1.8104086270603557e-05,
      "loss": 0.6541,
      "step": 235
    },
    {
      "epoch": 2.9734789391575664,
      "grad_norm": 0.36597594580891846,
      "learning_rate": 1.724692970825664e-05,
      "loss": 0.6581,
      "step": 240
    },
    {
      "epoch": 3.0249609984399375,
      "grad_norm": 0.7341541424865131,
      "learning_rate": 1.6394899243721887e-05,
      "loss": 0.5885,
      "step": 245
    },
    {
      "epoch": 3.0873634945397814,
      "grad_norm": 0.6266853196101121,
      "learning_rate": 1.5549581320873715e-05,
      "loss": 0.5173,
      "step": 250
    },
    {
      "epoch": 3.149765990639626,
      "grad_norm": 0.5783678509051325,
      "learning_rate": 1.4712549885124223e-05,
      "loss": 0.5069,
      "step": 255
    },
    {
      "epoch": 3.2121684867394698,
      "grad_norm": 0.5074575279662837,
      "learning_rate": 1.3885363452804948e-05,
      "loss": 0.5076,
      "step": 260
    },
    {
      "epoch": 3.2745709828393137,
      "grad_norm": 0.42242841517509344,
      "learning_rate": 1.30695622092768e-05,
      "loss": 0.517,
      "step": 265
    },
    {
      "epoch": 3.3369734789391576,
      "grad_norm": 0.5387202571795462,
      "learning_rate": 1.2266665141171625e-05,
      "loss": 0.5082,
      "step": 270
    },
    {
      "epoch": 3.3993759750390016,
      "grad_norm": 0.39380401595933495,
      "learning_rate": 1.1478167208104702e-05,
      "loss": 0.5002,
      "step": 275
    },
    {
      "epoch": 3.4617784711388455,
      "grad_norm": 0.36443335560609924,
      "learning_rate": 1.070553655912463e-05,
      "loss": 0.5127,
      "step": 280
    },
    {
      "epoch": 3.5241809672386895,
      "grad_norm": 0.37026561325454826,
      "learning_rate": 9.950211799083342e-06,
      "loss": 0.5018,
      "step": 285
    },
    {
      "epoch": 3.5865834633385334,
      "grad_norm": 0.3604714850229967,
      "learning_rate": 9.213599310016019e-06,
      "loss": 0.4968,
      "step": 290
    },
    {
      "epoch": 3.6489859594383773,
      "grad_norm": 0.36706513536399266,
      "learning_rate": 8.497070632518611e-06,
      "loss": 0.5096,
      "step": 295
    },
    {
      "epoch": 3.7113884555382217,
      "grad_norm": 0.3701521887361273,
      "learning_rate": 7.801959911998542e-06,
      "loss": 0.5083,
      "step": 300
    },
    {
      "epoch": 3.7737909516380657,
      "grad_norm": 0.36963297359098757,
      "learning_rate": 7.129561414553705e-06,
      "loss": 0.5005,
      "step": 305
    },
    {
      "epoch": 3.8361934477379096,
      "grad_norm": 0.3638193344055006,
      "learning_rate": 6.481127117104913e-06,
      "loss": 0.4924,
      "step": 310
    },
    {
      "epoch": 3.8985959438377535,
      "grad_norm": 0.3548422623821088,
      "learning_rate": 5.857864376269051e-06,
      "loss": 0.5067,
      "step": 315
    },
    {
      "epoch": 3.9609984399375975,
      "grad_norm": 0.3712378619120936,
      "learning_rate": 5.260933680313267e-06,
      "loss": 0.5193,
      "step": 320
    },
    {
      "epoch": 4.0124804992199685,
      "grad_norm": 1.1528495806886747,
      "learning_rate": 4.691446488376012e-06,
      "loss": 0.4716,
      "step": 325
    },
    {
      "epoch": 4.074882995319813,
      "grad_norm": 0.4707064263083223,
      "learning_rate": 4.150463160978196e-06,
      "loss": 0.4173,
      "step": 330
    },
    {
      "epoch": 4.137285491419656,
      "grad_norm": 0.5003057183040235,
      "learning_rate": 3.6389909856777437e-06,
      "loss": 0.4122,
      "step": 335
    },
    {
      "epoch": 4.199687987519501,
      "grad_norm": 0.4271046159597492,
      "learning_rate": 3.157982301543765e-06,
      "loss": 0.4154,
      "step": 340
    },
    {
      "epoch": 4.262090483619345,
      "grad_norm": 0.37817181457135235,
      "learning_rate": 2.708332725942353e-06,
      "loss": 0.4174,
      "step": 345
    },
    {
      "epoch": 4.324492979719189,
      "grad_norm": 0.41532204366967385,
      "learning_rate": 2.2908794869358044e-06,
      "loss": 0.4179,
      "step": 350
    },
    {
      "epoch": 4.386895475819033,
      "grad_norm": 0.4160950477529613,
      "learning_rate": 1.906399864400177e-06,
      "loss": 0.4204,
      "step": 355
    },
    {
      "epoch": 4.4492979719188765,
      "grad_norm": 0.3521722892815219,
      "learning_rate": 1.555609742763795e-06,
      "loss": 0.4018,
      "step": 360
    },
    {
      "epoch": 4.511700468018721,
      "grad_norm": 0.36749840193049166,
      "learning_rate": 1.2391622780613632e-06,
      "loss": 0.4075,
      "step": 365
    },
    {
      "epoch": 4.574102964118564,
      "grad_norm": 0.36972482090697484,
      "learning_rate": 9.576466817857177e-07,
      "loss": 0.4212,
      "step": 370
    },
    {
      "epoch": 4.636505460218409,
      "grad_norm": 0.4770546165307082,
      "learning_rate": 7.115871238014982e-07,
      "loss": 0.4248,
      "step": 375
    },
    {
      "epoch": 4.698907956318253,
      "grad_norm": 0.3660317900330527,
      "learning_rate": 5.014417563635276e-07,
      "loss": 0.41,
      "step": 380
    },
    {
      "epoch": 4.761310452418097,
      "grad_norm": 0.37278911996348923,
      "learning_rate": 3.2760186105712964e-07,
      "loss": 0.4149,
      "step": 385
    },
    {
      "epoch": 4.823712948517941,
      "grad_norm": 0.3450687349519788,
      "learning_rate": 1.903911202487363e-07,
      "loss": 0.4036,
      "step": 390
    },
    {
      "epoch": 4.886115444617785,
      "grad_norm": 0.36850041717911486,
      "learning_rate": 9.006501440333548e-08,
      "loss": 0.4127,
      "step": 395
    },
    {
      "epoch": 4.948517940717629,
      "grad_norm": 0.36455418895325487,
      "learning_rate": 2.681034639087754e-08,
      "loss": 0.4156,
      "step": 400
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.36112407086446535,
      "learning_rate": 7.448936674170349e-10,
      "loss": 0.4218,
      "step": 405
    },
    {
      "epoch": 5.0,
      "step": 405,
      "total_flos": 1011348253179904.0,
      "train_loss": 0.6949614560162579,
      "train_runtime": 41951.5472,
      "train_samples_per_second": 1.222,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 5,
  "max_steps": 405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1011348253179904.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}