{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 406,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024630541871921183,
      "grad_norm": 0.28437623381614685,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.9407,
      "step": 1
    },
    {
      "epoch": 0.012315270935960592,
      "grad_norm": 0.3386021554470062,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.9735,
      "step": 5
    },
    {
      "epoch": 0.024630541871921183,
      "grad_norm": 0.15559862554073334,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.9449,
      "step": 10
    },
    {
      "epoch": 0.03694581280788178,
      "grad_norm": 0.09031839668750763,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.9156,
      "step": 15
    },
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 0.07027982175350189,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.9273,
      "step": 20
    },
    {
      "epoch": 0.06157635467980296,
      "grad_norm": 0.07974544167518616,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9143,
      "step": 25
    },
    {
      "epoch": 0.07389162561576355,
      "grad_norm": 0.0783006027340889,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.8985,
      "step": 30
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.06993751972913742,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.903,
      "step": 35
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 0.07667742669582367,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.898,
      "step": 40
    },
    {
      "epoch": 0.11083743842364532,
      "grad_norm": 0.06702238321304321,
      "learning_rate": 0.0001999407400739705,
      "loss": 0.8896,
      "step": 45
    },
    {
      "epoch": 0.12315270935960591,
      "grad_norm": 0.0696224719285965,
      "learning_rate": 0.00019970011699250152,
      "loss": 0.8968,
      "step": 50
    },
    {
      "epoch": 0.1354679802955665,
      "grad_norm": 0.07405594736337662,
      "learning_rate": 0.00019927487224577402,
      "loss": 0.874,
      "step": 55
    },
    {
      "epoch": 0.1477832512315271,
      "grad_norm": 0.07150493562221527,
      "learning_rate": 0.0001986657932891657,
      "loss": 0.8893,
      "step": 60
    },
    {
      "epoch": 0.16009852216748768,
      "grad_norm": 0.07578982412815094,
      "learning_rate": 0.00019787400799669154,
      "loss": 0.8817,
      "step": 65
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.07320016622543335,
      "learning_rate": 0.00019690098257244064,
      "loss": 0.87,
      "step": 70
    },
    {
      "epoch": 0.18472906403940886,
      "grad_norm": 0.08941762149333954,
      "learning_rate": 0.00019574851883550395,
      "loss": 0.8894,
      "step": 75
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.07446017116308212,
      "learning_rate": 0.00019441875088341997,
      "loss": 0.8722,
      "step": 80
    },
    {
      "epoch": 0.20935960591133004,
      "grad_norm": 0.07567897439002991,
      "learning_rate": 0.00019291414114031743,
      "loss": 0.8901,
      "step": 85
    },
    {
      "epoch": 0.22167487684729065,
      "grad_norm": 0.08049421012401581,
      "learning_rate": 0.00019123747579707275,
      "loss": 0.8814,
      "step": 90
    },
    {
      "epoch": 0.23399014778325122,
      "grad_norm": 0.12433026731014252,
      "learning_rate": 0.0001893918596519257,
      "loss": 0.8727,
      "step": 95
    },
    {
      "epoch": 0.24630541871921183,
      "grad_norm": 0.07449541985988617,
      "learning_rate": 0.00018738071036110808,
      "loss": 0.8672,
      "step": 100
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 0.0773991122841835,
      "learning_rate": 0.00018520775211013093,
      "loss": 0.8566,
      "step": 105
    },
    {
      "epoch": 0.270935960591133,
      "grad_norm": 0.07121796160936356,
      "learning_rate": 0.00018287700871745036,
      "loss": 0.8608,
      "step": 110
    },
    {
      "epoch": 0.2832512315270936,
      "grad_norm": 0.07797464728355408,
      "learning_rate": 0.00018039279618328212,
      "loss": 0.8822,
      "step": 115
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 0.0803268775343895,
      "learning_rate": 0.0001777597146973627,
      "loss": 0.8747,
      "step": 120
    },
    {
      "epoch": 0.3078817733990148,
      "grad_norm": 0.07652761787176132,
      "learning_rate": 0.00017498264012045687,
      "loss": 0.8732,
      "step": 125
    },
    {
      "epoch": 0.32019704433497537,
      "grad_norm": 0.07376247644424438,
      "learning_rate": 0.00017206671495538612,
      "loss": 0.8736,
      "step": 130
    },
    {
      "epoch": 0.33251231527093594,
      "grad_norm": 0.07926958799362183,
      "learning_rate": 0.0001690173388242972,
      "loss": 0.8768,
      "step": 135
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.0875566154718399,
      "learning_rate": 0.0001658401584698049,
      "loss": 0.8745,
      "step": 140
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.08201688528060913,
      "learning_rate": 0.00016254105729852464,
      "loss": 0.8651,
      "step": 145
    },
    {
      "epoch": 0.3694581280788177,
      "grad_norm": 0.08041845262050629,
      "learning_rate": 0.00015912614448635782,
      "loss": 0.8682,
      "step": 150
    },
    {
      "epoch": 0.3817733990147783,
      "grad_norm": 0.08443805575370789,
      "learning_rate": 0.00015560174366570446,
      "loss": 0.8536,
      "step": 155
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.07965832948684692,
      "learning_rate": 0.0001519743812155516,
      "loss": 0.8482,
      "step": 160
    },
    {
      "epoch": 0.4064039408866995,
      "grad_norm": 0.08292090147733688,
      "learning_rate": 0.00014825077417612186,
      "loss": 0.8758,
      "step": 165
    },
    {
      "epoch": 0.4187192118226601,
      "grad_norm": 0.08210255950689316,
      "learning_rate": 0.00014443781781046136,
      "loss": 0.8585,
      "step": 170
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.07735207676887512,
      "learning_rate": 0.00014054257283599973,
      "loss": 0.9106,
      "step": 175
    },
    {
      "epoch": 0.4433497536945813,
      "grad_norm": 0.0821058601140976,
      "learning_rate": 0.00013657225234972695,
      "loss": 0.8574,
      "step": 180
    },
    {
      "epoch": 0.45566502463054187,
      "grad_norm": 0.08240474760532379,
      "learning_rate": 0.00013253420847119803,
      "loss": 0.8767,
      "step": 185
    },
    {
      "epoch": 0.46798029556650245,
      "grad_norm": 0.07591621577739716,
      "learning_rate": 0.0001284359187281004,
      "loss": 0.8537,
      "step": 190
    },
    {
      "epoch": 0.4802955665024631,
      "grad_norm": 0.07926048338413239,
      "learning_rate": 0.0001242849722095936,
      "loss": 0.8698,
      "step": 195
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.08197298645973206,
      "learning_rate": 0.00012008905551306356,
      "loss": 0.8533,
      "step": 200
    },
    {
      "epoch": 0.5049261083743842,
      "grad_norm": 0.07661041617393494,
      "learning_rate": 0.00011585593851031347,
      "loss": 0.8642,
      "step": 205
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.0772751197218895,
      "learning_rate": 0.00011159345995955006,
      "loss": 0.8688,
      "step": 210
    },
    {
      "epoch": 0.5295566502463054,
      "grad_norm": 0.08168666064739227,
      "learning_rate": 0.00010730951298980776,
      "loss": 0.8674,
      "step": 215
    },
    {
      "epoch": 0.541871921182266,
      "grad_norm": 0.08107247948646545,
      "learning_rate": 0.00010301203048469083,
      "loss": 0.873,
      "step": 220
    },
    {
      "epoch": 0.5541871921182266,
      "grad_norm": 0.07802799344062805,
      "learning_rate": 9.870897039249911e-05,
      "loss": 0.8521,
      "step": 225
    },
    {
      "epoch": 0.5665024630541872,
      "grad_norm": 0.07647371292114258,
      "learning_rate": 9.440830098993969e-05,
      "loss": 0.8582,
      "step": 230
    },
    {
      "epoch": 0.5788177339901478,
      "grad_norm": 0.08646470308303833,
      "learning_rate": 9.011798612671286e-05,
      "loss": 0.8612,
      "step": 235
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 0.0776691734790802,
      "learning_rate": 8.58459704782957e-05,
      "loss": 0.8586,
      "step": 240
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 0.08570775389671326,
      "learning_rate": 8.160016483423199e-05,
      "loss": 0.8574,
      "step": 245
    },
    {
      "epoch": 0.6157635467980296,
      "grad_norm": 0.08003751933574677,
      "learning_rate": 7.738843144917119e-05,
      "loss": 0.854,
      "step": 250
    },
    {
      "epoch": 0.6280788177339901,
      "grad_norm": 0.08129052817821503,
      "learning_rate": 7.321856948378259e-05,
      "loss": 0.8636,
      "step": 255
    },
    {
      "epoch": 0.6403940886699507,
      "grad_norm": 0.08401297777891159,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.8673,
      "step": 260
    },
    {
      "epoch": 0.6527093596059114,
      "grad_norm": 0.07763602584600449,
      "learning_rate": 6.503525447487715e-05,
      "loss": 0.8757,
      "step": 265
    },
    {
      "epoch": 0.6650246305418719,
      "grad_norm": 0.10503505915403366,
      "learning_rate": 6.103695504692122e-05,
      "loss": 0.8522,
      "step": 270
    },
    {
      "epoch": 0.6773399014778325,
      "grad_norm": 0.08000697195529938,
      "learning_rate": 5.7110806208751655e-05,
      "loss": 0.887,
      "step": 275
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.07380930334329605,
      "learning_rate": 5.326407828419979e-05,
      "loss": 0.854,
      "step": 280
    },
    {
      "epoch": 0.7019704433497537,
      "grad_norm": 0.07724297791719437,
      "learning_rate": 4.9503894527847964e-05,
      "loss": 0.8579,
      "step": 285
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.07541344314813614,
      "learning_rate": 4.583721793440188e-05,
      "loss": 0.8726,
      "step": 290
    },
    {
      "epoch": 0.7266009852216748,
      "grad_norm": 0.07829412072896957,
      "learning_rate": 4.227083834482728e-05,
      "loss": 0.8666,
      "step": 295
    },
    {
      "epoch": 0.7389162561576355,
      "grad_norm": 0.08106305450201035,
      "learning_rate": 3.881135987312757e-05,
      "loss": 0.8425,
      "step": 300
    },
    {
      "epoch": 0.7512315270935961,
      "grad_norm": 0.07838086783885956,
      "learning_rate": 3.546518867704499e-05,
      "loss": 0.8551,
      "step": 305
    },
    {
      "epoch": 0.7635467980295566,
      "grad_norm": 0.08704580366611481,
      "learning_rate": 3.223852109533112e-05,
      "loss": 0.8658,
      "step": 310
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 0.08024916052818298,
      "learning_rate": 2.9137332173554043e-05,
      "loss": 0.8691,
      "step": 315
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 0.07905606925487518,
      "learning_rate": 2.616736459968936e-05,
      "loss": 0.8687,
      "step": 320
    },
    {
      "epoch": 0.8004926108374384,
      "grad_norm": 0.07910972088575363,
      "learning_rate": 2.33341180699841e-05,
      "loss": 0.8592,
      "step": 325
    },
    {
      "epoch": 0.812807881773399,
      "grad_norm": 0.07642722129821777,
      "learning_rate": 2.0642839104785272e-05,
      "loss": 0.8698,
      "step": 330
    },
    {
      "epoch": 0.8251231527093597,
      "grad_norm": 0.08815363049507141,
      "learning_rate": 1.8098511333192024e-05,
      "loss": 0.8557,
      "step": 335
    },
    {
      "epoch": 0.8374384236453202,
      "grad_norm": 0.08000471442937851,
      "learning_rate": 1.570584626452173e-05,
      "loss": 0.8671,
      "step": 340
    },
    {
      "epoch": 0.8497536945812808,
      "grad_norm": 0.07913412153720856,
      "learning_rate": 1.3469274563679402e-05,
      "loss": 0.8588,
      "step": 345
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.08054699003696442,
      "learning_rate": 1.1392937846586215e-05,
      "loss": 0.8543,
      "step": 350
    },
    {
      "epoch": 0.874384236453202,
      "grad_norm": 0.08592665195465088,
      "learning_rate": 9.48068101086026e-06,
      "loss": 0.8595,
      "step": 355
    },
    {
      "epoch": 0.8866995073891626,
      "grad_norm": 0.08113285899162292,
      "learning_rate": 7.736045115951251e-06,
      "loss": 0.8542,
      "step": 360
    },
    {
      "epoch": 0.8990147783251231,
      "grad_norm": 0.08349265158176422,
      "learning_rate": 6.16226082591359e-06,
      "loss": 0.8712,
      "step": 365
    },
    {
      "epoch": 0.9113300492610837,
      "grad_norm": 0.08155006915330887,
      "learning_rate": 4.762242426960262e-06,
      "loss": 0.8498,
      "step": 370
    },
    {
      "epoch": 0.9236453201970444,
      "grad_norm": 0.08772558718919754,
      "learning_rate": 3.5385824308756587e-06,
      "loss": 0.8582,
      "step": 375
    },
    {
      "epoch": 0.9359605911330049,
      "grad_norm": 0.08002293854951859,
      "learning_rate": 2.493546774280531e-06,
      "loss": 0.8623,
      "step": 380
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 0.08070306479930878,
      "learning_rate": 1.6290706226390285e-06,
      "loss": 0.8508,
      "step": 385
    },
    {
      "epoch": 0.9605911330049262,
      "grad_norm": 0.07980693131685257,
      "learning_rate": 9.46754786777726e-07,
      "loss": 0.8451,
      "step": 390
    },
    {
      "epoch": 0.9729064039408867,
      "grad_norm": 0.09085196256637573,
      "learning_rate": 4.4786275855247527e-07,
      "loss": 0.8605,
      "step": 395
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.08073560893535614,
      "learning_rate": 1.333183711524133e-07,
      "loss": 0.86,
      "step": 400
    },
    {
      "epoch": 0.9975369458128078,
      "grad_norm": 0.08186531066894531,
      "learning_rate": 3.7040883734462683e-09,
      "loss": 0.8533,
      "step": 405
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 19680.5251,
      "eval_samples_per_second": 1.174,
      "eval_steps_per_second": 0.294,
      "step": 406
    },
    {
      "epoch": 1.0,
      "step": 406,
      "total_flos": 1.566096083950502e+18,
      "train_loss": 0.8717349902749649,
      "train_runtime": 143000.567,
      "train_samples_per_second": 0.727,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 5,
  "max_steps": 406,
  "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": 1.566096083950502e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}