{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 326,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030745580322828592,
      "grad_norm": 6.350613102744608,
      "learning_rate": 1.0204081632653061e-07,
      "loss": 6.5284,
      "step": 5
    },
    {
      "epoch": 0.061491160645657184,
      "grad_norm": 5.249984394687515,
      "learning_rate": 2.0408163265306121e-07,
      "loss": 6.4945,
      "step": 10
    },
    {
      "epoch": 0.09223674096848578,
      "grad_norm": 5.352306724137368,
      "learning_rate": 3.0612244897959183e-07,
      "loss": 6.6828,
      "step": 15
    },
    {
      "epoch": 0.12298232129131437,
      "grad_norm": 5.486794769339902,
      "learning_rate": 4.0816326530612243e-07,
      "loss": 6.467,
      "step": 20
    },
    {
      "epoch": 0.15372790161414296,
      "grad_norm": 4.077117426584361,
      "learning_rate": 5.10204081632653e-07,
      "loss": 6.1826,
      "step": 25
    },
    {
      "epoch": 0.18447348193697155,
      "grad_norm": 3.119167144675083,
      "learning_rate": 6.122448979591837e-07,
      "loss": 5.949,
      "step": 30
    },
    {
      "epoch": 0.21521906225980014,
      "grad_norm": 2.6950432819564356,
      "learning_rate": 7.142857142857143e-07,
      "loss": 5.4738,
      "step": 35
    },
    {
      "epoch": 0.24596464258262873,
      "grad_norm": 1.5382799926978608,
      "learning_rate": 8.163265306122449e-07,
      "loss": 5.2285,
      "step": 40
    },
    {
      "epoch": 0.2767102229054573,
      "grad_norm": 1.2825119089431523,
      "learning_rate": 9.183673469387755e-07,
      "loss": 5.0174,
      "step": 45
    },
    {
      "epoch": 0.3074558032282859,
      "grad_norm": 1.14912166210836,
      "learning_rate": 9.99987079628245e-07,
      "loss": 4.7716,
      "step": 50
    },
    {
      "epoch": 0.3382013835511145,
      "grad_norm": 1.285686948508955,
      "learning_rate": 9.995349367260807e-07,
      "loss": 4.5585,
      "step": 55
    },
    {
      "epoch": 0.3689469638739431,
      "grad_norm": 1.054957564577766,
      "learning_rate": 9.984374428250894e-07,
      "loss": 4.3855,
      "step": 60
    },
    {
      "epoch": 0.3996925441967717,
      "grad_norm": 0.9925990274913604,
      "learning_rate": 9.966960157816278e-07,
      "loss": 4.1541,
      "step": 65
    },
    {
      "epoch": 0.4304381245196003,
      "grad_norm": 0.8744404881743455,
      "learning_rate": 9.943129053516174e-07,
      "loss": 4.1257,
      "step": 70
    },
    {
      "epoch": 0.4611837048424289,
      "grad_norm": 0.7463667798296578,
      "learning_rate": 9.91291190284077e-07,
      "loss": 3.8852,
      "step": 75
    },
    {
      "epoch": 0.49192928516525747,
      "grad_norm": 0.7902691532243193,
      "learning_rate": 9.876347743436758e-07,
      "loss": 3.8846,
      "step": 80
    },
    {
      "epoch": 0.5226748654880861,
      "grad_norm": 0.926879835692504,
      "learning_rate": 9.833483812674452e-07,
      "loss": 3.9166,
      "step": 85
    },
    {
      "epoch": 0.5534204458109147,
      "grad_norm": 0.803407155130827,
      "learning_rate": 9.784375486621668e-07,
      "loss": 3.7194,
      "step": 90
    },
    {
      "epoch": 0.5841660261337432,
      "grad_norm": 0.8117888501469026,
      "learning_rate": 9.729086208503173e-07,
      "loss": 3.7475,
      "step": 95
    },
    {
      "epoch": 0.6149116064565718,
      "grad_norm": 0.7821755674358282,
      "learning_rate": 9.66768740673815e-07,
      "loss": 3.6407,
      "step": 100
    },
    {
      "epoch": 0.6149116064565718,
      "eval_loss": NaN,
      "eval_runtime": 349.4965,
      "eval_samples_per_second": 15.285,
      "eval_steps_per_second": 0.956,
      "step": 100
    },
    {
      "epoch": 0.6456571867794004,
      "grad_norm": 0.6822137175921249,
      "learning_rate": 9.600258402661569e-07,
      "loss": 3.6531,
      "step": 105
    },
    {
      "epoch": 0.676402767102229,
      "grad_norm": 0.7500359822402426,
      "learning_rate": 9.526886308048668e-07,
      "loss": 3.6282,
      "step": 110
    },
    {
      "epoch": 0.7071483474250576,
      "grad_norm": 0.8622924385168957,
      "learning_rate": 9.447665912574929e-07,
      "loss": 3.5622,
      "step": 115
    },
    {
      "epoch": 0.7378939277478862,
      "grad_norm": 0.7766220833707687,
      "learning_rate": 9.362699561356956e-07,
      "loss": 3.4787,
      "step": 120
    },
    {
      "epoch": 0.7686395080707148,
      "grad_norm": 0.7590912417940764,
      "learning_rate": 9.272097022732443e-07,
      "loss": 3.4078,
      "step": 125
    },
    {
      "epoch": 0.7993850883935434,
      "grad_norm": 0.822433668441714,
      "learning_rate": 9.175975346450062e-07,
      "loss": 3.3673,
      "step": 130
    },
    {
      "epoch": 0.830130668716372,
      "grad_norm": 0.7129904612641743,
      "learning_rate": 9.074458712452475e-07,
      "loss": 3.4122,
      "step": 135
    },
    {
      "epoch": 0.8608762490392006,
      "grad_norm": 0.8733565752917316,
      "learning_rate": 8.967678270447798e-07,
      "loss": 3.3817,
      "step": 140
    },
    {
      "epoch": 0.8916218293620292,
      "grad_norm": 0.7851319189409072,
      "learning_rate": 8.855771970476833e-07,
      "loss": 3.2653,
      "step": 145
    },
    {
      "epoch": 0.9223674096848578,
      "grad_norm": 0.8962287259777225,
      "learning_rate": 8.738884384694905e-07,
      "loss": 3.3029,
      "step": 150
    },
    {
      "epoch": 0.9531129900076863,
      "grad_norm": 0.9466863901587774,
      "learning_rate": 8.617166520598562e-07,
      "loss": 3.2964,
      "step": 155
    },
    {
      "epoch": 0.9838585703305149,
      "grad_norm": 0.8018084383307482,
      "learning_rate": 8.490775625938451e-07,
      "loss": 3.2516,
      "step": 160
    },
    {
      "epoch": 1.0122982321291314,
      "grad_norm": 0.7973445057492382,
      "learning_rate": 8.359874985570377e-07,
      "loss": 3.0663,
      "step": 165
    },
    {
      "epoch": 1.04304381245196,
      "grad_norm": 0.901771344389446,
      "learning_rate": 8.224633710506997e-07,
      "loss": 3.2066,
      "step": 170
    },
    {
      "epoch": 1.0737893927747886,
      "grad_norm": 0.7790569731296355,
      "learning_rate": 8.085226519442697e-07,
      "loss": 3.1987,
      "step": 175
    },
    {
      "epoch": 1.1045349730976173,
      "grad_norm": 0.8027091819730047,
      "learning_rate": 7.941833513033872e-07,
      "loss": 3.1081,
      "step": 180
    },
    {
      "epoch": 1.1352805534204458,
      "grad_norm": 0.836190595252302,
      "learning_rate": 7.794639941226237e-07,
      "loss": 3.2306,
      "step": 185
    },
    {
      "epoch": 1.1660261337432745,
      "grad_norm": 0.8184681552542381,
      "learning_rate": 7.643835963929746e-07,
      "loss": 3.071,
      "step": 190
    },
    {
      "epoch": 1.196771714066103,
      "grad_norm": 0.7396008036718764,
      "learning_rate": 7.489616405350318e-07,
      "loss": 3.1746,
      "step": 195
    },
    {
      "epoch": 1.2275172943889316,
      "grad_norm": 0.8695385291013205,
      "learning_rate": 7.332180502295728e-07,
      "loss": 3.1306,
      "step": 200
    },
    {
      "epoch": 1.2275172943889316,
      "eval_loss": NaN,
      "eval_runtime": 344.6921,
      "eval_samples_per_second": 15.498,
      "eval_steps_per_second": 0.969,
      "step": 200
    },
    {
      "epoch": 1.2582628747117601,
      "grad_norm": 0.9685883470665286,
      "learning_rate": 7.171731646780867e-07,
      "loss": 3.0465,
      "step": 205
    },
    {
      "epoch": 1.2890084550345888,
      "grad_norm": 0.9706097655856817,
      "learning_rate": 7.008477123264847e-07,
      "loss": 2.9686,
      "step": 210
    },
    {
      "epoch": 1.3197540353574173,
      "grad_norm": 0.8219747020280328,
      "learning_rate": 6.84262784085946e-07,
      "loss": 3.0241,
      "step": 215
    },
    {
      "epoch": 1.350499615680246,
      "grad_norm": 0.960997631829513,
      "learning_rate": 6.67439806085493e-07,
      "loss": 3.0101,
      "step": 220
    },
    {
      "epoch": 1.3812451960030745,
      "grad_norm": 0.9241788986351824,
      "learning_rate": 6.504005119914975e-07,
      "loss": 2.9648,
      "step": 225
    },
    {
      "epoch": 1.4119907763259032,
      "grad_norm": 0.8461980858410534,
      "learning_rate": 6.33166914929878e-07,
      "loss": 3.0516,
      "step": 230
    },
    {
      "epoch": 1.4427363566487317,
      "grad_norm": 0.788283378335606,
      "learning_rate": 6.157612790472625e-07,
      "loss": 3.0047,
      "step": 235
    },
    {
      "epoch": 1.4734819369715604,
      "grad_norm": 0.7867127269455163,
      "learning_rate": 5.982060907478567e-07,
      "loss": 2.9992,
      "step": 240
    },
    {
      "epoch": 1.5042275172943889,
      "grad_norm": 0.9174037687493481,
      "learning_rate": 5.805240296431765e-07,
      "loss": 2.9248,
      "step": 245
    },
    {
      "epoch": 1.5349730976172176,
      "grad_norm": 1.0136136957988287,
      "learning_rate": 5.627379392521757e-07,
      "loss": 3.1472,
      "step": 250
    },
    {
      "epoch": 1.5657186779400463,
      "grad_norm": 0.7666439492867059,
      "learning_rate": 5.448707974896213e-07,
      "loss": 2.8998,
      "step": 255
    },
    {
      "epoch": 1.5964642582628747,
      "grad_norm": 0.866265723726005,
      "learning_rate": 5.269456869808408e-07,
      "loss": 3.0281,
      "step": 260
    },
    {
      "epoch": 1.6272098385857032,
      "grad_norm": 0.9455130272746435,
      "learning_rate": 5.08985765241196e-07,
      "loss": 3.0122,
      "step": 265
    },
    {
      "epoch": 1.657955418908532,
      "grad_norm": 0.8976450298583974,
      "learning_rate": 4.910142347588041e-07,
      "loss": 2.9808,
      "step": 270
    },
    {
      "epoch": 1.6887009992313606,
      "grad_norm": 0.7984117514993636,
      "learning_rate": 4.7305431301915935e-07,
      "loss": 2.9423,
      "step": 275
    },
    {
      "epoch": 1.7194465795541891,
      "grad_norm": 0.9717048570700036,
      "learning_rate": 4.5512920251037885e-07,
      "loss": 2.9908,
      "step": 280
    },
    {
      "epoch": 1.7501921598770176,
      "grad_norm": 0.9953832113865739,
      "learning_rate": 4.372620607478241e-07,
      "loss": 2.9601,
      "step": 285
    },
    {
      "epoch": 1.7809377401998463,
      "grad_norm": 0.8785516378851284,
      "learning_rate": 4.1947597035682347e-07,
      "loss": 2.9295,
      "step": 290
    },
    {
      "epoch": 1.811683320522675,
      "grad_norm": 1.0560496189183655,
      "learning_rate": 4.0179390925214333e-07,
      "loss": 2.9191,
      "step": 295
    },
    {
      "epoch": 1.8424289008455035,
      "grad_norm": 0.9516031356529069,
      "learning_rate": 3.8423872095273733e-07,
      "loss": 2.9151,
      "step": 300
    },
    {
      "epoch": 1.8424289008455035,
      "eval_loss": NaN,
      "eval_runtime": 344.0766,
      "eval_samples_per_second": 15.526,
      "eval_steps_per_second": 0.971,
      "step": 300
    },
    {
      "epoch": 1.873174481168332,
      "grad_norm": 0.909396889323808,
      "learning_rate": 3.668330850701219e-07,
      "loss": 2.9435,
      "step": 305
    },
    {
      "epoch": 1.9039200614911607,
      "grad_norm": 0.9293115834232327,
      "learning_rate": 3.4959948800850247e-07,
      "loss": 2.9465,
      "step": 310
    },
    {
      "epoch": 1.9346656418139894,
      "grad_norm": 1.067559496517317,
      "learning_rate": 3.325601939145069e-07,
      "loss": 2.9686,
      "step": 315
    },
    {
      "epoch": 1.9654112221368178,
      "grad_norm": 1.1704277043479576,
      "learning_rate": 3.15737215914054e-07,
      "loss": 3.022,
      "step": 320
    },
    {
      "epoch": 1.9961568024596463,
      "grad_norm": 0.9427205447892176,
      "learning_rate": 2.9915228767351535e-07,
      "loss": 2.9455,
      "step": 325
    }
  ],
  "logging_steps": 5,
  "max_steps": 486,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 102476595888128.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}