{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3480985118788617,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006961970237577234,
      "grad_norm": 74.93397158603199,
      "learning_rate": 6.944444444444445e-07,
      "loss": 2.6763,
      "step": 1
    },
    {
      "epoch": 0.006961970237577234,
      "grad_norm": 42.51151469703164,
      "learning_rate": 6.944444444444445e-06,
      "loss": 2.5014,
      "step": 10
    },
    {
      "epoch": 0.013923940475154469,
      "grad_norm": 3.9060174491324595,
      "learning_rate": 1.388888888888889e-05,
      "loss": 2.1436,
      "step": 20
    },
    {
      "epoch": 0.020885910712731704,
      "grad_norm": 2.4653356578163312,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 2.1299,
      "step": 30
    },
    {
      "epoch": 0.027847880950308938,
      "grad_norm": 1.9758176342444926,
      "learning_rate": 2.777777777777778e-05,
      "loss": 2.0629,
      "step": 40
    },
    {
      "epoch": 0.034809851187886175,
      "grad_norm": 2.24304363639927,
      "learning_rate": 3.472222222222222e-05,
      "loss": 2.0022,
      "step": 50
    },
    {
      "epoch": 0.04177182142546341,
      "grad_norm": 2.137058600643756,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.9324,
      "step": 60
    },
    {
      "epoch": 0.04873379166304064,
      "grad_norm": 1.8905774575553251,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 1.8735,
      "step": 70
    },
    {
      "epoch": 0.055695761900617875,
      "grad_norm": 2.277356627020573,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.8459,
      "step": 80
    },
    {
      "epoch": 0.06265773213819512,
      "grad_norm": 2.1850479551940736,
      "learning_rate": 6.25e-05,
      "loss": 1.8657,
      "step": 90
    },
    {
      "epoch": 0.06961970237577235,
      "grad_norm": 2.2821298235140066,
      "learning_rate": 6.944444444444444e-05,
      "loss": 1.8105,
      "step": 100
    },
    {
      "epoch": 0.07658167261334958,
      "grad_norm": 1.7409612334315907,
      "learning_rate": 7.638888888888889e-05,
      "loss": 1.7874,
      "step": 110
    },
    {
      "epoch": 0.08354364285092682,
      "grad_norm": 1.9712592588798674,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.7892,
      "step": 120
    },
    {
      "epoch": 0.09050561308850405,
      "grad_norm": 2.509099517180512,
      "learning_rate": 9.027777777777779e-05,
      "loss": 1.7808,
      "step": 130
    },
    {
      "epoch": 0.09746758332608128,
      "grad_norm": 2.0842685380596038,
      "learning_rate": 9.722222222222223e-05,
      "loss": 1.803,
      "step": 140
    },
    {
      "epoch": 0.10442955356365852,
      "grad_norm": 1.8429004845744987,
      "learning_rate": 0.00010416666666666667,
      "loss": 1.7588,
      "step": 150
    },
    {
      "epoch": 0.11139152380123575,
      "grad_norm": 2.8327524674330524,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.7772,
      "step": 160
    },
    {
      "epoch": 0.11835349403881298,
      "grad_norm": 2.0729891765954154,
      "learning_rate": 0.00011805555555555556,
      "loss": 1.7641,
      "step": 170
    },
    {
      "epoch": 0.12531546427639023,
      "grad_norm": 7.58810403295457,
      "learning_rate": 0.000125,
      "loss": 1.833,
      "step": 180
    },
    {
      "epoch": 0.13227743451396745,
      "grad_norm": 19.362231963576104,
      "learning_rate": 0.00013194444444444446,
      "loss": 1.7874,
      "step": 190
    },
    {
      "epoch": 0.1392394047515447,
      "grad_norm": 3.96368325072897,
      "learning_rate": 0.0001388888888888889,
      "loss": 1.846,
      "step": 200
    },
    {
      "epoch": 0.14620137498912192,
      "grad_norm": 2.7386120910604945,
      "learning_rate": 0.00014583333333333335,
      "loss": 1.8197,
      "step": 210
    },
    {
      "epoch": 0.15316334522669917,
      "grad_norm": 2.110144128803464,
      "learning_rate": 0.00015277777777777777,
      "loss": 1.7561,
      "step": 220
    },
    {
      "epoch": 0.16012531546427639,
      "grad_norm": 2.5725492351480352,
      "learning_rate": 0.00015972222222222223,
      "loss": 1.7749,
      "step": 230
    },
    {
      "epoch": 0.16708728570185363,
      "grad_norm": 1.121359657360383,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.7614,
      "step": 240
    },
    {
      "epoch": 0.17404925593943085,
      "grad_norm": 2.155597643370339,
      "learning_rate": 0.00017361111111111112,
      "loss": 1.7587,
      "step": 250
    },
    {
      "epoch": 0.1810112261770081,
      "grad_norm": 2.5773482568660393,
      "learning_rate": 0.00018055555555555557,
      "loss": 1.7934,
      "step": 260
    },
    {
      "epoch": 0.18797319641458532,
      "grad_norm": 1.6740595013333657,
      "learning_rate": 0.0001875,
      "loss": 1.7504,
      "step": 270
    },
    {
      "epoch": 0.19493516665216257,
      "grad_norm": 2.2858392200215696,
      "learning_rate": 0.00019444444444444446,
      "loss": 1.7499,
      "step": 280
    },
    {
      "epoch": 0.2018971368897398,
      "grad_norm": 1.7434751943536266,
      "learning_rate": 0.0001999999336897035,
      "loss": 1.7543,
      "step": 290
    },
    {
      "epoch": 0.20885910712731703,
      "grad_norm": 1.3619486244331678,
      "learning_rate": 0.00019999761283856016,
      "loss": 1.7123,
      "step": 300
    },
    {
      "epoch": 0.21582107736489425,
      "grad_norm": 1.6373278228861707,
      "learning_rate": 0.00019999197656053288,
      "loss": 1.7195,
      "step": 310
    },
    {
      "epoch": 0.2227830476024715,
      "grad_norm": 1.281241393641898,
      "learning_rate": 0.00019998302504249278,
      "loss": 1.7336,
      "step": 320
    },
    {
      "epoch": 0.22974501784004872,
      "grad_norm": 1.4989445469875955,
      "learning_rate": 0.000199970758581228,
      "loss": 1.7219,
      "step": 330
    },
    {
      "epoch": 0.23670698807762597,
      "grad_norm": 1.321518251513136,
      "learning_rate": 0.00019995517758343386,
      "loss": 1.7302,
      "step": 340
    },
    {
      "epoch": 0.24366895831520322,
      "grad_norm": 1.2671299687318527,
      "learning_rate": 0.0001999362825656992,
      "loss": 1.7159,
      "step": 350
    },
    {
      "epoch": 0.25063092855278046,
      "grad_norm": 1.0577637068118013,
      "learning_rate": 0.00019991407415448947,
      "loss": 1.7203,
      "step": 360
    },
    {
      "epoch": 0.2575928987903577,
      "grad_norm": 1.134207084144878,
      "learning_rate": 0.00019988855308612595,
      "loss": 1.7114,
      "step": 370
    },
    {
      "epoch": 0.2645548690279349,
      "grad_norm": 1.2266368964891576,
      "learning_rate": 0.00019985972020676116,
      "loss": 1.7238,
      "step": 380
    },
    {
      "epoch": 0.2715168392655121,
      "grad_norm": 1.1990301126734546,
      "learning_rate": 0.00019982757647235094,
      "loss": 1.704,
      "step": 390
    },
    {
      "epoch": 0.2784788095030894,
      "grad_norm": 0.7719332777254844,
      "learning_rate": 0.0001997921229486228,
      "loss": 1.7127,
      "step": 400
    },
    {
      "epoch": 0.2854407797406666,
      "grad_norm": 0.9054141958817113,
      "learning_rate": 0.00019975336081104038,
      "loss": 1.6892,
      "step": 410
    },
    {
      "epoch": 0.29240274997824384,
      "grad_norm": 0.7201089451408423,
      "learning_rate": 0.00019971129134476473,
      "loss": 1.689,
      "step": 420
    },
    {
      "epoch": 0.29936472021582106,
      "grad_norm": 0.6596449276890678,
      "learning_rate": 0.00019966591594461157,
      "loss": 1.7046,
      "step": 430
    },
    {
      "epoch": 0.30632669045339833,
      "grad_norm": 0.9894358407915632,
      "learning_rate": 0.000199617236115005,
      "loss": 1.7063,
      "step": 440
    },
    {
      "epoch": 0.31328866069097555,
      "grad_norm": 0.6354863462129365,
      "learning_rate": 0.00019956525346992768,
      "loss": 1.6896,
      "step": 450
    },
    {
      "epoch": 0.32025063092855277,
      "grad_norm": 1.004907546559211,
      "learning_rate": 0.0001995099697328674,
      "loss": 1.6662,
      "step": 460
    },
    {
      "epoch": 0.32721260116613,
      "grad_norm": 0.5536272096656565,
      "learning_rate": 0.00019945138673675973,
      "loss": 1.7043,
      "step": 470
    },
    {
      "epoch": 0.33417457140370727,
      "grad_norm": 1.0951977004377467,
      "learning_rate": 0.00019938950642392746,
      "loss": 1.6751,
      "step": 480
    },
    {
      "epoch": 0.3411365416412845,
      "grad_norm": 2.3040787232248343,
      "learning_rate": 0.00019932433084601613,
      "loss": 1.7194,
      "step": 490
    },
    {
      "epoch": 0.3480985118788617,
      "grad_norm": 1.484568533076407,
      "learning_rate": 0.00019925586216392596,
      "loss": 1.6743,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 5744,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 418654621532160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}