{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1284,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.25848760281456373,
      "learning_rate": 9.743589743589744e-05,
      "loss": 1.0955,
      "step": 20
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.12152540967981099,
      "learning_rate": 0.0002,
      "loss": 0.8826,
      "step": 40
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.08766356744406019,
      "learning_rate": 0.00019987267934654538,
      "loss": 0.7805,
      "step": 60
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.07045964353767724,
      "learning_rate": 0.00019949104159715743,
      "loss": 0.7223,
      "step": 80
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.09463916110765375,
      "learning_rate": 0.00019885605855918885,
      "loss": 0.6933,
      "step": 100
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.09122862084573752,
      "learning_rate": 0.0001979693471617462,
      "loss": 0.6758,
      "step": 120
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.10577377685042465,
      "learning_rate": 0.00019683316533832042,
      "loss": 0.6605,
      "step": 140
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.11067163440878329,
      "learning_rate": 0.0001954504062771555,
      "loss": 0.6538,
      "step": 160
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.1121421761603273,
      "learning_rate": 0.00019382459105399632,
      "loss": 0.6534,
      "step": 180
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.10812490276750944,
      "learning_rate": 0.00019195985966597494,
      "loss": 0.6428,
      "step": 200
    },
    {
      "epoch": 1.02803738317757,
      "grad_norm": 0.11935465896028669,
      "learning_rate": 0.00018986096048946824,
      "loss": 0.6327,
      "step": 220
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 0.11781728745931254,
      "learning_rate": 0.0001875332381887699,
      "loss": 0.6322,
      "step": 240
    },
    {
      "epoch": 1.2149532710280373,
      "grad_norm": 0.1316640938577259,
      "learning_rate": 0.00018498262010636774,
      "loss": 0.6235,
      "step": 260
    },
    {
      "epoch": 1.308411214953271,
      "grad_norm": 0.13767423202221835,
      "learning_rate": 0.00018221560116948103,
      "loss": 0.6176,
      "step": 280
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 0.1255781456618538,
      "learning_rate": 0.00017923922735129302,
      "loss": 0.6194,
      "step": 300
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 0.12566754750336923,
      "learning_rate": 0.00017606107772899287,
      "loss": 0.6169,
      "step": 320
    },
    {
      "epoch": 1.588785046728972,
      "grad_norm": 0.1224054760200796,
      "learning_rate": 0.00017268924518431438,
      "loss": 0.6126,
      "step": 340
    },
    {
      "epoch": 1.6822429906542056,
      "grad_norm": 0.12754703201153322,
      "learning_rate": 0.00016913231579571608,
      "loss": 0.6127,
      "step": 360
    },
    {
      "epoch": 1.7757009345794392,
      "grad_norm": 0.13837660664241036,
      "learning_rate": 0.00016539934697467894,
      "loss": 0.6097,
      "step": 380
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 0.11566328949125707,
      "learning_rate": 0.00016149984440179537,
      "loss": 0.6039,
      "step": 400
    },
    {
      "epoch": 1.9626168224299065,
      "grad_norm": 0.13012304346488843,
      "learning_rate": 0.00015744373782137992,
      "loss": 0.6028,
      "step": 420
    },
    {
      "epoch": 2.05607476635514,
      "grad_norm": 0.13699329797526194,
      "learning_rate": 0.00015324135575623857,
      "loss": 0.5963,
      "step": 440
    },
    {
      "epoch": 2.149532710280374,
      "grad_norm": 0.12056530916496998,
      "learning_rate": 0.00014890339920698334,
      "loss": 0.5891,
      "step": 460
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 0.12376168201657378,
      "learning_rate": 0.0001444409144028644,
      "loss": 0.5913,
      "step": 480
    },
    {
      "epoch": 2.336448598130841,
      "grad_norm": 0.1285403052607913,
      "learning_rate": 0.0001398652646735076,
      "loss": 0.5893,
      "step": 500
    },
    {
      "epoch": 2.4299065420560746,
      "grad_norm": 0.12392132477639638,
      "learning_rate": 0.0001351881015131833,
      "loss": 0.5883,
      "step": 520
    },
    {
      "epoch": 2.5233644859813085,
      "grad_norm": 0.1338793765627719,
      "learning_rate": 0.00013042133491128935,
      "loss": 0.5859,
      "step": 540
    },
    {
      "epoch": 2.616822429906542,
      "grad_norm": 0.12415978424557397,
      "learning_rate": 0.00012557710302459803,
      "loss": 0.5856,
      "step": 560
    },
    {
      "epoch": 2.710280373831776,
      "grad_norm": 0.1313564813990853,
      "learning_rate": 0.00012066774126849529,
      "loss": 0.5893,
      "step": 580
    },
    {
      "epoch": 2.803738317757009,
      "grad_norm": 0.11960890307280825,
      "learning_rate": 0.00011570575090591791,
      "loss": 0.5849,
      "step": 600
    },
    {
      "epoch": 2.897196261682243,
      "grad_norm": 0.11986525148452289,
      "learning_rate": 0.00011070376721397373,
      "loss": 0.5861,
      "step": 620
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 0.12094208349063497,
      "learning_rate": 0.00010567452730930743,
      "loss": 0.5843,
      "step": 640
    },
    {
      "epoch": 3.0841121495327104,
      "grad_norm": 0.12592138466913735,
      "learning_rate": 0.00010063083771413975,
      "loss": 0.5776,
      "step": 660
    },
    {
      "epoch": 3.177570093457944,
      "grad_norm": 0.13879295451237433,
      "learning_rate": 9.55855417455723e-05,
      "loss": 0.5735,
      "step": 680
    },
    {
      "epoch": 3.2710280373831777,
      "grad_norm": 0.132827192019763,
      "learning_rate": 9.055148681119688e-05,
      "loss": 0.5762,
      "step": 700
    },
    {
      "epoch": 3.364485981308411,
      "grad_norm": 0.135202644806124,
      "learning_rate": 8.554149169428894e-05,
      "loss": 0.5738,
      "step": 720
    },
    {
      "epoch": 3.457943925233645,
      "grad_norm": 0.12535841207061021,
      "learning_rate": 8.056831391189023e-05,
      "loss": 0.5703,
      "step": 740
    },
    {
      "epoch": 3.5514018691588785,
      "grad_norm": 0.13117365043331122,
      "learning_rate": 7.564461722890081e-05,
      "loss": 0.5707,
      "step": 760
    },
    {
      "epoch": 3.6448598130841123,
      "grad_norm": 0.12563061031824993,
      "learning_rate": 7.078293941090249e-05,
      "loss": 0.5687,
      "step": 780
    },
    {
      "epoch": 3.7383177570093458,
      "grad_norm": 0.13424430991092495,
      "learning_rate": 6.599566029782863e-05,
      "loss": 0.5717,
      "step": 800
    },
    {
      "epoch": 3.831775700934579,
      "grad_norm": 0.12859665304631457,
      "learning_rate": 6.129497027977829e-05,
      "loss": 0.5694,
      "step": 820
    },
    {
      "epoch": 3.925233644859813,
      "grad_norm": 0.12403658321797129,
      "learning_rate": 5.669283925524715e-05,
      "loss": 0.5696,
      "step": 840
    },
    {
      "epoch": 4.018691588785047,
      "grad_norm": 0.1241236470560002,
      "learning_rate": 5.2200986150821696e-05,
      "loss": 0.5678,
      "step": 860
    },
    {
      "epoch": 4.11214953271028,
      "grad_norm": 0.13373450432597092,
      "learning_rate": 4.783084907995156e-05,
      "loss": 0.559,
      "step": 880
    },
    {
      "epoch": 4.205607476635514,
      "grad_norm": 0.12955521613965384,
      "learning_rate": 4.359355621678764e-05,
      "loss": 0.5626,
      "step": 900
    },
    {
      "epoch": 4.299065420560748,
      "grad_norm": 0.1201829111448084,
      "learning_rate": 3.9499897459254375e-05,
      "loss": 0.5655,
      "step": 920
    },
    {
      "epoch": 4.392523364485982,
      "grad_norm": 0.1293018490823381,
      "learning_rate": 3.5560296953512295e-05,
      "loss": 0.5638,
      "step": 940
    },
    {
      "epoch": 4.485981308411215,
      "grad_norm": 0.11920916186970969,
      "learning_rate": 3.178478654977624e-05,
      "loss": 0.5608,
      "step": 960
    },
    {
      "epoch": 4.579439252336448,
      "grad_norm": 0.11405851380231317,
      "learning_rate": 2.818298025708075e-05,
      "loss": 0.562,
      "step": 980
    },
    {
      "epoch": 4.672897196261682,
      "grad_norm": 0.12170514209424545,
      "learning_rate": 2.4764049762041874e-05,
      "loss": 0.5686,
      "step": 1000
    },
    {
      "epoch": 4.766355140186916,
      "grad_norm": 0.14556896397750538,
      "learning_rate": 2.1536701073954558e-05,
      "loss": 0.5635,
      "step": 1020
    },
    {
      "epoch": 4.859813084112149,
      "grad_norm": 0.12172194075595427,
      "learning_rate": 1.8509152355696623e-05,
      "loss": 0.559,
      "step": 1040
    },
    {
      "epoch": 4.953271028037383,
      "grad_norm": 0.1318350224140456,
      "learning_rate": 1.5689112996891576e-05,
      "loss": 0.5616,
      "step": 1060
    },
    {
      "epoch": 5.046728971962617,
      "grad_norm": 0.12691480311352626,
      "learning_rate": 1.3083763982618025e-05,
      "loss": 0.56,
      "step": 1080
    },
    {
      "epoch": 5.140186915887851,
      "grad_norm": 0.11296084200322255,
      "learning_rate": 1.0699739607655435e-05,
      "loss": 0.5558,
      "step": 1100
    },
    {
      "epoch": 5.233644859813084,
      "grad_norm": 0.1309044210983197,
      "learning_rate": 8.543110582829272e-06,
      "loss": 0.5588,
      "step": 1120
    },
    {
      "epoch": 5.327102803738318,
      "grad_norm": 0.13260357681059787,
      "learning_rate": 6.61936857647355e-06,
      "loss": 0.5605,
      "step": 1140
    },
    {
      "epoch": 5.420560747663552,
      "grad_norm": 0.12322372236537348,
      "learning_rate": 4.933412230374812e-06,
      "loss": 0.5554,
      "step": 1160
    },
    {
      "epoch": 5.5140186915887845,
      "grad_norm": 0.11617175237743727,
      "learning_rate": 3.4895346858066724e-06,
      "loss": 0.5605,
      "step": 1180
    },
    {
      "epoch": 5.607476635514018,
      "grad_norm": 0.12278895489019458,
      "learning_rate": 2.291412651418778e-06,
      "loss": 0.5642,
      "step": 1200
    },
    {
      "epoch": 5.700934579439252,
      "grad_norm": 0.12252134829919185,
      "learning_rate": 1.3420970408178913e-06,
      "loss": 0.5619,
      "step": 1220
    },
    {
      "epoch": 5.794392523364486,
      "grad_norm": 0.21509033654221743,
      "learning_rate": 6.440052036815081e-07,
      "loss": 0.5539,
      "step": 1240
    },
    {
      "epoch": 5.88785046728972,
      "grad_norm": 0.12357352260583994,
      "learning_rate": 1.989147701871641e-07,
      "loss": 0.5559,
      "step": 1260
    },
    {
      "epoch": 5.981308411214953,
      "grad_norm": 0.12149087465170151,
      "learning_rate": 7.959124431622389e-09,
      "loss": 0.5592,
      "step": 1280
    },
    {
      "epoch": 6.0,
      "step": 1284,
      "total_flos": 8949072262070272.0,
      "train_loss": 0.6056221575009118,
      "train_runtime": 16251.3363,
      "train_samples_per_second": 5.056,
      "train_steps_per_second": 0.079
    }
  ],
  "logging_steps": 20,
  "max_steps": 1284,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8949072262070272.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}