{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07437363454655324,
  "eval_steps": 100,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018593408636638311,
      "grad_norm": 0.5517500638961792,
      "learning_rate": 5e-06,
      "loss": 0.849,
      "mean_token_accuracy": 0.7567294089429264,
      "step": 5
    },
    {
      "epoch": 0.0037186817273276622,
      "grad_norm": 0.5036010146141052,
      "learning_rate": 1e-05,
      "loss": 0.8417,
      "mean_token_accuracy": 0.7602161832405375,
      "step": 10
    },
    {
      "epoch": 0.005578022590991494,
      "grad_norm": 0.3149392902851105,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7461,
      "mean_token_accuracy": 0.7812357557611331,
      "step": 15
    },
    {
      "epoch": 0.0074373634546553245,
      "grad_norm": 0.3778176009654999,
      "learning_rate": 2e-05,
      "loss": 0.7233,
      "mean_token_accuracy": 0.7826617092119108,
      "step": 20
    },
    {
      "epoch": 0.009296704318319155,
      "grad_norm": 0.2921108603477478,
      "learning_rate": 1.9961946980917457e-05,
      "loss": 0.745,
      "mean_token_accuracy": 0.7759210851951164,
      "step": 25
    },
    {
      "epoch": 0.011156045181982988,
      "grad_norm": 0.3256559371948242,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.7145,
      "mean_token_accuracy": 0.7840695255723248,
      "step": 30
    },
    {
      "epoch": 0.013015386045646818,
      "grad_norm": 0.2694910168647766,
      "learning_rate": 1.9659258262890683e-05,
      "loss": 0.7124,
      "mean_token_accuracy": 0.784175317004461,
      "step": 35
    },
    {
      "epoch": 0.014874726909310649,
      "grad_norm": 0.2669820487499237,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.7094,
      "mean_token_accuracy": 0.7820243731166748,
      "step": 40
    },
    {
      "epoch": 0.01673406777297448,
      "grad_norm": 0.26924929022789,
      "learning_rate": 1.9063077870366504e-05,
      "loss": 0.7151,
      "mean_token_accuracy": 0.7791444741833659,
      "step": 45
    },
    {
      "epoch": 0.01859340863663831,
      "grad_norm": 0.26232558488845825,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.7383,
      "mean_token_accuracy": 0.777497076097214,
      "step": 50
    },
    {
      "epoch": 0.020452749500302143,
      "grad_norm": 0.23832707107067108,
      "learning_rate": 1.819152044288992e-05,
      "loss": 0.7205,
      "mean_token_accuracy": 0.7795166406125732,
      "step": 55
    },
    {
      "epoch": 0.022312090363965975,
      "grad_norm": 0.30983492732048035,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.7106,
      "mean_token_accuracy": 0.7813780332583716,
      "step": 60
    },
    {
      "epoch": 0.024171431227629804,
      "grad_norm": 0.27913030982017517,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.7204,
      "mean_token_accuracy": 0.7806608674214954,
      "step": 65
    },
    {
      "epoch": 0.026030772091293636,
      "grad_norm": 0.2503748834133148,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 0.6764,
      "mean_token_accuracy": 0.7921326068873837,
      "step": 70
    },
    {
      "epoch": 0.02789011295495747,
      "grad_norm": 0.32490983605384827,
      "learning_rate": 1.573576436351046e-05,
      "loss": 0.7179,
      "mean_token_accuracy": 0.7781825838933683,
      "step": 75
    },
    {
      "epoch": 0.029749453818621298,
      "grad_norm": 0.2666051983833313,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.6915,
      "mean_token_accuracy": 0.7871176789479889,
      "step": 80
    },
    {
      "epoch": 0.03160879468228513,
      "grad_norm": 0.276684433221817,
      "learning_rate": 1.4226182617406996e-05,
      "loss": 0.6877,
      "mean_token_accuracy": 0.7900803501022032,
      "step": 85
    },
    {
      "epoch": 0.03346813554594896,
      "grad_norm": 0.286432147026062,
      "learning_rate": 1.342020143325669e-05,
      "loss": 0.7208,
      "mean_token_accuracy": 0.7803869265741546,
      "step": 90
    },
    {
      "epoch": 0.03532747640961279,
      "grad_norm": 0.21728664636611938,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 0.657,
      "mean_token_accuracy": 0.7990809317528936,
      "step": 95
    },
    {
      "epoch": 0.03718681727327662,
      "grad_norm": 0.23999415338039398,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.6769,
      "mean_token_accuracy": 0.7904624964468849,
      "step": 100
    },
    {
      "epoch": 0.03718681727327662,
      "eval_loss": 0.7101884484291077,
      "eval_mean_token_accuracy": 0.7805987882478478,
      "eval_runtime": 36.4141,
      "eval_samples_per_second": 7.003,
      "eval_steps_per_second": 3.515,
      "step": 100
    },
    {
      "epoch": 0.039046158136940456,
      "grad_norm": 0.2708650827407837,
      "learning_rate": 1.0871557427476585e-05,
      "loss": 0.6898,
      "mean_token_accuracy": 0.7857329375276986,
      "step": 105
    },
    {
      "epoch": 0.040905499000604285,
      "grad_norm": 0.2756446301937103,
      "learning_rate": 1e-05,
      "loss": 0.6699,
      "mean_token_accuracy": 0.7941881122764894,
      "step": 110
    },
    {
      "epoch": 0.042764839864268114,
      "grad_norm": 0.2609730660915375,
      "learning_rate": 9.128442572523418e-06,
      "loss": 0.6701,
      "mean_token_accuracy": 0.7917057155226149,
      "step": 115
    },
    {
      "epoch": 0.04462418072793195,
      "grad_norm": 0.24993322789669037,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.6932,
      "mean_token_accuracy": 0.785013354890821,
      "step": 120
    },
    {
      "epoch": 0.04648352159159578,
      "grad_norm": 0.26059097051620483,
      "learning_rate": 7.411809548974792e-06,
      "loss": 0.7185,
      "mean_token_accuracy": 0.7797458006772034,
      "step": 125
    },
    {
      "epoch": 0.04834286245525961,
      "grad_norm": 0.29260385036468506,
      "learning_rate": 6.579798566743314e-06,
      "loss": 0.6946,
      "mean_token_accuracy": 0.7872012509701252,
      "step": 130
    },
    {
      "epoch": 0.050202203318923444,
      "grad_norm": 0.2695474624633789,
      "learning_rate": 5.773817382593008e-06,
      "loss": 0.7062,
      "mean_token_accuracy": 0.7810278868453384,
      "step": 135
    },
    {
      "epoch": 0.05206154418258727,
      "grad_norm": 0.2609573006629944,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.714,
      "mean_token_accuracy": 0.7813100702221802,
      "step": 140
    },
    {
      "epoch": 0.0539208850462511,
      "grad_norm": 0.2358129918575287,
      "learning_rate": 4.264235636489542e-06,
      "loss": 0.6856,
      "mean_token_accuracy": 0.7875874510326348,
      "step": 145
    },
    {
      "epoch": 0.05578022590991494,
      "grad_norm": 0.2715813219547272,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 0.6763,
      "mean_token_accuracy": 0.7909748424399494,
      "step": 150
    },
    {
      "epoch": 0.05763956677357877,
      "grad_norm": 0.2746134400367737,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.6526,
      "mean_token_accuracy": 0.7976525522946976,
      "step": 155
    },
    {
      "epoch": 0.059498907637242596,
      "grad_norm": 0.27577507495880127,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.7025,
      "mean_token_accuracy": 0.7832329110436247,
      "step": 160
    },
    {
      "epoch": 0.06135824850090643,
      "grad_norm": 0.2632084786891937,
      "learning_rate": 1.808479557110081e-06,
      "loss": 0.7124,
      "mean_token_accuracy": 0.7811312896263776,
      "step": 165
    },
    {
      "epoch": 0.06321758936457025,
      "grad_norm": 0.24432240426540375,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.673,
      "mean_token_accuracy": 0.7929312039857386,
      "step": 170
    },
    {
      "epoch": 0.06507693022823409,
      "grad_norm": 0.29202762246131897,
      "learning_rate": 9.369221296335007e-07,
      "loss": 0.6661,
      "mean_token_accuracy": 0.7959059321766028,
      "step": 175
    },
    {
      "epoch": 0.06693627109189793,
      "grad_norm": 0.2842048406600952,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.6624,
      "mean_token_accuracy": 0.7954249017619823,
      "step": 180
    },
    {
      "epoch": 0.06879561195556175,
      "grad_norm": 0.27937719225883484,
      "learning_rate": 3.4074173710931804e-07,
      "loss": 0.6797,
      "mean_token_accuracy": 0.7905420581208954,
      "step": 185
    },
    {
      "epoch": 0.07065495281922558,
      "grad_norm": 0.2555555999279022,
      "learning_rate": 1.519224698779198e-07,
      "loss": 0.6621,
      "mean_token_accuracy": 0.7970947981270515,
      "step": 190
    },
    {
      "epoch": 0.07251429368288942,
      "grad_norm": 0.2836684286594391,
      "learning_rate": 3.805301908254455e-08,
      "loss": 0.6908,
      "mean_token_accuracy": 0.7861675013499152,
      "step": 195
    },
    {
      "epoch": 0.07437363454655324,
      "grad_norm": 0.2971171438694,
      "learning_rate": 0.0,
      "loss": 0.6917,
      "mean_token_accuracy": 0.7878082632745567,
      "step": 200
    },
    {
      "epoch": 0.07437363454655324,
      "eval_loss": 0.7039155960083008,
      "eval_mean_token_accuracy": 0.782441121027168,
      "eval_runtime": 36.4458,
      "eval_samples_per_second": 6.997,
      "eval_steps_per_second": 3.512,
      "step": 200
    },
    {
      "epoch": 0.07437363454655324,
      "step": 200,
      "total_flos": 6.070131503398912e+16,
      "train_loss": 0.7046466362476349,
      "train_runtime": 3718.7973,
      "train_samples_per_second": 0.86,
      "train_steps_per_second": 0.054
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.070131503398912e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}