{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99968,
  "eval_steps": 500,
  "global_step": 781,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0128,
      "grad_norm": 6.701968747476725,
      "learning_rate": 1.2658227848101267e-06,
      "loss": 2.0492,
      "step": 10
    },
    {
      "epoch": 0.0256,
      "grad_norm": 3.5864792739638993,
      "learning_rate": 2.5316455696202535e-06,
      "loss": 1.8655,
      "step": 20
    },
    {
      "epoch": 0.0384,
      "grad_norm": 2.259761356336166,
      "learning_rate": 3.7974683544303802e-06,
      "loss": 1.4331,
      "step": 30
    },
    {
      "epoch": 0.0512,
      "grad_norm": 1.2720768014744341,
      "learning_rate": 5.063291139240507e-06,
      "loss": 1.0761,
      "step": 40
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.0682982350883623,
      "learning_rate": 6.329113924050634e-06,
      "loss": 0.8806,
      "step": 50
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.9449369476401172,
      "learning_rate": 7.5949367088607605e-06,
      "loss": 0.7862,
      "step": 60
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.838448848722395,
      "learning_rate": 8.860759493670886e-06,
      "loss": 0.7079,
      "step": 70
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.8665745666024749,
      "learning_rate": 9.99994993147413e-06,
      "loss": 0.6374,
      "step": 80
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.9204076286525019,
      "learning_rate": 9.993942921593858e-06,
      "loss": 0.6237,
      "step": 90
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.8161132171073118,
      "learning_rate": 9.977935989714594e-06,
      "loss": 0.5959,
      "step": 100
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.8084929937439845,
      "learning_rate": 9.951961188279216e-06,
      "loss": 0.5679,
      "step": 110
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.8088758200190634,
      "learning_rate": 9.916070529493785e-06,
      "loss": 0.5446,
      "step": 120
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.9130344418330479,
      "learning_rate": 9.870335881177774e-06,
      "loss": 0.5291,
      "step": 130
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.872718919094986,
      "learning_rate": 9.814848822855216e-06,
      "loss": 0.5222,
      "step": 140
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.8235461664054124,
      "learning_rate": 9.749720462374939e-06,
      "loss": 0.5171,
      "step": 150
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.7993561717725581,
      "learning_rate": 9.675081213427076e-06,
      "loss": 0.501,
      "step": 160
    },
    {
      "epoch": 0.2176,
      "grad_norm": 0.8630181557231864,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.4905,
      "step": 170
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.7780745671601388,
      "learning_rate": 9.497886629110187e-06,
      "loss": 0.4887,
      "step": 180
    },
    {
      "epoch": 0.2432,
      "grad_norm": 0.8530578246740471,
      "learning_rate": 9.395686109975475e-06,
      "loss": 0.4754,
      "step": 190
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.8589511545486503,
      "learning_rate": 9.284683624354172e-06,
      "loss": 0.4681,
      "step": 200
    },
    {
      "epoch": 0.2688,
      "grad_norm": 0.8106070665074115,
      "learning_rate": 9.165101444750259e-06,
      "loss": 0.4503,
      "step": 210
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.828720382021103,
      "learning_rate": 9.037179023734036e-06,
      "loss": 0.4505,
      "step": 220
    },
    {
      "epoch": 0.2944,
      "grad_norm": 0.7971023327381064,
      "learning_rate": 8.901172514459864e-06,
      "loss": 0.4492,
      "step": 230
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.7508670805091862,
      "learning_rate": 8.757354257742501e-06,
      "loss": 0.4428,
      "step": 240
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.8374186185876672,
      "learning_rate": 8.606012236719073e-06,
      "loss": 0.4357,
      "step": 250
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.8494045534506517,
      "learning_rate": 8.447449500188731e-06,
      "loss": 0.4335,
      "step": 260
    },
    {
      "epoch": 0.3456,
      "grad_norm": 0.8159143844721547,
      "learning_rate": 8.28198355578465e-06,
      "loss": 0.4249,
      "step": 270
    },
    {
      "epoch": 0.3584,
      "grad_norm": 0.7945294112933121,
      "learning_rate": 8.10994573419352e-06,
      "loss": 0.417,
      "step": 280
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.8092393955680712,
      "learning_rate": 7.931680525695634e-06,
      "loss": 0.4101,
      "step": 290
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.8268532168275566,
      "learning_rate": 7.747544890354031e-06,
      "loss": 0.4102,
      "step": 300
    },
    {
      "epoch": 0.3968,
      "grad_norm": 0.8307675190521085,
      "learning_rate": 7.557907543234051e-06,
      "loss": 0.4005,
      "step": 310
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.8066842247859759,
      "learning_rate": 7.363148216084548e-06,
      "loss": 0.3938,
      "step": 320
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.8219121679671916,
      "learning_rate": 7.163656896959181e-06,
      "loss": 0.4025,
      "step": 330
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.7806012947481233,
      "learning_rate": 6.959833049300376e-06,
      "loss": 0.3917,
      "step": 340
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.7583628073160137,
      "learning_rate": 6.75208481204967e-06,
      "loss": 0.3956,
      "step": 350
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.7932654942930134,
      "learning_rate": 6.540828182386154e-06,
      "loss": 0.3863,
      "step": 360
    },
    {
      "epoch": 0.4736,
      "grad_norm": 0.7950343391931867,
      "learning_rate": 6.326486182729504e-06,
      "loss": 0.386,
      "step": 370
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.7556004511705458,
      "learning_rate": 6.1094880136755886e-06,
      "loss": 0.3876,
      "step": 380
    },
    {
      "epoch": 0.4992,
      "grad_norm": 0.7878348206227572,
      "learning_rate": 5.890268194560834e-06,
      "loss": 0.3751,
      "step": 390
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.9576214818021522,
      "learning_rate": 5.669265693376309e-06,
      "loss": 0.3773,
      "step": 400
    },
    {
      "epoch": 0.5248,
      "grad_norm": 0.7598363460040048,
      "learning_rate": 5.4469230477737466e-06,
      "loss": 0.3785,
      "step": 410
    },
    {
      "epoch": 0.5376,
      "grad_norm": 0.7420324190383087,
      "learning_rate": 5.223685478923671e-06,
      "loss": 0.3641,
      "step": 420
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.8017146285762878,
      "learning_rate": 5e-06,
      "loss": 0.3769,
      "step": 430
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.7670735510600653,
      "learning_rate": 4.77631452107633e-06,
      "loss": 0.3747,
      "step": 440
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.7840762329546958,
      "learning_rate": 4.553076952226255e-06,
      "loss": 0.3539,
      "step": 450
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.8119170658398085,
      "learning_rate": 4.330734306623694e-06,
      "loss": 0.3702,
      "step": 460
    },
    {
      "epoch": 0.6016,
      "grad_norm": 0.7778368273813389,
      "learning_rate": 4.109731805439168e-06,
      "loss": 0.36,
      "step": 470
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.7979085157539837,
      "learning_rate": 3.890511986324413e-06,
      "loss": 0.3655,
      "step": 480
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.8322448925414319,
      "learning_rate": 3.6735138172704967e-06,
      "loss": 0.355,
      "step": 490
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.8096327876710914,
      "learning_rate": 3.459171817613847e-06,
      "loss": 0.3593,
      "step": 500
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.801578229202024,
      "learning_rate": 3.2479151879503324e-06,
      "loss": 0.3547,
      "step": 510
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.7715945441438417,
      "learning_rate": 3.040166950699626e-06,
      "loss": 0.3564,
      "step": 520
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.7724629808163839,
      "learning_rate": 2.836343103040819e-06,
      "loss": 0.3455,
      "step": 530
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.7703132105218164,
      "learning_rate": 2.636851783915454e-06,
      "loss": 0.3574,
      "step": 540
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.8346457043519747,
      "learning_rate": 2.4420924567659508e-06,
      "loss": 0.3563,
      "step": 550
    },
    {
      "epoch": 0.7168,
      "grad_norm": 0.7478114203409938,
      "learning_rate": 2.2524551096459703e-06,
      "loss": 0.3442,
      "step": 560
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.7175822746663116,
      "learning_rate": 2.068319474304365e-06,
      "loss": 0.3513,
      "step": 570
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.7765522703854497,
      "learning_rate": 1.8900542658064807e-06,
      "loss": 0.3505,
      "step": 580
    },
    {
      "epoch": 0.7552,
      "grad_norm": 0.8131308220238767,
      "learning_rate": 1.7180164442153529e-06,
      "loss": 0.3436,
      "step": 590
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.7675648858585707,
      "learning_rate": 1.5525504998112717e-06,
      "loss": 0.3492,
      "step": 600
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.7848374060613897,
      "learning_rate": 1.3939877632809279e-06,
      "loss": 0.3376,
      "step": 610
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.7172688497141017,
      "learning_rate": 1.2426457422575e-06,
      "loss": 0.3509,
      "step": 620
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.7513406260924876,
      "learning_rate": 1.0988274855401377e-06,
      "loss": 0.3427,
      "step": 630
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.719098637869978,
      "learning_rate": 9.628209762659658e-07,
      "loss": 0.352,
      "step": 640
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.7878403671063132,
      "learning_rate": 8.348985552497424e-07,
      "loss": 0.3512,
      "step": 650
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.778349621811645,
      "learning_rate": 7.153163756458287e-07,
      "loss": 0.3418,
      "step": 660
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.7627951845894294,
      "learning_rate": 6.043138900245277e-07,
      "loss": 0.3415,
      "step": 670
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.7267205608588538,
      "learning_rate": 5.021133708898146e-07,
      "loss": 0.3498,
      "step": 680
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.774296421867312,
      "learning_rate": 4.089194655986306e-07,
      "loss": 0.3418,
      "step": 690
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.7629885918292927,
      "learning_rate": 3.2491878657292643e-07,
      "loss": 0.3417,
      "step": 700
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.7684825905537629,
      "learning_rate": 2.502795376250622e-07,
      "loss": 0.3414,
      "step": 710
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.7495748143605184,
      "learning_rate": 1.8515117714478447e-07,
      "loss": 0.3303,
      "step": 720
    },
    {
      "epoch": 0.9344,
      "grad_norm": 0.7729420979175768,
      "learning_rate": 1.2966411882222695e-07,
      "loss": 0.3516,
      "step": 730
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.7645078415028198,
      "learning_rate": 8.392947050621603e-08,
      "loss": 0.3459,
      "step": 740
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7401931558129734,
      "learning_rate": 4.803881172078473e-08,
      "loss": 0.3381,
      "step": 750
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.7847554015277991,
      "learning_rate": 2.206401028540639e-08,
      "loss": 0.3435,
      "step": 760
    },
    {
      "epoch": 0.9856,
      "grad_norm": 0.8032295395801471,
      "learning_rate": 6.057078406142003e-09,
      "loss": 0.3533,
      "step": 770
    },
    {
      "epoch": 0.9984,
      "grad_norm": 0.7538439870936887,
      "learning_rate": 5.0068525870305974e-11,
      "loss": 0.3355,
      "step": 780
    },
    {
      "epoch": 0.99968,
      "step": 781,
      "total_flos": 51822668021760.0,
      "train_loss": 0.4785180231902114,
      "train_runtime": 3564.8554,
      "train_samples_per_second": 28.052,
      "train_steps_per_second": 0.219
    }
  ],
  "logging_steps": 10,
  "max_steps": 781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 51822668021760.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}