{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6302521008403361,
  "eval_steps": 50,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01050420168067227,
      "grad_norm": 2.5582146644592285,
      "learning_rate": 4.98249299719888e-05,
      "loss": 1.6787,
      "step": 10
    },
    {
      "epoch": 0.02100840336134454,
      "grad_norm": 0.9345070719718933,
      "learning_rate": 4.96498599439776e-05,
      "loss": 0.518,
      "step": 20
    },
    {
      "epoch": 0.031512605042016806,
      "grad_norm": 1.6358414888381958,
      "learning_rate": 4.947478991596639e-05,
      "loss": 0.4604,
      "step": 30
    },
    {
      "epoch": 0.04201680672268908,
      "grad_norm": 0.7778844237327576,
      "learning_rate": 4.9299719887955186e-05,
      "loss": 0.3771,
      "step": 40
    },
    {
      "epoch": 0.052521008403361345,
      "grad_norm": 0.7006077766418457,
      "learning_rate": 4.912464985994398e-05,
      "loss": 0.3842,
      "step": 50
    },
    {
      "epoch": 0.052521008403361345,
      "eval_loss": 0.42603224515914917,
      "eval_runtime": 13.5673,
      "eval_samples_per_second": 35.379,
      "eval_steps_per_second": 2.211,
      "step": 50
    },
    {
      "epoch": 0.06302521008403361,
      "grad_norm": 0.6415153741836548,
      "learning_rate": 4.8949579831932775e-05,
      "loss": 0.3399,
      "step": 60
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 0.6030780076980591,
      "learning_rate": 4.877450980392157e-05,
      "loss": 0.3447,
      "step": 70
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 0.688852071762085,
      "learning_rate": 4.859943977591036e-05,
      "loss": 0.3219,
      "step": 80
    },
    {
      "epoch": 0.09453781512605042,
      "grad_norm": 0.6371557712554932,
      "learning_rate": 4.8424369747899164e-05,
      "loss": 0.3379,
      "step": 90
    },
    {
      "epoch": 0.10504201680672269,
      "grad_norm": 0.7739270329475403,
      "learning_rate": 4.824929971988796e-05,
      "loss": 0.3177,
      "step": 100
    },
    {
      "epoch": 0.10504201680672269,
      "eval_loss": 0.3801896274089813,
      "eval_runtime": 13.6107,
      "eval_samples_per_second": 35.266,
      "eval_steps_per_second": 2.204,
      "step": 100
    },
    {
      "epoch": 0.11554621848739496,
      "grad_norm": 0.649507462978363,
      "learning_rate": 4.807422969187675e-05,
      "loss": 0.3415,
      "step": 110
    },
    {
      "epoch": 0.12605042016806722,
      "grad_norm": 0.594717264175415,
      "learning_rate": 4.7899159663865554e-05,
      "loss": 0.3325,
      "step": 120
    },
    {
      "epoch": 0.13655462184873948,
      "grad_norm": 0.627918541431427,
      "learning_rate": 4.772408963585435e-05,
      "loss": 0.3222,
      "step": 130
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 0.5384674668312073,
      "learning_rate": 4.7549019607843135e-05,
      "loss": 0.3426,
      "step": 140
    },
    {
      "epoch": 0.15756302521008403,
      "grad_norm": 0.5673420429229736,
      "learning_rate": 4.7373949579831936e-05,
      "loss": 0.3061,
      "step": 150
    },
    {
      "epoch": 0.15756302521008403,
      "eval_loss": 0.3653399348258972,
      "eval_runtime": 13.5947,
      "eval_samples_per_second": 35.308,
      "eval_steps_per_second": 2.207,
      "step": 150
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 0.6111018657684326,
      "learning_rate": 4.719887955182073e-05,
      "loss": 0.3271,
      "step": 160
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.7422594428062439,
      "learning_rate": 4.7023809523809525e-05,
      "loss": 0.315,
      "step": 170
    },
    {
      "epoch": 0.18907563025210083,
      "grad_norm": 0.7226534485816956,
      "learning_rate": 4.684873949579832e-05,
      "loss": 0.3031,
      "step": 180
    },
    {
      "epoch": 0.19957983193277312,
      "grad_norm": 0.6302976012229919,
      "learning_rate": 4.667366946778712e-05,
      "loss": 0.3161,
      "step": 190
    },
    {
      "epoch": 0.21008403361344538,
      "grad_norm": 0.6225076913833618,
      "learning_rate": 4.6498599439775914e-05,
      "loss": 0.3038,
      "step": 200
    },
    {
      "epoch": 0.21008403361344538,
      "eval_loss": 0.35061606764793396,
      "eval_runtime": 13.5616,
      "eval_samples_per_second": 35.394,
      "eval_steps_per_second": 2.212,
      "step": 200
    },
    {
      "epoch": 0.22058823529411764,
      "grad_norm": 0.6001319885253906,
      "learning_rate": 4.632352941176471e-05,
      "loss": 0.3129,
      "step": 210
    },
    {
      "epoch": 0.23109243697478993,
      "grad_norm": 0.5385990142822266,
      "learning_rate": 4.61484593837535e-05,
      "loss": 0.2991,
      "step": 220
    },
    {
      "epoch": 0.2415966386554622,
      "grad_norm": 0.4513624906539917,
      "learning_rate": 4.59733893557423e-05,
      "loss": 0.2896,
      "step": 230
    },
    {
      "epoch": 0.25210084033613445,
      "grad_norm": 0.6142160892486572,
      "learning_rate": 4.579831932773109e-05,
      "loss": 0.3059,
      "step": 240
    },
    {
      "epoch": 0.26260504201680673,
      "grad_norm": 0.6714802384376526,
      "learning_rate": 4.562324929971989e-05,
      "loss": 0.2897,
      "step": 250
    },
    {
      "epoch": 0.26260504201680673,
      "eval_loss": 0.3456435203552246,
      "eval_runtime": 13.5552,
      "eval_samples_per_second": 35.411,
      "eval_steps_per_second": 2.213,
      "step": 250
    },
    {
      "epoch": 0.27310924369747897,
      "grad_norm": 0.6518235206604004,
      "learning_rate": 4.5448179271708687e-05,
      "loss": 0.312,
      "step": 260
    },
    {
      "epoch": 0.28361344537815125,
      "grad_norm": 0.6250632405281067,
      "learning_rate": 4.527310924369748e-05,
      "loss": 0.2959,
      "step": 270
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 0.5683826804161072,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.3027,
      "step": 280
    },
    {
      "epoch": 0.30462184873949577,
      "grad_norm": 0.560312807559967,
      "learning_rate": 4.4922969187675076e-05,
      "loss": 0.3002,
      "step": 290
    },
    {
      "epoch": 0.31512605042016806,
      "grad_norm": 0.66291743516922,
      "learning_rate": 4.474789915966387e-05,
      "loss": 0.2925,
      "step": 300
    },
    {
      "epoch": 0.31512605042016806,
      "eval_loss": 0.3431606888771057,
      "eval_runtime": 13.5629,
      "eval_samples_per_second": 35.391,
      "eval_steps_per_second": 2.212,
      "step": 300
    },
    {
      "epoch": 0.32563025210084034,
      "grad_norm": 0.6478439569473267,
      "learning_rate": 4.4572829131652665e-05,
      "loss": 0.2893,
      "step": 310
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.5832348465919495,
      "learning_rate": 4.439775910364146e-05,
      "loss": 0.2842,
      "step": 320
    },
    {
      "epoch": 0.34663865546218486,
      "grad_norm": 0.525932252407074,
      "learning_rate": 4.422268907563025e-05,
      "loss": 0.2837,
      "step": 330
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.5487508177757263,
      "learning_rate": 4.404761904761905e-05,
      "loss": 0.2706,
      "step": 340
    },
    {
      "epoch": 0.36764705882352944,
      "grad_norm": 0.5392388701438904,
      "learning_rate": 4.387254901960784e-05,
      "loss": 0.2835,
      "step": 350
    },
    {
      "epoch": 0.36764705882352944,
      "eval_loss": 0.33528536558151245,
      "eval_runtime": 13.5508,
      "eval_samples_per_second": 35.422,
      "eval_steps_per_second": 2.214,
      "step": 350
    },
    {
      "epoch": 0.37815126050420167,
      "grad_norm": 0.6706260442733765,
      "learning_rate": 4.369747899159664e-05,
      "loss": 0.2844,
      "step": 360
    },
    {
      "epoch": 0.38865546218487396,
      "grad_norm": 0.6042625904083252,
      "learning_rate": 4.352240896358544e-05,
      "loss": 0.2758,
      "step": 370
    },
    {
      "epoch": 0.39915966386554624,
      "grad_norm": 0.534008264541626,
      "learning_rate": 4.334733893557423e-05,
      "loss": 0.2918,
      "step": 380
    },
    {
      "epoch": 0.4096638655462185,
      "grad_norm": 0.48162588477134705,
      "learning_rate": 4.317226890756303e-05,
      "loss": 0.273,
      "step": 390
    },
    {
      "epoch": 0.42016806722689076,
      "grad_norm": 0.5669644474983215,
      "learning_rate": 4.2997198879551826e-05,
      "loss": 0.285,
      "step": 400
    },
    {
      "epoch": 0.42016806722689076,
      "eval_loss": 0.3348632752895355,
      "eval_runtime": 13.5507,
      "eval_samples_per_second": 35.423,
      "eval_steps_per_second": 2.214,
      "step": 400
    },
    {
      "epoch": 0.43067226890756305,
      "grad_norm": 0.6257824897766113,
      "learning_rate": 4.2822128851540614e-05,
      "loss": 0.299,
      "step": 410
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 0.5430576205253601,
      "learning_rate": 4.2647058823529415e-05,
      "loss": 0.2868,
      "step": 420
    },
    {
      "epoch": 0.45168067226890757,
      "grad_norm": 0.5633955597877502,
      "learning_rate": 4.247198879551821e-05,
      "loss": 0.2589,
      "step": 430
    },
    {
      "epoch": 0.46218487394957986,
      "grad_norm": 0.5294789671897888,
      "learning_rate": 4.2296918767507e-05,
      "loss": 0.2777,
      "step": 440
    },
    {
      "epoch": 0.4726890756302521,
      "grad_norm": 0.5480856895446777,
      "learning_rate": 4.21218487394958e-05,
      "loss": 0.2704,
      "step": 450
    },
    {
      "epoch": 0.4726890756302521,
      "eval_loss": 0.329515278339386,
      "eval_runtime": 13.5423,
      "eval_samples_per_second": 35.445,
      "eval_steps_per_second": 2.215,
      "step": 450
    },
    {
      "epoch": 0.4831932773109244,
      "grad_norm": 0.5051332116127014,
      "learning_rate": 4.19467787114846e-05,
      "loss": 0.2438,
      "step": 460
    },
    {
      "epoch": 0.49369747899159666,
      "grad_norm": 0.6251511573791504,
      "learning_rate": 4.177170868347339e-05,
      "loss": 0.2748,
      "step": 470
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.4729413092136383,
      "learning_rate": 4.159663865546219e-05,
      "loss": 0.2689,
      "step": 480
    },
    {
      "epoch": 0.5147058823529411,
      "grad_norm": 0.5220003724098206,
      "learning_rate": 4.142156862745099e-05,
      "loss": 0.2899,
      "step": 490
    },
    {
      "epoch": 0.5252100840336135,
      "grad_norm": 0.54283207654953,
      "learning_rate": 4.1246498599439776e-05,
      "loss": 0.272,
      "step": 500
    },
    {
      "epoch": 0.5252100840336135,
      "eval_loss": 0.32714489102363586,
      "eval_runtime": 13.5497,
      "eval_samples_per_second": 35.425,
      "eval_steps_per_second": 2.214,
      "step": 500
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.5851682424545288,
      "learning_rate": 4.107142857142857e-05,
      "loss": 0.2691,
      "step": 510
    },
    {
      "epoch": 0.5462184873949579,
      "grad_norm": 0.6026607751846313,
      "learning_rate": 4.089635854341737e-05,
      "loss": 0.2716,
      "step": 520
    },
    {
      "epoch": 0.5567226890756303,
      "grad_norm": 0.522422730922699,
      "learning_rate": 4.0721288515406165e-05,
      "loss": 0.2774,
      "step": 530
    },
    {
      "epoch": 0.5672268907563025,
      "grad_norm": 0.516901433467865,
      "learning_rate": 4.054621848739496e-05,
      "loss": 0.2726,
      "step": 540
    },
    {
      "epoch": 0.5777310924369747,
      "grad_norm": 0.667030394077301,
      "learning_rate": 4.0371148459383754e-05,
      "loss": 0.2622,
      "step": 550
    },
    {
      "epoch": 0.5777310924369747,
      "eval_loss": 0.3262839615345001,
      "eval_runtime": 13.5448,
      "eval_samples_per_second": 35.438,
      "eval_steps_per_second": 2.215,
      "step": 550
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.542658269405365,
      "learning_rate": 4.0196078431372555e-05,
      "loss": 0.2572,
      "step": 560
    },
    {
      "epoch": 0.5987394957983193,
      "grad_norm": 0.5408573746681213,
      "learning_rate": 4.002100840336135e-05,
      "loss": 0.2636,
      "step": 570
    },
    {
      "epoch": 0.6092436974789915,
      "grad_norm": 0.5691037774085999,
      "learning_rate": 3.984593837535014e-05,
      "loss": 0.268,
      "step": 580
    },
    {
      "epoch": 0.6197478991596639,
      "grad_norm": 0.5530794858932495,
      "learning_rate": 3.967086834733894e-05,
      "loss": 0.2583,
      "step": 590
    },
    {
      "epoch": 0.6302521008403361,
      "grad_norm": 0.546229362487793,
      "learning_rate": 3.949579831932773e-05,
      "loss": 0.2622,
      "step": 600
    },
    {
      "epoch": 0.6302521008403361,
      "eval_loss": 0.3219989836215973,
      "eval_runtime": 13.5524,
      "eval_samples_per_second": 35.418,
      "eval_steps_per_second": 2.214,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 2856,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.178628867607757e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}