{
  "best_metric": 0.0,
  "best_model_checkpoint": "hiera_model/checkpoint-283",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 849,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0353356890459364,
      "grad_norm": 4.513326644897461,
      "learning_rate": 5.882352941176471e-06,
      "loss": 7.6619,
      "step": 10
    },
    {
      "epoch": 0.0706713780918728,
      "grad_norm": 5.347131729125977,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 7.6612,
      "step": 20
    },
    {
      "epoch": 0.10600706713780919,
      "grad_norm": 7.650573253631592,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 7.6148,
      "step": 30
    },
    {
      "epoch": 0.1413427561837456,
      "grad_norm": 6.892947196960449,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 7.532,
      "step": 40
    },
    {
      "epoch": 0.17667844522968199,
      "grad_norm": 7.388574600219727,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 7.4152,
      "step": 50
    },
    {
      "epoch": 0.21201413427561838,
      "grad_norm": 8.62385368347168,
      "learning_rate": 3.529411764705883e-05,
      "loss": 7.4114,
      "step": 60
    },
    {
      "epoch": 0.24734982332155478,
      "grad_norm": 10.373017311096191,
      "learning_rate": 4.11764705882353e-05,
      "loss": 7.3113,
      "step": 70
    },
    {
      "epoch": 0.2826855123674912,
      "grad_norm": 6.3279500007629395,
      "learning_rate": 4.705882352941177e-05,
      "loss": 7.2527,
      "step": 80
    },
    {
      "epoch": 0.31802120141342755,
      "grad_norm": 5.869943618774414,
      "learning_rate": 4.967277486910995e-05,
      "loss": 7.2645,
      "step": 90
    },
    {
      "epoch": 0.35335689045936397,
      "grad_norm": 5.0281453132629395,
      "learning_rate": 4.9018324607329844e-05,
      "loss": 7.1714,
      "step": 100
    },
    {
      "epoch": 0.38869257950530034,
      "grad_norm": 7.027573585510254,
      "learning_rate": 4.836387434554974e-05,
      "loss": 7.1634,
      "step": 110
    },
    {
      "epoch": 0.42402826855123676,
      "grad_norm": 4.754793167114258,
      "learning_rate": 4.770942408376964e-05,
      "loss": 7.1112,
      "step": 120
    },
    {
      "epoch": 0.45936395759717313,
      "grad_norm": 6.395844459533691,
      "learning_rate": 4.7054973821989526e-05,
      "loss": 7.0364,
      "step": 130
    },
    {
      "epoch": 0.49469964664310956,
      "grad_norm": 5.85114049911499,
      "learning_rate": 4.6400523560209424e-05,
      "loss": 7.0286,
      "step": 140
    },
    {
      "epoch": 0.5300353356890459,
      "grad_norm": 5.452080249786377,
      "learning_rate": 4.574607329842932e-05,
      "loss": 7.1043,
      "step": 150
    },
    {
      "epoch": 0.5653710247349824,
      "grad_norm": 5.287403583526611,
      "learning_rate": 4.5091623036649215e-05,
      "loss": 6.9891,
      "step": 160
    },
    {
      "epoch": 0.6007067137809188,
      "grad_norm": 5.20114803314209,
      "learning_rate": 4.4437172774869113e-05,
      "loss": 6.9994,
      "step": 170
    },
    {
      "epoch": 0.6360424028268551,
      "grad_norm": 5.050561428070068,
      "learning_rate": 4.3782722513089005e-05,
      "loss": 6.9812,
      "step": 180
    },
    {
      "epoch": 0.6713780918727915,
      "grad_norm": 4.857853412628174,
      "learning_rate": 4.3128272251308904e-05,
      "loss": 7.1296,
      "step": 190
    },
    {
      "epoch": 0.7067137809187279,
      "grad_norm": 4.78601598739624,
      "learning_rate": 4.24738219895288e-05,
      "loss": 7.0627,
      "step": 200
    },
    {
      "epoch": 0.7420494699646644,
      "grad_norm": 7.134556293487549,
      "learning_rate": 4.181937172774869e-05,
      "loss": 7.0056,
      "step": 210
    },
    {
      "epoch": 0.7773851590106007,
      "grad_norm": 5.701265811920166,
      "learning_rate": 4.1164921465968586e-05,
      "loss": 6.9878,
      "step": 220
    },
    {
      "epoch": 0.8127208480565371,
      "grad_norm": 5.249512672424316,
      "learning_rate": 4.0510471204188485e-05,
      "loss": 6.9481,
      "step": 230
    },
    {
      "epoch": 0.8480565371024735,
      "grad_norm": 5.31380558013916,
      "learning_rate": 3.985602094240838e-05,
      "loss": 6.9556,
      "step": 240
    },
    {
      "epoch": 0.8833922261484098,
      "grad_norm": 5.351413726806641,
      "learning_rate": 3.9201570680628275e-05,
      "loss": 6.9064,
      "step": 250
    },
    {
      "epoch": 0.9187279151943463,
      "grad_norm": 5.594610214233398,
      "learning_rate": 3.8547120418848174e-05,
      "loss": 6.934,
      "step": 260
    },
    {
      "epoch": 0.9540636042402827,
      "grad_norm": 8.065481185913086,
      "learning_rate": 3.7892670157068066e-05,
      "loss": 6.8646,
      "step": 270
    },
    {
      "epoch": 0.9893992932862191,
      "grad_norm": 6.58479642868042,
      "learning_rate": 3.7238219895287964e-05,
      "loss": 6.9557,
      "step": 280
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_loss": 8.122916221618652,
      "eval_runtime": 9.1372,
      "eval_samples_per_second": 10.944,
      "eval_steps_per_second": 0.219,
      "step": 283
    },
    {
      "epoch": 1.0247349823321554,
      "grad_norm": 9.340655326843262,
      "learning_rate": 3.6583769633507856e-05,
      "loss": 6.7977,
      "step": 290
    },
    {
      "epoch": 1.0600706713780919,
      "grad_norm": 5.579546928405762,
      "learning_rate": 3.592931937172775e-05,
      "loss": 6.6527,
      "step": 300
    },
    {
      "epoch": 1.0954063604240283,
      "grad_norm": 6.204797267913818,
      "learning_rate": 3.5274869109947647e-05,
      "loss": 6.7087,
      "step": 310
    },
    {
      "epoch": 1.1307420494699647,
      "grad_norm": 5.36489725112915,
      "learning_rate": 3.462041884816754e-05,
      "loss": 6.7543,
      "step": 320
    },
    {
      "epoch": 1.1660777385159011,
      "grad_norm": 5.784945964813232,
      "learning_rate": 3.396596858638744e-05,
      "loss": 6.8001,
      "step": 330
    },
    {
      "epoch": 1.2014134275618376,
      "grad_norm": 8.815863609313965,
      "learning_rate": 3.3311518324607336e-05,
      "loss": 6.7099,
      "step": 340
    },
    {
      "epoch": 1.2367491166077738,
      "grad_norm": 8.466463088989258,
      "learning_rate": 3.265706806282723e-05,
      "loss": 6.6982,
      "step": 350
    },
    {
      "epoch": 1.2720848056537102,
      "grad_norm": 6.15283727645874,
      "learning_rate": 3.2002617801047126e-05,
      "loss": 6.6768,
      "step": 360
    },
    {
      "epoch": 1.3074204946996466,
      "grad_norm": 7.654407501220703,
      "learning_rate": 3.134816753926702e-05,
      "loss": 6.734,
      "step": 370
    },
    {
      "epoch": 1.342756183745583,
      "grad_norm": 7.1313347816467285,
      "learning_rate": 3.069371727748691e-05,
      "loss": 6.7348,
      "step": 380
    },
    {
      "epoch": 1.3780918727915195,
      "grad_norm": 6.387876987457275,
      "learning_rate": 3.003926701570681e-05,
      "loss": 6.6646,
      "step": 390
    },
    {
      "epoch": 1.4134275618374559,
      "grad_norm": 6.7032294273376465,
      "learning_rate": 2.9384816753926704e-05,
      "loss": 6.664,
      "step": 400
    },
    {
      "epoch": 1.4487632508833923,
      "grad_norm": 8.315750122070312,
      "learning_rate": 2.87303664921466e-05,
      "loss": 6.6876,
      "step": 410
    },
    {
      "epoch": 1.4840989399293285,
      "grad_norm": 7.1473259925842285,
      "learning_rate": 2.8075916230366494e-05,
      "loss": 6.7499,
      "step": 420
    },
    {
      "epoch": 1.5194346289752652,
      "grad_norm": 8.586325645446777,
      "learning_rate": 2.742146596858639e-05,
      "loss": 6.625,
      "step": 430
    },
    {
      "epoch": 1.5547703180212014,
      "grad_norm": 6.852565765380859,
      "learning_rate": 2.6767015706806288e-05,
      "loss": 6.6484,
      "step": 440
    },
    {
      "epoch": 1.5901060070671378,
      "grad_norm": 7.314846992492676,
      "learning_rate": 2.6112565445026176e-05,
      "loss": 6.6476,
      "step": 450
    },
    {
      "epoch": 1.6254416961130742,
      "grad_norm": 8.678882598876953,
      "learning_rate": 2.545811518324607e-05,
      "loss": 6.6164,
      "step": 460
    },
    {
      "epoch": 1.6607773851590106,
      "grad_norm": 7.417328357696533,
      "learning_rate": 2.480366492146597e-05,
      "loss": 6.5872,
      "step": 470
    },
    {
      "epoch": 1.696113074204947,
      "grad_norm": 9.037349700927734,
      "learning_rate": 2.4149214659685865e-05,
      "loss": 6.6096,
      "step": 480
    },
    {
      "epoch": 1.7314487632508833,
      "grad_norm": 9.220462799072266,
      "learning_rate": 2.349476439790576e-05,
      "loss": 6.598,
      "step": 490
    },
    {
      "epoch": 1.76678445229682,
      "grad_norm": 10.437491416931152,
      "learning_rate": 2.2840314136125656e-05,
      "loss": 6.5736,
      "step": 500
    },
    {
      "epoch": 1.802120141342756,
      "grad_norm": 7.730395317077637,
      "learning_rate": 2.218586387434555e-05,
      "loss": 6.5369,
      "step": 510
    },
    {
      "epoch": 1.8374558303886925,
      "grad_norm": 9.4498872756958,
      "learning_rate": 2.1531413612565446e-05,
      "loss": 6.5505,
      "step": 520
    },
    {
      "epoch": 1.872791519434629,
      "grad_norm": 9.64456558227539,
      "learning_rate": 2.087696335078534e-05,
      "loss": 6.5647,
      "step": 530
    },
    {
      "epoch": 1.9081272084805654,
      "grad_norm": 7.969595909118652,
      "learning_rate": 2.0222513089005237e-05,
      "loss": 6.4623,
      "step": 540
    },
    {
      "epoch": 1.9434628975265018,
      "grad_norm": 13.205784797668457,
      "learning_rate": 1.9568062827225132e-05,
      "loss": 6.5204,
      "step": 550
    },
    {
      "epoch": 1.978798586572438,
      "grad_norm": 8.421072006225586,
      "learning_rate": 1.8913612565445027e-05,
      "loss": 6.6176,
      "step": 560
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.0,
      "eval_loss": 7.943063735961914,
      "eval_runtime": 8.8235,
      "eval_samples_per_second": 11.333,
      "eval_steps_per_second": 0.227,
      "step": 566
    },
    {
      "epoch": 2.0141342756183747,
      "grad_norm": 10.754253387451172,
      "learning_rate": 1.8259162303664922e-05,
      "loss": 6.3718,
      "step": 570
    },
    {
      "epoch": 2.049469964664311,
      "grad_norm": 9.648688316345215,
      "learning_rate": 1.7604712041884818e-05,
      "loss": 6.2833,
      "step": 580
    },
    {
      "epoch": 2.0848056537102475,
      "grad_norm": 8.878774642944336,
      "learning_rate": 1.6950261780104713e-05,
      "loss": 6.3031,
      "step": 590
    },
    {
      "epoch": 2.1201413427561837,
      "grad_norm": 8.666033744812012,
      "learning_rate": 1.6295811518324608e-05,
      "loss": 6.3308,
      "step": 600
    },
    {
      "epoch": 2.1554770318021204,
      "grad_norm": 9.023731231689453,
      "learning_rate": 1.5641361256544503e-05,
      "loss": 6.2989,
      "step": 610
    },
    {
      "epoch": 2.1908127208480566,
      "grad_norm": 10.014788627624512,
      "learning_rate": 1.49869109947644e-05,
      "loss": 6.2167,
      "step": 620
    },
    {
      "epoch": 2.2261484098939928,
      "grad_norm": 9.36070442199707,
      "learning_rate": 1.4332460732984294e-05,
      "loss": 6.3361,
      "step": 630
    },
    {
      "epoch": 2.2614840989399294,
      "grad_norm": 11.200228691101074,
      "learning_rate": 1.3678010471204189e-05,
      "loss": 6.2062,
      "step": 640
    },
    {
      "epoch": 2.2968197879858656,
      "grad_norm": 11.959548950195312,
      "learning_rate": 1.3023560209424086e-05,
      "loss": 6.2845,
      "step": 650
    },
    {
      "epoch": 2.3321554770318023,
      "grad_norm": 11.0889892578125,
      "learning_rate": 1.236910994764398e-05,
      "loss": 6.3267,
      "step": 660
    },
    {
      "epoch": 2.3674911660777385,
      "grad_norm": 11.451295852661133,
      "learning_rate": 1.1714659685863876e-05,
      "loss": 6.3199,
      "step": 670
    },
    {
      "epoch": 2.402826855123675,
      "grad_norm": 10.989713668823242,
      "learning_rate": 1.106020942408377e-05,
      "loss": 6.3512,
      "step": 680
    },
    {
      "epoch": 2.4381625441696113,
      "grad_norm": 12.176304817199707,
      "learning_rate": 1.0405759162303667e-05,
      "loss": 6.3017,
      "step": 690
    },
    {
      "epoch": 2.4734982332155475,
      "grad_norm": 8.967185020446777,
      "learning_rate": 9.75130890052356e-06,
      "loss": 6.3324,
      "step": 700
    },
    {
      "epoch": 2.508833922261484,
      "grad_norm": 11.730249404907227,
      "learning_rate": 9.096858638743457e-06,
      "loss": 6.2276,
      "step": 710
    },
    {
      "epoch": 2.5441696113074204,
      "grad_norm": 9.879383087158203,
      "learning_rate": 8.44240837696335e-06,
      "loss": 6.2391,
      "step": 720
    },
    {
      "epoch": 2.579505300353357,
      "grad_norm": 11.204628944396973,
      "learning_rate": 7.787958115183248e-06,
      "loss": 6.2064,
      "step": 730
    },
    {
      "epoch": 2.614840989399293,
      "grad_norm": 11.713162422180176,
      "learning_rate": 7.133507853403142e-06,
      "loss": 6.1786,
      "step": 740
    },
    {
      "epoch": 2.65017667844523,
      "grad_norm": 11.1579008102417,
      "learning_rate": 6.479057591623037e-06,
      "loss": 6.2621,
      "step": 750
    },
    {
      "epoch": 2.685512367491166,
      "grad_norm": 10.596528053283691,
      "learning_rate": 5.824607329842932e-06,
      "loss": 6.2023,
      "step": 760
    },
    {
      "epoch": 2.7208480565371023,
      "grad_norm": 11.238260269165039,
      "learning_rate": 5.170157068062828e-06,
      "loss": 6.267,
      "step": 770
    },
    {
      "epoch": 2.756183745583039,
      "grad_norm": 10.648133277893066,
      "learning_rate": 4.515706806282723e-06,
      "loss": 6.2735,
      "step": 780
    },
    {
      "epoch": 2.791519434628975,
      "grad_norm": 10.547654151916504,
      "learning_rate": 3.861256544502618e-06,
      "loss": 6.2288,
      "step": 790
    },
    {
      "epoch": 2.8268551236749118,
      "grad_norm": 11.513481140136719,
      "learning_rate": 3.2068062827225132e-06,
      "loss": 6.2293,
      "step": 800
    },
    {
      "epoch": 2.862190812720848,
      "grad_norm": 12.321627616882324,
      "learning_rate": 2.5523560209424085e-06,
      "loss": 6.2343,
      "step": 810
    },
    {
      "epoch": 2.8975265017667846,
      "grad_norm": 10.748133659362793,
      "learning_rate": 1.8979057591623037e-06,
      "loss": 6.1784,
      "step": 820
    },
    {
      "epoch": 2.932862190812721,
      "grad_norm": 11.156218528747559,
      "learning_rate": 1.243455497382199e-06,
      "loss": 6.2708,
      "step": 830
    },
    {
      "epoch": 2.968197879858657,
      "grad_norm": 10.066128730773926,
      "learning_rate": 5.890052356020942e-07,
      "loss": 6.2068,
      "step": 840
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.0,
      "eval_loss": 7.837530136108398,
      "eval_runtime": 8.6213,
      "eval_samples_per_second": 11.599,
      "eval_steps_per_second": 0.232,
      "step": 849
    }
  ],
  "logging_steps": 10,
  "max_steps": 849,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.3953276781480673e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}