{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11494252873563218,
      "grad_norm": 4.644741535186768,
      "learning_rate": 2.272727272727273e-05,
      "loss": 1.1688,
      "step": 10
    },
    {
      "epoch": 0.22988505747126436,
      "grad_norm": 2.3340258598327637,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.5977,
      "step": 20
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 1.2856472730636597,
      "learning_rate": 6.818181818181818e-05,
      "loss": 0.4087,
      "step": 30
    },
    {
      "epoch": 0.45977011494252873,
      "grad_norm": 0.7791835069656372,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.3196,
      "step": 40
    },
    {
      "epoch": 0.5747126436781609,
      "grad_norm": 1.9682774543762207,
      "learning_rate": 9.998698142908953e-05,
      "loss": 0.2605,
      "step": 50
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 1.491060495376587,
      "learning_rate": 9.990744804507315e-05,
      "loss": 0.2392,
      "step": 60
    },
    {
      "epoch": 0.8045977011494253,
      "grad_norm": 1.1608132123947144,
      "learning_rate": 9.975572871372513e-05,
      "loss": 0.2292,
      "step": 70
    },
    {
      "epoch": 0.9195402298850575,
      "grad_norm": 0.7938467264175415,
      "learning_rate": 9.953204288132234e-05,
      "loss": 0.208,
      "step": 80
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 1.011293888092041,
      "learning_rate": 9.923671408622129e-05,
      "loss": 0.1914,
      "step": 90
    },
    {
      "epoch": 1.1494252873563218,
      "grad_norm": 0.6203814148902893,
      "learning_rate": 9.887016949089333e-05,
      "loss": 0.1906,
      "step": 100
    },
    {
      "epoch": 1.264367816091954,
      "grad_norm": 0.8494653701782227,
      "learning_rate": 9.843293926407866e-05,
      "loss": 0.1684,
      "step": 110
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 2.562549114227295,
      "learning_rate": 9.7925655813952e-05,
      "loss": 0.1627,
      "step": 120
    },
    {
      "epoch": 1.4942528735632183,
      "grad_norm": 0.9271527528762817,
      "learning_rate": 9.734905287340985e-05,
      "loss": 0.16,
      "step": 130
    },
    {
      "epoch": 1.6091954022988506,
      "grad_norm": 0.7429759502410889,
      "learning_rate": 9.670396443880208e-05,
      "loss": 0.1459,
      "step": 140
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 2.3561415672302246,
      "learning_rate": 9.599132356364247e-05,
      "loss": 0.1455,
      "step": 150
    },
    {
      "epoch": 1.839080459770115,
      "grad_norm": 0.823359489440918,
      "learning_rate": 9.521216100904378e-05,
      "loss": 0.1416,
      "step": 160
    },
    {
      "epoch": 1.9540229885057472,
      "grad_norm": 0.8451648950576782,
      "learning_rate": 9.436760375282859e-05,
      "loss": 0.1354,
      "step": 170
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 0.40135863423347473,
      "learning_rate": 9.345887335947281e-05,
      "loss": 0.1297,
      "step": 180
    },
    {
      "epoch": 2.1839080459770113,
      "grad_norm": 0.5253118276596069,
      "learning_rate": 9.248728421323941e-05,
      "loss": 0.1357,
      "step": 190
    },
    {
      "epoch": 2.2988505747126435,
      "grad_norm": 0.6746734976768494,
      "learning_rate": 9.145424161705776e-05,
      "loss": 0.1215,
      "step": 200
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 0.567961573600769,
      "learning_rate": 9.036123975989892e-05,
      "loss": 0.1223,
      "step": 210
    },
    {
      "epoch": 2.528735632183908,
      "grad_norm": 0.8848130702972412,
      "learning_rate": 8.9209859555586e-05,
      "loss": 0.1035,
      "step": 220
    },
    {
      "epoch": 2.6436781609195403,
      "grad_norm": 0.39595693349838257,
      "learning_rate": 8.800176635616657e-05,
      "loss": 0.1059,
      "step": 230
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 0.8946174383163452,
      "learning_rate": 8.673870754315336e-05,
      "loss": 0.1128,
      "step": 240
    },
    {
      "epoch": 2.873563218390805,
      "grad_norm": 0.3929500877857208,
      "learning_rate": 8.54225100001184e-05,
      "loss": 0.0929,
      "step": 250
    },
    {
      "epoch": 2.9885057471264367,
      "grad_norm": 0.45673438906669617,
      "learning_rate": 8.405507747029523e-05,
      "loss": 0.0947,
      "step": 260
    },
    {
      "epoch": 3.103448275862069,
      "grad_norm": 0.6119157671928406,
      "learning_rate": 8.263838780301182e-05,
      "loss": 0.0906,
      "step": 270
    },
    {
      "epoch": 3.218390804597701,
      "grad_norm": 0.39985448122024536,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0943,
      "step": 280
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.5258167386054993,
      "learning_rate": 7.966550171627592e-05,
      "loss": 0.0979,
      "step": 290
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 0.37616410851478577,
      "learning_rate": 7.81136052682082e-05,
      "loss": 0.0948,
      "step": 300
    },
    {
      "epoch": 3.5632183908045976,
      "grad_norm": 0.5887285470962524,
      "learning_rate": 7.652104540598712e-05,
      "loss": 0.0996,
      "step": 310
    },
    {
      "epoch": 3.67816091954023,
      "grad_norm": 0.6064506769180298,
      "learning_rate": 7.489012560227742e-05,
      "loss": 0.0915,
      "step": 320
    },
    {
      "epoch": 3.793103448275862,
      "grad_norm": 3.263113021850586,
      "learning_rate": 7.322320481342054e-05,
      "loss": 0.0906,
      "step": 330
    },
    {
      "epoch": 3.9080459770114944,
      "grad_norm": 0.49090155959129333,
      "learning_rate": 7.152269406744903e-05,
      "loss": 0.0784,
      "step": 340
    },
    {
      "epoch": 4.022988505747127,
      "grad_norm": 0.6040999889373779,
      "learning_rate": 6.979105297678462e-05,
      "loss": 0.0871,
      "step": 350
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 0.4672296941280365,
      "learning_rate": 6.803078618066378e-05,
      "loss": 0.0751,
      "step": 360
    },
    {
      "epoch": 4.252873563218391,
      "grad_norm": 2.379974365234375,
      "learning_rate": 6.624443972243698e-05,
      "loss": 0.0778,
      "step": 370
    },
    {
      "epoch": 4.3678160919540225,
      "grad_norm": 1.2806555032730103,
      "learning_rate": 6.443459736698105e-05,
      "loss": 0.0763,
      "step": 380
    },
    {
      "epoch": 4.482758620689655,
      "grad_norm": 0.937697172164917,
      "learning_rate": 6.260387686355121e-05,
      "loss": 0.0752,
      "step": 390
    },
    {
      "epoch": 4.597701149425287,
      "grad_norm": 0.45729660987854004,
      "learning_rate": 6.075492615947823e-05,
      "loss": 0.0844,
      "step": 400
    },
    {
      "epoch": 4.712643678160919,
      "grad_norm": 0.9074535369873047,
      "learning_rate": 5.889041957018745e-05,
      "loss": 0.0743,
      "step": 410
    },
    {
      "epoch": 4.827586206896552,
      "grad_norm": 0.4833395779132843,
      "learning_rate": 5.7013053911078677e-05,
      "loss": 0.0693,
      "step": 420
    },
    {
      "epoch": 4.942528735632184,
      "grad_norm": 0.7885887026786804,
      "learning_rate": 5.51255445968625e-05,
      "loss": 0.0785,
      "step": 430
    },
    {
      "epoch": 5.057471264367816,
      "grad_norm": 0.4227044880390167,
      "learning_rate": 5.32306217139946e-05,
      "loss": 0.1054,
      "step": 440
    },
    {
      "epoch": 5.172413793103448,
      "grad_norm": 0.6370951533317566,
      "learning_rate": 5.133102607188874e-05,
      "loss": 0.0729,
      "step": 450
    },
    {
      "epoch": 5.287356321839081,
      "grad_norm": 0.6800243258476257,
      "learning_rate": 4.942950523862033e-05,
      "loss": 0.0723,
      "step": 460
    },
    {
      "epoch": 5.402298850574713,
      "grad_norm": 0.4485301375389099,
      "learning_rate": 4.752880956685407e-05,
      "loss": 0.0817,
      "step": 470
    },
    {
      "epoch": 5.517241379310345,
      "grad_norm": 0.583954393863678,
      "learning_rate": 4.56316882157442e-05,
      "loss": 0.067,
      "step": 480
    },
    {
      "epoch": 5.6321839080459775,
      "grad_norm": 0.4566665589809418,
      "learning_rate": 4.3740885174560736e-05,
      "loss": 0.0609,
      "step": 490
    },
    {
      "epoch": 5.747126436781609,
      "grad_norm": 0.6292296051979065,
      "learning_rate": 4.185913529379381e-05,
      "loss": 0.0684,
      "step": 500
    },
    {
      "epoch": 5.862068965517241,
      "grad_norm": 6.967523097991943,
      "learning_rate": 3.998916032947594e-05,
      "loss": 0.0744,
      "step": 510
    },
    {
      "epoch": 5.977011494252873,
      "grad_norm": 0.7225087881088257,
      "learning_rate": 3.8133665006444255e-05,
      "loss": 0.0623,
      "step": 520
    },
    {
      "epoch": 6.091954022988506,
      "grad_norm": 0.35148298740386963,
      "learning_rate": 3.629533310623658e-05,
      "loss": 0.0744,
      "step": 530
    },
    {
      "epoch": 6.206896551724138,
      "grad_norm": 0.35271674394607544,
      "learning_rate": 3.447682358527974e-05,
      "loss": 0.0615,
      "step": 540
    },
    {
      "epoch": 6.32183908045977,
      "grad_norm": 0.47165122628211975,
      "learning_rate": 3.268076672898492e-05,
      "loss": 0.0657,
      "step": 550
    },
    {
      "epoch": 6.436781609195402,
      "grad_norm": 0.7261269092559814,
      "learning_rate": 3.090976034731257e-05,
      "loss": 0.0666,
      "step": 560
    },
    {
      "epoch": 6.551724137931035,
      "grad_norm": 0.30101433396339417,
      "learning_rate": 2.91663660173098e-05,
      "loss": 0.0618,
      "step": 570
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 1.2878450155258179,
      "learning_rate": 2.745310537805479e-05,
      "loss": 0.0549,
      "step": 580
    },
    {
      "epoch": 6.781609195402299,
      "grad_norm": 0.7477713227272034,
      "learning_rate": 2.5772456483367497e-05,
      "loss": 0.0673,
      "step": 590
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 0.9708021283149719,
      "learning_rate": 2.4126850217561698e-05,
      "loss": 0.0519,
      "step": 600
    },
    {
      "epoch": 7.011494252873563,
      "grad_norm": 0.3879060447216034,
      "learning_rate": 2.2518666779423074e-05,
      "loss": 0.0559,
      "step": 610
    },
    {
      "epoch": 7.126436781609195,
      "grad_norm": 0.7332598567008972,
      "learning_rate": 2.0950232239498446e-05,
      "loss": 0.0557,
      "step": 620
    },
    {
      "epoch": 7.241379310344827,
      "grad_norm": 0.5789719223976135,
      "learning_rate": 1.9423815175676025e-05,
      "loss": 0.0547,
      "step": 630
    },
    {
      "epoch": 7.35632183908046,
      "grad_norm": 0.7040994763374329,
      "learning_rate": 1.7941623391922772e-05,
      "loss": 0.0562,
      "step": 640
    },
    {
      "epoch": 7.471264367816092,
      "grad_norm": 0.37133750319480896,
      "learning_rate": 1.650580072492496e-05,
      "loss": 0.0604,
      "step": 650
    },
    {
      "epoch": 7.586206896551724,
      "grad_norm": 0.3775554895401001,
      "learning_rate": 1.5118423943250771e-05,
      "loss": 0.0526,
      "step": 660
    },
    {
      "epoch": 7.7011494252873565,
      "grad_norm": 0.46704328060150146,
      "learning_rate": 1.378149974351991e-05,
      "loss": 0.0507,
      "step": 670
    },
    {
      "epoch": 7.816091954022989,
      "grad_norm": 0.26738837361335754,
      "learning_rate": 1.2496961847925153e-05,
      "loss": 0.0534,
      "step": 680
    },
    {
      "epoch": 7.931034482758621,
      "grad_norm": 1.4386327266693115,
      "learning_rate": 1.126666820730366e-05,
      "loss": 0.0513,
      "step": 690
    },
    {
      "epoch": 8.045977011494253,
      "grad_norm": 0.4603922367095947,
      "learning_rate": 1.0092398313803863e-05,
      "loss": 0.0626,
      "step": 700
    },
    {
      "epoch": 8.160919540229886,
      "grad_norm": 0.49872225522994995,
      "learning_rate": 8.975850627034604e-06,
      "loss": 0.0553,
      "step": 710
    },
    {
      "epoch": 8.275862068965518,
      "grad_norm": 0.8791252374649048,
      "learning_rate": 7.918640117419507e-06,
      "loss": 0.0438,
      "step": 720
    },
    {
      "epoch": 8.39080459770115,
      "grad_norm": 0.621422290802002,
      "learning_rate": 6.922295930309691e-06,
      "loss": 0.0539,
      "step": 730
    },
    {
      "epoch": 8.505747126436782,
      "grad_norm": 1.4802906513214111,
      "learning_rate": 5.988259174233713e-06,
      "loss": 0.0514,
      "step": 740
    },
    {
      "epoch": 8.620689655172415,
      "grad_norm": 1.4139326810836792,
      "learning_rate": 5.117880836483452e-06,
      "loss": 0.0593,
      "step": 750
    },
    {
      "epoch": 8.735632183908045,
      "grad_norm": 0.7812165021896362,
      "learning_rate": 4.312419829051173e-06,
      "loss": 0.0468,
      "step": 760
    },
    {
      "epoch": 8.850574712643677,
      "grad_norm": 0.4393046200275421,
      "learning_rate": 3.5730411677439125e-06,
      "loss": 0.0553,
      "step": 770
    },
    {
      "epoch": 8.96551724137931,
      "grad_norm": 1.7484021186828613,
      "learning_rate": 2.9008142871088663e-06,
      "loss": 0.0504,
      "step": 780
    },
    {
      "epoch": 9.080459770114942,
      "grad_norm": 0.6218745708465576,
      "learning_rate": 2.296711493607334e-06,
      "loss": 0.0542,
      "step": 790
    },
    {
      "epoch": 9.195402298850574,
      "grad_norm": 0.4588974118232727,
      "learning_rate": 1.7616065592742038e-06,
      "loss": 0.0554,
      "step": 800
    },
    {
      "epoch": 9.310344827586206,
      "grad_norm": 1.559602975845337,
      "learning_rate": 1.2962734578973568e-06,
      "loss": 0.0484,
      "step": 810
    },
    {
      "epoch": 9.425287356321839,
      "grad_norm": 0.2676626145839691,
      "learning_rate": 9.013852455448335e-07,
      "loss": 0.0485,
      "step": 820
    },
    {
      "epoch": 9.540229885057471,
      "grad_norm": 0.4192800223827362,
      "learning_rate": 5.775130870590783e-07,
      "loss": 0.0488,
      "step": 830
    },
    {
      "epoch": 9.655172413793103,
      "grad_norm": 0.7301256656646729,
      "learning_rate": 3.251254299261874e-07,
      "loss": 0.0531,
      "step": 840
    },
    {
      "epoch": 9.770114942528735,
      "grad_norm": 0.2674349844455719,
      "learning_rate": 1.4458732671523977e-07,
      "loss": 0.0504,
      "step": 850
    },
    {
      "epoch": 9.885057471264368,
      "grad_norm": 0.4260900318622589,
      "learning_rate": 3.6159907067601085e-08,
      "loss": 0.0504,
      "step": 860
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2096983194351196,
      "learning_rate": 0.0,
      "loss": 0.0608,
      "step": 870
    },
    {
      "epoch": 10.0,
      "step": 870,
      "total_flos": 9.390719321209728e+16,
      "train_loss": 0.11421718011642325,
      "train_runtime": 878.5225,
      "train_samples_per_second": 48.217,
      "train_steps_per_second": 0.99
    }
  ],
  "logging_steps": 10,
  "max_steps": 870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.390719321209728e+16,
  "train_batch_size": 49,
  "trial_name": null,
  "trial_params": null
}