{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991537376586743,
  "eval_steps": 500,
  "global_step": 1329,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 1.3541167390816127,
      "learning_rate": 1e-06,
      "loss": 0.7892,
      "step": 10
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.7264231850744329,
      "learning_rate": 1e-06,
      "loss": 0.7186,
      "step": 20
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.6066684028794114,
      "learning_rate": 1e-06,
      "loss": 0.6958,
      "step": 30
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.5922845047115146,
      "learning_rate": 1e-06,
      "loss": 0.6703,
      "step": 40
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.5655949106141192,
      "learning_rate": 1e-06,
      "loss": 0.6624,
      "step": 50
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.6001006048051749,
      "learning_rate": 1e-06,
      "loss": 0.6603,
      "step": 60
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.5943745260723494,
      "learning_rate": 1e-06,
      "loss": 0.655,
      "step": 70
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.627834773775133,
      "learning_rate": 1e-06,
      "loss": 0.6557,
      "step": 80
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.5550793132057606,
      "learning_rate": 1e-06,
      "loss": 0.6531,
      "step": 90
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.5689760442146818,
      "learning_rate": 1e-06,
      "loss": 0.6513,
      "step": 100
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.5623137575600806,
      "learning_rate": 1e-06,
      "loss": 0.6417,
      "step": 110
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.5486362710231304,
      "learning_rate": 1e-06,
      "loss": 0.6406,
      "step": 120
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 0.7239936549173934,
      "learning_rate": 1e-06,
      "loss": 0.6415,
      "step": 130
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.5461401863831158,
      "learning_rate": 1e-06,
      "loss": 0.636,
      "step": 140
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.5483972404016155,
      "learning_rate": 1e-06,
      "loss": 0.6361,
      "step": 150
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.798239248846604,
      "learning_rate": 1e-06,
      "loss": 0.638,
      "step": 160
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.5775493583413234,
      "learning_rate": 1e-06,
      "loss": 0.6337,
      "step": 170
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.5471975796667967,
      "learning_rate": 1e-06,
      "loss": 0.6308,
      "step": 180
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.5770116378368964,
      "learning_rate": 1e-06,
      "loss": 0.625,
      "step": 190
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.6018358262436428,
      "learning_rate": 1e-06,
      "loss": 0.6311,
      "step": 200
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.6214575004609858,
      "learning_rate": 1e-06,
      "loss": 0.6277,
      "step": 210
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.5762569358894746,
      "learning_rate": 1e-06,
      "loss": 0.6189,
      "step": 220
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.572204338525046,
      "learning_rate": 1e-06,
      "loss": 0.628,
      "step": 230
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.5406800730091907,
      "learning_rate": 1e-06,
      "loss": 0.6264,
      "step": 240
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.7049926618754724,
      "learning_rate": 1e-06,
      "loss": 0.6202,
      "step": 250
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.5706039865907114,
      "learning_rate": 1e-06,
      "loss": 0.623,
      "step": 260
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.6199169688295726,
      "learning_rate": 1e-06,
      "loss": 0.6183,
      "step": 270
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.5856905093166911,
      "learning_rate": 1e-06,
      "loss": 0.6251,
      "step": 280
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.6047672043963276,
      "learning_rate": 1e-06,
      "loss": 0.6184,
      "step": 290
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.5860307869500213,
      "learning_rate": 1e-06,
      "loss": 0.6243,
      "step": 300
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.5557486139623895,
      "learning_rate": 1e-06,
      "loss": 0.6172,
      "step": 310
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.5891234296869776,
      "learning_rate": 1e-06,
      "loss": 0.6207,
      "step": 320
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.547918374354159,
      "learning_rate": 1e-06,
      "loss": 0.6162,
      "step": 330
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.5442402563667577,
      "learning_rate": 1e-06,
      "loss": 0.6151,
      "step": 340
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.5860646515907174,
      "learning_rate": 1e-06,
      "loss": 0.6165,
      "step": 350
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.5535463576219704,
      "learning_rate": 1e-06,
      "loss": 0.6156,
      "step": 360
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.5756281236150095,
      "learning_rate": 1e-06,
      "loss": 0.6226,
      "step": 370
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.5950482068214076,
      "learning_rate": 1e-06,
      "loss": 0.6191,
      "step": 380
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.6260982756368931,
      "learning_rate": 1e-06,
      "loss": 0.6131,
      "step": 390
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.5364333350591519,
      "learning_rate": 1e-06,
      "loss": 0.6154,
      "step": 400
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.6098043968571839,
      "learning_rate": 1e-06,
      "loss": 0.6134,
      "step": 410
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.6449811728681593,
      "learning_rate": 1e-06,
      "loss": 0.6138,
      "step": 420
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 0.5568535469034295,
      "learning_rate": 1e-06,
      "loss": 0.6078,
      "step": 430
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.6431203491501234,
      "learning_rate": 1e-06,
      "loss": 0.6126,
      "step": 440
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.6105000972747803,
      "eval_runtime": 685.4377,
      "eval_samples_per_second": 17.421,
      "eval_steps_per_second": 0.546,
      "step": 443
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.7779306881983701,
      "learning_rate": 1e-06,
      "loss": 0.6478,
      "step": 450
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.6328828703701227,
      "learning_rate": 1e-06,
      "loss": 0.5849,
      "step": 460
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.6082430510445967,
      "learning_rate": 1e-06,
      "loss": 0.6009,
      "step": 470
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 0.602028057200349,
      "learning_rate": 1e-06,
      "loss": 0.5871,
      "step": 480
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.7408617800573869,
      "learning_rate": 1e-06,
      "loss": 0.5984,
      "step": 490
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.5611898278455757,
      "learning_rate": 1e-06,
      "loss": 0.5964,
      "step": 500
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.5832472204993896,
      "learning_rate": 1e-06,
      "loss": 0.596,
      "step": 510
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.5695284469211872,
      "learning_rate": 1e-06,
      "loss": 0.5875,
      "step": 520
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.6568577698478514,
      "learning_rate": 1e-06,
      "loss": 0.5939,
      "step": 530
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.586435498560335,
      "learning_rate": 1e-06,
      "loss": 0.5906,
      "step": 540
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.5855700220689813,
      "learning_rate": 1e-06,
      "loss": 0.595,
      "step": 550
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.5614379605237669,
      "learning_rate": 1e-06,
      "loss": 0.5965,
      "step": 560
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.5641915546644509,
      "learning_rate": 1e-06,
      "loss": 0.5932,
      "step": 570
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.5891648230252526,
      "learning_rate": 1e-06,
      "loss": 0.5925,
      "step": 580
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.6055365904668806,
      "learning_rate": 1e-06,
      "loss": 0.5917,
      "step": 590
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.5835116087715779,
      "learning_rate": 1e-06,
      "loss": 0.598,
      "step": 600
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.5717115602804459,
      "learning_rate": 1e-06,
      "loss": 0.5894,
      "step": 610
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.6550994090581721,
      "learning_rate": 1e-06,
      "loss": 0.5932,
      "step": 620
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.5652647115951249,
      "learning_rate": 1e-06,
      "loss": 0.5909,
      "step": 630
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.603846199030464,
      "learning_rate": 1e-06,
      "loss": 0.5907,
      "step": 640
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.576216687167576,
      "learning_rate": 1e-06,
      "loss": 0.5912,
      "step": 650
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.5854798505920723,
      "learning_rate": 1e-06,
      "loss": 0.5947,
      "step": 660
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.6758805948706326,
      "learning_rate": 1e-06,
      "loss": 0.5887,
      "step": 670
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.5597355473960971,
      "learning_rate": 1e-06,
      "loss": 0.5823,
      "step": 680
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.5956678886860574,
      "learning_rate": 1e-06,
      "loss": 0.585,
      "step": 690
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.5686506141405391,
      "learning_rate": 1e-06,
      "loss": 0.5886,
      "step": 700
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.5755832522278349,
      "learning_rate": 1e-06,
      "loss": 0.5912,
      "step": 710
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.6014689265229756,
      "learning_rate": 1e-06,
      "loss": 0.5996,
      "step": 720
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.5728757135668859,
      "learning_rate": 1e-06,
      "loss": 0.5815,
      "step": 730
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.5921114444919704,
      "learning_rate": 1e-06,
      "loss": 0.5985,
      "step": 740
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.5806339365041464,
      "learning_rate": 1e-06,
      "loss": 0.5891,
      "step": 750
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.5685739123888505,
      "learning_rate": 1e-06,
      "loss": 0.5874,
      "step": 760
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.596569886181905,
      "learning_rate": 1e-06,
      "loss": 0.5876,
      "step": 770
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.5948382867064587,
      "learning_rate": 1e-06,
      "loss": 0.5834,
      "step": 780
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.560419630409488,
      "learning_rate": 1e-06,
      "loss": 0.587,
      "step": 790
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.6073231967396352,
      "learning_rate": 1e-06,
      "loss": 0.5813,
      "step": 800
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.5595516250387841,
      "learning_rate": 1e-06,
      "loss": 0.5923,
      "step": 810
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.5733241612129921,
      "learning_rate": 1e-06,
      "loss": 0.5789,
      "step": 820
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.574054154592995,
      "learning_rate": 1e-06,
      "loss": 0.5917,
      "step": 830
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.5814856685071563,
      "learning_rate": 1e-06,
      "loss": 0.5913,
      "step": 840
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.5895975578808779,
      "learning_rate": 1e-06,
      "loss": 0.5781,
      "step": 850
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.5589949521607741,
      "learning_rate": 1e-06,
      "loss": 0.583,
      "step": 860
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.5843925173653625,
      "learning_rate": 1e-06,
      "loss": 0.5899,
      "step": 870
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.5728967924600331,
      "learning_rate": 1e-06,
      "loss": 0.5879,
      "step": 880
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5974977016448975,
      "eval_runtime": 685.9643,
      "eval_samples_per_second": 17.408,
      "eval_steps_per_second": 0.545,
      "step": 886
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 0.6457869644641364,
      "learning_rate": 1e-06,
      "loss": 0.6318,
      "step": 890
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.5930954348218526,
      "learning_rate": 1e-06,
      "loss": 0.5662,
      "step": 900
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.6055346690385593,
      "learning_rate": 1e-06,
      "loss": 0.5694,
      "step": 910
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.562520339476423,
      "learning_rate": 1e-06,
      "loss": 0.5611,
      "step": 920
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.5561710805119879,
      "learning_rate": 1e-06,
      "loss": 0.5685,
      "step": 930
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.5979304183331132,
      "learning_rate": 1e-06,
      "loss": 0.572,
      "step": 940
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.6093159324869943,
      "learning_rate": 1e-06,
      "loss": 0.5734,
      "step": 950
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.6175829170597708,
      "learning_rate": 1e-06,
      "loss": 0.5691,
      "step": 960
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.6068960323831453,
      "learning_rate": 1e-06,
      "loss": 0.5652,
      "step": 970
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.6177800363612478,
      "learning_rate": 1e-06,
      "loss": 0.5591,
      "step": 980
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.6120518804072075,
      "learning_rate": 1e-06,
      "loss": 0.5581,
      "step": 990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.6185740976783666,
      "learning_rate": 1e-06,
      "loss": 0.5689,
      "step": 1000
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.6044905148971333,
      "learning_rate": 1e-06,
      "loss": 0.5755,
      "step": 1010
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.6787947041417691,
      "learning_rate": 1e-06,
      "loss": 0.5678,
      "step": 1020
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.6244782221013093,
      "learning_rate": 1e-06,
      "loss": 0.5726,
      "step": 1030
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.5838463678550949,
      "learning_rate": 1e-06,
      "loss": 0.5688,
      "step": 1040
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.5986795934805791,
      "learning_rate": 1e-06,
      "loss": 0.5654,
      "step": 1050
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.5491793607349916,
      "learning_rate": 1e-06,
      "loss": 0.565,
      "step": 1060
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.6275876027256113,
      "learning_rate": 1e-06,
      "loss": 0.5652,
      "step": 1070
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.5952317032256541,
      "learning_rate": 1e-06,
      "loss": 0.569,
      "step": 1080
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.5915109016237521,
      "learning_rate": 1e-06,
      "loss": 0.567,
      "step": 1090
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.5905585385598298,
      "learning_rate": 1e-06,
      "loss": 0.5693,
      "step": 1100
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.6031395826071679,
      "learning_rate": 1e-06,
      "loss": 0.573,
      "step": 1110
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.5861509889782255,
      "learning_rate": 1e-06,
      "loss": 0.5616,
      "step": 1120
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.6059625495599589,
      "learning_rate": 1e-06,
      "loss": 0.5672,
      "step": 1130
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.570836533993128,
      "learning_rate": 1e-06,
      "loss": 0.5651,
      "step": 1140
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.5561735145605855,
      "learning_rate": 1e-06,
      "loss": 0.5659,
      "step": 1150
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.6334567898240941,
      "learning_rate": 1e-06,
      "loss": 0.5696,
      "step": 1160
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.5610258684119728,
      "learning_rate": 1e-06,
      "loss": 0.5564,
      "step": 1170
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.6013204802258304,
      "learning_rate": 1e-06,
      "loss": 0.5686,
      "step": 1180
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.5914030753618424,
      "learning_rate": 1e-06,
      "loss": 0.5691,
      "step": 1190
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.6080013945750986,
      "learning_rate": 1e-06,
      "loss": 0.5673,
      "step": 1200
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.6801858228679418,
      "learning_rate": 1e-06,
      "loss": 0.5684,
      "step": 1210
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.6863898034527391,
      "learning_rate": 1e-06,
      "loss": 0.5638,
      "step": 1220
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.5906541395902623,
      "learning_rate": 1e-06,
      "loss": 0.5713,
      "step": 1230
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.5644242194086181,
      "learning_rate": 1e-06,
      "loss": 0.5694,
      "step": 1240
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.5714345353820881,
      "learning_rate": 1e-06,
      "loss": 0.5689,
      "step": 1250
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.5962882121230534,
      "learning_rate": 1e-06,
      "loss": 0.5704,
      "step": 1260
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.5799929393173268,
      "learning_rate": 1e-06,
      "loss": 0.5669,
      "step": 1270
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.5896163258532005,
      "learning_rate": 1e-06,
      "loss": 0.5641,
      "step": 1280
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.5855508417080076,
      "learning_rate": 1e-06,
      "loss": 0.5688,
      "step": 1290
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.5566279321823554,
      "learning_rate": 1e-06,
      "loss": 0.563,
      "step": 1300
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.6400231422216401,
      "learning_rate": 1e-06,
      "loss": 0.5677,
      "step": 1310
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.6067593940730119,
      "learning_rate": 1e-06,
      "loss": 0.562,
      "step": 1320
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.5919322371482849,
      "eval_runtime": 686.7261,
      "eval_samples_per_second": 17.388,
      "eval_steps_per_second": 0.545,
      "step": 1329
    },
    {
      "epoch": 2.9991537376586743,
      "step": 1329,
      "total_flos": 5064195066298368.0,
      "train_loss": 0.5987174125252316,
      "train_runtime": 120974.831,
      "train_samples_per_second": 5.626,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 1329,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5064195066298368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}