{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1320,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 4.307063447378547,
      "learning_rate": 7.575757575757576e-07,
      "loss": 0.7126,
      "step": 10
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 2.478183802674108,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.6907,
      "step": 20
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 2.093724232621029,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.6475,
      "step": 30
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.988326655453792,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.5679,
      "step": 40
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 1.5026333071399824,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 0.5262,
      "step": 50
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.1747754528130179,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.4857,
      "step": 60
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 1.3829995461023388,
      "learning_rate": 5.303030303030303e-06,
      "loss": 0.5007,
      "step": 70
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.1555847024592305,
      "learning_rate": 6.060606060606061e-06,
      "loss": 0.4704,
      "step": 80
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 1.530346299350765,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.4815,
      "step": 90
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.3258734821104459,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 0.4453,
      "step": 100
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0866300791021735,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.479,
      "step": 110
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.1145634533248179,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.4551,
      "step": 120
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 1.2164089669910587,
      "learning_rate": 9.84848484848485e-06,
      "loss": 0.4506,
      "step": 130
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.4715102015058124,
      "learning_rate": 9.99888115313551e-06,
      "loss": 0.4689,
      "step": 140
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 1.25166857918504,
      "learning_rate": 9.994336695915041e-06,
      "loss": 0.4648,
      "step": 150
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.1482193515136296,
      "learning_rate": 9.986299875742612e-06,
      "loss": 0.4508,
      "step": 160
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 1.4115865068533915,
      "learning_rate": 9.97477631248223e-06,
      "loss": 0.468,
      "step": 170
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 1.2290742002804682,
      "learning_rate": 9.959774064153977e-06,
      "loss": 0.4541,
      "step": 180
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 1.1793845606021387,
      "learning_rate": 9.941303621299332e-06,
      "loss": 0.4278,
      "step": 190
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.9220892011963717,
      "learning_rate": 9.919377899645497e-06,
      "loss": 0.4379,
      "step": 200
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 1.0861369533049958,
      "learning_rate": 9.894012231073895e-06,
      "loss": 0.418,
      "step": 210
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.0739119949772593,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.438,
      "step": 220
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 1.0583396452432017,
      "learning_rate": 9.833034395465866e-06,
      "loss": 0.4498,
      "step": 230
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.2558829873984296,
      "learning_rate": 9.797464868072489e-06,
      "loss": 0.4241,
      "step": 240
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.9274074484915623,
      "learning_rate": 9.758540643231041e-06,
      "loss": 0.4473,
      "step": 250
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 1.1351911624937234,
      "learning_rate": 9.716288939274818e-06,
      "loss": 0.4197,
      "step": 260
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 1.0488446178988242,
      "learning_rate": 9.670739301325534e-06,
      "loss": 0.4442,
      "step": 270
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.3143206978246442,
      "learning_rate": 9.621923580633462e-06,
      "loss": 0.4217,
      "step": 280
    },
    {
      "epoch": 0.6590909090909091,
      "grad_norm": 1.1646273970559764,
      "learning_rate": 9.56987591230498e-06,
      "loss": 0.4294,
      "step": 290
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 1.1283407631969753,
      "learning_rate": 9.514632691433108e-06,
      "loss": 0.4505,
      "step": 300
    },
    {
      "epoch": 0.7045454545454546,
      "grad_norm": 1.0905525560287967,
      "learning_rate": 9.456232547647695e-06,
      "loss": 0.4496,
      "step": 310
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.855761546485483,
      "learning_rate": 9.394716318103098e-06,
      "loss": 0.425,
      "step": 320
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.1885215313833324,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.4691,
      "step": 330
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.9705633869137796,
      "learning_rate": 9.262509815116732e-06,
      "loss": 0.4266,
      "step": 340
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.9460295884946632,
      "learning_rate": 9.191911989005038e-06,
      "loss": 0.4334,
      "step": 350
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.8244479504968187,
      "learning_rate": 9.118382907149164e-06,
      "loss": 0.4354,
      "step": 360
    },
    {
      "epoch": 0.8409090909090909,
      "grad_norm": 1.0907034782243845,
      "learning_rate": 9.041973985834595e-06,
      "loss": 0.4409,
      "step": 370
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.9011547089995718,
      "learning_rate": 8.96273865511666e-06,
      "loss": 0.4272,
      "step": 380
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 1.2220001058375158,
      "learning_rate": 8.880732321458785e-06,
      "loss": 0.4325,
      "step": 390
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.0552888697398697,
      "learning_rate": 8.796012328988716e-06,
      "loss": 0.4069,
      "step": 400
    },
    {
      "epoch": 0.9318181818181818,
      "grad_norm": 1.307751530018105,
      "learning_rate": 8.708637919399798e-06,
      "loss": 0.4396,
      "step": 410
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.9812773481606568,
      "learning_rate": 8.61867019052535e-06,
      "loss": 0.4171,
      "step": 420
    },
    {
      "epoch": 0.9772727272727273,
      "grad_norm": 1.0623603631162184,
      "learning_rate": 8.526172053615122e-06,
      "loss": 0.4095,
      "step": 430
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0466603824404057,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.4303,
      "step": 440
    },
    {
      "epoch": 1.0227272727272727,
      "grad_norm": 0.9422037793723509,
      "learning_rate": 8.33384500258146e-06,
      "loss": 0.3291,
      "step": 450
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 1.1439839179446254,
      "learning_rate": 8.234150575960288e-06,
      "loss": 0.3231,
      "step": 460
    },
    {
      "epoch": 1.0681818181818181,
      "grad_norm": 0.9363363052426827,
      "learning_rate": 8.132194622265508e-06,
      "loss": 0.3321,
      "step": 470
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.8976501587025572,
      "learning_rate": 8.028048435688333e-06,
      "loss": 0.307,
      "step": 480
    },
    {
      "epoch": 1.1136363636363635,
      "grad_norm": 0.8926726629185868,
      "learning_rate": 7.921784841972355e-06,
      "loss": 0.2804,
      "step": 490
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 1.0791854561775653,
      "learning_rate": 7.813478147489052e-06,
      "loss": 0.3356,
      "step": 500
    },
    {
      "epoch": 1.1590909090909092,
      "grad_norm": 0.9510040199261199,
      "learning_rate": 7.703204087277989e-06,
      "loss": 0.3192,
      "step": 510
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 1.0208622518742,
      "learning_rate": 7.5910397720879785e-06,
      "loss": 0.3253,
      "step": 520
    },
    {
      "epoch": 1.2045454545454546,
      "grad_norm": 1.1056530204649813,
      "learning_rate": 7.477063634456263e-06,
      "loss": 0.2948,
      "step": 530
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.8907984718041057,
      "learning_rate": 7.361355373863415e-06,
      "loss": 0.3303,
      "step": 540
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.9921150120480224,
      "learning_rate": 7.243995901002312e-06,
      "loss": 0.3281,
      "step": 550
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.1894145553342288,
      "learning_rate": 7.1250672812001505e-06,
      "loss": 0.3254,
      "step": 560
    },
    {
      "epoch": 1.2954545454545454,
      "grad_norm": 1.1062688043595825,
      "learning_rate": 7.004652677033069e-06,
      "loss": 0.328,
      "step": 570
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.8834038525733939,
      "learning_rate": 6.882836290173493e-06,
      "loss": 0.3242,
      "step": 580
    },
    {
      "epoch": 1.3409090909090908,
      "grad_norm": 1.032054335046655,
      "learning_rate": 6.759703302510898e-06,
      "loss": 0.3408,
      "step": 590
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 1.0032122077515986,
      "learning_rate": 6.635339816587109e-06,
      "loss": 0.3188,
      "step": 600
    },
    {
      "epoch": 1.3863636363636362,
      "grad_norm": 0.8472856067780782,
      "learning_rate": 6.5098327953878585e-06,
      "loss": 0.3108,
      "step": 610
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.9812797187008553,
      "learning_rate": 6.383270001532636e-06,
      "loss": 0.3192,
      "step": 620
    },
    {
      "epoch": 1.4318181818181819,
      "grad_norm": 0.982163512940909,
      "learning_rate": 6.255739935905396e-06,
      "loss": 0.3032,
      "step": 630
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.8121759235743116,
      "learning_rate": 6.127331775769023e-06,
      "loss": 0.328,
      "step": 640
    },
    {
      "epoch": 1.4772727272727273,
      "grad_norm": 0.8288842937391799,
      "learning_rate": 5.998135312406821e-06,
      "loss": 0.3241,
      "step": 650
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.1705693195996676,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.3097,
      "step": 660
    },
    {
      "epoch": 1.5227272727272727,
      "grad_norm": 1.1928631326301389,
      "learning_rate": 5.737739334127611e-06,
      "loss": 0.3306,
      "step": 670
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.8793536700861068,
      "learning_rate": 5.60672190490541e-06,
      "loss": 0.2965,
      "step": 680
    },
    {
      "epoch": 1.5681818181818183,
      "grad_norm": 1.1096056081901176,
      "learning_rate": 5.475280216520913e-06,
      "loss": 0.3149,
      "step": 690
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 1.0132771918230767,
      "learning_rate": 5.343506181496405e-06,
      "loss": 0.3376,
      "step": 700
    },
    {
      "epoch": 1.6136363636363638,
      "grad_norm": 1.0015800596494355,
      "learning_rate": 5.2114919447524155e-06,
      "loss": 0.3091,
      "step": 710
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 1.3217531318258682,
      "learning_rate": 5.07932981917404e-06,
      "loss": 0.3424,
      "step": 720
    },
    {
      "epoch": 1.6590909090909092,
      "grad_norm": 0.844031720581408,
      "learning_rate": 4.947112221059803e-06,
      "loss": 0.334,
      "step": 730
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.9811023453126005,
      "learning_rate": 4.81493160549821e-06,
      "loss": 0.3149,
      "step": 740
    },
    {
      "epoch": 1.7045454545454546,
      "grad_norm": 0.9120047314542666,
      "learning_rate": 4.682880401717178e-06,
      "loss": 0.3387,
      "step": 750
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.9645251862151868,
      "learning_rate": 4.551050948451542e-06,
      "loss": 0.3075,
      "step": 760
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.029589258346577,
      "learning_rate": 4.4195354293738484e-06,
      "loss": 0.2997,
      "step": 770
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.8289069672393073,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 0.3114,
      "step": 780
    },
    {
      "epoch": 1.7954545454545454,
      "grad_norm": 0.8269221372870464,
      "learning_rate": 4.1578137665498485e-06,
      "loss": 0.3162,
      "step": 790
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.0419412973934015,
      "learning_rate": 4.027790635502646e-06,
      "loss": 0.3022,
      "step": 800
    },
    {
      "epoch": 1.8409090909090908,
      "grad_norm": 0.828576197701733,
      "learning_rate": 3.898447336067297e-06,
      "loss": 0.3181,
      "step": 810
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.7902710878002056,
      "learning_rate": 3.769874313436933e-06,
      "loss": 0.2964,
      "step": 820
    },
    {
      "epoch": 1.8863636363636362,
      "grad_norm": 0.8650766226460292,
      "learning_rate": 3.6421614741773702e-06,
      "loss": 0.3083,
      "step": 830
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.911674397252804,
      "learning_rate": 3.5153981233586277e-06,
      "loss": 0.3278,
      "step": 840
    },
    {
      "epoch": 1.9318181818181817,
      "grad_norm": 1.0190901522385132,
      "learning_rate": 3.389672902107044e-06,
      "loss": 0.2963,
      "step": 850
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.9093931759022098,
      "learning_rate": 3.2650737256216885e-06,
      "loss": 0.3143,
      "step": 860
    },
    {
      "epoch": 1.9772727272727273,
      "grad_norm": 0.9726770446051795,
      "learning_rate": 3.141687721698363e-06,
      "loss": 0.3025,
      "step": 870
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8959220677622172,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.3343,
      "step": 880
    },
    {
      "epoch": 2.022727272727273,
      "grad_norm": 1.0245721987690635,
      "learning_rate": 2.898899440745569e-06,
      "loss": 0.2299,
      "step": 890
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.7717882058531099,
      "learning_rate": 2.7796669369711294e-06,
      "loss": 0.2129,
      "step": 900
    },
    {
      "epoch": 2.0681818181818183,
      "grad_norm": 1.4121404315256307,
      "learning_rate": 2.6619870335523434e-06,
      "loss": 0.1988,
      "step": 910
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.8228740125650449,
      "learning_rate": 2.5459420198821604e-06,
      "loss": 0.2377,
      "step": 920
    },
    {
      "epoch": 2.1136363636363638,
      "grad_norm": 1.0688882544650145,
      "learning_rate": 2.4316130421329696e-06,
      "loss": 0.243,
      "step": 930
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.6981423061851445,
      "learning_rate": 2.319080046513954e-06,
      "loss": 0.1995,
      "step": 940
    },
    {
      "epoch": 2.159090909090909,
      "grad_norm": 0.7538445094011031,
      "learning_rate": 2.2084217233675386e-06,
      "loss": 0.2313,
      "step": 950
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.7057622922962025,
      "learning_rate": 2.09971545214401e-06,
      "loss": 0.2037,
      "step": 960
    },
    {
      "epoch": 2.2045454545454546,
      "grad_norm": 0.8953813377341792,
      "learning_rate": 1.9930372472928095e-06,
      "loss": 0.2385,
      "step": 970
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.8650152971442162,
      "learning_rate": 1.8884617051083183e-06,
      "loss": 0.2231,
      "step": 980
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.7372775145267629,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.2233,
      "step": 990
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 1.1713711786724677,
      "learning_rate": 1.68590959119452e-06,
      "loss": 0.2302,
      "step": 1000
    },
    {
      "epoch": 2.2954545454545454,
      "grad_norm": 0.8830634163052888,
      "learning_rate": 1.5880746569921867e-06,
      "loss": 0.213,
      "step": 1010
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 0.7920929754273773,
      "learning_rate": 1.4926255614683931e-06,
      "loss": 0.2231,
      "step": 1020
    },
    {
      "epoch": 2.340909090909091,
      "grad_norm": 0.9483810580401165,
      "learning_rate": 1.3996290487986568e-06,
      "loss": 0.2046,
      "step": 1030
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.9124193486122323,
      "learning_rate": 1.3091501481540676e-06,
      "loss": 0.1922,
      "step": 1040
    },
    {
      "epoch": 2.3863636363636362,
      "grad_norm": 0.9345460355742555,
      "learning_rate": 1.2212521282287093e-06,
      "loss": 0.2193,
      "step": 1050
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 0.7947710523061967,
      "learning_rate": 1.135996452998085e-06,
      "loss": 0.2185,
      "step": 1060
    },
    {
      "epoch": 2.4318181818181817,
      "grad_norm": 0.8478563530801623,
      "learning_rate": 1.0534427387395391e-06,
      "loss": 0.2014,
      "step": 1070
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.847550358331553,
      "learning_rate": 9.73648712344707e-07,
      "loss": 0.2197,
      "step": 1080
    },
    {
      "epoch": 2.4772727272727275,
      "grad_norm": 0.9568357719105378,
      "learning_rate": 8.966701709531344e-07,
      "loss": 0.2239,
      "step": 1090
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.8646126050539757,
      "learning_rate": 8.225609429353187e-07,
      "loss": 0.2054,
      "step": 1100
    },
    {
      "epoch": 2.5227272727272725,
      "grad_norm": 0.8831276830491341,
      "learning_rate": 7.513728502524286e-07,
      "loss": 0.1895,
      "step": 1110
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.1049972930051686,
      "learning_rate": 6.831556722190453e-07,
      "loss": 0.2187,
      "step": 1120
    },
    {
      "epoch": 2.5681818181818183,
      "grad_norm": 0.819930369422315,
      "learning_rate": 6.179571106942466e-07,
      "loss": 0.2059,
      "step": 1130
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.8068522453155903,
      "learning_rate": 5.558227567253832e-07,
      "loss": 0.1974,
      "step": 1140
    },
    {
      "epoch": 2.6136363636363638,
      "grad_norm": 0.8627975251731292,
      "learning_rate": 4.967960586678722e-07,
      "loss": 0.215,
      "step": 1150
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.7571397611134698,
      "learning_rate": 4.4091829180330503e-07,
      "loss": 0.2067,
      "step": 1160
    },
    {
      "epoch": 2.659090909090909,
      "grad_norm": 0.8163877858341596,
      "learning_rate": 3.882285294770938e-07,
      "loss": 0.2185,
      "step": 1170
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 0.847944124408921,
      "learning_rate": 3.3876361577587115e-07,
      "loss": 0.2126,
      "step": 1180
    },
    {
      "epoch": 2.7045454545454546,
      "grad_norm": 0.8609864011531457,
      "learning_rate": 2.9255813976372227e-07,
      "loss": 0.2376,
      "step": 1190
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.8142965279668429,
      "learning_rate": 2.4964441129527337e-07,
      "loss": 0.1971,
      "step": 1200
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.8085909064873231,
      "learning_rate": 2.1005243842255552e-07,
      "loss": 0.2023,
      "step": 1210
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 0.7715524471203066,
      "learning_rate": 1.738099064114368e-07,
      "loss": 0.2122,
      "step": 1220
    },
    {
      "epoch": 2.7954545454545454,
      "grad_norm": 0.7256919162493282,
      "learning_rate": 1.4094215838229176e-07,
      "loss": 0.241,
      "step": 1230
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.7761363095194573,
      "learning_rate": 1.1147217758845752e-07,
      "loss": 0.2025,
      "step": 1240
    },
    {
      "epoch": 2.840909090909091,
      "grad_norm": 0.7416748760573418,
      "learning_rate": 8.542057134485638e-08,
      "loss": 0.219,
      "step": 1250
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 0.8096267555239283,
      "learning_rate": 6.280555661802857e-08,
      "loss": 0.2208,
      "step": 1260
    },
    {
      "epoch": 2.8863636363636362,
      "grad_norm": 0.9092729323776195,
      "learning_rate": 4.3642947287654284e-08,
      "loss": 0.239,
      "step": 1270
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.7872817827279941,
      "learning_rate": 2.7946143088466437e-08,
      "loss": 0.236,
      "step": 1280
    },
    {
      "epoch": 2.9318181818181817,
      "grad_norm": 0.9061945080911546,
      "learning_rate": 1.5726120240288632e-08,
      "loss": 0.1971,
      "step": 1290
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.9803191049167996,
      "learning_rate": 6.991423772753636e-09,
      "loss": 0.2157,
      "step": 1300
    },
    {
      "epoch": 2.9772727272727275,
      "grad_norm": 0.9109787805486621,
      "learning_rate": 1.7481615500691829e-09,
      "loss": 0.2044,
      "step": 1310
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7033421688883779,
      "learning_rate": 0.0,
      "loss": 0.2047,
      "step": 1320
    },
    {
      "epoch": 3.0,
      "step": 1320,
      "total_flos": 148330505830400.0,
      "train_loss": 0.33294462082964,
      "train_runtime": 5380.5167,
      "train_samples_per_second": 1.959,
      "train_steps_per_second": 0.245
    }
  ],
  "logging_steps": 10,
  "max_steps": 1320,
  "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": 148330505830400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}