{
  "best_metric": 3.367271661758423,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03194250349371132,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001597125174685566,
      "grad_norm": 3.151745080947876,
      "learning_rate": 1e-05,
      "loss": 3.3284,
      "step": 1
    },
    {
      "epoch": 0.0001597125174685566,
      "eval_loss": 3.7772867679595947,
      "eval_runtime": 366.9226,
      "eval_samples_per_second": 28.739,
      "eval_steps_per_second": 7.187,
      "step": 1
    },
    {
      "epoch": 0.0003194250349371132,
      "grad_norm": 3.5679922103881836,
      "learning_rate": 2e-05,
      "loss": 3.4465,
      "step": 2
    },
    {
      "epoch": 0.0004791375524056698,
      "grad_norm": 2.74743390083313,
      "learning_rate": 3e-05,
      "loss": 3.5335,
      "step": 3
    },
    {
      "epoch": 0.0006388500698742264,
      "grad_norm": 1.7880760431289673,
      "learning_rate": 4e-05,
      "loss": 3.5333,
      "step": 4
    },
    {
      "epoch": 0.000798562587342783,
      "grad_norm": 1.2010328769683838,
      "learning_rate": 5e-05,
      "loss": 3.5631,
      "step": 5
    },
    {
      "epoch": 0.0009582751048113396,
      "grad_norm": 1.1575998067855835,
      "learning_rate": 6e-05,
      "loss": 3.5508,
      "step": 6
    },
    {
      "epoch": 0.0011179876222798962,
      "grad_norm": 1.1091437339782715,
      "learning_rate": 7e-05,
      "loss": 3.3319,
      "step": 7
    },
    {
      "epoch": 0.0012777001397484527,
      "grad_norm": 1.1966826915740967,
      "learning_rate": 8e-05,
      "loss": 3.3852,
      "step": 8
    },
    {
      "epoch": 0.0014374126572170094,
      "grad_norm": 1.154388666152954,
      "learning_rate": 9e-05,
      "loss": 3.3556,
      "step": 9
    },
    {
      "epoch": 0.001597125174685566,
      "grad_norm": 1.1722689867019653,
      "learning_rate": 0.0001,
      "loss": 3.4343,
      "step": 10
    },
    {
      "epoch": 0.0017568376921541227,
      "grad_norm": 1.1810929775238037,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.3788,
      "step": 11
    },
    {
      "epoch": 0.0019165502096226792,
      "grad_norm": 1.3290044069290161,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.3814,
      "step": 12
    },
    {
      "epoch": 0.002076262727091236,
      "grad_norm": 1.166452407836914,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.4513,
      "step": 13
    },
    {
      "epoch": 0.0022359752445597924,
      "grad_norm": 1.225412368774414,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.4474,
      "step": 14
    },
    {
      "epoch": 0.002395687762028349,
      "grad_norm": 1.1704496145248413,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.3749,
      "step": 15
    },
    {
      "epoch": 0.0025554002794969054,
      "grad_norm": 1.0591427087783813,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.4146,
      "step": 16
    },
    {
      "epoch": 0.0027151127969654624,
      "grad_norm": 1.1226862668991089,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.435,
      "step": 17
    },
    {
      "epoch": 0.002874825314434019,
      "grad_norm": 1.1365058422088623,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.4596,
      "step": 18
    },
    {
      "epoch": 0.0030345378319025754,
      "grad_norm": 1.2042661905288696,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.5043,
      "step": 19
    },
    {
      "epoch": 0.003194250349371132,
      "grad_norm": 1.131988763809204,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.3334,
      "step": 20
    },
    {
      "epoch": 0.0033539628668396884,
      "grad_norm": 1.128745198249817,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.4878,
      "step": 21
    },
    {
      "epoch": 0.0035136753843082453,
      "grad_norm": 1.0882518291473389,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.3931,
      "step": 22
    },
    {
      "epoch": 0.003673387901776802,
      "grad_norm": 1.1464509963989258,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.4223,
      "step": 23
    },
    {
      "epoch": 0.0038331004192453584,
      "grad_norm": 1.2029162645339966,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.438,
      "step": 24
    },
    {
      "epoch": 0.003992812936713915,
      "grad_norm": 1.1562954187393188,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.4619,
      "step": 25
    },
    {
      "epoch": 0.004152525454182472,
      "grad_norm": 1.2155251502990723,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.5448,
      "step": 26
    },
    {
      "epoch": 0.004312237971651028,
      "grad_norm": 1.4336769580841064,
      "learning_rate": 9.803768380684242e-05,
      "loss": 3.3571,
      "step": 27
    },
    {
      "epoch": 0.004471950489119585,
      "grad_norm": 1.2620644569396973,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.5558,
      "step": 28
    },
    {
      "epoch": 0.004631663006588142,
      "grad_norm": 1.2853968143463135,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.5029,
      "step": 29
    },
    {
      "epoch": 0.004791375524056698,
      "grad_norm": 1.2344318628311157,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.3027,
      "step": 30
    },
    {
      "epoch": 0.004951088041525255,
      "grad_norm": 1.2450658082962036,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.4088,
      "step": 31
    },
    {
      "epoch": 0.005110800558993811,
      "grad_norm": 1.2341264486312866,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.5842,
      "step": 32
    },
    {
      "epoch": 0.005270513076462368,
      "grad_norm": 1.1591182947158813,
      "learning_rate": 9.642770192448536e-05,
      "loss": 3.4222,
      "step": 33
    },
    {
      "epoch": 0.005430225593930925,
      "grad_norm": 1.272977352142334,
      "learning_rate": 9.611448774886924e-05,
      "loss": 3.4161,
      "step": 34
    },
    {
      "epoch": 0.005589938111399481,
      "grad_norm": 1.3177355527877808,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.3891,
      "step": 35
    },
    {
      "epoch": 0.005749650628868038,
      "grad_norm": 1.2545990943908691,
      "learning_rate": 9.545032675245813e-05,
      "loss": 3.5182,
      "step": 36
    },
    {
      "epoch": 0.005909363146336594,
      "grad_norm": 1.2635751962661743,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.3449,
      "step": 37
    },
    {
      "epoch": 0.006069075663805151,
      "grad_norm": 1.3663057088851929,
      "learning_rate": 9.473646649103818e-05,
      "loss": 3.4379,
      "step": 38
    },
    {
      "epoch": 0.006228788181273708,
      "grad_norm": 1.4223135709762573,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.5357,
      "step": 39
    },
    {
      "epoch": 0.006388500698742264,
      "grad_norm": 1.3192325830459595,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.5013,
      "step": 40
    },
    {
      "epoch": 0.006548213216210821,
      "grad_norm": 1.394445776939392,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.4873,
      "step": 41
    },
    {
      "epoch": 0.006707925733679377,
      "grad_norm": 1.4524463415145874,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.3287,
      "step": 42
    },
    {
      "epoch": 0.006867638251147934,
      "grad_norm": 1.408828616142273,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.6322,
      "step": 43
    },
    {
      "epoch": 0.007027350768616491,
      "grad_norm": 1.3219882249832153,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.4385,
      "step": 44
    },
    {
      "epoch": 0.007187063286085047,
      "grad_norm": 1.455071210861206,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.5109,
      "step": 45
    },
    {
      "epoch": 0.007346775803553604,
      "grad_norm": 1.4796392917633057,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.4257,
      "step": 46
    },
    {
      "epoch": 0.00750648832102216,
      "grad_norm": 1.6102542877197266,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.542,
      "step": 47
    },
    {
      "epoch": 0.007666200838490717,
      "grad_norm": 1.6678898334503174,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.6093,
      "step": 48
    },
    {
      "epoch": 0.007825913355959273,
      "grad_norm": 1.6260260343551636,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.4118,
      "step": 49
    },
    {
      "epoch": 0.00798562587342783,
      "grad_norm": 1.672386884689331,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.6423,
      "step": 50
    },
    {
      "epoch": 0.00798562587342783,
      "eval_loss": 3.4769773483276367,
      "eval_runtime": 367.2827,
      "eval_samples_per_second": 28.711,
      "eval_steps_per_second": 7.18,
      "step": 50
    },
    {
      "epoch": 0.008145338390896387,
      "grad_norm": 2.1909384727478027,
      "learning_rate": 8.894386393810563e-05,
      "loss": 3.3174,
      "step": 51
    },
    {
      "epoch": 0.008305050908364944,
      "grad_norm": 1.9907581806182861,
      "learning_rate": 8.842005554284296e-05,
      "loss": 3.3028,
      "step": 52
    },
    {
      "epoch": 0.0084647634258335,
      "grad_norm": 1.730931282043457,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.3421,
      "step": 53
    },
    {
      "epoch": 0.008624475943302056,
      "grad_norm": 1.0730434656143188,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.2531,
      "step": 54
    },
    {
      "epoch": 0.008784188460770613,
      "grad_norm": 0.8905346989631653,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.4665,
      "step": 55
    },
    {
      "epoch": 0.00894390097823917,
      "grad_norm": 0.9960197806358337,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.2391,
      "step": 56
    },
    {
      "epoch": 0.009103613495707727,
      "grad_norm": 1.033240556716919,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.2298,
      "step": 57
    },
    {
      "epoch": 0.009263326013176284,
      "grad_norm": 0.9962211847305298,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.3652,
      "step": 58
    },
    {
      "epoch": 0.009423038530644839,
      "grad_norm": 1.0461599826812744,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.384,
      "step": 59
    },
    {
      "epoch": 0.009582751048113396,
      "grad_norm": 1.2479519844055176,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.3278,
      "step": 60
    },
    {
      "epoch": 0.009742463565581953,
      "grad_norm": 1.0600687265396118,
      "learning_rate": 8.32512286056924e-05,
      "loss": 3.4082,
      "step": 61
    },
    {
      "epoch": 0.00990217608305051,
      "grad_norm": 0.9880117774009705,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.2854,
      "step": 62
    },
    {
      "epoch": 0.010061888600519067,
      "grad_norm": 1.0537434816360474,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.3238,
      "step": 63
    },
    {
      "epoch": 0.010221601117987622,
      "grad_norm": 1.0725468397140503,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.3433,
      "step": 64
    },
    {
      "epoch": 0.010381313635456179,
      "grad_norm": 0.9658207297325134,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.2833,
      "step": 65
    },
    {
      "epoch": 0.010541026152924736,
      "grad_norm": 1.2380279302597046,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.263,
      "step": 66
    },
    {
      "epoch": 0.010700738670393293,
      "grad_norm": 1.213842749595642,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.2986,
      "step": 67
    },
    {
      "epoch": 0.01086045118786185,
      "grad_norm": 1.0403034687042236,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.2697,
      "step": 68
    },
    {
      "epoch": 0.011020163705330405,
      "grad_norm": 1.302343726158142,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.4476,
      "step": 69
    },
    {
      "epoch": 0.011179876222798962,
      "grad_norm": 1.2976610660552979,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.2577,
      "step": 70
    },
    {
      "epoch": 0.011339588740267519,
      "grad_norm": 1.0647670030593872,
      "learning_rate": 7.66515864363997e-05,
      "loss": 3.246,
      "step": 71
    },
    {
      "epoch": 0.011499301257736076,
      "grad_norm": 1.1078636646270752,
      "learning_rate": 7.594847868906076e-05,
      "loss": 3.2827,
      "step": 72
    },
    {
      "epoch": 0.011659013775204632,
      "grad_norm": 1.2592577934265137,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.4227,
      "step": 73
    },
    {
      "epoch": 0.011818726292673188,
      "grad_norm": 1.1672693490982056,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.3296,
      "step": 74
    },
    {
      "epoch": 0.011978438810141745,
      "grad_norm": 1.197126030921936,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.3463,
      "step": 75
    },
    {
      "epoch": 0.012138151327610302,
      "grad_norm": 1.1053833961486816,
      "learning_rate": 7.30670581489344e-05,
      "loss": 3.4383,
      "step": 76
    },
    {
      "epoch": 0.012297863845078858,
      "grad_norm": 1.1725811958312988,
      "learning_rate": 7.233044034264034e-05,
      "loss": 3.4708,
      "step": 77
    },
    {
      "epoch": 0.012457576362547415,
      "grad_norm": 1.1621438264846802,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.2999,
      "step": 78
    },
    {
      "epoch": 0.01261728888001597,
      "grad_norm": 1.0912461280822754,
      "learning_rate": 7.083909302476453e-05,
      "loss": 3.3547,
      "step": 79
    },
    {
      "epoch": 0.012777001397484528,
      "grad_norm": 1.1285887956619263,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.3484,
      "step": 80
    },
    {
      "epoch": 0.012936713914953085,
      "grad_norm": 1.1592434644699097,
      "learning_rate": 6.932495846462261e-05,
      "loss": 3.3856,
      "step": 81
    },
    {
      "epoch": 0.013096426432421641,
      "grad_norm": 1.1408761739730835,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.4119,
      "step": 82
    },
    {
      "epoch": 0.013256138949890198,
      "grad_norm": 1.237693428993225,
      "learning_rate": 6.778969234612584e-05,
      "loss": 3.3636,
      "step": 83
    },
    {
      "epoch": 0.013415851467358754,
      "grad_norm": 1.3598599433898926,
      "learning_rate": 6.701465872208216e-05,
      "loss": 3.3473,
      "step": 84
    },
    {
      "epoch": 0.01357556398482731,
      "grad_norm": 1.1378798484802246,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.3653,
      "step": 85
    },
    {
      "epoch": 0.013735276502295867,
      "grad_norm": 1.204046368598938,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.4396,
      "step": 86
    },
    {
      "epoch": 0.013894989019764424,
      "grad_norm": 1.1931564807891846,
      "learning_rate": 6.466250186922325e-05,
      "loss": 3.353,
      "step": 87
    },
    {
      "epoch": 0.014054701537232981,
      "grad_norm": 1.3617382049560547,
      "learning_rate": 6.387014543809223e-05,
      "loss": 3.5504,
      "step": 88
    },
    {
      "epoch": 0.014214414054701537,
      "grad_norm": 1.2841181755065918,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.4855,
      "step": 89
    },
    {
      "epoch": 0.014374126572170094,
      "grad_norm": 1.2569890022277832,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.3152,
      "step": 90
    },
    {
      "epoch": 0.01453383908963865,
      "grad_norm": 1.2988148927688599,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.4175,
      "step": 91
    },
    {
      "epoch": 0.014693551607107207,
      "grad_norm": 1.3015007972717285,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.4868,
      "step": 92
    },
    {
      "epoch": 0.014853264124575764,
      "grad_norm": 1.2875230312347412,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.4556,
      "step": 93
    },
    {
      "epoch": 0.01501297664204432,
      "grad_norm": 1.2617181539535522,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.4646,
      "step": 94
    },
    {
      "epoch": 0.015172689159512876,
      "grad_norm": 1.3132792711257935,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.4019,
      "step": 95
    },
    {
      "epoch": 0.015332401676981433,
      "grad_norm": 1.416114091873169,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.4673,
      "step": 96
    },
    {
      "epoch": 0.01549211419444999,
      "grad_norm": 1.361545443534851,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.5727,
      "step": 97
    },
    {
      "epoch": 0.015651826711918546,
      "grad_norm": 1.4774359464645386,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.3196,
      "step": 98
    },
    {
      "epoch": 0.015811539229387103,
      "grad_norm": 1.755661129951477,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.6677,
      "step": 99
    },
    {
      "epoch": 0.01597125174685566,
      "grad_norm": 1.7422082424163818,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.5913,
      "step": 100
    },
    {
      "epoch": 0.01597125174685566,
      "eval_loss": 3.437983512878418,
      "eval_runtime": 367.4365,
      "eval_samples_per_second": 28.699,
      "eval_steps_per_second": 7.177,
      "step": 100
    },
    {
      "epoch": 0.016130964264324216,
      "grad_norm": 2.563222646713257,
      "learning_rate": 5.330452921628497e-05,
      "loss": 3.1601,
      "step": 101
    },
    {
      "epoch": 0.016290676781792773,
      "grad_norm": 2.3833115100860596,
      "learning_rate": 5.247918773366112e-05,
      "loss": 3.2734,
      "step": 102
    },
    {
      "epoch": 0.01645038929926133,
      "grad_norm": 2.2120771408081055,
      "learning_rate": 5.165316846586541e-05,
      "loss": 3.3793,
      "step": 103
    },
    {
      "epoch": 0.016610101816729887,
      "grad_norm": 1.8844492435455322,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 3.2532,
      "step": 104
    },
    {
      "epoch": 0.016769814334198444,
      "grad_norm": 1.4038431644439697,
      "learning_rate": 5e-05,
      "loss": 3.2878,
      "step": 105
    },
    {
      "epoch": 0.016929526851667,
      "grad_norm": 1.0654053688049316,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.2445,
      "step": 106
    },
    {
      "epoch": 0.017089239369135555,
      "grad_norm": 0.8803927302360535,
      "learning_rate": 4.834683153413459e-05,
      "loss": 3.3826,
      "step": 107
    },
    {
      "epoch": 0.01724895188660411,
      "grad_norm": 0.8809193968772888,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.3263,
      "step": 108
    },
    {
      "epoch": 0.01740866440407267,
      "grad_norm": 0.9295204281806946,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.3115,
      "step": 109
    },
    {
      "epoch": 0.017568376921541225,
      "grad_norm": 0.9930161833763123,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.2609,
      "step": 110
    },
    {
      "epoch": 0.017728089439009782,
      "grad_norm": 1.0246449708938599,
      "learning_rate": 4.504772348747687e-05,
      "loss": 3.3752,
      "step": 111
    },
    {
      "epoch": 0.01788780195647834,
      "grad_norm": 0.9885937571525574,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 3.3546,
      "step": 112
    },
    {
      "epoch": 0.018047514473946896,
      "grad_norm": 0.934032142162323,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 3.4028,
      "step": 113
    },
    {
      "epoch": 0.018207226991415453,
      "grad_norm": 0.9788658618927002,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 3.3554,
      "step": 114
    },
    {
      "epoch": 0.01836693950888401,
      "grad_norm": 0.9676387310028076,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.3169,
      "step": 115
    },
    {
      "epoch": 0.018526652026352567,
      "grad_norm": 1.0396462678909302,
      "learning_rate": 4.095597328339452e-05,
      "loss": 3.2757,
      "step": 116
    },
    {
      "epoch": 0.01868636454382112,
      "grad_norm": 1.0794548988342285,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 3.327,
      "step": 117
    },
    {
      "epoch": 0.018846077061289677,
      "grad_norm": 1.0206615924835205,
      "learning_rate": 3.933501846281267e-05,
      "loss": 3.225,
      "step": 118
    },
    {
      "epoch": 0.019005789578758234,
      "grad_norm": 0.9828562140464783,
      "learning_rate": 3.852880399766243e-05,
      "loss": 3.3342,
      "step": 119
    },
    {
      "epoch": 0.01916550209622679,
      "grad_norm": 1.2915130853652954,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.3889,
      "step": 120
    },
    {
      "epoch": 0.01932521461369535,
      "grad_norm": 1.0610451698303223,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 3.3425,
      "step": 121
    },
    {
      "epoch": 0.019484927131163905,
      "grad_norm": 1.0585017204284668,
      "learning_rate": 3.612985456190778e-05,
      "loss": 3.3319,
      "step": 122
    },
    {
      "epoch": 0.019644639648632462,
      "grad_norm": 1.0622979402542114,
      "learning_rate": 3.533749813077677e-05,
      "loss": 3.527,
      "step": 123
    },
    {
      "epoch": 0.01980435216610102,
      "grad_norm": 1.0423346757888794,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.3608,
      "step": 124
    },
    {
      "epoch": 0.019964064683569576,
      "grad_norm": 1.0512298345565796,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.4576,
      "step": 125
    },
    {
      "epoch": 0.020123777201038133,
      "grad_norm": 1.050781011581421,
      "learning_rate": 3.298534127791785e-05,
      "loss": 3.429,
      "step": 126
    },
    {
      "epoch": 0.020283489718506686,
      "grad_norm": 1.0709890127182007,
      "learning_rate": 3.221030765387417e-05,
      "loss": 3.4985,
      "step": 127
    },
    {
      "epoch": 0.020443202235975243,
      "grad_norm": 1.146832823753357,
      "learning_rate": 3.144013755408895e-05,
      "loss": 3.4954,
      "step": 128
    },
    {
      "epoch": 0.0206029147534438,
      "grad_norm": 1.070890188217163,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 3.3281,
      "step": 129
    },
    {
      "epoch": 0.020762627270912357,
      "grad_norm": 1.0944342613220215,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.4404,
      "step": 130
    },
    {
      "epoch": 0.020922339788380914,
      "grad_norm": 1.1096227169036865,
      "learning_rate": 2.916090697523549e-05,
      "loss": 3.4476,
      "step": 131
    },
    {
      "epoch": 0.02108205230584947,
      "grad_norm": 1.2392953634262085,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.4012,
      "step": 132
    },
    {
      "epoch": 0.021241764823318028,
      "grad_norm": 1.1994134187698364,
      "learning_rate": 2.766955965735968e-05,
      "loss": 3.3475,
      "step": 133
    },
    {
      "epoch": 0.021401477340786585,
      "grad_norm": 1.1271154880523682,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.1871,
      "step": 134
    },
    {
      "epoch": 0.021561189858255142,
      "grad_norm": 1.1170655488967896,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.2844,
      "step": 135
    },
    {
      "epoch": 0.0217209023757237,
      "grad_norm": 1.148924469947815,
      "learning_rate": 2.547882480847461e-05,
      "loss": 3.5097,
      "step": 136
    },
    {
      "epoch": 0.021880614893192252,
      "grad_norm": 1.1717835664749146,
      "learning_rate": 2.476172311325783e-05,
      "loss": 3.5366,
      "step": 137
    },
    {
      "epoch": 0.02204032741066081,
      "grad_norm": 1.1314111948013306,
      "learning_rate": 2.405152131093926e-05,
      "loss": 3.2612,
      "step": 138
    },
    {
      "epoch": 0.022200039928129366,
      "grad_norm": 1.1890403032302856,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 3.4438,
      "step": 139
    },
    {
      "epoch": 0.022359752445597923,
      "grad_norm": 1.1819334030151367,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 3.4172,
      "step": 140
    },
    {
      "epoch": 0.02251946496306648,
      "grad_norm": 1.2623519897460938,
      "learning_rate": 2.196424713241637e-05,
      "loss": 3.4651,
      "step": 141
    },
    {
      "epoch": 0.022679177480535037,
      "grad_norm": 1.2643638849258423,
      "learning_rate": 2.128356686585282e-05,
      "loss": 3.4054,
      "step": 142
    },
    {
      "epoch": 0.022838889998003594,
      "grad_norm": 1.3270361423492432,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.5708,
      "step": 143
    },
    {
      "epoch": 0.02299860251547215,
      "grad_norm": 1.2927286624908447,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 3.5297,
      "step": 144
    },
    {
      "epoch": 0.023158315032940708,
      "grad_norm": 1.3989403247833252,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.3454,
      "step": 145
    },
    {
      "epoch": 0.023318027550409265,
      "grad_norm": 1.3746222257614136,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.3294,
      "step": 146
    },
    {
      "epoch": 0.02347774006787782,
      "grad_norm": 1.6690480709075928,
      "learning_rate": 1.800157297483417e-05,
      "loss": 3.4948,
      "step": 147
    },
    {
      "epoch": 0.023637452585346375,
      "grad_norm": 1.5143362283706665,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 3.5697,
      "step": 148
    },
    {
      "epoch": 0.023797165102814932,
      "grad_norm": 1.5836552381515503,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 3.5201,
      "step": 149
    },
    {
      "epoch": 0.02395687762028349,
      "grad_norm": 1.9442321062088013,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.5552,
      "step": 150
    },
    {
      "epoch": 0.02395687762028349,
      "eval_loss": 3.3761205673217773,
      "eval_runtime": 367.4841,
      "eval_samples_per_second": 28.695,
      "eval_steps_per_second": 7.176,
      "step": 150
    },
    {
      "epoch": 0.024116590137752046,
      "grad_norm": 1.2058228254318237,
      "learning_rate": 1.553232954407171e-05,
      "loss": 3.0102,
      "step": 151
    },
    {
      "epoch": 0.024276302655220603,
      "grad_norm": 1.277240514755249,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 3.1333,
      "step": 152
    },
    {
      "epoch": 0.02443601517268916,
      "grad_norm": 1.2933510541915894,
      "learning_rate": 1.435357758543015e-05,
      "loss": 3.3031,
      "step": 153
    },
    {
      "epoch": 0.024595727690157717,
      "grad_norm": 1.239011287689209,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 3.3346,
      "step": 154
    },
    {
      "epoch": 0.024755440207626274,
      "grad_norm": 1.0706086158752441,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.2335,
      "step": 155
    },
    {
      "epoch": 0.02491515272509483,
      "grad_norm": 1.1139898300170898,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 3.3206,
      "step": 156
    },
    {
      "epoch": 0.025074865242563384,
      "grad_norm": 1.0480912923812866,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 3.3239,
      "step": 157
    },
    {
      "epoch": 0.02523457776003194,
      "grad_norm": 0.9668595194816589,
      "learning_rate": 1.157994445715706e-05,
      "loss": 3.3882,
      "step": 158
    },
    {
      "epoch": 0.025394290277500498,
      "grad_norm": 0.977703869342804,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 3.1243,
      "step": 159
    },
    {
      "epoch": 0.025554002794969055,
      "grad_norm": 0.9336478114128113,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.3062,
      "step": 160
    },
    {
      "epoch": 0.025713715312437612,
      "grad_norm": 0.9409486651420593,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 3.3489,
      "step": 161
    },
    {
      "epoch": 0.02587342782990617,
      "grad_norm": 0.9133581519126892,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.3205,
      "step": 162
    },
    {
      "epoch": 0.026033140347374726,
      "grad_norm": 0.8993477821350098,
      "learning_rate": 9.068759265665384e-06,
      "loss": 3.3535,
      "step": 163
    },
    {
      "epoch": 0.026192852864843283,
      "grad_norm": 0.8666549921035767,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.3269,
      "step": 164
    },
    {
      "epoch": 0.02635256538231184,
      "grad_norm": 0.902008593082428,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.2821,
      "step": 165
    },
    {
      "epoch": 0.026512277899780397,
      "grad_norm": 0.898577094078064,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.3805,
      "step": 166
    },
    {
      "epoch": 0.02667199041724895,
      "grad_norm": 0.971285879611969,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.2937,
      "step": 167
    },
    {
      "epoch": 0.026831702934717507,
      "grad_norm": 0.9684900641441345,
      "learning_rate": 6.837175952121306e-06,
      "loss": 3.3841,
      "step": 168
    },
    {
      "epoch": 0.026991415452186064,
      "grad_norm": 0.964451014995575,
      "learning_rate": 6.425787818636131e-06,
      "loss": 3.3197,
      "step": 169
    },
    {
      "epoch": 0.02715112796965462,
      "grad_norm": 0.9131456017494202,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.2402,
      "step": 170
    },
    {
      "epoch": 0.027310840487123178,
      "grad_norm": 0.9907987713813782,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 3.3017,
      "step": 171
    },
    {
      "epoch": 0.027470553004591735,
      "grad_norm": 0.9800459742546082,
      "learning_rate": 5.263533508961827e-06,
      "loss": 3.2269,
      "step": 172
    },
    {
      "epoch": 0.027630265522060292,
      "grad_norm": 0.9744011759757996,
      "learning_rate": 4.900438493352055e-06,
      "loss": 3.3189,
      "step": 173
    },
    {
      "epoch": 0.02778997803952885,
      "grad_norm": 1.011372447013855,
      "learning_rate": 4.549673247541875e-06,
      "loss": 3.3501,
      "step": 174
    },
    {
      "epoch": 0.027949690556997406,
      "grad_norm": 1.0420602560043335,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.3644,
      "step": 175
    },
    {
      "epoch": 0.028109403074465963,
      "grad_norm": 1.0812755823135376,
      "learning_rate": 3.885512251130763e-06,
      "loss": 3.473,
      "step": 176
    },
    {
      "epoch": 0.028269115591934516,
      "grad_norm": 1.1200363636016846,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 3.3164,
      "step": 177
    },
    {
      "epoch": 0.028428828109403073,
      "grad_norm": 1.0469410419464111,
      "learning_rate": 3.271776770026963e-06,
      "loss": 3.3273,
      "step": 178
    },
    {
      "epoch": 0.02858854062687163,
      "grad_norm": 1.0869914293289185,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 3.3992,
      "step": 179
    },
    {
      "epoch": 0.028748253144340187,
      "grad_norm": 1.0805079936981201,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.4053,
      "step": 180
    },
    {
      "epoch": 0.028907965661808744,
      "grad_norm": 1.1055196523666382,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.5341,
      "step": 181
    },
    {
      "epoch": 0.0290676781792773,
      "grad_norm": 1.0971072912216187,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 3.4487,
      "step": 182
    },
    {
      "epoch": 0.029227390696745858,
      "grad_norm": 1.0869406461715698,
      "learning_rate": 1.962316193157593e-06,
      "loss": 3.227,
      "step": 183
    },
    {
      "epoch": 0.029387103214214415,
      "grad_norm": 1.1751338243484497,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 3.5124,
      "step": 184
    },
    {
      "epoch": 0.02954681573168297,
      "grad_norm": 1.1158000230789185,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.2949,
      "step": 185
    },
    {
      "epoch": 0.02970652824915153,
      "grad_norm": 1.1690402030944824,
      "learning_rate": 1.333670137599713e-06,
      "loss": 3.3323,
      "step": 186
    },
    {
      "epoch": 0.029866240766620082,
      "grad_norm": 1.155377984046936,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 3.2378,
      "step": 187
    },
    {
      "epoch": 0.03002595328408864,
      "grad_norm": 1.2173762321472168,
      "learning_rate": 9.810017062595322e-07,
      "loss": 3.3497,
      "step": 188
    },
    {
      "epoch": 0.030185665801557196,
      "grad_norm": 1.2455633878707886,
      "learning_rate": 8.247462563808817e-07,
      "loss": 3.3897,
      "step": 189
    },
    {
      "epoch": 0.030345378319025753,
      "grad_norm": 1.1714810132980347,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.3968,
      "step": 190
    },
    {
      "epoch": 0.03050509083649431,
      "grad_norm": 1.304261326789856,
      "learning_rate": 5.526064699265753e-07,
      "loss": 3.4113,
      "step": 191
    },
    {
      "epoch": 0.030664803353962867,
      "grad_norm": 1.3062227964401245,
      "learning_rate": 4.367965336512403e-07,
      "loss": 3.454,
      "step": 192
    },
    {
      "epoch": 0.030824515871431424,
      "grad_norm": 1.2830106019973755,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 3.4066,
      "step": 193
    },
    {
      "epoch": 0.03098422838889998,
      "grad_norm": 1.3283530473709106,
      "learning_rate": 2.458548727494292e-07,
      "loss": 3.5061,
      "step": 194
    },
    {
      "epoch": 0.031143940906368538,
      "grad_norm": 1.335413932800293,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.3675,
      "step": 195
    },
    {
      "epoch": 0.03130365342383709,
      "grad_norm": 1.4175186157226562,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 3.2426,
      "step": 196
    },
    {
      "epoch": 0.03146336594130565,
      "grad_norm": 1.4368746280670166,
      "learning_rate": 6.150154258476315e-08,
      "loss": 3.4478,
      "step": 197
    },
    {
      "epoch": 0.031623078458774205,
      "grad_norm": 1.5382282733917236,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.6388,
      "step": 198
    },
    {
      "epoch": 0.031782790976242765,
      "grad_norm": 1.64222252368927,
      "learning_rate": 6.834750376549792e-09,
      "loss": 3.4053,
      "step": 199
    },
    {
      "epoch": 0.03194250349371132,
      "grad_norm": 1.9791591167449951,
      "learning_rate": 0.0,
      "loss": 3.6244,
      "step": 200
    },
    {
      "epoch": 0.03194250349371132,
      "eval_loss": 3.367271661758423,
      "eval_runtime": 367.5568,
      "eval_samples_per_second": 28.689,
      "eval_steps_per_second": 7.174,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.111678115387802e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}