{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 338,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002962962962962963,
      "grad_norm": 23.6448917388916,
      "learning_rate": 0.0,
      "loss": 1.3412,
      "step": 1
    },
    {
      "epoch": 0.005925925925925926,
      "grad_norm": 25.21849250793457,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5497,
      "step": 2
    },
    {
      "epoch": 0.008888888888888889,
      "grad_norm": 21.700353622436523,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3551,
      "step": 3
    },
    {
      "epoch": 0.011851851851851851,
      "grad_norm": 17.531282424926758,
      "learning_rate": 6e-06,
      "loss": 0.9851,
      "step": 4
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 15.536476135253906,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7603,
      "step": 5
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 12.40047550201416,
      "learning_rate": 1e-05,
      "loss": 0.7298,
      "step": 6
    },
    {
      "epoch": 0.02074074074074074,
      "grad_norm": 8.99738883972168,
      "learning_rate": 9.96996996996997e-06,
      "loss": 0.5801,
      "step": 7
    },
    {
      "epoch": 0.023703703703703703,
      "grad_norm": 5.11964225769043,
      "learning_rate": 9.93993993993994e-06,
      "loss": 0.3985,
      "step": 8
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 4.69280481338501,
      "learning_rate": 9.90990990990991e-06,
      "loss": 0.4136,
      "step": 9
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 5.12566614151001,
      "learning_rate": 9.879879879879881e-06,
      "loss": 0.4577,
      "step": 10
    },
    {
      "epoch": 0.03259259259259259,
      "grad_norm": 3.3431992530822754,
      "learning_rate": 9.849849849849851e-06,
      "loss": 0.3142,
      "step": 11
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 3.8473381996154785,
      "learning_rate": 9.81981981981982e-06,
      "loss": 0.4053,
      "step": 12
    },
    {
      "epoch": 0.03851851851851852,
      "grad_norm": 2.717677354812622,
      "learning_rate": 9.78978978978979e-06,
      "loss": 0.2511,
      "step": 13
    },
    {
      "epoch": 0.04148148148148148,
      "grad_norm": 3.746281623840332,
      "learning_rate": 9.75975975975976e-06,
      "loss": 0.4057,
      "step": 14
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 3.172826051712036,
      "learning_rate": 9.729729729729732e-06,
      "loss": 0.275,
      "step": 15
    },
    {
      "epoch": 0.047407407407407405,
      "grad_norm": 3.4232017993927,
      "learning_rate": 9.699699699699701e-06,
      "loss": 0.3194,
      "step": 16
    },
    {
      "epoch": 0.05037037037037037,
      "grad_norm": 3.5079922676086426,
      "learning_rate": 9.669669669669671e-06,
      "loss": 0.323,
      "step": 17
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 2.982982635498047,
      "learning_rate": 9.63963963963964e-06,
      "loss": 0.1902,
      "step": 18
    },
    {
      "epoch": 0.056296296296296296,
      "grad_norm": 3.6872525215148926,
      "learning_rate": 9.60960960960961e-06,
      "loss": 0.3002,
      "step": 19
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 3.6152830123901367,
      "learning_rate": 9.57957957957958e-06,
      "loss": 0.315,
      "step": 20
    },
    {
      "epoch": 0.06222222222222222,
      "grad_norm": 2.864837408065796,
      "learning_rate": 9.54954954954955e-06,
      "loss": 0.1857,
      "step": 21
    },
    {
      "epoch": 0.06518518518518518,
      "grad_norm": 4.080569267272949,
      "learning_rate": 9.51951951951952e-06,
      "loss": 0.2901,
      "step": 22
    },
    {
      "epoch": 0.06814814814814815,
      "grad_norm": 3.539252758026123,
      "learning_rate": 9.489489489489491e-06,
      "loss": 0.309,
      "step": 23
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 3.7430624961853027,
      "learning_rate": 9.45945945945946e-06,
      "loss": 0.3323,
      "step": 24
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 3.128300666809082,
      "learning_rate": 9.42942942942943e-06,
      "loss": 0.1996,
      "step": 25
    },
    {
      "epoch": 0.07703703703703704,
      "grad_norm": 3.4212372303009033,
      "learning_rate": 9.3993993993994e-06,
      "loss": 0.2669,
      "step": 26
    },
    {
      "epoch": 0.08,
      "grad_norm": 4.060975074768066,
      "learning_rate": 9.36936936936937e-06,
      "loss": 0.3153,
      "step": 27
    },
    {
      "epoch": 0.08296296296296296,
      "grad_norm": 3.2724785804748535,
      "learning_rate": 9.339339339339341e-06,
      "loss": 0.3226,
      "step": 28
    },
    {
      "epoch": 0.08592592592592592,
      "grad_norm": 2.9977054595947266,
      "learning_rate": 9.30930930930931e-06,
      "loss": 0.2452,
      "step": 29
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 2.941364049911499,
      "learning_rate": 9.27927927927928e-06,
      "loss": 0.2119,
      "step": 30
    },
    {
      "epoch": 0.09185185185185185,
      "grad_norm": 2.4220614433288574,
      "learning_rate": 9.24924924924925e-06,
      "loss": 0.153,
      "step": 31
    },
    {
      "epoch": 0.09481481481481481,
      "grad_norm": 1.8197813034057617,
      "learning_rate": 9.21921921921922e-06,
      "loss": 0.102,
      "step": 32
    },
    {
      "epoch": 0.09777777777777778,
      "grad_norm": 2.3070192337036133,
      "learning_rate": 9.189189189189191e-06,
      "loss": 0.1494,
      "step": 33
    },
    {
      "epoch": 0.10074074074074074,
      "grad_norm": 2.744832754135132,
      "learning_rate": 9.15915915915916e-06,
      "loss": 0.2092,
      "step": 34
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 3.1204354763031006,
      "learning_rate": 9.129129129129129e-06,
      "loss": 0.2833,
      "step": 35
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 2.9139583110809326,
      "learning_rate": 9.0990990990991e-06,
      "loss": 0.2014,
      "step": 36
    },
    {
      "epoch": 0.10962962962962963,
      "grad_norm": 3.1219091415405273,
      "learning_rate": 9.06906906906907e-06,
      "loss": 0.2561,
      "step": 37
    },
    {
      "epoch": 0.11259259259259259,
      "grad_norm": 2.8254106044769287,
      "learning_rate": 9.03903903903904e-06,
      "loss": 0.2356,
      "step": 38
    },
    {
      "epoch": 0.11555555555555555,
      "grad_norm": 2.361168384552002,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.1437,
      "step": 39
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.241278886795044,
      "learning_rate": 8.97897897897898e-06,
      "loss": 0.1636,
      "step": 40
    },
    {
      "epoch": 0.12148148148148148,
      "grad_norm": 2.828160047531128,
      "learning_rate": 8.94894894894895e-06,
      "loss": 0.2143,
      "step": 41
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 3.3407044410705566,
      "learning_rate": 8.91891891891892e-06,
      "loss": 0.2857,
      "step": 42
    },
    {
      "epoch": 0.1274074074074074,
      "grad_norm": 2.013388156890869,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1207,
      "step": 43
    },
    {
      "epoch": 0.13037037037037036,
      "grad_norm": 2.393733501434326,
      "learning_rate": 8.85885885885886e-06,
      "loss": 0.1583,
      "step": 44
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 2.9230847358703613,
      "learning_rate": 8.82882882882883e-06,
      "loss": 0.2329,
      "step": 45
    },
    {
      "epoch": 0.1362962962962963,
      "grad_norm": 3.1788580417633057,
      "learning_rate": 8.798798798798799e-06,
      "loss": 0.2574,
      "step": 46
    },
    {
      "epoch": 0.13925925925925925,
      "grad_norm": 4.030456066131592,
      "learning_rate": 8.768768768768769e-06,
      "loss": 0.3448,
      "step": 47
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 2.2144923210144043,
      "learning_rate": 8.738738738738739e-06,
      "loss": 0.132,
      "step": 48
    },
    {
      "epoch": 0.1451851851851852,
      "grad_norm": 2.694098711013794,
      "learning_rate": 8.70870870870871e-06,
      "loss": 0.1822,
      "step": 49
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.9586241245269775,
      "learning_rate": 8.67867867867868e-06,
      "loss": 0.1487,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "eval_loss": 0.18576253950595856,
      "eval_runtime": 20.3032,
      "eval_samples_per_second": 29.552,
      "eval_steps_per_second": 14.776,
      "step": 50
    },
    {
      "epoch": 0.1511111111111111,
      "grad_norm": 3.3830959796905518,
      "learning_rate": 8.64864864864865e-06,
      "loss": 0.2566,
      "step": 51
    },
    {
      "epoch": 0.15407407407407409,
      "grad_norm": 2.820603609085083,
      "learning_rate": 8.618618618618619e-06,
      "loss": 0.2256,
      "step": 52
    },
    {
      "epoch": 0.15703703703703703,
      "grad_norm": 3.0057480335235596,
      "learning_rate": 8.588588588588589e-06,
      "loss": 0.2703,
      "step": 53
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.1539433002471924,
      "learning_rate": 8.55855855855856e-06,
      "loss": 0.2188,
      "step": 54
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 1.9106528759002686,
      "learning_rate": 8.52852852852853e-06,
      "loss": 0.1165,
      "step": 55
    },
    {
      "epoch": 0.16592592592592592,
      "grad_norm": 2.8492887020111084,
      "learning_rate": 8.4984984984985e-06,
      "loss": 0.1908,
      "step": 56
    },
    {
      "epoch": 0.1688888888888889,
      "grad_norm": 2.416990280151367,
      "learning_rate": 8.46846846846847e-06,
      "loss": 0.1613,
      "step": 57
    },
    {
      "epoch": 0.17185185185185184,
      "grad_norm": 2.108140230178833,
      "learning_rate": 8.438438438438439e-06,
      "loss": 0.1356,
      "step": 58
    },
    {
      "epoch": 0.1748148148148148,
      "grad_norm": 2.7550833225250244,
      "learning_rate": 8.408408408408409e-06,
      "loss": 0.2148,
      "step": 59
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.472651481628418,
      "learning_rate": 8.378378378378378e-06,
      "loss": 0.1968,
      "step": 60
    },
    {
      "epoch": 0.18074074074074073,
      "grad_norm": 2.4181461334228516,
      "learning_rate": 8.348348348348348e-06,
      "loss": 0.1685,
      "step": 61
    },
    {
      "epoch": 0.1837037037037037,
      "grad_norm": 2.0165748596191406,
      "learning_rate": 8.31831831831832e-06,
      "loss": 0.132,
      "step": 62
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 2.7900800704956055,
      "learning_rate": 8.288288288288289e-06,
      "loss": 0.2573,
      "step": 63
    },
    {
      "epoch": 0.18962962962962962,
      "grad_norm": 2.0542004108428955,
      "learning_rate": 8.258258258258259e-06,
      "loss": 0.1632,
      "step": 64
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 2.959893226623535,
      "learning_rate": 8.228228228228229e-06,
      "loss": 0.206,
      "step": 65
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 2.6163578033447266,
      "learning_rate": 8.198198198198198e-06,
      "loss": 0.1735,
      "step": 66
    },
    {
      "epoch": 0.1985185185185185,
      "grad_norm": 2.6444766521453857,
      "learning_rate": 8.16816816816817e-06,
      "loss": 0.2348,
      "step": 67
    },
    {
      "epoch": 0.20148148148148148,
      "grad_norm": 3.77386474609375,
      "learning_rate": 8.13813813813814e-06,
      "loss": 0.3072,
      "step": 68
    },
    {
      "epoch": 0.20444444444444446,
      "grad_norm": 3.037660598754883,
      "learning_rate": 8.108108108108109e-06,
      "loss": 0.2266,
      "step": 69
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 1.9209868907928467,
      "learning_rate": 8.078078078078079e-06,
      "loss": 0.1258,
      "step": 70
    },
    {
      "epoch": 0.21037037037037037,
      "grad_norm": 3.046133279800415,
      "learning_rate": 8.048048048048048e-06,
      "loss": 0.2142,
      "step": 71
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 2.759441375732422,
      "learning_rate": 8.018018018018018e-06,
      "loss": 0.2165,
      "step": 72
    },
    {
      "epoch": 0.2162962962962963,
      "grad_norm": 2.4459850788116455,
      "learning_rate": 7.987987987987988e-06,
      "loss": 0.1517,
      "step": 73
    },
    {
      "epoch": 0.21925925925925926,
      "grad_norm": 2.544855833053589,
      "learning_rate": 7.95795795795796e-06,
      "loss": 0.1262,
      "step": 74
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 2.1991183757781982,
      "learning_rate": 7.927927927927929e-06,
      "loss": 0.1455,
      "step": 75
    },
    {
      "epoch": 0.22518518518518518,
      "grad_norm": 2.5187621116638184,
      "learning_rate": 7.897897897897899e-06,
      "loss": 0.1897,
      "step": 76
    },
    {
      "epoch": 0.22814814814814816,
      "grad_norm": 2.9365651607513428,
      "learning_rate": 7.867867867867868e-06,
      "loss": 0.2555,
      "step": 77
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 2.8094255924224854,
      "learning_rate": 7.837837837837838e-06,
      "loss": 0.1971,
      "step": 78
    },
    {
      "epoch": 0.23407407407407407,
      "grad_norm": 2.139948606491089,
      "learning_rate": 7.807807807807808e-06,
      "loss": 0.1451,
      "step": 79
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 2.469129800796509,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.1928,
      "step": 80
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.1688756942749023,
      "learning_rate": 7.747747747747749e-06,
      "loss": 0.183,
      "step": 81
    },
    {
      "epoch": 0.24296296296296296,
      "grad_norm": 2.5731360912323,
      "learning_rate": 7.717717717717719e-06,
      "loss": 0.1505,
      "step": 82
    },
    {
      "epoch": 0.24592592592592594,
      "grad_norm": 1.8909518718719482,
      "learning_rate": 7.687687687687688e-06,
      "loss": 0.1299,
      "step": 83
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 2.420177459716797,
      "learning_rate": 7.657657657657658e-06,
      "loss": 0.1629,
      "step": 84
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 2.6778945922851562,
      "learning_rate": 7.6276276276276285e-06,
      "loss": 0.2,
      "step": 85
    },
    {
      "epoch": 0.2548148148148148,
      "grad_norm": 2.0715274810791016,
      "learning_rate": 7.597597597597598e-06,
      "loss": 0.1821,
      "step": 86
    },
    {
      "epoch": 0.2577777777777778,
      "grad_norm": 3.1410930156707764,
      "learning_rate": 7.567567567567569e-06,
      "loss": 0.2664,
      "step": 87
    },
    {
      "epoch": 0.2607407407407407,
      "grad_norm": 2.9329373836517334,
      "learning_rate": 7.5375375375375385e-06,
      "loss": 0.2469,
      "step": 88
    },
    {
      "epoch": 0.2637037037037037,
      "grad_norm": 2.078895092010498,
      "learning_rate": 7.507507507507507e-06,
      "loss": 0.1374,
      "step": 89
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.71140718460083,
      "learning_rate": 7.477477477477479e-06,
      "loss": 0.1793,
      "step": 90
    },
    {
      "epoch": 0.2696296296296296,
      "grad_norm": 2.4415054321289062,
      "learning_rate": 7.447447447447448e-06,
      "loss": 0.2277,
      "step": 91
    },
    {
      "epoch": 0.2725925925925926,
      "grad_norm": 1.975329041481018,
      "learning_rate": 7.417417417417418e-06,
      "loss": 0.1382,
      "step": 92
    },
    {
      "epoch": 0.27555555555555555,
      "grad_norm": 1.9105868339538574,
      "learning_rate": 7.387387387387388e-06,
      "loss": 0.1127,
      "step": 93
    },
    {
      "epoch": 0.2785185185185185,
      "grad_norm": 3.2444419860839844,
      "learning_rate": 7.3573573573573575e-06,
      "loss": 0.2851,
      "step": 94
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 2.214055299758911,
      "learning_rate": 7.327327327327328e-06,
      "loss": 0.177,
      "step": 95
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 2.7256484031677246,
      "learning_rate": 7.297297297297298e-06,
      "loss": 0.2114,
      "step": 96
    },
    {
      "epoch": 0.2874074074074074,
      "grad_norm": 2.5599944591522217,
      "learning_rate": 7.267267267267268e-06,
      "loss": 0.2251,
      "step": 97
    },
    {
      "epoch": 0.2903703703703704,
      "grad_norm": 2.5365970134735107,
      "learning_rate": 7.237237237237238e-06,
      "loss": 0.1914,
      "step": 98
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 3.165980577468872,
      "learning_rate": 7.207207207207208e-06,
      "loss": 0.2813,
      "step": 99
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.4388861656188965,
      "learning_rate": 7.177177177177178e-06,
      "loss": 0.2149,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 0.16989581286907196,
      "eval_runtime": 18.8414,
      "eval_samples_per_second": 31.845,
      "eval_steps_per_second": 15.922,
      "step": 100
    },
    {
      "epoch": 0.2992592592592593,
      "grad_norm": 1.9628535509109497,
      "learning_rate": 7.147147147147148e-06,
      "loss": 0.1214,
      "step": 101
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 2.5807762145996094,
      "learning_rate": 7.117117117117117e-06,
      "loss": 0.1882,
      "step": 102
    },
    {
      "epoch": 0.30518518518518517,
      "grad_norm": 3.405649423599243,
      "learning_rate": 7.087087087087087e-06,
      "loss": 0.2914,
      "step": 103
    },
    {
      "epoch": 0.30814814814814817,
      "grad_norm": 2.339322328567505,
      "learning_rate": 7.057057057057057e-06,
      "loss": 0.1674,
      "step": 104
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 2.6483521461486816,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.2551,
      "step": 105
    },
    {
      "epoch": 0.31407407407407406,
      "grad_norm": 1.7597674131393433,
      "learning_rate": 6.996996996996997e-06,
      "loss": 0.1298,
      "step": 106
    },
    {
      "epoch": 0.31703703703703706,
      "grad_norm": 2.4604454040527344,
      "learning_rate": 6.966966966966967e-06,
      "loss": 0.1509,
      "step": 107
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.053154706954956,
      "learning_rate": 6.936936936936938e-06,
      "loss": 0.1626,
      "step": 108
    },
    {
      "epoch": 0.32296296296296295,
      "grad_norm": 2.71750807762146,
      "learning_rate": 6.906906906906907e-06,
      "loss": 0.2174,
      "step": 109
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 2.4760804176330566,
      "learning_rate": 6.876876876876878e-06,
      "loss": 0.1846,
      "step": 110
    },
    {
      "epoch": 0.3288888888888889,
      "grad_norm": 3.0783157348632812,
      "learning_rate": 6.846846846846848e-06,
      "loss": 0.2468,
      "step": 111
    },
    {
      "epoch": 0.33185185185185184,
      "grad_norm": 2.0718297958374023,
      "learning_rate": 6.816816816816817e-06,
      "loss": 0.1704,
      "step": 112
    },
    {
      "epoch": 0.3348148148148148,
      "grad_norm": 2.2977042198181152,
      "learning_rate": 6.786786786786788e-06,
      "loss": 0.1659,
      "step": 113
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 3.082481622695923,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.2335,
      "step": 114
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 2.5278804302215576,
      "learning_rate": 6.726726726726728e-06,
      "loss": 0.1671,
      "step": 115
    },
    {
      "epoch": 0.3437037037037037,
      "grad_norm": 3.8675026893615723,
      "learning_rate": 6.696696696696697e-06,
      "loss": 0.3088,
      "step": 116
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 2.7119133472442627,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1754,
      "step": 117
    },
    {
      "epoch": 0.3496296296296296,
      "grad_norm": 2.8066439628601074,
      "learning_rate": 6.636636636636637e-06,
      "loss": 0.234,
      "step": 118
    },
    {
      "epoch": 0.35259259259259257,
      "grad_norm": 2.693225860595703,
      "learning_rate": 6.606606606606607e-06,
      "loss": 0.2357,
      "step": 119
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 2.4291188716888428,
      "learning_rate": 6.5765765765765775e-06,
      "loss": 0.1888,
      "step": 120
    },
    {
      "epoch": 0.3585185185185185,
      "grad_norm": 2.3033447265625,
      "learning_rate": 6.546546546546547e-06,
      "loss": 0.1912,
      "step": 121
    },
    {
      "epoch": 0.36148148148148146,
      "grad_norm": 2.0717411041259766,
      "learning_rate": 6.516516516516517e-06,
      "loss": 0.1571,
      "step": 122
    },
    {
      "epoch": 0.36444444444444446,
      "grad_norm": 2.5996158123016357,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.1688,
      "step": 123
    },
    {
      "epoch": 0.3674074074074074,
      "grad_norm": 2.878352165222168,
      "learning_rate": 6.456456456456457e-06,
      "loss": 0.2685,
      "step": 124
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.758709669113159,
      "learning_rate": 6.426426426426427e-06,
      "loss": 0.1808,
      "step": 125
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 2.755650520324707,
      "learning_rate": 6.396396396396397e-06,
      "loss": 0.2342,
      "step": 126
    },
    {
      "epoch": 0.3762962962962963,
      "grad_norm": 2.2327988147735596,
      "learning_rate": 6.366366366366366e-06,
      "loss": 0.1567,
      "step": 127
    },
    {
      "epoch": 0.37925925925925924,
      "grad_norm": 1.7839659452438354,
      "learning_rate": 6.336336336336338e-06,
      "loss": 0.1241,
      "step": 128
    },
    {
      "epoch": 0.38222222222222224,
      "grad_norm": 2.351475715637207,
      "learning_rate": 6.3063063063063065e-06,
      "loss": 0.1461,
      "step": 129
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 2.262983798980713,
      "learning_rate": 6.276276276276276e-06,
      "loss": 0.1303,
      "step": 130
    },
    {
      "epoch": 0.38814814814814813,
      "grad_norm": 2.712712526321411,
      "learning_rate": 6.246246246246247e-06,
      "loss": 0.2098,
      "step": 131
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 2.06648588180542,
      "learning_rate": 6.2162162162162164e-06,
      "loss": 0.1636,
      "step": 132
    },
    {
      "epoch": 0.3940740740740741,
      "grad_norm": 2.826694965362549,
      "learning_rate": 6.186186186186187e-06,
      "loss": 0.2327,
      "step": 133
    },
    {
      "epoch": 0.397037037037037,
      "grad_norm": 2.7293148040771484,
      "learning_rate": 6.156156156156157e-06,
      "loss": 0.2157,
      "step": 134
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.3280563354492188,
      "learning_rate": 6.126126126126126e-06,
      "loss": 0.178,
      "step": 135
    },
    {
      "epoch": 0.40296296296296297,
      "grad_norm": 2.1383044719696045,
      "learning_rate": 6.096096096096097e-06,
      "loss": 0.1478,
      "step": 136
    },
    {
      "epoch": 0.4059259259259259,
      "grad_norm": 2.0660064220428467,
      "learning_rate": 6.066066066066067e-06,
      "loss": 0.106,
      "step": 137
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 2.4490394592285156,
      "learning_rate": 6.036036036036037e-06,
      "loss": 0.1639,
      "step": 138
    },
    {
      "epoch": 0.41185185185185186,
      "grad_norm": 2.6293816566467285,
      "learning_rate": 6.006006006006007e-06,
      "loss": 0.1926,
      "step": 139
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 3.3421478271484375,
      "learning_rate": 5.975975975975976e-06,
      "loss": 0.2743,
      "step": 140
    },
    {
      "epoch": 0.4177777777777778,
      "grad_norm": 2.500579833984375,
      "learning_rate": 5.945945945945947e-06,
      "loss": 0.2181,
      "step": 141
    },
    {
      "epoch": 0.42074074074074075,
      "grad_norm": 2.0814573764801025,
      "learning_rate": 5.915915915915916e-06,
      "loss": 0.1347,
      "step": 142
    },
    {
      "epoch": 0.4237037037037037,
      "grad_norm": 2.848323345184326,
      "learning_rate": 5.885885885885886e-06,
      "loss": 0.2478,
      "step": 143
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 2.7516703605651855,
      "learning_rate": 5.855855855855856e-06,
      "loss": 0.1918,
      "step": 144
    },
    {
      "epoch": 0.42962962962962964,
      "grad_norm": 2.2866106033325195,
      "learning_rate": 5.825825825825826e-06,
      "loss": 0.1442,
      "step": 145
    },
    {
      "epoch": 0.4325925925925926,
      "grad_norm": 1.6569770574569702,
      "learning_rate": 5.7957957957957965e-06,
      "loss": 0.0933,
      "step": 146
    },
    {
      "epoch": 0.43555555555555553,
      "grad_norm": 2.133049964904785,
      "learning_rate": 5.765765765765766e-06,
      "loss": 0.1409,
      "step": 147
    },
    {
      "epoch": 0.43851851851851853,
      "grad_norm": 2.2599782943725586,
      "learning_rate": 5.735735735735736e-06,
      "loss": 0.1712,
      "step": 148
    },
    {
      "epoch": 0.4414814814814815,
      "grad_norm": 2.637643814086914,
      "learning_rate": 5.7057057057057065e-06,
      "loss": 0.1871,
      "step": 149
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.8962996006011963,
      "learning_rate": 5.675675675675676e-06,
      "loss": 0.2482,
      "step": 150
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.16217826306819916,
      "eval_runtime": 18.6297,
      "eval_samples_per_second": 32.207,
      "eval_steps_per_second": 16.103,
      "step": 150
    },
    {
      "epoch": 0.4474074074074074,
      "grad_norm": 3.0046534538269043,
      "learning_rate": 5.645645645645647e-06,
      "loss": 0.2459,
      "step": 151
    },
    {
      "epoch": 0.45037037037037037,
      "grad_norm": 1.8144192695617676,
      "learning_rate": 5.615615615615616e-06,
      "loss": 0.1297,
      "step": 152
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 2.704719305038452,
      "learning_rate": 5.585585585585585e-06,
      "loss": 0.1713,
      "step": 153
    },
    {
      "epoch": 0.4562962962962963,
      "grad_norm": 2.5016303062438965,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.171,
      "step": 154
    },
    {
      "epoch": 0.45925925925925926,
      "grad_norm": 1.8085451126098633,
      "learning_rate": 5.5255255255255255e-06,
      "loss": 0.1016,
      "step": 155
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 1.2781469821929932,
      "learning_rate": 5.495495495495496e-06,
      "loss": 0.0498,
      "step": 156
    },
    {
      "epoch": 0.4651851851851852,
      "grad_norm": 3.103789806365967,
      "learning_rate": 5.465465465465466e-06,
      "loss": 0.2089,
      "step": 157
    },
    {
      "epoch": 0.46814814814814815,
      "grad_norm": 1.9900543689727783,
      "learning_rate": 5.4354354354354355e-06,
      "loss": 0.1427,
      "step": 158
    },
    {
      "epoch": 0.4711111111111111,
      "grad_norm": 2.6663990020751953,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.2254,
      "step": 159
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 2.099485158920288,
      "learning_rate": 5.375375375375376e-06,
      "loss": 0.1259,
      "step": 160
    },
    {
      "epoch": 0.47703703703703704,
      "grad_norm": 2.455075740814209,
      "learning_rate": 5.345345345345346e-06,
      "loss": 0.1822,
      "step": 161
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.018821954727173,
      "learning_rate": 5.315315315315316e-06,
      "loss": 0.1175,
      "step": 162
    },
    {
      "epoch": 0.482962962962963,
      "grad_norm": 2.688997745513916,
      "learning_rate": 5.285285285285286e-06,
      "loss": 0.1687,
      "step": 163
    },
    {
      "epoch": 0.48592592592592593,
      "grad_norm": 2.1906509399414062,
      "learning_rate": 5.255255255255256e-06,
      "loss": 0.1173,
      "step": 164
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 2.5710160732269287,
      "learning_rate": 5.225225225225226e-06,
      "loss": 0.1802,
      "step": 165
    },
    {
      "epoch": 0.4918518518518519,
      "grad_norm": 2.13515567779541,
      "learning_rate": 5.195195195195195e-06,
      "loss": 0.137,
      "step": 166
    },
    {
      "epoch": 0.4948148148148148,
      "grad_norm": 2.5237185955047607,
      "learning_rate": 5.165165165165165e-06,
      "loss": 0.1488,
      "step": 167
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 3.2704756259918213,
      "learning_rate": 5.135135135135135e-06,
      "loss": 0.2799,
      "step": 168
    },
    {
      "epoch": 0.5007407407407407,
      "grad_norm": 2.2165119647979736,
      "learning_rate": 5.105105105105106e-06,
      "loss": 0.1558,
      "step": 169
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 2.799826145172119,
      "learning_rate": 5.075075075075075e-06,
      "loss": 0.2217,
      "step": 170
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 2.6558640003204346,
      "learning_rate": 5.045045045045045e-06,
      "loss": 0.2026,
      "step": 171
    },
    {
      "epoch": 0.5096296296296297,
      "grad_norm": 3.263536214828491,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.2329,
      "step": 172
    },
    {
      "epoch": 0.5125925925925926,
      "grad_norm": 2.5015125274658203,
      "learning_rate": 4.984984984984985e-06,
      "loss": 0.2042,
      "step": 173
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 2.701338052749634,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.1929,
      "step": 174
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 2.5164060592651367,
      "learning_rate": 4.9249249249249255e-06,
      "loss": 0.1771,
      "step": 175
    },
    {
      "epoch": 0.5214814814814814,
      "grad_norm": 2.54914927482605,
      "learning_rate": 4.894894894894895e-06,
      "loss": 0.2062,
      "step": 176
    },
    {
      "epoch": 0.5244444444444445,
      "grad_norm": 2.037391185760498,
      "learning_rate": 4.864864864864866e-06,
      "loss": 0.1161,
      "step": 177
    },
    {
      "epoch": 0.5274074074074074,
      "grad_norm": 2.4384162425994873,
      "learning_rate": 4.8348348348348355e-06,
      "loss": 0.1789,
      "step": 178
    },
    {
      "epoch": 0.5303703703703704,
      "grad_norm": 2.425513982772827,
      "learning_rate": 4.804804804804805e-06,
      "loss": 0.1778,
      "step": 179
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.109112024307251,
      "learning_rate": 4.774774774774775e-06,
      "loss": 0.1507,
      "step": 180
    },
    {
      "epoch": 0.5362962962962963,
      "grad_norm": 1.9205242395401,
      "learning_rate": 4.7447447447447454e-06,
      "loss": 0.1447,
      "step": 181
    },
    {
      "epoch": 0.5392592592592592,
      "grad_norm": 2.625530958175659,
      "learning_rate": 4.714714714714715e-06,
      "loss": 0.164,
      "step": 182
    },
    {
      "epoch": 0.5422222222222223,
      "grad_norm": 2.1721272468566895,
      "learning_rate": 4.684684684684685e-06,
      "loss": 0.1262,
      "step": 183
    },
    {
      "epoch": 0.5451851851851852,
      "grad_norm": 2.620934247970581,
      "learning_rate": 4.654654654654655e-06,
      "loss": 0.2292,
      "step": 184
    },
    {
      "epoch": 0.5481481481481482,
      "grad_norm": 2.1182472705841064,
      "learning_rate": 4.624624624624625e-06,
      "loss": 0.1094,
      "step": 185
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 2.9960718154907227,
      "learning_rate": 4.594594594594596e-06,
      "loss": 0.2101,
      "step": 186
    },
    {
      "epoch": 0.554074074074074,
      "grad_norm": 3.408501148223877,
      "learning_rate": 4.5645645645645645e-06,
      "loss": 0.2546,
      "step": 187
    },
    {
      "epoch": 0.557037037037037,
      "grad_norm": 2.3182435035705566,
      "learning_rate": 4.534534534534535e-06,
      "loss": 0.1593,
      "step": 188
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.6585004329681396,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.2106,
      "step": 189
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 2.7763864994049072,
      "learning_rate": 4.474474474474475e-06,
      "loss": 0.1797,
      "step": 190
    },
    {
      "epoch": 0.5659259259259259,
      "grad_norm": 2.3474674224853516,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.1863,
      "step": 191
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 2.0063486099243164,
      "learning_rate": 4.414414414414415e-06,
      "loss": 0.1248,
      "step": 192
    },
    {
      "epoch": 0.5718518518518518,
      "grad_norm": 2.480496644973755,
      "learning_rate": 4.384384384384384e-06,
      "loss": 0.2207,
      "step": 193
    },
    {
      "epoch": 0.5748148148148148,
      "grad_norm": 2.4518790245056152,
      "learning_rate": 4.354354354354355e-06,
      "loss": 0.2093,
      "step": 194
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 2.2619192600250244,
      "learning_rate": 4.324324324324325e-06,
      "loss": 0.1398,
      "step": 195
    },
    {
      "epoch": 0.5807407407407408,
      "grad_norm": 2.0269298553466797,
      "learning_rate": 4.294294294294294e-06,
      "loss": 0.1511,
      "step": 196
    },
    {
      "epoch": 0.5837037037037037,
      "grad_norm": 2.3991732597351074,
      "learning_rate": 4.264264264264265e-06,
      "loss": 0.1939,
      "step": 197
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 2.3390724658966064,
      "learning_rate": 4.234234234234235e-06,
      "loss": 0.1752,
      "step": 198
    },
    {
      "epoch": 0.5896296296296296,
      "grad_norm": 2.5494184494018555,
      "learning_rate": 4.204204204204204e-06,
      "loss": 0.1621,
      "step": 199
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.9658615589141846,
      "learning_rate": 4.174174174174174e-06,
      "loss": 0.1334,
      "step": 200
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 0.15738177299499512,
      "eval_runtime": 18.6239,
      "eval_samples_per_second": 32.217,
      "eval_steps_per_second": 16.108,
      "step": 200
    },
    {
      "epoch": 0.5955555555555555,
      "grad_norm": 2.3948702812194824,
      "learning_rate": 4.1441441441441446e-06,
      "loss": 0.2139,
      "step": 201
    },
    {
      "epoch": 0.5985185185185186,
      "grad_norm": 2.569880723953247,
      "learning_rate": 4.114114114114114e-06,
      "loss": 0.1616,
      "step": 202
    },
    {
      "epoch": 0.6014814814814815,
      "grad_norm": 1.9368224143981934,
      "learning_rate": 4.084084084084085e-06,
      "loss": 0.1148,
      "step": 203
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 3.202821969985962,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.2409,
      "step": 204
    },
    {
      "epoch": 0.6074074074074074,
      "grad_norm": 2.5674757957458496,
      "learning_rate": 4.024024024024024e-06,
      "loss": 0.1978,
      "step": 205
    },
    {
      "epoch": 0.6103703703703703,
      "grad_norm": 1.866659164428711,
      "learning_rate": 3.993993993993994e-06,
      "loss": 0.1309,
      "step": 206
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 2.034125566482544,
      "learning_rate": 3.9639639639639645e-06,
      "loss": 0.0943,
      "step": 207
    },
    {
      "epoch": 0.6162962962962963,
      "grad_norm": 1.9542365074157715,
      "learning_rate": 3.933933933933934e-06,
      "loss": 0.1337,
      "step": 208
    },
    {
      "epoch": 0.6192592592592593,
      "grad_norm": 2.17082142829895,
      "learning_rate": 3.903903903903904e-06,
      "loss": 0.1798,
      "step": 209
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.3680691719055176,
      "learning_rate": 3.8738738738738744e-06,
      "loss": 0.1894,
      "step": 210
    },
    {
      "epoch": 0.6251851851851852,
      "grad_norm": 2.4722814559936523,
      "learning_rate": 3.843843843843844e-06,
      "loss": 0.1902,
      "step": 211
    },
    {
      "epoch": 0.6281481481481481,
      "grad_norm": 2.22086763381958,
      "learning_rate": 3.8138138138138143e-06,
      "loss": 0.1675,
      "step": 212
    },
    {
      "epoch": 0.6311111111111111,
      "grad_norm": 2.7056663036346436,
      "learning_rate": 3.7837837837837844e-06,
      "loss": 0.19,
      "step": 213
    },
    {
      "epoch": 0.6340740740740741,
      "grad_norm": 2.1262118816375732,
      "learning_rate": 3.7537537537537537e-06,
      "loss": 0.1494,
      "step": 214
    },
    {
      "epoch": 0.6370370370370371,
      "grad_norm": 2.04746413230896,
      "learning_rate": 3.723723723723724e-06,
      "loss": 0.1277,
      "step": 215
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.169076442718506,
      "learning_rate": 3.693693693693694e-06,
      "loss": 0.1598,
      "step": 216
    },
    {
      "epoch": 0.642962962962963,
      "grad_norm": 2.273516893386841,
      "learning_rate": 3.663663663663664e-06,
      "loss": 0.1562,
      "step": 217
    },
    {
      "epoch": 0.6459259259259259,
      "grad_norm": 1.9352264404296875,
      "learning_rate": 3.633633633633634e-06,
      "loss": 0.106,
      "step": 218
    },
    {
      "epoch": 0.6488888888888888,
      "grad_norm": 2.962240695953369,
      "learning_rate": 3.603603603603604e-06,
      "loss": 0.2132,
      "step": 219
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 2.2328948974609375,
      "learning_rate": 3.573573573573574e-06,
      "loss": 0.1528,
      "step": 220
    },
    {
      "epoch": 0.6548148148148148,
      "grad_norm": 1.894344687461853,
      "learning_rate": 3.5435435435435437e-06,
      "loss": 0.1601,
      "step": 221
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 2.139770746231079,
      "learning_rate": 3.513513513513514e-06,
      "loss": 0.1421,
      "step": 222
    },
    {
      "epoch": 0.6607407407407407,
      "grad_norm": 2.1672022342681885,
      "learning_rate": 3.4834834834834835e-06,
      "loss": 0.142,
      "step": 223
    },
    {
      "epoch": 0.6637037037037037,
      "grad_norm": 2.4951388835906982,
      "learning_rate": 3.4534534534534537e-06,
      "loss": 0.1071,
      "step": 224
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.0641355514526367,
      "learning_rate": 3.423423423423424e-06,
      "loss": 0.1216,
      "step": 225
    },
    {
      "epoch": 0.6696296296296296,
      "grad_norm": 2.605839252471924,
      "learning_rate": 3.393393393393394e-06,
      "loss": 0.1408,
      "step": 226
    },
    {
      "epoch": 0.6725925925925926,
      "grad_norm": 2.6184885501861572,
      "learning_rate": 3.363363363363364e-06,
      "loss": 0.2164,
      "step": 227
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 1.7767698764801025,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.1102,
      "step": 228
    },
    {
      "epoch": 0.6785185185185185,
      "grad_norm": 1.8321311473846436,
      "learning_rate": 3.3033033033033035e-06,
      "loss": 0.0926,
      "step": 229
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.7934424877166748,
      "learning_rate": 3.2732732732732736e-06,
      "loss": 0.1196,
      "step": 230
    },
    {
      "epoch": 0.6844444444444444,
      "grad_norm": 2.7702689170837402,
      "learning_rate": 3.2432432432432437e-06,
      "loss": 0.2476,
      "step": 231
    },
    {
      "epoch": 0.6874074074074074,
      "grad_norm": 2.2534561157226562,
      "learning_rate": 3.2132132132132134e-06,
      "loss": 0.1513,
      "step": 232
    },
    {
      "epoch": 0.6903703703703704,
      "grad_norm": 1.995375394821167,
      "learning_rate": 3.183183183183183e-06,
      "loss": 0.1334,
      "step": 233
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 2.0202677249908447,
      "learning_rate": 3.1531531531531532e-06,
      "loss": 0.1088,
      "step": 234
    },
    {
      "epoch": 0.6962962962962963,
      "grad_norm": 2.7341086864471436,
      "learning_rate": 3.1231231231231234e-06,
      "loss": 0.1563,
      "step": 235
    },
    {
      "epoch": 0.6992592592592592,
      "grad_norm": 2.8716964721679688,
      "learning_rate": 3.0930930930930935e-06,
      "loss": 0.199,
      "step": 236
    },
    {
      "epoch": 0.7022222222222222,
      "grad_norm": 2.4406189918518066,
      "learning_rate": 3.063063063063063e-06,
      "loss": 0.1749,
      "step": 237
    },
    {
      "epoch": 0.7051851851851851,
      "grad_norm": 2.3873836994171143,
      "learning_rate": 3.0330330330330333e-06,
      "loss": 0.1665,
      "step": 238
    },
    {
      "epoch": 0.7081481481481482,
      "grad_norm": 2.0144615173339844,
      "learning_rate": 3.0030030030030034e-06,
      "loss": 0.1264,
      "step": 239
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.5600855350494385,
      "learning_rate": 2.9729729729729736e-06,
      "loss": 0.1863,
      "step": 240
    },
    {
      "epoch": 0.7140740740740741,
      "grad_norm": 2.3772830963134766,
      "learning_rate": 2.942942942942943e-06,
      "loss": 0.1735,
      "step": 241
    },
    {
      "epoch": 0.717037037037037,
      "grad_norm": 2.300318479537964,
      "learning_rate": 2.912912912912913e-06,
      "loss": 0.1655,
      "step": 242
    },
    {
      "epoch": 0.72,
      "grad_norm": 2.7702767848968506,
      "learning_rate": 2.882882882882883e-06,
      "loss": 0.2123,
      "step": 243
    },
    {
      "epoch": 0.7229629629629629,
      "grad_norm": 2.2175815105438232,
      "learning_rate": 2.8528528528528532e-06,
      "loss": 0.1265,
      "step": 244
    },
    {
      "epoch": 0.725925925925926,
      "grad_norm": 1.9076950550079346,
      "learning_rate": 2.8228228228228234e-06,
      "loss": 0.0901,
      "step": 245
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 2.686443567276001,
      "learning_rate": 2.7927927927927926e-06,
      "loss": 0.1951,
      "step": 246
    },
    {
      "epoch": 0.7318518518518519,
      "grad_norm": 1.8656299114227295,
      "learning_rate": 2.7627627627627628e-06,
      "loss": 0.1117,
      "step": 247
    },
    {
      "epoch": 0.7348148148148148,
      "grad_norm": 2.1867880821228027,
      "learning_rate": 2.732732732732733e-06,
      "loss": 0.1306,
      "step": 248
    },
    {
      "epoch": 0.7377777777777778,
      "grad_norm": 2.5537476539611816,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.2009,
      "step": 249
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.4839835166931152,
      "learning_rate": 2.672672672672673e-06,
      "loss": 0.1823,
      "step": 250
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.15435847640037537,
      "eval_runtime": 18.9365,
      "eval_samples_per_second": 31.685,
      "eval_steps_per_second": 15.842,
      "step": 250
    },
    {
      "epoch": 0.7437037037037038,
      "grad_norm": 2.252938985824585,
      "learning_rate": 2.642642642642643e-06,
      "loss": 0.1562,
      "step": 251
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 1.9709515571594238,
      "learning_rate": 2.612612612612613e-06,
      "loss": 0.1298,
      "step": 252
    },
    {
      "epoch": 0.7496296296296296,
      "grad_norm": 2.9127609729766846,
      "learning_rate": 2.5825825825825827e-06,
      "loss": 0.1969,
      "step": 253
    },
    {
      "epoch": 0.7525925925925926,
      "grad_norm": 2.250854969024658,
      "learning_rate": 2.552552552552553e-06,
      "loss": 0.1438,
      "step": 254
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 2.337545156478882,
      "learning_rate": 2.5225225225225225e-06,
      "loss": 0.1718,
      "step": 255
    },
    {
      "epoch": 0.7585185185185185,
      "grad_norm": 2.4176278114318848,
      "learning_rate": 2.4924924924924926e-06,
      "loss": 0.1679,
      "step": 256
    },
    {
      "epoch": 0.7614814814814815,
      "grad_norm": 2.451856851577759,
      "learning_rate": 2.4624624624624628e-06,
      "loss": 0.2122,
      "step": 257
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 2.3540382385253906,
      "learning_rate": 2.432432432432433e-06,
      "loss": 0.1779,
      "step": 258
    },
    {
      "epoch": 0.7674074074074074,
      "grad_norm": 2.6803536415100098,
      "learning_rate": 2.4024024024024026e-06,
      "loss": 0.188,
      "step": 259
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 2.3289761543273926,
      "learning_rate": 2.3723723723723727e-06,
      "loss": 0.153,
      "step": 260
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 2.7902815341949463,
      "learning_rate": 2.3423423423423424e-06,
      "loss": 0.2102,
      "step": 261
    },
    {
      "epoch": 0.7762962962962963,
      "grad_norm": 3.0851755142211914,
      "learning_rate": 2.3123123123123125e-06,
      "loss": 0.2104,
      "step": 262
    },
    {
      "epoch": 0.7792592592592592,
      "grad_norm": 3.098471164703369,
      "learning_rate": 2.2822822822822822e-06,
      "loss": 0.2358,
      "step": 263
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 2.063593626022339,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.1207,
      "step": 264
    },
    {
      "epoch": 0.7851851851851852,
      "grad_norm": 2.1788723468780518,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.1155,
      "step": 265
    },
    {
      "epoch": 0.7881481481481482,
      "grad_norm": 1.7954949140548706,
      "learning_rate": 2.192192192192192e-06,
      "loss": 0.1208,
      "step": 266
    },
    {
      "epoch": 0.7911111111111111,
      "grad_norm": 2.787583351135254,
      "learning_rate": 2.1621621621621623e-06,
      "loss": 0.2084,
      "step": 267
    },
    {
      "epoch": 0.794074074074074,
      "grad_norm": 2.2443230152130127,
      "learning_rate": 2.1321321321321325e-06,
      "loss": 0.1324,
      "step": 268
    },
    {
      "epoch": 0.797037037037037,
      "grad_norm": 2.849313735961914,
      "learning_rate": 2.102102102102102e-06,
      "loss": 0.183,
      "step": 269
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.6045637130737305,
      "learning_rate": 2.0720720720720723e-06,
      "loss": 0.2746,
      "step": 270
    },
    {
      "epoch": 0.802962962962963,
      "grad_norm": 2.2145416736602783,
      "learning_rate": 2.0420420420420424e-06,
      "loss": 0.1336,
      "step": 271
    },
    {
      "epoch": 0.8059259259259259,
      "grad_norm": 2.952852249145508,
      "learning_rate": 2.012012012012012e-06,
      "loss": 0.1928,
      "step": 272
    },
    {
      "epoch": 0.8088888888888889,
      "grad_norm": 3.254387855529785,
      "learning_rate": 1.9819819819819822e-06,
      "loss": 0.2389,
      "step": 273
    },
    {
      "epoch": 0.8118518518518518,
      "grad_norm": 1.5405303239822388,
      "learning_rate": 1.951951951951952e-06,
      "loss": 0.0824,
      "step": 274
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 2.4624598026275635,
      "learning_rate": 1.921921921921922e-06,
      "loss": 0.1989,
      "step": 275
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 3.1001126766204834,
      "learning_rate": 1.8918918918918922e-06,
      "loss": 0.2275,
      "step": 276
    },
    {
      "epoch": 0.8207407407407408,
      "grad_norm": 2.473565101623535,
      "learning_rate": 1.861861861861862e-06,
      "loss": 0.1769,
      "step": 277
    },
    {
      "epoch": 0.8237037037037037,
      "grad_norm": 1.6487822532653809,
      "learning_rate": 1.831831831831832e-06,
      "loss": 0.0901,
      "step": 278
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 2.3114559650421143,
      "learning_rate": 1.801801801801802e-06,
      "loss": 0.1404,
      "step": 279
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 2.4342026710510254,
      "learning_rate": 1.7717717717717719e-06,
      "loss": 0.1941,
      "step": 280
    },
    {
      "epoch": 0.8325925925925926,
      "grad_norm": 1.6942079067230225,
      "learning_rate": 1.7417417417417418e-06,
      "loss": 0.1011,
      "step": 281
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 2.9058849811553955,
      "learning_rate": 1.711711711711712e-06,
      "loss": 0.2005,
      "step": 282
    },
    {
      "epoch": 0.8385185185185186,
      "grad_norm": 1.9488892555236816,
      "learning_rate": 1.681681681681682e-06,
      "loss": 0.1235,
      "step": 283
    },
    {
      "epoch": 0.8414814814814815,
      "grad_norm": 2.4560811519622803,
      "learning_rate": 1.6516516516516517e-06,
      "loss": 0.1614,
      "step": 284
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 2.2537083625793457,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.1306,
      "step": 285
    },
    {
      "epoch": 0.8474074074074074,
      "grad_norm": 1.776450276374817,
      "learning_rate": 1.5915915915915916e-06,
      "loss": 0.1087,
      "step": 286
    },
    {
      "epoch": 0.8503703703703703,
      "grad_norm": 2.1298906803131104,
      "learning_rate": 1.5615615615615617e-06,
      "loss": 0.1098,
      "step": 287
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.838258981704712,
      "learning_rate": 1.5315315315315316e-06,
      "loss": 0.1145,
      "step": 288
    },
    {
      "epoch": 0.8562962962962963,
      "grad_norm": 2.178248167037964,
      "learning_rate": 1.5015015015015017e-06,
      "loss": 0.1465,
      "step": 289
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 1.4471555948257446,
      "learning_rate": 1.4714714714714714e-06,
      "loss": 0.0734,
      "step": 290
    },
    {
      "epoch": 0.8622222222222222,
      "grad_norm": 2.1363370418548584,
      "learning_rate": 1.4414414414414416e-06,
      "loss": 0.1263,
      "step": 291
    },
    {
      "epoch": 0.8651851851851852,
      "grad_norm": 2.0831563472747803,
      "learning_rate": 1.4114114114114117e-06,
      "loss": 0.1168,
      "step": 292
    },
    {
      "epoch": 0.8681481481481481,
      "grad_norm": 2.0286214351654053,
      "learning_rate": 1.3813813813813814e-06,
      "loss": 0.1009,
      "step": 293
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 2.9190995693206787,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.2288,
      "step": 294
    },
    {
      "epoch": 0.8740740740740741,
      "grad_norm": 1.6343410015106201,
      "learning_rate": 1.3213213213213214e-06,
      "loss": 0.1028,
      "step": 295
    },
    {
      "epoch": 0.8770370370370371,
      "grad_norm": 2.7702269554138184,
      "learning_rate": 1.2912912912912913e-06,
      "loss": 0.1608,
      "step": 296
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.8205175399780273,
      "learning_rate": 1.2612612612612613e-06,
      "loss": 0.1086,
      "step": 297
    },
    {
      "epoch": 0.882962962962963,
      "grad_norm": 2.274799346923828,
      "learning_rate": 1.2312312312312314e-06,
      "loss": 0.1703,
      "step": 298
    },
    {
      "epoch": 0.8859259259259259,
      "grad_norm": 1.8534551858901978,
      "learning_rate": 1.2012012012012013e-06,
      "loss": 0.1276,
      "step": 299
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.0699753761291504,
      "learning_rate": 1.1711711711711712e-06,
      "loss": 0.1287,
      "step": 300
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.15198387205600739,
      "eval_runtime": 19.0619,
      "eval_samples_per_second": 31.476,
      "eval_steps_per_second": 15.738,
      "step": 300
    },
    {
      "epoch": 0.8918518518518519,
      "grad_norm": 2.533606767654419,
      "learning_rate": 1.1411411411411411e-06,
      "loss": 0.1691,
      "step": 301
    },
    {
      "epoch": 0.8948148148148148,
      "grad_norm": 2.752211093902588,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.1744,
      "step": 302
    },
    {
      "epoch": 0.8977777777777778,
      "grad_norm": 1.819265604019165,
      "learning_rate": 1.0810810810810812e-06,
      "loss": 0.1091,
      "step": 303
    },
    {
      "epoch": 0.9007407407407407,
      "grad_norm": 2.454192876815796,
      "learning_rate": 1.051051051051051e-06,
      "loss": 0.194,
      "step": 304
    },
    {
      "epoch": 0.9037037037037037,
      "grad_norm": 2.2125589847564697,
      "learning_rate": 1.0210210210210212e-06,
      "loss": 0.1201,
      "step": 305
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 2.7960760593414307,
      "learning_rate": 9.909909909909911e-07,
      "loss": 0.1346,
      "step": 306
    },
    {
      "epoch": 0.9096296296296297,
      "grad_norm": 1.531630516052246,
      "learning_rate": 9.60960960960961e-07,
      "loss": 0.1029,
      "step": 307
    },
    {
      "epoch": 0.9125925925925926,
      "grad_norm": 2.686945915222168,
      "learning_rate": 9.30930930930931e-07,
      "loss": 0.2122,
      "step": 308
    },
    {
      "epoch": 0.9155555555555556,
      "grad_norm": 2.7788093090057373,
      "learning_rate": 9.00900900900901e-07,
      "loss": 0.2021,
      "step": 309
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 2.050950288772583,
      "learning_rate": 8.708708708708709e-07,
      "loss": 0.1364,
      "step": 310
    },
    {
      "epoch": 0.9214814814814815,
      "grad_norm": 1.5149585008621216,
      "learning_rate": 8.40840840840841e-07,
      "loss": 0.09,
      "step": 311
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 2.06543231010437,
      "learning_rate": 8.108108108108109e-07,
      "loss": 0.1072,
      "step": 312
    },
    {
      "epoch": 0.9274074074074075,
      "grad_norm": 2.5705268383026123,
      "learning_rate": 7.807807807807808e-07,
      "loss": 0.1842,
      "step": 313
    },
    {
      "epoch": 0.9303703703703704,
      "grad_norm": 1.863800287246704,
      "learning_rate": 7.507507507507509e-07,
      "loss": 0.0958,
      "step": 314
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 2.2778892517089844,
      "learning_rate": 7.207207207207208e-07,
      "loss": 0.156,
      "step": 315
    },
    {
      "epoch": 0.9362962962962963,
      "grad_norm": 2.4413187503814697,
      "learning_rate": 6.906906906906907e-07,
      "loss": 0.199,
      "step": 316
    },
    {
      "epoch": 0.9392592592592592,
      "grad_norm": 2.2605388164520264,
      "learning_rate": 6.606606606606607e-07,
      "loss": 0.1387,
      "step": 317
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 2.5504255294799805,
      "learning_rate": 6.306306306306306e-07,
      "loss": 0.154,
      "step": 318
    },
    {
      "epoch": 0.9451851851851852,
      "grad_norm": 2.006319284439087,
      "learning_rate": 6.006006006006006e-07,
      "loss": 0.1492,
      "step": 319
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 2.097008228302002,
      "learning_rate": 5.705705705705706e-07,
      "loss": 0.1251,
      "step": 320
    },
    {
      "epoch": 0.9511111111111111,
      "grad_norm": 2.146705389022827,
      "learning_rate": 5.405405405405406e-07,
      "loss": 0.1414,
      "step": 321
    },
    {
      "epoch": 0.9540740740740741,
      "grad_norm": 2.2391388416290283,
      "learning_rate": 5.105105105105106e-07,
      "loss": 0.1579,
      "step": 322
    },
    {
      "epoch": 0.957037037037037,
      "grad_norm": 1.9116389751434326,
      "learning_rate": 4.804804804804805e-07,
      "loss": 0.1377,
      "step": 323
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.3334124088287354,
      "learning_rate": 4.504504504504505e-07,
      "loss": 0.1088,
      "step": 324
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 1.6835885047912598,
      "learning_rate": 4.204204204204205e-07,
      "loss": 0.0997,
      "step": 325
    },
    {
      "epoch": 0.965925925925926,
      "grad_norm": 2.432762384414673,
      "learning_rate": 3.903903903903904e-07,
      "loss": 0.1783,
      "step": 326
    },
    {
      "epoch": 0.9688888888888889,
      "grad_norm": 1.679010272026062,
      "learning_rate": 3.603603603603604e-07,
      "loss": 0.0955,
      "step": 327
    },
    {
      "epoch": 0.9718518518518519,
      "grad_norm": 2.4820268154144287,
      "learning_rate": 3.3033033033033036e-07,
      "loss": 0.1863,
      "step": 328
    },
    {
      "epoch": 0.9748148148148148,
      "grad_norm": 2.4354779720306396,
      "learning_rate": 3.003003003003003e-07,
      "loss": 0.1654,
      "step": 329
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 2.1663825511932373,
      "learning_rate": 2.702702702702703e-07,
      "loss": 0.1091,
      "step": 330
    },
    {
      "epoch": 0.9807407407407407,
      "grad_norm": 2.80875825881958,
      "learning_rate": 2.4024024024024026e-07,
      "loss": 0.2227,
      "step": 331
    },
    {
      "epoch": 0.9837037037037037,
      "grad_norm": 1.9273627996444702,
      "learning_rate": 2.1021021021021025e-07,
      "loss": 0.1471,
      "step": 332
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 2.2786149978637695,
      "learning_rate": 1.801801801801802e-07,
      "loss": 0.1286,
      "step": 333
    },
    {
      "epoch": 0.9896296296296296,
      "grad_norm": 1.7414181232452393,
      "learning_rate": 1.5015015015015016e-07,
      "loss": 0.1035,
      "step": 334
    },
    {
      "epoch": 0.9925925925925926,
      "grad_norm": 2.656731605529785,
      "learning_rate": 1.2012012012012013e-07,
      "loss": 0.1802,
      "step": 335
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 2.7487423419952393,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.1948,
      "step": 336
    },
    {
      "epoch": 0.9985185185185185,
      "grad_norm": 2.4541685581207275,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.1569,
      "step": 337
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.514453411102295,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1664,
      "step": 338
    }
  ],
  "logging_steps": 1,
  "max_steps": 338,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.278297607345971e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}