{
  "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": 19.49534034729004,
      "learning_rate": 0.0,
      "loss": 1.1237,
      "step": 1
    },
    {
      "epoch": 0.005925925925925926,
      "grad_norm": 19.354833602905273,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.2529,
      "step": 2
    },
    {
      "epoch": 0.008888888888888889,
      "grad_norm": 16.767250061035156,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.08,
      "step": 3
    },
    {
      "epoch": 0.011851851851851851,
      "grad_norm": 13.555519104003906,
      "learning_rate": 6e-06,
      "loss": 0.8047,
      "step": 4
    },
    {
      "epoch": 0.014814814814814815,
      "grad_norm": 12.100520133972168,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6724,
      "step": 5
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 11.686114311218262,
      "learning_rate": 1e-05,
      "loss": 0.6653,
      "step": 6
    },
    {
      "epoch": 0.02074074074074074,
      "grad_norm": 10.689408302307129,
      "learning_rate": 9.96996996996997e-06,
      "loss": 0.5185,
      "step": 7
    },
    {
      "epoch": 0.023703703703703703,
      "grad_norm": 4.977103233337402,
      "learning_rate": 9.93993993993994e-06,
      "loss": 0.2985,
      "step": 8
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 4.187211513519287,
      "learning_rate": 9.90990990990991e-06,
      "loss": 0.3157,
      "step": 9
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 3.8093414306640625,
      "learning_rate": 9.879879879879881e-06,
      "loss": 0.3238,
      "step": 10
    },
    {
      "epoch": 0.03259259259259259,
      "grad_norm": 2.764106512069702,
      "learning_rate": 9.849849849849851e-06,
      "loss": 0.2339,
      "step": 11
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 3.5458824634552,
      "learning_rate": 9.81981981981982e-06,
      "loss": 0.3317,
      "step": 12
    },
    {
      "epoch": 0.03851851851851852,
      "grad_norm": 2.9258158206939697,
      "learning_rate": 9.78978978978979e-06,
      "loss": 0.1734,
      "step": 13
    },
    {
      "epoch": 0.04148148148148148,
      "grad_norm": 3.588153839111328,
      "learning_rate": 9.75975975975976e-06,
      "loss": 0.2946,
      "step": 14
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.34350848197937,
      "learning_rate": 9.729729729729732e-06,
      "loss": 0.1618,
      "step": 15
    },
    {
      "epoch": 0.047407407407407405,
      "grad_norm": 2.761561632156372,
      "learning_rate": 9.699699699699701e-06,
      "loss": 0.2361,
      "step": 16
    },
    {
      "epoch": 0.05037037037037037,
      "grad_norm": 2.3020567893981934,
      "learning_rate": 9.669669669669671e-06,
      "loss": 0.2125,
      "step": 17
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 1.9380403757095337,
      "learning_rate": 9.63963963963964e-06,
      "loss": 0.1306,
      "step": 18
    },
    {
      "epoch": 0.056296296296296296,
      "grad_norm": 2.2407524585723877,
      "learning_rate": 9.60960960960961e-06,
      "loss": 0.2344,
      "step": 19
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 2.096853494644165,
      "learning_rate": 9.57957957957958e-06,
      "loss": 0.241,
      "step": 20
    },
    {
      "epoch": 0.06222222222222222,
      "grad_norm": 1.726133942604065,
      "learning_rate": 9.54954954954955e-06,
      "loss": 0.1348,
      "step": 21
    },
    {
      "epoch": 0.06518518518518518,
      "grad_norm": 2.319309711456299,
      "learning_rate": 9.51951951951952e-06,
      "loss": 0.2455,
      "step": 22
    },
    {
      "epoch": 0.06814814814814815,
      "grad_norm": 2.466797351837158,
      "learning_rate": 9.489489489489491e-06,
      "loss": 0.2702,
      "step": 23
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 2.3349595069885254,
      "learning_rate": 9.45945945945946e-06,
      "loss": 0.276,
      "step": 24
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.883699655532837,
      "learning_rate": 9.42942942942943e-06,
      "loss": 0.165,
      "step": 25
    },
    {
      "epoch": 0.07703703703703704,
      "grad_norm": 1.8374661207199097,
      "learning_rate": 9.3993993993994e-06,
      "loss": 0.2193,
      "step": 26
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.4179415702819824,
      "learning_rate": 9.36936936936937e-06,
      "loss": 0.2682,
      "step": 27
    },
    {
      "epoch": 0.08296296296296296,
      "grad_norm": 2.0390024185180664,
      "learning_rate": 9.339339339339341e-06,
      "loss": 0.2654,
      "step": 28
    },
    {
      "epoch": 0.08592592592592592,
      "grad_norm": 1.9180946350097656,
      "learning_rate": 9.30930930930931e-06,
      "loss": 0.202,
      "step": 29
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.744606375694275,
      "learning_rate": 9.27927927927928e-06,
      "loss": 0.1683,
      "step": 30
    },
    {
      "epoch": 0.09185185185185185,
      "grad_norm": 1.4626421928405762,
      "learning_rate": 9.24924924924925e-06,
      "loss": 0.134,
      "step": 31
    },
    {
      "epoch": 0.09481481481481481,
      "grad_norm": 1.117967963218689,
      "learning_rate": 9.21921921921922e-06,
      "loss": 0.0921,
      "step": 32
    },
    {
      "epoch": 0.09777777777777778,
      "grad_norm": 1.2754089832305908,
      "learning_rate": 9.189189189189191e-06,
      "loss": 0.1244,
      "step": 33
    },
    {
      "epoch": 0.10074074074074074,
      "grad_norm": 1.7274144887924194,
      "learning_rate": 9.15915915915916e-06,
      "loss": 0.169,
      "step": 34
    },
    {
      "epoch": 0.1037037037037037,
      "grad_norm": 1.9858444929122925,
      "learning_rate": 9.129129129129129e-06,
      "loss": 0.2356,
      "step": 35
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 1.5841292142868042,
      "learning_rate": 9.0990990990991e-06,
      "loss": 0.1499,
      "step": 36
    },
    {
      "epoch": 0.10962962962962963,
      "grad_norm": 1.9121755361557007,
      "learning_rate": 9.06906906906907e-06,
      "loss": 0.2173,
      "step": 37
    },
    {
      "epoch": 0.11259259259259259,
      "grad_norm": 1.8218320608139038,
      "learning_rate": 9.03903903903904e-06,
      "loss": 0.1921,
      "step": 38
    },
    {
      "epoch": 0.11555555555555555,
      "grad_norm": 1.5346003770828247,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.1266,
      "step": 39
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 1.2988084554672241,
      "learning_rate": 8.97897897897898e-06,
      "loss": 0.1321,
      "step": 40
    },
    {
      "epoch": 0.12148148148148148,
      "grad_norm": 1.6627641916275024,
      "learning_rate": 8.94894894894895e-06,
      "loss": 0.1859,
      "step": 41
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 2.0329363346099854,
      "learning_rate": 8.91891891891892e-06,
      "loss": 0.2223,
      "step": 42
    },
    {
      "epoch": 0.1274074074074074,
      "grad_norm": 1.2202503681182861,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1059,
      "step": 43
    },
    {
      "epoch": 0.13037037037037036,
      "grad_norm": 1.2986619472503662,
      "learning_rate": 8.85885885885886e-06,
      "loss": 0.1265,
      "step": 44
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.915509581565857,
      "learning_rate": 8.82882882882883e-06,
      "loss": 0.1866,
      "step": 45
    },
    {
      "epoch": 0.1362962962962963,
      "grad_norm": 2.0464425086975098,
      "learning_rate": 8.798798798798799e-06,
      "loss": 0.2282,
      "step": 46
    },
    {
      "epoch": 0.13925925925925925,
      "grad_norm": 2.514810085296631,
      "learning_rate": 8.768768768768769e-06,
      "loss": 0.2933,
      "step": 47
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 1.2582273483276367,
      "learning_rate": 8.738738738738739e-06,
      "loss": 0.1053,
      "step": 48
    },
    {
      "epoch": 0.1451851851851852,
      "grad_norm": 1.5531758069992065,
      "learning_rate": 8.70870870870871e-06,
      "loss": 0.1432,
      "step": 49
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.270075798034668,
      "learning_rate": 8.67867867867868e-06,
      "loss": 0.127,
      "step": 50
    },
    {
      "epoch": 0.14814814814814814,
      "eval_loss": 0.1583847999572754,
      "eval_runtime": 70.7144,
      "eval_samples_per_second": 8.485,
      "eval_steps_per_second": 4.242,
      "step": 50
    },
    {
      "epoch": 0.1511111111111111,
      "grad_norm": 2.0574734210968018,
      "learning_rate": 8.64864864864865e-06,
      "loss": 0.2207,
      "step": 51
    },
    {
      "epoch": 0.15407407407407409,
      "grad_norm": 1.7001434564590454,
      "learning_rate": 8.618618618618619e-06,
      "loss": 0.1876,
      "step": 52
    },
    {
      "epoch": 0.15703703703703703,
      "grad_norm": 1.817590594291687,
      "learning_rate": 8.588588588588589e-06,
      "loss": 0.2011,
      "step": 53
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.106809616088867,
      "learning_rate": 8.55855855855856e-06,
      "loss": 0.1984,
      "step": 54
    },
    {
      "epoch": 0.16296296296296298,
      "grad_norm": 1.3052719831466675,
      "learning_rate": 8.52852852852853e-06,
      "loss": 0.1053,
      "step": 55
    },
    {
      "epoch": 0.16592592592592592,
      "grad_norm": 1.568976879119873,
      "learning_rate": 8.4984984984985e-06,
      "loss": 0.1571,
      "step": 56
    },
    {
      "epoch": 0.1688888888888889,
      "grad_norm": 1.4826037883758545,
      "learning_rate": 8.46846846846847e-06,
      "loss": 0.1412,
      "step": 57
    },
    {
      "epoch": 0.17185185185185184,
      "grad_norm": 1.242918610572815,
      "learning_rate": 8.438438438438439e-06,
      "loss": 0.1066,
      "step": 58
    },
    {
      "epoch": 0.1748148148148148,
      "grad_norm": 1.6517393589019775,
      "learning_rate": 8.408408408408409e-06,
      "loss": 0.1869,
      "step": 59
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.4644402265548706,
      "learning_rate": 8.378378378378378e-06,
      "loss": 0.1639,
      "step": 60
    },
    {
      "epoch": 0.18074074074074073,
      "grad_norm": 1.4390480518341064,
      "learning_rate": 8.348348348348348e-06,
      "loss": 0.1451,
      "step": 61
    },
    {
      "epoch": 0.1837037037037037,
      "grad_norm": 1.2160828113555908,
      "learning_rate": 8.31831831831832e-06,
      "loss": 0.1209,
      "step": 62
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 1.7920739650726318,
      "learning_rate": 8.288288288288289e-06,
      "loss": 0.2101,
      "step": 63
    },
    {
      "epoch": 0.18962962962962962,
      "grad_norm": 1.2824952602386475,
      "learning_rate": 8.258258258258259e-06,
      "loss": 0.1506,
      "step": 64
    },
    {
      "epoch": 0.1925925925925926,
      "grad_norm": 1.5710806846618652,
      "learning_rate": 8.228228228228229e-06,
      "loss": 0.1693,
      "step": 65
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 1.5337549448013306,
      "learning_rate": 8.198198198198198e-06,
      "loss": 0.1323,
      "step": 66
    },
    {
      "epoch": 0.1985185185185185,
      "grad_norm": 1.799993872642517,
      "learning_rate": 8.16816816816817e-06,
      "loss": 0.2086,
      "step": 67
    },
    {
      "epoch": 0.20148148148148148,
      "grad_norm": 2.228088617324829,
      "learning_rate": 8.13813813813814e-06,
      "loss": 0.2476,
      "step": 68
    },
    {
      "epoch": 0.20444444444444446,
      "grad_norm": 1.8109062910079956,
      "learning_rate": 8.108108108108109e-06,
      "loss": 0.1941,
      "step": 69
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 1.0647183656692505,
      "learning_rate": 8.078078078078079e-06,
      "loss": 0.1096,
      "step": 70
    },
    {
      "epoch": 0.21037037037037037,
      "grad_norm": 1.7846921682357788,
      "learning_rate": 8.048048048048048e-06,
      "loss": 0.1779,
      "step": 71
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 1.7732218503952026,
      "learning_rate": 8.018018018018018e-06,
      "loss": 0.191,
      "step": 72
    },
    {
      "epoch": 0.2162962962962963,
      "grad_norm": 1.4192458391189575,
      "learning_rate": 7.987987987987988e-06,
      "loss": 0.1237,
      "step": 73
    },
    {
      "epoch": 0.21925925925925926,
      "grad_norm": 1.2193058729171753,
      "learning_rate": 7.95795795795796e-06,
      "loss": 0.1016,
      "step": 74
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.4058624505996704,
      "learning_rate": 7.927927927927929e-06,
      "loss": 0.1288,
      "step": 75
    },
    {
      "epoch": 0.22518518518518518,
      "grad_norm": 1.490768313407898,
      "learning_rate": 7.897897897897899e-06,
      "loss": 0.1571,
      "step": 76
    },
    {
      "epoch": 0.22814814814814816,
      "grad_norm": 1.860007405281067,
      "learning_rate": 7.867867867867868e-06,
      "loss": 0.1956,
      "step": 77
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 1.5503745079040527,
      "learning_rate": 7.837837837837838e-06,
      "loss": 0.1565,
      "step": 78
    },
    {
      "epoch": 0.23407407407407407,
      "grad_norm": 1.2416739463806152,
      "learning_rate": 7.807807807807808e-06,
      "loss": 0.123,
      "step": 79
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.5890201330184937,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.1542,
      "step": 80
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.4586267471313477,
      "learning_rate": 7.747747747747749e-06,
      "loss": 0.1558,
      "step": 81
    },
    {
      "epoch": 0.24296296296296296,
      "grad_norm": 1.5166500806808472,
      "learning_rate": 7.717717717717719e-06,
      "loss": 0.1281,
      "step": 82
    },
    {
      "epoch": 0.24592592592592594,
      "grad_norm": 1.1885906457901,
      "learning_rate": 7.687687687687688e-06,
      "loss": 0.1082,
      "step": 83
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 1.3031468391418457,
      "learning_rate": 7.657657657657658e-06,
      "loss": 0.136,
      "step": 84
    },
    {
      "epoch": 0.2518518518518518,
      "grad_norm": 1.4578081369400024,
      "learning_rate": 7.6276276276276285e-06,
      "loss": 0.1648,
      "step": 85
    },
    {
      "epoch": 0.2548148148148148,
      "grad_norm": 1.2639418840408325,
      "learning_rate": 7.597597597597598e-06,
      "loss": 0.1508,
      "step": 86
    },
    {
      "epoch": 0.2577777777777778,
      "grad_norm": 1.7876205444335938,
      "learning_rate": 7.567567567567569e-06,
      "loss": 0.2198,
      "step": 87
    },
    {
      "epoch": 0.2607407407407407,
      "grad_norm": 1.7213354110717773,
      "learning_rate": 7.5375375375375385e-06,
      "loss": 0.1979,
      "step": 88
    },
    {
      "epoch": 0.2637037037037037,
      "grad_norm": 1.2988152503967285,
      "learning_rate": 7.507507507507507e-06,
      "loss": 0.1331,
      "step": 89
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.5244368314743042,
      "learning_rate": 7.477477477477479e-06,
      "loss": 0.1473,
      "step": 90
    },
    {
      "epoch": 0.2696296296296296,
      "grad_norm": 1.6809802055358887,
      "learning_rate": 7.447447447447448e-06,
      "loss": 0.2008,
      "step": 91
    },
    {
      "epoch": 0.2725925925925926,
      "grad_norm": 1.2355259656906128,
      "learning_rate": 7.417417417417418e-06,
      "loss": 0.1175,
      "step": 92
    },
    {
      "epoch": 0.27555555555555555,
      "grad_norm": 1.1461902856826782,
      "learning_rate": 7.387387387387388e-06,
      "loss": 0.0926,
      "step": 93
    },
    {
      "epoch": 0.2785185185185185,
      "grad_norm": 1.8003261089324951,
      "learning_rate": 7.3573573573573575e-06,
      "loss": 0.2328,
      "step": 94
    },
    {
      "epoch": 0.2814814814814815,
      "grad_norm": 1.3473647832870483,
      "learning_rate": 7.327327327327328e-06,
      "loss": 0.1491,
      "step": 95
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 1.586394190788269,
      "learning_rate": 7.297297297297298e-06,
      "loss": 0.1778,
      "step": 96
    },
    {
      "epoch": 0.2874074074074074,
      "grad_norm": 1.5974844694137573,
      "learning_rate": 7.267267267267268e-06,
      "loss": 0.1943,
      "step": 97
    },
    {
      "epoch": 0.2903703703703704,
      "grad_norm": 1.48704195022583,
      "learning_rate": 7.237237237237238e-06,
      "loss": 0.1572,
      "step": 98
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 1.715559720993042,
      "learning_rate": 7.207207207207208e-06,
      "loss": 0.246,
      "step": 99
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.506817102432251,
      "learning_rate": 7.177177177177178e-06,
      "loss": 0.1827,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 0.14720401167869568,
      "eval_runtime": 69.0543,
      "eval_samples_per_second": 8.689,
      "eval_steps_per_second": 4.344,
      "step": 100
    },
    {
      "epoch": 0.2992592592592593,
      "grad_norm": 1.4373360872268677,
      "learning_rate": 7.147147147147148e-06,
      "loss": 0.1167,
      "step": 101
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 1.70066499710083,
      "learning_rate": 7.117117117117117e-06,
      "loss": 0.1711,
      "step": 102
    },
    {
      "epoch": 0.30518518518518517,
      "grad_norm": 1.9972901344299316,
      "learning_rate": 7.087087087087087e-06,
      "loss": 0.2318,
      "step": 103
    },
    {
      "epoch": 0.30814814814814817,
      "grad_norm": 1.3953849077224731,
      "learning_rate": 7.057057057057057e-06,
      "loss": 0.1381,
      "step": 104
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 1.7421494722366333,
      "learning_rate": 7.027027027027028e-06,
      "loss": 0.2262,
      "step": 105
    },
    {
      "epoch": 0.31407407407407406,
      "grad_norm": 1.1622791290283203,
      "learning_rate": 6.996996996996997e-06,
      "loss": 0.1243,
      "step": 106
    },
    {
      "epoch": 0.31703703703703706,
      "grad_norm": 1.4985684156417847,
      "learning_rate": 6.966966966966967e-06,
      "loss": 0.1334,
      "step": 107
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.2254459857940674,
      "learning_rate": 6.936936936936938e-06,
      "loss": 0.1357,
      "step": 108
    },
    {
      "epoch": 0.32296296296296295,
      "grad_norm": 1.575952410697937,
      "learning_rate": 6.906906906906907e-06,
      "loss": 0.1768,
      "step": 109
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 1.565930724143982,
      "learning_rate": 6.876876876876878e-06,
      "loss": 0.1721,
      "step": 110
    },
    {
      "epoch": 0.3288888888888889,
      "grad_norm": 1.7282341718673706,
      "learning_rate": 6.846846846846848e-06,
      "loss": 0.2047,
      "step": 111
    },
    {
      "epoch": 0.33185185185185184,
      "grad_norm": 1.2962411642074585,
      "learning_rate": 6.816816816816817e-06,
      "loss": 0.1472,
      "step": 112
    },
    {
      "epoch": 0.3348148148148148,
      "grad_norm": 1.2629588842391968,
      "learning_rate": 6.786786786786788e-06,
      "loss": 0.1388,
      "step": 113
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 1.7146620750427246,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.1955,
      "step": 114
    },
    {
      "epoch": 0.34074074074074073,
      "grad_norm": 1.4778791666030884,
      "learning_rate": 6.726726726726728e-06,
      "loss": 0.1574,
      "step": 115
    },
    {
      "epoch": 0.3437037037037037,
      "grad_norm": 2.2636680603027344,
      "learning_rate": 6.696696696696697e-06,
      "loss": 0.2554,
      "step": 116
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 1.6432883739471436,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1441,
      "step": 117
    },
    {
      "epoch": 0.3496296296296296,
      "grad_norm": 1.7245186567306519,
      "learning_rate": 6.636636636636637e-06,
      "loss": 0.1982,
      "step": 118
    },
    {
      "epoch": 0.35259259259259257,
      "grad_norm": 1.5929793119430542,
      "learning_rate": 6.606606606606607e-06,
      "loss": 0.2073,
      "step": 119
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.3329964876174927,
      "learning_rate": 6.5765765765765775e-06,
      "loss": 0.16,
      "step": 120
    },
    {
      "epoch": 0.3585185185185185,
      "grad_norm": 1.5517818927764893,
      "learning_rate": 6.546546546546547e-06,
      "loss": 0.1743,
      "step": 121
    },
    {
      "epoch": 0.36148148148148146,
      "grad_norm": 1.1285929679870605,
      "learning_rate": 6.516516516516517e-06,
      "loss": 0.1341,
      "step": 122
    },
    {
      "epoch": 0.36444444444444446,
      "grad_norm": 1.4830421209335327,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.1426,
      "step": 123
    },
    {
      "epoch": 0.3674074074074074,
      "grad_norm": 2.0783519744873047,
      "learning_rate": 6.456456456456457e-06,
      "loss": 0.2473,
      "step": 124
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.5062538385391235,
      "learning_rate": 6.426426426426427e-06,
      "loss": 0.1477,
      "step": 125
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 1.6886259317398071,
      "learning_rate": 6.396396396396397e-06,
      "loss": 0.2089,
      "step": 126
    },
    {
      "epoch": 0.3762962962962963,
      "grad_norm": 1.2187070846557617,
      "learning_rate": 6.366366366366366e-06,
      "loss": 0.1305,
      "step": 127
    },
    {
      "epoch": 0.37925925925925924,
      "grad_norm": 1.1476843357086182,
      "learning_rate": 6.336336336336338e-06,
      "loss": 0.1061,
      "step": 128
    },
    {
      "epoch": 0.38222222222222224,
      "grad_norm": 1.352522611618042,
      "learning_rate": 6.3063063063063065e-06,
      "loss": 0.123,
      "step": 129
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 1.4498250484466553,
      "learning_rate": 6.276276276276276e-06,
      "loss": 0.1098,
      "step": 130
    },
    {
      "epoch": 0.38814814814814813,
      "grad_norm": 1.5865800380706787,
      "learning_rate": 6.246246246246247e-06,
      "loss": 0.1826,
      "step": 131
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 1.351646900177002,
      "learning_rate": 6.2162162162162164e-06,
      "loss": 0.1422,
      "step": 132
    },
    {
      "epoch": 0.3940740740740741,
      "grad_norm": 1.7679228782653809,
      "learning_rate": 6.186186186186187e-06,
      "loss": 0.1959,
      "step": 133
    },
    {
      "epoch": 0.397037037037037,
      "grad_norm": 1.7250772714614868,
      "learning_rate": 6.156156156156157e-06,
      "loss": 0.1839,
      "step": 134
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.6701372861862183,
      "learning_rate": 6.126126126126126e-06,
      "loss": 0.1502,
      "step": 135
    },
    {
      "epoch": 0.40296296296296297,
      "grad_norm": 1.3490396738052368,
      "learning_rate": 6.096096096096097e-06,
      "loss": 0.1081,
      "step": 136
    },
    {
      "epoch": 0.4059259259259259,
      "grad_norm": 1.1195135116577148,
      "learning_rate": 6.066066066066067e-06,
      "loss": 0.0884,
      "step": 137
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 1.5922040939331055,
      "learning_rate": 6.036036036036037e-06,
      "loss": 0.141,
      "step": 138
    },
    {
      "epoch": 0.41185185185185186,
      "grad_norm": 1.5146092176437378,
      "learning_rate": 6.006006006006007e-06,
      "loss": 0.1527,
      "step": 139
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 2.002960681915283,
      "learning_rate": 5.975975975975976e-06,
      "loss": 0.2392,
      "step": 140
    },
    {
      "epoch": 0.4177777777777778,
      "grad_norm": 1.5771265029907227,
      "learning_rate": 5.945945945945947e-06,
      "loss": 0.1912,
      "step": 141
    },
    {
      "epoch": 0.42074074074074075,
      "grad_norm": 1.2592802047729492,
      "learning_rate": 5.915915915915916e-06,
      "loss": 0.1215,
      "step": 142
    },
    {
      "epoch": 0.4237037037037037,
      "grad_norm": 1.6709723472595215,
      "learning_rate": 5.885885885885886e-06,
      "loss": 0.2022,
      "step": 143
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 1.7026015520095825,
      "learning_rate": 5.855855855855856e-06,
      "loss": 0.1642,
      "step": 144
    },
    {
      "epoch": 0.42962962962962964,
      "grad_norm": 1.3867233991622925,
      "learning_rate": 5.825825825825826e-06,
      "loss": 0.1175,
      "step": 145
    },
    {
      "epoch": 0.4325925925925926,
      "grad_norm": 0.9415301084518433,
      "learning_rate": 5.7957957957957965e-06,
      "loss": 0.0776,
      "step": 146
    },
    {
      "epoch": 0.43555555555555553,
      "grad_norm": 1.587620496749878,
      "learning_rate": 5.765765765765766e-06,
      "loss": 0.1301,
      "step": 147
    },
    {
      "epoch": 0.43851851851851853,
      "grad_norm": 1.4494909048080444,
      "learning_rate": 5.735735735735736e-06,
      "loss": 0.1585,
      "step": 148
    },
    {
      "epoch": 0.4414814814814815,
      "grad_norm": 1.6191442012786865,
      "learning_rate": 5.7057057057057065e-06,
      "loss": 0.1676,
      "step": 149
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.7290399074554443,
      "learning_rate": 5.675675675675676e-06,
      "loss": 0.2068,
      "step": 150
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.14076729118824005,
      "eval_runtime": 69.0508,
      "eval_samples_per_second": 8.689,
      "eval_steps_per_second": 4.345,
      "step": 150
    },
    {
      "epoch": 0.4474074074074074,
      "grad_norm": 1.8301669359207153,
      "learning_rate": 5.645645645645647e-06,
      "loss": 0.207,
      "step": 151
    },
    {
      "epoch": 0.45037037037037037,
      "grad_norm": 1.1271215677261353,
      "learning_rate": 5.615615615615616e-06,
      "loss": 0.1141,
      "step": 152
    },
    {
      "epoch": 0.4533333333333333,
      "grad_norm": 1.5564805269241333,
      "learning_rate": 5.585585585585585e-06,
      "loss": 0.1458,
      "step": 153
    },
    {
      "epoch": 0.4562962962962963,
      "grad_norm": 1.7967830896377563,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.1637,
      "step": 154
    },
    {
      "epoch": 0.45925925925925926,
      "grad_norm": 0.9989104270935059,
      "learning_rate": 5.5255255255255255e-06,
      "loss": 0.0865,
      "step": 155
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.7127548456192017,
      "learning_rate": 5.495495495495496e-06,
      "loss": 0.0423,
      "step": 156
    },
    {
      "epoch": 0.4651851851851852,
      "grad_norm": 1.7433053255081177,
      "learning_rate": 5.465465465465466e-06,
      "loss": 0.1758,
      "step": 157
    },
    {
      "epoch": 0.46814814814814815,
      "grad_norm": 1.3249409198760986,
      "learning_rate": 5.4354354354354355e-06,
      "loss": 0.128,
      "step": 158
    },
    {
      "epoch": 0.4711111111111111,
      "grad_norm": 1.6176677942276,
      "learning_rate": 5.405405405405406e-06,
      "loss": 0.1886,
      "step": 159
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 1.2487632036209106,
      "learning_rate": 5.375375375375376e-06,
      "loss": 0.1016,
      "step": 160
    },
    {
      "epoch": 0.47703703703703704,
      "grad_norm": 1.4374430179595947,
      "learning_rate": 5.345345345345346e-06,
      "loss": 0.1548,
      "step": 161
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.2337255477905273,
      "learning_rate": 5.315315315315316e-06,
      "loss": 0.0985,
      "step": 162
    },
    {
      "epoch": 0.482962962962963,
      "grad_norm": 1.3573967218399048,
      "learning_rate": 5.285285285285286e-06,
      "loss": 0.1368,
      "step": 163
    },
    {
      "epoch": 0.48592592592592593,
      "grad_norm": 1.2555123567581177,
      "learning_rate": 5.255255255255256e-06,
      "loss": 0.0961,
      "step": 164
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 1.546203851699829,
      "learning_rate": 5.225225225225226e-06,
      "loss": 0.1623,
      "step": 165
    },
    {
      "epoch": 0.4918518518518519,
      "grad_norm": 1.2774075269699097,
      "learning_rate": 5.195195195195195e-06,
      "loss": 0.1121,
      "step": 166
    },
    {
      "epoch": 0.4948148148148148,
      "grad_norm": 1.397123098373413,
      "learning_rate": 5.165165165165165e-06,
      "loss": 0.1238,
      "step": 167
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 1.9205617904663086,
      "learning_rate": 5.135135135135135e-06,
      "loss": 0.244,
      "step": 168
    },
    {
      "epoch": 0.5007407407407407,
      "grad_norm": 1.3287469148635864,
      "learning_rate": 5.105105105105106e-06,
      "loss": 0.1384,
      "step": 169
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 1.6500308513641357,
      "learning_rate": 5.075075075075075e-06,
      "loss": 0.1931,
      "step": 170
    },
    {
      "epoch": 0.5066666666666667,
      "grad_norm": 1.4601924419403076,
      "learning_rate": 5.045045045045045e-06,
      "loss": 0.1724,
      "step": 171
    },
    {
      "epoch": 0.5096296296296297,
      "grad_norm": 1.8577477931976318,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.1895,
      "step": 172
    },
    {
      "epoch": 0.5125925925925926,
      "grad_norm": 1.6146597862243652,
      "learning_rate": 4.984984984984985e-06,
      "loss": 0.1828,
      "step": 173
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 1.5603734254837036,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.1628,
      "step": 174
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.529084324836731,
      "learning_rate": 4.9249249249249255e-06,
      "loss": 0.1541,
      "step": 175
    },
    {
      "epoch": 0.5214814814814814,
      "grad_norm": 1.5798418521881104,
      "learning_rate": 4.894894894894895e-06,
      "loss": 0.1771,
      "step": 176
    },
    {
      "epoch": 0.5244444444444445,
      "grad_norm": 1.2269628047943115,
      "learning_rate": 4.864864864864866e-06,
      "loss": 0.0999,
      "step": 177
    },
    {
      "epoch": 0.5274074074074074,
      "grad_norm": 1.5021451711654663,
      "learning_rate": 4.8348348348348355e-06,
      "loss": 0.1537,
      "step": 178
    },
    {
      "epoch": 0.5303703703703704,
      "grad_norm": 1.5607895851135254,
      "learning_rate": 4.804804804804805e-06,
      "loss": 0.1653,
      "step": 179
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.2029038667678833,
      "learning_rate": 4.774774774774775e-06,
      "loss": 0.1286,
      "step": 180
    },
    {
      "epoch": 0.5362962962962963,
      "grad_norm": 1.2021962404251099,
      "learning_rate": 4.7447447447447454e-06,
      "loss": 0.1283,
      "step": 181
    },
    {
      "epoch": 0.5392592592592592,
      "grad_norm": 1.5320271253585815,
      "learning_rate": 4.714714714714715e-06,
      "loss": 0.1367,
      "step": 182
    },
    {
      "epoch": 0.5422222222222223,
      "grad_norm": 1.362162709236145,
      "learning_rate": 4.684684684684685e-06,
      "loss": 0.1065,
      "step": 183
    },
    {
      "epoch": 0.5451851851851852,
      "grad_norm": 1.6120872497558594,
      "learning_rate": 4.654654654654655e-06,
      "loss": 0.1946,
      "step": 184
    },
    {
      "epoch": 0.5481481481481482,
      "grad_norm": 1.20976722240448,
      "learning_rate": 4.624624624624625e-06,
      "loss": 0.0967,
      "step": 185
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 1.6096454858779907,
      "learning_rate": 4.594594594594596e-06,
      "loss": 0.1764,
      "step": 186
    },
    {
      "epoch": 0.554074074074074,
      "grad_norm": 1.6881582736968994,
      "learning_rate": 4.5645645645645645e-06,
      "loss": 0.2095,
      "step": 187
    },
    {
      "epoch": 0.557037037037037,
      "grad_norm": 1.2607136964797974,
      "learning_rate": 4.534534534534535e-06,
      "loss": 0.147,
      "step": 188
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.5755300521850586,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.1774,
      "step": 189
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 1.5509341955184937,
      "learning_rate": 4.474474474474475e-06,
      "loss": 0.157,
      "step": 190
    },
    {
      "epoch": 0.5659259259259259,
      "grad_norm": 1.2741116285324097,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.145,
      "step": 191
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 1.2587403059005737,
      "learning_rate": 4.414414414414415e-06,
      "loss": 0.1045,
      "step": 192
    },
    {
      "epoch": 0.5718518518518518,
      "grad_norm": 1.50287926197052,
      "learning_rate": 4.384384384384384e-06,
      "loss": 0.1844,
      "step": 193
    },
    {
      "epoch": 0.5748148148148148,
      "grad_norm": 1.3881644010543823,
      "learning_rate": 4.354354354354355e-06,
      "loss": 0.1771,
      "step": 194
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 1.2809717655181885,
      "learning_rate": 4.324324324324325e-06,
      "loss": 0.1206,
      "step": 195
    },
    {
      "epoch": 0.5807407407407408,
      "grad_norm": 1.235787034034729,
      "learning_rate": 4.294294294294294e-06,
      "loss": 0.1297,
      "step": 196
    },
    {
      "epoch": 0.5837037037037037,
      "grad_norm": 1.3157249689102173,
      "learning_rate": 4.264264264264265e-06,
      "loss": 0.1548,
      "step": 197
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 1.4521801471710205,
      "learning_rate": 4.234234234234235e-06,
      "loss": 0.158,
      "step": 198
    },
    {
      "epoch": 0.5896296296296296,
      "grad_norm": 1.2876291275024414,
      "learning_rate": 4.204204204204204e-06,
      "loss": 0.1241,
      "step": 199
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.2902220487594604,
      "learning_rate": 4.174174174174174e-06,
      "loss": 0.1147,
      "step": 200
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 0.1367669701576233,
      "eval_runtime": 69.0997,
      "eval_samples_per_second": 8.683,
      "eval_steps_per_second": 4.342,
      "step": 200
    },
    {
      "epoch": 0.5955555555555555,
      "grad_norm": 1.61051607131958,
      "learning_rate": 4.1441441441441446e-06,
      "loss": 0.1916,
      "step": 201
    },
    {
      "epoch": 0.5985185185185186,
      "grad_norm": 1.3838216066360474,
      "learning_rate": 4.114114114114114e-06,
      "loss": 0.1445,
      "step": 202
    },
    {
      "epoch": 0.6014814814814815,
      "grad_norm": 1.1877784729003906,
      "learning_rate": 4.084084084084085e-06,
      "loss": 0.0982,
      "step": 203
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 1.9751864671707153,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.2126,
      "step": 204
    },
    {
      "epoch": 0.6074074074074074,
      "grad_norm": 1.5907570123672485,
      "learning_rate": 4.024024024024024e-06,
      "loss": 0.1673,
      "step": 205
    },
    {
      "epoch": 0.6103703703703703,
      "grad_norm": 1.0832182168960571,
      "learning_rate": 3.993993993993994e-06,
      "loss": 0.1153,
      "step": 206
    },
    {
      "epoch": 0.6133333333333333,
      "grad_norm": 1.1242703199386597,
      "learning_rate": 3.9639639639639645e-06,
      "loss": 0.0807,
      "step": 207
    },
    {
      "epoch": 0.6162962962962963,
      "grad_norm": 1.0970396995544434,
      "learning_rate": 3.933933933933934e-06,
      "loss": 0.1042,
      "step": 208
    },
    {
      "epoch": 0.6192592592592593,
      "grad_norm": 1.3038502931594849,
      "learning_rate": 3.903903903903904e-06,
      "loss": 0.1509,
      "step": 209
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 1.4616066217422485,
      "learning_rate": 3.8738738738738744e-06,
      "loss": 0.1624,
      "step": 210
    },
    {
      "epoch": 0.6251851851851852,
      "grad_norm": 1.4689220190048218,
      "learning_rate": 3.843843843843844e-06,
      "loss": 0.164,
      "step": 211
    },
    {
      "epoch": 0.6281481481481481,
      "grad_norm": 1.3021526336669922,
      "learning_rate": 3.8138138138138143e-06,
      "loss": 0.1387,
      "step": 212
    },
    {
      "epoch": 0.6311111111111111,
      "grad_norm": 1.5484747886657715,
      "learning_rate": 3.7837837837837844e-06,
      "loss": 0.1594,
      "step": 213
    },
    {
      "epoch": 0.6340740740740741,
      "grad_norm": 1.3926817178726196,
      "learning_rate": 3.7537537537537537e-06,
      "loss": 0.1356,
      "step": 214
    },
    {
      "epoch": 0.6370370370370371,
      "grad_norm": 1.2632286548614502,
      "learning_rate": 3.723723723723724e-06,
      "loss": 0.111,
      "step": 215
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.3209017515182495,
      "learning_rate": 3.693693693693694e-06,
      "loss": 0.1339,
      "step": 216
    },
    {
      "epoch": 0.642962962962963,
      "grad_norm": 1.2629365921020508,
      "learning_rate": 3.663663663663664e-06,
      "loss": 0.133,
      "step": 217
    },
    {
      "epoch": 0.6459259259259259,
      "grad_norm": 1.2278132438659668,
      "learning_rate": 3.633633633633634e-06,
      "loss": 0.0962,
      "step": 218
    },
    {
      "epoch": 0.6488888888888888,
      "grad_norm": 1.665931224822998,
      "learning_rate": 3.603603603603604e-06,
      "loss": 0.184,
      "step": 219
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 1.2895967960357666,
      "learning_rate": 3.573573573573574e-06,
      "loss": 0.1253,
      "step": 220
    },
    {
      "epoch": 0.6548148148148148,
      "grad_norm": 1.0594205856323242,
      "learning_rate": 3.5435435435435437e-06,
      "loss": 0.1319,
      "step": 221
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 1.2554035186767578,
      "learning_rate": 3.513513513513514e-06,
      "loss": 0.126,
      "step": 222
    },
    {
      "epoch": 0.6607407407407407,
      "grad_norm": 1.3189946413040161,
      "learning_rate": 3.4834834834834835e-06,
      "loss": 0.1216,
      "step": 223
    },
    {
      "epoch": 0.6637037037037037,
      "grad_norm": 1.2903859615325928,
      "learning_rate": 3.4534534534534537e-06,
      "loss": 0.0925,
      "step": 224
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.273701548576355,
      "learning_rate": 3.423423423423424e-06,
      "loss": 0.1053,
      "step": 225
    },
    {
      "epoch": 0.6696296296296296,
      "grad_norm": 1.5140513181686401,
      "learning_rate": 3.393393393393394e-06,
      "loss": 0.1165,
      "step": 226
    },
    {
      "epoch": 0.6725925925925926,
      "grad_norm": 1.5443241596221924,
      "learning_rate": 3.363363363363364e-06,
      "loss": 0.1742,
      "step": 227
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 1.1264605522155762,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0902,
      "step": 228
    },
    {
      "epoch": 0.6785185185185185,
      "grad_norm": 1.039962649345398,
      "learning_rate": 3.3033033033033035e-06,
      "loss": 0.0858,
      "step": 229
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.0778369903564453,
      "learning_rate": 3.2732732732732736e-06,
      "loss": 0.1064,
      "step": 230
    },
    {
      "epoch": 0.6844444444444444,
      "grad_norm": 1.7718640565872192,
      "learning_rate": 3.2432432432432437e-06,
      "loss": 0.1944,
      "step": 231
    },
    {
      "epoch": 0.6874074074074074,
      "grad_norm": 1.3493353128433228,
      "learning_rate": 3.2132132132132134e-06,
      "loss": 0.1429,
      "step": 232
    },
    {
      "epoch": 0.6903703703703704,
      "grad_norm": 1.2641777992248535,
      "learning_rate": 3.183183183183183e-06,
      "loss": 0.1155,
      "step": 233
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 1.2105985879898071,
      "learning_rate": 3.1531531531531532e-06,
      "loss": 0.0979,
      "step": 234
    },
    {
      "epoch": 0.6962962962962963,
      "grad_norm": 1.673607349395752,
      "learning_rate": 3.1231231231231234e-06,
      "loss": 0.1319,
      "step": 235
    },
    {
      "epoch": 0.6992592592592592,
      "grad_norm": 1.7171119451522827,
      "learning_rate": 3.0930930930930935e-06,
      "loss": 0.163,
      "step": 236
    },
    {
      "epoch": 0.7022222222222222,
      "grad_norm": 1.4846197366714478,
      "learning_rate": 3.063063063063063e-06,
      "loss": 0.15,
      "step": 237
    },
    {
      "epoch": 0.7051851851851851,
      "grad_norm": 1.511883020401001,
      "learning_rate": 3.0330330330330333e-06,
      "loss": 0.1442,
      "step": 238
    },
    {
      "epoch": 0.7081481481481482,
      "grad_norm": 1.3171648979187012,
      "learning_rate": 3.0030030030030034e-06,
      "loss": 0.1039,
      "step": 239
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.5615602731704712,
      "learning_rate": 2.9729729729729736e-06,
      "loss": 0.1715,
      "step": 240
    },
    {
      "epoch": 0.7140740740740741,
      "grad_norm": 1.4079703092575073,
      "learning_rate": 2.942942942942943e-06,
      "loss": 0.1487,
      "step": 241
    },
    {
      "epoch": 0.717037037037037,
      "grad_norm": 1.4462891817092896,
      "learning_rate": 2.912912912912913e-06,
      "loss": 0.1221,
      "step": 242
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.620666265487671,
      "learning_rate": 2.882882882882883e-06,
      "loss": 0.1896,
      "step": 243
    },
    {
      "epoch": 0.7229629629629629,
      "grad_norm": 1.261318564414978,
      "learning_rate": 2.8528528528528532e-06,
      "loss": 0.1098,
      "step": 244
    },
    {
      "epoch": 0.725925925925926,
      "grad_norm": 1.0842806100845337,
      "learning_rate": 2.8228228228228234e-06,
      "loss": 0.0804,
      "step": 245
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 1.6169710159301758,
      "learning_rate": 2.7927927927927926e-06,
      "loss": 0.1798,
      "step": 246
    },
    {
      "epoch": 0.7318518518518519,
      "grad_norm": 1.2281765937805176,
      "learning_rate": 2.7627627627627628e-06,
      "loss": 0.0958,
      "step": 247
    },
    {
      "epoch": 0.7348148148148148,
      "grad_norm": 1.2307597398757935,
      "learning_rate": 2.732732732732733e-06,
      "loss": 0.1043,
      "step": 248
    },
    {
      "epoch": 0.7377777777777778,
      "grad_norm": 1.3789561986923218,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.162,
      "step": 249
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.5587233304977417,
      "learning_rate": 2.672672672672673e-06,
      "loss": 0.1573,
      "step": 250
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.13497158885002136,
      "eval_runtime": 68.9575,
      "eval_samples_per_second": 8.701,
      "eval_steps_per_second": 4.351,
      "step": 250
    },
    {
      "epoch": 0.7437037037037038,
      "grad_norm": 1.4598321914672852,
      "learning_rate": 2.642642642642643e-06,
      "loss": 0.14,
      "step": 251
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 1.2978421449661255,
      "learning_rate": 2.612612612612613e-06,
      "loss": 0.118,
      "step": 252
    },
    {
      "epoch": 0.7496296296296296,
      "grad_norm": 1.607700228691101,
      "learning_rate": 2.5825825825825827e-06,
      "loss": 0.1571,
      "step": 253
    },
    {
      "epoch": 0.7525925925925926,
      "grad_norm": 1.4654117822647095,
      "learning_rate": 2.552552552552553e-06,
      "loss": 0.1255,
      "step": 254
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 1.4342758655548096,
      "learning_rate": 2.5225225225225225e-06,
      "loss": 0.1417,
      "step": 255
    },
    {
      "epoch": 0.7585185185185185,
      "grad_norm": 1.516230821609497,
      "learning_rate": 2.4924924924924926e-06,
      "loss": 0.1458,
      "step": 256
    },
    {
      "epoch": 0.7614814814814815,
      "grad_norm": 1.3593307733535767,
      "learning_rate": 2.4624624624624628e-06,
      "loss": 0.1704,
      "step": 257
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 1.4198930263519287,
      "learning_rate": 2.432432432432433e-06,
      "loss": 0.1595,
      "step": 258
    },
    {
      "epoch": 0.7674074074074074,
      "grad_norm": 4.913775444030762,
      "learning_rate": 2.4024024024024026e-06,
      "loss": 0.162,
      "step": 259
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 1.4251230955123901,
      "learning_rate": 2.3723723723723727e-06,
      "loss": 0.1387,
      "step": 260
    },
    {
      "epoch": 0.7733333333333333,
      "grad_norm": 1.8029718399047852,
      "learning_rate": 2.3423423423423424e-06,
      "loss": 0.1893,
      "step": 261
    },
    {
      "epoch": 0.7762962962962963,
      "grad_norm": 1.7383553981781006,
      "learning_rate": 2.3123123123123125e-06,
      "loss": 0.1746,
      "step": 262
    },
    {
      "epoch": 0.7792592592592592,
      "grad_norm": 1.8577227592468262,
      "learning_rate": 2.2822822822822822e-06,
      "loss": 0.2032,
      "step": 263
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 1.2173237800598145,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.1005,
      "step": 264
    },
    {
      "epoch": 0.7851851851851852,
      "grad_norm": 1.2800841331481934,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.0994,
      "step": 265
    },
    {
      "epoch": 0.7881481481481482,
      "grad_norm": 1.143734097480774,
      "learning_rate": 2.192192192192192e-06,
      "loss": 0.11,
      "step": 266
    },
    {
      "epoch": 0.7911111111111111,
      "grad_norm": 1.6179982423782349,
      "learning_rate": 2.1621621621621623e-06,
      "loss": 0.1707,
      "step": 267
    },
    {
      "epoch": 0.794074074074074,
      "grad_norm": 1.3005707263946533,
      "learning_rate": 2.1321321321321325e-06,
      "loss": 0.1155,
      "step": 268
    },
    {
      "epoch": 0.797037037037037,
      "grad_norm": 1.7009978294372559,
      "learning_rate": 2.102102102102102e-06,
      "loss": 0.1664,
      "step": 269
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.8830610513687134,
      "learning_rate": 2.0720720720720723e-06,
      "loss": 0.2279,
      "step": 270
    },
    {
      "epoch": 0.802962962962963,
      "grad_norm": 1.2744908332824707,
      "learning_rate": 2.0420420420420424e-06,
      "loss": 0.1223,
      "step": 271
    },
    {
      "epoch": 0.8059259259259259,
      "grad_norm": 1.5405086278915405,
      "learning_rate": 2.012012012012012e-06,
      "loss": 0.1559,
      "step": 272
    },
    {
      "epoch": 0.8088888888888889,
      "grad_norm": 1.751500129699707,
      "learning_rate": 1.9819819819819822e-06,
      "loss": 0.2062,
      "step": 273
    },
    {
      "epoch": 0.8118518518518518,
      "grad_norm": 0.9337794780731201,
      "learning_rate": 1.951951951951952e-06,
      "loss": 0.0749,
      "step": 274
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.4448208808898926,
      "learning_rate": 1.921921921921922e-06,
      "loss": 0.1745,
      "step": 275
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 1.7837474346160889,
      "learning_rate": 1.8918918918918922e-06,
      "loss": 0.1949,
      "step": 276
    },
    {
      "epoch": 0.8207407407407408,
      "grad_norm": 1.4676810503005981,
      "learning_rate": 1.861861861861862e-06,
      "loss": 0.1492,
      "step": 277
    },
    {
      "epoch": 0.8237037037037037,
      "grad_norm": 1.0239405632019043,
      "learning_rate": 1.831831831831832e-06,
      "loss": 0.0803,
      "step": 278
    },
    {
      "epoch": 0.8266666666666667,
      "grad_norm": 1.3506311178207397,
      "learning_rate": 1.801801801801802e-06,
      "loss": 0.1189,
      "step": 279
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 1.4332555532455444,
      "learning_rate": 1.7717717717717719e-06,
      "loss": 0.1625,
      "step": 280
    },
    {
      "epoch": 0.8325925925925926,
      "grad_norm": 1.029037356376648,
      "learning_rate": 1.7417417417417418e-06,
      "loss": 0.0831,
      "step": 281
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 1.7254611253738403,
      "learning_rate": 1.711711711711712e-06,
      "loss": 0.1731,
      "step": 282
    },
    {
      "epoch": 0.8385185185185186,
      "grad_norm": 1.1570535898208618,
      "learning_rate": 1.681681681681682e-06,
      "loss": 0.1088,
      "step": 283
    },
    {
      "epoch": 0.8414814814814815,
      "grad_norm": 1.4497860670089722,
      "learning_rate": 1.6516516516516517e-06,
      "loss": 0.1402,
      "step": 284
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 1.4440678358078003,
      "learning_rate": 1.6216216216216219e-06,
      "loss": 0.1078,
      "step": 285
    },
    {
      "epoch": 0.8474074074074074,
      "grad_norm": 1.103289008140564,
      "learning_rate": 1.5915915915915916e-06,
      "loss": 0.0977,
      "step": 286
    },
    {
      "epoch": 0.8503703703703703,
      "grad_norm": 1.1989885568618774,
      "learning_rate": 1.5615615615615617e-06,
      "loss": 0.0959,
      "step": 287
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.1961288452148438,
      "learning_rate": 1.5315315315315316e-06,
      "loss": 0.1021,
      "step": 288
    },
    {
      "epoch": 0.8562962962962963,
      "grad_norm": 1.341914415359497,
      "learning_rate": 1.5015015015015017e-06,
      "loss": 0.1429,
      "step": 289
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 0.8464846611022949,
      "learning_rate": 1.4714714714714714e-06,
      "loss": 0.0614,
      "step": 290
    },
    {
      "epoch": 0.8622222222222222,
      "grad_norm": 1.175203561782837,
      "learning_rate": 1.4414414414414416e-06,
      "loss": 0.1073,
      "step": 291
    },
    {
      "epoch": 0.8651851851851852,
      "grad_norm": 0.9819923639297485,
      "learning_rate": 1.4114114114114117e-06,
      "loss": 0.0911,
      "step": 292
    },
    {
      "epoch": 0.8681481481481481,
      "grad_norm": 1.2278133630752563,
      "learning_rate": 1.3813813813813814e-06,
      "loss": 0.0918,
      "step": 293
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 1.6723119020462036,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.1981,
      "step": 294
    },
    {
      "epoch": 0.8740740740740741,
      "grad_norm": 1.006776213645935,
      "learning_rate": 1.3213213213213214e-06,
      "loss": 0.0927,
      "step": 295
    },
    {
      "epoch": 0.8770370370370371,
      "grad_norm": 1.5855094194412231,
      "learning_rate": 1.2912912912912913e-06,
      "loss": 0.1408,
      "step": 296
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.1803261041641235,
      "learning_rate": 1.2612612612612613e-06,
      "loss": 0.093,
      "step": 297
    },
    {
      "epoch": 0.882962962962963,
      "grad_norm": 1.461946725845337,
      "learning_rate": 1.2312312312312314e-06,
      "loss": 0.1597,
      "step": 298
    },
    {
      "epoch": 0.8859259259259259,
      "grad_norm": 1.2585445642471313,
      "learning_rate": 1.2012012012012013e-06,
      "loss": 0.1169,
      "step": 299
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.2737395763397217,
      "learning_rate": 1.1711711711711712e-06,
      "loss": 0.1036,
      "step": 300
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.1327555775642395,
      "eval_runtime": 69.1325,
      "eval_samples_per_second": 8.679,
      "eval_steps_per_second": 4.339,
      "step": 300
    },
    {
      "epoch": 0.8918518518518519,
      "grad_norm": 1.4698344469070435,
      "learning_rate": 1.1411411411411411e-06,
      "loss": 0.1536,
      "step": 301
    },
    {
      "epoch": 0.8948148148148148,
      "grad_norm": 1.5235050916671753,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.134,
      "step": 302
    },
    {
      "epoch": 0.8977777777777778,
      "grad_norm": 1.164963960647583,
      "learning_rate": 1.0810810810810812e-06,
      "loss": 0.0887,
      "step": 303
    },
    {
      "epoch": 0.9007407407407407,
      "grad_norm": 1.5177470445632935,
      "learning_rate": 1.051051051051051e-06,
      "loss": 0.1824,
      "step": 304
    },
    {
      "epoch": 0.9037037037037037,
      "grad_norm": 1.2707066535949707,
      "learning_rate": 1.0210210210210212e-06,
      "loss": 0.1051,
      "step": 305
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 1.6276848316192627,
      "learning_rate": 9.909909909909911e-07,
      "loss": 0.1203,
      "step": 306
    },
    {
      "epoch": 0.9096296296296297,
      "grad_norm": 0.9868956804275513,
      "learning_rate": 9.60960960960961e-07,
      "loss": 0.0921,
      "step": 307
    },
    {
      "epoch": 0.9125925925925926,
      "grad_norm": 1.5601303577423096,
      "learning_rate": 9.30930930930931e-07,
      "loss": 0.1833,
      "step": 308
    },
    {
      "epoch": 0.9155555555555556,
      "grad_norm": 1.7755447626113892,
      "learning_rate": 9.00900900900901e-07,
      "loss": 0.1902,
      "step": 309
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 1.3140467405319214,
      "learning_rate": 8.708708708708709e-07,
      "loss": 0.1309,
      "step": 310
    },
    {
      "epoch": 0.9214814814814815,
      "grad_norm": 0.899591863155365,
      "learning_rate": 8.40840840840841e-07,
      "loss": 0.0763,
      "step": 311
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 1.0422495603561401,
      "learning_rate": 8.108108108108109e-07,
      "loss": 0.0932,
      "step": 312
    },
    {
      "epoch": 0.9274074074074075,
      "grad_norm": 1.5284807682037354,
      "learning_rate": 7.807807807807808e-07,
      "loss": 0.1636,
      "step": 313
    },
    {
      "epoch": 0.9303703703703704,
      "grad_norm": 1.161861777305603,
      "learning_rate": 7.507507507507509e-07,
      "loss": 0.08,
      "step": 314
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 1.4089093208312988,
      "learning_rate": 7.207207207207208e-07,
      "loss": 0.1319,
      "step": 315
    },
    {
      "epoch": 0.9362962962962963,
      "grad_norm": 1.4112168550491333,
      "learning_rate": 6.906906906906907e-07,
      "loss": 0.1693,
      "step": 316
    },
    {
      "epoch": 0.9392592592592592,
      "grad_norm": 1.3189918994903564,
      "learning_rate": 6.606606606606607e-07,
      "loss": 0.1206,
      "step": 317
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 2.039505958557129,
      "learning_rate": 6.306306306306306e-07,
      "loss": 0.1227,
      "step": 318
    },
    {
      "epoch": 0.9451851851851852,
      "grad_norm": 1.229431390762329,
      "learning_rate": 6.006006006006006e-07,
      "loss": 0.1319,
      "step": 319
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 1.2763376235961914,
      "learning_rate": 5.705705705705706e-07,
      "loss": 0.1147,
      "step": 320
    },
    {
      "epoch": 0.9511111111111111,
      "grad_norm": 1.243894338607788,
      "learning_rate": 5.405405405405406e-07,
      "loss": 0.123,
      "step": 321
    },
    {
      "epoch": 0.9540740740740741,
      "grad_norm": 1.30033278465271,
      "learning_rate": 5.105105105105106e-07,
      "loss": 0.1334,
      "step": 322
    },
    {
      "epoch": 0.957037037037037,
      "grad_norm": 1.148809552192688,
      "learning_rate": 4.804804804804805e-07,
      "loss": 0.1212,
      "step": 323
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.2611253261566162,
      "learning_rate": 4.504504504504505e-07,
      "loss": 0.0872,
      "step": 324
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.9735010862350464,
      "learning_rate": 4.204204204204205e-07,
      "loss": 0.0871,
      "step": 325
    },
    {
      "epoch": 0.965925925925926,
      "grad_norm": 1.4074807167053223,
      "learning_rate": 3.903903903903904e-07,
      "loss": 0.1555,
      "step": 326
    },
    {
      "epoch": 0.9688888888888889,
      "grad_norm": 1.0532164573669434,
      "learning_rate": 3.603603603603604e-07,
      "loss": 0.0844,
      "step": 327
    },
    {
      "epoch": 0.9718518518518519,
      "grad_norm": 1.4992691278457642,
      "learning_rate": 3.3033033033033036e-07,
      "loss": 0.1536,
      "step": 328
    },
    {
      "epoch": 0.9748148148148148,
      "grad_norm": 1.3960808515548706,
      "learning_rate": 3.003003003003003e-07,
      "loss": 0.1364,
      "step": 329
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.1466952562332153,
      "learning_rate": 2.702702702702703e-07,
      "loss": 0.0773,
      "step": 330
    },
    {
      "epoch": 0.9807407407407407,
      "grad_norm": 1.6948280334472656,
      "learning_rate": 2.4024024024024026e-07,
      "loss": 0.1798,
      "step": 331
    },
    {
      "epoch": 0.9837037037037037,
      "grad_norm": 1.1860636472702026,
      "learning_rate": 2.1021021021021025e-07,
      "loss": 0.1369,
      "step": 332
    },
    {
      "epoch": 0.9866666666666667,
      "grad_norm": 1.2593287229537964,
      "learning_rate": 1.801801801801802e-07,
      "loss": 0.1103,
      "step": 333
    },
    {
      "epoch": 0.9896296296296296,
      "grad_norm": 1.0438348054885864,
      "learning_rate": 1.5015015015015016e-07,
      "loss": 0.0924,
      "step": 334
    },
    {
      "epoch": 0.9925925925925926,
      "grad_norm": 1.5413618087768555,
      "learning_rate": 1.2012012012012013e-07,
      "loss": 0.1582,
      "step": 335
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 1.5658713579177856,
      "learning_rate": 9.00900900900901e-08,
      "loss": 0.1662,
      "step": 336
    },
    {
      "epoch": 0.9985185185185185,
      "grad_norm": 1.50312340259552,
      "learning_rate": 6.006006006006006e-08,
      "loss": 0.1395,
      "step": 337
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.954053282737732,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1468,
      "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": 2.8975168118133965e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}