{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.9564288854599,
      "learning_rate": 0.0,
      "loss": 0.5559,
      "step": 1
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 1.9618585109710693,
      "learning_rate": 7.142857142857143e-07,
      "loss": 0.557,
      "step": 2
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.8868215084075928,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.5259,
      "step": 3
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 1.9663314819335938,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 0.5896,
      "step": 4
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 1.9502723217010498,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.5813,
      "step": 5
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.7730481624603271,
      "learning_rate": 3.5714285714285718e-06,
      "loss": 0.5903,
      "step": 6
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 1.3099936246871948,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.55,
      "step": 7
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 1.1662466526031494,
      "learning_rate": 5e-06,
      "loss": 0.5079,
      "step": 8
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 1.130672574043274,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.531,
      "step": 9
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 1.1151994466781616,
      "learning_rate": 6.4285714285714295e-06,
      "loss": 0.4898,
      "step": 10
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 1.0189985036849976,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.4947,
      "step": 11
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.3632686138153076,
      "learning_rate": 7.857142857142858e-06,
      "loss": 0.5293,
      "step": 12
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4208382368087769,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.5368,
      "step": 13
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 1.2137521505355835,
      "learning_rate": 9.285714285714288e-06,
      "loss": 0.4978,
      "step": 14
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.9733414649963379,
      "learning_rate": 1e-05,
      "loss": 0.4951,
      "step": 15
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.9022915363311768,
      "learning_rate": 9.998445910004082e-06,
      "loss": 0.458,
      "step": 16
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.9689977169036865,
      "learning_rate": 9.993784606094612e-06,
      "loss": 0.4841,
      "step": 17
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.9414687156677246,
      "learning_rate": 9.986018985905901e-06,
      "loss": 0.4624,
      "step": 18
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.8624492287635803,
      "learning_rate": 9.975153876827008e-06,
      "loss": 0.4951,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8624492287635803,
      "learning_rate": 9.961196033000862e-06,
      "loss": 0.4747,
      "step": 20
    },
    {
      "epoch": 1.0512820512820513,
      "grad_norm": 0.5165559649467468,
      "learning_rate": 9.944154131125643e-06,
      "loss": 0.4401,
      "step": 21
    },
    {
      "epoch": 1.1025641025641026,
      "grad_norm": 0.5158498287200928,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.418,
      "step": 22
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.38535529375076294,
      "learning_rate": 9.900862439242719e-06,
      "loss": 0.4326,
      "step": 23
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 0.47305503487586975,
      "learning_rate": 9.874639560909118e-06,
      "loss": 0.4238,
      "step": 24
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.5309538841247559,
      "learning_rate": 9.84538643114539e-06,
      "loss": 0.414,
      "step": 25
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.4675985872745514,
      "learning_rate": 9.81312123475006e-06,
      "loss": 0.4323,
      "step": 26
    },
    {
      "epoch": 1.358974358974359,
      "grad_norm": 0.47324472665786743,
      "learning_rate": 9.777864028930705e-06,
      "loss": 0.4064,
      "step": 27
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.4767780005931854,
      "learning_rate": 9.73963673083566e-06,
      "loss": 0.4046,
      "step": 28
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.664870023727417,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.4267,
      "step": 29
    },
    {
      "epoch": 1.5128205128205128,
      "grad_norm": 0.4001618027687073,
      "learning_rate": 9.654368743221022e-06,
      "loss": 0.3848,
      "step": 30
    },
    {
      "epoch": 1.564102564102564,
      "grad_norm": 0.5149535536766052,
      "learning_rate": 9.60738105935204e-06,
      "loss": 0.3986,
      "step": 31
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.47418010234832764,
      "learning_rate": 9.557529261558367e-06,
      "loss": 0.3846,
      "step": 32
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.42334499955177307,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.4087,
      "step": 33
    },
    {
      "epoch": 1.717948717948718,
      "grad_norm": 0.4349881410598755,
      "learning_rate": 9.449359044057344e-06,
      "loss": 0.3742,
      "step": 34
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.4938202202320099,
      "learning_rate": 9.391107866851143e-06,
      "loss": 0.3718,
      "step": 35
    },
    {
      "epoch": 1.8205128205128205,
      "grad_norm": 0.4592251479625702,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.3984,
      "step": 36
    },
    {
      "epoch": 1.8717948717948718,
      "grad_norm": 0.44737333059310913,
      "learning_rate": 9.266454408160779e-06,
      "loss": 0.3645,
      "step": 37
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.40523794293403625,
      "learning_rate": 9.200129615753858e-06,
      "loss": 0.3692,
      "step": 38
    },
    {
      "epoch": 1.9743589743589745,
      "grad_norm": 0.43106111884117126,
      "learning_rate": 9.131193871579975e-06,
      "loss": 0.3639,
      "step": 39
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8424760103225708,
      "learning_rate": 9.059690028579285e-06,
      "loss": 0.3757,
      "step": 40
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.8100979328155518,
      "learning_rate": 8.985662536114614e-06,
      "loss": 0.3387,
      "step": 41
    },
    {
      "epoch": 2.1025641025641026,
      "grad_norm": 0.7191058397293091,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.3416,
      "step": 42
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.7003081440925598,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.3445,
      "step": 43
    },
    {
      "epoch": 2.2051282051282053,
      "grad_norm": 0.6775451302528381,
      "learning_rate": 8.748906014838672e-06,
      "loss": 0.3485,
      "step": 44
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.7644338011741638,
      "learning_rate": 8.665259359149132e-06,
      "loss": 0.3075,
      "step": 45
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.7315237522125244,
      "learning_rate": 8.579334246298593e-06,
      "loss": 0.3196,
      "step": 46
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.7535768747329712,
      "learning_rate": 8.491184090430365e-06,
      "loss": 0.2996,
      "step": 47
    },
    {
      "epoch": 2.41025641025641,
      "grad_norm": 0.7894508838653564,
      "learning_rate": 8.400863688854598e-06,
      "loss": 0.3268,
      "step": 48
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.763268232345581,
      "learning_rate": 8.308429187984298e-06,
      "loss": 0.364,
      "step": 49
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.8217648863792419,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.3174,
      "step": 50
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.7683055996894836,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.343,
      "step": 51
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.7462410926818848,
      "learning_rate": 8.019022051627387e-06,
      "loss": 0.3313,
      "step": 52
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.8326151967048645,
      "learning_rate": 7.918718361173951e-06,
      "loss": 0.3159,
      "step": 53
    },
    {
      "epoch": 2.717948717948718,
      "grad_norm": 0.80051189661026,
      "learning_rate": 7.81660029031811e-06,
      "loss": 0.3129,
      "step": 54
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.6719040274620056,
      "learning_rate": 7.712731319328798e-06,
      "loss": 0.3315,
      "step": 55
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 0.850169837474823,
      "learning_rate": 7.607176016897491e-06,
      "loss": 0.3518,
      "step": 56
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.619449257850647,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.3296,
      "step": 57
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.6999353170394897,
      "learning_rate": 7.391269893106592e-06,
      "loss": 0.332,
      "step": 58
    },
    {
      "epoch": 2.9743589743589745,
      "grad_norm": 0.7099286317825317,
      "learning_rate": 7.281053286765816e-06,
      "loss": 0.3264,
      "step": 59
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7099286317825317,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.3204,
      "step": 60
    },
    {
      "epoch": 3.051282051282051,
      "grad_norm": 0.4556316137313843,
      "learning_rate": 7.056435515653059e-06,
      "loss": 0.2581,
      "step": 61
    },
    {
      "epoch": 3.1025641025641026,
      "grad_norm": 0.4446384906768799,
      "learning_rate": 6.942173981373474e-06,
      "loss": 0.2327,
      "step": 62
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 0.3839487135410309,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 0.2407,
      "step": 63
    },
    {
      "epoch": 3.2051282051282053,
      "grad_norm": 0.5989745259284973,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.2376,
      "step": 64
    },
    {
      "epoch": 3.2564102564102564,
      "grad_norm": 0.3802066147327423,
      "learning_rate": 6.592433251258423e-06,
      "loss": 0.2427,
      "step": 65
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.43709322810173035,
      "learning_rate": 6.473775872054522e-06,
      "loss": 0.2489,
      "step": 66
    },
    {
      "epoch": 3.358974358974359,
      "grad_norm": 0.4659179449081421,
      "learning_rate": 6.354202340715027e-06,
      "loss": 0.2482,
      "step": 67
    },
    {
      "epoch": 3.41025641025641,
      "grad_norm": 0.5887600183486938,
      "learning_rate": 6.233786988451468e-06,
      "loss": 0.239,
      "step": 68
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.37879472970962524,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.2576,
      "step": 69
    },
    {
      "epoch": 3.5128205128205128,
      "grad_norm": 0.5379507541656494,
      "learning_rate": 5.990730715996989e-06,
      "loss": 0.2365,
      "step": 70
    },
    {
      "epoch": 3.564102564102564,
      "grad_norm": 0.4845743775367737,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.2444,
      "step": 71
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 0.5118707418441772,
      "learning_rate": 5.745211330880872e-06,
      "loss": 0.2762,
      "step": 72
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.44185978174209595,
      "learning_rate": 5.621718523237427e-06,
      "loss": 0.2315,
      "step": 73
    },
    {
      "epoch": 3.717948717948718,
      "grad_norm": 0.48046407103538513,
      "learning_rate": 5.497839232979084e-06,
      "loss": 0.2154,
      "step": 74
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.5489363074302673,
      "learning_rate": 5.373650467932122e-06,
      "loss": 0.2577,
      "step": 75
    },
    {
      "epoch": 3.8205128205128203,
      "grad_norm": 0.5312072038650513,
      "learning_rate": 5.249229428303486e-06,
      "loss": 0.2408,
      "step": 76
    },
    {
      "epoch": 3.871794871794872,
      "grad_norm": 0.49800771474838257,
      "learning_rate": 5.1246534586903655e-06,
      "loss": 0.2402,
      "step": 77
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.4377903938293457,
      "learning_rate": 5e-06,
      "loss": 0.2275,
      "step": 78
    },
    {
      "epoch": 3.9743589743589745,
      "grad_norm": 0.5316174030303955,
      "learning_rate": 4.875346541309637e-06,
      "loss": 0.206,
      "step": 79
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0420175790786743,
      "learning_rate": 4.750770571696514e-06,
      "loss": 0.2376,
      "step": 80
    },
    {
      "epoch": 4.051282051282051,
      "grad_norm": 0.8337558507919312,
      "learning_rate": 4.626349532067879e-06,
      "loss": 0.2047,
      "step": 81
    },
    {
      "epoch": 4.102564102564102,
      "grad_norm": 0.8273127675056458,
      "learning_rate": 4.502160767020918e-06,
      "loss": 0.1939,
      "step": 82
    },
    {
      "epoch": 4.153846153846154,
      "grad_norm": 0.6782451868057251,
      "learning_rate": 4.3782814767625755e-06,
      "loss": 0.1993,
      "step": 83
    },
    {
      "epoch": 4.205128205128205,
      "grad_norm": 1.0298625230789185,
      "learning_rate": 4.254788669119127e-06,
      "loss": 0.2273,
      "step": 84
    },
    {
      "epoch": 4.256410256410256,
      "grad_norm": 0.9771720170974731,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.1755,
      "step": 85
    },
    {
      "epoch": 4.3076923076923075,
      "grad_norm": 0.6001358032226562,
      "learning_rate": 4.009269284003014e-06,
      "loss": 0.2165,
      "step": 86
    },
    {
      "epoch": 4.358974358974359,
      "grad_norm": 0.6149842739105225,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.2054,
      "step": 87
    },
    {
      "epoch": 4.410256410256411,
      "grad_norm": 0.9460979700088501,
      "learning_rate": 3.7662130115485317e-06,
      "loss": 0.1852,
      "step": 88
    },
    {
      "epoch": 4.461538461538462,
      "grad_norm": 0.7113755345344543,
      "learning_rate": 3.6457976592849753e-06,
      "loss": 0.1814,
      "step": 89
    },
    {
      "epoch": 4.512820512820513,
      "grad_norm": 0.7413190603256226,
      "learning_rate": 3.526224127945479e-06,
      "loss": 0.2183,
      "step": 90
    },
    {
      "epoch": 4.564102564102564,
      "grad_norm": 0.6740837097167969,
      "learning_rate": 3.4075667487415785e-06,
      "loss": 0.1917,
      "step": 91
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 1.0257478952407837,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.1836,
      "step": 92
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.7094879150390625,
      "learning_rate": 3.173294878168025e-06,
      "loss": 0.1656,
      "step": 93
    },
    {
      "epoch": 4.717948717948718,
      "grad_norm": 0.8563149571418762,
      "learning_rate": 3.057826018626527e-06,
      "loss": 0.2118,
      "step": 94
    },
    {
      "epoch": 4.769230769230769,
      "grad_norm": 0.7314854860305786,
      "learning_rate": 2.9435644843469434e-06,
      "loss": 0.2197,
      "step": 95
    },
    {
      "epoch": 4.82051282051282,
      "grad_norm": 0.7570611238479614,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.1928,
      "step": 96
    },
    {
      "epoch": 4.871794871794872,
      "grad_norm": 0.7279669046401978,
      "learning_rate": 2.718946713234185e-06,
      "loss": 0.2223,
      "step": 97
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 0.8072247505187988,
      "learning_rate": 2.608730106893411e-06,
      "loss": 0.2124,
      "step": 98
    },
    {
      "epoch": 4.9743589743589745,
      "grad_norm": 0.795748770236969,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.2096,
      "step": 99
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.795748770236969,
      "learning_rate": 2.39282398310251e-06,
      "loss": 0.1846,
      "step": 100
    },
    {
      "epoch": 5.051282051282051,
      "grad_norm": 0.6358088850975037,
      "learning_rate": 2.2872686806712037e-06,
      "loss": 0.1792,
      "step": 101
    },
    {
      "epoch": 5.102564102564102,
      "grad_norm": 0.483383446931839,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 0.1642,
      "step": 102
    },
    {
      "epoch": 5.153846153846154,
      "grad_norm": 0.583175778388977,
      "learning_rate": 2.081281638826052e-06,
      "loss": 0.1841,
      "step": 103
    },
    {
      "epoch": 5.205128205128205,
      "grad_norm": 0.43060994148254395,
      "learning_rate": 1.980977948372612e-06,
      "loss": 0.1438,
      "step": 104
    },
    {
      "epoch": 5.256410256410256,
      "grad_norm": 0.5004289150238037,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.1569,
      "step": 105
    },
    {
      "epoch": 5.3076923076923075,
      "grad_norm": 0.4494492709636688,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.1549,
      "step": 106
    },
    {
      "epoch": 5.358974358974359,
      "grad_norm": 0.5149475932121277,
      "learning_rate": 1.6915708120157042e-06,
      "loss": 0.1775,
      "step": 107
    },
    {
      "epoch": 5.410256410256411,
      "grad_norm": 0.4416249096393585,
      "learning_rate": 1.5991363111454023e-06,
      "loss": 0.1224,
      "step": 108
    },
    {
      "epoch": 5.461538461538462,
      "grad_norm": 0.41449978947639465,
      "learning_rate": 1.5088159095696365e-06,
      "loss": 0.1652,
      "step": 109
    },
    {
      "epoch": 5.512820512820513,
      "grad_norm": 0.5547433495521545,
      "learning_rate": 1.4206657537014078e-06,
      "loss": 0.1492,
      "step": 110
    },
    {
      "epoch": 5.564102564102564,
      "grad_norm": 0.40120941400527954,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 0.1272,
      "step": 111
    },
    {
      "epoch": 5.615384615384615,
      "grad_norm": 0.4389178454875946,
      "learning_rate": 1.2510939851613285e-06,
      "loss": 0.1546,
      "step": 112
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 0.4163663387298584,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.1419,
      "step": 113
    },
    {
      "epoch": 5.717948717948718,
      "grad_norm": 0.4604851007461548,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.1803,
      "step": 114
    },
    {
      "epoch": 5.769230769230769,
      "grad_norm": 0.43833422660827637,
      "learning_rate": 1.0143374638853892e-06,
      "loss": 0.1509,
      "step": 115
    },
    {
      "epoch": 5.82051282051282,
      "grad_norm": 0.3609459400177002,
      "learning_rate": 9.403099714207175e-07,
      "loss": 0.1615,
      "step": 116
    },
    {
      "epoch": 5.871794871794872,
      "grad_norm": 0.5134753584861755,
      "learning_rate": 8.688061284200266e-07,
      "loss": 0.1543,
      "step": 117
    },
    {
      "epoch": 5.923076923076923,
      "grad_norm": 0.36548706889152527,
      "learning_rate": 7.99870384246143e-07,
      "loss": 0.1512,
      "step": 118
    },
    {
      "epoch": 5.9743589743589745,
      "grad_norm": 0.4181966781616211,
      "learning_rate": 7.33545591839222e-07,
      "loss": 0.1299,
      "step": 119
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.8071304559707642,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.1754,
      "step": 120
    },
    {
      "epoch": 6.051282051282051,
      "grad_norm": 0.7366305589675903,
      "learning_rate": 6.088921331488568e-07,
      "loss": 0.1118,
      "step": 121
    },
    {
      "epoch": 6.102564102564102,
      "grad_norm": 0.5726804137229919,
      "learning_rate": 5.506409559426573e-07,
      "loss": 0.1523,
      "step": 122
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 0.6024473309516907,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.1666,
      "step": 123
    },
    {
      "epoch": 6.205128205128205,
      "grad_norm": 0.5764136910438538,
      "learning_rate": 4.4247073844163434e-07,
      "loss": 0.1453,
      "step": 124
    },
    {
      "epoch": 6.256410256410256,
      "grad_norm": 0.5406211614608765,
      "learning_rate": 3.9261894064796136e-07,
      "loss": 0.1613,
      "step": 125
    },
    {
      "epoch": 6.3076923076923075,
      "grad_norm": 0.5909959077835083,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 0.1178,
      "step": 126
    },
    {
      "epoch": 6.358974358974359,
      "grad_norm": 0.5980213284492493,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.1494,
      "step": 127
    },
    {
      "epoch": 6.410256410256411,
      "grad_norm": 0.4546549320220947,
      "learning_rate": 2.6036326916434153e-07,
      "loss": 0.1482,
      "step": 128
    },
    {
      "epoch": 6.461538461538462,
      "grad_norm": 0.6100173592567444,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 0.1353,
      "step": 129
    },
    {
      "epoch": 6.512820512820513,
      "grad_norm": 0.5816954374313354,
      "learning_rate": 1.8687876524993987e-07,
      "loss": 0.127,
      "step": 130
    },
    {
      "epoch": 6.564102564102564,
      "grad_norm": 0.5663636326789856,
      "learning_rate": 1.5461356885461077e-07,
      "loss": 0.1682,
      "step": 131
    },
    {
      "epoch": 6.615384615384615,
      "grad_norm": 0.6042241454124451,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.1727,
      "step": 132
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.6464774012565613,
      "learning_rate": 9.913756075728088e-08,
      "loss": 0.107,
      "step": 133
    },
    {
      "epoch": 6.717948717948718,
      "grad_norm": 0.620516300201416,
      "learning_rate": 7.59612349389599e-08,
      "loss": 0.1352,
      "step": 134
    },
    {
      "epoch": 6.769230769230769,
      "grad_norm": 0.5116777420043945,
      "learning_rate": 5.584586887435739e-08,
      "loss": 0.145,
      "step": 135
    },
    {
      "epoch": 6.82051282051282,
      "grad_norm": 0.5570549964904785,
      "learning_rate": 3.8803966999139686e-08,
      "loss": 0.1249,
      "step": 136
    },
    {
      "epoch": 6.871794871794872,
      "grad_norm": 0.6090102195739746,
      "learning_rate": 2.4846123172992953e-08,
      "loss": 0.1372,
      "step": 137
    },
    {
      "epoch": 6.923076923076923,
      "grad_norm": 0.6167779564857483,
      "learning_rate": 1.3981014094099354e-08,
      "loss": 0.1507,
      "step": 138
    },
    {
      "epoch": 6.9743589743589745,
      "grad_norm": 0.5277255773544312,
      "learning_rate": 6.215393905388278e-09,
      "loss": 0.1738,
      "step": 139
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.5277255773544312,
      "learning_rate": 1.5540899959187727e-09,
      "loss": 0.1754,
      "step": 140
    },
    {
      "epoch": 7.0,
      "step": 140,
      "total_flos": 1.6197160748764365e+18,
      "train_loss": 0.2846659729523318,
      "train_runtime": 5176.6993,
      "train_samples_per_second": 0.841,
      "train_steps_per_second": 0.027
    }
  ],
  "logging_steps": 1,
  "max_steps": 140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6197160748764365e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}