{
  "best_metric": 1.3178023099899292,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.8648018648018647,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009324009324009324,
      "grad_norm": 0.9052971601486206,
      "learning_rate": 1e-05,
      "loss": 2.6031,
      "step": 1
    },
    {
      "epoch": 0.009324009324009324,
      "eval_loss": 4.63709831237793,
      "eval_runtime": 23.6327,
      "eval_samples_per_second": 7.659,
      "eval_steps_per_second": 1.946,
      "step": 1
    },
    {
      "epoch": 0.018648018648018648,
      "grad_norm": 0.9589207172393799,
      "learning_rate": 2e-05,
      "loss": 2.6018,
      "step": 2
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 0.8114789128303528,
      "learning_rate": 3e-05,
      "loss": 2.5984,
      "step": 3
    },
    {
      "epoch": 0.037296037296037296,
      "grad_norm": 0.7336462736129761,
      "learning_rate": 4e-05,
      "loss": 2.6466,
      "step": 4
    },
    {
      "epoch": 0.046620046620046623,
      "grad_norm": 0.6166083812713623,
      "learning_rate": 5e-05,
      "loss": 2.5624,
      "step": 5
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.508660078048706,
      "learning_rate": 6e-05,
      "loss": 2.5785,
      "step": 6
    },
    {
      "epoch": 0.06526806526806526,
      "grad_norm": 0.37203967571258545,
      "learning_rate": 7e-05,
      "loss": 2.5042,
      "step": 7
    },
    {
      "epoch": 0.07459207459207459,
      "grad_norm": 5.761959552764893,
      "learning_rate": 8e-05,
      "loss": 3.2324,
      "step": 8
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 6.318662643432617,
      "learning_rate": 9e-05,
      "loss": 3.9094,
      "step": 9
    },
    {
      "epoch": 0.09324009324009325,
      "grad_norm": 7.090140342712402,
      "learning_rate": 0.0001,
      "loss": 3.5904,
      "step": 10
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 3.8666465282440186,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.7369,
      "step": 11
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 3.0069384574890137,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4285,
      "step": 12
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 3.584061622619629,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.0111,
      "step": 13
    },
    {
      "epoch": 0.13053613053613053,
      "grad_norm": 2.8933489322662354,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8366,
      "step": 14
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 3.5508038997650146,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7308,
      "step": 15
    },
    {
      "epoch": 0.14918414918414918,
      "grad_norm": 3.6720080375671387,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.3085,
      "step": 16
    },
    {
      "epoch": 0.1585081585081585,
      "grad_norm": 3.109001636505127,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.0038,
      "step": 17
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 6.3707427978515625,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8736,
      "step": 18
    },
    {
      "epoch": 0.17715617715617715,
      "grad_norm": 3.97749400138855,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5588,
      "step": 19
    },
    {
      "epoch": 0.1864801864801865,
      "grad_norm": 17.7021427154541,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.3649,
      "step": 20
    },
    {
      "epoch": 0.1958041958041958,
      "grad_norm": 14.480169296264648,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.8813,
      "step": 21
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 13.668733596801758,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.4802,
      "step": 22
    },
    {
      "epoch": 0.21445221445221446,
      "grad_norm": 24.39434814453125,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.375,
      "step": 23
    },
    {
      "epoch": 0.22377622377622378,
      "grad_norm": 17.264524459838867,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.1331,
      "step": 24
    },
    {
      "epoch": 0.2331002331002331,
      "grad_norm": 13.653349876403809,
      "learning_rate": 9.847001329696653e-05,
      "loss": 8.7509,
      "step": 25
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 10.447142601013184,
      "learning_rate": 9.826044551386744e-05,
      "loss": 7.1565,
      "step": 26
    },
    {
      "epoch": 0.2517482517482518,
      "grad_norm": 9.965043067932129,
      "learning_rate": 9.803768380684242e-05,
      "loss": 6.2914,
      "step": 27
    },
    {
      "epoch": 0.26107226107226106,
      "grad_norm": 7.446625709533691,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.8879,
      "step": 28
    },
    {
      "epoch": 0.2703962703962704,
      "grad_norm": 3.536201238632202,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.0709,
      "step": 29
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 3.104968547821045,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.6103,
      "step": 30
    },
    {
      "epoch": 0.289044289044289,
      "grad_norm": 2.7738285064697266,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.4302,
      "step": 31
    },
    {
      "epoch": 0.29836829836829837,
      "grad_norm": 2.0230393409729004,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.1553,
      "step": 32
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.4073158502578735,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.9311,
      "step": 33
    },
    {
      "epoch": 0.317016317016317,
      "grad_norm": 1.496517539024353,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.9758,
      "step": 34
    },
    {
      "epoch": 0.32634032634032634,
      "grad_norm": 3.6811649799346924,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.0748,
      "step": 35
    },
    {
      "epoch": 0.3356643356643357,
      "grad_norm": 3.8763797283172607,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.8409,
      "step": 36
    },
    {
      "epoch": 0.34498834498834496,
      "grad_norm": 3.274489641189575,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.76,
      "step": 37
    },
    {
      "epoch": 0.3543123543123543,
      "grad_norm": 2.7024476528167725,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2701,
      "step": 38
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.5326497554779053,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.2039,
      "step": 39
    },
    {
      "epoch": 0.372960372960373,
      "grad_norm": 2.4200806617736816,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0836,
      "step": 40
    },
    {
      "epoch": 0.3822843822843823,
      "grad_norm": 2.772533893585205,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.365,
      "step": 41
    },
    {
      "epoch": 0.3916083916083916,
      "grad_norm": 2.8213281631469727,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2156,
      "step": 42
    },
    {
      "epoch": 0.40093240093240096,
      "grad_norm": 2.860793113708496,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0374,
      "step": 43
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 2.5321226119995117,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8041,
      "step": 44
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 1.5017755031585693,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5734,
      "step": 45
    },
    {
      "epoch": 0.4289044289044289,
      "grad_norm": 9.57406234741211,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.172,
      "step": 46
    },
    {
      "epoch": 0.4382284382284382,
      "grad_norm": 10.73863697052002,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.7436,
      "step": 47
    },
    {
      "epoch": 0.44755244755244755,
      "grad_norm": 19.06208610534668,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.2096,
      "step": 48
    },
    {
      "epoch": 0.4568764568764569,
      "grad_norm": 23.685718536376953,
      "learning_rate": 8.995939984474624e-05,
      "loss": 9.0384,
      "step": 49
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 20.235055923461914,
      "learning_rate": 8.945702546981969e-05,
      "loss": 8.1085,
      "step": 50
    },
    {
      "epoch": 0.4662004662004662,
      "eval_loss": 3.4241437911987305,
      "eval_runtime": 23.8752,
      "eval_samples_per_second": 7.581,
      "eval_steps_per_second": 1.927,
      "step": 50
    },
    {
      "epoch": 0.4755244755244755,
      "grad_norm": 13.107210159301758,
      "learning_rate": 8.894386393810563e-05,
      "loss": 6.2935,
      "step": 51
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 10.209434509277344,
      "learning_rate": 8.842005554284296e-05,
      "loss": 5.4817,
      "step": 52
    },
    {
      "epoch": 0.49417249417249415,
      "grad_norm": 8.573369979858398,
      "learning_rate": 8.788574348801675e-05,
      "loss": 4.6889,
      "step": 53
    },
    {
      "epoch": 0.5034965034965035,
      "grad_norm": 5.875744819641113,
      "learning_rate": 8.73410738492077e-05,
      "loss": 4.0269,
      "step": 54
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 3.586548089981079,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.5538,
      "step": 55
    },
    {
      "epoch": 0.5221445221445221,
      "grad_norm": 2.4353981018066406,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.2449,
      "step": 56
    },
    {
      "epoch": 0.5314685314685315,
      "grad_norm": 1.6592824459075928,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.0454,
      "step": 57
    },
    {
      "epoch": 0.5407925407925408,
      "grad_norm": 1.1470218896865845,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.8716,
      "step": 58
    },
    {
      "epoch": 0.5501165501165501,
      "grad_norm": 0.8195887804031372,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.7486,
      "step": 59
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.6640823483467102,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.5602,
      "step": 60
    },
    {
      "epoch": 0.5687645687645687,
      "grad_norm": 5.409642219543457,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3301,
      "step": 61
    },
    {
      "epoch": 0.578088578088578,
      "grad_norm": 2.585865020751953,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.4385,
      "step": 62
    },
    {
      "epoch": 0.5874125874125874,
      "grad_norm": 2.5655100345611572,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3801,
      "step": 63
    },
    {
      "epoch": 0.5967365967365967,
      "grad_norm": 2.7277238368988037,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.4771,
      "step": 64
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.403661012649536,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1543,
      "step": 65
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.5392746925354004,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9689,
      "step": 66
    },
    {
      "epoch": 0.6247086247086248,
      "grad_norm": 3.272602081298828,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.3686,
      "step": 67
    },
    {
      "epoch": 0.634032634032634,
      "grad_norm": 4.134822368621826,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.3357,
      "step": 68
    },
    {
      "epoch": 0.6433566433566433,
      "grad_norm": 3.7982683181762695,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.3123,
      "step": 69
    },
    {
      "epoch": 0.6526806526806527,
      "grad_norm": 2.409498929977417,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8563,
      "step": 70
    },
    {
      "epoch": 0.662004662004662,
      "grad_norm": 2.2970447540283203,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7132,
      "step": 71
    },
    {
      "epoch": 0.6713286713286714,
      "grad_norm": 1.4753090143203735,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5703,
      "step": 72
    },
    {
      "epoch": 0.6806526806526807,
      "grad_norm": 3.6676437854766846,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.94,
      "step": 73
    },
    {
      "epoch": 0.6899766899766899,
      "grad_norm": 7.585810661315918,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.0341,
      "step": 74
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 9.101621627807617,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.8516,
      "step": 75
    },
    {
      "epoch": 0.7086247086247086,
      "grad_norm": 8.40028190612793,
      "learning_rate": 7.30670581489344e-05,
      "loss": 3.2035,
      "step": 76
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 4.906830787658691,
      "learning_rate": 7.233044034264034e-05,
      "loss": 3.0318,
      "step": 77
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.5188441276550293,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.8912,
      "step": 78
    },
    {
      "epoch": 0.7365967365967366,
      "grad_norm": 1.7097022533416748,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.6992,
      "step": 79
    },
    {
      "epoch": 0.745920745920746,
      "grad_norm": 0.8072945475578308,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.6552,
      "step": 80
    },
    {
      "epoch": 0.7552447552447552,
      "grad_norm": 0.4082029163837433,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.5582,
      "step": 81
    },
    {
      "epoch": 0.7645687645687645,
      "grad_norm": 0.30556273460388184,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.5512,
      "step": 82
    },
    {
      "epoch": 0.7738927738927739,
      "grad_norm": 0.3099868893623352,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.5527,
      "step": 83
    },
    {
      "epoch": 0.7832167832167832,
      "grad_norm": 0.3245290219783783,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.5315,
      "step": 84
    },
    {
      "epoch": 0.7925407925407926,
      "grad_norm": 0.36144259572029114,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.4907,
      "step": 85
    },
    {
      "epoch": 0.8018648018648019,
      "grad_norm": 6.569423675537109,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7643,
      "step": 86
    },
    {
      "epoch": 0.8111888111888111,
      "grad_norm": 6.559696674346924,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.1438,
      "step": 87
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 6.0541300773620605,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.9074,
      "step": 88
    },
    {
      "epoch": 0.8298368298368298,
      "grad_norm": 3.1737139225006104,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.4259,
      "step": 89
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 2.7937543392181396,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.2564,
      "step": 90
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 2.7111880779266357,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1447,
      "step": 91
    },
    {
      "epoch": 0.8578088578088578,
      "grad_norm": 3.3274316787719727,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0399,
      "step": 92
    },
    {
      "epoch": 0.8671328671328671,
      "grad_norm": 4.327089786529541,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0551,
      "step": 93
    },
    {
      "epoch": 0.8764568764568764,
      "grad_norm": 3.275545597076416,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.9486,
      "step": 94
    },
    {
      "epoch": 0.8857808857808858,
      "grad_norm": 2.7076406478881836,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.77,
      "step": 95
    },
    {
      "epoch": 0.8951048951048951,
      "grad_norm": 3.4894814491271973,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.666,
      "step": 96
    },
    {
      "epoch": 0.9044289044289044,
      "grad_norm": 1.3948708772659302,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5652,
      "step": 97
    },
    {
      "epoch": 0.9137529137529138,
      "grad_norm": 2.8939266204833984,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.1998,
      "step": 98
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 5.626367568969727,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.7294,
      "step": 99
    },
    {
      "epoch": 0.9324009324009324,
      "grad_norm": 16.60027313232422,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.6439,
      "step": 100
    },
    {
      "epoch": 0.9324009324009324,
      "eval_loss": 1.57069730758667,
      "eval_runtime": 24.1455,
      "eval_samples_per_second": 7.496,
      "eval_steps_per_second": 1.905,
      "step": 100
    },
    {
      "epoch": 0.9417249417249417,
      "grad_norm": 0.6660596132278442,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.5302,
      "step": 101
    },
    {
      "epoch": 0.951048951048951,
      "grad_norm": 0.36493605375289917,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.5459,
      "step": 102
    },
    {
      "epoch": 0.9603729603729604,
      "grad_norm": 0.31290921568870544,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.5298,
      "step": 103
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.542377233505249,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.335,
      "step": 104
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 0.22271700203418732,
      "learning_rate": 5e-05,
      "loss": 2.4205,
      "step": 105
    },
    {
      "epoch": 0.9883449883449883,
      "grad_norm": 2.942105531692505,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.0007,
      "step": 106
    },
    {
      "epoch": 0.9976689976689976,
      "grad_norm": 1.8956243991851807,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6704,
      "step": 107
    },
    {
      "epoch": 1.006993006993007,
      "grad_norm": 1.9723633527755737,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.1549,
      "step": 108
    },
    {
      "epoch": 1.0163170163170163,
      "grad_norm": 0.1735471934080124,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.4268,
      "step": 109
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.21562330424785614,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.4465,
      "step": 110
    },
    {
      "epoch": 1.034965034965035,
      "grad_norm": 0.19110897183418274,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.4676,
      "step": 111
    },
    {
      "epoch": 1.0442890442890442,
      "grad_norm": 0.2500961720943451,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.4745,
      "step": 112
    },
    {
      "epoch": 1.0536130536130537,
      "grad_norm": 0.19169417023658752,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.48,
      "step": 113
    },
    {
      "epoch": 1.062937062937063,
      "grad_norm": 0.2851697504520416,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 3.0048,
      "step": 114
    },
    {
      "epoch": 1.0722610722610724,
      "grad_norm": 2.6353838443756104,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7559,
      "step": 115
    },
    {
      "epoch": 1.0815850815850816,
      "grad_norm": 3.3857853412628174,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.0286,
      "step": 116
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 3.1199066638946533,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.0096,
      "step": 117
    },
    {
      "epoch": 1.1002331002331003,
      "grad_norm": 2.9276974201202393,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9039,
      "step": 118
    },
    {
      "epoch": 1.1095571095571095,
      "grad_norm": 2.443124294281006,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7381,
      "step": 119
    },
    {
      "epoch": 1.118881118881119,
      "grad_norm": 2.1647462844848633,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.605,
      "step": 120
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 1.250878930091858,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.544,
      "step": 121
    },
    {
      "epoch": 1.1375291375291376,
      "grad_norm": 1.8800292015075684,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6084,
      "step": 122
    },
    {
      "epoch": 1.1468531468531469,
      "grad_norm": 1.9703083038330078,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6472,
      "step": 123
    },
    {
      "epoch": 1.156177156177156,
      "grad_norm": 2.0282840728759766,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6155,
      "step": 124
    },
    {
      "epoch": 1.1655011655011656,
      "grad_norm": 1.8367279767990112,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5723,
      "step": 125
    },
    {
      "epoch": 1.1748251748251748,
      "grad_norm": 1.7862775325775146,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.576,
      "step": 126
    },
    {
      "epoch": 1.1841491841491842,
      "grad_norm": 2.454814910888672,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8574,
      "step": 127
    },
    {
      "epoch": 1.1934731934731935,
      "grad_norm": 4.414870262145996,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.2128,
      "step": 128
    },
    {
      "epoch": 1.2027972027972027,
      "grad_norm": 3.4398910999298096,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.248,
      "step": 129
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 4.762664794921875,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2057,
      "step": 130
    },
    {
      "epoch": 1.2214452214452214,
      "grad_norm": 1.2467693090438843,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.2475,
      "step": 131
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3888402283191681,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.323,
      "step": 132
    },
    {
      "epoch": 1.24009324009324,
      "grad_norm": 0.5149527192115784,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.5671,
      "step": 133
    },
    {
      "epoch": 1.2494172494172493,
      "grad_norm": 0.3172931969165802,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.1747,
      "step": 134
    },
    {
      "epoch": 1.2587412587412588,
      "grad_norm": 0.21860957145690918,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.3786,
      "step": 135
    },
    {
      "epoch": 1.2680652680652682,
      "grad_norm": 0.18373554944992065,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.4827,
      "step": 136
    },
    {
      "epoch": 1.2773892773892774,
      "grad_norm": 0.19047728180885315,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.3228,
      "step": 137
    },
    {
      "epoch": 1.2867132867132867,
      "grad_norm": 0.17042529582977295,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.4518,
      "step": 138
    },
    {
      "epoch": 1.2960372960372961,
      "grad_norm": 0.19628658890724182,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.4526,
      "step": 139
    },
    {
      "epoch": 1.3053613053613053,
      "grad_norm": 0.20845463871955872,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.4844,
      "step": 140
    },
    {
      "epoch": 1.3146853146853146,
      "grad_norm": 0.4709472954273224,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.5694,
      "step": 141
    },
    {
      "epoch": 1.324009324009324,
      "grad_norm": 2.323354721069336,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6289,
      "step": 142
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 2.1040561199188232,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6739,
      "step": 143
    },
    {
      "epoch": 1.3426573426573427,
      "grad_norm": 2.162606716156006,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7304,
      "step": 144
    },
    {
      "epoch": 1.351981351981352,
      "grad_norm": 1.941840410232544,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6936,
      "step": 145
    },
    {
      "epoch": 1.3613053613053614,
      "grad_norm": 1.9493544101715088,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7318,
      "step": 146
    },
    {
      "epoch": 1.3706293706293706,
      "grad_norm": 1.8778190612792969,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6226,
      "step": 147
    },
    {
      "epoch": 1.3799533799533799,
      "grad_norm": 0.9945464134216309,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4764,
      "step": 148
    },
    {
      "epoch": 1.3892773892773893,
      "grad_norm": 1.3842207193374634,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5212,
      "step": 149
    },
    {
      "epoch": 1.3986013986013985,
      "grad_norm": 1.1556576490402222,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4962,
      "step": 150
    },
    {
      "epoch": 1.3986013986013985,
      "eval_loss": 1.3634928464889526,
      "eval_runtime": 23.9044,
      "eval_samples_per_second": 7.572,
      "eval_steps_per_second": 1.924,
      "step": 150
    },
    {
      "epoch": 1.407925407925408,
      "grad_norm": 1.640689492225647,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4773,
      "step": 151
    },
    {
      "epoch": 1.4172494172494172,
      "grad_norm": 1.22251296043396,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4961,
      "step": 152
    },
    {
      "epoch": 1.4265734265734267,
      "grad_norm": 1.3368197679519653,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.568,
      "step": 153
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 4.207174777984619,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.0386,
      "step": 154
    },
    {
      "epoch": 1.4452214452214451,
      "grad_norm": 2.792340040206909,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.9463,
      "step": 155
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.8088156580924988,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1702,
      "step": 156
    },
    {
      "epoch": 1.4638694638694638,
      "grad_norm": 0.7213298678398132,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.3048,
      "step": 157
    },
    {
      "epoch": 1.4731934731934733,
      "grad_norm": 0.49519312381744385,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.8123,
      "step": 158
    },
    {
      "epoch": 1.4825174825174825,
      "grad_norm": 0.5530074834823608,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.0512,
      "step": 159
    },
    {
      "epoch": 1.491841491841492,
      "grad_norm": 0.24376797676086426,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.1301,
      "step": 160
    },
    {
      "epoch": 1.5011655011655012,
      "grad_norm": 0.23720410466194153,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 2.2742,
      "step": 161
    },
    {
      "epoch": 1.5104895104895104,
      "grad_norm": 0.1612791270017624,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.5549,
      "step": 162
    },
    {
      "epoch": 1.5198135198135199,
      "grad_norm": 0.16237673163414001,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.2917,
      "step": 163
    },
    {
      "epoch": 1.529137529137529,
      "grad_norm": 0.16159634292125702,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.5396,
      "step": 164
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.20810441672801971,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.3768,
      "step": 165
    },
    {
      "epoch": 1.5477855477855478,
      "grad_norm": 0.1781262904405594,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.4224,
      "step": 166
    },
    {
      "epoch": 1.5571095571095572,
      "grad_norm": 0.262898325920105,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.9139,
      "step": 167
    },
    {
      "epoch": 1.5664335664335665,
      "grad_norm": 2.195039987564087,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.467,
      "step": 168
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 1.6936416625976562,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5788,
      "step": 169
    },
    {
      "epoch": 1.5850815850815851,
      "grad_norm": 1.8443245887756348,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5529,
      "step": 170
    },
    {
      "epoch": 1.5944055944055944,
      "grad_norm": 1.7671632766723633,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5759,
      "step": 171
    },
    {
      "epoch": 1.6037296037296036,
      "grad_norm": 1.7097530364990234,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5703,
      "step": 172
    },
    {
      "epoch": 1.613053613053613,
      "grad_norm": 1.034725308418274,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5056,
      "step": 173
    },
    {
      "epoch": 1.6223776223776225,
      "grad_norm": 1.1529875993728638,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.413,
      "step": 174
    },
    {
      "epoch": 1.6317016317016317,
      "grad_norm": 0.9455154538154602,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4644,
      "step": 175
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 1.180922031402588,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4792,
      "step": 176
    },
    {
      "epoch": 1.6503496503496504,
      "grad_norm": 1.212121844291687,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.4391,
      "step": 177
    },
    {
      "epoch": 1.6596736596736597,
      "grad_norm": 1.1538395881652832,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4395,
      "step": 178
    },
    {
      "epoch": 1.6689976689976689,
      "grad_norm": 1.2972369194030762,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5308,
      "step": 179
    },
    {
      "epoch": 1.6783216783216783,
      "grad_norm": 4.335882186889648,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.9924,
      "step": 180
    },
    {
      "epoch": 1.6876456876456878,
      "grad_norm": 4.141752243041992,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9547,
      "step": 181
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 1.5893715620040894,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5625,
      "step": 182
    },
    {
      "epoch": 1.7062937062937062,
      "grad_norm": 1.5563182830810547,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.0385,
      "step": 183
    },
    {
      "epoch": 1.7156177156177157,
      "grad_norm": 0.337815523147583,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.712,
      "step": 184
    },
    {
      "epoch": 1.724941724941725,
      "grad_norm": 0.47128012776374817,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.2716,
      "step": 185
    },
    {
      "epoch": 1.7342657342657342,
      "grad_norm": 0.17721541225910187,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.8733,
      "step": 186
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.17461764812469482,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.4595,
      "step": 187
    },
    {
      "epoch": 1.752913752913753,
      "grad_norm": 0.16015562415122986,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.4225,
      "step": 188
    },
    {
      "epoch": 1.762237762237762,
      "grad_norm": 0.18493416905403137,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.3811,
      "step": 189
    },
    {
      "epoch": 1.7715617715617715,
      "grad_norm": 0.18942628800868988,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.5149,
      "step": 190
    },
    {
      "epoch": 1.780885780885781,
      "grad_norm": 0.18171672523021698,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.3779,
      "step": 191
    },
    {
      "epoch": 1.7902097902097902,
      "grad_norm": 0.18900567293167114,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.5729,
      "step": 192
    },
    {
      "epoch": 1.7995337995337994,
      "grad_norm": 2.0383760929107666,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9037,
      "step": 193
    },
    {
      "epoch": 1.808857808857809,
      "grad_norm": 1.7374560832977295,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5833,
      "step": 194
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.6285470724105835,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5181,
      "step": 195
    },
    {
      "epoch": 1.8275058275058274,
      "grad_norm": 1.6779515743255615,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5102,
      "step": 196
    },
    {
      "epoch": 1.8368298368298368,
      "grad_norm": 1.644882321357727,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5265,
      "step": 197
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.648485779762268,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5145,
      "step": 198
    },
    {
      "epoch": 1.8554778554778555,
      "grad_norm": 1.667608618736267,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5141,
      "step": 199
    },
    {
      "epoch": 1.8648018648018647,
      "grad_norm": 0.9910750389099121,
      "learning_rate": 0.0,
      "loss": 0.4815,
      "step": 200
    },
    {
      "epoch": 1.8648018648018647,
      "eval_loss": 1.3178023099899292,
      "eval_runtime": 24.2257,
      "eval_samples_per_second": 7.471,
      "eval_steps_per_second": 1.899,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.044657884097413e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}