{
  "best_metric": 0.6912915706634521,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.026439288783131735,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013219644391565866,
      "grad_norm": 0.19907163083553314,
      "learning_rate": 1e-05,
      "loss": 0.7056,
      "step": 1
    },
    {
      "epoch": 0.00013219644391565866,
      "eval_loss": 1.0835129022598267,
      "eval_runtime": 1288.5293,
      "eval_samples_per_second": 9.887,
      "eval_steps_per_second": 2.472,
      "step": 1
    },
    {
      "epoch": 0.0002643928878313173,
      "grad_norm": 0.24988684058189392,
      "learning_rate": 2e-05,
      "loss": 0.782,
      "step": 2
    },
    {
      "epoch": 0.000396589331746976,
      "grad_norm": 0.27034634351730347,
      "learning_rate": 3e-05,
      "loss": 0.8054,
      "step": 3
    },
    {
      "epoch": 0.0005287857756626346,
      "grad_norm": 0.31130942702293396,
      "learning_rate": 4e-05,
      "loss": 0.8834,
      "step": 4
    },
    {
      "epoch": 0.0006609822195782933,
      "grad_norm": 0.2468542903661728,
      "learning_rate": 5e-05,
      "loss": 0.8018,
      "step": 5
    },
    {
      "epoch": 0.000793178663493952,
      "grad_norm": 0.2454385757446289,
      "learning_rate": 6e-05,
      "loss": 0.8879,
      "step": 6
    },
    {
      "epoch": 0.0009253751074096107,
      "grad_norm": 0.25996339321136475,
      "learning_rate": 7e-05,
      "loss": 0.874,
      "step": 7
    },
    {
      "epoch": 0.0010575715513252693,
      "grad_norm": 0.2632141709327698,
      "learning_rate": 8e-05,
      "loss": 0.9047,
      "step": 8
    },
    {
      "epoch": 0.001189767995240928,
      "grad_norm": 0.27899569272994995,
      "learning_rate": 9e-05,
      "loss": 0.9292,
      "step": 9
    },
    {
      "epoch": 0.0013219644391565867,
      "grad_norm": 0.2870829701423645,
      "learning_rate": 0.0001,
      "loss": 0.839,
      "step": 10
    },
    {
      "epoch": 0.0014541608830722455,
      "grad_norm": 0.3339110016822815,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7648,
      "step": 11
    },
    {
      "epoch": 0.001586357326987904,
      "grad_norm": 0.3318046033382416,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9358,
      "step": 12
    },
    {
      "epoch": 0.0017185537709035626,
      "grad_norm": 0.2891906499862671,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.816,
      "step": 13
    },
    {
      "epoch": 0.0018507502148192214,
      "grad_norm": 0.33678507804870605,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9115,
      "step": 14
    },
    {
      "epoch": 0.00198294665873488,
      "grad_norm": 0.29576581716537476,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9148,
      "step": 15
    },
    {
      "epoch": 0.0021151431026505386,
      "grad_norm": 0.30421528220176697,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7969,
      "step": 16
    },
    {
      "epoch": 0.0022473395465661974,
      "grad_norm": 0.28432103991508484,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8462,
      "step": 17
    },
    {
      "epoch": 0.002379535990481856,
      "grad_norm": 0.31790468096733093,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8638,
      "step": 18
    },
    {
      "epoch": 0.0025117324343975145,
      "grad_norm": 0.2695980668067932,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8375,
      "step": 19
    },
    {
      "epoch": 0.0026439288783131733,
      "grad_norm": 0.2560156285762787,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.844,
      "step": 20
    },
    {
      "epoch": 0.002776125322228832,
      "grad_norm": 0.2801140248775482,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8196,
      "step": 21
    },
    {
      "epoch": 0.002908321766144491,
      "grad_norm": 0.2795511782169342,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8558,
      "step": 22
    },
    {
      "epoch": 0.0030405182100601493,
      "grad_norm": 0.28868985176086426,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8086,
      "step": 23
    },
    {
      "epoch": 0.003172714653975808,
      "grad_norm": 0.2757827043533325,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7993,
      "step": 24
    },
    {
      "epoch": 0.003304911097891467,
      "grad_norm": 0.3054489195346832,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9127,
      "step": 25
    },
    {
      "epoch": 0.003437107541807125,
      "grad_norm": 0.3149811327457428,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9135,
      "step": 26
    },
    {
      "epoch": 0.003569303985722784,
      "grad_norm": 0.3033928871154785,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8242,
      "step": 27
    },
    {
      "epoch": 0.003701500429638443,
      "grad_norm": 0.3094732463359833,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.931,
      "step": 28
    },
    {
      "epoch": 0.0038336968735541016,
      "grad_norm": 0.3037339746952057,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9231,
      "step": 29
    },
    {
      "epoch": 0.00396589331746976,
      "grad_norm": 0.3039802610874176,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8578,
      "step": 30
    },
    {
      "epoch": 0.004098089761385418,
      "grad_norm": 0.32226693630218506,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.852,
      "step": 31
    },
    {
      "epoch": 0.004230286205301077,
      "grad_norm": 0.3024626076221466,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9268,
      "step": 32
    },
    {
      "epoch": 0.004362482649216736,
      "grad_norm": 0.3129371106624603,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8091,
      "step": 33
    },
    {
      "epoch": 0.004494679093132395,
      "grad_norm": 0.3346866965293884,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8698,
      "step": 34
    },
    {
      "epoch": 0.0046268755370480535,
      "grad_norm": 0.3507196307182312,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8524,
      "step": 35
    },
    {
      "epoch": 0.004759071980963712,
      "grad_norm": 0.35556769371032715,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8095,
      "step": 36
    },
    {
      "epoch": 0.004891268424879371,
      "grad_norm": 0.3588707745075226,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8525,
      "step": 37
    },
    {
      "epoch": 0.005023464868795029,
      "grad_norm": 0.35559579730033875,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8739,
      "step": 38
    },
    {
      "epoch": 0.005155661312710688,
      "grad_norm": 0.35974085330963135,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8515,
      "step": 39
    },
    {
      "epoch": 0.005287857756626347,
      "grad_norm": 0.3806246817111969,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7688,
      "step": 40
    },
    {
      "epoch": 0.005420054200542005,
      "grad_norm": 0.34556135535240173,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8072,
      "step": 41
    },
    {
      "epoch": 0.005552250644457664,
      "grad_norm": 0.37214338779449463,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8728,
      "step": 42
    },
    {
      "epoch": 0.005684447088373323,
      "grad_norm": 0.37648141384124756,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7623,
      "step": 43
    },
    {
      "epoch": 0.005816643532288982,
      "grad_norm": 0.33934396505355835,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7707,
      "step": 44
    },
    {
      "epoch": 0.00594883997620464,
      "grad_norm": 0.383687287569046,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7691,
      "step": 45
    },
    {
      "epoch": 0.0060810364201202985,
      "grad_norm": 0.3688667416572571,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7647,
      "step": 46
    },
    {
      "epoch": 0.006213232864035957,
      "grad_norm": 0.4019969403743744,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7542,
      "step": 47
    },
    {
      "epoch": 0.006345429307951616,
      "grad_norm": 0.38373300433158875,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7444,
      "step": 48
    },
    {
      "epoch": 0.006477625751867275,
      "grad_norm": 0.40427687764167786,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7061,
      "step": 49
    },
    {
      "epoch": 0.006609822195782934,
      "grad_norm": 0.586796224117279,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6336,
      "step": 50
    },
    {
      "epoch": 0.006609822195782934,
      "eval_loss": 0.7983591556549072,
      "eval_runtime": 1297.6383,
      "eval_samples_per_second": 9.818,
      "eval_steps_per_second": 2.454,
      "step": 50
    },
    {
      "epoch": 0.0067420186396985925,
      "grad_norm": 0.28511500358581543,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.651,
      "step": 51
    },
    {
      "epoch": 0.00687421508361425,
      "grad_norm": 0.27332431077957153,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6603,
      "step": 52
    },
    {
      "epoch": 0.007006411527529909,
      "grad_norm": 0.2159067839384079,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6719,
      "step": 53
    },
    {
      "epoch": 0.007138607971445568,
      "grad_norm": 0.20144110918045044,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7026,
      "step": 54
    },
    {
      "epoch": 0.007270804415361227,
      "grad_norm": 0.19617719948291779,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7491,
      "step": 55
    },
    {
      "epoch": 0.007403000859276886,
      "grad_norm": 0.20323942601680756,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6962,
      "step": 56
    },
    {
      "epoch": 0.007535197303192544,
      "grad_norm": 0.22517581284046173,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7197,
      "step": 57
    },
    {
      "epoch": 0.007667393747108203,
      "grad_norm": 0.19670049846172333,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7349,
      "step": 58
    },
    {
      "epoch": 0.007799590191023861,
      "grad_norm": 0.22828136384487152,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7543,
      "step": 59
    },
    {
      "epoch": 0.00793178663493952,
      "grad_norm": 0.22368234395980835,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.776,
      "step": 60
    },
    {
      "epoch": 0.00806398307885518,
      "grad_norm": 0.22974425554275513,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7536,
      "step": 61
    },
    {
      "epoch": 0.008196179522770837,
      "grad_norm": 0.2255934476852417,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8714,
      "step": 62
    },
    {
      "epoch": 0.008328375966686495,
      "grad_norm": 0.24428120255470276,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8089,
      "step": 63
    },
    {
      "epoch": 0.008460572410602154,
      "grad_norm": 0.2589269280433655,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6915,
      "step": 64
    },
    {
      "epoch": 0.008592768854517813,
      "grad_norm": 0.2671506702899933,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.836,
      "step": 65
    },
    {
      "epoch": 0.008724965298433472,
      "grad_norm": 0.290968656539917,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8378,
      "step": 66
    },
    {
      "epoch": 0.00885716174234913,
      "grad_norm": 0.28429681062698364,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8242,
      "step": 67
    },
    {
      "epoch": 0.00898935818626479,
      "grad_norm": 0.2940610349178314,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9007,
      "step": 68
    },
    {
      "epoch": 0.009121554630180448,
      "grad_norm": 0.26045677065849304,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7044,
      "step": 69
    },
    {
      "epoch": 0.009253751074096107,
      "grad_norm": 0.2554974853992462,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7129,
      "step": 70
    },
    {
      "epoch": 0.009385947518011766,
      "grad_norm": 0.24801850318908691,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7456,
      "step": 71
    },
    {
      "epoch": 0.009518143961927425,
      "grad_norm": 0.26676586270332336,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8307,
      "step": 72
    },
    {
      "epoch": 0.009650340405843083,
      "grad_norm": 0.28508061170578003,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7025,
      "step": 73
    },
    {
      "epoch": 0.009782536849758742,
      "grad_norm": 0.2627425789833069,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8818,
      "step": 74
    },
    {
      "epoch": 0.009914733293674401,
      "grad_norm": 0.27217817306518555,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8648,
      "step": 75
    },
    {
      "epoch": 0.010046929737590058,
      "grad_norm": 0.26670771837234497,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7436,
      "step": 76
    },
    {
      "epoch": 0.010179126181505717,
      "grad_norm": 0.2777654826641083,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8184,
      "step": 77
    },
    {
      "epoch": 0.010311322625421376,
      "grad_norm": 0.2620057761669159,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8208,
      "step": 78
    },
    {
      "epoch": 0.010443519069337034,
      "grad_norm": 0.2977304756641388,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8203,
      "step": 79
    },
    {
      "epoch": 0.010575715513252693,
      "grad_norm": 0.29825136065483093,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7629,
      "step": 80
    },
    {
      "epoch": 0.010707911957168352,
      "grad_norm": 0.30665692687034607,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8057,
      "step": 81
    },
    {
      "epoch": 0.01084010840108401,
      "grad_norm": 0.304373562335968,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.851,
      "step": 82
    },
    {
      "epoch": 0.01097230484499967,
      "grad_norm": 0.30313679575920105,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6742,
      "step": 83
    },
    {
      "epoch": 0.011104501288915328,
      "grad_norm": 0.3030165731906891,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7918,
      "step": 84
    },
    {
      "epoch": 0.011236697732830987,
      "grad_norm": 0.32320520281791687,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8337,
      "step": 85
    },
    {
      "epoch": 0.011368894176746646,
      "grad_norm": 0.3468799591064453,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7626,
      "step": 86
    },
    {
      "epoch": 0.011501090620662305,
      "grad_norm": 0.32202163338661194,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6401,
      "step": 87
    },
    {
      "epoch": 0.011633287064577964,
      "grad_norm": 0.3291841745376587,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.848,
      "step": 88
    },
    {
      "epoch": 0.01176548350849362,
      "grad_norm": 0.33629122376441956,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7528,
      "step": 89
    },
    {
      "epoch": 0.01189767995240928,
      "grad_norm": 0.3629985749721527,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7181,
      "step": 90
    },
    {
      "epoch": 0.012029876396324938,
      "grad_norm": 0.3643951714038849,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6931,
      "step": 91
    },
    {
      "epoch": 0.012162072840240597,
      "grad_norm": 0.3484621047973633,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7821,
      "step": 92
    },
    {
      "epoch": 0.012294269284156256,
      "grad_norm": 0.3612138330936432,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7201,
      "step": 93
    },
    {
      "epoch": 0.012426465728071915,
      "grad_norm": 0.4237396717071533,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7003,
      "step": 94
    },
    {
      "epoch": 0.012558662171987573,
      "grad_norm": 0.4192473888397217,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7339,
      "step": 95
    },
    {
      "epoch": 0.012690858615903232,
      "grad_norm": 0.40529993176460266,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.723,
      "step": 96
    },
    {
      "epoch": 0.012823055059818891,
      "grad_norm": 0.4157446622848511,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6994,
      "step": 97
    },
    {
      "epoch": 0.01295525150373455,
      "grad_norm": 0.426584392786026,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6503,
      "step": 98
    },
    {
      "epoch": 0.013087447947650209,
      "grad_norm": 0.4566839337348938,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.623,
      "step": 99
    },
    {
      "epoch": 0.013219644391565867,
      "grad_norm": 0.5874345302581787,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6912,
      "step": 100
    },
    {
      "epoch": 0.013219644391565867,
      "eval_loss": 0.7339485883712769,
      "eval_runtime": 1295.8455,
      "eval_samples_per_second": 9.831,
      "eval_steps_per_second": 2.458,
      "step": 100
    },
    {
      "epoch": 0.013351840835481526,
      "grad_norm": 0.2449018806219101,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5968,
      "step": 101
    },
    {
      "epoch": 0.013484037279397185,
      "grad_norm": 0.2391372174024582,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5804,
      "step": 102
    },
    {
      "epoch": 0.013616233723312842,
      "grad_norm": 0.259091854095459,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5899,
      "step": 103
    },
    {
      "epoch": 0.0137484301672285,
      "grad_norm": 0.21162453293800354,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5955,
      "step": 104
    },
    {
      "epoch": 0.01388062661114416,
      "grad_norm": 0.2207092046737671,
      "learning_rate": 5e-05,
      "loss": 0.7089,
      "step": 105
    },
    {
      "epoch": 0.014012823055059818,
      "grad_norm": 0.21915991604328156,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6625,
      "step": 106
    },
    {
      "epoch": 0.014145019498975477,
      "grad_norm": 0.21760006248950958,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6857,
      "step": 107
    },
    {
      "epoch": 0.014277215942891136,
      "grad_norm": 0.21286870539188385,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.5821,
      "step": 108
    },
    {
      "epoch": 0.014409412386806795,
      "grad_norm": 0.2752554416656494,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8374,
      "step": 109
    },
    {
      "epoch": 0.014541608830722454,
      "grad_norm": 0.2630784213542938,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7673,
      "step": 110
    },
    {
      "epoch": 0.014673805274638112,
      "grad_norm": 0.2437119334936142,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6531,
      "step": 111
    },
    {
      "epoch": 0.014806001718553771,
      "grad_norm": 0.2728565037250519,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6917,
      "step": 112
    },
    {
      "epoch": 0.01493819816246943,
      "grad_norm": 0.2970212399959564,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.802,
      "step": 113
    },
    {
      "epoch": 0.015070394606385089,
      "grad_norm": 0.2753089666366577,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7221,
      "step": 114
    },
    {
      "epoch": 0.015202591050300748,
      "grad_norm": 0.3019776940345764,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7218,
      "step": 115
    },
    {
      "epoch": 0.015334787494216406,
      "grad_norm": 0.3079054057598114,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7368,
      "step": 116
    },
    {
      "epoch": 0.015466983938132063,
      "grad_norm": 0.34811916947364807,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8815,
      "step": 117
    },
    {
      "epoch": 0.015599180382047722,
      "grad_norm": 0.2802199721336365,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7978,
      "step": 118
    },
    {
      "epoch": 0.015731376825963383,
      "grad_norm": 0.2739661633968353,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7422,
      "step": 119
    },
    {
      "epoch": 0.01586357326987904,
      "grad_norm": 0.2667839229106903,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7184,
      "step": 120
    },
    {
      "epoch": 0.0159957697137947,
      "grad_norm": 0.27689000964164734,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6337,
      "step": 121
    },
    {
      "epoch": 0.01612796615771036,
      "grad_norm": 0.26580536365509033,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6738,
      "step": 122
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 0.2640027105808258,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6694,
      "step": 123
    },
    {
      "epoch": 0.016392359045541673,
      "grad_norm": 0.2729874849319458,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7466,
      "step": 124
    },
    {
      "epoch": 0.016524555489457332,
      "grad_norm": 0.32576844096183777,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8741,
      "step": 125
    },
    {
      "epoch": 0.01665675193337299,
      "grad_norm": 0.27072277665138245,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6398,
      "step": 126
    },
    {
      "epoch": 0.01678894837728865,
      "grad_norm": 0.2898540496826172,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7319,
      "step": 127
    },
    {
      "epoch": 0.01692114482120431,
      "grad_norm": 0.28591421246528625,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6388,
      "step": 128
    },
    {
      "epoch": 0.017053341265119967,
      "grad_norm": 0.32040935754776,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8053,
      "step": 129
    },
    {
      "epoch": 0.017185537709035626,
      "grad_norm": 0.2715124487876892,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6613,
      "step": 130
    },
    {
      "epoch": 0.017317734152951285,
      "grad_norm": 0.32151684165000916,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7721,
      "step": 131
    },
    {
      "epoch": 0.017449930596866944,
      "grad_norm": 0.3153347074985504,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.778,
      "step": 132
    },
    {
      "epoch": 0.017582127040782602,
      "grad_norm": 0.27657490968704224,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6472,
      "step": 133
    },
    {
      "epoch": 0.01771432348469826,
      "grad_norm": 0.29782021045684814,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6402,
      "step": 134
    },
    {
      "epoch": 0.01784651992861392,
      "grad_norm": 0.36264482140541077,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8151,
      "step": 135
    },
    {
      "epoch": 0.01797871637252958,
      "grad_norm": 0.3695935904979706,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7485,
      "step": 136
    },
    {
      "epoch": 0.018110912816445238,
      "grad_norm": 0.376255601644516,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8114,
      "step": 137
    },
    {
      "epoch": 0.018243109260360896,
      "grad_norm": 0.3442426919937134,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7121,
      "step": 138
    },
    {
      "epoch": 0.018375305704276555,
      "grad_norm": 0.3616703748703003,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.747,
      "step": 139
    },
    {
      "epoch": 0.018507502148192214,
      "grad_norm": 0.3357325494289398,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6589,
      "step": 140
    },
    {
      "epoch": 0.018639698592107873,
      "grad_norm": 0.44670650362968445,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7165,
      "step": 141
    },
    {
      "epoch": 0.01877189503602353,
      "grad_norm": 0.3949689567089081,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7339,
      "step": 142
    },
    {
      "epoch": 0.01890409147993919,
      "grad_norm": 0.3814798891544342,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7213,
      "step": 143
    },
    {
      "epoch": 0.01903628792385485,
      "grad_norm": 0.40541478991508484,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.744,
      "step": 144
    },
    {
      "epoch": 0.019168484367770508,
      "grad_norm": 0.3879254460334778,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7091,
      "step": 145
    },
    {
      "epoch": 0.019300680811686167,
      "grad_norm": 0.39314571022987366,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.632,
      "step": 146
    },
    {
      "epoch": 0.019432877255601826,
      "grad_norm": 0.401945561170578,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6097,
      "step": 147
    },
    {
      "epoch": 0.019565073699517484,
      "grad_norm": 0.40109848976135254,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5687,
      "step": 148
    },
    {
      "epoch": 0.019697270143433143,
      "grad_norm": 0.4402889311313629,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5392,
      "step": 149
    },
    {
      "epoch": 0.019829466587348802,
      "grad_norm": 0.6230471730232239,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.579,
      "step": 150
    },
    {
      "epoch": 0.019829466587348802,
      "eval_loss": 0.7001804709434509,
      "eval_runtime": 1297.795,
      "eval_samples_per_second": 9.817,
      "eval_steps_per_second": 2.454,
      "step": 150
    },
    {
      "epoch": 0.019961663031264457,
      "grad_norm": 0.22197431325912476,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5478,
      "step": 151
    },
    {
      "epoch": 0.020093859475180116,
      "grad_norm": 0.21502351760864258,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6139,
      "step": 152
    },
    {
      "epoch": 0.020226055919095775,
      "grad_norm": 0.24084487557411194,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6676,
      "step": 153
    },
    {
      "epoch": 0.020358252363011434,
      "grad_norm": 0.2299962192773819,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6047,
      "step": 154
    },
    {
      "epoch": 0.020490448806927093,
      "grad_norm": 0.23507559299468994,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6331,
      "step": 155
    },
    {
      "epoch": 0.02062264525084275,
      "grad_norm": 0.2816745936870575,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6266,
      "step": 156
    },
    {
      "epoch": 0.02075484169475841,
      "grad_norm": 0.242003932595253,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6411,
      "step": 157
    },
    {
      "epoch": 0.02088703813867407,
      "grad_norm": 0.2502986192703247,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6425,
      "step": 158
    },
    {
      "epoch": 0.021019234582589728,
      "grad_norm": 0.26039353013038635,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.6891,
      "step": 159
    },
    {
      "epoch": 0.021151431026505386,
      "grad_norm": 0.2787843644618988,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7302,
      "step": 160
    },
    {
      "epoch": 0.021283627470421045,
      "grad_norm": 0.25993210077285767,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7215,
      "step": 161
    },
    {
      "epoch": 0.021415823914336704,
      "grad_norm": 0.25290802121162415,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6854,
      "step": 162
    },
    {
      "epoch": 0.021548020358252363,
      "grad_norm": 0.30008333921432495,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.652,
      "step": 163
    },
    {
      "epoch": 0.02168021680216802,
      "grad_norm": 0.3080776333808899,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7674,
      "step": 164
    },
    {
      "epoch": 0.02181241324608368,
      "grad_norm": 0.28364238142967224,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6617,
      "step": 165
    },
    {
      "epoch": 0.02194460968999934,
      "grad_norm": 0.3111041188240051,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7853,
      "step": 166
    },
    {
      "epoch": 0.022076806133914998,
      "grad_norm": 0.32185930013656616,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7072,
      "step": 167
    },
    {
      "epoch": 0.022209002577830657,
      "grad_norm": 0.2824515402317047,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6561,
      "step": 168
    },
    {
      "epoch": 0.022341199021746316,
      "grad_norm": 0.34787365794181824,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7325,
      "step": 169
    },
    {
      "epoch": 0.022473395465661974,
      "grad_norm": 0.2667436897754669,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6375,
      "step": 170
    },
    {
      "epoch": 0.022605591909577633,
      "grad_norm": 0.2661244869232178,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7065,
      "step": 171
    },
    {
      "epoch": 0.022737788353493292,
      "grad_norm": 0.27021366357803345,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6792,
      "step": 172
    },
    {
      "epoch": 0.02286998479740895,
      "grad_norm": 0.2824627161026001,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7068,
      "step": 173
    },
    {
      "epoch": 0.02300218124132461,
      "grad_norm": 0.29387539625167847,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.739,
      "step": 174
    },
    {
      "epoch": 0.02313437768524027,
      "grad_norm": 0.2964057922363281,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6702,
      "step": 175
    },
    {
      "epoch": 0.023266574129155927,
      "grad_norm": 0.29672032594680786,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6956,
      "step": 176
    },
    {
      "epoch": 0.023398770573071586,
      "grad_norm": 0.3046170771121979,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7628,
      "step": 177
    },
    {
      "epoch": 0.02353096701698724,
      "grad_norm": 0.3279201090335846,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6563,
      "step": 178
    },
    {
      "epoch": 0.0236631634609029,
      "grad_norm": 0.28089141845703125,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6747,
      "step": 179
    },
    {
      "epoch": 0.02379535990481856,
      "grad_norm": 0.3343091309070587,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.8329,
      "step": 180
    },
    {
      "epoch": 0.023927556348734218,
      "grad_norm": 0.3131818473339081,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6915,
      "step": 181
    },
    {
      "epoch": 0.024059752792649877,
      "grad_norm": 0.35552290081977844,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7611,
      "step": 182
    },
    {
      "epoch": 0.024191949236565535,
      "grad_norm": 0.30909493565559387,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.661,
      "step": 183
    },
    {
      "epoch": 0.024324145680481194,
      "grad_norm": 0.34362322092056274,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7195,
      "step": 184
    },
    {
      "epoch": 0.024456342124396853,
      "grad_norm": 0.33635377883911133,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7171,
      "step": 185
    },
    {
      "epoch": 0.02458853856831251,
      "grad_norm": 0.36710497736930847,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7877,
      "step": 186
    },
    {
      "epoch": 0.02472073501222817,
      "grad_norm": 0.3873934745788574,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7987,
      "step": 187
    },
    {
      "epoch": 0.02485293145614383,
      "grad_norm": 0.3363410532474518,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6828,
      "step": 188
    },
    {
      "epoch": 0.024985127900059488,
      "grad_norm": 0.3702673316001892,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6746,
      "step": 189
    },
    {
      "epoch": 0.025117324343975147,
      "grad_norm": 0.4157086908817291,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8022,
      "step": 190
    },
    {
      "epoch": 0.025249520787890806,
      "grad_norm": 0.3965856432914734,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.744,
      "step": 191
    },
    {
      "epoch": 0.025381717231806464,
      "grad_norm": 0.41364598274230957,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7628,
      "step": 192
    },
    {
      "epoch": 0.025513913675722123,
      "grad_norm": 0.36574241518974304,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5987,
      "step": 193
    },
    {
      "epoch": 0.025646110119637782,
      "grad_norm": 0.39211803674697876,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6974,
      "step": 194
    },
    {
      "epoch": 0.02577830656355344,
      "grad_norm": 0.4119443893432617,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7052,
      "step": 195
    },
    {
      "epoch": 0.0259105030074691,
      "grad_norm": 0.4326936900615692,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7098,
      "step": 196
    },
    {
      "epoch": 0.02604269945138476,
      "grad_norm": 0.4216960370540619,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6271,
      "step": 197
    },
    {
      "epoch": 0.026174895895300417,
      "grad_norm": 0.4399435818195343,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6338,
      "step": 198
    },
    {
      "epoch": 0.026307092339216076,
      "grad_norm": 0.436718612909317,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6532,
      "step": 199
    },
    {
      "epoch": 0.026439288783131735,
      "grad_norm": 0.5619792938232422,
      "learning_rate": 0.0,
      "loss": 0.604,
      "step": 200
    },
    {
      "epoch": 0.026439288783131735,
      "eval_loss": 0.6912915706634521,
      "eval_runtime": 1295.737,
      "eval_samples_per_second": 9.832,
      "eval_steps_per_second": 2.458,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.7586505622880256e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}