xlm-roberta-large-qqp-1 / trainer_state.json
tmnam20's picture
Upload trainer_state.json with huggingface_hub
adb714d verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 10000,
"global_step": 34113,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.997068566235746e-05,
"loss": 0.6281,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 1.994137132471492e-05,
"loss": 0.5202,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 1.9912056987072378e-05,
"loss": 0.4662,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 1.9882742649429837e-05,
"loss": 0.4858,
"step": 200
},
{
"epoch": 0.02,
"learning_rate": 1.9853428311787297e-05,
"loss": 0.4833,
"step": 250
},
{
"epoch": 0.03,
"learning_rate": 1.9824113974144757e-05,
"loss": 0.4475,
"step": 300
},
{
"epoch": 0.03,
"learning_rate": 1.9794799636502217e-05,
"loss": 0.4323,
"step": 350
},
{
"epoch": 0.04,
"learning_rate": 1.9765485298859673e-05,
"loss": 0.4407,
"step": 400
},
{
"epoch": 0.04,
"learning_rate": 1.9736170961217133e-05,
"loss": 0.4114,
"step": 450
},
{
"epoch": 0.04,
"learning_rate": 1.9706856623574592e-05,
"loss": 0.4057,
"step": 500
},
{
"epoch": 0.05,
"learning_rate": 1.9677542285932052e-05,
"loss": 0.3949,
"step": 550
},
{
"epoch": 0.05,
"learning_rate": 1.9648227948289512e-05,
"loss": 0.4088,
"step": 600
},
{
"epoch": 0.06,
"learning_rate": 1.961891361064697e-05,
"loss": 0.3899,
"step": 650
},
{
"epoch": 0.06,
"learning_rate": 1.9589599273004428e-05,
"loss": 0.3895,
"step": 700
},
{
"epoch": 0.07,
"learning_rate": 1.9560284935361888e-05,
"loss": 0.3964,
"step": 750
},
{
"epoch": 0.07,
"learning_rate": 1.9530970597719344e-05,
"loss": 0.3829,
"step": 800
},
{
"epoch": 0.07,
"learning_rate": 1.9501656260076804e-05,
"loss": 0.4039,
"step": 850
},
{
"epoch": 0.08,
"learning_rate": 1.9472341922434264e-05,
"loss": 0.3919,
"step": 900
},
{
"epoch": 0.08,
"learning_rate": 1.9443027584791724e-05,
"loss": 0.3625,
"step": 950
},
{
"epoch": 0.09,
"learning_rate": 1.9413713247149183e-05,
"loss": 0.3813,
"step": 1000
},
{
"epoch": 0.09,
"learning_rate": 1.938439890950664e-05,
"loss": 0.3829,
"step": 1050
},
{
"epoch": 0.1,
"learning_rate": 1.93550845718641e-05,
"loss": 0.3652,
"step": 1100
},
{
"epoch": 0.1,
"learning_rate": 1.932577023422156e-05,
"loss": 0.3755,
"step": 1150
},
{
"epoch": 0.11,
"learning_rate": 1.929645589657902e-05,
"loss": 0.3469,
"step": 1200
},
{
"epoch": 0.11,
"learning_rate": 1.926714155893648e-05,
"loss": 0.389,
"step": 1250
},
{
"epoch": 0.11,
"learning_rate": 1.9237827221293935e-05,
"loss": 0.3616,
"step": 1300
},
{
"epoch": 0.12,
"learning_rate": 1.9208512883651395e-05,
"loss": 0.3505,
"step": 1350
},
{
"epoch": 0.12,
"learning_rate": 1.9179198546008855e-05,
"loss": 0.3444,
"step": 1400
},
{
"epoch": 0.13,
"learning_rate": 1.9149884208366314e-05,
"loss": 0.3647,
"step": 1450
},
{
"epoch": 0.13,
"learning_rate": 1.9120569870723774e-05,
"loss": 0.377,
"step": 1500
},
{
"epoch": 0.14,
"learning_rate": 1.909125553308123e-05,
"loss": 0.3695,
"step": 1550
},
{
"epoch": 0.14,
"learning_rate": 1.906194119543869e-05,
"loss": 0.3751,
"step": 1600
},
{
"epoch": 0.15,
"learning_rate": 1.903262685779615e-05,
"loss": 0.3525,
"step": 1650
},
{
"epoch": 0.15,
"learning_rate": 1.900331252015361e-05,
"loss": 0.3801,
"step": 1700
},
{
"epoch": 0.15,
"learning_rate": 1.897399818251107e-05,
"loss": 0.3302,
"step": 1750
},
{
"epoch": 0.16,
"learning_rate": 1.894468384486853e-05,
"loss": 0.3635,
"step": 1800
},
{
"epoch": 0.16,
"learning_rate": 1.8915369507225986e-05,
"loss": 0.3556,
"step": 1850
},
{
"epoch": 0.17,
"learning_rate": 1.8886055169583445e-05,
"loss": 0.3506,
"step": 1900
},
{
"epoch": 0.17,
"learning_rate": 1.8856740831940902e-05,
"loss": 0.3519,
"step": 1950
},
{
"epoch": 0.18,
"learning_rate": 1.882742649429836e-05,
"loss": 0.3155,
"step": 2000
},
{
"epoch": 0.18,
"learning_rate": 1.879811215665582e-05,
"loss": 0.3303,
"step": 2050
},
{
"epoch": 0.18,
"learning_rate": 1.876879781901328e-05,
"loss": 0.3295,
"step": 2100
},
{
"epoch": 0.19,
"learning_rate": 1.873948348137074e-05,
"loss": 0.3144,
"step": 2150
},
{
"epoch": 0.19,
"learning_rate": 1.8710169143728197e-05,
"loss": 0.3038,
"step": 2200
},
{
"epoch": 0.2,
"learning_rate": 1.8680854806085657e-05,
"loss": 0.3355,
"step": 2250
},
{
"epoch": 0.2,
"learning_rate": 1.8651540468443117e-05,
"loss": 0.327,
"step": 2300
},
{
"epoch": 0.21,
"learning_rate": 1.8622226130800576e-05,
"loss": 0.3445,
"step": 2350
},
{
"epoch": 0.21,
"learning_rate": 1.8592911793158036e-05,
"loss": 0.3546,
"step": 2400
},
{
"epoch": 0.22,
"learning_rate": 1.8563597455515493e-05,
"loss": 0.3307,
"step": 2450
},
{
"epoch": 0.22,
"learning_rate": 1.8534283117872952e-05,
"loss": 0.3564,
"step": 2500
},
{
"epoch": 0.22,
"learning_rate": 1.8504968780230412e-05,
"loss": 0.359,
"step": 2550
},
{
"epoch": 0.23,
"learning_rate": 1.8475654442587872e-05,
"loss": 0.3233,
"step": 2600
},
{
"epoch": 0.23,
"learning_rate": 1.844634010494533e-05,
"loss": 0.3339,
"step": 2650
},
{
"epoch": 0.24,
"learning_rate": 1.8417025767302788e-05,
"loss": 0.322,
"step": 2700
},
{
"epoch": 0.24,
"learning_rate": 1.8387711429660248e-05,
"loss": 0.3231,
"step": 2750
},
{
"epoch": 0.25,
"learning_rate": 1.8358397092017708e-05,
"loss": 0.3404,
"step": 2800
},
{
"epoch": 0.25,
"learning_rate": 1.8329082754375167e-05,
"loss": 0.3368,
"step": 2850
},
{
"epoch": 0.26,
"learning_rate": 1.8299768416732627e-05,
"loss": 0.3148,
"step": 2900
},
{
"epoch": 0.26,
"learning_rate": 1.8270454079090087e-05,
"loss": 0.3289,
"step": 2950
},
{
"epoch": 0.26,
"learning_rate": 1.8241139741447543e-05,
"loss": 0.3105,
"step": 3000
},
{
"epoch": 0.27,
"learning_rate": 1.8211825403805003e-05,
"loss": 0.3433,
"step": 3050
},
{
"epoch": 0.27,
"learning_rate": 1.8182511066162463e-05,
"loss": 0.3295,
"step": 3100
},
{
"epoch": 0.28,
"learning_rate": 1.815319672851992e-05,
"loss": 0.3334,
"step": 3150
},
{
"epoch": 0.28,
"learning_rate": 1.812388239087738e-05,
"loss": 0.3352,
"step": 3200
},
{
"epoch": 0.29,
"learning_rate": 1.809456805323484e-05,
"loss": 0.3587,
"step": 3250
},
{
"epoch": 0.29,
"learning_rate": 1.80652537155923e-05,
"loss": 0.3537,
"step": 3300
},
{
"epoch": 0.29,
"learning_rate": 1.8035939377949755e-05,
"loss": 0.3124,
"step": 3350
},
{
"epoch": 0.3,
"learning_rate": 1.8006625040307214e-05,
"loss": 0.3378,
"step": 3400
},
{
"epoch": 0.3,
"learning_rate": 1.7977310702664674e-05,
"loss": 0.3569,
"step": 3450
},
{
"epoch": 0.31,
"learning_rate": 1.7947996365022134e-05,
"loss": 0.3771,
"step": 3500
},
{
"epoch": 0.31,
"learning_rate": 1.7918682027379594e-05,
"loss": 0.3137,
"step": 3550
},
{
"epoch": 0.32,
"learning_rate": 1.788936768973705e-05,
"loss": 0.2959,
"step": 3600
},
{
"epoch": 0.32,
"learning_rate": 1.786005335209451e-05,
"loss": 0.3436,
"step": 3650
},
{
"epoch": 0.33,
"learning_rate": 1.783073901445197e-05,
"loss": 0.3241,
"step": 3700
},
{
"epoch": 0.33,
"learning_rate": 1.780142467680943e-05,
"loss": 0.2967,
"step": 3750
},
{
"epoch": 0.33,
"learning_rate": 1.777211033916689e-05,
"loss": 0.3361,
"step": 3800
},
{
"epoch": 0.34,
"learning_rate": 1.7742796001524346e-05,
"loss": 0.3318,
"step": 3850
},
{
"epoch": 0.34,
"learning_rate": 1.7713481663881805e-05,
"loss": 0.3171,
"step": 3900
},
{
"epoch": 0.35,
"learning_rate": 1.7684167326239265e-05,
"loss": 0.3296,
"step": 3950
},
{
"epoch": 0.35,
"learning_rate": 1.7654852988596725e-05,
"loss": 0.3257,
"step": 4000
},
{
"epoch": 0.36,
"learning_rate": 1.7625538650954185e-05,
"loss": 0.3082,
"step": 4050
},
{
"epoch": 0.36,
"learning_rate": 1.7596224313311644e-05,
"loss": 0.327,
"step": 4100
},
{
"epoch": 0.36,
"learning_rate": 1.75669099756691e-05,
"loss": 0.3418,
"step": 4150
},
{
"epoch": 0.37,
"learning_rate": 1.753759563802656e-05,
"loss": 0.3221,
"step": 4200
},
{
"epoch": 0.37,
"learning_rate": 1.750828130038402e-05,
"loss": 0.3092,
"step": 4250
},
{
"epoch": 0.38,
"learning_rate": 1.747896696274148e-05,
"loss": 0.3166,
"step": 4300
},
{
"epoch": 0.38,
"learning_rate": 1.744965262509894e-05,
"loss": 0.3082,
"step": 4350
},
{
"epoch": 0.39,
"learning_rate": 1.7420338287456396e-05,
"loss": 0.3187,
"step": 4400
},
{
"epoch": 0.39,
"learning_rate": 1.7391023949813856e-05,
"loss": 0.3031,
"step": 4450
},
{
"epoch": 0.4,
"learning_rate": 1.7361709612171312e-05,
"loss": 0.3257,
"step": 4500
},
{
"epoch": 0.4,
"learning_rate": 1.7332395274528772e-05,
"loss": 0.304,
"step": 4550
},
{
"epoch": 0.4,
"learning_rate": 1.7303080936886232e-05,
"loss": 0.3156,
"step": 4600
},
{
"epoch": 0.41,
"learning_rate": 1.727376659924369e-05,
"loss": 0.3294,
"step": 4650
},
{
"epoch": 0.41,
"learning_rate": 1.724445226160115e-05,
"loss": 0.3006,
"step": 4700
},
{
"epoch": 0.42,
"learning_rate": 1.7215137923958608e-05,
"loss": 0.2908,
"step": 4750
},
{
"epoch": 0.42,
"learning_rate": 1.7185823586316067e-05,
"loss": 0.3361,
"step": 4800
},
{
"epoch": 0.43,
"learning_rate": 1.7156509248673527e-05,
"loss": 0.2889,
"step": 4850
},
{
"epoch": 0.43,
"learning_rate": 1.7127194911030987e-05,
"loss": 0.3146,
"step": 4900
},
{
"epoch": 0.44,
"learning_rate": 1.7097880573388447e-05,
"loss": 0.3445,
"step": 4950
},
{
"epoch": 0.44,
"learning_rate": 1.7068566235745903e-05,
"loss": 0.3119,
"step": 5000
},
{
"epoch": 0.44,
"learning_rate": 1.7039251898103363e-05,
"loss": 0.3311,
"step": 5050
},
{
"epoch": 0.45,
"learning_rate": 1.7009937560460823e-05,
"loss": 0.3214,
"step": 5100
},
{
"epoch": 0.45,
"learning_rate": 1.6980623222818282e-05,
"loss": 0.3317,
"step": 5150
},
{
"epoch": 0.46,
"learning_rate": 1.6951308885175742e-05,
"loss": 0.3327,
"step": 5200
},
{
"epoch": 0.46,
"learning_rate": 1.6921994547533202e-05,
"loss": 0.2962,
"step": 5250
},
{
"epoch": 0.47,
"learning_rate": 1.6892680209890658e-05,
"loss": 0.3066,
"step": 5300
},
{
"epoch": 0.47,
"learning_rate": 1.6863365872248118e-05,
"loss": 0.3217,
"step": 5350
},
{
"epoch": 0.47,
"learning_rate": 1.6834051534605578e-05,
"loss": 0.3091,
"step": 5400
},
{
"epoch": 0.48,
"learning_rate": 1.6804737196963038e-05,
"loss": 0.3268,
"step": 5450
},
{
"epoch": 0.48,
"learning_rate": 1.6775422859320497e-05,
"loss": 0.3026,
"step": 5500
},
{
"epoch": 0.49,
"learning_rate": 1.6746108521677954e-05,
"loss": 0.2969,
"step": 5550
},
{
"epoch": 0.49,
"learning_rate": 1.6716794184035413e-05,
"loss": 0.2922,
"step": 5600
},
{
"epoch": 0.5,
"learning_rate": 1.668747984639287e-05,
"loss": 0.3184,
"step": 5650
},
{
"epoch": 0.5,
"learning_rate": 1.665816550875033e-05,
"loss": 0.3204,
"step": 5700
},
{
"epoch": 0.51,
"learning_rate": 1.662885117110779e-05,
"loss": 0.3003,
"step": 5750
},
{
"epoch": 0.51,
"learning_rate": 1.659953683346525e-05,
"loss": 0.3245,
"step": 5800
},
{
"epoch": 0.51,
"learning_rate": 1.657022249582271e-05,
"loss": 0.3176,
"step": 5850
},
{
"epoch": 0.52,
"learning_rate": 1.6540908158180165e-05,
"loss": 0.3316,
"step": 5900
},
{
"epoch": 0.52,
"learning_rate": 1.6511593820537625e-05,
"loss": 0.3105,
"step": 5950
},
{
"epoch": 0.53,
"learning_rate": 1.6482279482895085e-05,
"loss": 0.3202,
"step": 6000
},
{
"epoch": 0.53,
"learning_rate": 1.6452965145252545e-05,
"loss": 0.2881,
"step": 6050
},
{
"epoch": 0.54,
"learning_rate": 1.6423650807610004e-05,
"loss": 0.3012,
"step": 6100
},
{
"epoch": 0.54,
"learning_rate": 1.639433646996746e-05,
"loss": 0.3174,
"step": 6150
},
{
"epoch": 0.55,
"learning_rate": 1.636502213232492e-05,
"loss": 0.3067,
"step": 6200
},
{
"epoch": 0.55,
"learning_rate": 1.633570779468238e-05,
"loss": 0.3064,
"step": 6250
},
{
"epoch": 0.55,
"learning_rate": 1.630639345703984e-05,
"loss": 0.3077,
"step": 6300
},
{
"epoch": 0.56,
"learning_rate": 1.62770791193973e-05,
"loss": 0.3341,
"step": 6350
},
{
"epoch": 0.56,
"learning_rate": 1.624776478175476e-05,
"loss": 0.3244,
"step": 6400
},
{
"epoch": 0.57,
"learning_rate": 1.6218450444112216e-05,
"loss": 0.2882,
"step": 6450
},
{
"epoch": 0.57,
"learning_rate": 1.6189136106469676e-05,
"loss": 0.3132,
"step": 6500
},
{
"epoch": 0.58,
"learning_rate": 1.6159821768827135e-05,
"loss": 0.3454,
"step": 6550
},
{
"epoch": 0.58,
"learning_rate": 1.6130507431184595e-05,
"loss": 0.2851,
"step": 6600
},
{
"epoch": 0.58,
"learning_rate": 1.6101193093542055e-05,
"loss": 0.3147,
"step": 6650
},
{
"epoch": 0.59,
"learning_rate": 1.607187875589951e-05,
"loss": 0.2849,
"step": 6700
},
{
"epoch": 0.59,
"learning_rate": 1.604256441825697e-05,
"loss": 0.3047,
"step": 6750
},
{
"epoch": 0.6,
"learning_rate": 1.601325008061443e-05,
"loss": 0.2967,
"step": 6800
},
{
"epoch": 0.6,
"learning_rate": 1.5983935742971887e-05,
"loss": 0.3039,
"step": 6850
},
{
"epoch": 0.61,
"learning_rate": 1.5954621405329347e-05,
"loss": 0.2859,
"step": 6900
},
{
"epoch": 0.61,
"learning_rate": 1.5925307067686807e-05,
"loss": 0.3062,
"step": 6950
},
{
"epoch": 0.62,
"learning_rate": 1.5895992730044266e-05,
"loss": 0.3233,
"step": 7000
},
{
"epoch": 0.62,
"learning_rate": 1.5866678392401723e-05,
"loss": 0.3019,
"step": 7050
},
{
"epoch": 0.62,
"learning_rate": 1.5837364054759183e-05,
"loss": 0.3196,
"step": 7100
},
{
"epoch": 0.63,
"learning_rate": 1.5808049717116642e-05,
"loss": 0.2887,
"step": 7150
},
{
"epoch": 0.63,
"learning_rate": 1.5778735379474102e-05,
"loss": 0.2927,
"step": 7200
},
{
"epoch": 0.64,
"learning_rate": 1.5749421041831562e-05,
"loss": 0.2858,
"step": 7250
},
{
"epoch": 0.64,
"learning_rate": 1.5720106704189018e-05,
"loss": 0.3034,
"step": 7300
},
{
"epoch": 0.65,
"learning_rate": 1.5690792366546478e-05,
"loss": 0.3009,
"step": 7350
},
{
"epoch": 0.65,
"learning_rate": 1.5661478028903938e-05,
"loss": 0.2802,
"step": 7400
},
{
"epoch": 0.66,
"learning_rate": 1.5632163691261397e-05,
"loss": 0.2887,
"step": 7450
},
{
"epoch": 0.66,
"learning_rate": 1.5602849353618857e-05,
"loss": 0.3005,
"step": 7500
},
{
"epoch": 0.66,
"learning_rate": 1.5573535015976317e-05,
"loss": 0.2973,
"step": 7550
},
{
"epoch": 0.67,
"learning_rate": 1.5544220678333773e-05,
"loss": 0.285,
"step": 7600
},
{
"epoch": 0.67,
"learning_rate": 1.5514906340691233e-05,
"loss": 0.2867,
"step": 7650
},
{
"epoch": 0.68,
"learning_rate": 1.5485592003048693e-05,
"loss": 0.2901,
"step": 7700
},
{
"epoch": 0.68,
"learning_rate": 1.5456277665406153e-05,
"loss": 0.2778,
"step": 7750
},
{
"epoch": 0.69,
"learning_rate": 1.5426963327763612e-05,
"loss": 0.2953,
"step": 7800
},
{
"epoch": 0.69,
"learning_rate": 1.539764899012107e-05,
"loss": 0.2928,
"step": 7850
},
{
"epoch": 0.69,
"learning_rate": 1.536833465247853e-05,
"loss": 0.3083,
"step": 7900
},
{
"epoch": 0.7,
"learning_rate": 1.5339020314835988e-05,
"loss": 0.3086,
"step": 7950
},
{
"epoch": 0.7,
"learning_rate": 1.5309705977193448e-05,
"loss": 0.2842,
"step": 8000
},
{
"epoch": 0.71,
"learning_rate": 1.5280391639550908e-05,
"loss": 0.2753,
"step": 8050
},
{
"epoch": 0.71,
"learning_rate": 1.5251077301908364e-05,
"loss": 0.3001,
"step": 8100
},
{
"epoch": 0.72,
"learning_rate": 1.5221762964265822e-05,
"loss": 0.2791,
"step": 8150
},
{
"epoch": 0.72,
"learning_rate": 1.5192448626623282e-05,
"loss": 0.3117,
"step": 8200
},
{
"epoch": 0.73,
"learning_rate": 1.516313428898074e-05,
"loss": 0.3069,
"step": 8250
},
{
"epoch": 0.73,
"learning_rate": 1.51338199513382e-05,
"loss": 0.2973,
"step": 8300
},
{
"epoch": 0.73,
"learning_rate": 1.510450561369566e-05,
"loss": 0.2969,
"step": 8350
},
{
"epoch": 0.74,
"learning_rate": 1.5075191276053118e-05,
"loss": 0.3136,
"step": 8400
},
{
"epoch": 0.74,
"learning_rate": 1.5045876938410577e-05,
"loss": 0.3016,
"step": 8450
},
{
"epoch": 0.75,
"learning_rate": 1.5016562600768037e-05,
"loss": 0.291,
"step": 8500
},
{
"epoch": 0.75,
"learning_rate": 1.4987248263125495e-05,
"loss": 0.305,
"step": 8550
},
{
"epoch": 0.76,
"learning_rate": 1.4957933925482955e-05,
"loss": 0.2854,
"step": 8600
},
{
"epoch": 0.76,
"learning_rate": 1.4928619587840413e-05,
"loss": 0.2727,
"step": 8650
},
{
"epoch": 0.77,
"learning_rate": 1.4899305250197873e-05,
"loss": 0.308,
"step": 8700
},
{
"epoch": 0.77,
"learning_rate": 1.4869990912555333e-05,
"loss": 0.2835,
"step": 8750
},
{
"epoch": 0.77,
"learning_rate": 1.484067657491279e-05,
"loss": 0.2879,
"step": 8800
},
{
"epoch": 0.78,
"learning_rate": 1.481136223727025e-05,
"loss": 0.3039,
"step": 8850
},
{
"epoch": 0.78,
"learning_rate": 1.478204789962771e-05,
"loss": 0.2878,
"step": 8900
},
{
"epoch": 0.79,
"learning_rate": 1.4752733561985168e-05,
"loss": 0.2843,
"step": 8950
},
{
"epoch": 0.79,
"learning_rate": 1.4723419224342628e-05,
"loss": 0.2962,
"step": 9000
},
{
"epoch": 0.8,
"learning_rate": 1.4694104886700086e-05,
"loss": 0.2892,
"step": 9050
},
{
"epoch": 0.8,
"learning_rate": 1.4664790549057546e-05,
"loss": 0.3037,
"step": 9100
},
{
"epoch": 0.8,
"learning_rate": 1.4635476211415006e-05,
"loss": 0.2909,
"step": 9150
},
{
"epoch": 0.81,
"learning_rate": 1.4606161873772464e-05,
"loss": 0.2923,
"step": 9200
},
{
"epoch": 0.81,
"learning_rate": 1.4576847536129923e-05,
"loss": 0.3013,
"step": 9250
},
{
"epoch": 0.82,
"learning_rate": 1.4547533198487383e-05,
"loss": 0.2687,
"step": 9300
},
{
"epoch": 0.82,
"learning_rate": 1.451821886084484e-05,
"loss": 0.2923,
"step": 9350
},
{
"epoch": 0.83,
"learning_rate": 1.4488904523202298e-05,
"loss": 0.2809,
"step": 9400
},
{
"epoch": 0.83,
"learning_rate": 1.4459590185559757e-05,
"loss": 0.3254,
"step": 9450
},
{
"epoch": 0.84,
"learning_rate": 1.4430275847917217e-05,
"loss": 0.2734,
"step": 9500
},
{
"epoch": 0.84,
"learning_rate": 1.4400961510274675e-05,
"loss": 0.2907,
"step": 9550
},
{
"epoch": 0.84,
"learning_rate": 1.4371647172632135e-05,
"loss": 0.3013,
"step": 9600
},
{
"epoch": 0.85,
"learning_rate": 1.4342332834989595e-05,
"loss": 0.2883,
"step": 9650
},
{
"epoch": 0.85,
"learning_rate": 1.4313018497347053e-05,
"loss": 0.2874,
"step": 9700
},
{
"epoch": 0.86,
"learning_rate": 1.4283704159704513e-05,
"loss": 0.2795,
"step": 9750
},
{
"epoch": 0.86,
"learning_rate": 1.425438982206197e-05,
"loss": 0.3135,
"step": 9800
},
{
"epoch": 0.87,
"learning_rate": 1.422507548441943e-05,
"loss": 0.2752,
"step": 9850
},
{
"epoch": 0.87,
"learning_rate": 1.419576114677689e-05,
"loss": 0.2725,
"step": 9900
},
{
"epoch": 0.88,
"learning_rate": 1.4166446809134348e-05,
"loss": 0.2875,
"step": 9950
},
{
"epoch": 0.88,
"learning_rate": 1.4137132471491808e-05,
"loss": 0.3045,
"step": 10000
},
{
"epoch": 0.88,
"eval_accuracy": 0.8808063319317339,
"eval_combined_score": 0.8565798923530646,
"eval_f1": 0.8323534527743954,
"eval_loss": 0.27471473813056946,
"eval_runtime": 155.6978,
"eval_samples_per_second": 259.67,
"eval_steps_per_second": 16.23,
"step": 10000
},
{
"epoch": 0.88,
"learning_rate": 1.4107818133849268e-05,
"loss": 0.2842,
"step": 10050
},
{
"epoch": 0.89,
"learning_rate": 1.4078503796206726e-05,
"loss": 0.2877,
"step": 10100
},
{
"epoch": 0.89,
"learning_rate": 1.4049189458564186e-05,
"loss": 0.3025,
"step": 10150
},
{
"epoch": 0.9,
"learning_rate": 1.4019875120921644e-05,
"loss": 0.2924,
"step": 10200
},
{
"epoch": 0.9,
"learning_rate": 1.3990560783279103e-05,
"loss": 0.2989,
"step": 10250
},
{
"epoch": 0.91,
"learning_rate": 1.3961246445636563e-05,
"loss": 0.2878,
"step": 10300
},
{
"epoch": 0.91,
"learning_rate": 1.3931932107994021e-05,
"loss": 0.3027,
"step": 10350
},
{
"epoch": 0.91,
"learning_rate": 1.3902617770351481e-05,
"loss": 0.2781,
"step": 10400
},
{
"epoch": 0.92,
"learning_rate": 1.387330343270894e-05,
"loss": 0.2744,
"step": 10450
},
{
"epoch": 0.92,
"learning_rate": 1.3843989095066399e-05,
"loss": 0.2678,
"step": 10500
},
{
"epoch": 0.93,
"learning_rate": 1.3814674757423859e-05,
"loss": 0.306,
"step": 10550
},
{
"epoch": 0.93,
"learning_rate": 1.3785360419781315e-05,
"loss": 0.281,
"step": 10600
},
{
"epoch": 0.94,
"learning_rate": 1.3756046082138775e-05,
"loss": 0.2689,
"step": 10650
},
{
"epoch": 0.94,
"learning_rate": 1.3726731744496233e-05,
"loss": 0.291,
"step": 10700
},
{
"epoch": 0.95,
"learning_rate": 1.3697417406853692e-05,
"loss": 0.2632,
"step": 10750
},
{
"epoch": 0.95,
"learning_rate": 1.3668103069211152e-05,
"loss": 0.3064,
"step": 10800
},
{
"epoch": 0.95,
"learning_rate": 1.363878873156861e-05,
"loss": 0.2797,
"step": 10850
},
{
"epoch": 0.96,
"learning_rate": 1.360947439392607e-05,
"loss": 0.2923,
"step": 10900
},
{
"epoch": 0.96,
"learning_rate": 1.3580160056283528e-05,
"loss": 0.2965,
"step": 10950
},
{
"epoch": 0.97,
"learning_rate": 1.3550845718640988e-05,
"loss": 0.2909,
"step": 11000
},
{
"epoch": 0.97,
"learning_rate": 1.3521531380998448e-05,
"loss": 0.2721,
"step": 11050
},
{
"epoch": 0.98,
"learning_rate": 1.3492217043355906e-05,
"loss": 0.2898,
"step": 11100
},
{
"epoch": 0.98,
"learning_rate": 1.3462902705713365e-05,
"loss": 0.2667,
"step": 11150
},
{
"epoch": 0.98,
"learning_rate": 1.3433588368070825e-05,
"loss": 0.2841,
"step": 11200
},
{
"epoch": 0.99,
"learning_rate": 1.3404274030428283e-05,
"loss": 0.2924,
"step": 11250
},
{
"epoch": 0.99,
"learning_rate": 1.3374959692785743e-05,
"loss": 0.2785,
"step": 11300
},
{
"epoch": 1.0,
"learning_rate": 1.3345645355143201e-05,
"loss": 0.2844,
"step": 11350
},
{
"epoch": 1.0,
"learning_rate": 1.3316331017500661e-05,
"loss": 0.2431,
"step": 11400
},
{
"epoch": 1.01,
"learning_rate": 1.328701667985812e-05,
"loss": 0.2813,
"step": 11450
},
{
"epoch": 1.01,
"learning_rate": 1.3257702342215579e-05,
"loss": 0.2514,
"step": 11500
},
{
"epoch": 1.02,
"learning_rate": 1.3228388004573038e-05,
"loss": 0.2525,
"step": 11550
},
{
"epoch": 1.02,
"learning_rate": 1.3199073666930498e-05,
"loss": 0.2371,
"step": 11600
},
{
"epoch": 1.02,
"learning_rate": 1.3169759329287956e-05,
"loss": 0.2541,
"step": 11650
},
{
"epoch": 1.03,
"learning_rate": 1.3140444991645416e-05,
"loss": 0.2406,
"step": 11700
},
{
"epoch": 1.03,
"learning_rate": 1.3111130654002874e-05,
"loss": 0.2362,
"step": 11750
},
{
"epoch": 1.04,
"learning_rate": 1.3081816316360334e-05,
"loss": 0.2574,
"step": 11800
},
{
"epoch": 1.04,
"learning_rate": 1.305250197871779e-05,
"loss": 0.2562,
"step": 11850
},
{
"epoch": 1.05,
"learning_rate": 1.302318764107525e-05,
"loss": 0.2547,
"step": 11900
},
{
"epoch": 1.05,
"learning_rate": 1.299387330343271e-05,
"loss": 0.2226,
"step": 11950
},
{
"epoch": 1.06,
"learning_rate": 1.2964558965790168e-05,
"loss": 0.2393,
"step": 12000
},
{
"epoch": 1.06,
"learning_rate": 1.2935244628147628e-05,
"loss": 0.2333,
"step": 12050
},
{
"epoch": 1.06,
"learning_rate": 1.2905930290505086e-05,
"loss": 0.257,
"step": 12100
},
{
"epoch": 1.07,
"learning_rate": 1.2876615952862545e-05,
"loss": 0.2403,
"step": 12150
},
{
"epoch": 1.07,
"learning_rate": 1.2847301615220005e-05,
"loss": 0.2517,
"step": 12200
},
{
"epoch": 1.08,
"learning_rate": 1.2817987277577463e-05,
"loss": 0.2476,
"step": 12250
},
{
"epoch": 1.08,
"learning_rate": 1.2788672939934923e-05,
"loss": 0.2464,
"step": 12300
},
{
"epoch": 1.09,
"learning_rate": 1.2759358602292383e-05,
"loss": 0.2153,
"step": 12350
},
{
"epoch": 1.09,
"learning_rate": 1.2730044264649841e-05,
"loss": 0.2331,
"step": 12400
},
{
"epoch": 1.09,
"learning_rate": 1.27007299270073e-05,
"loss": 0.2437,
"step": 12450
},
{
"epoch": 1.1,
"learning_rate": 1.2671415589364759e-05,
"loss": 0.2761,
"step": 12500
},
{
"epoch": 1.1,
"learning_rate": 1.2642101251722218e-05,
"loss": 0.2244,
"step": 12550
},
{
"epoch": 1.11,
"learning_rate": 1.2612786914079678e-05,
"loss": 0.2584,
"step": 12600
},
{
"epoch": 1.11,
"learning_rate": 1.2583472576437136e-05,
"loss": 0.2435,
"step": 12650
},
{
"epoch": 1.12,
"learning_rate": 1.2554158238794596e-05,
"loss": 0.2713,
"step": 12700
},
{
"epoch": 1.12,
"learning_rate": 1.2524843901152056e-05,
"loss": 0.2247,
"step": 12750
},
{
"epoch": 1.13,
"learning_rate": 1.2495529563509514e-05,
"loss": 0.2237,
"step": 12800
},
{
"epoch": 1.13,
"learning_rate": 1.2466215225866974e-05,
"loss": 0.2389,
"step": 12850
},
{
"epoch": 1.13,
"learning_rate": 1.2436900888224432e-05,
"loss": 0.2512,
"step": 12900
},
{
"epoch": 1.14,
"learning_rate": 1.2407586550581891e-05,
"loss": 0.2624,
"step": 12950
},
{
"epoch": 1.14,
"learning_rate": 1.2378272212939351e-05,
"loss": 0.2301,
"step": 13000
},
{
"epoch": 1.15,
"learning_rate": 1.234895787529681e-05,
"loss": 0.2544,
"step": 13050
},
{
"epoch": 1.15,
"learning_rate": 1.2319643537654267e-05,
"loss": 0.2236,
"step": 13100
},
{
"epoch": 1.16,
"learning_rate": 1.2290329200011725e-05,
"loss": 0.2349,
"step": 13150
},
{
"epoch": 1.16,
"learning_rate": 1.2261014862369185e-05,
"loss": 0.2418,
"step": 13200
},
{
"epoch": 1.17,
"learning_rate": 1.2231700524726643e-05,
"loss": 0.2263,
"step": 13250
},
{
"epoch": 1.17,
"learning_rate": 1.2202386187084103e-05,
"loss": 0.2617,
"step": 13300
},
{
"epoch": 1.17,
"learning_rate": 1.2173071849441563e-05,
"loss": 0.2556,
"step": 13350
},
{
"epoch": 1.18,
"learning_rate": 1.214375751179902e-05,
"loss": 0.2267,
"step": 13400
},
{
"epoch": 1.18,
"learning_rate": 1.211444317415648e-05,
"loss": 0.2311,
"step": 13450
},
{
"epoch": 1.19,
"learning_rate": 1.208512883651394e-05,
"loss": 0.2471,
"step": 13500
},
{
"epoch": 1.19,
"learning_rate": 1.2055814498871398e-05,
"loss": 0.2679,
"step": 13550
},
{
"epoch": 1.2,
"learning_rate": 1.2026500161228858e-05,
"loss": 0.2352,
"step": 13600
},
{
"epoch": 1.2,
"learning_rate": 1.1997185823586316e-05,
"loss": 0.234,
"step": 13650
},
{
"epoch": 1.2,
"learning_rate": 1.1967871485943776e-05,
"loss": 0.21,
"step": 13700
},
{
"epoch": 1.21,
"learning_rate": 1.1938557148301236e-05,
"loss": 0.2277,
"step": 13750
},
{
"epoch": 1.21,
"learning_rate": 1.1909242810658694e-05,
"loss": 0.2513,
"step": 13800
},
{
"epoch": 1.22,
"learning_rate": 1.1879928473016154e-05,
"loss": 0.2422,
"step": 13850
},
{
"epoch": 1.22,
"learning_rate": 1.1850614135373613e-05,
"loss": 0.2415,
"step": 13900
},
{
"epoch": 1.23,
"learning_rate": 1.1821299797731071e-05,
"loss": 0.2373,
"step": 13950
},
{
"epoch": 1.23,
"learning_rate": 1.1791985460088531e-05,
"loss": 0.242,
"step": 14000
},
{
"epoch": 1.24,
"learning_rate": 1.176267112244599e-05,
"loss": 0.2532,
"step": 14050
},
{
"epoch": 1.24,
"learning_rate": 1.1733356784803449e-05,
"loss": 0.2333,
"step": 14100
},
{
"epoch": 1.24,
"learning_rate": 1.1704042447160909e-05,
"loss": 0.2264,
"step": 14150
},
{
"epoch": 1.25,
"learning_rate": 1.1674728109518367e-05,
"loss": 0.2216,
"step": 14200
},
{
"epoch": 1.25,
"learning_rate": 1.1645413771875827e-05,
"loss": 0.228,
"step": 14250
},
{
"epoch": 1.26,
"learning_rate": 1.1616099434233283e-05,
"loss": 0.2355,
"step": 14300
},
{
"epoch": 1.26,
"learning_rate": 1.1586785096590743e-05,
"loss": 0.2162,
"step": 14350
},
{
"epoch": 1.27,
"learning_rate": 1.15574707589482e-05,
"loss": 0.2358,
"step": 14400
},
{
"epoch": 1.27,
"learning_rate": 1.152815642130566e-05,
"loss": 0.2173,
"step": 14450
},
{
"epoch": 1.28,
"learning_rate": 1.149884208366312e-05,
"loss": 0.2419,
"step": 14500
},
{
"epoch": 1.28,
"learning_rate": 1.1469527746020578e-05,
"loss": 0.2553,
"step": 14550
},
{
"epoch": 1.28,
"learning_rate": 1.1440213408378038e-05,
"loss": 0.2113,
"step": 14600
},
{
"epoch": 1.29,
"learning_rate": 1.1410899070735498e-05,
"loss": 0.2305,
"step": 14650
},
{
"epoch": 1.29,
"learning_rate": 1.1381584733092956e-05,
"loss": 0.2463,
"step": 14700
},
{
"epoch": 1.3,
"learning_rate": 1.1352270395450416e-05,
"loss": 0.2265,
"step": 14750
},
{
"epoch": 1.3,
"learning_rate": 1.1322956057807874e-05,
"loss": 0.256,
"step": 14800
},
{
"epoch": 1.31,
"learning_rate": 1.1293641720165334e-05,
"loss": 0.2445,
"step": 14850
},
{
"epoch": 1.31,
"learning_rate": 1.1264327382522793e-05,
"loss": 0.2196,
"step": 14900
},
{
"epoch": 1.31,
"learning_rate": 1.1235013044880251e-05,
"loss": 0.2283,
"step": 14950
},
{
"epoch": 1.32,
"learning_rate": 1.1205698707237711e-05,
"loss": 0.2424,
"step": 15000
},
{
"epoch": 1.32,
"learning_rate": 1.1176384369595171e-05,
"loss": 0.2443,
"step": 15050
},
{
"epoch": 1.33,
"learning_rate": 1.1147070031952629e-05,
"loss": 0.2341,
"step": 15100
},
{
"epoch": 1.33,
"learning_rate": 1.1117755694310089e-05,
"loss": 0.2099,
"step": 15150
},
{
"epoch": 1.34,
"learning_rate": 1.1088441356667547e-05,
"loss": 0.2494,
"step": 15200
},
{
"epoch": 1.34,
"learning_rate": 1.1059127019025007e-05,
"loss": 0.2341,
"step": 15250
},
{
"epoch": 1.35,
"learning_rate": 1.1029812681382466e-05,
"loss": 0.226,
"step": 15300
},
{
"epoch": 1.35,
"learning_rate": 1.1000498343739924e-05,
"loss": 0.2355,
"step": 15350
},
{
"epoch": 1.35,
"learning_rate": 1.0971184006097384e-05,
"loss": 0.2541,
"step": 15400
},
{
"epoch": 1.36,
"learning_rate": 1.0941869668454844e-05,
"loss": 0.224,
"step": 15450
},
{
"epoch": 1.36,
"learning_rate": 1.0912555330812302e-05,
"loss": 0.2525,
"step": 15500
},
{
"epoch": 1.37,
"learning_rate": 1.0883240993169758e-05,
"loss": 0.2342,
"step": 15550
},
{
"epoch": 1.37,
"learning_rate": 1.0853926655527218e-05,
"loss": 0.2517,
"step": 15600
},
{
"epoch": 1.38,
"learning_rate": 1.0824612317884678e-05,
"loss": 0.2609,
"step": 15650
},
{
"epoch": 1.38,
"learning_rate": 1.0795297980242136e-05,
"loss": 0.2362,
"step": 15700
},
{
"epoch": 1.39,
"learning_rate": 1.0765983642599596e-05,
"loss": 0.2256,
"step": 15750
},
{
"epoch": 1.39,
"learning_rate": 1.0736669304957055e-05,
"loss": 0.2219,
"step": 15800
},
{
"epoch": 1.39,
"learning_rate": 1.0707354967314513e-05,
"loss": 0.2402,
"step": 15850
},
{
"epoch": 1.4,
"learning_rate": 1.0678040629671973e-05,
"loss": 0.2358,
"step": 15900
},
{
"epoch": 1.4,
"learning_rate": 1.0648726292029431e-05,
"loss": 0.2345,
"step": 15950
},
{
"epoch": 1.41,
"learning_rate": 1.0619411954386891e-05,
"loss": 0.2255,
"step": 16000
},
{
"epoch": 1.41,
"learning_rate": 1.059009761674435e-05,
"loss": 0.2426,
"step": 16050
},
{
"epoch": 1.42,
"learning_rate": 1.0560783279101809e-05,
"loss": 0.2611,
"step": 16100
},
{
"epoch": 1.42,
"learning_rate": 1.0531468941459269e-05,
"loss": 0.2395,
"step": 16150
},
{
"epoch": 1.42,
"learning_rate": 1.0502154603816728e-05,
"loss": 0.2179,
"step": 16200
},
{
"epoch": 1.43,
"learning_rate": 1.0472840266174186e-05,
"loss": 0.2381,
"step": 16250
},
{
"epoch": 1.43,
"learning_rate": 1.0443525928531646e-05,
"loss": 0.242,
"step": 16300
},
{
"epoch": 1.44,
"learning_rate": 1.0414211590889104e-05,
"loss": 0.2568,
"step": 16350
},
{
"epoch": 1.44,
"learning_rate": 1.0384897253246564e-05,
"loss": 0.2518,
"step": 16400
},
{
"epoch": 1.45,
"learning_rate": 1.0355582915604024e-05,
"loss": 0.2503,
"step": 16450
},
{
"epoch": 1.45,
"learning_rate": 1.0326268577961482e-05,
"loss": 0.2502,
"step": 16500
},
{
"epoch": 1.46,
"learning_rate": 1.0296954240318942e-05,
"loss": 0.2531,
"step": 16550
},
{
"epoch": 1.46,
"learning_rate": 1.0267639902676401e-05,
"loss": 0.2407,
"step": 16600
},
{
"epoch": 1.46,
"learning_rate": 1.023832556503386e-05,
"loss": 0.2122,
"step": 16650
},
{
"epoch": 1.47,
"learning_rate": 1.020901122739132e-05,
"loss": 0.2156,
"step": 16700
},
{
"epoch": 1.47,
"learning_rate": 1.0179696889748777e-05,
"loss": 0.238,
"step": 16750
},
{
"epoch": 1.48,
"learning_rate": 1.0150382552106235e-05,
"loss": 0.2218,
"step": 16800
},
{
"epoch": 1.48,
"learning_rate": 1.0121068214463693e-05,
"loss": 0.2432,
"step": 16850
},
{
"epoch": 1.49,
"learning_rate": 1.0091753876821153e-05,
"loss": 0.2436,
"step": 16900
},
{
"epoch": 1.49,
"learning_rate": 1.0062439539178613e-05,
"loss": 0.2441,
"step": 16950
},
{
"epoch": 1.5,
"learning_rate": 1.0033125201536071e-05,
"loss": 0.2551,
"step": 17000
},
{
"epoch": 1.5,
"learning_rate": 1.000381086389353e-05,
"loss": 0.2143,
"step": 17050
},
{
"epoch": 1.5,
"learning_rate": 9.974496526250989e-06,
"loss": 0.2347,
"step": 17100
},
{
"epoch": 1.51,
"learning_rate": 9.945182188608449e-06,
"loss": 0.2416,
"step": 17150
},
{
"epoch": 1.51,
"learning_rate": 9.915867850965908e-06,
"loss": 0.2327,
"step": 17200
},
{
"epoch": 1.52,
"learning_rate": 9.886553513323366e-06,
"loss": 0.2461,
"step": 17250
},
{
"epoch": 1.52,
"learning_rate": 9.857239175680826e-06,
"loss": 0.2194,
"step": 17300
},
{
"epoch": 1.53,
"learning_rate": 9.827924838038286e-06,
"loss": 0.2474,
"step": 17350
},
{
"epoch": 1.53,
"learning_rate": 9.798610500395744e-06,
"loss": 0.2365,
"step": 17400
},
{
"epoch": 1.53,
"learning_rate": 9.769296162753204e-06,
"loss": 0.2419,
"step": 17450
},
{
"epoch": 1.54,
"learning_rate": 9.739981825110662e-06,
"loss": 0.2323,
"step": 17500
},
{
"epoch": 1.54,
"learning_rate": 9.710667487468122e-06,
"loss": 0.2396,
"step": 17550
},
{
"epoch": 1.55,
"learning_rate": 9.681353149825581e-06,
"loss": 0.236,
"step": 17600
},
{
"epoch": 1.55,
"learning_rate": 9.65203881218304e-06,
"loss": 0.2401,
"step": 17650
},
{
"epoch": 1.56,
"learning_rate": 9.6227244745405e-06,
"loss": 0.2169,
"step": 17700
},
{
"epoch": 1.56,
"learning_rate": 9.593410136897957e-06,
"loss": 0.233,
"step": 17750
},
{
"epoch": 1.57,
"learning_rate": 9.564095799255417e-06,
"loss": 0.2248,
"step": 17800
},
{
"epoch": 1.57,
"learning_rate": 9.534781461612875e-06,
"loss": 0.2257,
"step": 17850
},
{
"epoch": 1.57,
"learning_rate": 9.505467123970335e-06,
"loss": 0.2333,
"step": 17900
},
{
"epoch": 1.58,
"learning_rate": 9.476152786327793e-06,
"loss": 0.2477,
"step": 17950
},
{
"epoch": 1.58,
"learning_rate": 9.446838448685253e-06,
"loss": 0.227,
"step": 18000
},
{
"epoch": 1.59,
"learning_rate": 9.417524111042712e-06,
"loss": 0.2523,
"step": 18050
},
{
"epoch": 1.59,
"learning_rate": 9.38820977340017e-06,
"loss": 0.2408,
"step": 18100
},
{
"epoch": 1.6,
"learning_rate": 9.35889543575763e-06,
"loss": 0.2153,
"step": 18150
},
{
"epoch": 1.6,
"learning_rate": 9.329581098115088e-06,
"loss": 0.243,
"step": 18200
},
{
"epoch": 1.6,
"learning_rate": 9.300266760472548e-06,
"loss": 0.2354,
"step": 18250
},
{
"epoch": 1.61,
"learning_rate": 9.270952422830008e-06,
"loss": 0.2402,
"step": 18300
},
{
"epoch": 1.61,
"learning_rate": 9.241638085187466e-06,
"loss": 0.2385,
"step": 18350
},
{
"epoch": 1.62,
"learning_rate": 9.212323747544924e-06,
"loss": 0.2208,
"step": 18400
},
{
"epoch": 1.62,
"learning_rate": 9.183009409902384e-06,
"loss": 0.2163,
"step": 18450
},
{
"epoch": 1.63,
"learning_rate": 9.153695072259843e-06,
"loss": 0.2556,
"step": 18500
},
{
"epoch": 1.63,
"learning_rate": 9.124380734617302e-06,
"loss": 0.2431,
"step": 18550
},
{
"epoch": 1.64,
"learning_rate": 9.095066396974761e-06,
"loss": 0.2066,
"step": 18600
},
{
"epoch": 1.64,
"learning_rate": 9.06575205933222e-06,
"loss": 0.2468,
"step": 18650
},
{
"epoch": 1.64,
"learning_rate": 9.036437721689679e-06,
"loss": 0.2391,
"step": 18700
},
{
"epoch": 1.65,
"learning_rate": 9.007123384047139e-06,
"loss": 0.2267,
"step": 18750
},
{
"epoch": 1.65,
"learning_rate": 8.977809046404597e-06,
"loss": 0.261,
"step": 18800
},
{
"epoch": 1.66,
"learning_rate": 8.948494708762057e-06,
"loss": 0.232,
"step": 18850
},
{
"epoch": 1.66,
"learning_rate": 8.919180371119516e-06,
"loss": 0.2305,
"step": 18900
},
{
"epoch": 1.67,
"learning_rate": 8.889866033476975e-06,
"loss": 0.236,
"step": 18950
},
{
"epoch": 1.67,
"learning_rate": 8.860551695834433e-06,
"loss": 0.2054,
"step": 19000
},
{
"epoch": 1.68,
"learning_rate": 8.831237358191892e-06,
"loss": 0.239,
"step": 19050
},
{
"epoch": 1.68,
"learning_rate": 8.80192302054935e-06,
"loss": 0.2037,
"step": 19100
},
{
"epoch": 1.68,
"learning_rate": 8.77260868290681e-06,
"loss": 0.2391,
"step": 19150
},
{
"epoch": 1.69,
"learning_rate": 8.74329434526427e-06,
"loss": 0.2306,
"step": 19200
},
{
"epoch": 1.69,
"learning_rate": 8.713980007621728e-06,
"loss": 0.2378,
"step": 19250
},
{
"epoch": 1.7,
"learning_rate": 8.684665669979188e-06,
"loss": 0.227,
"step": 19300
},
{
"epoch": 1.7,
"learning_rate": 8.655351332336648e-06,
"loss": 0.2007,
"step": 19350
},
{
"epoch": 1.71,
"learning_rate": 8.626036994694106e-06,
"loss": 0.2196,
"step": 19400
},
{
"epoch": 1.71,
"learning_rate": 8.596722657051565e-06,
"loss": 0.222,
"step": 19450
},
{
"epoch": 1.71,
"learning_rate": 8.567408319409023e-06,
"loss": 0.2342,
"step": 19500
},
{
"epoch": 1.72,
"learning_rate": 8.538093981766483e-06,
"loss": 0.2348,
"step": 19550
},
{
"epoch": 1.72,
"learning_rate": 8.508779644123941e-06,
"loss": 0.2273,
"step": 19600
},
{
"epoch": 1.73,
"learning_rate": 8.479465306481401e-06,
"loss": 0.2603,
"step": 19650
},
{
"epoch": 1.73,
"learning_rate": 8.450150968838859e-06,
"loss": 0.2146,
"step": 19700
},
{
"epoch": 1.74,
"learning_rate": 8.420836631196319e-06,
"loss": 0.2094,
"step": 19750
},
{
"epoch": 1.74,
"learning_rate": 8.391522293553777e-06,
"loss": 0.2484,
"step": 19800
},
{
"epoch": 1.75,
"learning_rate": 8.362207955911237e-06,
"loss": 0.2376,
"step": 19850
},
{
"epoch": 1.75,
"learning_rate": 8.332893618268696e-06,
"loss": 0.2388,
"step": 19900
},
{
"epoch": 1.75,
"learning_rate": 8.303579280626155e-06,
"loss": 0.2163,
"step": 19950
},
{
"epoch": 1.76,
"learning_rate": 8.274264942983614e-06,
"loss": 0.2256,
"step": 20000
},
{
"epoch": 1.76,
"eval_accuracy": 0.8956962651496414,
"eval_combined_score": 0.8787147183645188,
"eval_f1": 0.861733171579396,
"eval_loss": 0.2695234715938568,
"eval_runtime": 155.9822,
"eval_samples_per_second": 259.196,
"eval_steps_per_second": 16.201,
"step": 20000
},
{
"epoch": 1.76,
"learning_rate": 8.244950605341074e-06,
"loss": 0.2357,
"step": 20050
},
{
"epoch": 1.77,
"learning_rate": 8.215636267698532e-06,
"loss": 0.2264,
"step": 20100
},
{
"epoch": 1.77,
"learning_rate": 8.186321930055992e-06,
"loss": 0.2099,
"step": 20150
},
{
"epoch": 1.78,
"learning_rate": 8.15700759241345e-06,
"loss": 0.2299,
"step": 20200
},
{
"epoch": 1.78,
"learning_rate": 8.127693254770908e-06,
"loss": 0.2218,
"step": 20250
},
{
"epoch": 1.79,
"learning_rate": 8.098378917128368e-06,
"loss": 0.2319,
"step": 20300
},
{
"epoch": 1.79,
"learning_rate": 8.069064579485828e-06,
"loss": 0.2438,
"step": 20350
},
{
"epoch": 1.79,
"learning_rate": 8.039750241843286e-06,
"loss": 0.2047,
"step": 20400
},
{
"epoch": 1.8,
"learning_rate": 8.010435904200745e-06,
"loss": 0.2253,
"step": 20450
},
{
"epoch": 1.8,
"learning_rate": 7.981121566558205e-06,
"loss": 0.2202,
"step": 20500
},
{
"epoch": 1.81,
"learning_rate": 7.951807228915663e-06,
"loss": 0.2434,
"step": 20550
},
{
"epoch": 1.81,
"learning_rate": 7.922492891273123e-06,
"loss": 0.2103,
"step": 20600
},
{
"epoch": 1.82,
"learning_rate": 7.893178553630581e-06,
"loss": 0.2253,
"step": 20650
},
{
"epoch": 1.82,
"learning_rate": 7.86386421598804e-06,
"loss": 0.2383,
"step": 20700
},
{
"epoch": 1.82,
"learning_rate": 7.8345498783455e-06,
"loss": 0.2202,
"step": 20750
},
{
"epoch": 1.83,
"learning_rate": 7.805235540702959e-06,
"loss": 0.2341,
"step": 20800
},
{
"epoch": 1.83,
"learning_rate": 7.775921203060417e-06,
"loss": 0.2068,
"step": 20850
},
{
"epoch": 1.84,
"learning_rate": 7.746606865417876e-06,
"loss": 0.253,
"step": 20900
},
{
"epoch": 1.84,
"learning_rate": 7.717292527775334e-06,
"loss": 0.2123,
"step": 20950
},
{
"epoch": 1.85,
"learning_rate": 7.687978190132794e-06,
"loss": 0.2179,
"step": 21000
},
{
"epoch": 1.85,
"learning_rate": 7.658663852490254e-06,
"loss": 0.2411,
"step": 21050
},
{
"epoch": 1.86,
"learning_rate": 7.629349514847713e-06,
"loss": 0.2336,
"step": 21100
},
{
"epoch": 1.86,
"learning_rate": 7.600035177205172e-06,
"loss": 0.2237,
"step": 21150
},
{
"epoch": 1.86,
"learning_rate": 7.570720839562631e-06,
"loss": 0.2367,
"step": 21200
},
{
"epoch": 1.87,
"learning_rate": 7.54140650192009e-06,
"loss": 0.2418,
"step": 21250
},
{
"epoch": 1.87,
"learning_rate": 7.512092164277549e-06,
"loss": 0.2246,
"step": 21300
},
{
"epoch": 1.88,
"learning_rate": 7.482777826635008e-06,
"loss": 0.2095,
"step": 21350
},
{
"epoch": 1.88,
"learning_rate": 7.453463488992467e-06,
"loss": 0.2328,
"step": 21400
},
{
"epoch": 1.89,
"learning_rate": 7.424149151349925e-06,
"loss": 0.2062,
"step": 21450
},
{
"epoch": 1.89,
"learning_rate": 7.394834813707384e-06,
"loss": 0.2315,
"step": 21500
},
{
"epoch": 1.9,
"learning_rate": 7.365520476064844e-06,
"loss": 0.2167,
"step": 21550
},
{
"epoch": 1.9,
"learning_rate": 7.336206138422303e-06,
"loss": 0.2082,
"step": 21600
},
{
"epoch": 1.9,
"learning_rate": 7.306891800779762e-06,
"loss": 0.2307,
"step": 21650
},
{
"epoch": 1.91,
"learning_rate": 7.277577463137221e-06,
"loss": 0.2391,
"step": 21700
},
{
"epoch": 1.91,
"learning_rate": 7.24826312549468e-06,
"loss": 0.2128,
"step": 21750
},
{
"epoch": 1.92,
"learning_rate": 7.218948787852139e-06,
"loss": 0.2354,
"step": 21800
},
{
"epoch": 1.92,
"learning_rate": 7.189634450209598e-06,
"loss": 0.2298,
"step": 21850
},
{
"epoch": 1.93,
"learning_rate": 7.160320112567057e-06,
"loss": 0.206,
"step": 21900
},
{
"epoch": 1.93,
"learning_rate": 7.131005774924516e-06,
"loss": 0.2369,
"step": 21950
},
{
"epoch": 1.93,
"learning_rate": 7.101691437281976e-06,
"loss": 0.2152,
"step": 22000
},
{
"epoch": 1.94,
"learning_rate": 7.072377099639435e-06,
"loss": 0.2351,
"step": 22050
},
{
"epoch": 1.94,
"learning_rate": 7.043062761996893e-06,
"loss": 0.2127,
"step": 22100
},
{
"epoch": 1.95,
"learning_rate": 7.013748424354352e-06,
"loss": 0.1972,
"step": 22150
},
{
"epoch": 1.95,
"learning_rate": 6.984434086711811e-06,
"loss": 0.2513,
"step": 22200
},
{
"epoch": 1.96,
"learning_rate": 6.9551197490692704e-06,
"loss": 0.2142,
"step": 22250
},
{
"epoch": 1.96,
"learning_rate": 6.925805411426729e-06,
"loss": 0.2425,
"step": 22300
},
{
"epoch": 1.97,
"learning_rate": 6.896491073784188e-06,
"loss": 0.2272,
"step": 22350
},
{
"epoch": 1.97,
"learning_rate": 6.867176736141647e-06,
"loss": 0.2266,
"step": 22400
},
{
"epoch": 1.97,
"learning_rate": 6.837862398499107e-06,
"loss": 0.2101,
"step": 22450
},
{
"epoch": 1.98,
"learning_rate": 6.808548060856566e-06,
"loss": 0.2308,
"step": 22500
},
{
"epoch": 1.98,
"learning_rate": 6.779233723214025e-06,
"loss": 0.2231,
"step": 22550
},
{
"epoch": 1.99,
"learning_rate": 6.749919385571484e-06,
"loss": 0.2224,
"step": 22600
},
{
"epoch": 1.99,
"learning_rate": 6.7206050479289434e-06,
"loss": 0.2242,
"step": 22650
},
{
"epoch": 2.0,
"learning_rate": 6.6912907102864015e-06,
"loss": 0.2377,
"step": 22700
},
{
"epoch": 2.0,
"learning_rate": 6.66197637264386e-06,
"loss": 0.2111,
"step": 22750
},
{
"epoch": 2.01,
"learning_rate": 6.632662035001319e-06,
"loss": 0.1807,
"step": 22800
},
{
"epoch": 2.01,
"learning_rate": 6.603347697358778e-06,
"loss": 0.162,
"step": 22850
},
{
"epoch": 2.01,
"learning_rate": 6.574033359716237e-06,
"loss": 0.1671,
"step": 22900
},
{
"epoch": 2.02,
"learning_rate": 6.544719022073697e-06,
"loss": 0.1696,
"step": 22950
},
{
"epoch": 2.02,
"learning_rate": 6.515404684431156e-06,
"loss": 0.158,
"step": 23000
},
{
"epoch": 2.03,
"learning_rate": 6.486090346788615e-06,
"loss": 0.176,
"step": 23050
},
{
"epoch": 2.03,
"learning_rate": 6.456776009146074e-06,
"loss": 0.1731,
"step": 23100
},
{
"epoch": 2.04,
"learning_rate": 6.427461671503533e-06,
"loss": 0.1759,
"step": 23150
},
{
"epoch": 2.04,
"learning_rate": 6.398147333860992e-06,
"loss": 0.1943,
"step": 23200
},
{
"epoch": 2.04,
"learning_rate": 6.368832996218451e-06,
"loss": 0.1605,
"step": 23250
},
{
"epoch": 2.05,
"learning_rate": 6.33951865857591e-06,
"loss": 0.1568,
"step": 23300
},
{
"epoch": 2.05,
"learning_rate": 6.310204320933368e-06,
"loss": 0.1777,
"step": 23350
},
{
"epoch": 2.06,
"learning_rate": 6.280889983290828e-06,
"loss": 0.1729,
"step": 23400
},
{
"epoch": 2.06,
"learning_rate": 6.251575645648287e-06,
"loss": 0.1789,
"step": 23450
},
{
"epoch": 2.07,
"learning_rate": 6.222261308005746e-06,
"loss": 0.1975,
"step": 23500
},
{
"epoch": 2.07,
"learning_rate": 6.192946970363205e-06,
"loss": 0.1899,
"step": 23550
},
{
"epoch": 2.08,
"learning_rate": 6.1636326327206645e-06,
"loss": 0.1773,
"step": 23600
},
{
"epoch": 2.08,
"learning_rate": 6.134318295078123e-06,
"loss": 0.1535,
"step": 23650
},
{
"epoch": 2.08,
"learning_rate": 6.105003957435582e-06,
"loss": 0.1917,
"step": 23700
},
{
"epoch": 2.09,
"learning_rate": 6.075689619793041e-06,
"loss": 0.1716,
"step": 23750
},
{
"epoch": 2.09,
"learning_rate": 6.046375282150501e-06,
"loss": 0.1826,
"step": 23800
},
{
"epoch": 2.1,
"learning_rate": 6.01706094450796e-06,
"loss": 0.1886,
"step": 23850
},
{
"epoch": 2.1,
"learning_rate": 5.987746606865419e-06,
"loss": 0.1716,
"step": 23900
},
{
"epoch": 2.11,
"learning_rate": 5.958432269222877e-06,
"loss": 0.1729,
"step": 23950
},
{
"epoch": 2.11,
"learning_rate": 5.929117931580336e-06,
"loss": 0.1671,
"step": 24000
},
{
"epoch": 2.12,
"learning_rate": 5.8998035939377955e-06,
"loss": 0.1582,
"step": 24050
},
{
"epoch": 2.12,
"learning_rate": 5.8704892562952545e-06,
"loss": 0.1766,
"step": 24100
},
{
"epoch": 2.12,
"learning_rate": 5.841174918652713e-06,
"loss": 0.1664,
"step": 24150
},
{
"epoch": 2.13,
"learning_rate": 5.811860581010172e-06,
"loss": 0.1873,
"step": 24200
},
{
"epoch": 2.13,
"learning_rate": 5.782546243367631e-06,
"loss": 0.1754,
"step": 24250
},
{
"epoch": 2.14,
"learning_rate": 5.753231905725091e-06,
"loss": 0.19,
"step": 24300
},
{
"epoch": 2.14,
"learning_rate": 5.72391756808255e-06,
"loss": 0.1789,
"step": 24350
},
{
"epoch": 2.15,
"learning_rate": 5.694603230440009e-06,
"loss": 0.1782,
"step": 24400
},
{
"epoch": 2.15,
"learning_rate": 5.665288892797468e-06,
"loss": 0.1925,
"step": 24450
},
{
"epoch": 2.15,
"learning_rate": 5.6359745551549274e-06,
"loss": 0.1829,
"step": 24500
},
{
"epoch": 2.16,
"learning_rate": 5.606660217512386e-06,
"loss": 0.1705,
"step": 24550
},
{
"epoch": 2.16,
"learning_rate": 5.5773458798698444e-06,
"loss": 0.1795,
"step": 24600
},
{
"epoch": 2.17,
"learning_rate": 5.548031542227303e-06,
"loss": 0.188,
"step": 24650
},
{
"epoch": 2.17,
"learning_rate": 5.518717204584762e-06,
"loss": 0.1856,
"step": 24700
},
{
"epoch": 2.18,
"learning_rate": 5.489402866942222e-06,
"loss": 0.1724,
"step": 24750
},
{
"epoch": 2.18,
"learning_rate": 5.460088529299681e-06,
"loss": 0.1755,
"step": 24800
},
{
"epoch": 2.19,
"learning_rate": 5.43077419165714e-06,
"loss": 0.1649,
"step": 24850
},
{
"epoch": 2.19,
"learning_rate": 5.401459854014599e-06,
"loss": 0.2087,
"step": 24900
},
{
"epoch": 2.19,
"learning_rate": 5.3721455163720585e-06,
"loss": 0.1827,
"step": 24950
},
{
"epoch": 2.2,
"learning_rate": 5.3428311787295174e-06,
"loss": 0.1981,
"step": 25000
},
{
"epoch": 2.2,
"learning_rate": 5.313516841086976e-06,
"loss": 0.1482,
"step": 25050
},
{
"epoch": 2.21,
"learning_rate": 5.284202503444435e-06,
"loss": 0.1704,
"step": 25100
},
{
"epoch": 2.21,
"learning_rate": 5.254888165801895e-06,
"loss": 0.1974,
"step": 25150
},
{
"epoch": 2.22,
"learning_rate": 5.225573828159353e-06,
"loss": 0.1681,
"step": 25200
},
{
"epoch": 2.22,
"learning_rate": 5.196259490516812e-06,
"loss": 0.202,
"step": 25250
},
{
"epoch": 2.22,
"learning_rate": 5.166945152874271e-06,
"loss": 0.1913,
"step": 25300
},
{
"epoch": 2.23,
"learning_rate": 5.13763081523173e-06,
"loss": 0.1769,
"step": 25350
},
{
"epoch": 2.23,
"learning_rate": 5.108316477589189e-06,
"loss": 0.151,
"step": 25400
},
{
"epoch": 2.24,
"learning_rate": 5.0790021399466485e-06,
"loss": 0.1895,
"step": 25450
},
{
"epoch": 2.24,
"learning_rate": 5.049687802304107e-06,
"loss": 0.1836,
"step": 25500
},
{
"epoch": 2.25,
"learning_rate": 5.020373464661566e-06,
"loss": 0.1754,
"step": 25550
},
{
"epoch": 2.25,
"learning_rate": 4.991059127019025e-06,
"loss": 0.1623,
"step": 25600
},
{
"epoch": 2.26,
"learning_rate": 4.961744789376484e-06,
"loss": 0.1755,
"step": 25650
},
{
"epoch": 2.26,
"learning_rate": 4.932430451733943e-06,
"loss": 0.1884,
"step": 25700
},
{
"epoch": 2.26,
"learning_rate": 4.903116114091403e-06,
"loss": 0.1636,
"step": 25750
},
{
"epoch": 2.27,
"learning_rate": 4.873801776448862e-06,
"loss": 0.1722,
"step": 25800
},
{
"epoch": 2.27,
"learning_rate": 4.844487438806321e-06,
"loss": 0.1871,
"step": 25850
},
{
"epoch": 2.28,
"learning_rate": 4.8151731011637796e-06,
"loss": 0.171,
"step": 25900
},
{
"epoch": 2.28,
"learning_rate": 4.785858763521239e-06,
"loss": 0.1865,
"step": 25950
},
{
"epoch": 2.29,
"learning_rate": 4.756544425878697e-06,
"loss": 0.1582,
"step": 26000
},
{
"epoch": 2.29,
"learning_rate": 4.727230088236156e-06,
"loss": 0.1749,
"step": 26050
},
{
"epoch": 2.3,
"learning_rate": 4.697915750593616e-06,
"loss": 0.1783,
"step": 26100
},
{
"epoch": 2.3,
"learning_rate": 4.668601412951075e-06,
"loss": 0.171,
"step": 26150
},
{
"epoch": 2.3,
"learning_rate": 4.639287075308534e-06,
"loss": 0.1982,
"step": 26200
},
{
"epoch": 2.31,
"learning_rate": 4.609972737665993e-06,
"loss": 0.1847,
"step": 26250
},
{
"epoch": 2.31,
"learning_rate": 4.580658400023452e-06,
"loss": 0.1755,
"step": 26300
},
{
"epoch": 2.32,
"learning_rate": 4.551344062380911e-06,
"loss": 0.1673,
"step": 26350
},
{
"epoch": 2.32,
"learning_rate": 4.5220297247383695e-06,
"loss": 0.1719,
"step": 26400
},
{
"epoch": 2.33,
"learning_rate": 4.492715387095829e-06,
"loss": 0.1738,
"step": 26450
},
{
"epoch": 2.33,
"learning_rate": 4.463401049453288e-06,
"loss": 0.1799,
"step": 26500
},
{
"epoch": 2.33,
"learning_rate": 4.434086711810747e-06,
"loss": 0.1979,
"step": 26550
},
{
"epoch": 2.34,
"learning_rate": 4.404772374168206e-06,
"loss": 0.1626,
"step": 26600
},
{
"epoch": 2.34,
"learning_rate": 4.375458036525665e-06,
"loss": 0.1953,
"step": 26650
},
{
"epoch": 2.35,
"learning_rate": 4.346143698883124e-06,
"loss": 0.1673,
"step": 26700
},
{
"epoch": 2.35,
"learning_rate": 4.316829361240583e-06,
"loss": 0.1889,
"step": 26750
},
{
"epoch": 2.36,
"learning_rate": 4.2875150235980425e-06,
"loss": 0.1637,
"step": 26800
},
{
"epoch": 2.36,
"learning_rate": 4.2582006859555014e-06,
"loss": 0.1905,
"step": 26850
},
{
"epoch": 2.37,
"learning_rate": 4.22888634831296e-06,
"loss": 0.1942,
"step": 26900
},
{
"epoch": 2.37,
"learning_rate": 4.199572010670419e-06,
"loss": 0.1971,
"step": 26950
},
{
"epoch": 2.37,
"learning_rate": 4.170257673027878e-06,
"loss": 0.1691,
"step": 27000
},
{
"epoch": 2.38,
"learning_rate": 4.140943335385337e-06,
"loss": 0.168,
"step": 27050
},
{
"epoch": 2.38,
"learning_rate": 4.111628997742797e-06,
"loss": 0.1942,
"step": 27100
},
{
"epoch": 2.39,
"learning_rate": 4.082314660100256e-06,
"loss": 0.1801,
"step": 27150
},
{
"epoch": 2.39,
"learning_rate": 4.053000322457714e-06,
"loss": 0.1777,
"step": 27200
},
{
"epoch": 2.4,
"learning_rate": 4.023685984815174e-06,
"loss": 0.2106,
"step": 27250
},
{
"epoch": 2.4,
"learning_rate": 3.9943716471726325e-06,
"loss": 0.1856,
"step": 27300
},
{
"epoch": 2.41,
"learning_rate": 3.965057309530091e-06,
"loss": 0.1827,
"step": 27350
},
{
"epoch": 2.41,
"learning_rate": 3.93574297188755e-06,
"loss": 0.1651,
"step": 27400
},
{
"epoch": 2.41,
"learning_rate": 3.90642863424501e-06,
"loss": 0.1747,
"step": 27450
},
{
"epoch": 2.42,
"learning_rate": 3.877114296602469e-06,
"loss": 0.1487,
"step": 27500
},
{
"epoch": 2.42,
"learning_rate": 3.847799958959927e-06,
"loss": 0.1759,
"step": 27550
},
{
"epoch": 2.43,
"learning_rate": 3.818485621317387e-06,
"loss": 0.1477,
"step": 27600
},
{
"epoch": 2.43,
"learning_rate": 3.7891712836748457e-06,
"loss": 0.1631,
"step": 27650
},
{
"epoch": 2.44,
"learning_rate": 3.7598569460323047e-06,
"loss": 0.1862,
"step": 27700
},
{
"epoch": 2.44,
"learning_rate": 3.730542608389764e-06,
"loss": 0.1919,
"step": 27750
},
{
"epoch": 2.44,
"learning_rate": 3.701228270747223e-06,
"loss": 0.1705,
"step": 27800
},
{
"epoch": 2.45,
"learning_rate": 3.6719139331046814e-06,
"loss": 0.1698,
"step": 27850
},
{
"epoch": 2.45,
"learning_rate": 3.6425995954621407e-06,
"loss": 0.1871,
"step": 27900
},
{
"epoch": 2.46,
"learning_rate": 3.6132852578195996e-06,
"loss": 0.1711,
"step": 27950
},
{
"epoch": 2.46,
"learning_rate": 3.583970920177059e-06,
"loss": 0.1519,
"step": 28000
},
{
"epoch": 2.47,
"learning_rate": 3.554656582534518e-06,
"loss": 0.1634,
"step": 28050
},
{
"epoch": 2.47,
"learning_rate": 3.5253422448919772e-06,
"loss": 0.157,
"step": 28100
},
{
"epoch": 2.48,
"learning_rate": 3.4960279072494357e-06,
"loss": 0.1466,
"step": 28150
},
{
"epoch": 2.48,
"learning_rate": 3.466713569606895e-06,
"loss": 0.1911,
"step": 28200
},
{
"epoch": 2.48,
"learning_rate": 3.437399231964354e-06,
"loss": 0.1707,
"step": 28250
},
{
"epoch": 2.49,
"learning_rate": 3.4080848943218133e-06,
"loss": 0.1399,
"step": 28300
},
{
"epoch": 2.49,
"learning_rate": 3.3787705566792722e-06,
"loss": 0.1857,
"step": 28350
},
{
"epoch": 2.5,
"learning_rate": 3.3494562190367316e-06,
"loss": 0.1715,
"step": 28400
},
{
"epoch": 2.5,
"learning_rate": 3.32014188139419e-06,
"loss": 0.1711,
"step": 28450
},
{
"epoch": 2.51,
"learning_rate": 3.290827543751649e-06,
"loss": 0.1972,
"step": 28500
},
{
"epoch": 2.51,
"learning_rate": 3.2615132061091083e-06,
"loss": 0.1646,
"step": 28550
},
{
"epoch": 2.52,
"learning_rate": 3.232198868466567e-06,
"loss": 0.1777,
"step": 28600
},
{
"epoch": 2.52,
"learning_rate": 3.2028845308240265e-06,
"loss": 0.1586,
"step": 28650
},
{
"epoch": 2.52,
"learning_rate": 3.1735701931814855e-06,
"loss": 0.1628,
"step": 28700
},
{
"epoch": 2.53,
"learning_rate": 3.144255855538944e-06,
"loss": 0.1719,
"step": 28750
},
{
"epoch": 2.53,
"learning_rate": 3.1149415178964033e-06,
"loss": 0.1763,
"step": 28800
},
{
"epoch": 2.54,
"learning_rate": 3.085627180253862e-06,
"loss": 0.1688,
"step": 28850
},
{
"epoch": 2.54,
"learning_rate": 3.0563128426113215e-06,
"loss": 0.1662,
"step": 28900
},
{
"epoch": 2.55,
"learning_rate": 3.0269985049687804e-06,
"loss": 0.1538,
"step": 28950
},
{
"epoch": 2.55,
"learning_rate": 2.9976841673262398e-06,
"loss": 0.1475,
"step": 29000
},
{
"epoch": 2.55,
"learning_rate": 2.9683698296836987e-06,
"loss": 0.1724,
"step": 29050
},
{
"epoch": 2.56,
"learning_rate": 2.939055492041157e-06,
"loss": 0.1645,
"step": 29100
},
{
"epoch": 2.56,
"learning_rate": 2.9097411543986165e-06,
"loss": 0.2028,
"step": 29150
},
{
"epoch": 2.57,
"learning_rate": 2.8804268167560754e-06,
"loss": 0.1667,
"step": 29200
},
{
"epoch": 2.57,
"learning_rate": 2.8511124791135348e-06,
"loss": 0.1446,
"step": 29250
},
{
"epoch": 2.58,
"learning_rate": 2.8217981414709937e-06,
"loss": 0.1969,
"step": 29300
},
{
"epoch": 2.58,
"learning_rate": 2.792483803828453e-06,
"loss": 0.1733,
"step": 29350
},
{
"epoch": 2.59,
"learning_rate": 2.7631694661859115e-06,
"loss": 0.1736,
"step": 29400
},
{
"epoch": 2.59,
"learning_rate": 2.733855128543371e-06,
"loss": 0.1668,
"step": 29450
},
{
"epoch": 2.59,
"learning_rate": 2.7045407909008298e-06,
"loss": 0.1759,
"step": 29500
},
{
"epoch": 2.6,
"learning_rate": 2.675226453258289e-06,
"loss": 0.1709,
"step": 29550
},
{
"epoch": 2.6,
"learning_rate": 2.645912115615748e-06,
"loss": 0.1607,
"step": 29600
},
{
"epoch": 2.61,
"learning_rate": 2.616597777973207e-06,
"loss": 0.1575,
"step": 29650
},
{
"epoch": 2.61,
"learning_rate": 2.587283440330666e-06,
"loss": 0.1665,
"step": 29700
},
{
"epoch": 2.62,
"learning_rate": 2.5579691026881247e-06,
"loss": 0.1785,
"step": 29750
},
{
"epoch": 2.62,
"learning_rate": 2.528654765045584e-06,
"loss": 0.1575,
"step": 29800
},
{
"epoch": 2.63,
"learning_rate": 2.499340427403043e-06,
"loss": 0.1668,
"step": 29850
},
{
"epoch": 2.63,
"learning_rate": 2.4700260897605023e-06,
"loss": 0.1858,
"step": 29900
},
{
"epoch": 2.63,
"learning_rate": 2.440711752117961e-06,
"loss": 0.1762,
"step": 29950
},
{
"epoch": 2.64,
"learning_rate": 2.41139741447542e-06,
"loss": 0.1643,
"step": 30000
},
{
"epoch": 2.64,
"eval_accuracy": 0.9019045263418254,
"eval_combined_score": 0.8851374606485098,
"eval_f1": 0.8683703949551942,
"eval_loss": 0.28078874945640564,
"eval_runtime": 155.6736,
"eval_samples_per_second": 259.71,
"eval_steps_per_second": 16.233,
"step": 30000
},
{
"epoch": 2.64,
"learning_rate": 2.382083076832879e-06,
"loss": 0.1729,
"step": 30050
},
{
"epoch": 2.65,
"learning_rate": 2.352768739190338e-06,
"loss": 0.195,
"step": 30100
},
{
"epoch": 2.65,
"learning_rate": 2.3234544015477973e-06,
"loss": 0.1335,
"step": 30150
},
{
"epoch": 2.66,
"learning_rate": 2.2941400639052562e-06,
"loss": 0.1879,
"step": 30200
},
{
"epoch": 2.66,
"learning_rate": 2.264825726262715e-06,
"loss": 0.1652,
"step": 30250
},
{
"epoch": 2.66,
"learning_rate": 2.2355113886201745e-06,
"loss": 0.1546,
"step": 30300
},
{
"epoch": 2.67,
"learning_rate": 2.2061970509776334e-06,
"loss": 0.1713,
"step": 30350
},
{
"epoch": 2.67,
"learning_rate": 2.1768827133350923e-06,
"loss": 0.187,
"step": 30400
},
{
"epoch": 2.68,
"learning_rate": 2.1475683756925512e-06,
"loss": 0.1508,
"step": 30450
},
{
"epoch": 2.68,
"learning_rate": 2.1182540380500106e-06,
"loss": 0.1675,
"step": 30500
},
{
"epoch": 2.69,
"learning_rate": 2.0889397004074695e-06,
"loss": 0.1587,
"step": 30550
},
{
"epoch": 2.69,
"learning_rate": 2.0596253627649284e-06,
"loss": 0.1551,
"step": 30600
},
{
"epoch": 2.7,
"learning_rate": 2.0303110251223877e-06,
"loss": 0.1781,
"step": 30650
},
{
"epoch": 2.7,
"learning_rate": 2.0009966874798466e-06,
"loss": 0.1747,
"step": 30700
},
{
"epoch": 2.7,
"learning_rate": 1.9716823498373055e-06,
"loss": 0.152,
"step": 30750
},
{
"epoch": 2.71,
"learning_rate": 1.9423680121947645e-06,
"loss": 0.1822,
"step": 30800
},
{
"epoch": 2.71,
"learning_rate": 1.9130536745522234e-06,
"loss": 0.1714,
"step": 30850
},
{
"epoch": 2.72,
"learning_rate": 1.8837393369096827e-06,
"loss": 0.1578,
"step": 30900
},
{
"epoch": 2.72,
"learning_rate": 1.8544249992671418e-06,
"loss": 0.1605,
"step": 30950
},
{
"epoch": 2.73,
"learning_rate": 1.825110661624601e-06,
"loss": 0.1655,
"step": 31000
},
{
"epoch": 2.73,
"learning_rate": 1.7957963239820597e-06,
"loss": 0.1662,
"step": 31050
},
{
"epoch": 2.74,
"learning_rate": 1.7664819863395188e-06,
"loss": 0.1718,
"step": 31100
},
{
"epoch": 2.74,
"learning_rate": 1.737167648696978e-06,
"loss": 0.1697,
"step": 31150
},
{
"epoch": 2.74,
"learning_rate": 1.7078533110544368e-06,
"loss": 0.1676,
"step": 31200
},
{
"epoch": 2.75,
"learning_rate": 1.678538973411896e-06,
"loss": 0.1727,
"step": 31250
},
{
"epoch": 2.75,
"learning_rate": 1.649224635769355e-06,
"loss": 0.1808,
"step": 31300
},
{
"epoch": 2.76,
"learning_rate": 1.619910298126814e-06,
"loss": 0.1647,
"step": 31350
},
{
"epoch": 2.76,
"learning_rate": 1.590595960484273e-06,
"loss": 0.1737,
"step": 31400
},
{
"epoch": 2.77,
"learning_rate": 1.561281622841732e-06,
"loss": 0.1636,
"step": 31450
},
{
"epoch": 2.77,
"learning_rate": 1.531967285199191e-06,
"loss": 0.1433,
"step": 31500
},
{
"epoch": 2.77,
"learning_rate": 1.50265294755665e-06,
"loss": 0.1628,
"step": 31550
},
{
"epoch": 2.78,
"learning_rate": 1.4733386099141092e-06,
"loss": 0.1835,
"step": 31600
},
{
"epoch": 2.78,
"learning_rate": 1.444024272271568e-06,
"loss": 0.169,
"step": 31650
},
{
"epoch": 2.79,
"learning_rate": 1.4147099346290272e-06,
"loss": 0.1724,
"step": 31700
},
{
"epoch": 2.79,
"learning_rate": 1.3853955969864864e-06,
"loss": 0.1512,
"step": 31750
},
{
"epoch": 2.8,
"learning_rate": 1.356081259343945e-06,
"loss": 0.1695,
"step": 31800
},
{
"epoch": 2.8,
"learning_rate": 1.3267669217014042e-06,
"loss": 0.1432,
"step": 31850
},
{
"epoch": 2.81,
"learning_rate": 1.2974525840588633e-06,
"loss": 0.183,
"step": 31900
},
{
"epoch": 2.81,
"learning_rate": 1.2681382464163222e-06,
"loss": 0.159,
"step": 31950
},
{
"epoch": 2.81,
"learning_rate": 1.2388239087737813e-06,
"loss": 0.1824,
"step": 32000
},
{
"epoch": 2.82,
"learning_rate": 1.2095095711312405e-06,
"loss": 0.1707,
"step": 32050
},
{
"epoch": 2.82,
"learning_rate": 1.1801952334886994e-06,
"loss": 0.1909,
"step": 32100
},
{
"epoch": 2.83,
"learning_rate": 1.1508808958461585e-06,
"loss": 0.1695,
"step": 32150
},
{
"epoch": 2.83,
"learning_rate": 1.1215665582036176e-06,
"loss": 0.1556,
"step": 32200
},
{
"epoch": 2.84,
"learning_rate": 1.0922522205610765e-06,
"loss": 0.1722,
"step": 32250
},
{
"epoch": 2.84,
"learning_rate": 1.0629378829185355e-06,
"loss": 0.1675,
"step": 32300
},
{
"epoch": 2.84,
"learning_rate": 1.0336235452759946e-06,
"loss": 0.1514,
"step": 32350
},
{
"epoch": 2.85,
"learning_rate": 1.0043092076334537e-06,
"loss": 0.1742,
"step": 32400
},
{
"epoch": 2.85,
"learning_rate": 9.749948699909126e-07,
"loss": 0.1494,
"step": 32450
},
{
"epoch": 2.86,
"learning_rate": 9.456805323483717e-07,
"loss": 0.1727,
"step": 32500
},
{
"epoch": 2.86,
"learning_rate": 9.163661947058307e-07,
"loss": 0.1691,
"step": 32550
},
{
"epoch": 2.87,
"learning_rate": 8.870518570632897e-07,
"loss": 0.166,
"step": 32600
},
{
"epoch": 2.87,
"learning_rate": 8.577375194207488e-07,
"loss": 0.1776,
"step": 32650
},
{
"epoch": 2.88,
"learning_rate": 8.284231817782078e-07,
"loss": 0.1587,
"step": 32700
},
{
"epoch": 2.88,
"learning_rate": 7.991088441356669e-07,
"loss": 0.1468,
"step": 32750
},
{
"epoch": 2.88,
"learning_rate": 7.697945064931259e-07,
"loss": 0.1896,
"step": 32800
},
{
"epoch": 2.89,
"learning_rate": 7.404801688505849e-07,
"loss": 0.1698,
"step": 32850
},
{
"epoch": 2.89,
"learning_rate": 7.11165831208044e-07,
"loss": 0.1526,
"step": 32900
},
{
"epoch": 2.9,
"learning_rate": 6.818514935655029e-07,
"loss": 0.1623,
"step": 32950
},
{
"epoch": 2.9,
"learning_rate": 6.525371559229619e-07,
"loss": 0.1699,
"step": 33000
},
{
"epoch": 2.91,
"learning_rate": 6.23222818280421e-07,
"loss": 0.1598,
"step": 33050
},
{
"epoch": 2.91,
"learning_rate": 5.939084806378801e-07,
"loss": 0.1612,
"step": 33100
},
{
"epoch": 2.92,
"learning_rate": 5.645941429953391e-07,
"loss": 0.186,
"step": 33150
},
{
"epoch": 2.92,
"learning_rate": 5.352798053527981e-07,
"loss": 0.1599,
"step": 33200
},
{
"epoch": 2.92,
"learning_rate": 5.059654677102571e-07,
"loss": 0.1432,
"step": 33250
},
{
"epoch": 2.93,
"learning_rate": 4.7665113006771615e-07,
"loss": 0.1675,
"step": 33300
},
{
"epoch": 2.93,
"learning_rate": 4.473367924251752e-07,
"loss": 0.1687,
"step": 33350
},
{
"epoch": 2.94,
"learning_rate": 4.180224547826342e-07,
"loss": 0.1611,
"step": 33400
},
{
"epoch": 2.94,
"learning_rate": 3.8870811714009326e-07,
"loss": 0.1613,
"step": 33450
},
{
"epoch": 2.95,
"learning_rate": 3.5939377949755233e-07,
"loss": 0.1654,
"step": 33500
},
{
"epoch": 2.95,
"learning_rate": 3.300794418550113e-07,
"loss": 0.1605,
"step": 33550
},
{
"epoch": 2.95,
"learning_rate": 3.007651042124703e-07,
"loss": 0.1465,
"step": 33600
},
{
"epoch": 2.96,
"learning_rate": 2.714507665699294e-07,
"loss": 0.1618,
"step": 33650
},
{
"epoch": 2.96,
"learning_rate": 2.421364289273884e-07,
"loss": 0.1408,
"step": 33700
},
{
"epoch": 2.97,
"learning_rate": 2.1282209128484745e-07,
"loss": 0.1524,
"step": 33750
},
{
"epoch": 2.97,
"learning_rate": 1.8350775364230647e-07,
"loss": 0.171,
"step": 33800
},
{
"epoch": 2.98,
"learning_rate": 1.5419341599976551e-07,
"loss": 0.152,
"step": 33850
},
{
"epoch": 2.98,
"learning_rate": 1.2487907835722453e-07,
"loss": 0.1645,
"step": 33900
},
{
"epoch": 2.99,
"learning_rate": 9.556474071468355e-08,
"loss": 0.187,
"step": 33950
},
{
"epoch": 2.99,
"learning_rate": 6.62504030721426e-08,
"loss": 0.1644,
"step": 34000
},
{
"epoch": 2.99,
"learning_rate": 3.693606542960162e-08,
"loss": 0.1756,
"step": 34050
},
{
"epoch": 3.0,
"learning_rate": 7.621727787060652e-09,
"loss": 0.1776,
"step": 34100
},
{
"epoch": 3.0,
"step": 34113,
"total_flos": 1.6912713679960627e+17,
"train_loss": 0.24277812267493906,
"train_runtime": 14385.031,
"train_samples_per_second": 75.88,
"train_steps_per_second": 2.371
}
],
"logging_steps": 50,
"max_steps": 34113,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 10000,
"total_flos": 1.6912713679960627e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}