bart-base-cantonese-v3 / trainer_state.json
raptorkwok's picture
End of training
c08dbf3
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 126927,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.9695895375403767e-06,
"loss": 2.2799,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 3.9391790750807535e-06,
"loss": 1.5412,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 5.90876861262113e-06,
"loss": 1.4193,
"step": 1500
},
{
"epoch": 0.05,
"learning_rate": 7.878358150161507e-06,
"loss": 1.3533,
"step": 2000
},
{
"epoch": 0.06,
"learning_rate": 9.847947687701884e-06,
"loss": 1.3108,
"step": 2500
},
{
"epoch": 0.07,
"learning_rate": 1.181753722524226e-05,
"loss": 1.2817,
"step": 3000
},
{
"epoch": 0.08,
"learning_rate": 1.3787126762782637e-05,
"loss": 1.2611,
"step": 3500
},
{
"epoch": 0.09,
"learning_rate": 1.5756716300323014e-05,
"loss": 1.2603,
"step": 4000
},
{
"epoch": 0.11,
"learning_rate": 1.7726305837863392e-05,
"loss": 1.2644,
"step": 4500
},
{
"epoch": 0.12,
"learning_rate": 1.9695895375403767e-05,
"loss": 1.2576,
"step": 5000
},
{
"epoch": 0.13,
"learning_rate": 2.1665484912944143e-05,
"loss": 1.2588,
"step": 5500
},
{
"epoch": 0.14,
"learning_rate": 2.363507445048452e-05,
"loss": 1.2928,
"step": 6000
},
{
"epoch": 0.15,
"learning_rate": 2.5604663988024896e-05,
"loss": 1.284,
"step": 6500
},
{
"epoch": 0.17,
"learning_rate": 2.7574253525565274e-05,
"loss": 1.2794,
"step": 7000
},
{
"epoch": 0.18,
"learning_rate": 2.9543843063105653e-05,
"loss": 1.2619,
"step": 7500
},
{
"epoch": 0.19,
"learning_rate": 3.151343260064603e-05,
"loss": 1.2615,
"step": 8000
},
{
"epoch": 0.2,
"learning_rate": 3.34830221381864e-05,
"loss": 1.2579,
"step": 8500
},
{
"epoch": 0.21,
"learning_rate": 3.5452611675726785e-05,
"loss": 1.2797,
"step": 9000
},
{
"epoch": 0.22,
"learning_rate": 3.742220121326715e-05,
"loss": 1.3019,
"step": 9500
},
{
"epoch": 0.24,
"learning_rate": 3.9391790750807535e-05,
"loss": 1.3154,
"step": 10000
},
{
"epoch": 0.25,
"learning_rate": 4.136138028834791e-05,
"loss": 1.3198,
"step": 10500
},
{
"epoch": 0.26,
"learning_rate": 4.3330969825888285e-05,
"loss": 1.3181,
"step": 11000
},
{
"epoch": 0.27,
"learning_rate": 4.530055936342866e-05,
"loss": 1.3222,
"step": 11500
},
{
"epoch": 0.28,
"learning_rate": 4.727014890096904e-05,
"loss": 1.3179,
"step": 12000
},
{
"epoch": 0.3,
"learning_rate": 4.923973843850942e-05,
"loss": 1.3137,
"step": 12500
},
{
"epoch": 0.31,
"learning_rate": 4.9865626696079984e-05,
"loss": 1.319,
"step": 13000
},
{
"epoch": 0.32,
"learning_rate": 4.964677766689427e-05,
"loss": 1.3219,
"step": 13500
},
{
"epoch": 0.33,
"learning_rate": 4.9427928637708566e-05,
"loss": 1.3225,
"step": 14000
},
{
"epoch": 0.34,
"learning_rate": 4.9209079608522854e-05,
"loss": 1.3235,
"step": 14500
},
{
"epoch": 0.35,
"learning_rate": 4.8990230579337155e-05,
"loss": 1.3323,
"step": 15000
},
{
"epoch": 0.37,
"learning_rate": 4.877138155015144e-05,
"loss": 1.332,
"step": 15500
},
{
"epoch": 0.38,
"learning_rate": 4.855253252096574e-05,
"loss": 1.337,
"step": 16000
},
{
"epoch": 0.39,
"learning_rate": 4.833368349178003e-05,
"loss": 1.3473,
"step": 16500
},
{
"epoch": 0.4,
"learning_rate": 4.811483446259433e-05,
"loss": 1.3547,
"step": 17000
},
{
"epoch": 0.41,
"learning_rate": 4.789598543340862e-05,
"loss": 1.3607,
"step": 17500
},
{
"epoch": 0.43,
"learning_rate": 4.767713640422291e-05,
"loss": 1.3697,
"step": 18000
},
{
"epoch": 0.44,
"learning_rate": 4.745828737503721e-05,
"loss": 1.3835,
"step": 18500
},
{
"epoch": 0.45,
"learning_rate": 4.72394383458515e-05,
"loss": 1.39,
"step": 19000
},
{
"epoch": 0.46,
"learning_rate": 4.702058931666579e-05,
"loss": 1.3967,
"step": 19500
},
{
"epoch": 0.47,
"learning_rate": 4.680174028748009e-05,
"loss": 1.4147,
"step": 20000
},
{
"epoch": 0.48,
"learning_rate": 4.658289125829438e-05,
"loss": 1.4176,
"step": 20500
},
{
"epoch": 0.5,
"learning_rate": 4.636404222910867e-05,
"loss": 1.4212,
"step": 21000
},
{
"epoch": 0.51,
"learning_rate": 4.6145193199922965e-05,
"loss": 1.4412,
"step": 21500
},
{
"epoch": 0.52,
"learning_rate": 4.592634417073726e-05,
"loss": 1.4453,
"step": 22000
},
{
"epoch": 0.53,
"learning_rate": 4.5707495141551554e-05,
"loss": 1.459,
"step": 22500
},
{
"epoch": 0.54,
"learning_rate": 4.548864611236585e-05,
"loss": 1.4673,
"step": 23000
},
{
"epoch": 0.56,
"learning_rate": 4.526979708318014e-05,
"loss": 1.4801,
"step": 23500
},
{
"epoch": 0.57,
"learning_rate": 4.505094805399444e-05,
"loss": 1.49,
"step": 24000
},
{
"epoch": 0.58,
"learning_rate": 4.4832099024808725e-05,
"loss": 1.5053,
"step": 24500
},
{
"epoch": 0.59,
"learning_rate": 4.461324999562303e-05,
"loss": 1.5219,
"step": 25000
},
{
"epoch": 0.6,
"learning_rate": 4.4394400966437315e-05,
"loss": 1.5357,
"step": 25500
},
{
"epoch": 0.61,
"learning_rate": 4.417555193725161e-05,
"loss": 1.5541,
"step": 26000
},
{
"epoch": 0.63,
"learning_rate": 4.39567029080659e-05,
"loss": 1.5622,
"step": 26500
},
{
"epoch": 0.64,
"learning_rate": 4.37378538788802e-05,
"loss": 1.5767,
"step": 27000
},
{
"epoch": 0.65,
"learning_rate": 4.3519004849694486e-05,
"loss": 1.5989,
"step": 27500
},
{
"epoch": 0.66,
"learning_rate": 4.330015582050878e-05,
"loss": 1.6185,
"step": 28000
},
{
"epoch": 0.67,
"learning_rate": 4.3081306791323075e-05,
"loss": 1.6308,
"step": 28500
},
{
"epoch": 0.69,
"learning_rate": 4.286245776213737e-05,
"loss": 1.6442,
"step": 29000
},
{
"epoch": 0.7,
"learning_rate": 4.2643608732951665e-05,
"loss": 1.6663,
"step": 29500
},
{
"epoch": 0.71,
"learning_rate": 4.242475970376595e-05,
"loss": 1.6664,
"step": 30000
},
{
"epoch": 0.72,
"learning_rate": 4.2205910674580254e-05,
"loss": 1.6863,
"step": 30500
},
{
"epoch": 0.73,
"learning_rate": 4.198706164539454e-05,
"loss": 1.7141,
"step": 31000
},
{
"epoch": 0.74,
"learning_rate": 4.1768212616208836e-05,
"loss": 1.7386,
"step": 31500
},
{
"epoch": 0.76,
"learning_rate": 4.154936358702313e-05,
"loss": 1.7529,
"step": 32000
},
{
"epoch": 0.77,
"learning_rate": 4.1330514557837425e-05,
"loss": 1.7677,
"step": 32500
},
{
"epoch": 0.78,
"learning_rate": 4.111166552865171e-05,
"loss": 1.7869,
"step": 33000
},
{
"epoch": 0.79,
"learning_rate": 4.089281649946601e-05,
"loss": 1.8113,
"step": 33500
},
{
"epoch": 0.8,
"learning_rate": 4.06739674702803e-05,
"loss": 1.8355,
"step": 34000
},
{
"epoch": 0.82,
"learning_rate": 4.04551184410946e-05,
"loss": 1.8553,
"step": 34500
},
{
"epoch": 0.83,
"learning_rate": 4.023626941190889e-05,
"loss": 1.8627,
"step": 35000
},
{
"epoch": 0.84,
"learning_rate": 4.0017420382723186e-05,
"loss": 1.8882,
"step": 35500
},
{
"epoch": 0.85,
"learning_rate": 3.979857135353748e-05,
"loss": 1.9145,
"step": 36000
},
{
"epoch": 0.86,
"learning_rate": 3.957972232435177e-05,
"loss": 1.943,
"step": 36500
},
{
"epoch": 0.87,
"learning_rate": 3.936087329516606e-05,
"loss": 1.9686,
"step": 37000
},
{
"epoch": 0.89,
"learning_rate": 3.914202426598036e-05,
"loss": 1.9603,
"step": 37500
},
{
"epoch": 0.9,
"learning_rate": 3.892317523679465e-05,
"loss": 1.9882,
"step": 38000
},
{
"epoch": 0.91,
"learning_rate": 3.870432620760894e-05,
"loss": 2.0193,
"step": 38500
},
{
"epoch": 0.92,
"learning_rate": 3.848547717842324e-05,
"loss": 2.0497,
"step": 39000
},
{
"epoch": 0.93,
"learning_rate": 3.826662814923753e-05,
"loss": 2.0652,
"step": 39500
},
{
"epoch": 0.95,
"learning_rate": 3.8047779120051824e-05,
"loss": 2.0841,
"step": 40000
},
{
"epoch": 0.96,
"learning_rate": 3.782893009086612e-05,
"loss": 2.0982,
"step": 40500
},
{
"epoch": 0.97,
"learning_rate": 3.761008106168041e-05,
"loss": 2.1247,
"step": 41000
},
{
"epoch": 0.98,
"learning_rate": 3.739123203249471e-05,
"loss": 2.166,
"step": 41500
},
{
"epoch": 0.99,
"learning_rate": 3.7172383003308995e-05,
"loss": 2.2057,
"step": 42000
},
{
"epoch": 1.0,
"learning_rate": 3.69535339741233e-05,
"loss": 2.2021,
"step": 42500
},
{
"epoch": 1.02,
"learning_rate": 3.6734684944937585e-05,
"loss": 2.1949,
"step": 43000
},
{
"epoch": 1.03,
"learning_rate": 3.651583591575188e-05,
"loss": 2.2436,
"step": 43500
},
{
"epoch": 1.04,
"learning_rate": 3.6296986886566174e-05,
"loss": 2.2572,
"step": 44000
},
{
"epoch": 1.05,
"learning_rate": 3.607813785738047e-05,
"loss": 2.3058,
"step": 44500
},
{
"epoch": 1.06,
"learning_rate": 3.5859288828194756e-05,
"loss": 2.3194,
"step": 45000
},
{
"epoch": 1.08,
"learning_rate": 3.564043979900905e-05,
"loss": 2.3435,
"step": 45500
},
{
"epoch": 1.09,
"learning_rate": 3.5421590769823345e-05,
"loss": 2.36,
"step": 46000
},
{
"epoch": 1.1,
"learning_rate": 3.520274174063764e-05,
"loss": 2.3517,
"step": 46500
},
{
"epoch": 1.11,
"learning_rate": 3.4983892711451935e-05,
"loss": 2.3883,
"step": 47000
},
{
"epoch": 1.12,
"learning_rate": 3.476504368226623e-05,
"loss": 2.4303,
"step": 47500
},
{
"epoch": 1.13,
"learning_rate": 3.4546194653080524e-05,
"loss": 2.4461,
"step": 48000
},
{
"epoch": 1.15,
"learning_rate": 3.432734562389481e-05,
"loss": 2.4838,
"step": 48500
},
{
"epoch": 1.16,
"learning_rate": 3.4108496594709106e-05,
"loss": 2.4896,
"step": 49000
},
{
"epoch": 1.17,
"learning_rate": 3.38896475655234e-05,
"loss": 2.5103,
"step": 49500
},
{
"epoch": 1.18,
"learning_rate": 3.3670798536337695e-05,
"loss": 2.52,
"step": 50000
},
{
"epoch": 1.19,
"learning_rate": 3.345194950715198e-05,
"loss": 2.5623,
"step": 50500
},
{
"epoch": 1.21,
"learning_rate": 3.3233100477966284e-05,
"loss": 2.6071,
"step": 51000
},
{
"epoch": 1.22,
"learning_rate": 3.301425144878057e-05,
"loss": 2.6037,
"step": 51500
},
{
"epoch": 1.23,
"learning_rate": 3.279540241959487e-05,
"loss": 2.612,
"step": 52000
},
{
"epoch": 1.24,
"learning_rate": 3.257655339040916e-05,
"loss": 2.6439,
"step": 52500
},
{
"epoch": 1.25,
"learning_rate": 3.2357704361223456e-05,
"loss": 2.68,
"step": 53000
},
{
"epoch": 1.26,
"learning_rate": 3.213885533203775e-05,
"loss": 2.7046,
"step": 53500
},
{
"epoch": 1.28,
"learning_rate": 3.192000630285204e-05,
"loss": 2.7324,
"step": 54000
},
{
"epoch": 1.29,
"learning_rate": 3.170115727366634e-05,
"loss": 2.7083,
"step": 54500
},
{
"epoch": 1.3,
"learning_rate": 3.148230824448063e-05,
"loss": 2.7454,
"step": 55000
},
{
"epoch": 1.31,
"learning_rate": 3.126345921529492e-05,
"loss": 2.7702,
"step": 55500
},
{
"epoch": 1.32,
"learning_rate": 3.104461018610922e-05,
"loss": 2.8178,
"step": 56000
},
{
"epoch": 1.34,
"learning_rate": 3.082576115692351e-05,
"loss": 2.8356,
"step": 56500
},
{
"epoch": 1.35,
"learning_rate": 3.06069121277378e-05,
"loss": 2.882,
"step": 57000
},
{
"epoch": 1.36,
"learning_rate": 3.0388063098552094e-05,
"loss": 2.875,
"step": 57500
},
{
"epoch": 1.37,
"learning_rate": 3.0169214069366392e-05,
"loss": 2.89,
"step": 58000
},
{
"epoch": 1.38,
"learning_rate": 2.9950365040180683e-05,
"loss": 2.9216,
"step": 58500
},
{
"epoch": 1.39,
"learning_rate": 2.9731516010994974e-05,
"loss": 2.9342,
"step": 59000
},
{
"epoch": 1.41,
"learning_rate": 2.9512666981809272e-05,
"loss": 2.9611,
"step": 59500
},
{
"epoch": 1.42,
"learning_rate": 2.9293817952623563e-05,
"loss": 2.985,
"step": 60000
},
{
"epoch": 1.43,
"learning_rate": 2.9074968923437858e-05,
"loss": 3.0417,
"step": 60500
},
{
"epoch": 1.44,
"learning_rate": 2.885611989425215e-05,
"loss": 3.0432,
"step": 61000
},
{
"epoch": 1.45,
"learning_rate": 2.8637270865066447e-05,
"loss": 3.1159,
"step": 61500
},
{
"epoch": 1.47,
"learning_rate": 2.8418421835880738e-05,
"loss": 3.0895,
"step": 62000
},
{
"epoch": 1.48,
"learning_rate": 2.819957280669503e-05,
"loss": 3.1405,
"step": 62500
},
{
"epoch": 1.49,
"learning_rate": 2.7980723777509327e-05,
"loss": 3.1702,
"step": 63000
},
{
"epoch": 1.5,
"learning_rate": 2.776187474832362e-05,
"loss": 3.1864,
"step": 63500
},
{
"epoch": 1.51,
"learning_rate": 2.754302571913791e-05,
"loss": 3.2205,
"step": 64000
},
{
"epoch": 1.52,
"learning_rate": 2.73241766899522e-05,
"loss": 3.2553,
"step": 64500
},
{
"epoch": 1.54,
"learning_rate": 2.71053276607665e-05,
"loss": 3.2286,
"step": 65000
},
{
"epoch": 1.55,
"learning_rate": 2.688647863158079e-05,
"loss": 3.2645,
"step": 65500
},
{
"epoch": 1.56,
"learning_rate": 2.6667629602395085e-05,
"loss": 3.3086,
"step": 66000
},
{
"epoch": 1.57,
"learning_rate": 2.644878057320938e-05,
"loss": 3.329,
"step": 66500
},
{
"epoch": 1.58,
"learning_rate": 2.6229931544023674e-05,
"loss": 3.3106,
"step": 67000
},
{
"epoch": 1.6,
"learning_rate": 2.6011082514837965e-05,
"loss": 3.3475,
"step": 67500
},
{
"epoch": 1.61,
"learning_rate": 2.5792233485652256e-05,
"loss": 3.4266,
"step": 68000
},
{
"epoch": 1.62,
"learning_rate": 2.5573384456466554e-05,
"loss": 3.4385,
"step": 68500
},
{
"epoch": 1.63,
"learning_rate": 2.5354535427280846e-05,
"loss": 3.4392,
"step": 69000
},
{
"epoch": 1.64,
"learning_rate": 2.5135686398095137e-05,
"loss": 3.4493,
"step": 69500
},
{
"epoch": 1.65,
"learning_rate": 2.491683736890943e-05,
"loss": 3.4658,
"step": 70000
},
{
"epoch": 1.67,
"learning_rate": 2.4697988339723726e-05,
"loss": 3.5192,
"step": 70500
},
{
"epoch": 1.68,
"learning_rate": 2.4479139310538017e-05,
"loss": 3.5097,
"step": 71000
},
{
"epoch": 1.69,
"learning_rate": 2.4260290281352312e-05,
"loss": 3.508,
"step": 71500
},
{
"epoch": 1.7,
"learning_rate": 2.4041441252166606e-05,
"loss": 3.5515,
"step": 72000
},
{
"epoch": 1.71,
"learning_rate": 2.38225922229809e-05,
"loss": 3.5713,
"step": 72500
},
{
"epoch": 1.73,
"learning_rate": 2.3603743193795196e-05,
"loss": 3.5763,
"step": 73000
},
{
"epoch": 1.74,
"learning_rate": 2.3384894164609487e-05,
"loss": 3.5625,
"step": 73500
},
{
"epoch": 1.75,
"learning_rate": 2.316604513542378e-05,
"loss": 3.5827,
"step": 74000
},
{
"epoch": 1.76,
"learning_rate": 2.2947196106238073e-05,
"loss": 3.6353,
"step": 74500
},
{
"epoch": 1.77,
"learning_rate": 2.2728347077052367e-05,
"loss": 3.6288,
"step": 75000
},
{
"epoch": 1.78,
"learning_rate": 2.250949804786666e-05,
"loss": 3.6533,
"step": 75500
},
{
"epoch": 1.8,
"learning_rate": 2.2290649018680953e-05,
"loss": 3.6699,
"step": 76000
},
{
"epoch": 1.81,
"learning_rate": 2.2071799989495247e-05,
"loss": 3.7291,
"step": 76500
},
{
"epoch": 1.82,
"learning_rate": 2.185295096030954e-05,
"loss": 3.7706,
"step": 77000
},
{
"epoch": 1.83,
"learning_rate": 2.1634101931123833e-05,
"loss": 3.7364,
"step": 77500
},
{
"epoch": 1.84,
"learning_rate": 2.1415252901938128e-05,
"loss": 3.7643,
"step": 78000
},
{
"epoch": 1.86,
"learning_rate": 2.1196403872752422e-05,
"loss": 3.7627,
"step": 78500
},
{
"epoch": 1.87,
"learning_rate": 2.0977554843566717e-05,
"loss": 3.8162,
"step": 79000
},
{
"epoch": 1.88,
"learning_rate": 2.0758705814381008e-05,
"loss": 3.7577,
"step": 79500
},
{
"epoch": 1.89,
"learning_rate": 2.0539856785195303e-05,
"loss": 3.8726,
"step": 80000
},
{
"epoch": 1.9,
"learning_rate": 2.0321007756009594e-05,
"loss": 3.7651,
"step": 80500
},
{
"epoch": 1.91,
"learning_rate": 2.010215872682389e-05,
"loss": 3.8335,
"step": 81000
},
{
"epoch": 1.93,
"learning_rate": 1.9883309697638183e-05,
"loss": 3.9479,
"step": 81500
},
{
"epoch": 1.94,
"learning_rate": 1.9664460668452474e-05,
"loss": 3.9535,
"step": 82000
},
{
"epoch": 1.95,
"learning_rate": 1.944561163926677e-05,
"loss": 3.8729,
"step": 82500
},
{
"epoch": 1.96,
"learning_rate": 1.922676261008106e-05,
"loss": 3.8346,
"step": 83000
},
{
"epoch": 1.97,
"learning_rate": 1.9007913580895355e-05,
"loss": 3.8862,
"step": 83500
},
{
"epoch": 1.99,
"learning_rate": 1.878906455170965e-05,
"loss": 3.9375,
"step": 84000
},
{
"epoch": 2.0,
"learning_rate": 1.8570215522523944e-05,
"loss": 3.9473,
"step": 84500
},
{
"epoch": 2.01,
"learning_rate": 1.835136649333824e-05,
"loss": 3.8917,
"step": 85000
},
{
"epoch": 2.02,
"learning_rate": 1.813251746415253e-05,
"loss": 3.9098,
"step": 85500
},
{
"epoch": 2.03,
"learning_rate": 1.7913668434966824e-05,
"loss": 3.9818,
"step": 86000
},
{
"epoch": 2.04,
"learning_rate": 1.7694819405781116e-05,
"loss": 4.0648,
"step": 86500
},
{
"epoch": 2.06,
"learning_rate": 1.747597037659541e-05,
"loss": 3.9938,
"step": 87000
},
{
"epoch": 2.07,
"learning_rate": 1.7257121347409705e-05,
"loss": 4.0287,
"step": 87500
},
{
"epoch": 2.08,
"learning_rate": 1.7038272318223996e-05,
"loss": 4.0314,
"step": 88000
},
{
"epoch": 2.09,
"learning_rate": 1.681942328903829e-05,
"loss": 4.064,
"step": 88500
},
{
"epoch": 2.1,
"learning_rate": 1.660057425985258e-05,
"loss": 4.1593,
"step": 89000
},
{
"epoch": 2.12,
"learning_rate": 1.6381725230666876e-05,
"loss": 4.0682,
"step": 89500
},
{
"epoch": 2.13,
"learning_rate": 1.616287620148117e-05,
"loss": 4.0718,
"step": 90000
},
{
"epoch": 2.14,
"learning_rate": 1.5944027172295465e-05,
"loss": 4.1568,
"step": 90500
},
{
"epoch": 2.15,
"learning_rate": 1.572517814310976e-05,
"loss": 4.1404,
"step": 91000
},
{
"epoch": 2.16,
"learning_rate": 1.550632911392405e-05,
"loss": 4.1093,
"step": 91500
},
{
"epoch": 2.17,
"learning_rate": 1.5287480084738346e-05,
"loss": 4.1537,
"step": 92000
},
{
"epoch": 2.19,
"learning_rate": 1.5068631055552637e-05,
"loss": 4.1525,
"step": 92500
},
{
"epoch": 2.2,
"learning_rate": 1.4849782026366932e-05,
"loss": 4.2281,
"step": 93000
},
{
"epoch": 2.21,
"learning_rate": 1.4630932997181226e-05,
"loss": 4.2084,
"step": 93500
},
{
"epoch": 2.22,
"learning_rate": 1.4412083967995519e-05,
"loss": 4.1527,
"step": 94000
},
{
"epoch": 2.23,
"learning_rate": 1.4193234938809814e-05,
"loss": 4.1998,
"step": 94500
},
{
"epoch": 2.25,
"learning_rate": 1.3974385909624105e-05,
"loss": 4.2787,
"step": 95000
},
{
"epoch": 2.26,
"learning_rate": 1.37555368804384e-05,
"loss": 4.2254,
"step": 95500
},
{
"epoch": 2.27,
"learning_rate": 1.353668785125269e-05,
"loss": 4.3185,
"step": 96000
},
{
"epoch": 2.28,
"learning_rate": 1.3317838822066985e-05,
"loss": 4.224,
"step": 96500
},
{
"epoch": 2.29,
"learning_rate": 1.309898979288128e-05,
"loss": 4.2883,
"step": 97000
},
{
"epoch": 2.3,
"learning_rate": 1.2880140763695573e-05,
"loss": 4.3107,
"step": 97500
},
{
"epoch": 2.32,
"learning_rate": 1.2661291734509867e-05,
"loss": 4.3294,
"step": 98000
},
{
"epoch": 2.33,
"learning_rate": 1.244244270532416e-05,
"loss": 4.2324,
"step": 98500
},
{
"epoch": 2.34,
"learning_rate": 1.2223593676138453e-05,
"loss": 4.2461,
"step": 99000
},
{
"epoch": 2.35,
"learning_rate": 1.2004744646952746e-05,
"loss": 4.2851,
"step": 99500
},
{
"epoch": 2.36,
"learning_rate": 1.178589561776704e-05,
"loss": 4.3212,
"step": 100000
},
{
"epoch": 2.38,
"learning_rate": 1.1567046588581334e-05,
"loss": 4.2605,
"step": 100500
},
{
"epoch": 2.39,
"learning_rate": 1.1348197559395628e-05,
"loss": 4.3192,
"step": 101000
},
{
"epoch": 2.4,
"learning_rate": 1.1129348530209921e-05,
"loss": 4.2155,
"step": 101500
},
{
"epoch": 2.41,
"learning_rate": 1.0910499501024214e-05,
"loss": 4.3539,
"step": 102000
},
{
"epoch": 2.42,
"learning_rate": 1.0691650471838507e-05,
"loss": 4.3861,
"step": 102500
},
{
"epoch": 2.43,
"learning_rate": 1.0472801442652801e-05,
"loss": 4.3794,
"step": 103000
},
{
"epoch": 2.45,
"learning_rate": 1.0253952413467094e-05,
"loss": 4.4012,
"step": 103500
},
{
"epoch": 2.46,
"learning_rate": 1.0035103384281387e-05,
"loss": 4.4926,
"step": 104000
},
{
"epoch": 2.47,
"learning_rate": 9.816254355095682e-06,
"loss": 4.4272,
"step": 104500
},
{
"epoch": 2.48,
"learning_rate": 9.597405325909975e-06,
"loss": 4.4388,
"step": 105000
},
{
"epoch": 2.49,
"learning_rate": 9.378556296724268e-06,
"loss": 4.5219,
"step": 105500
},
{
"epoch": 2.51,
"learning_rate": 9.159707267538562e-06,
"loss": 4.4793,
"step": 106000
},
{
"epoch": 2.52,
"learning_rate": 8.940858238352855e-06,
"loss": 4.4689,
"step": 106500
},
{
"epoch": 2.53,
"learning_rate": 8.722009209167148e-06,
"loss": 4.5059,
"step": 107000
},
{
"epoch": 2.54,
"learning_rate": 8.503160179981443e-06,
"loss": 4.4757,
"step": 107500
},
{
"epoch": 2.55,
"learning_rate": 8.284311150795735e-06,
"loss": 4.4278,
"step": 108000
},
{
"epoch": 2.56,
"learning_rate": 8.065462121610028e-06,
"loss": 4.456,
"step": 108500
},
{
"epoch": 2.58,
"learning_rate": 7.846613092424323e-06,
"loss": 4.4488,
"step": 109000
},
{
"epoch": 2.59,
"learning_rate": 7.627764063238616e-06,
"loss": 4.4274,
"step": 109500
},
{
"epoch": 2.6,
"learning_rate": 7.408915034052909e-06,
"loss": 4.5074,
"step": 110000
},
{
"epoch": 2.61,
"learning_rate": 7.190066004867203e-06,
"loss": 4.4552,
"step": 110500
},
{
"epoch": 2.62,
"learning_rate": 6.971216975681496e-06,
"loss": 4.6251,
"step": 111000
},
{
"epoch": 2.64,
"learning_rate": 6.75236794649579e-06,
"loss": 4.4865,
"step": 111500
},
{
"epoch": 2.65,
"learning_rate": 6.533518917310083e-06,
"loss": 4.538,
"step": 112000
},
{
"epoch": 2.66,
"learning_rate": 6.3146698881243765e-06,
"loss": 4.5254,
"step": 112500
},
{
"epoch": 2.67,
"learning_rate": 6.09582085893867e-06,
"loss": 4.5184,
"step": 113000
},
{
"epoch": 2.68,
"learning_rate": 5.876971829752963e-06,
"loss": 4.5289,
"step": 113500
},
{
"epoch": 2.69,
"learning_rate": 5.658122800567257e-06,
"loss": 4.5344,
"step": 114000
},
{
"epoch": 2.71,
"learning_rate": 5.439273771381551e-06,
"loss": 4.4482,
"step": 114500
},
{
"epoch": 2.72,
"learning_rate": 5.2204247421958435e-06,
"loss": 4.3568,
"step": 115000
},
{
"epoch": 2.73,
"learning_rate": 5.001575713010137e-06,
"loss": 4.4135,
"step": 115500
},
{
"epoch": 2.74,
"learning_rate": 4.782726683824431e-06,
"loss": 4.5899,
"step": 116000
},
{
"epoch": 2.75,
"learning_rate": 4.563877654638724e-06,
"loss": 4.5756,
"step": 116500
},
{
"epoch": 2.77,
"learning_rate": 4.345028625453018e-06,
"loss": 4.5709,
"step": 117000
},
{
"epoch": 2.78,
"learning_rate": 4.126179596267311e-06,
"loss": 4.4579,
"step": 117500
},
{
"epoch": 2.79,
"learning_rate": 3.907330567081604e-06,
"loss": 4.5885,
"step": 118000
},
{
"epoch": 2.8,
"learning_rate": 3.688481537895898e-06,
"loss": 4.5342,
"step": 118500
},
{
"epoch": 2.81,
"learning_rate": 3.4696325087101918e-06,
"loss": 4.5425,
"step": 119000
},
{
"epoch": 2.82,
"learning_rate": 3.250783479524485e-06,
"loss": 4.4677,
"step": 119500
},
{
"epoch": 2.84,
"learning_rate": 3.0319344503387784e-06,
"loss": 4.5301,
"step": 120000
},
{
"epoch": 2.85,
"learning_rate": 2.8130854211530717e-06,
"loss": 4.6553,
"step": 120500
},
{
"epoch": 2.86,
"learning_rate": 2.5942363919673655e-06,
"loss": 4.5941,
"step": 121000
},
{
"epoch": 2.87,
"learning_rate": 2.375387362781659e-06,
"loss": 4.5893,
"step": 121500
},
{
"epoch": 2.88,
"learning_rate": 2.156538333595952e-06,
"loss": 4.5517,
"step": 122000
},
{
"epoch": 2.9,
"learning_rate": 1.937689304410246e-06,
"loss": 4.5529,
"step": 122500
},
{
"epoch": 2.91,
"learning_rate": 1.718840275224539e-06,
"loss": 4.5209,
"step": 123000
},
{
"epoch": 2.92,
"learning_rate": 1.4999912460388327e-06,
"loss": 4.5149,
"step": 123500
},
{
"epoch": 2.93,
"learning_rate": 1.2811422168531262e-06,
"loss": 4.5322,
"step": 124000
},
{
"epoch": 2.94,
"learning_rate": 1.0622931876674195e-06,
"loss": 4.5249,
"step": 124500
},
{
"epoch": 2.95,
"learning_rate": 8.43444158481713e-07,
"loss": 4.5291,
"step": 125000
},
{
"epoch": 2.97,
"learning_rate": 6.245951292960065e-07,
"loss": 4.5445,
"step": 125500
},
{
"epoch": 2.98,
"learning_rate": 4.057461001102999e-07,
"loss": 4.5969,
"step": 126000
},
{
"epoch": 2.99,
"learning_rate": 1.868970709245934e-07,
"loss": 4.5407,
"step": 126500
},
{
"epoch": 3.0,
"step": 126927,
"total_flos": 1.2382668233323315e+18,
"train_loss": 3.0266231093955582,
"train_runtime": 107352.3632,
"train_samples_per_second": 37.835,
"train_steps_per_second": 1.182
}
],
"max_steps": 126927,
"num_train_epochs": 3,
"total_flos": 1.2382668233323315e+18,
"trial_name": null,
"trial_params": null
}