roberta-base-qqp-sft / trainer_state.json
EvaristeL's picture
Upload folder using huggingface_hub
aa12cdb verified
{
"best_metric": 0.8990160346845362,
"best_model_checkpoint": "./save_models/qqp/roberta-base_lr1e-05_run0/checkpoint-204670",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 204670,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.0713296962788053e-07,
"loss": 0.6914,
"step": 500
},
{
"epoch": 0.05,
"learning_rate": 8.142659392557611e-07,
"loss": 0.6479,
"step": 1000
},
{
"epoch": 0.07,
"learning_rate": 1.2213989088836414e-06,
"loss": 0.5224,
"step": 1500
},
{
"epoch": 0.1,
"learning_rate": 1.6285318785115221e-06,
"loss": 0.4532,
"step": 2000
},
{
"epoch": 0.12,
"learning_rate": 2.0356648481394024e-06,
"loss": 0.4179,
"step": 2500
},
{
"epoch": 0.15,
"learning_rate": 2.442797817767283e-06,
"loss": 0.4075,
"step": 3000
},
{
"epoch": 0.17,
"learning_rate": 2.8499307873951637e-06,
"loss": 0.3777,
"step": 3500
},
{
"epoch": 0.2,
"learning_rate": 3.2570637570230442e-06,
"loss": 0.3735,
"step": 4000
},
{
"epoch": 0.22,
"learning_rate": 3.6641967266509243e-06,
"loss": 0.3609,
"step": 4500
},
{
"epoch": 0.24,
"learning_rate": 4.071329696278805e-06,
"loss": 0.3624,
"step": 5000
},
{
"epoch": 0.27,
"learning_rate": 4.478462665906685e-06,
"loss": 0.3574,
"step": 5500
},
{
"epoch": 0.29,
"learning_rate": 4.885595635534566e-06,
"loss": 0.3509,
"step": 6000
},
{
"epoch": 0.32,
"learning_rate": 5.292728605162446e-06,
"loss": 0.3387,
"step": 6500
},
{
"epoch": 0.34,
"learning_rate": 5.6998615747903275e-06,
"loss": 0.335,
"step": 7000
},
{
"epoch": 0.37,
"learning_rate": 6.106994544418208e-06,
"loss": 0.3242,
"step": 7500
},
{
"epoch": 0.39,
"learning_rate": 6.5141275140460884e-06,
"loss": 0.3317,
"step": 8000
},
{
"epoch": 0.42,
"learning_rate": 6.921260483673968e-06,
"loss": 0.3182,
"step": 8500
},
{
"epoch": 0.44,
"learning_rate": 7.3283934533018485e-06,
"loss": 0.3197,
"step": 9000
},
{
"epoch": 0.46,
"learning_rate": 7.73552642292973e-06,
"loss": 0.3213,
"step": 9500
},
{
"epoch": 0.49,
"learning_rate": 8.14265939255761e-06,
"loss": 0.3204,
"step": 10000
},
{
"epoch": 0.51,
"learning_rate": 8.54979236218549e-06,
"loss": 0.3271,
"step": 10500
},
{
"epoch": 0.54,
"learning_rate": 8.95692533181337e-06,
"loss": 0.3107,
"step": 11000
},
{
"epoch": 0.56,
"learning_rate": 9.364058301441251e-06,
"loss": 0.31,
"step": 11500
},
{
"epoch": 0.59,
"learning_rate": 9.771191271069131e-06,
"loss": 0.3089,
"step": 12000
},
{
"epoch": 0.61,
"learning_rate": 9.988616812811544e-06,
"loss": 0.2948,
"step": 12500
},
{
"epoch": 0.64,
"learning_rate": 9.962627800965753e-06,
"loss": 0.3019,
"step": 13000
},
{
"epoch": 0.66,
"learning_rate": 9.936638789119961e-06,
"loss": 0.3093,
"step": 13500
},
{
"epoch": 0.68,
"learning_rate": 9.91064977727417e-06,
"loss": 0.3032,
"step": 14000
},
{
"epoch": 0.71,
"learning_rate": 9.884660765428378e-06,
"loss": 0.3014,
"step": 14500
},
{
"epoch": 0.73,
"learning_rate": 9.858671753582586e-06,
"loss": 0.3039,
"step": 15000
},
{
"epoch": 0.76,
"learning_rate": 9.832682741736795e-06,
"loss": 0.2994,
"step": 15500
},
{
"epoch": 0.78,
"learning_rate": 9.806693729891003e-06,
"loss": 0.2954,
"step": 16000
},
{
"epoch": 0.81,
"learning_rate": 9.78070471804521e-06,
"loss": 0.2907,
"step": 16500
},
{
"epoch": 0.83,
"learning_rate": 9.75471570619942e-06,
"loss": 0.2887,
"step": 17000
},
{
"epoch": 0.86,
"learning_rate": 9.728726694353629e-06,
"loss": 0.299,
"step": 17500
},
{
"epoch": 0.88,
"learning_rate": 9.702737682507836e-06,
"loss": 0.2789,
"step": 18000
},
{
"epoch": 0.9,
"learning_rate": 9.676748670662046e-06,
"loss": 0.2883,
"step": 18500
},
{
"epoch": 0.93,
"learning_rate": 9.650759658816253e-06,
"loss": 0.2873,
"step": 19000
},
{
"epoch": 0.95,
"learning_rate": 9.624770646970461e-06,
"loss": 0.2948,
"step": 19500
},
{
"epoch": 0.98,
"learning_rate": 9.59878163512467e-06,
"loss": 0.2746,
"step": 20000
},
{
"epoch": 1.0,
"eval_accuracy": 0.8817094956712931,
"eval_averaged_scores": 0.8643799788235642,
"eval_f1": 0.8470504619758352,
"eval_loss": 0.2860792577266693,
"eval_runtime": 36.8913,
"eval_samples_per_second": 986.277,
"eval_steps_per_second": 61.668,
"step": 20467
},
{
"epoch": 1.0,
"learning_rate": 9.572792623278878e-06,
"loss": 0.2906,
"step": 20500
},
{
"epoch": 1.03,
"learning_rate": 9.546803611433086e-06,
"loss": 0.2525,
"step": 21000
},
{
"epoch": 1.05,
"learning_rate": 9.520814599587295e-06,
"loss": 0.2551,
"step": 21500
},
{
"epoch": 1.07,
"learning_rate": 9.494825587741504e-06,
"loss": 0.259,
"step": 22000
},
{
"epoch": 1.1,
"learning_rate": 9.468836575895712e-06,
"loss": 0.2459,
"step": 22500
},
{
"epoch": 1.12,
"learning_rate": 9.442847564049921e-06,
"loss": 0.256,
"step": 23000
},
{
"epoch": 1.15,
"learning_rate": 9.416858552204129e-06,
"loss": 0.2573,
"step": 23500
},
{
"epoch": 1.17,
"learning_rate": 9.390869540358337e-06,
"loss": 0.2465,
"step": 24000
},
{
"epoch": 1.2,
"learning_rate": 9.364880528512546e-06,
"loss": 0.2519,
"step": 24500
},
{
"epoch": 1.22,
"learning_rate": 9.338891516666754e-06,
"loss": 0.2457,
"step": 25000
},
{
"epoch": 1.25,
"learning_rate": 9.312902504820961e-06,
"loss": 0.2502,
"step": 25500
},
{
"epoch": 1.27,
"learning_rate": 9.28691349297517e-06,
"loss": 0.253,
"step": 26000
},
{
"epoch": 1.29,
"learning_rate": 9.26092448112938e-06,
"loss": 0.2453,
"step": 26500
},
{
"epoch": 1.32,
"learning_rate": 9.234935469283588e-06,
"loss": 0.2576,
"step": 27000
},
{
"epoch": 1.34,
"learning_rate": 9.208946457437797e-06,
"loss": 0.2505,
"step": 27500
},
{
"epoch": 1.37,
"learning_rate": 9.182957445592005e-06,
"loss": 0.252,
"step": 28000
},
{
"epoch": 1.39,
"learning_rate": 9.156968433746212e-06,
"loss": 0.2536,
"step": 28500
},
{
"epoch": 1.42,
"learning_rate": 9.130979421900422e-06,
"loss": 0.2369,
"step": 29000
},
{
"epoch": 1.44,
"learning_rate": 9.10499041005463e-06,
"loss": 0.2459,
"step": 29500
},
{
"epoch": 1.47,
"learning_rate": 9.079001398208837e-06,
"loss": 0.2446,
"step": 30000
},
{
"epoch": 1.49,
"learning_rate": 9.053012386363046e-06,
"loss": 0.2434,
"step": 30500
},
{
"epoch": 1.51,
"learning_rate": 9.027023374517256e-06,
"loss": 0.2493,
"step": 31000
},
{
"epoch": 1.54,
"learning_rate": 9.001034362671463e-06,
"loss": 0.2506,
"step": 31500
},
{
"epoch": 1.56,
"learning_rate": 8.975045350825672e-06,
"loss": 0.2421,
"step": 32000
},
{
"epoch": 1.59,
"learning_rate": 8.94905633897988e-06,
"loss": 0.2467,
"step": 32500
},
{
"epoch": 1.61,
"learning_rate": 8.923067327134088e-06,
"loss": 0.2439,
"step": 33000
},
{
"epoch": 1.64,
"learning_rate": 8.897078315288297e-06,
"loss": 0.2423,
"step": 33500
},
{
"epoch": 1.66,
"learning_rate": 8.871089303442505e-06,
"loss": 0.25,
"step": 34000
},
{
"epoch": 1.69,
"learning_rate": 8.845100291596712e-06,
"loss": 0.2367,
"step": 34500
},
{
"epoch": 1.71,
"learning_rate": 8.819111279750922e-06,
"loss": 0.2387,
"step": 35000
},
{
"epoch": 1.73,
"learning_rate": 8.793122267905131e-06,
"loss": 0.2455,
"step": 35500
},
{
"epoch": 1.76,
"learning_rate": 8.767133256059339e-06,
"loss": 0.2439,
"step": 36000
},
{
"epoch": 1.78,
"learning_rate": 8.741144244213548e-06,
"loss": 0.2332,
"step": 36500
},
{
"epoch": 1.81,
"learning_rate": 8.715155232367756e-06,
"loss": 0.2446,
"step": 37000
},
{
"epoch": 1.83,
"learning_rate": 8.689166220521963e-06,
"loss": 0.2389,
"step": 37500
},
{
"epoch": 1.86,
"learning_rate": 8.663177208676173e-06,
"loss": 0.2346,
"step": 38000
},
{
"epoch": 1.88,
"learning_rate": 8.63718819683038e-06,
"loss": 0.2305,
"step": 38500
},
{
"epoch": 1.91,
"learning_rate": 8.61119918498459e-06,
"loss": 0.2331,
"step": 39000
},
{
"epoch": 1.93,
"learning_rate": 8.585210173138797e-06,
"loss": 0.2393,
"step": 39500
},
{
"epoch": 1.95,
"learning_rate": 8.559221161293007e-06,
"loss": 0.2371,
"step": 40000
},
{
"epoch": 1.98,
"learning_rate": 8.533232149447214e-06,
"loss": 0.2291,
"step": 40500
},
{
"epoch": 2.0,
"eval_accuracy": 0.8982272914662636,
"eval_averaged_scores": 0.8808907930119556,
"eval_f1": 0.8635542945576477,
"eval_loss": 0.27606385946273804,
"eval_runtime": 36.4573,
"eval_samples_per_second": 998.018,
"eval_steps_per_second": 62.402,
"step": 40934
},
{
"epoch": 2.0,
"learning_rate": 8.507243137601424e-06,
"loss": 0.2293,
"step": 41000
},
{
"epoch": 2.03,
"learning_rate": 8.481254125755631e-06,
"loss": 0.1943,
"step": 41500
},
{
"epoch": 2.05,
"learning_rate": 8.455265113909839e-06,
"loss": 0.2058,
"step": 42000
},
{
"epoch": 2.08,
"learning_rate": 8.429276102064048e-06,
"loss": 0.2089,
"step": 42500
},
{
"epoch": 2.1,
"learning_rate": 8.403287090218256e-06,
"loss": 0.2043,
"step": 43000
},
{
"epoch": 2.13,
"learning_rate": 8.377298078372465e-06,
"loss": 0.2005,
"step": 43500
},
{
"epoch": 2.15,
"learning_rate": 8.351309066526673e-06,
"loss": 0.2061,
"step": 44000
},
{
"epoch": 2.17,
"learning_rate": 8.325320054680882e-06,
"loss": 0.2058,
"step": 44500
},
{
"epoch": 2.2,
"learning_rate": 8.29933104283509e-06,
"loss": 0.2114,
"step": 45000
},
{
"epoch": 2.22,
"learning_rate": 8.2733420309893e-06,
"loss": 0.2008,
"step": 45500
},
{
"epoch": 2.25,
"learning_rate": 8.247353019143507e-06,
"loss": 0.2198,
"step": 46000
},
{
"epoch": 2.27,
"learning_rate": 8.221364007297714e-06,
"loss": 0.2153,
"step": 46500
},
{
"epoch": 2.3,
"learning_rate": 8.195374995451924e-06,
"loss": 0.2116,
"step": 47000
},
{
"epoch": 2.32,
"learning_rate": 8.169385983606131e-06,
"loss": 0.1998,
"step": 47500
},
{
"epoch": 2.35,
"learning_rate": 8.14339697176034e-06,
"loss": 0.2122,
"step": 48000
},
{
"epoch": 2.37,
"learning_rate": 8.117407959914548e-06,
"loss": 0.2036,
"step": 48500
},
{
"epoch": 2.39,
"learning_rate": 8.091418948068758e-06,
"loss": 0.2065,
"step": 49000
},
{
"epoch": 2.42,
"learning_rate": 8.065429936222965e-06,
"loss": 0.2038,
"step": 49500
},
{
"epoch": 2.44,
"learning_rate": 8.039440924377175e-06,
"loss": 0.207,
"step": 50000
},
{
"epoch": 2.47,
"learning_rate": 8.013451912531382e-06,
"loss": 0.2046,
"step": 50500
},
{
"epoch": 2.49,
"learning_rate": 7.98746290068559e-06,
"loss": 0.2116,
"step": 51000
},
{
"epoch": 2.52,
"learning_rate": 7.9614738888398e-06,
"loss": 0.2072,
"step": 51500
},
{
"epoch": 2.54,
"learning_rate": 7.935484876994007e-06,
"loss": 0.2117,
"step": 52000
},
{
"epoch": 2.57,
"learning_rate": 7.909495865148216e-06,
"loss": 0.2197,
"step": 52500
},
{
"epoch": 2.59,
"learning_rate": 7.883506853302424e-06,
"loss": 0.2037,
"step": 53000
},
{
"epoch": 2.61,
"learning_rate": 7.857517841456633e-06,
"loss": 0.207,
"step": 53500
},
{
"epoch": 2.64,
"learning_rate": 7.831528829610841e-06,
"loss": 0.219,
"step": 54000
},
{
"epoch": 2.66,
"learning_rate": 7.80553981776505e-06,
"loss": 0.2082,
"step": 54500
},
{
"epoch": 2.69,
"learning_rate": 7.779550805919258e-06,
"loss": 0.201,
"step": 55000
},
{
"epoch": 2.71,
"learning_rate": 7.753561794073467e-06,
"loss": 0.2127,
"step": 55500
},
{
"epoch": 2.74,
"learning_rate": 7.727572782227675e-06,
"loss": 0.2165,
"step": 56000
},
{
"epoch": 2.76,
"learning_rate": 7.701583770381883e-06,
"loss": 0.203,
"step": 56500
},
{
"epoch": 2.78,
"learning_rate": 7.675594758536092e-06,
"loss": 0.2147,
"step": 57000
},
{
"epoch": 2.81,
"learning_rate": 7.6496057466903e-06,
"loss": 0.2006,
"step": 57500
},
{
"epoch": 2.83,
"learning_rate": 7.623616734844508e-06,
"loss": 0.2063,
"step": 58000
},
{
"epoch": 2.86,
"learning_rate": 7.597627722998717e-06,
"loss": 0.2046,
"step": 58500
},
{
"epoch": 2.88,
"learning_rate": 7.571638711152926e-06,
"loss": 0.1942,
"step": 59000
},
{
"epoch": 2.91,
"learning_rate": 7.5456496993071335e-06,
"loss": 0.1976,
"step": 59500
},
{
"epoch": 2.93,
"learning_rate": 7.519660687461342e-06,
"loss": 0.2047,
"step": 60000
},
{
"epoch": 2.96,
"learning_rate": 7.4936716756155505e-06,
"loss": 0.2047,
"step": 60500
},
{
"epoch": 2.98,
"learning_rate": 7.467682663769759e-06,
"loss": 0.2035,
"step": 61000
},
{
"epoch": 3.0,
"eval_accuracy": 0.9074618661536348,
"eval_averaged_scores": 0.8925016186560136,
"eval_f1": 0.8775413711583925,
"eval_loss": 0.2975204288959503,
"eval_runtime": 36.3008,
"eval_samples_per_second": 1002.319,
"eval_steps_per_second": 62.671,
"step": 61401
},
{
"epoch": 3.0,
"learning_rate": 7.441693651923967e-06,
"loss": 0.1955,
"step": 61500
},
{
"epoch": 3.03,
"learning_rate": 7.415704640078175e-06,
"loss": 0.1745,
"step": 62000
},
{
"epoch": 3.05,
"learning_rate": 7.389715628232384e-06,
"loss": 0.1855,
"step": 62500
},
{
"epoch": 3.08,
"learning_rate": 7.363726616386593e-06,
"loss": 0.1743,
"step": 63000
},
{
"epoch": 3.1,
"learning_rate": 7.337737604540801e-06,
"loss": 0.1829,
"step": 63500
},
{
"epoch": 3.13,
"learning_rate": 7.311748592695009e-06,
"loss": 0.1898,
"step": 64000
},
{
"epoch": 3.15,
"learning_rate": 7.2857595808492175e-06,
"loss": 0.1878,
"step": 64500
},
{
"epoch": 3.18,
"learning_rate": 7.259770569003426e-06,
"loss": 0.1886,
"step": 65000
},
{
"epoch": 3.2,
"learning_rate": 7.2337815571576345e-06,
"loss": 0.1941,
"step": 65500
},
{
"epoch": 3.22,
"learning_rate": 7.207792545311842e-06,
"loss": 0.1901,
"step": 66000
},
{
"epoch": 3.25,
"learning_rate": 7.181803533466051e-06,
"loss": 0.1813,
"step": 66500
},
{
"epoch": 3.27,
"learning_rate": 7.155814521620259e-06,
"loss": 0.1947,
"step": 67000
},
{
"epoch": 3.3,
"learning_rate": 7.1298255097744685e-06,
"loss": 0.1787,
"step": 67500
},
{
"epoch": 3.32,
"learning_rate": 7.103836497928677e-06,
"loss": 0.1927,
"step": 68000
},
{
"epoch": 3.35,
"learning_rate": 7.077847486082885e-06,
"loss": 0.1961,
"step": 68500
},
{
"epoch": 3.37,
"learning_rate": 7.051858474237093e-06,
"loss": 0.1785,
"step": 69000
},
{
"epoch": 3.4,
"learning_rate": 7.025869462391302e-06,
"loss": 0.1892,
"step": 69500
},
{
"epoch": 3.42,
"learning_rate": 6.99988045054551e-06,
"loss": 0.1853,
"step": 70000
},
{
"epoch": 3.44,
"learning_rate": 6.973891438699718e-06,
"loss": 0.1892,
"step": 70500
},
{
"epoch": 3.47,
"learning_rate": 6.947902426853926e-06,
"loss": 0.1908,
"step": 71000
},
{
"epoch": 3.49,
"learning_rate": 6.921913415008135e-06,
"loss": 0.1859,
"step": 71500
},
{
"epoch": 3.52,
"learning_rate": 6.895924403162344e-06,
"loss": 0.1855,
"step": 72000
},
{
"epoch": 3.54,
"learning_rate": 6.8699353913165525e-06,
"loss": 0.1763,
"step": 72500
},
{
"epoch": 3.57,
"learning_rate": 6.84394637947076e-06,
"loss": 0.1886,
"step": 73000
},
{
"epoch": 3.59,
"learning_rate": 6.817957367624969e-06,
"loss": 0.1935,
"step": 73500
},
{
"epoch": 3.62,
"learning_rate": 6.791968355779177e-06,
"loss": 0.1889,
"step": 74000
},
{
"epoch": 3.64,
"learning_rate": 6.765979343933386e-06,
"loss": 0.1837,
"step": 74500
},
{
"epoch": 3.66,
"learning_rate": 6.739990332087593e-06,
"loss": 0.1782,
"step": 75000
},
{
"epoch": 3.69,
"learning_rate": 6.714001320241802e-06,
"loss": 0.1738,
"step": 75500
},
{
"epoch": 3.71,
"learning_rate": 6.68801230839601e-06,
"loss": 0.1833,
"step": 76000
},
{
"epoch": 3.74,
"learning_rate": 6.66202329655022e-06,
"loss": 0.1826,
"step": 76500
},
{
"epoch": 3.76,
"learning_rate": 6.636034284704428e-06,
"loss": 0.1856,
"step": 77000
},
{
"epoch": 3.79,
"learning_rate": 6.610045272858637e-06,
"loss": 0.1843,
"step": 77500
},
{
"epoch": 3.81,
"learning_rate": 6.584056261012844e-06,
"loss": 0.1948,
"step": 78000
},
{
"epoch": 3.84,
"learning_rate": 6.558067249167053e-06,
"loss": 0.1764,
"step": 78500
},
{
"epoch": 3.86,
"learning_rate": 6.532078237321261e-06,
"loss": 0.179,
"step": 79000
},
{
"epoch": 3.88,
"learning_rate": 6.50608922547547e-06,
"loss": 0.1906,
"step": 79500
},
{
"epoch": 3.91,
"learning_rate": 6.480100213629677e-06,
"loss": 0.1853,
"step": 80000
},
{
"epoch": 3.93,
"learning_rate": 6.454111201783886e-06,
"loss": 0.1918,
"step": 80500
},
{
"epoch": 3.96,
"learning_rate": 6.428122189938095e-06,
"loss": 0.1769,
"step": 81000
},
{
"epoch": 3.98,
"learning_rate": 6.402133178092304e-06,
"loss": 0.1969,
"step": 81500
},
{
"epoch": 4.0,
"eval_accuracy": 0.9094407035866429,
"eval_averaged_scores": 0.8949438560203089,
"eval_f1": 0.8804470084539749,
"eval_loss": 0.3116997480392456,
"eval_runtime": 36.2351,
"eval_samples_per_second": 1004.137,
"eval_steps_per_second": 62.784,
"step": 81868
},
{
"epoch": 4.01,
"learning_rate": 6.376144166246512e-06,
"loss": 0.1737,
"step": 82000
},
{
"epoch": 4.03,
"learning_rate": 6.35015515440072e-06,
"loss": 0.1467,
"step": 82500
},
{
"epoch": 4.06,
"learning_rate": 6.324166142554928e-06,
"loss": 0.1557,
"step": 83000
},
{
"epoch": 4.08,
"learning_rate": 6.298177130709137e-06,
"loss": 0.1533,
"step": 83500
},
{
"epoch": 4.1,
"learning_rate": 6.272188118863345e-06,
"loss": 0.1573,
"step": 84000
},
{
"epoch": 4.13,
"learning_rate": 6.246199107017553e-06,
"loss": 0.1602,
"step": 84500
},
{
"epoch": 4.15,
"learning_rate": 6.220210095171761e-06,
"loss": 0.1598,
"step": 85000
},
{
"epoch": 4.18,
"learning_rate": 6.194221083325971e-06,
"loss": 0.162,
"step": 85500
},
{
"epoch": 4.2,
"learning_rate": 6.168232071480179e-06,
"loss": 0.1668,
"step": 86000
},
{
"epoch": 4.23,
"learning_rate": 6.142243059634388e-06,
"loss": 0.1673,
"step": 86500
},
{
"epoch": 4.25,
"learning_rate": 6.116254047788595e-06,
"loss": 0.159,
"step": 87000
},
{
"epoch": 4.28,
"learning_rate": 6.090265035942804e-06,
"loss": 0.1615,
"step": 87500
},
{
"epoch": 4.3,
"learning_rate": 6.064276024097012e-06,
"loss": 0.1742,
"step": 88000
},
{
"epoch": 4.32,
"learning_rate": 6.038287012251221e-06,
"loss": 0.1663,
"step": 88500
},
{
"epoch": 4.35,
"learning_rate": 6.0122980004054285e-06,
"loss": 0.1699,
"step": 89000
},
{
"epoch": 4.37,
"learning_rate": 5.986308988559637e-06,
"loss": 0.1625,
"step": 89500
},
{
"epoch": 4.4,
"learning_rate": 5.9603199767138455e-06,
"loss": 0.158,
"step": 90000
},
{
"epoch": 4.42,
"learning_rate": 5.934330964868055e-06,
"loss": 0.1636,
"step": 90500
},
{
"epoch": 4.45,
"learning_rate": 5.908341953022263e-06,
"loss": 0.1568,
"step": 91000
},
{
"epoch": 4.47,
"learning_rate": 5.882352941176471e-06,
"loss": 0.165,
"step": 91500
},
{
"epoch": 4.5,
"learning_rate": 5.856363929330679e-06,
"loss": 0.1687,
"step": 92000
},
{
"epoch": 4.52,
"learning_rate": 5.830374917484888e-06,
"loss": 0.1595,
"step": 92500
},
{
"epoch": 4.54,
"learning_rate": 5.804385905639096e-06,
"loss": 0.1769,
"step": 93000
},
{
"epoch": 4.57,
"learning_rate": 5.778396893793304e-06,
"loss": 0.1567,
"step": 93500
},
{
"epoch": 4.59,
"learning_rate": 5.7524078819475125e-06,
"loss": 0.1724,
"step": 94000
},
{
"epoch": 4.62,
"learning_rate": 5.726418870101721e-06,
"loss": 0.1745,
"step": 94500
},
{
"epoch": 4.64,
"learning_rate": 5.70042985825593e-06,
"loss": 0.167,
"step": 95000
},
{
"epoch": 4.67,
"learning_rate": 5.674440846410139e-06,
"loss": 0.1632,
"step": 95500
},
{
"epoch": 4.69,
"learning_rate": 5.6484518345643465e-06,
"loss": 0.1737,
"step": 96000
},
{
"epoch": 4.71,
"learning_rate": 5.622462822718555e-06,
"loss": 0.1625,
"step": 96500
},
{
"epoch": 4.74,
"learning_rate": 5.5964738108727635e-06,
"loss": 0.1582,
"step": 97000
},
{
"epoch": 4.76,
"learning_rate": 5.570484799026972e-06,
"loss": 0.1691,
"step": 97500
},
{
"epoch": 4.79,
"learning_rate": 5.54449578718118e-06,
"loss": 0.1652,
"step": 98000
},
{
"epoch": 4.81,
"learning_rate": 5.518506775335388e-06,
"loss": 0.1813,
"step": 98500
},
{
"epoch": 4.84,
"learning_rate": 5.4925177634895966e-06,
"loss": 0.1738,
"step": 99000
},
{
"epoch": 4.86,
"learning_rate": 5.466528751643806e-06,
"loss": 0.1717,
"step": 99500
},
{
"epoch": 4.89,
"learning_rate": 5.440539739798014e-06,
"loss": 0.1623,
"step": 100000
},
{
"epoch": 4.91,
"learning_rate": 5.414550727952223e-06,
"loss": 0.1771,
"step": 100500
},
{
"epoch": 4.93,
"learning_rate": 5.3885617161064305e-06,
"loss": 0.157,
"step": 101000
},
{
"epoch": 4.96,
"learning_rate": 5.362572704260639e-06,
"loss": 0.1654,
"step": 101500
},
{
"epoch": 4.98,
"learning_rate": 5.3365836924148475e-06,
"loss": 0.165,
"step": 102000
},
{
"epoch": 5.0,
"eval_accuracy": 0.9078741239521781,
"eval_averaged_scores": 0.893031472907116,
"eval_f1": 0.8781888218620539,
"eval_loss": 0.3768274188041687,
"eval_runtime": 36.2704,
"eval_samples_per_second": 1003.16,
"eval_steps_per_second": 62.723,
"step": 102335
},
{
"epoch": 5.01,
"learning_rate": 5.310594680569056e-06,
"loss": 0.1649,
"step": 102500
},
{
"epoch": 5.03,
"learning_rate": 5.284605668723264e-06,
"loss": 0.1318,
"step": 103000
},
{
"epoch": 5.06,
"learning_rate": 5.258616656877472e-06,
"loss": 0.1436,
"step": 103500
},
{
"epoch": 5.08,
"learning_rate": 5.2326276450316815e-06,
"loss": 0.1509,
"step": 104000
},
{
"epoch": 5.11,
"learning_rate": 5.20663863318589e-06,
"loss": 0.1363,
"step": 104500
},
{
"epoch": 5.13,
"learning_rate": 5.1806496213400985e-06,
"loss": 0.1321,
"step": 105000
},
{
"epoch": 5.15,
"learning_rate": 5.154660609494306e-06,
"loss": 0.1412,
"step": 105500
},
{
"epoch": 5.18,
"learning_rate": 5.128671597648515e-06,
"loss": 0.1347,
"step": 106000
},
{
"epoch": 5.2,
"learning_rate": 5.102682585802723e-06,
"loss": 0.1455,
"step": 106500
},
{
"epoch": 5.23,
"learning_rate": 5.0766935739569316e-06,
"loss": 0.1356,
"step": 107000
},
{
"epoch": 5.25,
"learning_rate": 5.050704562111139e-06,
"loss": 0.1446,
"step": 107500
},
{
"epoch": 5.28,
"learning_rate": 5.024715550265348e-06,
"loss": 0.1403,
"step": 108000
},
{
"epoch": 5.3,
"learning_rate": 4.998726538419556e-06,
"loss": 0.1339,
"step": 108500
},
{
"epoch": 5.33,
"learning_rate": 4.972737526573765e-06,
"loss": 0.1342,
"step": 109000
},
{
"epoch": 5.35,
"learning_rate": 4.946748514727974e-06,
"loss": 0.1281,
"step": 109500
},
{
"epoch": 5.37,
"learning_rate": 4.920759502882182e-06,
"loss": 0.1373,
"step": 110000
},
{
"epoch": 5.4,
"learning_rate": 4.89477049103639e-06,
"loss": 0.1349,
"step": 110500
},
{
"epoch": 5.42,
"learning_rate": 4.868781479190599e-06,
"loss": 0.1572,
"step": 111000
},
{
"epoch": 5.45,
"learning_rate": 4.842792467344807e-06,
"loss": 0.1316,
"step": 111500
},
{
"epoch": 5.47,
"learning_rate": 4.816803455499016e-06,
"loss": 0.1287,
"step": 112000
},
{
"epoch": 5.5,
"learning_rate": 4.790814443653224e-06,
"loss": 0.1416,
"step": 112500
},
{
"epoch": 5.52,
"learning_rate": 4.764825431807433e-06,
"loss": 0.1419,
"step": 113000
},
{
"epoch": 5.55,
"learning_rate": 4.73883641996164e-06,
"loss": 0.1397,
"step": 113500
},
{
"epoch": 5.57,
"learning_rate": 4.712847408115849e-06,
"loss": 0.1466,
"step": 114000
},
{
"epoch": 5.59,
"learning_rate": 4.686858396270057e-06,
"loss": 0.143,
"step": 114500
},
{
"epoch": 5.62,
"learning_rate": 4.660869384424266e-06,
"loss": 0.1428,
"step": 115000
},
{
"epoch": 5.64,
"learning_rate": 4.634880372578474e-06,
"loss": 0.1413,
"step": 115500
},
{
"epoch": 5.67,
"learning_rate": 4.608891360732683e-06,
"loss": 0.1479,
"step": 116000
},
{
"epoch": 5.69,
"learning_rate": 4.582902348886891e-06,
"loss": 0.1454,
"step": 116500
},
{
"epoch": 5.72,
"learning_rate": 4.5569133370411e-06,
"loss": 0.1332,
"step": 117000
},
{
"epoch": 5.74,
"learning_rate": 4.530924325195308e-06,
"loss": 0.1473,
"step": 117500
},
{
"epoch": 5.77,
"learning_rate": 4.504935313349516e-06,
"loss": 0.1353,
"step": 118000
},
{
"epoch": 5.79,
"learning_rate": 4.478946301503724e-06,
"loss": 0.1557,
"step": 118500
},
{
"epoch": 5.81,
"learning_rate": 4.452957289657933e-06,
"loss": 0.1452,
"step": 119000
},
{
"epoch": 5.84,
"learning_rate": 4.426968277812141e-06,
"loss": 0.1469,
"step": 119500
},
{
"epoch": 5.86,
"learning_rate": 4.40097926596635e-06,
"loss": 0.1394,
"step": 120000
},
{
"epoch": 5.89,
"learning_rate": 4.374990254120558e-06,
"loss": 0.1525,
"step": 120500
},
{
"epoch": 5.91,
"learning_rate": 4.349001242274767e-06,
"loss": 0.1448,
"step": 121000
},
{
"epoch": 5.94,
"learning_rate": 4.323012230428975e-06,
"loss": 0.146,
"step": 121500
},
{
"epoch": 5.96,
"learning_rate": 4.297023218583184e-06,
"loss": 0.1365,
"step": 122000
},
{
"epoch": 5.99,
"learning_rate": 4.271034206737391e-06,
"loss": 0.1467,
"step": 122500
},
{
"epoch": 6.0,
"eval_accuracy": 0.9117768311117218,
"eval_averaged_scores": 0.8970713531108301,
"eval_f1": 0.8823658751099384,
"eval_loss": 0.44876691699028015,
"eval_runtime": 36.3498,
"eval_samples_per_second": 1000.969,
"eval_steps_per_second": 62.586,
"step": 122802
},
{
"epoch": 6.01,
"learning_rate": 4.2450451948916e-06,
"loss": 0.1278,
"step": 123000
},
{
"epoch": 6.03,
"learning_rate": 4.219056183045809e-06,
"loss": 0.1097,
"step": 123500
},
{
"epoch": 6.06,
"learning_rate": 4.193067171200017e-06,
"loss": 0.118,
"step": 124000
},
{
"epoch": 6.08,
"learning_rate": 4.167078159354225e-06,
"loss": 0.1108,
"step": 124500
},
{
"epoch": 6.11,
"learning_rate": 4.141089147508434e-06,
"loss": 0.1124,
"step": 125000
},
{
"epoch": 6.13,
"learning_rate": 4.115100135662642e-06,
"loss": 0.1161,
"step": 125500
},
{
"epoch": 6.16,
"learning_rate": 4.089111123816851e-06,
"loss": 0.1159,
"step": 126000
},
{
"epoch": 6.18,
"learning_rate": 4.063122111971059e-06,
"loss": 0.1152,
"step": 126500
},
{
"epoch": 6.21,
"learning_rate": 4.037133100125267e-06,
"loss": 0.1125,
"step": 127000
},
{
"epoch": 6.23,
"learning_rate": 4.011144088279475e-06,
"loss": 0.1126,
"step": 127500
},
{
"epoch": 6.25,
"learning_rate": 3.985155076433685e-06,
"loss": 0.1233,
"step": 128000
},
{
"epoch": 6.28,
"learning_rate": 3.959166064587892e-06,
"loss": 0.1183,
"step": 128500
},
{
"epoch": 6.3,
"learning_rate": 3.933177052742101e-06,
"loss": 0.1207,
"step": 129000
},
{
"epoch": 6.33,
"learning_rate": 3.907188040896309e-06,
"loss": 0.1114,
"step": 129500
},
{
"epoch": 6.35,
"learning_rate": 3.881199029050518e-06,
"loss": 0.1164,
"step": 130000
},
{
"epoch": 6.38,
"learning_rate": 3.855210017204726e-06,
"loss": 0.1179,
"step": 130500
},
{
"epoch": 6.4,
"learning_rate": 3.829221005358935e-06,
"loss": 0.1115,
"step": 131000
},
{
"epoch": 6.42,
"learning_rate": 3.803231993513143e-06,
"loss": 0.1124,
"step": 131500
},
{
"epoch": 6.45,
"learning_rate": 3.777242981667351e-06,
"loss": 0.1228,
"step": 132000
},
{
"epoch": 6.47,
"learning_rate": 3.75125396982156e-06,
"loss": 0.1314,
"step": 132500
},
{
"epoch": 6.5,
"learning_rate": 3.7252649579757684e-06,
"loss": 0.1076,
"step": 133000
},
{
"epoch": 6.52,
"learning_rate": 3.6992759461299764e-06,
"loss": 0.1189,
"step": 133500
},
{
"epoch": 6.55,
"learning_rate": 3.673286934284185e-06,
"loss": 0.1234,
"step": 134000
},
{
"epoch": 6.57,
"learning_rate": 3.647297922438393e-06,
"loss": 0.1199,
"step": 134500
},
{
"epoch": 6.6,
"learning_rate": 3.621308910592602e-06,
"loss": 0.1295,
"step": 135000
},
{
"epoch": 6.62,
"learning_rate": 3.5953198987468104e-06,
"loss": 0.1282,
"step": 135500
},
{
"epoch": 6.64,
"learning_rate": 3.5693308869010185e-06,
"loss": 0.124,
"step": 136000
},
{
"epoch": 6.67,
"learning_rate": 3.543341875055227e-06,
"loss": 0.1292,
"step": 136500
},
{
"epoch": 6.69,
"learning_rate": 3.5173528632094355e-06,
"loss": 0.112,
"step": 137000
},
{
"epoch": 6.72,
"learning_rate": 3.491363851363644e-06,
"loss": 0.1225,
"step": 137500
},
{
"epoch": 6.74,
"learning_rate": 3.465374839517852e-06,
"loss": 0.1262,
"step": 138000
},
{
"epoch": 6.77,
"learning_rate": 3.4393858276720605e-06,
"loss": 0.1174,
"step": 138500
},
{
"epoch": 6.79,
"learning_rate": 3.4133968158262686e-06,
"loss": 0.1219,
"step": 139000
},
{
"epoch": 6.82,
"learning_rate": 3.3874078039804775e-06,
"loss": 0.1172,
"step": 139500
},
{
"epoch": 6.84,
"learning_rate": 3.361418792134686e-06,
"loss": 0.126,
"step": 140000
},
{
"epoch": 6.86,
"learning_rate": 3.335429780288894e-06,
"loss": 0.1206,
"step": 140500
},
{
"epoch": 6.89,
"learning_rate": 3.3094407684431025e-06,
"loss": 0.1216,
"step": 141000
},
{
"epoch": 6.91,
"learning_rate": 3.283451756597311e-06,
"loss": 0.1215,
"step": 141500
},
{
"epoch": 6.94,
"learning_rate": 3.2574627447515195e-06,
"loss": 0.12,
"step": 142000
},
{
"epoch": 6.96,
"learning_rate": 3.2314737329057276e-06,
"loss": 0.1198,
"step": 142500
},
{
"epoch": 6.99,
"learning_rate": 3.205484721059936e-06,
"loss": 0.1093,
"step": 143000
},
{
"epoch": 7.0,
"eval_accuracy": 0.9125738628555724,
"eval_averaged_scores": 0.8981269870097512,
"eval_f1": 0.8836801111639301,
"eval_loss": 0.48590707778930664,
"eval_runtime": 36.5067,
"eval_samples_per_second": 996.667,
"eval_steps_per_second": 62.317,
"step": 143269
},
{
"epoch": 7.01,
"learning_rate": 3.179495709214144e-06,
"loss": 0.1072,
"step": 143500
},
{
"epoch": 7.04,
"learning_rate": 3.153506697368353e-06,
"loss": 0.0934,
"step": 144000
},
{
"epoch": 7.06,
"learning_rate": 3.1275176855225615e-06,
"loss": 0.0963,
"step": 144500
},
{
"epoch": 7.08,
"learning_rate": 3.1015286736767696e-06,
"loss": 0.0962,
"step": 145000
},
{
"epoch": 7.11,
"learning_rate": 3.075539661830978e-06,
"loss": 0.0964,
"step": 145500
},
{
"epoch": 7.13,
"learning_rate": 3.049550649985186e-06,
"loss": 0.0983,
"step": 146000
},
{
"epoch": 7.16,
"learning_rate": 3.023561638139395e-06,
"loss": 0.0942,
"step": 146500
},
{
"epoch": 7.18,
"learning_rate": 2.9975726262936036e-06,
"loss": 0.1016,
"step": 147000
},
{
"epoch": 7.21,
"learning_rate": 2.9715836144478116e-06,
"loss": 0.0806,
"step": 147500
},
{
"epoch": 7.23,
"learning_rate": 2.94559460260202e-06,
"loss": 0.1037,
"step": 148000
},
{
"epoch": 7.26,
"learning_rate": 2.9196055907562286e-06,
"loss": 0.1013,
"step": 148500
},
{
"epoch": 7.28,
"learning_rate": 2.893616578910437e-06,
"loss": 0.0929,
"step": 149000
},
{
"epoch": 7.3,
"learning_rate": 2.867627567064645e-06,
"loss": 0.1034,
"step": 149500
},
{
"epoch": 7.33,
"learning_rate": 2.8416385552188536e-06,
"loss": 0.0955,
"step": 150000
},
{
"epoch": 7.35,
"learning_rate": 2.8156495433730617e-06,
"loss": 0.0857,
"step": 150500
},
{
"epoch": 7.38,
"learning_rate": 2.7896605315272706e-06,
"loss": 0.106,
"step": 151000
},
{
"epoch": 7.4,
"learning_rate": 2.763671519681479e-06,
"loss": 0.0914,
"step": 151500
},
{
"epoch": 7.43,
"learning_rate": 2.737682507835687e-06,
"loss": 0.0979,
"step": 152000
},
{
"epoch": 7.45,
"learning_rate": 2.7116934959898957e-06,
"loss": 0.0986,
"step": 152500
},
{
"epoch": 7.48,
"learning_rate": 2.685704484144104e-06,
"loss": 0.1024,
"step": 153000
},
{
"epoch": 7.5,
"learning_rate": 2.6597154722983127e-06,
"loss": 0.0968,
"step": 153500
},
{
"epoch": 7.52,
"learning_rate": 2.6337264604525207e-06,
"loss": 0.0964,
"step": 154000
},
{
"epoch": 7.55,
"learning_rate": 2.607737448606729e-06,
"loss": 0.1112,
"step": 154500
},
{
"epoch": 7.57,
"learning_rate": 2.5817484367609373e-06,
"loss": 0.0961,
"step": 155000
},
{
"epoch": 7.6,
"learning_rate": 2.555759424915146e-06,
"loss": 0.0994,
"step": 155500
},
{
"epoch": 7.62,
"learning_rate": 2.5297704130693547e-06,
"loss": 0.0928,
"step": 156000
},
{
"epoch": 7.65,
"learning_rate": 2.5037814012235627e-06,
"loss": 0.0964,
"step": 156500
},
{
"epoch": 7.67,
"learning_rate": 2.4777923893777712e-06,
"loss": 0.0817,
"step": 157000
},
{
"epoch": 7.7,
"learning_rate": 2.4518033775319797e-06,
"loss": 0.1125,
"step": 157500
},
{
"epoch": 7.72,
"learning_rate": 2.425814365686188e-06,
"loss": 0.0903,
"step": 158000
},
{
"epoch": 7.74,
"learning_rate": 2.3998253538403967e-06,
"loss": 0.0947,
"step": 158500
},
{
"epoch": 7.77,
"learning_rate": 2.3738363419946048e-06,
"loss": 0.0947,
"step": 159000
},
{
"epoch": 7.79,
"learning_rate": 2.3478473301488133e-06,
"loss": 0.0958,
"step": 159500
},
{
"epoch": 7.82,
"learning_rate": 2.3218583183030217e-06,
"loss": 0.1071,
"step": 160000
},
{
"epoch": 7.84,
"learning_rate": 2.2958693064572302e-06,
"loss": 0.0878,
"step": 160500
},
{
"epoch": 7.87,
"learning_rate": 2.2698802946114383e-06,
"loss": 0.0985,
"step": 161000
},
{
"epoch": 7.89,
"learning_rate": 2.243891282765647e-06,
"loss": 0.0942,
"step": 161500
},
{
"epoch": 7.92,
"learning_rate": 2.2179022709198553e-06,
"loss": 0.1043,
"step": 162000
},
{
"epoch": 7.94,
"learning_rate": 2.1919132590740634e-06,
"loss": 0.0908,
"step": 162500
},
{
"epoch": 7.96,
"learning_rate": 2.1659242472282723e-06,
"loss": 0.0969,
"step": 163000
},
{
"epoch": 7.99,
"learning_rate": 2.1399352353824803e-06,
"loss": 0.1005,
"step": 163500
},
{
"epoch": 8.0,
"eval_accuracy": 0.9120241857908479,
"eval_averaged_scores": 0.897542067688103,
"eval_f1": 0.8830599495853579,
"eval_loss": 0.543989360332489,
"eval_runtime": 36.3255,
"eval_samples_per_second": 1001.637,
"eval_steps_per_second": 62.628,
"step": 163736
},
{
"epoch": 8.01,
"learning_rate": 2.113946223536689e-06,
"loss": 0.0745,
"step": 164000
},
{
"epoch": 8.04,
"learning_rate": 2.0879572116908973e-06,
"loss": 0.0656,
"step": 164500
},
{
"epoch": 8.06,
"learning_rate": 2.061968199845106e-06,
"loss": 0.0775,
"step": 165000
},
{
"epoch": 8.09,
"learning_rate": 2.035979187999314e-06,
"loss": 0.0877,
"step": 165500
},
{
"epoch": 8.11,
"learning_rate": 2.0099901761535224e-06,
"loss": 0.0785,
"step": 166000
},
{
"epoch": 8.14,
"learning_rate": 1.984001164307731e-06,
"loss": 0.07,
"step": 166500
},
{
"epoch": 8.16,
"learning_rate": 1.9580121524619393e-06,
"loss": 0.0866,
"step": 167000
},
{
"epoch": 8.18,
"learning_rate": 1.932023140616148e-06,
"loss": 0.0714,
"step": 167500
},
{
"epoch": 8.21,
"learning_rate": 1.9060341287703559e-06,
"loss": 0.0878,
"step": 168000
},
{
"epoch": 8.23,
"learning_rate": 1.8800451169245646e-06,
"loss": 0.083,
"step": 168500
},
{
"epoch": 8.26,
"learning_rate": 1.8540561050787729e-06,
"loss": 0.081,
"step": 169000
},
{
"epoch": 8.28,
"learning_rate": 1.8280670932329814e-06,
"loss": 0.0726,
"step": 169500
},
{
"epoch": 8.31,
"learning_rate": 1.8020780813871896e-06,
"loss": 0.0764,
"step": 170000
},
{
"epoch": 8.33,
"learning_rate": 1.776089069541398e-06,
"loss": 0.0739,
"step": 170500
},
{
"epoch": 8.35,
"learning_rate": 1.7501000576956064e-06,
"loss": 0.0881,
"step": 171000
},
{
"epoch": 8.38,
"learning_rate": 1.7241110458498147e-06,
"loss": 0.0763,
"step": 171500
},
{
"epoch": 8.4,
"learning_rate": 1.6981220340040234e-06,
"loss": 0.0754,
"step": 172000
},
{
"epoch": 8.43,
"learning_rate": 1.6721330221582317e-06,
"loss": 0.0842,
"step": 172500
},
{
"epoch": 8.45,
"learning_rate": 1.6461440103124402e-06,
"loss": 0.0804,
"step": 173000
},
{
"epoch": 8.48,
"learning_rate": 1.6201549984666484e-06,
"loss": 0.0871,
"step": 173500
},
{
"epoch": 8.5,
"learning_rate": 1.5941659866208567e-06,
"loss": 0.0784,
"step": 174000
},
{
"epoch": 8.53,
"learning_rate": 1.5681769747750652e-06,
"loss": 0.0769,
"step": 174500
},
{
"epoch": 8.55,
"learning_rate": 1.5421879629292735e-06,
"loss": 0.0786,
"step": 175000
},
{
"epoch": 8.57,
"learning_rate": 1.5161989510834822e-06,
"loss": 0.0787,
"step": 175500
},
{
"epoch": 8.6,
"learning_rate": 1.4902099392376905e-06,
"loss": 0.0735,
"step": 176000
},
{
"epoch": 8.62,
"learning_rate": 1.464220927391899e-06,
"loss": 0.0853,
"step": 176500
},
{
"epoch": 8.65,
"learning_rate": 1.4382319155461072e-06,
"loss": 0.0775,
"step": 177000
},
{
"epoch": 8.67,
"learning_rate": 1.4122429037003157e-06,
"loss": 0.0794,
"step": 177500
},
{
"epoch": 8.7,
"learning_rate": 1.386253891854524e-06,
"loss": 0.0814,
"step": 178000
},
{
"epoch": 8.72,
"learning_rate": 1.3602648800087323e-06,
"loss": 0.0792,
"step": 178500
},
{
"epoch": 8.75,
"learning_rate": 1.3342758681629408e-06,
"loss": 0.0857,
"step": 179000
},
{
"epoch": 8.77,
"learning_rate": 1.308286856317149e-06,
"loss": 0.086,
"step": 179500
},
{
"epoch": 8.79,
"learning_rate": 1.2822978444713577e-06,
"loss": 0.0811,
"step": 180000
},
{
"epoch": 8.82,
"learning_rate": 1.256308832625566e-06,
"loss": 0.077,
"step": 180500
},
{
"epoch": 8.84,
"learning_rate": 1.2303198207797743e-06,
"loss": 0.0813,
"step": 181000
},
{
"epoch": 8.87,
"learning_rate": 1.2043308089339828e-06,
"loss": 0.0726,
"step": 181500
},
{
"epoch": 8.89,
"learning_rate": 1.1783417970881913e-06,
"loss": 0.0813,
"step": 182000
},
{
"epoch": 8.92,
"learning_rate": 1.1523527852423996e-06,
"loss": 0.081,
"step": 182500
},
{
"epoch": 8.94,
"learning_rate": 1.126363773396608e-06,
"loss": 0.0774,
"step": 183000
},
{
"epoch": 8.97,
"learning_rate": 1.1003747615508165e-06,
"loss": 0.0806,
"step": 183500
},
{
"epoch": 8.99,
"learning_rate": 1.0743857497050248e-06,
"loss": 0.0671,
"step": 184000
},
{
"epoch": 9.0,
"eval_accuracy": 0.9127112821217535,
"eval_averaged_scores": 0.8981017892633713,
"eval_f1": 0.883492296404989,
"eval_loss": 0.5674276351928711,
"eval_runtime": 36.287,
"eval_samples_per_second": 1002.701,
"eval_steps_per_second": 62.695,
"step": 184203
},
{
"epoch": 9.01,
"learning_rate": 1.048396737859233e-06,
"loss": 0.073,
"step": 184500
},
{
"epoch": 9.04,
"learning_rate": 1.0224077260134416e-06,
"loss": 0.0623,
"step": 185000
},
{
"epoch": 9.06,
"learning_rate": 9.9641871416765e-07,
"loss": 0.0562,
"step": 185500
},
{
"epoch": 9.09,
"learning_rate": 9.704297023218584e-07,
"loss": 0.062,
"step": 186000
},
{
"epoch": 9.11,
"learning_rate": 9.444406904760668e-07,
"loss": 0.0753,
"step": 186500
},
{
"epoch": 9.14,
"learning_rate": 9.184516786302752e-07,
"loss": 0.0624,
"step": 187000
},
{
"epoch": 9.16,
"learning_rate": 8.924626667844836e-07,
"loss": 0.0593,
"step": 187500
},
{
"epoch": 9.19,
"learning_rate": 8.664736549386919e-07,
"loss": 0.0758,
"step": 188000
},
{
"epoch": 9.21,
"learning_rate": 8.404846430929004e-07,
"loss": 0.0766,
"step": 188500
},
{
"epoch": 9.23,
"learning_rate": 8.144956312471088e-07,
"loss": 0.0681,
"step": 189000
},
{
"epoch": 9.26,
"learning_rate": 7.885066194013171e-07,
"loss": 0.0778,
"step": 189500
},
{
"epoch": 9.28,
"learning_rate": 7.625176075555256e-07,
"loss": 0.0596,
"step": 190000
},
{
"epoch": 9.31,
"learning_rate": 7.36528595709734e-07,
"loss": 0.0702,
"step": 190500
},
{
"epoch": 9.33,
"learning_rate": 7.105395838639424e-07,
"loss": 0.0658,
"step": 191000
},
{
"epoch": 9.36,
"learning_rate": 6.845505720181508e-07,
"loss": 0.0729,
"step": 191500
},
{
"epoch": 9.38,
"learning_rate": 6.585615601723591e-07,
"loss": 0.0656,
"step": 192000
},
{
"epoch": 9.41,
"learning_rate": 6.325725483265676e-07,
"loss": 0.0592,
"step": 192500
},
{
"epoch": 9.43,
"learning_rate": 6.065835364807759e-07,
"loss": 0.0653,
"step": 193000
},
{
"epoch": 9.45,
"learning_rate": 5.805945246349843e-07,
"loss": 0.0637,
"step": 193500
},
{
"epoch": 9.48,
"learning_rate": 5.546055127891928e-07,
"loss": 0.0597,
"step": 194000
},
{
"epoch": 9.5,
"learning_rate": 5.286165009434012e-07,
"loss": 0.074,
"step": 194500
},
{
"epoch": 9.53,
"learning_rate": 5.026274890976096e-07,
"loss": 0.0531,
"step": 195000
},
{
"epoch": 9.55,
"learning_rate": 4.7663847725181796e-07,
"loss": 0.0644,
"step": 195500
},
{
"epoch": 9.58,
"learning_rate": 4.5064946540602635e-07,
"loss": 0.0585,
"step": 196000
},
{
"epoch": 9.6,
"learning_rate": 4.246604535602348e-07,
"loss": 0.0624,
"step": 196500
},
{
"epoch": 9.63,
"learning_rate": 3.986714417144431e-07,
"loss": 0.0615,
"step": 197000
},
{
"epoch": 9.65,
"learning_rate": 3.7268242986865155e-07,
"loss": 0.07,
"step": 197500
},
{
"epoch": 9.67,
"learning_rate": 3.4669341802286e-07,
"loss": 0.0612,
"step": 198000
},
{
"epoch": 9.7,
"learning_rate": 3.207044061770684e-07,
"loss": 0.0703,
"step": 198500
},
{
"epoch": 9.72,
"learning_rate": 2.9471539433127676e-07,
"loss": 0.0748,
"step": 199000
},
{
"epoch": 9.75,
"learning_rate": 2.6872638248548514e-07,
"loss": 0.0602,
"step": 199500
},
{
"epoch": 9.77,
"learning_rate": 2.427373706396936e-07,
"loss": 0.063,
"step": 200000
},
{
"epoch": 9.8,
"learning_rate": 2.1674835879390194e-07,
"loss": 0.0722,
"step": 200500
},
{
"epoch": 9.82,
"learning_rate": 1.9075934694811035e-07,
"loss": 0.0528,
"step": 201000
},
{
"epoch": 9.85,
"learning_rate": 1.6477033510231873e-07,
"loss": 0.0783,
"step": 201500
},
{
"epoch": 9.87,
"learning_rate": 1.3878132325652717e-07,
"loss": 0.0623,
"step": 202000
},
{
"epoch": 9.89,
"learning_rate": 1.1279231141073555e-07,
"loss": 0.0745,
"step": 202500
},
{
"epoch": 9.92,
"learning_rate": 8.680329956494395e-08,
"loss": 0.0507,
"step": 203000
},
{
"epoch": 9.94,
"learning_rate": 6.081428771915235e-08,
"loss": 0.0633,
"step": 203500
},
{
"epoch": 9.97,
"learning_rate": 3.4825275873360744e-08,
"loss": 0.0659,
"step": 204000
},
{
"epoch": 9.99,
"learning_rate": 8.836264027569144e-09,
"loss": 0.0669,
"step": 204500
},
{
"epoch": 10.0,
"eval_accuracy": 0.913398378452659,
"eval_averaged_scores": 0.8990160346845362,
"eval_f1": 0.8846336909164134,
"eval_loss": 0.611711859703064,
"eval_runtime": 36.3229,
"eval_samples_per_second": 1001.71,
"eval_steps_per_second": 62.633,
"step": 204670
},
{
"epoch": 10.0,
"step": 204670,
"total_flos": 1.0022032836134272e+17,
"train_loss": 0.16490516577327513,
"train_runtime": 10899.0474,
"train_samples_per_second": 300.449,
"train_steps_per_second": 18.779
}
],
"logging_steps": 500,
"max_steps": 204670,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.0022032836134272e+17,
"trial_name": null,
"trial_params": null
}