{
"best_metric": 0.6404494377165132,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/ner-qa/run-442/checkpoints/checkpoint-44000",
"epoch": 275.0,
"global_step": 44000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"eval_loss": 0.05795547366142273,
"eval_micro_f1": 0.0,
"eval_runtime": 16.5292,
"eval_samples_per_second": 366.26,
"step": 80
},
{
"epoch": 1.0,
"eval_loss": 0.04793815314769745,
"eval_micro_f1": 0.0,
"eval_runtime": 17.2119,
"eval_samples_per_second": 351.734,
"step": 160
},
{
"epoch": 1.5,
"eval_loss": 0.039343029260635376,
"eval_micro_f1": 0.2935665204250389,
"eval_runtime": 17.1479,
"eval_samples_per_second": 353.045,
"step": 240
},
{
"epoch": 2.0,
"eval_loss": 0.037178002297878265,
"eval_micro_f1": 0.39274141233513093,
"eval_runtime": 17.4422,
"eval_samples_per_second": 347.089,
"step": 320
},
{
"epoch": 2.5,
"eval_loss": 0.037717554718256,
"eval_micro_f1": 0.459636363159023,
"eval_runtime": 18.3194,
"eval_samples_per_second": 330.469,
"step": 400
},
{
"epoch": 3.0,
"eval_loss": 0.035402264446020126,
"eval_micro_f1": 0.5083032486182091,
"eval_runtime": 17.0419,
"eval_samples_per_second": 355.241,
"step": 480
},
{
"epoch": 3.12,
"learning_rate": 9.895833333333334e-06,
"loss": 0.0329,
"step": 500
},
{
"epoch": 3.5,
"eval_loss": 0.03709366172552109,
"eval_micro_f1": 0.5241286858336526,
"eval_runtime": 19.592,
"eval_samples_per_second": 309.003,
"step": 560
},
{
"epoch": 4.0,
"eval_loss": 0.03474647179245949,
"eval_micro_f1": 0.5232722139017647,
"eval_runtime": 20.0754,
"eval_samples_per_second": 301.563,
"step": 640
},
{
"epoch": 4.5,
"eval_loss": 0.0367262028157711,
"eval_micro_f1": 0.5109922751975721,
"eval_runtime": 20.8465,
"eval_samples_per_second": 290.409,
"step": 720
},
{
"epoch": 5.0,
"eval_loss": 0.03650993853807449,
"eval_micro_f1": 0.5546975541997236,
"eval_runtime": 16.8574,
"eval_samples_per_second": 359.131,
"step": 800
},
{
"epoch": 5.5,
"eval_loss": 0.03861010819673538,
"eval_micro_f1": 0.5305591672534306,
"eval_runtime": 16.9753,
"eval_samples_per_second": 356.635,
"step": 880
},
{
"epoch": 6.0,
"eval_loss": 0.03903694078326225,
"eval_micro_f1": 0.5522682440801386,
"eval_runtime": 15.6078,
"eval_samples_per_second": 387.883,
"step": 960
},
{
"epoch": 6.25,
"learning_rate": 9.791666666666666e-06,
"loss": 0.0071,
"step": 1000
},
{
"epoch": 6.5,
"eval_loss": 0.04015379399061203,
"eval_micro_f1": 0.5710594310270183,
"eval_runtime": 17.0335,
"eval_samples_per_second": 355.416,
"step": 1040
},
{
"epoch": 7.0,
"eval_loss": 0.039332009851932526,
"eval_micro_f1": 0.5617685300622326,
"eval_runtime": 20.0284,
"eval_samples_per_second": 302.271,
"step": 1120
},
{
"epoch": 7.5,
"eval_loss": 0.043486420065164566,
"eval_micro_f1": 0.5484508894188013,
"eval_runtime": 16.9137,
"eval_samples_per_second": 357.935,
"step": 1200
},
{
"epoch": 8.0,
"eval_loss": 0.04180828854441643,
"eval_micro_f1": 0.5737483080328718,
"eval_runtime": 16.5916,
"eval_samples_per_second": 364.883,
"step": 1280
},
{
"epoch": 8.5,
"eval_loss": 0.04581056535243988,
"eval_micro_f1": 0.5737373732445296,
"eval_runtime": 16.6683,
"eval_samples_per_second": 363.204,
"step": 1360
},
{
"epoch": 9.0,
"eval_loss": 0.04363492503762245,
"eval_micro_f1": 0.5805194800224001,
"eval_runtime": 17.3207,
"eval_samples_per_second": 349.524,
"step": 1440
},
{
"epoch": 9.38,
"learning_rate": 9.6875e-06,
"loss": 0.0033,
"step": 1500
},
{
"epoch": 9.5,
"eval_loss": 0.04809512197971344,
"eval_micro_f1": 0.5765517236488561,
"eval_runtime": 16.8607,
"eval_samples_per_second": 359.06,
"step": 1520
},
{
"epoch": 10.0,
"eval_loss": 0.04443039372563362,
"eval_micro_f1": 0.5890957441863064,
"eval_runtime": 17.2876,
"eval_samples_per_second": 350.194,
"step": 1600
},
{
"epoch": 10.5,
"eval_loss": 0.045258477330207825,
"eval_micro_f1": 0.5751295331814478,
"eval_runtime": 17.2906,
"eval_samples_per_second": 350.132,
"step": 1680
},
{
"epoch": 11.0,
"eval_loss": 0.048896025866270065,
"eval_micro_f1": 0.5844686643589955,
"eval_runtime": 17.3757,
"eval_samples_per_second": 348.417,
"step": 1760
},
{
"epoch": 11.5,
"eval_loss": 0.04590630158782005,
"eval_micro_f1": 0.5901218724973798,
"eval_runtime": 17.5945,
"eval_samples_per_second": 344.085,
"step": 1840
},
{
"epoch": 12.0,
"eval_loss": 0.04861527681350708,
"eval_micro_f1": 0.5997322618891595,
"eval_runtime": 17.3255,
"eval_samples_per_second": 349.427,
"step": 1920
},
{
"epoch": 12.5,
"learning_rate": 9.583333333333335e-06,
"loss": 0.0018,
"step": 2000
},
{
"epoch": 12.5,
"eval_loss": 0.04979348182678223,
"eval_micro_f1": 0.5925423723894714,
"eval_runtime": 17.2052,
"eval_samples_per_second": 351.869,
"step": 2000
},
{
"epoch": 13.0,
"eval_loss": 0.04861849918961525,
"eval_micro_f1": 0.5977468517250549,
"eval_runtime": 17.5478,
"eval_samples_per_second": 345.001,
"step": 2080
},
{
"epoch": 13.5,
"eval_loss": 0.0501537099480629,
"eval_micro_f1": 0.6004056790208869,
"eval_runtime": 16.8069,
"eval_samples_per_second": 360.208,
"step": 2160
},
{
"epoch": 14.0,
"eval_loss": 0.0499655157327652,
"eval_micro_f1": 0.5963975979047966,
"eval_runtime": 18.3258,
"eval_samples_per_second": 330.354,
"step": 2240
},
{
"epoch": 14.5,
"eval_loss": 0.052439846098423004,
"eval_micro_f1": 0.5867937367449643,
"eval_runtime": 16.6104,
"eval_samples_per_second": 364.471,
"step": 2320
},
{
"epoch": 15.0,
"eval_loss": 0.04969755932688713,
"eval_micro_f1": 0.5921325046870086,
"eval_runtime": 17.1265,
"eval_samples_per_second": 353.488,
"step": 2400
},
{
"epoch": 15.5,
"eval_loss": 0.05039890855550766,
"eval_micro_f1": 0.588940705701574,
"eval_runtime": 17.3467,
"eval_samples_per_second": 349.0,
"step": 2480
},
{
"epoch": 15.62,
"learning_rate": 9.479166666666667e-06,
"loss": 0.0012,
"step": 2500
},
{
"epoch": 16.0,
"eval_loss": 0.04942774027585983,
"eval_micro_f1": 0.589918255639642,
"eval_runtime": 17.192,
"eval_samples_per_second": 352.141,
"step": 2560
},
{
"epoch": 16.5,
"eval_loss": 0.05067664012312889,
"eval_micro_f1": 0.5922459888109415,
"eval_runtime": 17.1765,
"eval_samples_per_second": 352.458,
"step": 2640
},
{
"epoch": 17.0,
"eval_loss": 0.050292644649744034,
"eval_micro_f1": 0.6021361810813759,
"eval_runtime": 16.3708,
"eval_samples_per_second": 369.804,
"step": 2720
},
{
"epoch": 17.5,
"eval_loss": 0.05239620804786682,
"eval_micro_f1": 0.6060606055712496,
"eval_runtime": 17.1594,
"eval_samples_per_second": 352.81,
"step": 2800
},
{
"epoch": 18.0,
"eval_loss": 0.05083390697836876,
"eval_micro_f1": 0.6115155521190299,
"eval_runtime": 17.2923,
"eval_samples_per_second": 350.097,
"step": 2880
},
{
"epoch": 18.5,
"eval_loss": 0.05318547412753105,
"eval_micro_f1": 0.5975935823938219,
"eval_runtime": 16.773,
"eval_samples_per_second": 360.937,
"step": 2960
},
{
"epoch": 18.75,
"learning_rate": 9.375000000000001e-06,
"loss": 0.0009,
"step": 3000
},
{
"epoch": 19.0,
"eval_loss": 0.05370296165347099,
"eval_micro_f1": 0.603412968792435,
"eval_runtime": 17.1936,
"eval_samples_per_second": 352.108,
"step": 3040
},
{
"epoch": 19.5,
"eval_loss": 0.05372468754649162,
"eval_micro_f1": 0.6097883592931521,
"eval_runtime": 16.7386,
"eval_samples_per_second": 361.678,
"step": 3120
},
{
"epoch": 20.0,
"eval_loss": 0.05507222190499306,
"eval_micro_f1": 0.5993079579890183,
"eval_runtime": 17.1956,
"eval_samples_per_second": 352.066,
"step": 3200
},
{
"epoch": 20.5,
"eval_loss": 0.052869588136672974,
"eval_micro_f1": 0.6108179414569952,
"eval_runtime": 17.0832,
"eval_samples_per_second": 354.382,
"step": 3280
},
{
"epoch": 21.0,
"eval_loss": 0.053149886429309845,
"eval_micro_f1": 0.6074766350199536,
"eval_runtime": 16.2577,
"eval_samples_per_second": 372.378,
"step": 3360
},
{
"epoch": 21.5,
"eval_loss": 0.0545358806848526,
"eval_micro_f1": 0.6045883935694806,
"eval_runtime": 16.7079,
"eval_samples_per_second": 362.344,
"step": 3440
},
{
"epoch": 21.88,
"learning_rate": 9.270833333333334e-06,
"loss": 0.0007,
"step": 3500
},
{
"epoch": 22.0,
"eval_loss": 0.05478763207793236,
"eval_micro_f1": 0.6021080363949982,
"eval_runtime": 17.3975,
"eval_samples_per_second": 347.981,
"step": 3520
},
{
"epoch": 22.5,
"eval_loss": 0.05779687687754631,
"eval_micro_f1": 0.5924426445816428,
"eval_runtime": 21.5354,
"eval_samples_per_second": 281.119,
"step": 3600
},
{
"epoch": 23.0,
"eval_loss": 0.05761467665433884,
"eval_micro_f1": 0.5973482200294736,
"eval_runtime": 17.2239,
"eval_samples_per_second": 351.489,
"step": 3680
},
{
"epoch": 23.5,
"eval_loss": 0.057251278311014175,
"eval_micro_f1": 0.605691056418565,
"eval_runtime": 17.1526,
"eval_samples_per_second": 352.95,
"step": 3760
},
{
"epoch": 24.0,
"eval_loss": 0.05608842521905899,
"eval_micro_f1": 0.6064782903446707,
"eval_runtime": 17.1138,
"eval_samples_per_second": 353.749,
"step": 3840
},
{
"epoch": 24.5,
"eval_loss": 0.05778781324625015,
"eval_micro_f1": 0.6029411759767026,
"eval_runtime": 18.1557,
"eval_samples_per_second": 333.45,
"step": 3920
},
{
"epoch": 25.0,
"learning_rate": 9.166666666666666e-06,
"loss": 0.0005,
"step": 4000
},
{
"epoch": 25.0,
"eval_loss": 0.05877626687288284,
"eval_micro_f1": 0.6109589036192945,
"eval_runtime": 17.7363,
"eval_samples_per_second": 341.333,
"step": 4000
},
{
"epoch": 25.5,
"eval_loss": 0.06109144166111946,
"eval_micro_f1": 0.6111869026468288,
"eval_runtime": 20.0785,
"eval_samples_per_second": 301.517,
"step": 4080
},
{
"epoch": 26.0,
"eval_loss": 0.059862054884433746,
"eval_micro_f1": 0.6044260022776294,
"eval_runtime": 19.0692,
"eval_samples_per_second": 317.475,
"step": 4160
},
{
"epoch": 26.5,
"eval_loss": 0.06034718453884125,
"eval_micro_f1": 0.6080536907818116,
"eval_runtime": 18.9792,
"eval_samples_per_second": 318.981,
"step": 4240
},
{
"epoch": 27.0,
"eval_loss": 0.059672508388757706,
"eval_micro_f1": 0.5978835973884059,
"eval_runtime": 20.6901,
"eval_samples_per_second": 292.604,
"step": 4320
},
{
"epoch": 27.5,
"eval_loss": 0.06152050197124481,
"eval_micro_f1": 0.6059351271852642,
"eval_runtime": 17.0186,
"eval_samples_per_second": 355.729,
"step": 4400
},
{
"epoch": 28.0,
"eval_loss": 0.055551182478666306,
"eval_micro_f1": 0.6194926563817533,
"eval_runtime": 20.2971,
"eval_samples_per_second": 298.27,
"step": 4480
},
{
"epoch": 28.12,
"learning_rate": 9.0625e-06,
"loss": 0.0004,
"step": 4500
},
{
"epoch": 28.5,
"eval_loss": 0.05939110368490219,
"eval_micro_f1": 0.6106254198162655,
"eval_runtime": 18.2571,
"eval_samples_per_second": 331.597,
"step": 4560
},
{
"epoch": 29.0,
"eval_loss": 0.05611806735396385,
"eval_micro_f1": 0.6059016388481135,
"eval_runtime": 17.4557,
"eval_samples_per_second": 346.821,
"step": 4640
},
{
"epoch": 29.5,
"eval_loss": 0.06076602265238762,
"eval_micro_f1": 0.6084507037402419,
"eval_runtime": 17.1105,
"eval_samples_per_second": 353.819,
"step": 4720
},
{
"epoch": 30.0,
"eval_loss": 0.059305932372808456,
"eval_micro_f1": 0.6061433442190526,
"eval_runtime": 18.9474,
"eval_samples_per_second": 319.516,
"step": 4800
},
{
"epoch": 30.5,
"eval_loss": 0.06068538874387741,
"eval_micro_f1": 0.6165211546444006,
"eval_runtime": 17.8582,
"eval_samples_per_second": 339.004,
"step": 4880
},
{
"epoch": 31.0,
"eval_loss": 0.058998413383960724,
"eval_micro_f1": 0.6182056314617866,
"eval_runtime": 17.3847,
"eval_samples_per_second": 348.237,
"step": 4960
},
{
"epoch": 31.25,
"learning_rate": 8.958333333333334e-06,
"loss": 0.0004,
"step": 5000
},
{
"epoch": 31.5,
"eval_loss": 0.059548743069171906,
"eval_micro_f1": 0.6158984630998644,
"eval_runtime": 18.9723,
"eval_samples_per_second": 319.098,
"step": 5040
},
{
"epoch": 32.0,
"eval_loss": 0.05749301612377167,
"eval_micro_f1": 0.6149768053366956,
"eval_runtime": 17.7162,
"eval_samples_per_second": 341.721,
"step": 5120
},
{
"epoch": 32.5,
"eval_loss": 0.05796879157423973,
"eval_micro_f1": 0.6074766350199536,
"eval_runtime": 17.1796,
"eval_samples_per_second": 352.395,
"step": 5200
},
{
"epoch": 33.0,
"eval_loss": 0.06406603753566742,
"eval_micro_f1": 0.6078291810118535,
"eval_runtime": 17.3364,
"eval_samples_per_second": 349.208,
"step": 5280
},
{
"epoch": 33.5,
"eval_loss": 0.06082414463162422,
"eval_micro_f1": 0.6137931029591496,
"eval_runtime": 18.007,
"eval_samples_per_second": 336.203,
"step": 5360
},
{
"epoch": 34.0,
"eval_loss": 0.060966573655605316,
"eval_micro_f1": 0.6200403492042824,
"eval_runtime": 17.9749,
"eval_samples_per_second": 336.803,
"step": 5440
},
{
"epoch": 34.38,
"learning_rate": 8.854166666666667e-06,
"loss": 0.0004,
"step": 5500
},
{
"epoch": 34.5,
"eval_loss": 0.06196989119052887,
"eval_micro_f1": 0.6098081018622857,
"eval_runtime": 18.3492,
"eval_samples_per_second": 329.932,
"step": 5520
},
{
"epoch": 35.0,
"eval_loss": 0.05659567192196846,
"eval_micro_f1": 0.6088682986445134,
"eval_runtime": 18.3622,
"eval_samples_per_second": 329.7,
"step": 5600
},
{
"epoch": 35.5,
"eval_loss": 0.059034302830696106,
"eval_micro_f1": 0.6175485594527764,
"eval_runtime": 17.5687,
"eval_samples_per_second": 344.591,
"step": 5680
},
{
"epoch": 36.0,
"eval_loss": 0.06015234440565109,
"eval_micro_f1": 0.609109448862688,
"eval_runtime": 17.6439,
"eval_samples_per_second": 343.122,
"step": 5760
},
{
"epoch": 36.5,
"eval_loss": 0.05944640561938286,
"eval_micro_f1": 0.6106973590204137,
"eval_runtime": 16.9527,
"eval_samples_per_second": 357.111,
"step": 5840
},
{
"epoch": 37.0,
"eval_loss": 0.05665986239910126,
"eval_micro_f1": 0.6295081962251318,
"eval_runtime": 17.1893,
"eval_samples_per_second": 352.196,
"step": 5920
},
{
"epoch": 37.5,
"learning_rate": 8.750000000000001e-06,
"loss": 0.0004,
"step": 6000
},
{
"epoch": 37.5,
"eval_loss": 0.05723871663212776,
"eval_micro_f1": 0.6169088502311827,
"eval_runtime": 17.8567,
"eval_samples_per_second": 339.033,
"step": 6000
},
{
"epoch": 38.0,
"eval_loss": 0.06018886715173721,
"eval_micro_f1": 0.6088154265078849,
"eval_runtime": 18.3094,
"eval_samples_per_second": 330.651,
"step": 6080
},
{
"epoch": 38.5,
"eval_loss": 0.058001838624477386,
"eval_micro_f1": 0.617218542551295,
"eval_runtime": 17.5611,
"eval_samples_per_second": 344.738,
"step": 6160
},
{
"epoch": 39.0,
"eval_loss": 0.06053003668785095,
"eval_micro_f1": 0.6195286190357138,
"eval_runtime": 17.622,
"eval_samples_per_second": 343.549,
"step": 6240
},
{
"epoch": 39.5,
"eval_loss": 0.06181808188557625,
"eval_micro_f1": 0.613119142745902,
"eval_runtime": 17.7898,
"eval_samples_per_second": 340.308,
"step": 6320
},
{
"epoch": 40.0,
"eval_loss": 0.06046893447637558,
"eval_micro_f1": 0.6191135729188101,
"eval_runtime": 17.2133,
"eval_samples_per_second": 351.705,
"step": 6400
},
{
"epoch": 40.5,
"eval_loss": 0.06222919374704361,
"eval_micro_f1": 0.6166551956564147,
"eval_runtime": 17.2477,
"eval_samples_per_second": 351.004,
"step": 6480
},
{
"epoch": 40.62,
"learning_rate": 8.645833333333335e-06,
"loss": 0.0003,
"step": 6500
},
{
"epoch": 41.0,
"eval_loss": 0.060848742723464966,
"eval_micro_f1": 0.6126943000207774,
"eval_runtime": 17.8139,
"eval_samples_per_second": 339.847,
"step": 6560
},
{
"epoch": 41.5,
"eval_loss": 0.059979844838380814,
"eval_micro_f1": 0.629973474306139,
"eval_runtime": 17.6084,
"eval_samples_per_second": 343.813,
"step": 6640
},
{
"epoch": 42.0,
"eval_loss": 0.06330998241901398,
"eval_micro_f1": 0.612021857432754,
"eval_runtime": 17.532,
"eval_samples_per_second": 345.312,
"step": 6720
},
{
"epoch": 42.5,
"eval_loss": 0.06147892773151398,
"eval_micro_f1": 0.6177451629481304,
"eval_runtime": 17.3343,
"eval_samples_per_second": 349.25,
"step": 6800
},
{
"epoch": 43.0,
"eval_loss": 0.06393156945705414,
"eval_micro_f1": 0.6238030090853861,
"eval_runtime": 20.315,
"eval_samples_per_second": 298.006,
"step": 6880
},
{
"epoch": 43.5,
"eval_loss": 0.06525754183530807,
"eval_micro_f1": 0.612969282785596,
"eval_runtime": 18.4438,
"eval_samples_per_second": 328.241,
"step": 6960
},
{
"epoch": 43.75,
"learning_rate": 8.541666666666666e-06,
"loss": 0.0002,
"step": 7000
},
{
"epoch": 44.0,
"eval_loss": 0.060691650956869125,
"eval_micro_f1": 0.6096256679553033,
"eval_runtime": 17.5097,
"eval_samples_per_second": 345.752,
"step": 7040
},
{
"epoch": 44.5,
"eval_loss": 0.06889559328556061,
"eval_micro_f1": 0.6002906971966835,
"eval_runtime": 20.2025,
"eval_samples_per_second": 299.665,
"step": 7120
},
{
"epoch": 45.0,
"eval_loss": 0.06343601644039154,
"eval_micro_f1": 0.6080332405088531,
"eval_runtime": 16.8302,
"eval_samples_per_second": 359.711,
"step": 7200
},
{
"epoch": 45.5,
"eval_loss": 0.060039348900318146,
"eval_micro_f1": 0.5927940171835804,
"eval_runtime": 20.0758,
"eval_samples_per_second": 301.558,
"step": 7280
},
{
"epoch": 46.0,
"eval_loss": 0.06268353015184402,
"eval_micro_f1": 0.6065573765584445,
"eval_runtime": 17.945,
"eval_samples_per_second": 337.364,
"step": 7360
},
{
"epoch": 46.5,
"eval_loss": 0.06181902438402176,
"eval_micro_f1": 0.6229729724805461,
"eval_runtime": 21.2929,
"eval_samples_per_second": 284.32,
"step": 7440
},
{
"epoch": 46.88,
"learning_rate": 8.4375e-06,
"loss": 0.0003,
"step": 7500
},
{
"epoch": 47.0,
"eval_loss": 0.05919589474797249,
"eval_micro_f1": 0.6232370713670242,
"eval_runtime": 20.6302,
"eval_samples_per_second": 293.454,
"step": 7520
},
{
"epoch": 47.5,
"eval_loss": 0.060944102704524994,
"eval_micro_f1": 0.6141304342910044,
"eval_runtime": 17.8092,
"eval_samples_per_second": 339.936,
"step": 7600
},
{
"epoch": 48.0,
"eval_loss": 0.06423073261976242,
"eval_micro_f1": 0.6009582472851024,
"eval_runtime": 17.5034,
"eval_samples_per_second": 345.875,
"step": 7680
},
{
"epoch": 48.5,
"eval_loss": 0.05955960601568222,
"eval_micro_f1": 0.6014445169038645,
"eval_runtime": 17.6446,
"eval_samples_per_second": 343.107,
"step": 7760
},
{
"epoch": 49.0,
"eval_loss": 0.05804387852549553,
"eval_micro_f1": 0.6130992567660972,
"eval_runtime": 17.8072,
"eval_samples_per_second": 339.975,
"step": 7840
},
{
"epoch": 49.5,
"eval_loss": 0.06169767677783966,
"eval_micro_f1": 0.6165211546444006,
"eval_runtime": 19.5005,
"eval_samples_per_second": 310.454,
"step": 7920
},
{
"epoch": 50.0,
"learning_rate": 8.333333333333334e-06,
"loss": 0.0004,
"step": 8000
},
{
"epoch": 50.0,
"eval_loss": 0.06193612515926361,
"eval_micro_f1": 0.6043569917843125,
"eval_runtime": 17.0913,
"eval_samples_per_second": 354.214,
"step": 8000
},
{
"epoch": 50.5,
"eval_loss": 0.06298398971557617,
"eval_micro_f1": 0.6191474488494448,
"eval_runtime": 17.6599,
"eval_samples_per_second": 342.81,
"step": 8080
},
{
"epoch": 51.0,
"eval_loss": 0.06652193516492844,
"eval_micro_f1": 0.6129722019408852,
"eval_runtime": 17.6708,
"eval_samples_per_second": 342.598,
"step": 8160
},
{
"epoch": 51.5,
"eval_loss": 0.06569021940231323,
"eval_micro_f1": 0.6218487390095253,
"eval_runtime": 17.5245,
"eval_samples_per_second": 345.46,
"step": 8240
},
{
"epoch": 52.0,
"eval_loss": 0.06410817801952362,
"eval_micro_f1": 0.6253443521276969,
"eval_runtime": 17.0132,
"eval_samples_per_second": 355.841,
"step": 8320
},
{
"epoch": 52.5,
"eval_loss": 0.06484386324882507,
"eval_micro_f1": 0.6137135093521486,
"eval_runtime": 18.0524,
"eval_samples_per_second": 335.357,
"step": 8400
},
{
"epoch": 53.0,
"eval_loss": 0.06505156308412552,
"eval_micro_f1": 0.6197564271126472,
"eval_runtime": 16.8085,
"eval_samples_per_second": 360.174,
"step": 8480
},
{
"epoch": 53.12,
"learning_rate": 8.229166666666667e-06,
"loss": 0.0003,
"step": 8500
},
{
"epoch": 53.5,
"eval_loss": 0.06969663500785828,
"eval_micro_f1": 0.6012793172141102,
"eval_runtime": 17.4443,
"eval_samples_per_second": 347.048,
"step": 8560
},
{
"epoch": 54.0,
"eval_loss": 0.061523161828517914,
"eval_micro_f1": 0.6242383204286553,
"eval_runtime": 19.6574,
"eval_samples_per_second": 307.975,
"step": 8640
},
{
"epoch": 54.5,
"eval_loss": 0.06353439390659332,
"eval_micro_f1": 0.613011401250342,
"eval_runtime": 17.5276,
"eval_samples_per_second": 345.398,
"step": 8720
},
{
"epoch": 55.0,
"eval_loss": 0.061741847544908524,
"eval_micro_f1": 0.6117021271649997,
"eval_runtime": 17.1523,
"eval_samples_per_second": 352.955,
"step": 8800
},
{
"epoch": 55.5,
"eval_loss": 0.06357300281524658,
"eval_micro_f1": 0.6196024669532615,
"eval_runtime": 17.8685,
"eval_samples_per_second": 338.809,
"step": 8880
},
{
"epoch": 56.0,
"eval_loss": 0.06232788413763046,
"eval_micro_f1": 0.620502375611474,
"eval_runtime": 17.7525,
"eval_samples_per_second": 341.022,
"step": 8960
},
{
"epoch": 56.25,
"learning_rate": 8.125000000000001e-06,
"loss": 0.0002,
"step": 9000
},
{
"epoch": 56.5,
"eval_loss": 0.06787831336259842,
"eval_micro_f1": 0.616551723648801,
"eval_runtime": 18.076,
"eval_samples_per_second": 334.919,
"step": 9040
},
{
"epoch": 57.0,
"eval_loss": 0.06536683440208435,
"eval_micro_f1": 0.6189821178047488,
"eval_runtime": 17.231,
"eval_samples_per_second": 351.343,
"step": 9120
},
{
"epoch": 57.5,
"eval_loss": 0.06487737596035004,
"eval_micro_f1": 0.6204986144700547,
"eval_runtime": 17.677,
"eval_samples_per_second": 342.478,
"step": 9200
},
{
"epoch": 58.0,
"eval_loss": 0.06839023530483246,
"eval_micro_f1": 0.611347517246893,
"eval_runtime": 18.2127,
"eval_samples_per_second": 332.406,
"step": 9280
},
{
"epoch": 58.5,
"eval_loss": 0.06471898406744003,
"eval_micro_f1": 0.6205479447151717,
"eval_runtime": 17.3918,
"eval_samples_per_second": 348.095,
"step": 9360
},
{
"epoch": 59.0,
"eval_loss": 0.06914057582616806,
"eval_micro_f1": 0.6174033144282397,
"eval_runtime": 18.4288,
"eval_samples_per_second": 328.507,
"step": 9440
},
{
"epoch": 59.38,
"learning_rate": 8.020833333333335e-06,
"loss": 0.0002,
"step": 9500
},
{
"epoch": 59.5,
"eval_loss": 0.06447169184684753,
"eval_micro_f1": 0.617218542551295,
"eval_runtime": 18.5863,
"eval_samples_per_second": 325.724,
"step": 9520
},
{
"epoch": 60.0,
"eval_loss": 0.06466624140739441,
"eval_micro_f1": 0.6208791203892721,
"eval_runtime": 17.3418,
"eval_samples_per_second": 349.098,
"step": 9600
},
{
"epoch": 60.5,
"eval_loss": 0.06636277586221695,
"eval_micro_f1": 0.6149584482650763,
"eval_runtime": 18.1336,
"eval_samples_per_second": 333.856,
"step": 9680
},
{
"epoch": 61.0,
"eval_loss": 0.06290476024150848,
"eval_micro_f1": 0.6150684926603847,
"eval_runtime": 18.6329,
"eval_samples_per_second": 324.908,
"step": 9760
},
{
"epoch": 61.5,
"eval_loss": 0.0675923228263855,
"eval_micro_f1": 0.6197583506184904,
"eval_runtime": 17.2171,
"eval_samples_per_second": 351.627,
"step": 9840
},
{
"epoch": 62.0,
"eval_loss": 0.06755334138870239,
"eval_micro_f1": 0.6075085319323613,
"eval_runtime": 16.8819,
"eval_samples_per_second": 358.61,
"step": 9920
},
{
"epoch": 62.5,
"learning_rate": 7.916666666666667e-06,
"loss": 0.0003,
"step": 10000
},
{
"epoch": 62.5,
"eval_loss": 0.06649085879325867,
"eval_micro_f1": 0.6157024788494733,
"eval_runtime": 20.709,
"eval_samples_per_second": 292.337,
"step": 10000
},
{
"epoch": 63.0,
"eval_loss": 0.06577686220407486,
"eval_micro_f1": 0.6075085319323613,
"eval_runtime": 17.7055,
"eval_samples_per_second": 341.928,
"step": 10080
},
{
"epoch": 63.5,
"eval_loss": 0.0697290301322937,
"eval_micro_f1": 0.6166783456946731,
"eval_runtime": 20.6017,
"eval_samples_per_second": 293.86,
"step": 10160
},
{
"epoch": 64.0,
"eval_loss": 0.06230561435222626,
"eval_micro_f1": 0.6070199582166484,
"eval_runtime": 20.8761,
"eval_samples_per_second": 289.997,
"step": 10240
},
{
"epoch": 64.5,
"eval_loss": 0.06587366759777069,
"eval_micro_f1": 0.6005665717540627,
"eval_runtime": 19.7894,
"eval_samples_per_second": 305.921,
"step": 10320
},
{
"epoch": 65.0,
"eval_loss": 0.0650835931301117,
"eval_micro_f1": 0.6130790185823898,
"eval_runtime": 18.9729,
"eval_samples_per_second": 319.087,
"step": 10400
},
{
"epoch": 65.5,
"eval_loss": 0.06411252170801163,
"eval_micro_f1": 0.6177715086830137,
"eval_runtime": 17.7693,
"eval_samples_per_second": 340.701,
"step": 10480
},
{
"epoch": 65.62,
"learning_rate": 7.8125e-06,
"loss": 0.0003,
"step": 10500
},
{
"epoch": 66.0,
"eval_loss": 0.06296994537115097,
"eval_micro_f1": 0.6206896546775043,
"eval_runtime": 16.9517,
"eval_samples_per_second": 357.132,
"step": 10560
},
{
"epoch": 66.5,
"eval_loss": 0.06631151586771011,
"eval_micro_f1": 0.6123557361002835,
"eval_runtime": 16.5178,
"eval_samples_per_second": 366.514,
"step": 10640
},
{
"epoch": 67.0,
"eval_loss": 0.06790296733379364,
"eval_micro_f1": 0.5960082582854866,
"eval_runtime": 19.0012,
"eval_samples_per_second": 318.612,
"step": 10720
},
{
"epoch": 67.5,
"eval_loss": 0.06526356935501099,
"eval_micro_f1": 0.624075318942004,
"eval_runtime": 18.5495,
"eval_samples_per_second": 326.37,
"step": 10800
},
{
"epoch": 68.0,
"eval_loss": 0.07024352997541428,
"eval_micro_f1": 0.6167582412683986,
"eval_runtime": 17.3077,
"eval_samples_per_second": 349.787,
"step": 10880
},
{
"epoch": 68.5,
"eval_loss": 0.07011512666940689,
"eval_micro_f1": 0.623789764379954,
"eval_runtime": 17.7582,
"eval_samples_per_second": 340.913,
"step": 10960
},
{
"epoch": 68.75,
"learning_rate": 7.708333333333334e-06,
"loss": 0.0002,
"step": 11000
},
{
"epoch": 69.0,
"eval_loss": 0.06176885962486267,
"eval_micro_f1": 0.6070245190543998,
"eval_runtime": 18.2609,
"eval_samples_per_second": 331.527,
"step": 11040
},
{
"epoch": 69.5,
"eval_loss": 0.06635753810405731,
"eval_micro_f1": 0.6118656178169498,
"eval_runtime": 17.7023,
"eval_samples_per_second": 341.99,
"step": 11120
},
{
"epoch": 70.0,
"eval_loss": 0.06404802203178406,
"eval_micro_f1": 0.6128391788562884,
"eval_runtime": 17.9624,
"eval_samples_per_second": 337.038,
"step": 11200
},
{
"epoch": 70.5,
"eval_loss": 0.07109695672988892,
"eval_micro_f1": 0.6074498562521983,
"eval_runtime": 18.1899,
"eval_samples_per_second": 332.822,
"step": 11280
},
{
"epoch": 71.0,
"eval_loss": 0.07133074104785919,
"eval_micro_f1": 0.6162544164767535,
"eval_runtime": 17.5812,
"eval_samples_per_second": 344.345,
"step": 11360
},
{
"epoch": 71.5,
"eval_loss": 0.07133891433477402,
"eval_micro_f1": 0.6141078833287917,
"eval_runtime": 17.2343,
"eval_samples_per_second": 351.276,
"step": 11440
},
{
"epoch": 71.88,
"learning_rate": 7.6041666666666666e-06,
"loss": 0.0002,
"step": 11500
},
{
"epoch": 72.0,
"eval_loss": 0.06819088011980057,
"eval_micro_f1": 0.6141732278649523,
"eval_runtime": 18.8917,
"eval_samples_per_second": 320.458,
"step": 11520
},
{
"epoch": 72.5,
"eval_loss": 0.06992849707603455,
"eval_micro_f1": 0.6122733607402551,
"eval_runtime": 18.2855,
"eval_samples_per_second": 331.082,
"step": 11600
},
{
"epoch": 73.0,
"eval_loss": 0.06930901855230331,
"eval_micro_f1": 0.6092990973607194,
"eval_runtime": 16.7785,
"eval_samples_per_second": 360.819,
"step": 11680
},
{
"epoch": 73.5,
"eval_loss": 0.06919851154088974,
"eval_micro_f1": 0.6112637357739007,
"eval_runtime": 17.6086,
"eval_samples_per_second": 343.809,
"step": 11760
},
{
"epoch": 74.0,
"eval_loss": 0.0678936168551445,
"eval_micro_f1": 0.6146475012207442,
"eval_runtime": 17.3735,
"eval_samples_per_second": 348.462,
"step": 11840
},
{
"epoch": 74.5,
"eval_loss": 0.06851907074451447,
"eval_micro_f1": 0.6205962054700354,
"eval_runtime": 16.8084,
"eval_samples_per_second": 360.176,
"step": 11920
},
{
"epoch": 75.0,
"learning_rate": 7.500000000000001e-06,
"loss": 0.0002,
"step": 12000
},
{
"epoch": 75.0,
"eval_loss": 0.06772681325674057,
"eval_micro_f1": 0.6231983522897163,
"eval_runtime": 16.8409,
"eval_samples_per_second": 359.482,
"step": 12000
},
{
"epoch": 75.5,
"eval_loss": 0.06931421905755997,
"eval_micro_f1": 0.6111888107022758,
"eval_runtime": 18.1839,
"eval_samples_per_second": 332.931,
"step": 12080
},
{
"epoch": 76.0,
"eval_loss": 0.0699552446603775,
"eval_micro_f1": 0.6062283732139222,
"eval_runtime": 18.1565,
"eval_samples_per_second": 333.435,
"step": 12160
},
{
"epoch": 76.5,
"eval_loss": 0.07175280153751373,
"eval_micro_f1": 0.6160220989586285,
"eval_runtime": 17.757,
"eval_samples_per_second": 340.936,
"step": 12240
},
{
"epoch": 77.0,
"eval_loss": 0.07182992994785309,
"eval_micro_f1": 0.6149584482650763,
"eval_runtime": 17.9643,
"eval_samples_per_second": 337.002,
"step": 12320
},
{
"epoch": 77.5,
"eval_loss": 0.0754663497209549,
"eval_micro_f1": 0.6127415886380396,
"eval_runtime": 17.74,
"eval_samples_per_second": 341.263,
"step": 12400
},
{
"epoch": 78.0,
"eval_loss": 0.06644661724567413,
"eval_micro_f1": 0.6191780817014748,
"eval_runtime": 17.5642,
"eval_samples_per_second": 344.679,
"step": 12480
},
{
"epoch": 78.12,
"learning_rate": 7.395833333333335e-06,
"loss": 0.0002,
"step": 12500
},
{
"epoch": 78.5,
"eval_loss": 0.06699120998382568,
"eval_micro_f1": 0.6141522024431756,
"eval_runtime": 18.4844,
"eval_samples_per_second": 327.52,
"step": 12560
},
{
"epoch": 79.0,
"eval_loss": 0.06848654896020889,
"eval_micro_f1": 0.623641303856209,
"eval_runtime": 17.7647,
"eval_samples_per_second": 340.789,
"step": 12640
},
{
"epoch": 79.5,
"eval_loss": 0.06864441931247711,
"eval_micro_f1": 0.6191780817014748,
"eval_runtime": 17.1639,
"eval_samples_per_second": 352.717,
"step": 12720
},
{
"epoch": 80.0,
"eval_loss": 0.06860464811325073,
"eval_micro_f1": 0.612359550076103,
"eval_runtime": 18.2794,
"eval_samples_per_second": 331.193,
"step": 12800
},
{
"epoch": 80.5,
"eval_loss": 0.06682693958282471,
"eval_micro_f1": 0.6178521612981274,
"eval_runtime": 17.6313,
"eval_samples_per_second": 343.367,
"step": 12880
},
{
"epoch": 81.0,
"eval_loss": 0.07296701520681381,
"eval_micro_f1": 0.6099789172937915,
"eval_runtime": 19.5945,
"eval_samples_per_second": 308.965,
"step": 12960
},
{
"epoch": 81.25,
"learning_rate": 7.291666666666667e-06,
"loss": 0.0002,
"step": 13000
},
{
"epoch": 81.5,
"eval_loss": 0.07352607697248459,
"eval_micro_f1": 0.6289655167522321,
"eval_runtime": 17.9674,
"eval_samples_per_second": 336.944,
"step": 13040
},
{
"epoch": 82.0,
"eval_loss": 0.07045363634824753,
"eval_micro_f1": 0.6069364157057452,
"eval_runtime": 17.3851,
"eval_samples_per_second": 348.23,
"step": 13120
},
{
"epoch": 82.5,
"eval_loss": 0.07319997251033783,
"eval_micro_f1": 0.612359550076103,
"eval_runtime": 17.717,
"eval_samples_per_second": 341.707,
"step": 13200
},
{
"epoch": 83.0,
"eval_loss": 0.07398298382759094,
"eval_micro_f1": 0.6172148350629297,
"eval_runtime": 17.376,
"eval_samples_per_second": 348.413,
"step": 13280
},
{
"epoch": 83.5,
"eval_loss": 0.07164302468299866,
"eval_micro_f1": 0.621602786969218,
"eval_runtime": 20.5339,
"eval_samples_per_second": 294.829,
"step": 13360
},
{
"epoch": 84.0,
"eval_loss": 0.0759439691901207,
"eval_micro_f1": 0.6070921980979629,
"eval_runtime": 17.8337,
"eval_samples_per_second": 339.47,
"step": 13440
},
{
"epoch": 84.38,
"learning_rate": 7.1875e-06,
"loss": 0.0002,
"step": 13500
},
{
"epoch": 84.5,
"eval_loss": 0.07017052173614502,
"eval_micro_f1": 0.6223118274637982,
"eval_runtime": 19.4127,
"eval_samples_per_second": 311.858,
"step": 13520
},
{
"epoch": 85.0,
"eval_loss": 0.07273142039775848,
"eval_micro_f1": 0.6244035441578559,
"eval_runtime": 17.7344,
"eval_samples_per_second": 341.371,
"step": 13600
},
{
"epoch": 85.5,
"eval_loss": 0.06989909708499908,
"eval_micro_f1": 0.6178428756706956,
"eval_runtime": 18.8021,
"eval_samples_per_second": 321.985,
"step": 13680
},
{
"epoch": 86.0,
"eval_loss": 0.07146839052438736,
"eval_micro_f1": 0.6226040973236018,
"eval_runtime": 20.7218,
"eval_samples_per_second": 292.157,
"step": 13760
},
{
"epoch": 86.5,
"eval_loss": 0.07019157707691193,
"eval_micro_f1": 0.623553437221429,
"eval_runtime": 17.8827,
"eval_samples_per_second": 338.54,
"step": 13840
},
{
"epoch": 87.0,
"eval_loss": 0.072687067091465,
"eval_micro_f1": 0.618724558531249,
"eval_runtime": 20.3379,
"eval_samples_per_second": 297.671,
"step": 13920
},
{
"epoch": 87.5,
"learning_rate": 7.083333333333335e-06,
"loss": 0.0002,
"step": 14000
},
{
"epoch": 87.5,
"eval_loss": 0.0728105679154396,
"eval_micro_f1": 0.6164290558558788,
"eval_runtime": 20.2153,
"eval_samples_per_second": 299.476,
"step": 14000
},
{
"epoch": 88.0,
"eval_loss": 0.0721791610121727,
"eval_micro_f1": 0.6140350872266878,
"eval_runtime": 19.0737,
"eval_samples_per_second": 317.401,
"step": 14080
},
{
"epoch": 88.5,
"eval_loss": 0.07765121757984161,
"eval_micro_f1": 0.6234701219100668,
"eval_runtime": 17.1553,
"eval_samples_per_second": 352.894,
"step": 14160
},
{
"epoch": 89.0,
"eval_loss": 0.07423113286495209,
"eval_micro_f1": 0.6213592228128293,
"eval_runtime": 18.4324,
"eval_samples_per_second": 328.443,
"step": 14240
},
{
"epoch": 89.5,
"eval_loss": 0.07649640738964081,
"eval_micro_f1": 0.6157082744088271,
"eval_runtime": 21.451,
"eval_samples_per_second": 282.225,
"step": 14320
},
{
"epoch": 90.0,
"eval_loss": 0.0730544924736023,
"eval_micro_f1": 0.631061137954338,
"eval_runtime": 18.3506,
"eval_samples_per_second": 329.907,
"step": 14400
},
{
"epoch": 90.5,
"eval_loss": 0.07447430491447449,
"eval_micro_f1": 0.6318021196569436,
"eval_runtime": 20.4659,
"eval_samples_per_second": 295.809,
"step": 14480
},
{
"epoch": 90.62,
"learning_rate": 6.979166666666667e-06,
"loss": 0.0002,
"step": 14500
},
{
"epoch": 91.0,
"eval_loss": 0.06852135807275772,
"eval_micro_f1": 0.6260869560279102,
"eval_runtime": 21.0673,
"eval_samples_per_second": 287.364,
"step": 14560
},
{
"epoch": 91.5,
"eval_loss": 0.06931998580694199,
"eval_micro_f1": 0.6268861449145756,
"eval_runtime": 18.3492,
"eval_samples_per_second": 329.933,
"step": 14640
},
{
"epoch": 92.0,
"eval_loss": 0.07071425020694733,
"eval_micro_f1": 0.6241426606896138,
"eval_runtime": 20.2485,
"eval_samples_per_second": 298.985,
"step": 14720
},
{
"epoch": 92.5,
"eval_loss": 0.07094167917966843,
"eval_micro_f1": 0.6312887658787508,
"eval_runtime": 18.8108,
"eval_samples_per_second": 321.836,
"step": 14800
},
{
"epoch": 93.0,
"eval_loss": 0.07239685952663422,
"eval_micro_f1": 0.6288448388804996,
"eval_runtime": 19.0906,
"eval_samples_per_second": 317.12,
"step": 14880
},
{
"epoch": 93.5,
"eval_loss": 0.07216338813304901,
"eval_micro_f1": 0.6237288130673954,
"eval_runtime": 17.6155,
"eval_samples_per_second": 343.674,
"step": 14960
},
{
"epoch": 93.75,
"learning_rate": 6.875e-06,
"loss": 0.0002,
"step": 15000
},
{
"epoch": 94.0,
"eval_loss": 0.07330916076898575,
"eval_micro_f1": 0.6273712732207037,
"eval_runtime": 17.0903,
"eval_samples_per_second": 354.236,
"step": 15040
},
{
"epoch": 94.5,
"eval_loss": 0.0746123343706131,
"eval_micro_f1": 0.6262763779974634,
"eval_runtime": 17.4151,
"eval_samples_per_second": 347.63,
"step": 15120
},
{
"epoch": 95.0,
"eval_loss": 0.0756663978099823,
"eval_micro_f1": 0.6174216023002344,
"eval_runtime": 16.8244,
"eval_samples_per_second": 359.835,
"step": 15200
},
{
"epoch": 95.5,
"eval_loss": 0.07750966399908066,
"eval_micro_f1": 0.6240337310674893,
"eval_runtime": 17.2065,
"eval_samples_per_second": 351.844,
"step": 15280
},
{
"epoch": 96.0,
"eval_loss": 0.06780446320772171,
"eval_micro_f1": 0.6128170889585313,
"eval_runtime": 17.1717,
"eval_samples_per_second": 352.556,
"step": 15360
},
{
"epoch": 96.5,
"eval_loss": 0.0717654749751091,
"eval_micro_f1": 0.6192121626072942,
"eval_runtime": 19.0168,
"eval_samples_per_second": 318.35,
"step": 15440
},
{
"epoch": 96.88,
"learning_rate": 6.770833333333334e-06,
"loss": 0.0002,
"step": 15500
},
{
"epoch": 97.0,
"eval_loss": 0.071573406457901,
"eval_micro_f1": 0.6197952213521396,
"eval_runtime": 17.415,
"eval_samples_per_second": 347.632,
"step": 15520
},
{
"epoch": 97.5,
"eval_loss": 0.07653269171714783,
"eval_micro_f1": 0.6141953614259008,
"eval_runtime": 16.7325,
"eval_samples_per_second": 361.811,
"step": 15600
},
{
"epoch": 98.0,
"eval_loss": 0.07383699715137482,
"eval_micro_f1": 0.6129032253204718,
"eval_runtime": 17.2798,
"eval_samples_per_second": 350.352,
"step": 15680
},
{
"epoch": 98.5,
"eval_loss": 0.07400070875883102,
"eval_micro_f1": 0.6197952213521396,
"eval_runtime": 16.3298,
"eval_samples_per_second": 370.734,
"step": 15760
},
{
"epoch": 99.0,
"eval_loss": 0.07562475651502609,
"eval_micro_f1": 0.6004228324960207,
"eval_runtime": 17.1596,
"eval_samples_per_second": 352.806,
"step": 15840
},
{
"epoch": 99.5,
"eval_loss": 0.06941039115190506,
"eval_micro_f1": 0.62403100725434,
"eval_runtime": 17.0551,
"eval_samples_per_second": 354.966,
"step": 15920
},
{
"epoch": 100.0,
"learning_rate": 6.666666666666667e-06,
"loss": 0.0002,
"step": 16000
},
{
"epoch": 100.0,
"eval_loss": 0.07257622480392456,
"eval_micro_f1": 0.5998617825105691,
"eval_runtime": 17.2272,
"eval_samples_per_second": 351.42,
"step": 16000
},
{
"epoch": 100.5,
"eval_loss": 0.06931755691766739,
"eval_micro_f1": 0.6249120332937496,
"eval_runtime": 17.0871,
"eval_samples_per_second": 354.302,
"step": 16080
},
{
"epoch": 101.0,
"eval_loss": 0.07044119387865067,
"eval_micro_f1": 0.631939684225349,
"eval_runtime": 18.7586,
"eval_samples_per_second": 322.732,
"step": 16160
},
{
"epoch": 101.5,
"eval_loss": 0.06791292876005173,
"eval_micro_f1": 0.6293800534155319,
"eval_runtime": 17.0572,
"eval_samples_per_second": 354.924,
"step": 16240
},
{
"epoch": 102.0,
"eval_loss": 0.06589435040950775,
"eval_micro_f1": 0.6284558322786828,
"eval_runtime": 16.8164,
"eval_samples_per_second": 360.006,
"step": 16320
},
{
"epoch": 102.5,
"eval_loss": 0.07133129239082336,
"eval_micro_f1": 0.606819762908491,
"eval_runtime": 17.5266,
"eval_samples_per_second": 345.418,
"step": 16400
},
{
"epoch": 103.0,
"eval_loss": 0.07038109004497528,
"eval_micro_f1": 0.6192754608900819,
"eval_runtime": 16.9346,
"eval_samples_per_second": 357.494,
"step": 16480
},
{
"epoch": 103.12,
"learning_rate": 6.5625e-06,
"loss": 0.0002,
"step": 16500
},
{
"epoch": 103.5,
"eval_loss": 0.07022614032030106,
"eval_micro_f1": 0.6346025379161386,
"eval_runtime": 17.3566,
"eval_samples_per_second": 348.8,
"step": 16560
},
{
"epoch": 104.0,
"eval_loss": 0.0707772821187973,
"eval_micro_f1": 0.6330645156358267,
"eval_runtime": 16.6921,
"eval_samples_per_second": 362.686,
"step": 16640
},
{
"epoch": 104.5,
"eval_loss": 0.07519261538982391,
"eval_micro_f1": 0.6052998600429148,
"eval_runtime": 17.2834,
"eval_samples_per_second": 350.279,
"step": 16720
},
{
"epoch": 105.0,
"eval_loss": 0.06973288953304291,
"eval_micro_f1": 0.6191744335934636,
"eval_runtime": 17.1171,
"eval_samples_per_second": 353.682,
"step": 16800
},
{
"epoch": 105.5,
"eval_loss": 0.07181514799594879,
"eval_micro_f1": 0.6286863265841827,
"eval_runtime": 17.4479,
"eval_samples_per_second": 346.977,
"step": 16880
},
{
"epoch": 106.0,
"eval_loss": 0.0750337615609169,
"eval_micro_f1": 0.6282578870270565,
"eval_runtime": 20.1307,
"eval_samples_per_second": 300.735,
"step": 16960
},
{
"epoch": 106.25,
"learning_rate": 6.458333333333334e-06,
"loss": 0.0002,
"step": 17000
},
{
"epoch": 106.5,
"eval_loss": 0.07513300329446793,
"eval_micro_f1": 0.6270949715802077,
"eval_runtime": 17.3898,
"eval_samples_per_second": 348.135,
"step": 17040
},
{
"epoch": 107.0,
"eval_loss": 0.07476061582565308,
"eval_micro_f1": 0.6160108543250112,
"eval_runtime": 19.9678,
"eval_samples_per_second": 303.189,
"step": 17120
},
{
"epoch": 107.5,
"eval_loss": 0.07374893128871918,
"eval_micro_f1": 0.6248313085492103,
"eval_runtime": 17.0794,
"eval_samples_per_second": 354.462,
"step": 17200
},
{
"epoch": 108.0,
"eval_loss": 0.07439166307449341,
"eval_micro_f1": 0.6260162596705701,
"eval_runtime": 17.2551,
"eval_samples_per_second": 350.852,
"step": 17280
},
{
"epoch": 108.5,
"eval_loss": 0.07690379023551941,
"eval_micro_f1": 0.6179540704937226,
"eval_runtime": 17.7902,
"eval_samples_per_second": 340.3,
"step": 17360
},
{
"epoch": 109.0,
"eval_loss": 0.07610183954238892,
"eval_micro_f1": 0.620979020492472,
"eval_runtime": 16.9271,
"eval_samples_per_second": 357.65,
"step": 17440
},
{
"epoch": 109.38,
"learning_rate": 6.354166666666667e-06,
"loss": 0.0002,
"step": 17500
},
{
"epoch": 109.5,
"eval_loss": 0.07505128532648087,
"eval_micro_f1": 0.5891472863367695,
"eval_runtime": 17.0979,
"eval_samples_per_second": 354.08,
"step": 17520
},
{
"epoch": 110.0,
"eval_loss": 0.07259324193000793,
"eval_micro_f1": 0.6152805945043016,
"eval_runtime": 17.3501,
"eval_samples_per_second": 348.932,
"step": 17600
},
{
"epoch": 110.5,
"eval_loss": 0.07482381165027618,
"eval_micro_f1": 0.604296603808359,
"eval_runtime": 16.9295,
"eval_samples_per_second": 357.601,
"step": 17680
},
{
"epoch": 111.0,
"eval_loss": 0.0700354054570198,
"eval_micro_f1": 0.6145624577558447,
"eval_runtime": 16.8904,
"eval_samples_per_second": 358.429,
"step": 17760
},
{
"epoch": 111.5,
"eval_loss": 0.07188516110181808,
"eval_micro_f1": 0.6217331494416087,
"eval_runtime": 18.3403,
"eval_samples_per_second": 330.093,
"step": 17840
},
{
"epoch": 112.0,
"eval_loss": 0.07414805144071579,
"eval_micro_f1": 0.6201232027950009,
"eval_runtime": 17.0796,
"eval_samples_per_second": 354.457,
"step": 17920
},
{
"epoch": 112.5,
"learning_rate": 6.25e-06,
"loss": 0.0002,
"step": 18000
},
{
"epoch": 112.5,
"eval_loss": 0.07325228303670883,
"eval_micro_f1": 0.6227951148406057,
"eval_runtime": 17.7106,
"eval_samples_per_second": 341.829,
"step": 18000
},
{
"epoch": 113.0,
"eval_loss": 0.0752234011888504,
"eval_micro_f1": 0.6220689650281037,
"eval_runtime": 17.2326,
"eval_samples_per_second": 351.311,
"step": 18080
},
{
"epoch": 113.5,
"eval_loss": 0.07352042198181152,
"eval_micro_f1": 0.6255088190468436,
"eval_runtime": 18.1244,
"eval_samples_per_second": 334.024,
"step": 18160
},
{
"epoch": 114.0,
"eval_loss": 0.07509664446115494,
"eval_micro_f1": 0.6200274343521708,
"eval_runtime": 16.4931,
"eval_samples_per_second": 367.063,
"step": 18240
},
{
"epoch": 114.5,
"eval_loss": 0.07555115222930908,
"eval_micro_f1": 0.6195054940156477,
"eval_runtime": 17.366,
"eval_samples_per_second": 348.613,
"step": 18320
},
{
"epoch": 115.0,
"eval_loss": 0.07472817599773407,
"eval_micro_f1": 0.6206415615770635,
"eval_runtime": 17.065,
"eval_samples_per_second": 354.762,
"step": 18400
},
{
"epoch": 115.5,
"eval_loss": 0.07418936491012573,
"eval_micro_f1": 0.6265389871975574,
"eval_runtime": 17.1121,
"eval_samples_per_second": 353.784,
"step": 18480
},
{
"epoch": 115.62,
"learning_rate": 6.145833333333334e-06,
"loss": 0.0001,
"step": 18500
},
{
"epoch": 116.0,
"eval_loss": 0.07474187761545181,
"eval_micro_f1": 0.6207376473900306,
"eval_runtime": 16.96,
"eval_samples_per_second": 356.959,
"step": 18560
},
{
"epoch": 116.5,
"eval_loss": 0.07691577821969986,
"eval_micro_f1": 0.6208333328454494,
"eval_runtime": 16.91,
"eval_samples_per_second": 358.014,
"step": 18640
},
{
"epoch": 117.0,
"eval_loss": 0.07347321510314941,
"eval_micro_f1": 0.635310156291447,
"eval_runtime": 17.538,
"eval_samples_per_second": 345.194,
"step": 18720
},
{
"epoch": 117.5,
"eval_loss": 0.07574611157178879,
"eval_micro_f1": 0.6327223348782599,
"eval_runtime": 16.9204,
"eval_samples_per_second": 357.794,
"step": 18800
},
{
"epoch": 118.0,
"eval_loss": 0.0736304372549057,
"eval_micro_f1": 0.62273032902943,
"eval_runtime": 17.0313,
"eval_samples_per_second": 355.463,
"step": 18880
},
{
"epoch": 118.5,
"eval_loss": 0.07677203416824341,
"eval_micro_f1": 0.6190476185562183,
"eval_runtime": 17.2022,
"eval_samples_per_second": 351.931,
"step": 18960
},
{
"epoch": 118.75,
"learning_rate": 6.041666666666667e-06,
"loss": 0.0001,
"step": 19000
},
{
"epoch": 119.0,
"eval_loss": 0.07457544654607773,
"eval_micro_f1": 0.6274509798998227,
"eval_runtime": 17.2918,
"eval_samples_per_second": 350.108,
"step": 19040
},
{
"epoch": 119.5,
"eval_loss": 0.07726600021123886,
"eval_micro_f1": 0.6243093917762964,
"eval_runtime": 17.6695,
"eval_samples_per_second": 342.625,
"step": 19120
},
{
"epoch": 120.0,
"eval_loss": 0.08045264333486557,
"eval_micro_f1": 0.6105563475918526,
"eval_runtime": 16.8794,
"eval_samples_per_second": 358.663,
"step": 19200
},
{
"epoch": 120.5,
"eval_loss": 0.07310644537210464,
"eval_micro_f1": 0.6088709672487624,
"eval_runtime": 17.1821,
"eval_samples_per_second": 352.343,
"step": 19280
},
{
"epoch": 121.0,
"eval_loss": 0.08004646003246307,
"eval_micro_f1": 0.5984363889980516,
"eval_runtime": 16.5355,
"eval_samples_per_second": 366.122,
"step": 19360
},
{
"epoch": 121.5,
"eval_loss": 0.08445169776678085,
"eval_micro_f1": 0.6005547845326916,
"eval_runtime": 17.1638,
"eval_samples_per_second": 352.719,
"step": 19440
},
{
"epoch": 121.88,
"learning_rate": 5.9375e-06,
"loss": 0.0002,
"step": 19500
},
{
"epoch": 122.0,
"eval_loss": 0.07806424051523209,
"eval_micro_f1": 0.6038709672442539,
"eval_runtime": 16.7176,
"eval_samples_per_second": 362.132,
"step": 19520
},
{
"epoch": 122.5,
"eval_loss": 0.07848659157752991,
"eval_micro_f1": 0.5977808594286733,
"eval_runtime": 17.8575,
"eval_samples_per_second": 339.017,
"step": 19600
},
{
"epoch": 123.0,
"eval_loss": 0.07834003120660782,
"eval_micro_f1": 0.6025280894019596,
"eval_runtime": 18.4947,
"eval_samples_per_second": 327.338,
"step": 19680
},
{
"epoch": 123.5,
"eval_loss": 0.07368773221969604,
"eval_micro_f1": 0.620452985096858,
"eval_runtime": 16.98,
"eval_samples_per_second": 356.538,
"step": 19760
},
{
"epoch": 124.0,
"eval_loss": 0.07416415214538574,
"eval_micro_f1": 0.6055668698409581,
"eval_runtime": 16.9571,
"eval_samples_per_second": 357.019,
"step": 19840
},
{
"epoch": 124.5,
"eval_loss": 0.0750683844089508,
"eval_micro_f1": 0.6046195647258001,
"eval_runtime": 17.271,
"eval_samples_per_second": 350.53,
"step": 19920
},
{
"epoch": 125.0,
"learning_rate": 5.833333333333334e-06,
"loss": 0.0002,
"step": 20000
},
{
"epoch": 125.0,
"eval_loss": 0.07247128337621689,
"eval_micro_f1": 0.6086369765654265,
"eval_runtime": 20.1504,
"eval_samples_per_second": 300.44,
"step": 20000
},
{
"epoch": 125.5,
"eval_loss": 0.07572506368160248,
"eval_micro_f1": 0.6009922036268159,
"eval_runtime": 19.9063,
"eval_samples_per_second": 304.125,
"step": 20080
},
{
"epoch": 126.0,
"eval_loss": 0.07710001617670059,
"eval_micro_f1": 0.6110721789112191,
"eval_runtime": 16.4601,
"eval_samples_per_second": 367.798,
"step": 20160
},
{
"epoch": 126.5,
"eval_loss": 0.0783923789858818,
"eval_micro_f1": 0.6116983786552719,
"eval_runtime": 17.2143,
"eval_samples_per_second": 351.684,
"step": 20240
},
{
"epoch": 127.0,
"eval_loss": 0.0790233314037323,
"eval_micro_f1": 0.6100981762321167,
"eval_runtime": 17.2113,
"eval_samples_per_second": 351.745,
"step": 20320
},
{
"epoch": 127.5,
"eval_loss": 0.07875987887382507,
"eval_micro_f1": 0.6043656202457466,
"eval_runtime": 18.6325,
"eval_samples_per_second": 324.916,
"step": 20400
},
{
"epoch": 128.0,
"eval_loss": 0.07836011052131653,
"eval_micro_f1": 0.5997229912013854,
"eval_runtime": 17.1837,
"eval_samples_per_second": 352.31,
"step": 20480
},
{
"epoch": 128.12,
"learning_rate": 5.729166666666667e-06,
"loss": 0.0001,
"step": 20500
},
{
"epoch": 128.5,
"eval_loss": 0.07462245225906372,
"eval_micro_f1": 0.6178082186877781,
"eval_runtime": 17.847,
"eval_samples_per_second": 339.217,
"step": 20560
},
{
"epoch": 129.0,
"eval_loss": 0.07530470192432404,
"eval_micro_f1": 0.6146408834890169,
"eval_runtime": 18.1901,
"eval_samples_per_second": 332.818,
"step": 20640
},
{
"epoch": 129.5,
"eval_loss": 0.07442829757928848,
"eval_micro_f1": 0.6152787331650196,
"eval_runtime": 20.3126,
"eval_samples_per_second": 298.041,
"step": 20720
},
{
"epoch": 130.0,
"eval_loss": 0.0762370303273201,
"eval_micro_f1": 0.6155969629340432,
"eval_runtime": 17.3325,
"eval_samples_per_second": 349.286,
"step": 20800
},
{
"epoch": 130.5,
"eval_loss": 0.08040288835763931,
"eval_micro_f1": 0.6038543892394735,
"eval_runtime": 17.1299,
"eval_samples_per_second": 353.417,
"step": 20880
},
{
"epoch": 131.0,
"eval_loss": 0.0800437331199646,
"eval_micro_f1": 0.601408450219125,
"eval_runtime": 19.5794,
"eval_samples_per_second": 309.202,
"step": 20960
},
{
"epoch": 131.25,
"learning_rate": 5.625e-06,
"loss": 0.0001,
"step": 21000
},
{
"epoch": 131.5,
"eval_loss": 0.07892248779535294,
"eval_micro_f1": 0.6193103443384522,
"eval_runtime": 16.8619,
"eval_samples_per_second": 359.034,
"step": 21040
},
{
"epoch": 132.0,
"eval_loss": 0.08070007711648941,
"eval_micro_f1": 0.614184396679513,
"eval_runtime": 17.4679,
"eval_samples_per_second": 346.578,
"step": 21120
},
{
"epoch": 132.5,
"eval_loss": 0.0803392305970192,
"eval_micro_f1": 0.6144067791764919,
"eval_runtime": 16.7536,
"eval_samples_per_second": 361.356,
"step": 21200
},
{
"epoch": 133.0,
"eval_loss": 0.07724644988775253,
"eval_micro_f1": 0.6118466894082559,
"eval_runtime": 17.3241,
"eval_samples_per_second": 349.455,
"step": 21280
},
{
"epoch": 133.5,
"eval_loss": 0.0794701799750328,
"eval_micro_f1": 0.6056236476817372,
"eval_runtime": 17.2234,
"eval_samples_per_second": 351.499,
"step": 21360
},
{
"epoch": 134.0,
"eval_loss": 0.0772969126701355,
"eval_micro_f1": 0.6155950747488721,
"eval_runtime": 16.8856,
"eval_samples_per_second": 358.531,
"step": 21440
},
{
"epoch": 134.38,
"learning_rate": 5.520833333333334e-06,
"loss": 0.0001,
"step": 21500
},
{
"epoch": 134.5,
"eval_loss": 0.07610785216093063,
"eval_micro_f1": 0.6210235126510505,
"eval_runtime": 18.0841,
"eval_samples_per_second": 334.77,
"step": 21520
},
{
"epoch": 135.0,
"eval_loss": 0.07849609851837158,
"eval_micro_f1": 0.6219426969277078,
"eval_runtime": 16.9946,
"eval_samples_per_second": 356.23,
"step": 21600
},
{
"epoch": 135.5,
"eval_loss": 0.08091599494218826,
"eval_micro_f1": 0.6042553186653428,
"eval_runtime": 17.3375,
"eval_samples_per_second": 349.186,
"step": 21680
},
{
"epoch": 136.0,
"eval_loss": 0.08291663974523544,
"eval_micro_f1": 0.6037195989460971,
"eval_runtime": 16.5571,
"eval_samples_per_second": 365.645,
"step": 21760
},
{
"epoch": 136.5,
"eval_loss": 0.08029178529977798,
"eval_micro_f1": 0.6215083794014447,
"eval_runtime": 17.4445,
"eval_samples_per_second": 347.043,
"step": 21840
},
{
"epoch": 137.0,
"eval_loss": 0.07960797846317291,
"eval_micro_f1": 0.6208333328454494,
"eval_runtime": 16.8543,
"eval_samples_per_second": 359.196,
"step": 21920
},
{
"epoch": 137.5,
"learning_rate": 5.416666666666667e-06,
"loss": 0.0001,
"step": 22000
},
{
"epoch": 137.5,
"eval_loss": 0.07969075441360474,
"eval_micro_f1": 0.6126373621475252,
"eval_runtime": 16.6783,
"eval_samples_per_second": 362.987,
"step": 22000
},
{
"epoch": 138.0,
"eval_loss": 0.07750562578439713,
"eval_micro_f1": 0.6218256686932871,
"eval_runtime": 17.0132,
"eval_samples_per_second": 355.842,
"step": 22080
},
{
"epoch": 138.5,
"eval_loss": 0.07673478126525879,
"eval_micro_f1": 0.6137491136197106,
"eval_runtime": 18.146,
"eval_samples_per_second": 333.628,
"step": 22160
},
{
"epoch": 139.0,
"eval_loss": 0.07523728907108307,
"eval_micro_f1": 0.6317907439733217,
"eval_runtime": 18.3882,
"eval_samples_per_second": 329.234,
"step": 22240
},
{
"epoch": 139.5,
"eval_loss": 0.07430022954940796,
"eval_micro_f1": 0.6318644062877233,
"eval_runtime": 16.9466,
"eval_samples_per_second": 357.239,
"step": 22320
},
{
"epoch": 140.0,
"eval_loss": 0.07161477953195572,
"eval_micro_f1": 0.62516733551697,
"eval_runtime": 16.9261,
"eval_samples_per_second": 357.673,
"step": 22400
},
{
"epoch": 140.5,
"eval_loss": 0.0744733139872551,
"eval_micro_f1": 0.6175438591632783,
"eval_runtime": 16.8852,
"eval_samples_per_second": 358.539,
"step": 22480
},
{
"epoch": 140.62,
"learning_rate": 5.3125e-06,
"loss": 0.0002,
"step": 22500
},
{
"epoch": 141.0,
"eval_loss": 0.07611773163080215,
"eval_micro_f1": 0.6206415615770635,
"eval_runtime": 16.9471,
"eval_samples_per_second": 357.228,
"step": 22560
},
{
"epoch": 141.5,
"eval_loss": 0.07565868645906448,
"eval_micro_f1": 0.6235375081133909,
"eval_runtime": 17.3729,
"eval_samples_per_second": 348.473,
"step": 22640
},
{
"epoch": 142.0,
"eval_loss": 0.07787012308835983,
"eval_micro_f1": 0.618585297708811,
"eval_runtime": 17.2176,
"eval_samples_per_second": 351.616,
"step": 22720
},
{
"epoch": 142.5,
"eval_loss": 0.07844871282577515,
"eval_micro_f1": 0.6205962054700354,
"eval_runtime": 17.0413,
"eval_samples_per_second": 355.255,
"step": 22800
},
{
"epoch": 143.0,
"eval_loss": 0.07767446339130402,
"eval_micro_f1": 0.6273684205667732,
"eval_runtime": 17.5702,
"eval_samples_per_second": 344.56,
"step": 22880
},
{
"epoch": 143.5,
"eval_loss": 0.07706889510154724,
"eval_micro_f1": 0.6291208786310191,
"eval_runtime": 16.5126,
"eval_samples_per_second": 366.629,
"step": 22960
},
{
"epoch": 143.75,
"learning_rate": 5.208333333333334e-06,
"loss": 0.0001,
"step": 23000
},
{
"epoch": 144.0,
"eval_loss": 0.07562633603811264,
"eval_micro_f1": 0.6320109434219001,
"eval_runtime": 17.6321,
"eval_samples_per_second": 343.352,
"step": 23040
},
{
"epoch": 144.5,
"eval_loss": 0.07655955851078033,
"eval_micro_f1": 0.6327223348782599,
"eval_runtime": 16.6452,
"eval_samples_per_second": 363.709,
"step": 23120
},
{
"epoch": 145.0,
"eval_loss": 0.07613572478294373,
"eval_micro_f1": 0.6373477667607966,
"eval_runtime": 16.6065,
"eval_samples_per_second": 364.556,
"step": 23200
},
{
"epoch": 145.5,
"eval_loss": 0.07516056299209595,
"eval_micro_f1": 0.6387362632463904,
"eval_runtime": 17.331,
"eval_samples_per_second": 349.317,
"step": 23280
},
{
"epoch": 146.0,
"eval_loss": 0.07722523808479309,
"eval_micro_f1": 0.6294765835326499,
"eval_runtime": 17.1097,
"eval_samples_per_second": 353.834,
"step": 23360
},
{
"epoch": 146.5,
"eval_loss": 0.07731063663959503,
"eval_micro_f1": 0.6278272784679865,
"eval_runtime": 16.313,
"eval_samples_per_second": 371.116,
"step": 23440
},
{
"epoch": 146.88,
"learning_rate": 5.104166666666667e-06,
"loss": 0.0001,
"step": 23500
},
{
"epoch": 147.0,
"eval_loss": 0.07477465271949768,
"eval_micro_f1": 0.6232179221152042,
"eval_runtime": 17.1005,
"eval_samples_per_second": 354.025,
"step": 23520
},
{
"epoch": 147.5,
"eval_loss": 0.07632264494895935,
"eval_micro_f1": 0.6134275613530827,
"eval_runtime": 16.5289,
"eval_samples_per_second": 366.268,
"step": 23600
},
{
"epoch": 148.0,
"eval_loss": 0.07872546464204788,
"eval_micro_f1": 0.6241426606896138,
"eval_runtime": 17.1939,
"eval_samples_per_second": 352.101,
"step": 23680
},
{
"epoch": 148.5,
"eval_loss": 0.08146443963050842,
"eval_micro_f1": 0.623789764379954,
"eval_runtime": 19.3474,
"eval_samples_per_second": 312.91,
"step": 23760
},
{
"epoch": 149.0,
"eval_loss": 0.07886698096990585,
"eval_micro_f1": 0.6279069762536431,
"eval_runtime": 16.4532,
"eval_samples_per_second": 367.954,
"step": 23840
},
{
"epoch": 149.5,
"eval_loss": 0.07898648083209991,
"eval_micro_f1": 0.6153846148933256,
"eval_runtime": 17.1382,
"eval_samples_per_second": 353.245,
"step": 23920
},
{
"epoch": 150.0,
"learning_rate": 5e-06,
"loss": 0.0001,
"step": 24000
},
{
"epoch": 150.0,
"eval_loss": 0.07938884198665619,
"eval_micro_f1": 0.6178299926003852,
"eval_runtime": 17.3297,
"eval_samples_per_second": 349.342,
"step": 24000
},
{
"epoch": 150.5,
"eval_loss": 0.07822619378566742,
"eval_micro_f1": 0.6178299926003852,
"eval_runtime": 19.2245,
"eval_samples_per_second": 314.911,
"step": 24080
},
{
"epoch": 151.0,
"eval_loss": 0.08154425024986267,
"eval_micro_f1": 0.6164574611586593,
"eval_runtime": 17.0925,
"eval_samples_per_second": 354.191,
"step": 24160
},
{
"epoch": 151.5,
"eval_loss": 0.0790754184126854,
"eval_micro_f1": 0.6079891667387654,
"eval_runtime": 19.527,
"eval_samples_per_second": 310.032,
"step": 24240
},
{
"epoch": 152.0,
"eval_loss": 0.07897268980741501,
"eval_micro_f1": 0.6110344822694982,
"eval_runtime": 16.4455,
"eval_samples_per_second": 368.125,
"step": 24320
},
{
"epoch": 152.5,
"eval_loss": 0.07881367951631546,
"eval_micro_f1": 0.615803814222713,
"eval_runtime": 16.4867,
"eval_samples_per_second": 367.206,
"step": 24400
},
{
"epoch": 153.0,
"eval_loss": 0.07816250622272491,
"eval_micro_f1": 0.6115591392917696,
"eval_runtime": 18.3925,
"eval_samples_per_second": 329.157,
"step": 24480
},
{
"epoch": 153.12,
"learning_rate": 4.895833333333333e-06,
"loss": 0.0001,
"step": 24500
},
{
"epoch": 153.5,
"eval_loss": 0.07881301641464233,
"eval_micro_f1": 0.6124401908969266,
"eval_runtime": 19.513,
"eval_samples_per_second": 310.254,
"step": 24560
},
{
"epoch": 154.0,
"eval_loss": 0.07897321879863739,
"eval_micro_f1": 0.6105407250400516,
"eval_runtime": 16.7633,
"eval_samples_per_second": 361.147,
"step": 24640
},
{
"epoch": 154.5,
"eval_loss": 0.08134573698043823,
"eval_micro_f1": 0.6099789172937915,
"eval_runtime": 16.9319,
"eval_samples_per_second": 357.55,
"step": 24720
},
{
"epoch": 155.0,
"eval_loss": 0.07890238612890244,
"eval_micro_f1": 0.6219765026211121,
"eval_runtime": 16.9019,
"eval_samples_per_second": 358.184,
"step": 24800
},
{
"epoch": 155.5,
"eval_loss": 0.08068861812353134,
"eval_micro_f1": 0.6214532867087109,
"eval_runtime": 16.7215,
"eval_samples_per_second": 362.05,
"step": 24880
},
{
"epoch": 156.0,
"eval_loss": 0.0799139142036438,
"eval_micro_f1": 0.6122168835182832,
"eval_runtime": 17.7552,
"eval_samples_per_second": 340.97,
"step": 24960
},
{
"epoch": 156.25,
"learning_rate": 4.791666666666668e-06,
"loss": 0.0001,
"step": 25000
},
{
"epoch": 156.5,
"eval_loss": 0.08100180327892303,
"eval_micro_f1": 0.6159169545287877,
"eval_runtime": 16.9815,
"eval_samples_per_second": 356.505,
"step": 25040
},
{
"epoch": 157.0,
"eval_loss": 0.08270429819822311,
"eval_micro_f1": 0.6144156748110091,
"eval_runtime": 16.9781,
"eval_samples_per_second": 356.578,
"step": 25120
},
{
"epoch": 157.5,
"eval_loss": 0.08458416163921356,
"eval_micro_f1": 0.6188153305232288,
"eval_runtime": 16.8677,
"eval_samples_per_second": 358.912,
"step": 25200
},
{
"epoch": 158.0,
"eval_loss": 0.08306228369474411,
"eval_micro_f1": 0.6108726747686906,
"eval_runtime": 17.0143,
"eval_samples_per_second": 355.819,
"step": 25280
},
{
"epoch": 158.5,
"eval_loss": 0.07792879641056061,
"eval_micro_f1": 0.6145479260890573,
"eval_runtime": 17.1198,
"eval_samples_per_second": 353.625,
"step": 25360
},
{
"epoch": 159.0,
"eval_loss": 0.0798240602016449,
"eval_micro_f1": 0.6190145727250363,
"eval_runtime": 17.3834,
"eval_samples_per_second": 348.263,
"step": 25440
},
{
"epoch": 159.38,
"learning_rate": 4.6875000000000004e-06,
"loss": 0.0001,
"step": 25500
},
{
"epoch": 159.5,
"eval_loss": 0.0795895904302597,
"eval_micro_f1": 0.6134969320242648,
"eval_runtime": 17.7618,
"eval_samples_per_second": 340.844,
"step": 25520
},
{
"epoch": 160.0,
"eval_loss": 0.08039452880620956,
"eval_micro_f1": 0.6166551956564147,
"eval_runtime": 16.8911,
"eval_samples_per_second": 358.414,
"step": 25600
},
{
"epoch": 160.5,
"eval_loss": 0.08161735534667969,
"eval_micro_f1": 0.6173853520078725,
"eval_runtime": 17.0226,
"eval_samples_per_second": 355.646,
"step": 25680
},
{
"epoch": 161.0,
"eval_loss": 0.08040950447320938,
"eval_micro_f1": 0.6034364256271305,
"eval_runtime": 16.8042,
"eval_samples_per_second": 360.268,
"step": 25760
},
{
"epoch": 161.5,
"eval_loss": 0.08206964284181595,
"eval_micro_f1": 0.6070921980979629,
"eval_runtime": 18.2849,
"eval_samples_per_second": 331.093,
"step": 25840
},
{
"epoch": 162.0,
"eval_loss": 0.08252940326929092,
"eval_micro_f1": 0.6099092807412495,
"eval_runtime": 17.421,
"eval_samples_per_second": 347.512,
"step": 25920
},
{
"epoch": 162.5,
"learning_rate": 4.583333333333333e-06,
"loss": 0.0001,
"step": 26000
},
{
"epoch": 162.5,
"eval_loss": 0.08051127195358276,
"eval_micro_f1": 0.6199312709879327,
"eval_runtime": 16.7717,
"eval_samples_per_second": 360.965,
"step": 26000
},
{
"epoch": 163.0,
"eval_loss": 0.07985124737024307,
"eval_micro_f1": 0.6199312709879327,
"eval_runtime": 17.4916,
"eval_samples_per_second": 346.109,
"step": 26080
},
{
"epoch": 163.5,
"eval_loss": 0.08263160288333893,
"eval_micro_f1": 0.6159217872226815,
"eval_runtime": 16.8384,
"eval_samples_per_second": 359.535,
"step": 26160
},
{
"epoch": 164.0,
"eval_loss": 0.08581520617008209,
"eval_micro_f1": 0.6096866092039593,
"eval_runtime": 17.6625,
"eval_samples_per_second": 342.76,
"step": 26240
},
{
"epoch": 164.5,
"eval_loss": 0.08564102649688721,
"eval_micro_f1": 0.614184396679513,
"eval_runtime": 16.802,
"eval_samples_per_second": 360.313,
"step": 26320
},
{
"epoch": 165.0,
"eval_loss": 0.07846783846616745,
"eval_micro_f1": 0.6127484573576576,
"eval_runtime": 16.7021,
"eval_samples_per_second": 362.469,
"step": 26400
},
{
"epoch": 165.5,
"eval_loss": 0.08020030707120895,
"eval_micro_f1": 0.6139986135103553,
"eval_runtime": 18.6177,
"eval_samples_per_second": 325.174,
"step": 26480
},
{
"epoch": 165.62,
"learning_rate": 4.479166666666667e-06,
"loss": 0.0001,
"step": 26500
},
{
"epoch": 166.0,
"eval_loss": 0.08084024488925934,
"eval_micro_f1": 0.6151704935974147,
"eval_runtime": 17.7299,
"eval_samples_per_second": 341.457,
"step": 26560
},
{
"epoch": 166.5,
"eval_loss": 0.08220770210027695,
"eval_micro_f1": 0.6150627610191912,
"eval_runtime": 17.6073,
"eval_samples_per_second": 343.836,
"step": 26640
},
{
"epoch": 167.0,
"eval_loss": 0.08183563500642776,
"eval_micro_f1": 0.6149506342119316,
"eval_runtime": 16.9098,
"eval_samples_per_second": 358.018,
"step": 26720
},
{
"epoch": 167.5,
"eval_loss": 0.08281593769788742,
"eval_micro_f1": 0.6145172651950846,
"eval_runtime": 19.3658,
"eval_samples_per_second": 312.613,
"step": 26800
},
{
"epoch": 168.0,
"eval_loss": 0.08229009807109833,
"eval_micro_f1": 0.615168538840144,
"eval_runtime": 16.7396,
"eval_samples_per_second": 361.657,
"step": 26880
},
{
"epoch": 168.5,
"eval_loss": 0.081607386469841,
"eval_micro_f1": 0.6166666661787885,
"eval_runtime": 16.948,
"eval_samples_per_second": 357.21,
"step": 26960
},
{
"epoch": 168.75,
"learning_rate": 4.3750000000000005e-06,
"loss": 0.0001,
"step": 27000
},
{
"epoch": 169.0,
"eval_loss": 0.07696817070245743,
"eval_micro_f1": 0.621492128188565,
"eval_runtime": 17.0604,
"eval_samples_per_second": 354.857,
"step": 27040
},
{
"epoch": 169.5,
"eval_loss": 0.07619831711053848,
"eval_micro_f1": 0.6228373697536917,
"eval_runtime": 16.7154,
"eval_samples_per_second": 362.181,
"step": 27120
},
{
"epoch": 170.0,
"eval_loss": 0.07810193300247192,
"eval_micro_f1": 0.6182074801081214,
"eval_runtime": 19.5579,
"eval_samples_per_second": 309.542,
"step": 27200
},
{
"epoch": 170.5,
"eval_loss": 0.07956741005182266,
"eval_micro_f1": 0.6195804190938725,
"eval_runtime": 20.8119,
"eval_samples_per_second": 290.891,
"step": 27280
},
{
"epoch": 171.0,
"eval_loss": 0.08011212944984436,
"eval_micro_f1": 0.6230661035933402,
"eval_runtime": 19.7079,
"eval_samples_per_second": 307.187,
"step": 27360
},
{
"epoch": 171.5,
"eval_loss": 0.07831978052854538,
"eval_micro_f1": 0.6230876212091743,
"eval_runtime": 17.2763,
"eval_samples_per_second": 350.423,
"step": 27440
},
{
"epoch": 171.88,
"learning_rate": 4.270833333333333e-06,
"loss": 0.0001,
"step": 27500
},
{
"epoch": 172.0,
"eval_loss": 0.07922139763832092,
"eval_micro_f1": 0.6233586726280209,
"eval_runtime": 17.7842,
"eval_samples_per_second": 340.414,
"step": 27520
},
{
"epoch": 172.5,
"eval_loss": 0.07859333604574203,
"eval_micro_f1": 0.6244841810784687,
"eval_runtime": 19.4471,
"eval_samples_per_second": 311.306,
"step": 27600
},
{
"epoch": 173.0,
"eval_loss": 0.08133268356323242,
"eval_micro_f1": 0.6205450728885764,
"eval_runtime": 16.7067,
"eval_samples_per_second": 362.37,
"step": 27680
},
{
"epoch": 173.5,
"eval_loss": 0.08039842545986176,
"eval_micro_f1": 0.6249999995121103,
"eval_runtime": 20.6917,
"eval_samples_per_second": 292.581,
"step": 27760
},
{
"epoch": 174.0,
"eval_loss": 0.08307138085365295,
"eval_micro_f1": 0.6105111586271481,
"eval_runtime": 17.0193,
"eval_samples_per_second": 355.713,
"step": 27840
},
{
"epoch": 174.5,
"eval_loss": 0.08071048557758331,
"eval_micro_f1": 0.6177935938232272,
"eval_runtime": 20.1141,
"eval_samples_per_second": 300.982,
"step": 27920
},
{
"epoch": 175.0,
"learning_rate": 4.166666666666667e-06,
"loss": 0.0001,
"step": 28000
},
{
"epoch": 175.0,
"eval_loss": 0.07760833203792572,
"eval_micro_f1": 0.631650749850075,
"eval_runtime": 21.5832,
"eval_samples_per_second": 280.495,
"step": 28000
},
{
"epoch": 175.5,
"eval_loss": 0.07824752479791641,
"eval_micro_f1": 0.622284512478127,
"eval_runtime": 16.9167,
"eval_samples_per_second": 357.871,
"step": 28080
},
{
"epoch": 176.0,
"eval_loss": 0.0806986466050148,
"eval_micro_f1": 0.6126510300783441,
"eval_runtime": 17.1532,
"eval_samples_per_second": 352.937,
"step": 28160
},
{
"epoch": 176.5,
"eval_loss": 0.07852751761674881,
"eval_micro_f1": 0.6265734260868697,
"eval_runtime": 16.8889,
"eval_samples_per_second": 358.461,
"step": 28240
},
{
"epoch": 177.0,
"eval_loss": 0.07842987775802612,
"eval_micro_f1": 0.6257839716382018,
"eval_runtime": 17.3617,
"eval_samples_per_second": 348.698,
"step": 28320
},
{
"epoch": 177.5,
"eval_loss": 0.07947345823049545,
"eval_micro_f1": 0.6273684205667732,
"eval_runtime": 16.71,
"eval_samples_per_second": 362.299,
"step": 28400
},
{
"epoch": 178.0,
"eval_loss": 0.07978292554616928,
"eval_micro_f1": 0.628330995306425,
"eval_runtime": 18.8157,
"eval_samples_per_second": 321.753,
"step": 28480
},
{
"epoch": 178.12,
"learning_rate": 4.0625000000000005e-06,
"loss": 0.0001,
"step": 28500
},
{
"epoch": 178.5,
"eval_loss": 0.0816904678940773,
"eval_micro_f1": 0.6196789946281864,
"eval_runtime": 16.9239,
"eval_samples_per_second": 357.719,
"step": 28560
},
{
"epoch": 179.0,
"eval_loss": 0.0790763571858406,
"eval_micro_f1": 0.6212534055033595,
"eval_runtime": 17.8676,
"eval_samples_per_second": 338.825,
"step": 28640
},
{
"epoch": 179.5,
"eval_loss": 0.08148709684610367,
"eval_micro_f1": 0.6248256619954676,
"eval_runtime": 18.0913,
"eval_samples_per_second": 334.636,
"step": 28720
},
{
"epoch": 180.0,
"eval_loss": 0.08251102268695831,
"eval_micro_f1": 0.6229739248145231,
"eval_runtime": 17.4372,
"eval_samples_per_second": 347.189,
"step": 28800
},
{
"epoch": 180.5,
"eval_loss": 0.08115926384925842,
"eval_micro_f1": 0.6292749653097288,
"eval_runtime": 17.0206,
"eval_samples_per_second": 355.687,
"step": 28880
},
{
"epoch": 181.0,
"eval_loss": 0.07920870929956436,
"eval_micro_f1": 0.6286490151226646,
"eval_runtime": 17.0815,
"eval_samples_per_second": 354.418,
"step": 28960
},
{
"epoch": 181.25,
"learning_rate": 3.958333333333333e-06,
"loss": 0.0001,
"step": 29000
},
{
"epoch": 181.5,
"eval_loss": 0.07930129021406174,
"eval_micro_f1": 0.6275579804094257,
"eval_runtime": 16.8454,
"eval_samples_per_second": 359.385,
"step": 29040
},
{
"epoch": 182.0,
"eval_loss": 0.0802033543586731,
"eval_micro_f1": 0.6293995854322988,
"eval_runtime": 18.5297,
"eval_samples_per_second": 326.718,
"step": 29120
},
{
"epoch": 182.5,
"eval_loss": 0.08131420612335205,
"eval_micro_f1": 0.6243016754908262,
"eval_runtime": 16.8653,
"eval_samples_per_second": 358.961,
"step": 29200
},
{
"epoch": 183.0,
"eval_loss": 0.08183193951845169,
"eval_micro_f1": 0.6251728902444057,
"eval_runtime": 16.4451,
"eval_samples_per_second": 368.135,
"step": 29280
},
{
"epoch": 183.5,
"eval_loss": 0.08073034882545471,
"eval_micro_f1": 0.6232179221152042,
"eval_runtime": 21.0303,
"eval_samples_per_second": 287.87,
"step": 29360
},
{
"epoch": 184.0,
"eval_loss": 0.08178406208753586,
"eval_micro_f1": 0.62785862737035,
"eval_runtime": 16.769,
"eval_samples_per_second": 361.024,
"step": 29440
},
{
"epoch": 184.38,
"learning_rate": 3.854166666666667e-06,
"loss": 0.0001,
"step": 29500
},
{
"epoch": 184.5,
"eval_loss": 0.08160873502492905,
"eval_micro_f1": 0.6314325447140305,
"eval_runtime": 16.6508,
"eval_samples_per_second": 363.586,
"step": 29520
},
{
"epoch": 185.0,
"eval_loss": 0.08086729794740677,
"eval_micro_f1": 0.6316516926694746,
"eval_runtime": 17.1614,
"eval_samples_per_second": 352.768,
"step": 29600
},
{
"epoch": 185.5,
"eval_loss": 0.08093345165252686,
"eval_micro_f1": 0.6313617601706187,
"eval_runtime": 16.4092,
"eval_samples_per_second": 368.939,
"step": 29680
},
{
"epoch": 186.0,
"eval_loss": 0.08275554329156876,
"eval_micro_f1": 0.6291666661787712,
"eval_runtime": 16.8004,
"eval_samples_per_second": 360.348,
"step": 29760
},
{
"epoch": 186.5,
"eval_loss": 0.08147411793470383,
"eval_micro_f1": 0.6223146218263522,
"eval_runtime": 16.775,
"eval_samples_per_second": 360.893,
"step": 29840
},
{
"epoch": 187.0,
"eval_loss": 0.08342599868774414,
"eval_micro_f1": 0.620786516368226,
"eval_runtime": 16.8517,
"eval_samples_per_second": 359.252,
"step": 29920
},
{
"epoch": 187.5,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0001,
"step": 30000
},
{
"epoch": 187.5,
"eval_loss": 0.08346762508153915,
"eval_micro_f1": 0.621602786969218,
"eval_runtime": 19.7994,
"eval_samples_per_second": 305.767,
"step": 30000
},
{
"epoch": 188.0,
"eval_loss": 0.08355218172073364,
"eval_micro_f1": 0.6259541979852625,
"eval_runtime": 20.8741,
"eval_samples_per_second": 290.025,
"step": 30080
},
{
"epoch": 188.5,
"eval_loss": 0.08347421884536743,
"eval_micro_f1": 0.6243902434152071,
"eval_runtime": 16.807,
"eval_samples_per_second": 360.207,
"step": 30160
},
{
"epoch": 189.0,
"eval_loss": 0.08183272927999496,
"eval_micro_f1": 0.6233586726280209,
"eval_runtime": 20.1242,
"eval_samples_per_second": 300.832,
"step": 30240
},
{
"epoch": 189.5,
"eval_loss": 0.08212146162986755,
"eval_micro_f1": 0.6229050274461355,
"eval_runtime": 17.2633,
"eval_samples_per_second": 350.685,
"step": 30320
},
{
"epoch": 190.0,
"eval_loss": 0.08236584812402725,
"eval_micro_f1": 0.6193458589418767,
"eval_runtime": 19.8917,
"eval_samples_per_second": 304.349,
"step": 30400
},
{
"epoch": 190.5,
"eval_loss": 0.07945527136325836,
"eval_micro_f1": 0.6205479447151717,
"eval_runtime": 17.0968,
"eval_samples_per_second": 354.101,
"step": 30480
},
{
"epoch": 190.62,
"learning_rate": 3.6458333333333333e-06,
"loss": 0.0001,
"step": 30500
},
{
"epoch": 191.0,
"eval_loss": 0.0807671919465065,
"eval_micro_f1": 0.6191135729188101,
"eval_runtime": 16.6821,
"eval_samples_per_second": 362.904,
"step": 30560
},
{
"epoch": 191.5,
"eval_loss": 0.08280323445796967,
"eval_micro_f1": 0.6209286204403526,
"eval_runtime": 16.3516,
"eval_samples_per_second": 370.239,
"step": 30640
},
{
"epoch": 192.0,
"eval_loss": 0.08444526046514511,
"eval_micro_f1": 0.6226282496901195,
"eval_runtime": 16.2894,
"eval_samples_per_second": 371.654,
"step": 30720
},
{
"epoch": 192.5,
"eval_loss": 0.08369226008653641,
"eval_micro_f1": 0.620979020492472,
"eval_runtime": 19.075,
"eval_samples_per_second": 317.379,
"step": 30800
},
{
"epoch": 193.0,
"eval_loss": 0.079885333776474,
"eval_micro_f1": 0.6240549823281332,
"eval_runtime": 17.7428,
"eval_samples_per_second": 341.209,
"step": 30880
},
{
"epoch": 193.5,
"eval_loss": 0.0790458619594574,
"eval_micro_f1": 0.6225895311910616,
"eval_runtime": 17.0644,
"eval_samples_per_second": 354.775,
"step": 30960
},
{
"epoch": 193.75,
"learning_rate": 3.5416666666666673e-06,
"loss": 0.0001,
"step": 31000
},
{
"epoch": 194.0,
"eval_loss": 0.08131275326013565,
"eval_micro_f1": 0.6230876212091743,
"eval_runtime": 19.5917,
"eval_samples_per_second": 309.008,
"step": 31040
},
{
"epoch": 194.5,
"eval_loss": 0.08145122975111008,
"eval_micro_f1": 0.6241331479168476,
"eval_runtime": 19.715,
"eval_samples_per_second": 307.076,
"step": 31120
},
{
"epoch": 195.0,
"eval_loss": 0.08212591707706451,
"eval_micro_f1": 0.623249299233613,
"eval_runtime": 18.2946,
"eval_samples_per_second": 330.917,
"step": 31200
},
{
"epoch": 195.5,
"eval_loss": 0.08119417726993561,
"eval_micro_f1": 0.6203059800408891,
"eval_runtime": 16.9942,
"eval_samples_per_second": 356.24,
"step": 31280
},
{
"epoch": 196.0,
"eval_loss": 0.08186686784029007,
"eval_micro_f1": 0.6164574611586593,
"eval_runtime": 17.3136,
"eval_samples_per_second": 349.668,
"step": 31360
},
{
"epoch": 196.5,
"eval_loss": 0.08255809545516968,
"eval_micro_f1": 0.6235212242863383,
"eval_runtime": 16.8171,
"eval_samples_per_second": 359.991,
"step": 31440
},
{
"epoch": 196.88,
"learning_rate": 3.4375e-06,
"loss": 0.0001,
"step": 31500
},
{
"epoch": 197.0,
"eval_loss": 0.08143466711044312,
"eval_micro_f1": 0.6198749126463681,
"eval_runtime": 15.8553,
"eval_samples_per_second": 381.829,
"step": 31520
},
{
"epoch": 197.5,
"eval_loss": 0.08111200481653214,
"eval_micro_f1": 0.6238030090853861,
"eval_runtime": 16.1908,
"eval_samples_per_second": 373.916,
"step": 31600
},
{
"epoch": 198.0,
"eval_loss": 0.08183975517749786,
"eval_micro_f1": 0.6227056419286111,
"eval_runtime": 16.2329,
"eval_samples_per_second": 372.946,
"step": 31680
},
{
"epoch": 198.5,
"eval_loss": 0.0829155445098877,
"eval_micro_f1": 0.6262068960625807,
"eval_runtime": 16.1708,
"eval_samples_per_second": 374.379,
"step": 31760
},
{
"epoch": 199.0,
"eval_loss": 0.08178234100341797,
"eval_micro_f1": 0.6244035441578559,
"eval_runtime": 16.2966,
"eval_samples_per_second": 371.489,
"step": 31840
},
{
"epoch": 199.5,
"eval_loss": 0.08157362788915634,
"eval_micro_f1": 0.6239782011436829,
"eval_runtime": 15.9387,
"eval_samples_per_second": 379.83,
"step": 31920
},
{
"epoch": 200.0,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.0001,
"step": 32000
},
{
"epoch": 200.0,
"eval_loss": 0.08296258747577667,
"eval_micro_f1": 0.630193905328767,
"eval_runtime": 15.9238,
"eval_samples_per_second": 380.186,
"step": 32000
},
{
"epoch": 200.5,
"eval_loss": 0.08385813236236572,
"eval_micro_f1": 0.6234309618559997,
"eval_runtime": 16.2289,
"eval_samples_per_second": 373.038,
"step": 32080
},
{
"epoch": 201.0,
"eval_loss": 0.08215318620204926,
"eval_micro_f1": 0.621602786969218,
"eval_runtime": 16.1528,
"eval_samples_per_second": 374.797,
"step": 32160
},
{
"epoch": 201.5,
"eval_loss": 0.08247260004281998,
"eval_micro_f1": 0.6216968006250317,
"eval_runtime": 16.1607,
"eval_samples_per_second": 374.612,
"step": 32240
},
{
"epoch": 202.0,
"eval_loss": 0.08089154213666916,
"eval_micro_f1": 0.6236559134853017,
"eval_runtime": 16.5905,
"eval_samples_per_second": 364.908,
"step": 32320
},
{
"epoch": 202.5,
"eval_loss": 0.08202090859413147,
"eval_micro_f1": 0.6254248805417957,
"eval_runtime": 16.0045,
"eval_samples_per_second": 378.27,
"step": 32400
},
{
"epoch": 203.0,
"eval_loss": 0.08320967853069305,
"eval_micro_f1": 0.6264564765488657,
"eval_runtime": 16.3576,
"eval_samples_per_second": 370.103,
"step": 32480
},
{
"epoch": 203.12,
"learning_rate": 3.229166666666667e-06,
"loss": 0.0001,
"step": 32500
},
{
"epoch": 203.5,
"eval_loss": 0.08348571509122849,
"eval_micro_f1": 0.6262068960625807,
"eval_runtime": 16.3225,
"eval_samples_per_second": 370.9,
"step": 32560
},
{
"epoch": 204.0,
"eval_loss": 0.085007444024086,
"eval_micro_f1": 0.6229739248145231,
"eval_runtime": 17.3683,
"eval_samples_per_second": 348.566,
"step": 32640
},
{
"epoch": 204.5,
"eval_loss": 0.08498197048902512,
"eval_micro_f1": 0.6304044625533399,
"eval_runtime": 16.0089,
"eval_samples_per_second": 378.165,
"step": 32720
},
{
"epoch": 205.0,
"eval_loss": 0.08476021885871887,
"eval_micro_f1": 0.618485058581047,
"eval_runtime": 16.0693,
"eval_samples_per_second": 376.743,
"step": 32800
},
{
"epoch": 205.5,
"eval_loss": 0.08475890010595322,
"eval_micro_f1": 0.6239554312675104,
"eval_runtime": 16.0082,
"eval_samples_per_second": 378.181,
"step": 32880
},
{
"epoch": 206.0,
"eval_loss": 0.08441813290119171,
"eval_micro_f1": 0.6240444748423317,
"eval_runtime": 16.1564,
"eval_samples_per_second": 374.713,
"step": 32960
},
{
"epoch": 206.25,
"learning_rate": 3.125e-06,
"loss": 0.0001,
"step": 33000
},
{
"epoch": 206.5,
"eval_loss": 0.08344842493534088,
"eval_micro_f1": 0.6261230126418388,
"eval_runtime": 16.0402,
"eval_samples_per_second": 377.427,
"step": 33040
},
{
"epoch": 207.0,
"eval_loss": 0.08337745815515518,
"eval_micro_f1": 0.6273421230373077,
"eval_runtime": 16.4488,
"eval_samples_per_second": 368.052,
"step": 33120
},
{
"epoch": 207.5,
"eval_loss": 0.0838770791888237,
"eval_micro_f1": 0.6275862064074065,
"eval_runtime": 15.8906,
"eval_samples_per_second": 380.98,
"step": 33200
},
{
"epoch": 208.0,
"eval_loss": 0.08224862813949585,
"eval_micro_f1": 0.6322930795624382,
"eval_runtime": 17.2585,
"eval_samples_per_second": 350.784,
"step": 33280
},
{
"epoch": 208.5,
"eval_loss": 0.08270945399999619,
"eval_micro_f1": 0.6312201767413504,
"eval_runtime": 19.1341,
"eval_samples_per_second": 316.399,
"step": 33360
},
{
"epoch": 209.0,
"eval_loss": 0.08589319884777069,
"eval_micro_f1": 0.6134275613530827,
"eval_runtime": 18.7603,
"eval_samples_per_second": 322.702,
"step": 33440
},
{
"epoch": 209.38,
"learning_rate": 3.0208333333333334e-06,
"loss": 0.0001,
"step": 33500
},
{
"epoch": 209.5,
"eval_loss": 0.08514928817749023,
"eval_micro_f1": 0.6129943497979627,
"eval_runtime": 15.9643,
"eval_samples_per_second": 379.222,
"step": 33520
},
{
"epoch": 210.0,
"eval_loss": 0.08509651571512222,
"eval_micro_f1": 0.62116991594718,
"eval_runtime": 16.0556,
"eval_samples_per_second": 377.065,
"step": 33600
},
{
"epoch": 210.5,
"eval_loss": 0.08311175554990768,
"eval_micro_f1": 0.6264564765488657,
"eval_runtime": 16.0639,
"eval_samples_per_second": 376.871,
"step": 33680
},
{
"epoch": 211.0,
"eval_loss": 0.07980132102966309,
"eval_micro_f1": 0.6267652987671518,
"eval_runtime": 16.0915,
"eval_samples_per_second": 376.223,
"step": 33760
},
{
"epoch": 211.5,
"eval_loss": 0.08052228391170502,
"eval_micro_f1": 0.630727762310409,
"eval_runtime": 16.5278,
"eval_samples_per_second": 366.293,
"step": 33840
},
{
"epoch": 212.0,
"eval_loss": 0.08136559277772903,
"eval_micro_f1": 0.6277173908127252,
"eval_runtime": 19.3341,
"eval_samples_per_second": 313.125,
"step": 33920
},
{
"epoch": 212.5,
"learning_rate": 2.916666666666667e-06,
"loss": 0.0001,
"step": 34000
},
{
"epoch": 212.5,
"eval_loss": 0.08123795688152313,
"eval_micro_f1": 0.6227951148406057,
"eval_runtime": 17.4815,
"eval_samples_per_second": 346.308,
"step": 34000
},
{
"epoch": 213.0,
"eval_loss": 0.08348256349563599,
"eval_micro_f1": 0.62637362588377,
"eval_runtime": 16.8604,
"eval_samples_per_second": 359.066,
"step": 34080
},
{
"epoch": 213.5,
"eval_loss": 0.08409759402275085,
"eval_micro_f1": 0.6225255967787572,
"eval_runtime": 16.3158,
"eval_samples_per_second": 371.051,
"step": 34160
},
{
"epoch": 214.0,
"eval_loss": 0.08258362859487534,
"eval_micro_f1": 0.6260162596705701,
"eval_runtime": 16.2453,
"eval_samples_per_second": 372.661,
"step": 34240
},
{
"epoch": 214.5,
"eval_loss": 0.08510701358318329,
"eval_micro_f1": 0.6155988853065192,
"eval_runtime": 17.2937,
"eval_samples_per_second": 350.069,
"step": 34320
},
{
"epoch": 215.0,
"eval_loss": 0.08370614051818848,
"eval_micro_f1": 0.6256055358436531,
"eval_runtime": 16.0313,
"eval_samples_per_second": 377.636,
"step": 34400
},
{
"epoch": 215.5,
"eval_loss": 0.08299410343170166,
"eval_micro_f1": 0.6199312709879327,
"eval_runtime": 15.9807,
"eval_samples_per_second": 378.833,
"step": 34480
},
{
"epoch": 215.62,
"learning_rate": 2.8125e-06,
"loss": 0.0001,
"step": 34500
},
{
"epoch": 216.0,
"eval_loss": 0.08349087834358215,
"eval_micro_f1": 0.6172839501272088,
"eval_runtime": 16.3001,
"eval_samples_per_second": 371.408,
"step": 34560
},
{
"epoch": 216.5,
"eval_loss": 0.08390067517757416,
"eval_micro_f1": 0.6262904330961814,
"eval_runtime": 16.2159,
"eval_samples_per_second": 373.337,
"step": 34640
},
{
"epoch": 217.0,
"eval_loss": 0.08320938050746918,
"eval_micro_f1": 0.6223440707915033,
"eval_runtime": 16.3877,
"eval_samples_per_second": 369.423,
"step": 34720
},
{
"epoch": 217.5,
"eval_loss": 0.08388946205377579,
"eval_micro_f1": 0.6253443521276969,
"eval_runtime": 16.076,
"eval_samples_per_second": 376.586,
"step": 34800
},
{
"epoch": 218.0,
"eval_loss": 0.08333836495876312,
"eval_micro_f1": 0.6259437194825745,
"eval_runtime": 16.3316,
"eval_samples_per_second": 370.692,
"step": 34880
},
{
"epoch": 218.5,
"eval_loss": 0.08376310020685196,
"eval_micro_f1": 0.6270491798371051,
"eval_runtime": 15.9402,
"eval_samples_per_second": 379.794,
"step": 34960
},
{
"epoch": 218.75,
"learning_rate": 2.7083333333333334e-06,
"loss": 0.0001,
"step": 35000
},
{
"epoch": 219.0,
"eval_loss": 0.08345824480056763,
"eval_micro_f1": 0.6240652612352036,
"eval_runtime": 16.1423,
"eval_samples_per_second": 375.039,
"step": 35040
},
{
"epoch": 219.5,
"eval_loss": 0.08312048017978668,
"eval_micro_f1": 0.623641303856209,
"eval_runtime": 16.0212,
"eval_samples_per_second": 377.874,
"step": 35120
},
{
"epoch": 220.0,
"eval_loss": 0.0848860889673233,
"eval_micro_f1": 0.6231086652600387,
"eval_runtime": 16.036,
"eval_samples_per_second": 377.526,
"step": 35200
},
{
"epoch": 220.5,
"eval_loss": 0.08470774441957474,
"eval_micro_f1": 0.6170648459255222,
"eval_runtime": 15.9109,
"eval_samples_per_second": 380.495,
"step": 35280
},
{
"epoch": 221.0,
"eval_loss": 0.08581811934709549,
"eval_micro_f1": 0.6088765598447466,
"eval_runtime": 15.9846,
"eval_samples_per_second": 378.739,
"step": 35360
},
{
"epoch": 221.5,
"eval_loss": 0.08372768014669418,
"eval_micro_f1": 0.6098052379217769,
"eval_runtime": 16.048,
"eval_samples_per_second": 377.244,
"step": 35440
},
{
"epoch": 221.88,
"learning_rate": 2.604166666666667e-06,
"loss": 0.0001,
"step": 35500
},
{
"epoch": 222.0,
"eval_loss": 0.08530912548303604,
"eval_micro_f1": 0.6112637357739007,
"eval_runtime": 16.2383,
"eval_samples_per_second": 372.823,
"step": 35520
},
{
"epoch": 222.5,
"eval_loss": 0.08453893661499023,
"eval_micro_f1": 0.6149584482650763,
"eval_runtime": 16.183,
"eval_samples_per_second": 374.097,
"step": 35600
},
{
"epoch": 223.0,
"eval_loss": 0.08551745116710663,
"eval_micro_f1": 0.611149345690834,
"eval_runtime": 17.3798,
"eval_samples_per_second": 348.334,
"step": 35680
},
{
"epoch": 223.5,
"eval_loss": 0.08507832139730453,
"eval_micro_f1": 0.6150656525865673,
"eval_runtime": 16.2586,
"eval_samples_per_second": 372.356,
"step": 35760
},
{
"epoch": 224.0,
"eval_loss": 0.08530396968126297,
"eval_micro_f1": 0.6146408834890169,
"eval_runtime": 15.8464,
"eval_samples_per_second": 382.042,
"step": 35840
},
{
"epoch": 224.5,
"eval_loss": 0.08577084541320801,
"eval_micro_f1": 0.6186851206187493,
"eval_runtime": 17.7107,
"eval_samples_per_second": 341.827,
"step": 35920
},
{
"epoch": 225.0,
"learning_rate": 2.5e-06,
"loss": 0.0001,
"step": 36000
},
{
"epoch": 225.0,
"eval_loss": 0.08716136962175369,
"eval_micro_f1": 0.6173184352673722,
"eval_runtime": 15.9338,
"eval_samples_per_second": 379.947,
"step": 36000
},
{
"epoch": 225.5,
"eval_loss": 0.08573056757450104,
"eval_micro_f1": 0.6191474488494448,
"eval_runtime": 16.5077,
"eval_samples_per_second": 366.737,
"step": 36080
},
{
"epoch": 226.0,
"eval_loss": 0.08673667162656784,
"eval_micro_f1": 0.6191474488494448,
"eval_runtime": 16.4756,
"eval_samples_per_second": 367.453,
"step": 36160
},
{
"epoch": 226.5,
"eval_loss": 0.08662193268537521,
"eval_micro_f1": 0.6214135754408104,
"eval_runtime": 16.3997,
"eval_samples_per_second": 369.153,
"step": 36240
},
{
"epoch": 227.0,
"eval_loss": 0.0869198590517044,
"eval_micro_f1": 0.618181817695273,
"eval_runtime": 16.1208,
"eval_samples_per_second": 375.541,
"step": 36320
},
{
"epoch": 227.5,
"eval_loss": 0.08756957203149796,
"eval_micro_f1": 0.6191474488494448,
"eval_runtime": 17.272,
"eval_samples_per_second": 350.509,
"step": 36400
},
{
"epoch": 228.0,
"eval_loss": 0.08506962656974792,
"eval_micro_f1": 0.6247436768846063,
"eval_runtime": 15.9837,
"eval_samples_per_second": 378.761,
"step": 36480
},
{
"epoch": 228.12,
"learning_rate": 2.395833333333334e-06,
"loss": 0.0001,
"step": 36500
},
{
"epoch": 228.5,
"eval_loss": 0.08585916459560394,
"eval_micro_f1": 0.6285320463749642,
"eval_runtime": 16.2524,
"eval_samples_per_second": 372.5,
"step": 36560
},
{
"epoch": 229.0,
"eval_loss": 0.08489272743463516,
"eval_micro_f1": 0.6299104061268576,
"eval_runtime": 15.9642,
"eval_samples_per_second": 379.224,
"step": 36640
},
{
"epoch": 229.5,
"eval_loss": 0.08417373150587082,
"eval_micro_f1": 0.6303448270970577,
"eval_runtime": 18.6647,
"eval_samples_per_second": 324.355,
"step": 36720
},
{
"epoch": 230.0,
"eval_loss": 0.08540572226047516,
"eval_micro_f1": 0.6303448270970577,
"eval_runtime": 18.5709,
"eval_samples_per_second": 325.994,
"step": 36800
},
{
"epoch": 230.5,
"eval_loss": 0.08537723124027252,
"eval_micro_f1": 0.6291208786310191,
"eval_runtime": 15.8517,
"eval_samples_per_second": 381.914,
"step": 36880
},
{
"epoch": 231.0,
"eval_loss": 0.08588951826095581,
"eval_micro_f1": 0.6270718227155192,
"eval_runtime": 18.9345,
"eval_samples_per_second": 319.733,
"step": 36960
},
{
"epoch": 231.25,
"learning_rate": 2.2916666666666666e-06,
"loss": 0.0001,
"step": 37000
},
{
"epoch": 231.5,
"eval_loss": 0.08617712557315826,
"eval_micro_f1": 0.6275862064074065,
"eval_runtime": 16.1485,
"eval_samples_per_second": 374.895,
"step": 37040
},
{
"epoch": 232.0,
"eval_loss": 0.08601192384958267,
"eval_micro_f1": 0.629009762413872,
"eval_runtime": 16.5662,
"eval_samples_per_second": 365.443,
"step": 37120
},
{
"epoch": 232.5,
"eval_loss": 0.08504713326692581,
"eval_micro_f1": 0.6309192195683363,
"eval_runtime": 18.6896,
"eval_samples_per_second": 323.923,
"step": 37200
},
{
"epoch": 233.0,
"eval_loss": 0.08586889505386353,
"eval_micro_f1": 0.6340097965744527,
"eval_runtime": 16.3152,
"eval_samples_per_second": 371.065,
"step": 37280
},
{
"epoch": 233.5,
"eval_loss": 0.08513804525136948,
"eval_micro_f1": 0.6286509035457452,
"eval_runtime": 16.7154,
"eval_samples_per_second": 362.181,
"step": 37360
},
{
"epoch": 234.0,
"eval_loss": 0.08490224182605743,
"eval_micro_f1": 0.6321601099319498,
"eval_runtime": 16.3708,
"eval_samples_per_second": 369.805,
"step": 37440
},
{
"epoch": 234.38,
"learning_rate": 2.1875000000000002e-06,
"loss": 0.0001,
"step": 37500
},
{
"epoch": 234.5,
"eval_loss": 0.0840383768081665,
"eval_micro_f1": 0.622009568887344,
"eval_runtime": 18.6633,
"eval_samples_per_second": 324.379,
"step": 37520
},
{
"epoch": 235.0,
"eval_loss": 0.08362243324518204,
"eval_micro_f1": 0.6294765835326499,
"eval_runtime": 16.1684,
"eval_samples_per_second": 374.434,
"step": 37600
},
{
"epoch": 235.5,
"eval_loss": 0.08382296562194824,
"eval_micro_f1": 0.631939684225349,
"eval_runtime": 18.5906,
"eval_samples_per_second": 325.649,
"step": 37680
},
{
"epoch": 236.0,
"eval_loss": 0.08526131510734558,
"eval_micro_f1": 0.6285320463749642,
"eval_runtime": 18.6,
"eval_samples_per_second": 325.483,
"step": 37760
},
{
"epoch": 236.5,
"eval_loss": 0.08496516942977905,
"eval_micro_f1": 0.6229281763066852,
"eval_runtime": 20.3397,
"eval_samples_per_second": 297.645,
"step": 37840
},
{
"epoch": 237.0,
"eval_loss": 0.0855923593044281,
"eval_micro_f1": 0.6269896188886339,
"eval_runtime": 16.0442,
"eval_samples_per_second": 377.333,
"step": 37920
},
{
"epoch": 237.5,
"learning_rate": 2.0833333333333334e-06,
"loss": 0.0001,
"step": 38000
},
{
"epoch": 237.5,
"eval_loss": 0.08599404990673065,
"eval_micro_f1": 0.6297577849785956,
"eval_runtime": 16.2053,
"eval_samples_per_second": 373.582,
"step": 38000
},
{
"epoch": 238.0,
"eval_loss": 0.08566141873598099,
"eval_micro_f1": 0.6263888884009973,
"eval_runtime": 16.033,
"eval_samples_per_second": 377.596,
"step": 38080
},
{
"epoch": 238.5,
"eval_loss": 0.08613350987434387,
"eval_micro_f1": 0.6273421230373077,
"eval_runtime": 17.1384,
"eval_samples_per_second": 353.242,
"step": 38160
},
{
"epoch": 239.0,
"eval_loss": 0.08556976914405823,
"eval_micro_f1": 0.628730048089353,
"eval_runtime": 16.4717,
"eval_samples_per_second": 367.539,
"step": 38240
},
{
"epoch": 239.5,
"eval_loss": 0.08288603276014328,
"eval_micro_f1": 0.6247491633857716,
"eval_runtime": 16.0945,
"eval_samples_per_second": 376.154,
"step": 38320
},
{
"epoch": 240.0,
"eval_loss": 0.0845007672905922,
"eval_micro_f1": 0.6240549823281332,
"eval_runtime": 16.1929,
"eval_samples_per_second": 373.868,
"step": 38400
},
{
"epoch": 240.5,
"eval_loss": 0.08415930718183517,
"eval_micro_f1": 0.6268861449145756,
"eval_runtime": 16.1729,
"eval_samples_per_second": 374.33,
"step": 38480
},
{
"epoch": 240.62,
"learning_rate": 1.9791666666666666e-06,
"loss": 0.0001,
"step": 38500
},
{
"epoch": 241.0,
"eval_loss": 0.08481507748365402,
"eval_micro_f1": 0.6299104061268576,
"eval_runtime": 16.4943,
"eval_samples_per_second": 367.037,
"step": 38560
},
{
"epoch": 241.5,
"eval_loss": 0.08481340855360031,
"eval_micro_f1": 0.6294765835326499,
"eval_runtime": 16.3732,
"eval_samples_per_second": 369.751,
"step": 38640
},
{
"epoch": 242.0,
"eval_loss": 0.08480625599622726,
"eval_micro_f1": 0.6290433580789718,
"eval_runtime": 16.1989,
"eval_samples_per_second": 373.73,
"step": 38720
},
{
"epoch": 242.5,
"eval_loss": 0.08580206334590912,
"eval_micro_f1": 0.6311418680235764,
"eval_runtime": 17.3074,
"eval_samples_per_second": 349.792,
"step": 38800
},
{
"epoch": 243.0,
"eval_loss": 0.08505971729755402,
"eval_micro_f1": 0.6313617601706187,
"eval_runtime": 16.0669,
"eval_samples_per_second": 376.798,
"step": 38880
},
{
"epoch": 243.5,
"eval_loss": 0.08133690059185028,
"eval_micro_f1": 0.6298788689551688,
"eval_runtime": 16.0293,
"eval_samples_per_second": 377.684,
"step": 38960
},
{
"epoch": 243.75,
"learning_rate": 1.8750000000000003e-06,
"loss": 0.0001,
"step": 39000
},
{
"epoch": 244.0,
"eval_loss": 0.08608271926641464,
"eval_micro_f1": 0.6132952103830664,
"eval_runtime": 16.3903,
"eval_samples_per_second": 369.364,
"step": 39040
},
{
"epoch": 244.5,
"eval_loss": 0.08715465664863586,
"eval_micro_f1": 0.613733905097728,
"eval_runtime": 16.8264,
"eval_samples_per_second": 359.792,
"step": 39120
},
{
"epoch": 245.0,
"eval_loss": 0.08673280477523804,
"eval_micro_f1": 0.6119828811153885,
"eval_runtime": 17.5788,
"eval_samples_per_second": 344.393,
"step": 39200
},
{
"epoch": 245.5,
"eval_loss": 0.08807853609323502,
"eval_micro_f1": 0.6132556440967445,
"eval_runtime": 16.1687,
"eval_samples_per_second": 374.427,
"step": 39280
},
{
"epoch": 246.0,
"eval_loss": 0.0873696580529213,
"eval_micro_f1": 0.6095790996670128,
"eval_runtime": 16.0779,
"eval_samples_per_second": 376.543,
"step": 39360
},
{
"epoch": 246.5,
"eval_loss": 0.08759798109531403,
"eval_micro_f1": 0.6101449270577336,
"eval_runtime": 16.3888,
"eval_samples_per_second": 369.398,
"step": 39440
},
{
"epoch": 246.88,
"learning_rate": 1.7708333333333337e-06,
"loss": 0.0001,
"step": 39500
},
{
"epoch": 247.0,
"eval_loss": 0.08361474424600601,
"eval_micro_f1": 0.6220971142226766,
"eval_runtime": 16.0633,
"eval_samples_per_second": 376.883,
"step": 39520
},
{
"epoch": 247.5,
"eval_loss": 0.08224516361951828,
"eval_micro_f1": 0.6296809981248843,
"eval_runtime": 16.1887,
"eval_samples_per_second": 373.966,
"step": 39600
},
{
"epoch": 248.0,
"eval_loss": 0.08218865841627121,
"eval_micro_f1": 0.6297577849785956,
"eval_runtime": 15.8562,
"eval_samples_per_second": 381.806,
"step": 39680
},
{
"epoch": 248.5,
"eval_loss": 0.08233033865690231,
"eval_micro_f1": 0.629322267837761,
"eval_runtime": 15.9428,
"eval_samples_per_second": 379.732,
"step": 39760
},
{
"epoch": 249.0,
"eval_loss": 0.08230016380548477,
"eval_micro_f1": 0.6297577849785956,
"eval_runtime": 15.8238,
"eval_samples_per_second": 382.589,
"step": 39840
},
{
"epoch": 249.5,
"eval_loss": 0.08239591121673584,
"eval_micro_f1": 0.6292446287563495,
"eval_runtime": 16.5744,
"eval_samples_per_second": 365.263,
"step": 39920
},
{
"epoch": 250.0,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.0001,
"step": 40000
},
{
"epoch": 250.0,
"eval_loss": 0.08268050849437714,
"eval_micro_f1": 0.6301179731413983,
"eval_runtime": 16.1232,
"eval_samples_per_second": 375.485,
"step": 40000
},
{
"epoch": 250.5,
"eval_loss": 0.08247067779302597,
"eval_micro_f1": 0.6269896188886339,
"eval_runtime": 18.5371,
"eval_samples_per_second": 326.588,
"step": 40080
},
{
"epoch": 251.0,
"eval_loss": 0.08313719928264618,
"eval_micro_f1": 0.6323835992342589,
"eval_runtime": 15.8329,
"eval_samples_per_second": 382.369,
"step": 40160
},
{
"epoch": 251.5,
"eval_loss": 0.0830114334821701,
"eval_micro_f1": 0.6279391419733092,
"eval_runtime": 16.1965,
"eval_samples_per_second": 373.784,
"step": 40240
},
{
"epoch": 252.0,
"eval_loss": 0.08285050094127655,
"eval_micro_f1": 0.628730048089353,
"eval_runtime": 15.7641,
"eval_samples_per_second": 384.038,
"step": 40320
},
{
"epoch": 252.5,
"eval_loss": 0.08274269104003906,
"eval_micro_f1": 0.6301179731413983,
"eval_runtime": 18.9588,
"eval_samples_per_second": 319.323,
"step": 40400
},
{
"epoch": 253.0,
"eval_loss": 0.0831095352768898,
"eval_micro_f1": 0.6269070730208659,
"eval_runtime": 19.1662,
"eval_samples_per_second": 315.868,
"step": 40480
},
{
"epoch": 253.12,
"learning_rate": 1.5625e-06,
"loss": 0.0001,
"step": 40500
},
{
"epoch": 253.5,
"eval_loss": 0.08287804573774338,
"eval_micro_f1": 0.6268041232216002,
"eval_runtime": 16.088,
"eval_samples_per_second": 376.306,
"step": 40560
},
{
"epoch": 254.0,
"eval_loss": 0.08318732678890228,
"eval_micro_f1": 0.6284530381851305,
"eval_runtime": 17.645,
"eval_samples_per_second": 343.101,
"step": 40640
},
{
"epoch": 254.5,
"eval_loss": 0.08398754149675369,
"eval_micro_f1": 0.6285714280841909,
"eval_runtime": 16.3633,
"eval_samples_per_second": 369.975,
"step": 40720
},
{
"epoch": 255.0,
"eval_loss": 0.08324674516916275,
"eval_micro_f1": 0.6267409465878407,
"eval_runtime": 16.0191,
"eval_samples_per_second": 377.925,
"step": 40800
},
{
"epoch": 255.5,
"eval_loss": 0.08338189125061035,
"eval_micro_f1": 0.6276965896308003,
"eval_runtime": 20.0674,
"eval_samples_per_second": 301.683,
"step": 40880
},
{
"epoch": 256.0,
"eval_loss": 0.08291594684123993,
"eval_micro_f1": 0.6267217625960145,
"eval_runtime": 16.404,
"eval_samples_per_second": 369.055,
"step": 40960
},
{
"epoch": 256.25,
"learning_rate": 1.4583333333333335e-06,
"loss": 0.0001,
"step": 41000
},
{
"epoch": 256.5,
"eval_loss": 0.08292824029922485,
"eval_micro_f1": 0.6254295527748666,
"eval_runtime": 18.8864,
"eval_samples_per_second": 320.548,
"step": 41040
},
{
"epoch": 257.0,
"eval_loss": 0.08325041830539703,
"eval_micro_f1": 0.6280193231824732,
"eval_runtime": 18.9164,
"eval_samples_per_second": 320.041,
"step": 41120
},
{
"epoch": 257.5,
"eval_loss": 0.08349461853504181,
"eval_micro_f1": 0.6288088637775224,
"eval_runtime": 17.5914,
"eval_samples_per_second": 344.146,
"step": 41200
},
{
"epoch": 258.0,
"eval_loss": 0.08327367901802063,
"eval_micro_f1": 0.629322267837761,
"eval_runtime": 16.1831,
"eval_samples_per_second": 374.093,
"step": 41280
},
{
"epoch": 258.5,
"eval_loss": 0.08393372595310211,
"eval_micro_f1": 0.6300417241298879,
"eval_runtime": 16.052,
"eval_samples_per_second": 377.149,
"step": 41360
},
{
"epoch": 259.0,
"eval_loss": 0.08352518826723099,
"eval_micro_f1": 0.6283737019336146,
"eval_runtime": 16.0409,
"eval_samples_per_second": 377.411,
"step": 41440
},
{
"epoch": 259.38,
"learning_rate": 1.3541666666666667e-06,
"loss": 0.0001,
"step": 41500
},
{
"epoch": 259.5,
"eval_loss": 0.0835677832365036,
"eval_micro_f1": 0.629322267837761,
"eval_runtime": 16.0109,
"eval_samples_per_second": 378.117,
"step": 41520
},
{
"epoch": 260.0,
"eval_loss": 0.08409415930509567,
"eval_micro_f1": 0.629322267837761,
"eval_runtime": 15.8407,
"eval_samples_per_second": 382.18,
"step": 41600
},
{
"epoch": 260.5,
"eval_loss": 0.08409157395362854,
"eval_micro_f1": 0.6283737019336146,
"eval_runtime": 17.0414,
"eval_samples_per_second": 355.253,
"step": 41680
},
{
"epoch": 261.0,
"eval_loss": 0.08529385924339294,
"eval_micro_f1": 0.6356589142436807,
"eval_runtime": 15.9983,
"eval_samples_per_second": 378.415,
"step": 41760
},
{
"epoch": 261.5,
"eval_loss": 0.08481864631175995,
"eval_micro_f1": 0.6366830634638173,
"eval_runtime": 16.0857,
"eval_samples_per_second": 376.36,
"step": 41840
},
{
"epoch": 262.0,
"eval_loss": 0.08486687391996384,
"eval_micro_f1": 0.6367461425714903,
"eval_runtime": 16.5641,
"eval_samples_per_second": 365.488,
"step": 41920
},
{
"epoch": 262.5,
"learning_rate": 1.25e-06,
"loss": 0.0001,
"step": 42000
},
{
"epoch": 262.5,
"eval_loss": 0.08423876017332077,
"eval_micro_f1": 0.6341463409761692,
"eval_runtime": 16.4745,
"eval_samples_per_second": 367.478,
"step": 42000
},
{
"epoch": 263.0,
"eval_loss": 0.08475633710622787,
"eval_micro_f1": 0.6337047348886666,
"eval_runtime": 16.0802,
"eval_samples_per_second": 376.487,
"step": 42080
},
{
"epoch": 263.5,
"eval_loss": 0.08528608828783035,
"eval_micro_f1": 0.6335664330798669,
"eval_runtime": 16.3481,
"eval_samples_per_second": 370.319,
"step": 42160
},
{
"epoch": 264.0,
"eval_loss": 0.08486173301935196,
"eval_micro_f1": 0.631871954975262,
"eval_runtime": 16.6215,
"eval_samples_per_second": 364.228,
"step": 42240
},
{
"epoch": 264.5,
"eval_loss": 0.0850144699215889,
"eval_micro_f1": 0.633333332845432,
"eval_runtime": 16.2023,
"eval_samples_per_second": 373.65,
"step": 42320
},
{
"epoch": 265.0,
"eval_loss": 0.08447064459323883,
"eval_micro_f1": 0.6350314021648014,
"eval_runtime": 16.0809,
"eval_samples_per_second": 376.471,
"step": 42400
},
{
"epoch": 265.5,
"eval_loss": 0.08411368727684021,
"eval_micro_f1": 0.634281748297534,
"eval_runtime": 16.2862,
"eval_samples_per_second": 371.726,
"step": 42480
},
{
"epoch": 265.62,
"learning_rate": 1.1458333333333333e-06,
"loss": 0.0001,
"step": 42500
},
{
"epoch": 266.0,
"eval_loss": 0.0853659063577652,
"eval_micro_f1": 0.6314305844339615,
"eval_runtime": 16.1215,
"eval_samples_per_second": 375.524,
"step": 42560
},
{
"epoch": 266.5,
"eval_loss": 0.08541795611381531,
"eval_micro_f1": 0.6318758810384241,
"eval_runtime": 17.2404,
"eval_samples_per_second": 351.151,
"step": 42640
},
{
"epoch": 267.0,
"eval_loss": 0.08526263386011124,
"eval_micro_f1": 0.6314305844339615,
"eval_runtime": 15.8936,
"eval_samples_per_second": 380.909,
"step": 42720
},
{
"epoch": 267.5,
"eval_loss": 0.08557014167308807,
"eval_micro_f1": 0.6318758810384241,
"eval_runtime": 16.0629,
"eval_samples_per_second": 376.893,
"step": 42800
},
{
"epoch": 268.0,
"eval_loss": 0.08650677651166916,
"eval_micro_f1": 0.6298655338400406,
"eval_runtime": 16.0983,
"eval_samples_per_second": 376.064,
"step": 42880
},
{
"epoch": 268.5,
"eval_loss": 0.08635231852531433,
"eval_micro_f1": 0.633215547218779,
"eval_runtime": 16.2968,
"eval_samples_per_second": 371.484,
"step": 42960
},
{
"epoch": 268.75,
"learning_rate": 1.0416666666666667e-06,
"loss": 0.0001,
"step": 43000
},
{
"epoch": 269.0,
"eval_loss": 0.08649694174528122,
"eval_micro_f1": 0.6337332387531243,
"eval_runtime": 16.7125,
"eval_samples_per_second": 362.243,
"step": 43040
},
{
"epoch": 269.5,
"eval_loss": 0.08648818731307983,
"eval_micro_f1": 0.6337332387531243,
"eval_runtime": 16.8124,
"eval_samples_per_second": 360.092,
"step": 43120
},
{
"epoch": 270.0,
"eval_loss": 0.08633594959974289,
"eval_micro_f1": 0.6351446713572154,
"eval_runtime": 16.5901,
"eval_samples_per_second": 364.916,
"step": 43200
},
{
"epoch": 270.5,
"eval_loss": 0.08617065101861954,
"eval_micro_f1": 0.636107192745047,
"eval_runtime": 16.8725,
"eval_samples_per_second": 358.808,
"step": 43280
},
{
"epoch": 271.0,
"eval_loss": 0.08661621809005737,
"eval_micro_f1": 0.637068357513587,
"eval_runtime": 19.7691,
"eval_samples_per_second": 306.236,
"step": 43360
},
{
"epoch": 271.5,
"eval_loss": 0.08705565333366394,
"eval_micro_f1": 0.6337332387531243,
"eval_runtime": 16.1704,
"eval_samples_per_second": 374.387,
"step": 43440
},
{
"epoch": 271.88,
"learning_rate": 9.375000000000001e-07,
"loss": 0.0001,
"step": 43500
},
{
"epoch": 272.0,
"eval_loss": 0.08664233982563019,
"eval_micro_f1": 0.637068357513587,
"eval_runtime": 18.9676,
"eval_samples_per_second": 319.175,
"step": 43520
},
{
"epoch": 272.5,
"eval_loss": 0.08728037774562836,
"eval_micro_f1": 0.6327683610973698,
"eval_runtime": 16.7945,
"eval_samples_per_second": 360.476,
"step": 43600
},
{
"epoch": 273.0,
"eval_loss": 0.08681470900774002,
"eval_micro_f1": 0.633215547218779,
"eval_runtime": 16.6008,
"eval_samples_per_second": 364.682,
"step": 43680
},
{
"epoch": 273.5,
"eval_loss": 0.08652900159358978,
"eval_micro_f1": 0.636107192745047,
"eval_runtime": 17.0301,
"eval_samples_per_second": 355.489,
"step": 43760
},
{
"epoch": 274.0,
"eval_loss": 0.08647780120372772,
"eval_micro_f1": 0.6351446713572154,
"eval_runtime": 17.3239,
"eval_samples_per_second": 349.459,
"step": 43840
},
{
"epoch": 274.5,
"eval_loss": 0.08547478914260864,
"eval_micro_f1": 0.6380885448411869,
"eval_runtime": 19.6857,
"eval_samples_per_second": 307.532,
"step": 43920
},
{
"epoch": 275.0,
"learning_rate": 8.333333333333333e-07,
"loss": 0.0001,
"step": 44000
},
{
"epoch": 275.0,
"eval_loss": 0.08565804362297058,
"eval_micro_f1": 0.6404494377165132,
"eval_runtime": 16.5733,
"eval_samples_per_second": 365.286,
"step": 44000
}
],
"max_steps": 48000,
"num_train_epochs": 300,
"total_flos": 278727694333037520,
"trial_name": null,
"trial_params": null
}
{
"best_metric": 0.6404494377165132,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/ner-qa/run-442/checkpoints/checkpoint-44000",
"epoch": 275.0,
"global_step": 44000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.5,
"eval_loss": 0.05795547366142273,
"eval_micro_f1": 0.0,
"eval_runtime": 16.5292,
"eval_samples_per_second": 366.26,
"step": 80
},
{
"epoch": 1.0,
"eval_loss": 0.04793815314769745,
"eval_micro_f1": 0.0,
"eval_runtime": 17.2119,
"eval_samples_per_second": 351.734,
"step": 160
},
{
"epoch": 1.5,
"eval_loss": 0.039343029260635376,
"eval_micro_f1": 0.2935665204250389,
"eval_runtime": 17.1479,
"eval_samples_per_second": 353.045,
"step": 240
},
{
"epoch": 2.0,
"eval_loss": 0.037178002297878265,
"eval_micro_f1": 0.39274141233513093,
"eval_runtime": 17.4422,
"eval_samples_per_second": 347.089,
"step": 320
},
{
"epoch": 2.5,
"eval_loss": 0.037717554718256,
"eval_micro_f1": 0.459636363159023,
"eval_runtime": 18.3194,
"eval_samples_per_second": 330.469,
"step": 400
},
{
"epoch": 3.0,
"eval_loss": 0.035402264446020126,
"eval_micro_f1": 0.5083032486182091,
"eval_runtime": 17.0419,
"eval_samples_per_second": 355.241,
"step": 480
},
{
"epoch": 3.12,
"learning_rate": 9.895833333333334e-06,
"loss": 0.0329,
"step": 500
},
{
"epoch": 3.5,
"eval_loss": 0.03709366172552109,
"eval_micro_f1": 0.5241286858336526,
"eval_runtime": 19.592,
"eval_samples_per_second": 309.003,
"step": 560
},
{
"epoch": 4.0,
"eval_loss": 0.03474647179245949,
"eval_micro_f1": 0.5232722139017647,
"eval_runtime": 20.0754,
"eval_samples_per_second": 301.563,
"step": 640
},
{
"epoch": 4.5,
"eval_loss": 0.0367262028157711,
"eval_micro_f1": 0.5109922751975721,
"eval_runtime": 20.8465,
"eval_samples_per_second": 290.409,
"step": 720
},
{
"epoch": 5.0,
"eval_loss": 0.03650993853807449,
"eval_micro_f1": 0.5546975541997236,
"eval_runtime": 16.8574,
"eval_samples_per_second": 359.131,
"step": 800
},
{
"epoch": 5.5,
"eval_loss": 0.03861010819673538,
"eval_micro_f1": 0.5305591672534306,
"eval_runtime": 16.9753,