Instructions to use splitner/spanclass-qa-crossentropy-ontonotes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use splitner/spanclass-qa-crossentropy-ontonotes with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("splitner/spanclass-qa-crossentropy-ontonotes") model = AutoModel.from_pretrained("splitner/spanclass-qa-crossentropy-ontonotes", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from splitner/spanclass-qa-crossentropy-ontonotes: direct link, hf CLI and curl.
- Browser
- Download file 114 kB
-
https://huggingface.co/splitner/spanclass-qa-crossentropy-ontonotes/resolve/main/trainer_state.json
- Command line
-
hf download hf://splitner/spanclass-qa-crossentropy-ontonotes/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/splitner/spanclass-qa-crossentropy-ontonotes/resolve/main/trainer_state.json
114 kB
{
"best_metric": 0.960328934977954,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/onto_final/class-ce-new/run-42/checkpoints/checkpoint-134750",
"epoch": 210.546875,
"global_step": 134750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.390625,
"eval_loss": 0.3807726800441742,
"eval_micro_f1": 0.9149647564129842,
"step": 250
},
{
"epoch": 0.78125,
"learning_rate": 9.973958333333335e-06,
"loss": 0.7134353637695312,
"step": 500
},
{
"epoch": 0.78125,
"eval_loss": 0.26241013407707214,
"eval_micro_f1": 0.9413518881679069,
"step": 500
},
{
"epoch": 1.171875,
"eval_loss": 0.21784928441047668,
"eval_micro_f1": 0.9512922460207887,
"step": 750
},
{
"epoch": 1.5625,
"learning_rate": 9.947916666666667e-06,
"loss": 0.19096646118164062,
"step": 1000
},
{
"epoch": 1.5625,
"eval_loss": 0.20647455751895905,
"eval_micro_f1": 0.9507500446833588,
"step": 1000
},
{
"epoch": 1.953125,
"eval_loss": 0.20064181089401245,
"eval_micro_f1": 0.9518344473582186,
"step": 1250
},
{
"epoch": 2.34375,
"learning_rate": 9.921875e-06,
"loss": 0.13846273803710937,
"step": 1500
},
{
"epoch": 2.34375,
"eval_loss": 0.2122383713722229,
"eval_micro_f1": 0.949936742677214,
"step": 1500
},
{
"epoch": 2.734375,
"eval_loss": 0.2097567319869995,
"eval_micro_f1": 0.9505693109042156,
"step": 1750
},
{
"epoch": 3.125,
"learning_rate": 9.895833333333334e-06,
"loss": 0.11275356292724609,
"step": 2000
},
{
"epoch": 3.125,
"eval_loss": 0.2129451185464859,
"eval_micro_f1": 0.9540032527079383,
"step": 2000
},
{
"epoch": 3.515625,
"eval_loss": 0.20601296424865723,
"eval_micro_f1": 0.9537321520392233,
"step": 2250
},
{
"epoch": 3.90625,
"learning_rate": 9.869791666666667e-06,
"loss": 0.092468017578125,
"step": 2500
},
{
"epoch": 3.90625,
"eval_loss": 0.20766089856624603,
"eval_micro_f1": 0.9565335256159445,
"step": 2500
},
{
"epoch": 4.296875,
"eval_loss": 0.2053472399711609,
"eval_micro_f1": 0.9559913242785146,
"step": 2750
},
{
"epoch": 4.6875,
"learning_rate": 9.84375e-06,
"loss": 0.07561186981201172,
"step": 3000
},
{
"epoch": 4.6875,
"eval_loss": 0.21163810789585114,
"eval_micro_f1": 0.9532803175913651,
"step": 3000
},
{
"epoch": 5.078125,
"eval_loss": 0.2081116884946823,
"eval_micro_f1": 0.9549972884932264,
"step": 3250
},
{
"epoch": 5.46875,
"learning_rate": 9.817708333333334e-06,
"loss": 0.06890515899658203,
"step": 3500
},
{
"epoch": 5.46875,
"eval_loss": 0.20766735076904297,
"eval_micro_f1": 0.9566238925055163,
"step": 3500
},
{
"epoch": 5.859375,
"eval_loss": 0.22146223485469818,
"eval_micro_f1": 0.9561720580576579,
"step": 3750
},
{
"epoch": 6.25,
"learning_rate": 9.791666666666666e-06,
"loss": 0.059096569061279296,
"step": 4000
},
{
"epoch": 6.25,
"eval_loss": 0.23278285562992096,
"eval_micro_f1": 0.9534610513705084,
"step": 4000
},
{
"epoch": 6.640625,
"eval_loss": 0.240151509642601,
"eval_micro_f1": 0.9529188500330784,
"step": 4250
},
{
"epoch": 7.03125,
"learning_rate": 9.765625e-06,
"loss": 0.05005146789550781,
"step": 4500
},
{
"epoch": 7.03125,
"eval_loss": 0.23893651366233826,
"eval_micro_f1": 0.9528284831435068,
"step": 4500
},
{
"epoch": 7.421875,
"eval_loss": 0.25410574674606323,
"eval_micro_f1": 0.9525573824747918,
"step": 4750
},
{
"epoch": 7.8125,
"learning_rate": 9.739583333333334e-06,
"loss": 0.04328378295898438,
"step": 5000
},
{
"epoch": 7.8125,
"eval_loss": 0.2430105060338974,
"eval_micro_f1": 0.9558105904993713,
"step": 5000
},
{
"epoch": 8.203125,
"eval_loss": 0.2743004858493805,
"eval_micro_f1": 0.9498463757876422,
"step": 5250
},
{
"epoch": 8.59375,
"learning_rate": 9.713541666666668e-06,
"loss": 0.03830230712890625,
"step": 5500
},
{
"epoch": 8.59375,
"eval_loss": 0.25857266783714294,
"eval_micro_f1": 0.9558105904993713,
"step": 5500
},
{
"epoch": 8.984375,
"eval_loss": 0.2579847276210785,
"eval_micro_f1": 0.9522862818060769,
"step": 5750
},
{
"epoch": 9.375,
"learning_rate": 9.6875e-06,
"loss": 0.03396718978881836,
"step": 6000
},
{
"epoch": 9.375,
"eval_loss": 0.26473912596702576,
"eval_micro_f1": 0.9542743533766532,
"step": 6000
},
{
"epoch": 9.765625,
"eval_loss": 0.263930082321167,
"eval_micro_f1": 0.9542743533766532,
"step": 6250
},
{
"epoch": 10.15625,
"learning_rate": 9.661458333333334e-06,
"loss": 0.029433568954467772,
"step": 6500
},
{
"epoch": 10.15625,
"eval_loss": 0.2725895643234253,
"eval_micro_f1": 0.9549972884932264,
"step": 6500
},
{
"epoch": 10.546875,
"eval_loss": 0.29378774762153625,
"eval_micro_f1": 0.9531899507017935,
"step": 6750
},
{
"epoch": 10.9375,
"learning_rate": 9.635416666666668e-06,
"loss": 0.028068063735961914,
"step": 7000
},
{
"epoch": 10.9375,
"eval_loss": 0.2847367525100708,
"eval_micro_f1": 0.9530092169226502,
"step": 7000
},
{
"epoch": 11.328125,
"eval_loss": 0.29993003606796265,
"eval_micro_f1": 0.9534610513705084,
"step": 7250
},
{
"epoch": 11.71875,
"learning_rate": 9.609375000000001e-06,
"loss": 0.02054808807373047,
"step": 7500
},
{
"epoch": 11.71875,
"eval_loss": 0.2724398970603943,
"eval_micro_f1": 0.9574371945116611,
"step": 7500
},
{
"epoch": 12.109375,
"eval_loss": 0.3062136471271515,
"eval_micro_f1": 0.9549972884932264,
"step": 7750
},
{
"epoch": 12.5,
"learning_rate": 9.583333333333335e-06,
"loss": 0.02030120277404785,
"step": 8000
},
{
"epoch": 12.5,
"eval_loss": 0.29937082529067993,
"eval_micro_f1": 0.9549069216036549,
"step": 8000
},
{
"epoch": 12.890625,
"eval_loss": 0.2990036606788635,
"eval_micro_f1": 0.9533706844809368,
"step": 8250
},
{
"epoch": 13.28125,
"learning_rate": 9.557291666666667e-06,
"loss": 0.01842806625366211,
"step": 8500
},
{
"epoch": 13.28125,
"eval_loss": 0.2937905788421631,
"eval_micro_f1": 0.9552683891619415,
"step": 8500
},
{
"epoch": 13.671875,
"eval_loss": 0.3103709816932678,
"eval_micro_f1": 0.9546358209349399,
"step": 8750
},
{
"epoch": 14.0625,
"learning_rate": 9.531250000000001e-06,
"loss": 0.01711715507507324,
"step": 9000
},
{
"epoch": 14.0625,
"eval_loss": 0.32456886768341064,
"eval_micro_f1": 0.9549069216036549,
"step": 9000
},
{
"epoch": 14.453125,
"eval_loss": 0.3178841471672058,
"eval_micro_f1": 0.955629856720228,
"step": 9250
},
{
"epoch": 14.84375,
"learning_rate": 9.505208333333335e-06,
"loss": 0.013700548171997071,
"step": 9500
},
{
"epoch": 14.84375,
"eval_loss": 0.30276453495025635,
"eval_micro_f1": 0.9568046262846596,
"step": 9500
},
{
"epoch": 15.234375,
"eval_loss": 0.328804612159729,
"eval_micro_f1": 0.9542743533766532,
"step": 9750
},
{
"epoch": 15.625,
"learning_rate": 9.479166666666667e-06,
"loss": 0.012017199516296387,
"step": 10000
},
{
"epoch": 15.625,
"eval_loss": 0.35955560207366943,
"eval_micro_f1": 0.9521055480269336,
"step": 10000
},
{
"epoch": 16.015625,
"eval_loss": 0.3190496265888214,
"eval_micro_f1": 0.9553587560515131,
"step": 10250
},
{
"epoch": 16.40625,
"learning_rate": 9.453125000000001e-06,
"loss": 0.014203130722045898,
"step": 10500
},
{
"epoch": 16.40625,
"eval_loss": 0.34149059653282166,
"eval_micro_f1": 0.9539128858183666,
"step": 10500
},
{
"epoch": 16.796875,
"eval_loss": 0.34821048378944397,
"eval_micro_f1": 0.953822518928795,
"step": 10750
},
{
"epoch": 17.1875,
"learning_rate": 9.427083333333335e-06,
"loss": 0.013178150177001953,
"step": 11000
},
{
"epoch": 17.1875,
"eval_loss": 0.3536815345287323,
"eval_micro_f1": 0.9519248142477903,
"step": 11000
},
{
"epoch": 17.578125,
"eval_loss": 0.3218971788883209,
"eval_micro_f1": 0.9562624249472296,
"step": 11250
},
{
"epoch": 17.96875,
"learning_rate": 9.401041666666667e-06,
"loss": 0.009782636642456054,
"step": 11500
},
{
"epoch": 17.96875,
"eval_loss": 0.33723413944244385,
"eval_micro_f1": 0.9574371945116611,
"step": 11500
},
{
"epoch": 18.359375,
"eval_loss": 0.34638723731040955,
"eval_micro_f1": 0.9549069216036549,
"step": 11750
},
{
"epoch": 18.75,
"learning_rate": 9.375000000000001e-06,
"loss": 0.009303528785705567,
"step": 12000
},
{
"epoch": 18.75,
"eval_loss": 0.33177536725997925,
"eval_micro_f1": 0.9558105904993713,
"step": 12000
},
{
"epoch": 19.140625,
"eval_loss": 0.35774126648902893,
"eval_micro_f1": 0.9537321520392233,
"step": 12250
},
{
"epoch": 19.53125,
"learning_rate": 9.348958333333335e-06,
"loss": 0.008318093299865723,
"step": 12500
},
{
"epoch": 19.53125,
"eval_loss": 0.35392969846725464,
"eval_micro_f1": 0.9555394898306564,
"step": 12500
},
{
"epoch": 19.921875,
"eval_loss": 0.3639703392982483,
"eval_micro_f1": 0.9545454540453682,
"step": 12750
},
{
"epoch": 20.3125,
"learning_rate": 9.322916666666667e-06,
"loss": 0.01003277587890625,
"step": 13000
},
{
"epoch": 20.3125,
"eval_loss": 0.3368658423423767,
"eval_micro_f1": 0.9560816911680863,
"step": 13000
},
{
"epoch": 20.703125,
"eval_loss": 0.36042386293411255,
"eval_micro_f1": 0.9552683891619415,
"step": 13250
},
{
"epoch": 21.09375,
"learning_rate": 9.296875e-06,
"loss": 0.008895337104797363,
"step": 13500
},
{
"epoch": 21.09375,
"eval_loss": 0.35547035932540894,
"eval_micro_f1": 0.9531899507017935,
"step": 13500
},
{
"epoch": 21.484375,
"eval_loss": 0.350028395652771,
"eval_micro_f1": 0.9574371945116611,
"step": 13750
},
{
"epoch": 21.875,
"learning_rate": 9.270833333333334e-06,
"loss": 0.008737407684326171,
"step": 14000
},
{
"epoch": 21.875,
"eval_loss": 0.3534579575061798,
"eval_micro_f1": 0.9558105904993713,
"step": 14000
},
{
"epoch": 22.265625,
"eval_loss": 0.3564068377017975,
"eval_micro_f1": 0.9561720580576579,
"step": 14250
},
{
"epoch": 22.65625,
"learning_rate": 9.244791666666667e-06,
"loss": 0.008814117431640626,
"step": 14500
},
{
"epoch": 22.65625,
"eval_loss": 0.36208266019821167,
"eval_micro_f1": 0.9562624249472296,
"step": 14500
},
{
"epoch": 23.046875,
"eval_loss": 0.3518032133579254,
"eval_micro_f1": 0.955900957388943,
"step": 14750
},
{
"epoch": 23.4375,
"learning_rate": 9.21875e-06,
"loss": 0.006992603302001953,
"step": 15000
},
{
"epoch": 23.4375,
"eval_loss": 0.3722230792045593,
"eval_micro_f1": 0.9562624249472296,
"step": 15000
},
{
"epoch": 23.828125,
"eval_loss": 0.3631362020969391,
"eval_micro_f1": 0.9566238925055163,
"step": 15250
},
{
"epoch": 24.21875,
"learning_rate": 9.192708333333334e-06,
"loss": 0.007241117477416992,
"step": 15500
},
{
"epoch": 24.21875,
"eval_loss": 0.34882068634033203,
"eval_micro_f1": 0.9574371945116611,
"step": 15500
},
{
"epoch": 24.609375,
"eval_loss": 0.37857645750045776,
"eval_micro_f1": 0.9552683891619415,
"step": 15750
},
{
"epoch": 25.0,
"learning_rate": 9.166666666666666e-06,
"loss": 0.006694699287414551,
"step": 16000
},
{
"epoch": 25.0,
"eval_loss": 0.36459803581237793,
"eval_micro_f1": 0.9575275614012327,
"step": 16000
},
{
"epoch": 25.390625,
"eval_loss": 0.38562464714050293,
"eval_micro_f1": 0.9530995838122216,
"step": 16250
},
{
"epoch": 25.78125,
"learning_rate": 9.140625e-06,
"loss": 0.007339463710784912,
"step": 16500
},
{
"epoch": 25.78125,
"eval_loss": 0.3878008723258972,
"eval_micro_f1": 0.9549972884932264,
"step": 16500
},
{
"epoch": 26.171875,
"eval_loss": 0.3903466761112213,
"eval_micro_f1": 0.9564431587263729,
"step": 16750
},
{
"epoch": 26.5625,
"learning_rate": 9.114583333333334e-06,
"loss": 0.005757175922393799,
"step": 17000
},
{
"epoch": 26.5625,
"eval_loss": 0.3799821436405182,
"eval_micro_f1": 0.9560816911680863,
"step": 17000
},
{
"epoch": 26.953125,
"eval_loss": 0.3822616636753082,
"eval_micro_f1": 0.9561720580576579,
"step": 17250
},
{
"epoch": 27.34375,
"learning_rate": 9.088541666666666e-06,
"loss": 0.0057654943466186525,
"step": 17500
},
{
"epoch": 27.34375,
"eval_loss": 0.40128475427627563,
"eval_micro_f1": 0.9532803175913651,
"step": 17500
},
{
"epoch": 27.734375,
"eval_loss": 0.3788779079914093,
"eval_micro_f1": 0.9561720580576579,
"step": 17750
},
{
"epoch": 28.125,
"learning_rate": 9.0625e-06,
"loss": 0.006710000991821289,
"step": 18000
},
{
"epoch": 28.125,
"eval_loss": 0.38382503390312195,
"eval_micro_f1": 0.9558105904993713,
"step": 18000
},
{
"epoch": 28.515625,
"eval_loss": 0.3863045871257782,
"eval_micro_f1": 0.957979395849091,
"step": 18250
},
{
"epoch": 28.90625,
"learning_rate": 9.036458333333334e-06,
"loss": 0.004883807182312011,
"step": 18500
},
{
"epoch": 28.90625,
"eval_loss": 0.4066820740699768,
"eval_micro_f1": 0.9541839864870816,
"step": 18500
},
{
"epoch": 29.296875,
"eval_loss": 0.3915826380252838,
"eval_micro_f1": 0.9569853600638029,
"step": 18750
},
{
"epoch": 29.6875,
"learning_rate": 9.010416666666668e-06,
"loss": 0.005992436408996582,
"step": 19000
},
{
"epoch": 29.6875,
"eval_loss": 0.3970724642276764,
"eval_micro_f1": 0.9557202236097997,
"step": 19000
},
{
"epoch": 30.078125,
"eval_loss": 0.39998212456703186,
"eval_micro_f1": 0.9561720580576579,
"step": 19250
},
{
"epoch": 30.46875,
"learning_rate": 8.984375000000002e-06,
"loss": 0.006145555973052979,
"step": 19500
},
{
"epoch": 30.46875,
"eval_loss": 0.4036008417606354,
"eval_micro_f1": 0.9530092169226502,
"step": 19500
},
{
"epoch": 30.859375,
"eval_loss": 0.39797595143318176,
"eval_micro_f1": 0.9572564607325178,
"step": 19750
},
{
"epoch": 31.25,
"learning_rate": 8.958333333333334e-06,
"loss": 0.004870827198028564,
"step": 20000
},
{
"epoch": 31.25,
"eval_loss": 0.4146208167076111,
"eval_micro_f1": 0.9531899507017935,
"step": 20000
},
{
"epoch": 31.640625,
"eval_loss": 0.39097198843955994,
"eval_micro_f1": 0.953822518928795,
"step": 20250
},
{
"epoch": 32.03125,
"learning_rate": 8.932291666666668e-06,
"loss": 0.005132315635681152,
"step": 20500
},
{
"epoch": 32.03125,
"eval_loss": 0.39996615052223206,
"eval_micro_f1": 0.955629856720228,
"step": 20500
},
{
"epoch": 32.421875,
"eval_loss": 0.3952488601207733,
"eval_micro_f1": 0.9551780222723698,
"step": 20750
},
{
"epoch": 32.8125,
"learning_rate": 8.906250000000001e-06,
"loss": 0.006632910251617431,
"step": 21000
},
{
"epoch": 32.8125,
"eval_loss": 0.37737417221069336,
"eval_micro_f1": 0.9549972884932264,
"step": 21000
},
{
"epoch": 33.203125,
"eval_loss": 0.3909129202365875,
"eval_micro_f1": 0.9567142593950879,
"step": 21250
},
{
"epoch": 33.59375,
"learning_rate": 8.880208333333335e-06,
"loss": 0.005495747089385986,
"step": 21500
},
{
"epoch": 33.59375,
"eval_loss": 0.40529489517211914,
"eval_micro_f1": 0.9526477493643635,
"step": 21500
},
{
"epoch": 33.984375,
"eval_loss": 0.40730831027030945,
"eval_micro_f1": 0.9551780222723698,
"step": 21750
},
{
"epoch": 34.375,
"learning_rate": 8.854166666666667e-06,
"loss": 0.0050001730918884275,
"step": 22000
},
{
"epoch": 34.375,
"eval_loss": 0.38948163390159607,
"eval_micro_f1": 0.9564431587263729,
"step": 22000
},
{
"epoch": 34.765625,
"eval_loss": 0.39216139912605286,
"eval_micro_f1": 0.9572564607325178,
"step": 22250
},
{
"epoch": 35.15625,
"learning_rate": 8.828125000000001e-06,
"loss": 0.005100529670715332,
"step": 22500
},
{
"epoch": 35.15625,
"eval_loss": 0.4039481282234192,
"eval_micro_f1": 0.9547261878245115,
"step": 22500
},
{
"epoch": 35.546875,
"eval_loss": 0.39026039838790894,
"eval_micro_f1": 0.9568046262846596,
"step": 22750
},
{
"epoch": 35.9375,
"learning_rate": 8.802083333333335e-06,
"loss": 0.004579799652099609,
"step": 23000
},
{
"epoch": 35.9375,
"eval_loss": 0.3824807405471802,
"eval_micro_f1": 0.9575275614012327,
"step": 23000
},
{
"epoch": 36.328125,
"eval_loss": 0.40704017877578735,
"eval_micro_f1": 0.9568949931742312,
"step": 23250
},
{
"epoch": 36.71875,
"learning_rate": 8.776041666666667e-06,
"loss": 0.004869240283966065,
"step": 23500
},
{
"epoch": 36.71875,
"eval_loss": 0.4177151322364807,
"eval_micro_f1": 0.9560816911680863,
"step": 23500
},
{
"epoch": 37.109375,
"eval_loss": 0.40177252888679504,
"eval_micro_f1": 0.9563527918368012,
"step": 23750
},
{
"epoch": 37.5,
"learning_rate": 8.750000000000001e-06,
"loss": 0.005543815612792969,
"step": 24000
},
{
"epoch": 37.5,
"eval_loss": 0.40816840529441833,
"eval_micro_f1": 0.9564431587263729,
"step": 24000
},
{
"epoch": 37.890625,
"eval_loss": 0.41492441296577454,
"eval_micro_f1": 0.9563527918368012,
"step": 24250
},
{
"epoch": 38.28125,
"learning_rate": 8.723958333333335e-06,
"loss": 0.0052886676788330075,
"step": 24500
},
{
"epoch": 38.28125,
"eval_loss": 0.3990243673324585,
"eval_micro_f1": 0.9576179282908044,
"step": 24500
},
{
"epoch": 38.671875,
"eval_loss": 0.39962267875671387,
"eval_micro_f1": 0.9574371945116611,
"step": 24750
},
{
"epoch": 39.0625,
"learning_rate": 8.697916666666667e-06,
"loss": 0.004812153339385986,
"step": 25000
},
{
"epoch": 39.0625,
"eval_loss": 0.3885045051574707,
"eval_micro_f1": 0.9581601296282343,
"step": 25000
},
{
"epoch": 39.453125,
"eval_loss": 0.40117233991622925,
"eval_micro_f1": 0.957708295180376,
"step": 25250
},
{
"epoch": 39.84375,
"learning_rate": 8.671875e-06,
"loss": 0.003595633029937744,
"step": 25500
},
{
"epoch": 39.84375,
"eval_loss": 0.42534133791923523,
"eval_micro_f1": 0.955629856720228,
"step": 25500
},
{
"epoch": 40.234375,
"eval_loss": 0.42309701442718506,
"eval_micro_f1": 0.9549069216036549,
"step": 25750
},
{
"epoch": 40.625,
"learning_rate": 8.645833333333335e-06,
"loss": 0.004000110149383545,
"step": 26000
},
{
"epoch": 40.625,
"eval_loss": 0.4201319217681885,
"eval_micro_f1": 0.9543647202662249,
"step": 26000
},
{
"epoch": 41.015625,
"eval_loss": 0.42158493399620056,
"eval_micro_f1": 0.9530092169226502,
"step": 26250
},
{
"epoch": 41.40625,
"learning_rate": 8.619791666666667e-06,
"loss": 0.004323803424835205,
"step": 26500
},
{
"epoch": 41.40625,
"eval_loss": 0.42989957332611084,
"eval_micro_f1": 0.9547261878245115,
"step": 26500
},
{
"epoch": 41.796875,
"eval_loss": 0.4312675893306732,
"eval_micro_f1": 0.9522862818060769,
"step": 26750
},
{
"epoch": 42.1875,
"learning_rate": 8.59375e-06,
"loss": 0.004182614803314209,
"step": 27000
},
{
"epoch": 42.1875,
"eval_loss": 0.42522692680358887,
"eval_micro_f1": 0.9534610513705084,
"step": 27000
},
{
"epoch": 42.578125,
"eval_loss": 0.4281964600086212,
"eval_micro_f1": 0.9537321520392233,
"step": 27250
},
{
"epoch": 42.96875,
"learning_rate": 8.567708333333334e-06,
"loss": 0.002612123966217041,
"step": 27500
},
{
"epoch": 42.96875,
"eval_loss": 0.4192436933517456,
"eval_micro_f1": 0.9560816911680863,
"step": 27500
},
{
"epoch": 43.359375,
"eval_loss": 0.4303324222564697,
"eval_micro_f1": 0.9540936195975099,
"step": 27750
},
{
"epoch": 43.75,
"learning_rate": 8.541666666666666e-06,
"loss": 0.0036287589073181153,
"step": 28000
},
{
"epoch": 43.75,
"eval_loss": 0.4526871144771576,
"eval_micro_f1": 0.951744080468647,
"step": 28000
},
{
"epoch": 44.140625,
"eval_loss": 0.4479342997074127,
"eval_micro_f1": 0.9521055480269336,
"step": 28250
},
{
"epoch": 44.53125,
"learning_rate": 8.515625e-06,
"loss": 0.004274591922760009,
"step": 28500
},
{
"epoch": 44.53125,
"eval_loss": 0.44339069724082947,
"eval_micro_f1": 0.9512922460207887,
"step": 28500
},
{
"epoch": 44.921875,
"eval_loss": 0.43463507294654846,
"eval_micro_f1": 0.9532803175913651,
"step": 28750
},
{
"epoch": 45.3125,
"learning_rate": 8.489583333333334e-06,
"loss": 0.004847230434417725,
"step": 29000
},
{
"epoch": 45.3125,
"eval_loss": 0.42614614963531494,
"eval_micro_f1": 0.9544550871557965,
"step": 29000
},
{
"epoch": 45.703125,
"eval_loss": 0.4271053671836853,
"eval_micro_f1": 0.9542743533766532,
"step": 29250
},
{
"epoch": 46.09375,
"learning_rate": 8.463541666666666e-06,
"loss": 0.003514364242553711,
"step": 29500
},
{
"epoch": 46.09375,
"eval_loss": 0.4235973656177521,
"eval_micro_f1": 0.95355141826008,
"step": 29500
},
{
"epoch": 46.484375,
"eval_loss": 0.4449480175971985,
"eval_micro_f1": 0.9537321520392233,
"step": 29750
},
{
"epoch": 46.875,
"learning_rate": 8.4375e-06,
"loss": 0.002777634859085083,
"step": 30000
},
{
"epoch": 46.875,
"eval_loss": 0.4563918113708496,
"eval_micro_f1": 0.9507500446833588,
"step": 30000
},
{
"epoch": 47.265625,
"eval_loss": 0.4347975552082062,
"eval_micro_f1": 0.9549972884932264,
"step": 30250
},
{
"epoch": 47.65625,
"learning_rate": 8.411458333333334e-06,
"loss": 0.003947774887084961,
"step": 30500
},
{
"epoch": 47.65625,
"eval_loss": 0.4479941725730896,
"eval_micro_f1": 0.9549069216036549,
"step": 30500
},
{
"epoch": 48.046875,
"eval_loss": 0.4393841624259949,
"eval_micro_f1": 0.955629856720228,
"step": 30750
},
{
"epoch": 48.4375,
"learning_rate": 8.385416666666668e-06,
"loss": 0.0038207385540008545,
"step": 31000
},
{
"epoch": 48.4375,
"eval_loss": 0.42423856258392334,
"eval_micro_f1": 0.9570757269533745,
"step": 31000
},
{
"epoch": 48.828125,
"eval_loss": 0.410977840423584,
"eval_micro_f1": 0.9568949931742312,
"step": 31250
},
{
"epoch": 49.21875,
"learning_rate": 8.359375e-06,
"loss": 0.003576582670211792,
"step": 31500
},
{
"epoch": 49.21875,
"eval_loss": 0.4434860050678253,
"eval_micro_f1": 0.9549069216036549,
"step": 31500
},
{
"epoch": 49.609375,
"eval_loss": 0.420529305934906,
"eval_micro_f1": 0.9566238925055163,
"step": 31750
},
{
"epoch": 50.0,
"learning_rate": 8.333333333333334e-06,
"loss": 0.00438494873046875,
"step": 32000
},
{
"epoch": 50.0,
"eval_loss": 0.4262810945510864,
"eval_micro_f1": 0.9541839864870816,
"step": 32000
},
{
"epoch": 50.390625,
"eval_loss": 0.4242883026599884,
"eval_micro_f1": 0.9551780222723698,
"step": 32250
},
{
"epoch": 50.78125,
"learning_rate": 8.307291666666668e-06,
"loss": 0.004263808727264404,
"step": 32500
},
{
"epoch": 50.78125,
"eval_loss": 0.43042808771133423,
"eval_micro_f1": 0.9532803175913651,
"step": 32500
},
{
"epoch": 51.171875,
"eval_loss": 0.4431949555873871,
"eval_micro_f1": 0.9544550871557965,
"step": 32750
},
{
"epoch": 51.5625,
"learning_rate": 8.281250000000001e-06,
"loss": 0.0023831374645233152,
"step": 33000
},
{
"epoch": 51.5625,
"eval_loss": 0.4313192367553711,
"eval_micro_f1": 0.955629856720228,
"step": 33000
},
{
"epoch": 51.953125,
"eval_loss": 0.42930471897125244,
"eval_micro_f1": 0.9554491229410847,
"step": 33250
},
{
"epoch": 52.34375,
"learning_rate": 8.255208333333335e-06,
"loss": 0.0040452079772949215,
"step": 33500
},
{
"epoch": 52.34375,
"eval_loss": 0.43207278847694397,
"eval_micro_f1": 0.9524670155852202,
"step": 33500
},
{
"epoch": 52.734375,
"eval_loss": 0.4343126714229584,
"eval_micro_f1": 0.953822518928795,
"step": 33750
},
{
"epoch": 53.125,
"learning_rate": 8.229166666666667e-06,
"loss": 0.0033658578395843507,
"step": 34000
},
{
"epoch": 53.125,
"eval_loss": 0.4390556514263153,
"eval_micro_f1": 0.955900957388943,
"step": 34000
},
{
"epoch": 53.515625,
"eval_loss": 0.43600189685821533,
"eval_micro_f1": 0.95355141826008,
"step": 34250
},
{
"epoch": 53.90625,
"learning_rate": 8.203125000000001e-06,
"loss": 0.0036824307441711427,
"step": 34500
},
{
"epoch": 53.90625,
"eval_loss": 0.4360972046852112,
"eval_micro_f1": 0.9551780222723698,
"step": 34500
},
{
"epoch": 54.296875,
"eval_loss": 0.4302920997142792,
"eval_micro_f1": 0.9557202236097997,
"step": 34750
},
{
"epoch": 54.6875,
"learning_rate": 8.177083333333335e-06,
"loss": 0.00411603307723999,
"step": 35000
},
{
"epoch": 54.6875,
"eval_loss": 0.4295671582221985,
"eval_micro_f1": 0.9557202236097997,
"step": 35000
},
{
"epoch": 55.078125,
"eval_loss": 0.4309457838535309,
"eval_micro_f1": 0.9561720580576579,
"step": 35250
},
{
"epoch": 55.46875,
"learning_rate": 8.151041666666667e-06,
"loss": 0.0036915135383605957,
"step": 35500
},
{
"epoch": 55.46875,
"eval_loss": 0.4137577414512634,
"eval_micro_f1": 0.9562624249472296,
"step": 35500
},
{
"epoch": 55.859375,
"eval_loss": 0.4461974501609802,
"eval_micro_f1": 0.9545454540453682,
"step": 35750
},
{
"epoch": 56.25,
"learning_rate": 8.125000000000001e-06,
"loss": 0.002755143404006958,
"step": 36000
},
{
"epoch": 56.25,
"eval_loss": 0.46042367815971375,
"eval_micro_f1": 0.9546358209349399,
"step": 36000
},
{
"epoch": 56.640625,
"eval_loss": 0.45196840167045593,
"eval_micro_f1": 0.9540032527079383,
"step": 36250
},
{
"epoch": 57.03125,
"learning_rate": 8.098958333333335e-06,
"loss": 0.00377594518661499,
"step": 36500
},
{
"epoch": 57.03125,
"eval_loss": 0.43639326095581055,
"eval_micro_f1": 0.9546358209349399,
"step": 36500
},
{
"epoch": 57.421875,
"eval_loss": 0.4334815442562103,
"eval_micro_f1": 0.9550876553827982,
"step": 36750
},
{
"epoch": 57.8125,
"learning_rate": 8.072916666666667e-06,
"loss": 0.0031781716346740724,
"step": 37000
},
{
"epoch": 57.8125,
"eval_loss": 0.4552783668041229,
"eval_micro_f1": 0.9531899507017935,
"step": 37000
},
{
"epoch": 58.203125,
"eval_loss": 0.4552616775035858,
"eval_micro_f1": 0.9549972884932264,
"step": 37250
},
{
"epoch": 58.59375,
"learning_rate": 8.046875e-06,
"loss": 0.002401029825210571,
"step": 37500
},
{
"epoch": 58.59375,
"eval_loss": 0.44952359795570374,
"eval_micro_f1": 0.9569853600638029,
"step": 37500
},
{
"epoch": 58.984375,
"eval_loss": 0.44536933302879333,
"eval_micro_f1": 0.9568046262846596,
"step": 37750
},
{
"epoch": 59.375,
"learning_rate": 8.020833333333335e-06,
"loss": 0.0028808960914611815,
"step": 38000
},
{
"epoch": 59.375,
"eval_loss": 0.4368811845779419,
"eval_micro_f1": 0.9559913242785146,
"step": 38000
},
{
"epoch": 59.765625,
"eval_loss": 0.44166305661201477,
"eval_micro_f1": 0.9543647202662249,
"step": 38250
},
{
"epoch": 60.15625,
"learning_rate": 7.994791666666667e-06,
"loss": 0.003074864864349365,
"step": 38500
},
{
"epoch": 60.15625,
"eval_loss": 0.43950924277305603,
"eval_micro_f1": 0.9555394898306564,
"step": 38500
},
{
"epoch": 60.546875,
"eval_loss": 0.4601697325706482,
"eval_micro_f1": 0.9541839864870816,
"step": 38750
},
{
"epoch": 60.9375,
"learning_rate": 7.96875e-06,
"loss": 0.003602522134780884,
"step": 39000
},
{
"epoch": 60.9375,
"eval_loss": 0.42789286375045776,
"eval_micro_f1": 0.9541839864870816,
"step": 39000
},
{
"epoch": 61.328125,
"eval_loss": 0.45940083265304565,
"eval_micro_f1": 0.9534610513705084,
"step": 39250
},
{
"epoch": 61.71875,
"learning_rate": 7.942708333333334e-06,
"loss": 0.002418166399002075,
"step": 39500
},
{
"epoch": 61.71875,
"eval_loss": 0.4370346963405609,
"eval_micro_f1": 0.9548165547140831,
"step": 39500
},
{
"epoch": 62.109375,
"eval_loss": 0.4390202760696411,
"eval_micro_f1": 0.9557202236097997,
"step": 39750
},
{
"epoch": 62.5,
"learning_rate": 7.916666666666667e-06,
"loss": 0.0038499054908752444,
"step": 40000
},
{
"epoch": 62.5,
"eval_loss": 0.45617660880088806,
"eval_micro_f1": 0.9534610513705084,
"step": 40000
},
{
"epoch": 62.890625,
"eval_loss": 0.45370620489120483,
"eval_micro_f1": 0.9548165547140831,
"step": 40250
},
{
"epoch": 63.28125,
"learning_rate": 7.890625e-06,
"loss": 0.0026343622207641603,
"step": 40500
},
{
"epoch": 63.28125,
"eval_loss": 0.45049142837524414,
"eval_micro_f1": 0.9564431587263729,
"step": 40500
},
{
"epoch": 63.671875,
"eval_loss": 0.4485730230808258,
"eval_micro_f1": 0.955629856720228,
"step": 40750
},
{
"epoch": 64.0625,
"learning_rate": 7.864583333333334e-06,
"loss": 0.0030656917095184325,
"step": 41000
},
{
"epoch": 64.0625,
"eval_loss": 0.4620691239833832,
"eval_micro_f1": 0.9554491229410847,
"step": 41000
},
{
"epoch": 64.453125,
"eval_loss": 0.41894611716270447,
"eval_micro_f1": 0.9562624249472296,
"step": 41250
},
{
"epoch": 64.84375,
"learning_rate": 7.838541666666666e-06,
"loss": 0.0034964179992675783,
"step": 41500
},
{
"epoch": 64.84375,
"eval_loss": 0.4436146914958954,
"eval_micro_f1": 0.9552683891619415,
"step": 41500
},
{
"epoch": 65.234375,
"eval_loss": 0.4417327344417572,
"eval_micro_f1": 0.9565335256159445,
"step": 41750
},
{
"epoch": 65.625,
"learning_rate": 7.8125e-06,
"loss": 0.00310700798034668,
"step": 42000
},
{
"epoch": 65.625,
"eval_loss": 0.44122764468193054,
"eval_micro_f1": 0.955900957388943,
"step": 42000
},
{
"epoch": 66.015625,
"eval_loss": 0.4555808901786804,
"eval_micro_f1": 0.9557202236097997,
"step": 42250
},
{
"epoch": 66.40625,
"learning_rate": 7.786458333333334e-06,
"loss": 0.001553797483444214,
"step": 42500
},
{
"epoch": 66.40625,
"eval_loss": 0.4602338373661041,
"eval_micro_f1": 0.9549972884932264,
"step": 42500
},
{
"epoch": 66.796875,
"eval_loss": 0.4758880138397217,
"eval_micro_f1": 0.9521055480269336,
"step": 42750
},
{
"epoch": 67.1875,
"learning_rate": 7.760416666666666e-06,
"loss": 0.0026735084056854247,
"step": 43000
},
{
"epoch": 67.1875,
"eval_loss": 0.45357489585876465,
"eval_micro_f1": 0.9543647202662249,
"step": 43000
},
{
"epoch": 67.578125,
"eval_loss": 0.44592177867889404,
"eval_micro_f1": 0.9542743533766532,
"step": 43250
},
{
"epoch": 67.96875,
"learning_rate": 7.734375e-06,
"loss": 0.002014574289321899,
"step": 43500
},
{
"epoch": 67.96875,
"eval_loss": 0.45128655433654785,
"eval_micro_f1": 0.9572564607325178,
"step": 43500
},
{
"epoch": 68.359375,
"eval_loss": 0.45038333535194397,
"eval_micro_f1": 0.9566238925055163,
"step": 43750
},
{
"epoch": 68.75,
"learning_rate": 7.708333333333334e-06,
"loss": 0.0028191041946411134,
"step": 44000
},
{
"epoch": 68.75,
"eval_loss": 0.4510774612426758,
"eval_micro_f1": 0.9550876553827982,
"step": 44000
},
{
"epoch": 69.140625,
"eval_loss": 0.4548089802265167,
"eval_micro_f1": 0.9557202236097997,
"step": 44250
},
{
"epoch": 69.53125,
"learning_rate": 7.682291666666668e-06,
"loss": 0.002224735498428345,
"step": 44500
},
{
"epoch": 69.53125,
"eval_loss": 0.4716925621032715,
"eval_micro_f1": 0.9547261878245115,
"step": 44500
},
{
"epoch": 69.921875,
"eval_loss": 0.45062172412872314,
"eval_micro_f1": 0.9541839864870816,
"step": 44750
},
{
"epoch": 70.3125,
"learning_rate": 7.656250000000001e-06,
"loss": 0.002732285499572754,
"step": 45000
},
{
"epoch": 70.3125,
"eval_loss": 0.46174412965774536,
"eval_micro_f1": 0.955900957388943,
"step": 45000
},
{
"epoch": 70.703125,
"eval_loss": 0.44746488332748413,
"eval_micro_f1": 0.9551780222723698,
"step": 45250
},
{
"epoch": 71.09375,
"learning_rate": 7.630208333333334e-06,
"loss": 0.002997767448425293,
"step": 45500
},
{
"epoch": 71.09375,
"eval_loss": 0.4627792239189148,
"eval_micro_f1": 0.9547261878245115,
"step": 45500
},
{
"epoch": 71.484375,
"eval_loss": 0.4578235447406769,
"eval_micro_f1": 0.9561720580576579,
"step": 45750
},
{
"epoch": 71.875,
"learning_rate": 7.6041666666666666e-06,
"loss": 0.0035129733085632322,
"step": 46000
},
{
"epoch": 71.875,
"eval_loss": 0.47479936480522156,
"eval_micro_f1": 0.9551780222723698,
"step": 46000
},
{
"epoch": 72.265625,
"eval_loss": 0.4830751419067383,
"eval_micro_f1": 0.9521959149165052,
"step": 46250
},
{
"epoch": 72.65625,
"learning_rate": 7.578125e-06,
"loss": 0.002358717679977417,
"step": 46500
},
{
"epoch": 72.65625,
"eval_loss": 0.49385973811149597,
"eval_micro_f1": 0.9527381162539351,
"step": 46500
},
{
"epoch": 73.046875,
"eval_loss": 0.485090434551239,
"eval_micro_f1": 0.9513826129103604,
"step": 46750
},
{
"epoch": 73.4375,
"learning_rate": 7.552083333333334e-06,
"loss": 0.0024431445598602293,
"step": 47000
},
{
"epoch": 73.4375,
"eval_loss": 0.47454530000686646,
"eval_micro_f1": 0.9530092169226502,
"step": 47000
},
{
"epoch": 73.828125,
"eval_loss": 0.49554669857025146,
"eval_micro_f1": 0.9520151811373619,
"step": 47250
},
{
"epoch": 74.21875,
"learning_rate": 7.526041666666667e-06,
"loss": 0.002499669313430786,
"step": 47500
},
{
"epoch": 74.21875,
"eval_loss": 0.4643559455871582,
"eval_micro_f1": 0.955900957388943,
"step": 47500
},
{
"epoch": 74.609375,
"eval_loss": 0.4897753894329071,
"eval_micro_f1": 0.9521055480269336,
"step": 47750
},
{
"epoch": 75.0,
"learning_rate": 7.500000000000001e-06,
"loss": 0.002981294870376587,
"step": 48000
},
{
"epoch": 75.0,
"eval_loss": 0.4792202115058899,
"eval_micro_f1": 0.9541839864870816,
"step": 48000
},
{
"epoch": 75.390625,
"eval_loss": 0.45594480633735657,
"eval_micro_f1": 0.955629856720228,
"step": 48250
},
{
"epoch": 75.78125,
"learning_rate": 7.473958333333334e-06,
"loss": 0.0021955225467681885,
"step": 48500
},
{
"epoch": 75.78125,
"eval_loss": 0.44637104868888855,
"eval_micro_f1": 0.9561720580576579,
"step": 48500
},
{
"epoch": 76.171875,
"eval_loss": 0.4405333697795868,
"eval_micro_f1": 0.9572564607325178,
"step": 48750
},
{
"epoch": 76.5625,
"learning_rate": 7.447916666666667e-06,
"loss": 0.0020350840091705323,
"step": 49000
},
{
"epoch": 76.5625,
"eval_loss": 0.48498404026031494,
"eval_micro_f1": 0.9518344473582186,
"step": 49000
},
{
"epoch": 76.953125,
"eval_loss": 0.4864804446697235,
"eval_micro_f1": 0.9543647202662249,
"step": 49250
},
{
"epoch": 77.34375,
"learning_rate": 7.421875000000001e-06,
"loss": 0.002485860824584961,
"step": 49500
},
{
"epoch": 77.34375,
"eval_loss": 0.47656679153442383,
"eval_micro_f1": 0.9537321520392233,
"step": 49500
},
{
"epoch": 77.734375,
"eval_loss": 0.471832811832428,
"eval_micro_f1": 0.9541839864870816,
"step": 49750
},
{
"epoch": 78.125,
"learning_rate": 7.395833333333335e-06,
"loss": 0.002093456983566284,
"step": 50000
},
{
"epoch": 78.125,
"eval_loss": 0.48530158400535583,
"eval_micro_f1": 0.9550876553827982,
"step": 50000
},
{
"epoch": 78.515625,
"eval_loss": 0.5012282729148865,
"eval_micro_f1": 0.951744080468647,
"step": 50250
},
{
"epoch": 78.90625,
"learning_rate": 7.369791666666667e-06,
"loss": 0.0027083990573883057,
"step": 50500
},
{
"epoch": 78.90625,
"eval_loss": 0.48788008093833923,
"eval_micro_f1": 0.9527381162539351,
"step": 50500
},
{
"epoch": 79.296875,
"eval_loss": 0.488650381565094,
"eval_micro_f1": 0.9549972884932264,
"step": 50750
},
{
"epoch": 79.6875,
"learning_rate": 7.343750000000001e-06,
"loss": 0.0016907109022140502,
"step": 51000
},
{
"epoch": 79.6875,
"eval_loss": 0.5115341544151306,
"eval_micro_f1": 0.9516537135790754,
"step": 51000
},
{
"epoch": 80.078125,
"eval_loss": 0.4950931966304779,
"eval_micro_f1": 0.9521055480269336,
"step": 51250
},
{
"epoch": 80.46875,
"learning_rate": 7.3177083333333345e-06,
"loss": 0.0021991755962371827,
"step": 51500
},
{
"epoch": 80.46875,
"eval_loss": 0.49377667903900146,
"eval_micro_f1": 0.9540032527079383,
"step": 51500
},
{
"epoch": 80.859375,
"eval_loss": 0.46162134408950806,
"eval_micro_f1": 0.9560816911680863,
"step": 51750
},
{
"epoch": 81.25,
"learning_rate": 7.291666666666667e-06,
"loss": 0.0024211430549621583,
"step": 52000
},
{
"epoch": 81.25,
"eval_loss": 0.475384920835495,
"eval_micro_f1": 0.9536417851496517,
"step": 52000
},
{
"epoch": 81.640625,
"eval_loss": 0.4879942536354065,
"eval_micro_f1": 0.9542743533766532,
"step": 52250
},
{
"epoch": 82.03125,
"learning_rate": 7.265625e-06,
"loss": 0.0020658926963806152,
"step": 52500
},
{
"epoch": 82.03125,
"eval_loss": 0.48459747433662415,
"eval_micro_f1": 0.9533706844809368,
"step": 52500
},
{
"epoch": 82.421875,
"eval_loss": 0.4901907444000244,
"eval_micro_f1": 0.9532803175913651,
"step": 52750
},
{
"epoch": 82.8125,
"learning_rate": 7.239583333333334e-06,
"loss": 0.0018260172605514527,
"step": 53000
},
{
"epoch": 82.8125,
"eval_loss": 0.4930051267147064,
"eval_micro_f1": 0.9534610513705084,
"step": 53000
},
{
"epoch": 83.203125,
"eval_loss": 0.5144211053848267,
"eval_micro_f1": 0.9511115122416454,
"step": 53250
},
{
"epoch": 83.59375,
"learning_rate": 7.213541666666667e-06,
"loss": 0.002775990962982178,
"step": 53500
},
{
"epoch": 83.59375,
"eval_loss": 0.48391565680503845,
"eval_micro_f1": 0.953822518928795,
"step": 53500
},
{
"epoch": 83.984375,
"eval_loss": 0.4679352045059204,
"eval_micro_f1": 0.9542743533766532,
"step": 53750
},
{
"epoch": 84.375,
"learning_rate": 7.1875e-06,
"loss": 0.0023252568244934084,
"step": 54000
},
{
"epoch": 84.375,
"eval_loss": 0.46378326416015625,
"eval_micro_f1": 0.9566238925055163,
"step": 54000
},
{
"epoch": 84.765625,
"eval_loss": 0.481300413608551,
"eval_micro_f1": 0.9559913242785146,
"step": 54250
},
{
"epoch": 85.15625,
"learning_rate": 7.161458333333334e-06,
"loss": 0.0021955559253692626,
"step": 54500
},
{
"epoch": 85.15625,
"eval_loss": 0.4885358512401581,
"eval_micro_f1": 0.9548165547140831,
"step": 54500
},
{
"epoch": 85.546875,
"eval_loss": 0.4550429880619049,
"eval_micro_f1": 0.9573468276220894,
"step": 54750
},
{
"epoch": 85.9375,
"learning_rate": 7.135416666666667e-06,
"loss": 0.002524984836578369,
"step": 55000
},
{
"epoch": 85.9375,
"eval_loss": 0.4919373095035553,
"eval_micro_f1": 0.9553587560515131,
"step": 55000
},
{
"epoch": 86.328125,
"eval_loss": 0.4945307672023773,
"eval_micro_f1": 0.9540032527079383,
"step": 55250
},
{
"epoch": 86.71875,
"learning_rate": 7.109375000000001e-06,
"loss": 0.0017629317045211792,
"step": 55500
},
{
"epoch": 86.71875,
"eval_loss": 0.4791640639305115,
"eval_micro_f1": 0.9560816911680863,
"step": 55500
},
{
"epoch": 87.109375,
"eval_loss": 0.4697716534137726,
"eval_micro_f1": 0.9555394898306564,
"step": 55750
},
{
"epoch": 87.5,
"learning_rate": 7.083333333333335e-06,
"loss": 0.002000133514404297,
"step": 56000
},
{
"epoch": 87.5,
"eval_loss": 0.47411954402923584,
"eval_micro_f1": 0.9568949931742312,
"step": 56000
},
{
"epoch": 87.890625,
"eval_loss": 0.4790748655796051,
"eval_micro_f1": 0.9558105904993713,
"step": 56250
},
{
"epoch": 88.28125,
"learning_rate": 7.057291666666667e-06,
"loss": 0.0017289879322052002,
"step": 56500
},
{
"epoch": 88.28125,
"eval_loss": 0.48500174283981323,
"eval_micro_f1": 0.9549972884932264,
"step": 56500
},
{
"epoch": 88.671875,
"eval_loss": 0.4781242907047272,
"eval_micro_f1": 0.9547261878245115,
"step": 56750
},
{
"epoch": 89.0625,
"learning_rate": 7.031250000000001e-06,
"loss": 0.0027364423274993895,
"step": 57000
},
{
"epoch": 89.0625,
"eval_loss": 0.49343815445899963,
"eval_micro_f1": 0.9531899507017935,
"step": 57000
},
{
"epoch": 89.453125,
"eval_loss": 0.49449023604393005,
"eval_micro_f1": 0.9545454540453682,
"step": 57250
},
{
"epoch": 89.84375,
"learning_rate": 7.0052083333333345e-06,
"loss": 0.0023274903297424315,
"step": 57500
},
{
"epoch": 89.84375,
"eval_loss": 0.4677713215351105,
"eval_micro_f1": 0.9540032527079383,
"step": 57500
},
{
"epoch": 90.234375,
"eval_loss": 0.48951372504234314,
"eval_micro_f1": 0.9546358209349399,
"step": 57750
},
{
"epoch": 90.625,
"learning_rate": 6.979166666666667e-06,
"loss": 0.0016663209199905395,
"step": 58000
},
{
"epoch": 90.625,
"eval_loss": 0.49210092425346375,
"eval_micro_f1": 0.9547261878245115,
"step": 58000
},
{
"epoch": 91.015625,
"eval_loss": 0.49002575874328613,
"eval_micro_f1": 0.9533706844809368,
"step": 58250
},
{
"epoch": 91.40625,
"learning_rate": 6.9531250000000004e-06,
"loss": 0.002302605628967285,
"step": 58500
},
{
"epoch": 91.40625,
"eval_loss": 0.48044490814208984,
"eval_micro_f1": 0.9549069216036549,
"step": 58500
},
{
"epoch": 91.796875,
"eval_loss": 0.4660518765449524,
"eval_micro_f1": 0.9551780222723698,
"step": 58750
},
{
"epoch": 92.1875,
"learning_rate": 6.927083333333334e-06,
"loss": 0.002198941707611084,
"step": 59000
},
{
"epoch": 92.1875,
"eval_loss": 0.4683954119682312,
"eval_micro_f1": 0.9557202236097997,
"step": 59000
},
{
"epoch": 92.578125,
"eval_loss": 0.46796247363090515,
"eval_micro_f1": 0.9561720580576579,
"step": 59250
},
{
"epoch": 92.96875,
"learning_rate": 6.901041666666667e-06,
"loss": 0.002277945041656494,
"step": 59500
},
{
"epoch": 92.96875,
"eval_loss": 0.45878687500953674,
"eval_micro_f1": 0.9567142593950879,
"step": 59500
},
{
"epoch": 93.359375,
"eval_loss": 0.47060781717300415,
"eval_micro_f1": 0.9546358209349399,
"step": 59750
},
{
"epoch": 93.75,
"learning_rate": 6.875e-06,
"loss": 0.0018320727348327638,
"step": 60000
},
{
"epoch": 93.75,
"eval_loss": 0.49141716957092285,
"eval_micro_f1": 0.9540032527079383,
"step": 60000
},
{
"epoch": 94.140625,
"eval_loss": 0.5055791735649109,
"eval_micro_f1": 0.9532803175913651,
"step": 60250
},
{
"epoch": 94.53125,
"learning_rate": 6.848958333333334e-06,
"loss": 0.0015210705995559693,
"step": 60500
},
{
"epoch": 94.53125,
"eval_loss": 0.49519988894462585,
"eval_micro_f1": 0.9545454540453682,
"step": 60500
},
{
"epoch": 94.921875,
"eval_loss": 0.4903446435928345,
"eval_micro_f1": 0.9545454540453682,
"step": 60750
},
{
"epoch": 95.3125,
"learning_rate": 6.822916666666667e-06,
"loss": 0.0022848103046417237,
"step": 61000
},
{
"epoch": 95.3125,
"eval_loss": 0.503937304019928,
"eval_micro_f1": 0.95355141826008,
"step": 61000
},
{
"epoch": 95.703125,
"eval_loss": 0.4825381338596344,
"eval_micro_f1": 0.9544550871557965,
"step": 61250
},
{
"epoch": 96.09375,
"learning_rate": 6.796875000000001e-06,
"loss": 0.00252921724319458,
"step": 61500
},
{
"epoch": 96.09375,
"eval_loss": 0.47266891598701477,
"eval_micro_f1": 0.9533706844809368,
"step": 61500
},
{
"epoch": 96.484375,
"eval_loss": 0.49913957715034485,
"eval_micro_f1": 0.9526477493643635,
"step": 61750
},
{
"epoch": 96.875,
"learning_rate": 6.770833333333334e-06,
"loss": 0.0019248281717300416,
"step": 62000
},
{
"epoch": 96.875,
"eval_loss": 0.48467129468917847,
"eval_micro_f1": 0.9540032527079383,
"step": 62000
},
{
"epoch": 97.265625,
"eval_loss": 0.4900929033756256,
"eval_micro_f1": 0.9537321520392233,
"step": 62250
},
{
"epoch": 97.65625,
"learning_rate": 6.744791666666667e-06,
"loss": 0.0021258397102355956,
"step": 62500
},
{
"epoch": 97.65625,
"eval_loss": 0.4734007716178894,
"eval_micro_f1": 0.9549069216036549,
"step": 62500
},
{
"epoch": 98.046875,
"eval_loss": 0.4875606894493103,
"eval_micro_f1": 0.9543647202662249,
"step": 62750
},
{
"epoch": 98.4375,
"learning_rate": 6.718750000000001e-06,
"loss": 0.001915825843811035,
"step": 63000
},
{
"epoch": 98.4375,
"eval_loss": 0.5087093114852905,
"eval_micro_f1": 0.9529188500330784,
"step": 63000
},
{
"epoch": 98.828125,
"eval_loss": 0.4745830297470093,
"eval_micro_f1": 0.9527381162539351,
"step": 63250
},
{
"epoch": 99.21875,
"learning_rate": 6.6927083333333345e-06,
"loss": 0.002059025287628174,
"step": 63500
},
{
"epoch": 99.21875,
"eval_loss": 0.48629626631736755,
"eval_micro_f1": 0.9542743533766532,
"step": 63500
},
{
"epoch": 99.609375,
"eval_loss": 0.47800007462501526,
"eval_micro_f1": 0.9541839864870816,
"step": 63750
},
{
"epoch": 100.0,
"learning_rate": 6.666666666666667e-06,
"loss": 0.002289721965789795,
"step": 64000
},
{
"epoch": 100.0,
"eval_loss": 0.4688805937767029,
"eval_micro_f1": 0.9549972884932264,
"step": 64000
},
{
"epoch": 100.390625,
"eval_loss": 0.47758203744888306,
"eval_micro_f1": 0.9552683891619415,
"step": 64250
},
{
"epoch": 100.78125,
"learning_rate": 6.6406250000000005e-06,
"loss": 0.0018642715215682983,
"step": 64500
},
{
"epoch": 100.78125,
"eval_loss": 0.47510960698127747,
"eval_micro_f1": 0.9555394898306564,
"step": 64500
},
{
"epoch": 101.171875,
"eval_loss": 0.4897288382053375,
"eval_micro_f1": 0.9546358209349399,
"step": 64750
},
{
"epoch": 101.5625,
"learning_rate": 6.614583333333334e-06,
"loss": 0.001942821741104126,
"step": 65000
},
{
"epoch": 101.5625,
"eval_loss": 0.4843326807022095,
"eval_micro_f1": 0.9560816911680863,
"step": 65000
},
{
"epoch": 101.953125,
"eval_loss": 0.4883817732334137,
"eval_micro_f1": 0.9540032527079383,
"step": 65250
},
{
"epoch": 102.34375,
"learning_rate": 6.5885416666666664e-06,
"loss": 0.0018447362184524536,
"step": 65500
},
{
"epoch": 102.34375,
"eval_loss": 0.48431694507598877,
"eval_micro_f1": 0.9549069216036549,
"step": 65500
},
{
"epoch": 102.734375,
"eval_loss": 0.48874521255493164,
"eval_micro_f1": 0.9555394898306564,
"step": 65750
},
{
"epoch": 103.125,
"learning_rate": 6.5625e-06,
"loss": 0.0017244215011596679,
"step": 66000
},
{
"epoch": 103.125,
"eval_loss": 0.49347972869873047,
"eval_micro_f1": 0.9550876553827982,
"step": 66000
},
{
"epoch": 103.515625,
"eval_loss": 0.49385011196136475,
"eval_micro_f1": 0.9552683891619415,
"step": 66250
},
{
"epoch": 103.90625,
"learning_rate": 6.536458333333334e-06,
"loss": 0.001685309886932373,
"step": 66500
},
{
"epoch": 103.90625,
"eval_loss": 0.48293107748031616,
"eval_micro_f1": 0.9568046262846596,
"step": 66500
},
{
"epoch": 104.296875,
"eval_loss": 0.5344578623771667,
"eval_micro_f1": 0.9501174764563572,
"step": 66750
},
{
"epoch": 104.6875,
"learning_rate": 6.510416666666667e-06,
"loss": 0.0011567432880401612,
"step": 67000
},
{
"epoch": 104.6875,
"eval_loss": 0.5163060426712036,
"eval_micro_f1": 0.9515633466895037,
"step": 67000
},
{
"epoch": 105.078125,
"eval_loss": 0.5108720064163208,
"eval_micro_f1": 0.9530995838122216,
"step": 67250
},
{
"epoch": 105.46875,
"learning_rate": 6.484375000000001e-06,
"loss": 0.0021894519329071047,
"step": 67500
},
{
"epoch": 105.46875,
"eval_loss": 0.48115983605384827,
"eval_micro_f1": 0.9565335256159445,
"step": 67500
},
{
"epoch": 105.859375,
"eval_loss": 0.47960832715034485,
"eval_micro_f1": 0.9549069216036549,
"step": 67750
},
{
"epoch": 106.25,
"learning_rate": 6.458333333333334e-06,
"loss": 0.001834203839302063,
"step": 68000
},
{
"epoch": 106.25,
"eval_loss": 0.48520734906196594,
"eval_micro_f1": 0.9554491229410847,
"step": 68000
},
{
"epoch": 106.640625,
"eval_loss": 0.4825701415538788,
"eval_micro_f1": 0.9539128858183666,
"step": 68250
},
{
"epoch": 107.03125,
"learning_rate": 6.432291666666667e-06,
"loss": 0.0016704331636428833,
"step": 68500
},
{
"epoch": 107.03125,
"eval_loss": 0.5040125250816345,
"eval_micro_f1": 0.9540032527079383,
"step": 68500
},
{
"epoch": 107.421875,
"eval_loss": 0.47774025797843933,
"eval_micro_f1": 0.9560816911680863,
"step": 68750
},
{
"epoch": 107.8125,
"learning_rate": 6.406250000000001e-06,
"loss": 0.0015281115770339965,
"step": 69000
},
{
"epoch": 107.8125,
"eval_loss": 0.4911847412586212,
"eval_micro_f1": 0.9551780222723698,
"step": 69000
},
{
"epoch": 108.203125,
"eval_loss": 0.5112791657447815,
"eval_micro_f1": 0.9539128858183666,
"step": 69250
},
{
"epoch": 108.59375,
"learning_rate": 6.3802083333333345e-06,
"loss": 0.00198592209815979,
"step": 69500
},
{
"epoch": 108.59375,
"eval_loss": 0.47339317202568054,
"eval_micro_f1": 0.9563527918368012,
"step": 69500
},
{
"epoch": 108.984375,
"eval_loss": 0.46538305282592773,
"eval_micro_f1": 0.9554491229410847,
"step": 69750
},
{
"epoch": 109.375,
"learning_rate": 6.354166666666667e-06,
"loss": 0.002657374620437622,
"step": 70000
},
{
"epoch": 109.375,
"eval_loss": 0.47396034002304077,
"eval_micro_f1": 0.9558105904993713,
"step": 70000
},
{
"epoch": 109.765625,
"eval_loss": 0.44200068712234497,
"eval_micro_f1": 0.9582504965178059,
"step": 70250
},
{
"epoch": 110.15625,
"learning_rate": 6.3281250000000005e-06,
"loss": 0.0017114403247833253,
"step": 70500
},
{
"epoch": 110.15625,
"eval_loss": 0.4598837196826935,
"eval_micro_f1": 0.9559913242785146,
"step": 70500
},
{
"epoch": 110.546875,
"eval_loss": 0.4613502323627472,
"eval_micro_f1": 0.9577986620699477,
"step": 70750
},
{
"epoch": 110.9375,
"learning_rate": 6.302083333333334e-06,
"loss": 0.0016733938455581665,
"step": 71000
},
{
"epoch": 110.9375,
"eval_loss": 0.5067228674888611,
"eval_micro_f1": 0.9526477493643635,
"step": 71000
},
{
"epoch": 111.328125,
"eval_loss": 0.45689287781715393,
"eval_micro_f1": 0.9568046262846596,
"step": 71250
},
{
"epoch": 111.71875,
"learning_rate": 6.2760416666666665e-06,
"loss": 0.001667667269706726,
"step": 71500
},
{
"epoch": 111.71875,
"eval_loss": 0.4848833680152893,
"eval_micro_f1": 0.9559913242785146,
"step": 71500
},
{
"epoch": 112.109375,
"eval_loss": 0.5001658201217651,
"eval_micro_f1": 0.9537321520392233,
"step": 71750
},
{
"epoch": 112.5,
"learning_rate": 6.25e-06,
"loss": 0.0019739651679992675,
"step": 72000
},
{
"epoch": 112.5,
"eval_loss": 0.48745259642601013,
"eval_micro_f1": 0.9551780222723698,
"step": 72000
},
{
"epoch": 112.890625,
"eval_loss": 0.4806417226791382,
"eval_micro_f1": 0.9565335256159445,
"step": 72250
},
{
"epoch": 113.28125,
"learning_rate": 6.223958333333334e-06,
"loss": 0.0011185383796691894,
"step": 72500
},
{
"epoch": 113.28125,
"eval_loss": 0.49310290813446045,
"eval_micro_f1": 0.9558105904993713,
"step": 72500
},
{
"epoch": 113.671875,
"eval_loss": 0.48347705602645874,
"eval_micro_f1": 0.9557202236097997,
"step": 72750
},
{
"epoch": 114.0625,
"learning_rate": 6.197916666666667e-06,
"loss": 0.001661333441734314,
"step": 73000
},
{
"epoch": 114.0625,
"eval_loss": 0.49293068051338196,
"eval_micro_f1": 0.9564431587263729,
"step": 73000
},
{
"epoch": 114.453125,
"eval_loss": 0.4897063076496124,
"eval_micro_f1": 0.9549069216036549,
"step": 73250
},
{
"epoch": 114.84375,
"learning_rate": 6.171875e-06,
"loss": 0.0015794031620025635,
"step": 73500
},
{
"epoch": 114.84375,
"eval_loss": 0.46339982748031616,
"eval_micro_f1": 0.9580697627386626,
"step": 73500
},
{
"epoch": 115.234375,
"eval_loss": 0.4552219808101654,
"eval_micro_f1": 0.9561720580576579,
"step": 73750
},
{
"epoch": 115.625,
"learning_rate": 6.145833333333334e-06,
"loss": 0.002178269863128662,
"step": 74000
},
{
"epoch": 115.625,
"eval_loss": 0.4753931164741516,
"eval_micro_f1": 0.9563527918368012,
"step": 74000
},
{
"epoch": 116.015625,
"eval_loss": 0.46642887592315674,
"eval_micro_f1": 0.9564431587263729,
"step": 74250
},
{
"epoch": 116.40625,
"learning_rate": 6.119791666666667e-06,
"loss": 0.0020141665935516358,
"step": 74500
},
{
"epoch": 116.40625,
"eval_loss": 0.46825623512268066,
"eval_micro_f1": 0.9568046262846596,
"step": 74500
},
{
"epoch": 116.796875,
"eval_loss": 0.4602838456630707,
"eval_micro_f1": 0.9578890289595193,
"step": 74750
},
{
"epoch": 117.1875,
"learning_rate": 6.093750000000001e-06,
"loss": 0.002131371974945068,
"step": 75000
},
{
"epoch": 117.1875,
"eval_loss": 0.4559440612792969,
"eval_micro_f1": 0.955900957388943,
"step": 75000
},
{
"epoch": 117.578125,
"eval_loss": 0.4531676173210144,
"eval_micro_f1": 0.9571660938429462,
"step": 75250
},
{
"epoch": 117.96875,
"learning_rate": 6.0677083333333346e-06,
"loss": 0.0013822354078292848,
"step": 75500
},
{
"epoch": 117.96875,
"eval_loss": 0.44739657640457153,
"eval_micro_f1": 0.9569853600638029,
"step": 75500
},
{
"epoch": 118.359375,
"eval_loss": 0.455036461353302,
"eval_micro_f1": 0.9564431587263729,
"step": 75750
},
{
"epoch": 118.75,
"learning_rate": 6.041666666666667e-06,
"loss": 0.0008003501296043396,
"step": 76000
},
{
"epoch": 118.75,
"eval_loss": 0.47583281993865967,
"eval_micro_f1": 0.9557202236097997,
"step": 76000
},
{
"epoch": 119.140625,
"eval_loss": 0.45802202820777893,
"eval_micro_f1": 0.9573468276220894,
"step": 76250
},
{
"epoch": 119.53125,
"learning_rate": 6.0156250000000005e-06,
"loss": 0.001308007001876831,
"step": 76500
},
{
"epoch": 119.53125,
"eval_loss": 0.4517691433429718,
"eval_micro_f1": 0.9589734316343792,
"step": 76500
},
{
"epoch": 119.921875,
"eval_loss": 0.45664095878601074,
"eval_micro_f1": 0.9576179282908044,
"step": 76750
},
{
"epoch": 120.3125,
"learning_rate": 5.989583333333334e-06,
"loss": 0.0017539136409759522,
"step": 77000
},
{
"epoch": 120.3125,
"eval_loss": 0.45444396138191223,
"eval_micro_f1": 0.9577986620699477,
"step": 77000
},
{
"epoch": 120.703125,
"eval_loss": 0.44284310936927795,
"eval_micro_f1": 0.9575275614012327,
"step": 77250
},
{
"epoch": 121.09375,
"learning_rate": 5.9635416666666665e-06,
"loss": 0.0018911951780319215,
"step": 77500
},
{
"epoch": 121.09375,
"eval_loss": 0.4578006863594055,
"eval_micro_f1": 0.9578890289595193,
"step": 77500
},
{
"epoch": 121.484375,
"eval_loss": 0.4757349491119385,
"eval_micro_f1": 0.9563527918368012,
"step": 77750
},
{
"epoch": 121.875,
"learning_rate": 5.9375e-06,
"loss": 0.001980394244194031,
"step": 78000
},
{
"epoch": 121.875,
"eval_loss": 0.46946921944618225,
"eval_micro_f1": 0.9570757269533745,
"step": 78000
},
{
"epoch": 122.265625,
"eval_loss": 0.46618929505348206,
"eval_micro_f1": 0.9565335256159445,
"step": 78250
},
{
"epoch": 122.65625,
"learning_rate": 5.911458333333334e-06,
"loss": 0.0022814586162567137,
"step": 78500
},
{
"epoch": 122.65625,
"eval_loss": 0.45111116766929626,
"eval_micro_f1": 0.9578890289595193,
"step": 78500
},
{
"epoch": 123.046875,
"eval_loss": 0.4752413332462311,
"eval_micro_f1": 0.955629856720228,
"step": 78750
},
{
"epoch": 123.4375,
"learning_rate": 5.885416666666667e-06,
"loss": 0.0009786565303802491,
"step": 79000
},
{
"epoch": 123.4375,
"eval_loss": 0.4820725917816162,
"eval_micro_f1": 0.9543647202662249,
"step": 79000
},
{
"epoch": 123.828125,
"eval_loss": 0.4637223780155182,
"eval_micro_f1": 0.9564431587263729,
"step": 79250
},
{
"epoch": 124.21875,
"learning_rate": 5.859375e-06,
"loss": 0.0011963229179382325,
"step": 79500
},
{
"epoch": 124.21875,
"eval_loss": 0.46158409118652344,
"eval_micro_f1": 0.9565335256159445,
"step": 79500
},
{
"epoch": 124.609375,
"eval_loss": 0.48602670431137085,
"eval_micro_f1": 0.9553587560515131,
"step": 79750
},
{
"epoch": 125.0,
"learning_rate": 5.833333333333334e-06,
"loss": 0.0010341901779174804,
"step": 80000
},
{
"epoch": 125.0,
"eval_loss": 0.4955455958843231,
"eval_micro_f1": 0.9542743533766532,
"step": 80000
},
{
"epoch": 125.390625,
"eval_loss": 0.4932277798652649,
"eval_micro_f1": 0.9533706844809368,
"step": 80250
},
{
"epoch": 125.78125,
"learning_rate": 5.807291666666667e-06,
"loss": 0.0018729145526885987,
"step": 80500
},
{
"epoch": 125.78125,
"eval_loss": 0.4936227798461914,
"eval_micro_f1": 0.9531899507017935,
"step": 80500
},
{
"epoch": 126.171875,
"eval_loss": 0.48130080103874207,
"eval_micro_f1": 0.9558105904993713,
"step": 80750
},
{
"epoch": 126.5625,
"learning_rate": 5.781250000000001e-06,
"loss": 0.0016083452701568604,
"step": 81000
},
{
"epoch": 126.5625,
"eval_loss": 0.4902788996696472,
"eval_micro_f1": 0.9547261878245115,
"step": 81000
},
{
"epoch": 126.953125,
"eval_loss": 0.478575199842453,
"eval_micro_f1": 0.9559913242785146,
"step": 81250
},
{
"epoch": 127.34375,
"learning_rate": 5.755208333333335e-06,
"loss": 0.0019021440744400025,
"step": 81500
},
{
"epoch": 127.34375,
"eval_loss": 0.46817725896835327,
"eval_micro_f1": 0.9568949931742312,
"step": 81500
},
{
"epoch": 127.734375,
"eval_loss": 0.5080971717834473,
"eval_micro_f1": 0.9537321520392233,
"step": 81750
},
{
"epoch": 128.125,
"learning_rate": 5.729166666666667e-06,
"loss": 0.0011152828931808472,
"step": 82000
},
{
"epoch": 128.125,
"eval_loss": 0.4870184063911438,
"eval_micro_f1": 0.9548165547140831,
"step": 82000
},
{
"epoch": 128.515625,
"eval_loss": 0.4859660267829895,
"eval_micro_f1": 0.9550876553827982,
"step": 82250
},
{
"epoch": 128.90625,
"learning_rate": 5.7031250000000006e-06,
"loss": 0.0014413068294525148,
"step": 82500
},
{
"epoch": 128.90625,
"eval_loss": 0.483054518699646,
"eval_micro_f1": 0.9558105904993713,
"step": 82500
},
{
"epoch": 129.296875,
"eval_loss": 0.4892100691795349,
"eval_micro_f1": 0.955629856720228,
"step": 82750
},
{
"epoch": 129.6875,
"learning_rate": 5.677083333333334e-06,
"loss": 0.0008179132342338562,
"step": 83000
},
{
"epoch": 129.6875,
"eval_loss": 0.4885927736759186,
"eval_micro_f1": 0.9565335256159445,
"step": 83000
},
{
"epoch": 130.078125,
"eval_loss": 0.46208667755126953,
"eval_micro_f1": 0.9570757269533745,
"step": 83250
},
{
"epoch": 130.46875,
"learning_rate": 5.6510416666666665e-06,
"loss": 0.00198653781414032,
"step": 83500
},
{
"epoch": 130.46875,
"eval_loss": 0.49356088042259216,
"eval_micro_f1": 0.9545454540453682,
"step": 83500
},
{
"epoch": 130.859375,
"eval_loss": 0.4530411958694458,
"eval_micro_f1": 0.9573468276220894,
"step": 83750
},
{
"epoch": 131.25,
"learning_rate": 5.625e-06,
"loss": 0.0018807079792022706,
"step": 84000
},
{
"epoch": 131.25,
"eval_loss": 0.4840020537376404,
"eval_micro_f1": 0.9552683891619415,
"step": 84000
},
{
"epoch": 131.640625,
"eval_loss": 0.46675539016723633,
"eval_micro_f1": 0.9574371945116611,
"step": 84250
},
{
"epoch": 132.03125,
"learning_rate": 5.598958333333334e-06,
"loss": 0.0010489890575408937,
"step": 84500
},
{
"epoch": 132.03125,
"eval_loss": 0.47622087597846985,
"eval_micro_f1": 0.9567142593950879,
"step": 84500
},
{
"epoch": 132.421875,
"eval_loss": 0.45651882886886597,
"eval_micro_f1": 0.9581601296282343,
"step": 84750
},
{
"epoch": 132.8125,
"learning_rate": 5.572916666666667e-06,
"loss": 0.000915440320968628,
"step": 85000
},
{
"epoch": 132.8125,
"eval_loss": 0.4659966826438904,
"eval_micro_f1": 0.9588830647448077,
"step": 85000
},
{
"epoch": 133.203125,
"eval_loss": 0.47744855284690857,
"eval_micro_f1": 0.957979395849091,
"step": 85250
},
{
"epoch": 133.59375,
"learning_rate": 5.546875e-06,
"loss": 0.000913662850856781,
"step": 85500
},
{
"epoch": 133.59375,
"eval_loss": 0.47570568323135376,
"eval_micro_f1": 0.957979395849091,
"step": 85500
},
{
"epoch": 133.984375,
"eval_loss": 0.47211819887161255,
"eval_micro_f1": 0.9573468276220894,
"step": 85750
},
{
"epoch": 134.375,
"learning_rate": 5.520833333333334e-06,
"loss": 0.001812052607536316,
"step": 86000
},
{
"epoch": 134.375,
"eval_loss": 0.48618432879447937,
"eval_micro_f1": 0.9545454540453682,
"step": 86000
},
{
"epoch": 134.765625,
"eval_loss": 0.48798438906669617,
"eval_micro_f1": 0.9554491229410847,
"step": 86250
},
{
"epoch": 135.15625,
"learning_rate": 5.494791666666667e-06,
"loss": 0.0017163900136947631,
"step": 86500
},
{
"epoch": 135.15625,
"eval_loss": 0.4877680838108063,
"eval_micro_f1": 0.9567142593950879,
"step": 86500
},
{
"epoch": 135.546875,
"eval_loss": 0.4691210985183716,
"eval_micro_f1": 0.9568046262846596,
"step": 86750
},
{
"epoch": 135.9375,
"learning_rate": 5.468750000000001e-06,
"loss": 0.0017735313177108766,
"step": 87000
},
{
"epoch": 135.9375,
"eval_loss": 0.4566178023815155,
"eval_micro_f1": 0.9584312302969493,
"step": 87000
},
{
"epoch": 136.328125,
"eval_loss": 0.4712260365486145,
"eval_micro_f1": 0.9580697627386626,
"step": 87250
},
{
"epoch": 136.71875,
"learning_rate": 5.442708333333334e-06,
"loss": 0.001345875382423401,
"step": 87500
},
{
"epoch": 136.71875,
"eval_loss": 0.4661507308483124,
"eval_micro_f1": 0.957979395849091,
"step": 87500
},
{
"epoch": 137.109375,
"eval_loss": 0.46459558606147766,
"eval_micro_f1": 0.9573468276220894,
"step": 87750
},
{
"epoch": 137.5,
"learning_rate": 5.416666666666667e-06,
"loss": 0.0015607985258102417,
"step": 88000
},
{
"epoch": 137.5,
"eval_loss": 0.45446011424064636,
"eval_micro_f1": 0.9575275614012327,
"step": 88000
},
{
"epoch": 137.890625,
"eval_loss": 0.4627591371536255,
"eval_micro_f1": 0.9582504965178059,
"step": 88250
},
{
"epoch": 138.28125,
"learning_rate": 5.390625000000001e-06,
"loss": 0.0015689713954925538,
"step": 88500
},
{
"epoch": 138.28125,
"eval_loss": 0.4577704668045044,
"eval_micro_f1": 0.9583408634073777,
"step": 88500
},
{
"epoch": 138.671875,
"eval_loss": 0.46517786383628845,
"eval_micro_f1": 0.9590637985239509,
"step": 88750
},
{
"epoch": 139.0625,
"learning_rate": 5.364583333333334e-06,
"loss": 0.0014539624452590942,
"step": 89000
},
{
"epoch": 139.0625,
"eval_loss": 0.4680992662906647,
"eval_micro_f1": 0.9575275614012327,
"step": 89000
},
{
"epoch": 139.453125,
"eval_loss": 0.46736598014831543,
"eval_micro_f1": 0.957979395849091,
"step": 89250
},
{
"epoch": 139.84375,
"learning_rate": 5.3385416666666666e-06,
"loss": 0.001553522825241089,
"step": 89500
},
{
"epoch": 139.84375,
"eval_loss": 0.4783024489879608,
"eval_micro_f1": 0.9568046262846596,
"step": 89500
},
{
"epoch": 140.234375,
"eval_loss": 0.47698917984962463,
"eval_micro_f1": 0.9577986620699477,
"step": 89750
},
{
"epoch": 140.625,
"learning_rate": 5.3125e-06,
"loss": 0.0012228368520736694,
"step": 90000
},
{
"epoch": 140.625,
"eval_loss": 0.4828680753707886,
"eval_micro_f1": 0.9568046262846596,
"step": 90000
},
{
"epoch": 141.015625,
"eval_loss": 0.4879053235054016,
"eval_micro_f1": 0.9552683891619415,
"step": 90250
},
{
"epoch": 141.40625,
"learning_rate": 5.286458333333334e-06,
"loss": 0.0023292930126190188,
"step": 90500
},
{
"epoch": 141.40625,
"eval_loss": 0.47452378273010254,
"eval_micro_f1": 0.9567142593950879,
"step": 90500
},
{
"epoch": 141.796875,
"eval_loss": 0.48333415389060974,
"eval_micro_f1": 0.955629856720228,
"step": 90750
},
{
"epoch": 142.1875,
"learning_rate": 5.260416666666666e-06,
"loss": 0.0009778518080711365,
"step": 91000
},
{
"epoch": 142.1875,
"eval_loss": 0.4799218773841858,
"eval_micro_f1": 0.9558105904993713,
"step": 91000
},
{
"epoch": 142.578125,
"eval_loss": 0.4843633472919464,
"eval_micro_f1": 0.9554491229410847,
"step": 91250
},
{
"epoch": 142.96875,
"learning_rate": 5.234375e-06,
"loss": 0.0014442535638809204,
"step": 91500
},
{
"epoch": 142.96875,
"eval_loss": 0.4599187672138214,
"eval_micro_f1": 0.9583408634073777,
"step": 91500
},
{
"epoch": 143.359375,
"eval_loss": 0.4672365188598633,
"eval_micro_f1": 0.9583408634073777,
"step": 91750
},
{
"epoch": 143.75,
"learning_rate": 5.208333333333334e-06,
"loss": 0.001025896668434143,
"step": 92000
},
{
"epoch": 143.75,
"eval_loss": 0.4796949028968811,
"eval_micro_f1": 0.9568046262846596,
"step": 92000
},
{
"epoch": 144.140625,
"eval_loss": 0.46014097332954407,
"eval_micro_f1": 0.9588830647448077,
"step": 92250
},
{
"epoch": 144.53125,
"learning_rate": 5.182291666666667e-06,
"loss": 0.0010135362148284911,
"step": 92500
},
{
"epoch": 144.53125,
"eval_loss": 0.4803791642189026,
"eval_micro_f1": 0.9568046262846596,
"step": 92500
},
{
"epoch": 144.921875,
"eval_loss": 0.459188848733902,
"eval_micro_f1": 0.9571660938429462,
"step": 92750
},
{
"epoch": 145.3125,
"learning_rate": 5.156250000000001e-06,
"loss": 0.0017544155120849609,
"step": 93000
},
{
"epoch": 145.3125,
"eval_loss": 0.452279269695282,
"eval_micro_f1": 0.9572564607325178,
"step": 93000
},
{
"epoch": 145.703125,
"eval_loss": 0.4516051709651947,
"eval_micro_f1": 0.9594252660822374,
"step": 93250
},
{
"epoch": 146.09375,
"learning_rate": 5.130208333333334e-06,
"loss": 0.0013422099351882934,
"step": 93500
},
{
"epoch": 146.09375,
"eval_loss": 0.47804853320121765,
"eval_micro_f1": 0.9568949931742312,
"step": 93500
},
{
"epoch": 146.484375,
"eval_loss": 0.47818654775619507,
"eval_micro_f1": 0.9561720580576579,
"step": 93750
},
{
"epoch": 146.875,
"learning_rate": 5.104166666666667e-06,
"loss": 0.001085343360900879,
"step": 94000
},
{
"epoch": 146.875,
"eval_loss": 0.4857484996318817,
"eval_micro_f1": 0.9563527918368012,
"step": 94000
},
{
"epoch": 147.265625,
"eval_loss": 0.48884207010269165,
"eval_micro_f1": 0.9574371945116611,
"step": 94250
},
{
"epoch": 147.65625,
"learning_rate": 5.078125000000001e-06,
"loss": 0.0012642680406570435,
"step": 94500
},
{
"epoch": 147.65625,
"eval_loss": 0.48324593901634216,
"eval_micro_f1": 0.9574371945116611,
"step": 94500
},
{
"epoch": 148.046875,
"eval_loss": 0.505977988243103,
"eval_micro_f1": 0.9554491229410847,
"step": 94750
},
{
"epoch": 148.4375,
"learning_rate": 5.0520833333333344e-06,
"loss": 0.0012435098886489867,
"step": 95000
},
{
"epoch": 148.4375,
"eval_loss": 0.48819980025291443,
"eval_micro_f1": 0.9563527918368012,
"step": 95000
},
{
"epoch": 148.828125,
"eval_loss": 0.4745419919490814,
"eval_micro_f1": 0.9582504965178059,
"step": 95250
},
{
"epoch": 149.21875,
"learning_rate": 5.026041666666667e-06,
"loss": 0.0009713127613067627,
"step": 95500
},
{
"epoch": 149.21875,
"eval_loss": 0.48586732149124146,
"eval_micro_f1": 0.9565335256159445,
"step": 95500
},
{
"epoch": 149.609375,
"eval_loss": 0.4772854745388031,
"eval_micro_f1": 0.9568046262846596,
"step": 95750
},
{
"epoch": 150.0,
"learning_rate": 5e-06,
"loss": 0.001130869746208191,
"step": 96000
},
{
"epoch": 150.0,
"eval_loss": 0.4793156385421753,
"eval_micro_f1": 0.9576179282908044,
"step": 96000
},
{
"epoch": 150.390625,
"eval_loss": 0.48595643043518066,
"eval_micro_f1": 0.9572564607325178,
"step": 96250
},
{
"epoch": 150.78125,
"learning_rate": 4.973958333333333e-06,
"loss": 0.001210302710533142,
"step": 96500
},
{
"epoch": 150.78125,
"eval_loss": 0.4763987958431244,
"eval_micro_f1": 0.9566238925055163,
"step": 96500
},
{
"epoch": 151.171875,
"eval_loss": 0.4809951186180115,
"eval_micro_f1": 0.955900957388943,
"step": 96750
},
{
"epoch": 151.5625,
"learning_rate": 4.947916666666667e-06,
"loss": 0.0016631172895431518,
"step": 97000
},
{
"epoch": 151.5625,
"eval_loss": 0.4714573919773102,
"eval_micro_f1": 0.9577986620699477,
"step": 97000
},
{
"epoch": 151.953125,
"eval_loss": 0.4787580370903015,
"eval_micro_f1": 0.9572564607325178,
"step": 97250
},
{
"epoch": 152.34375,
"learning_rate": 4.921875e-06,
"loss": 0.0009993813633918762,
"step": 97500
},
{
"epoch": 152.34375,
"eval_loss": 0.4912763237953186,
"eval_micro_f1": 0.955900957388943,
"step": 97500
},
{
"epoch": 152.734375,
"eval_loss": 0.47841978073120117,
"eval_micro_f1": 0.957708295180376,
"step": 97750
},
{
"epoch": 153.125,
"learning_rate": 4.895833333333333e-06,
"loss": 0.0009511631727218628,
"step": 98000
},
{
"epoch": 153.125,
"eval_loss": 0.4844542145729065,
"eval_micro_f1": 0.9571660938429462,
"step": 98000
},
{
"epoch": 153.515625,
"eval_loss": 0.48957568407058716,
"eval_micro_f1": 0.9567142593950879,
"step": 98250
},
{
"epoch": 153.90625,
"learning_rate": 4.869791666666667e-06,
"loss": 0.0008402570486068726,
"step": 98500
},
{
"epoch": 153.90625,
"eval_loss": 0.4688386917114258,
"eval_micro_f1": 0.9587926978552359,
"step": 98500
},
{
"epoch": 154.296875,
"eval_loss": 0.5029594302177429,
"eval_micro_f1": 0.9565335256159445,
"step": 98750
},
{
"epoch": 154.6875,
"learning_rate": 4.84375e-06,
"loss": 0.0008744259476661683,
"step": 99000
},
{
"epoch": 154.6875,
"eval_loss": 0.5083732604980469,
"eval_micro_f1": 0.9561720580576579,
"step": 99000
},
{
"epoch": 155.078125,
"eval_loss": 0.4855863153934479,
"eval_micro_f1": 0.9583408634073777,
"step": 99250
},
{
"epoch": 155.46875,
"learning_rate": 4.817708333333334e-06,
"loss": 0.0014339350461959838,
"step": 99500
},
{
"epoch": 155.46875,
"eval_loss": 0.49837982654571533,
"eval_micro_f1": 0.9571660938429462,
"step": 99500
},
{
"epoch": 155.859375,
"eval_loss": 0.48717859387397766,
"eval_micro_f1": 0.9573468276220894,
"step": 99750
},
{
"epoch": 156.25,
"learning_rate": 4.791666666666668e-06,
"loss": 0.0007853381633758545,
"step": 100000
},
{
"epoch": 156.25,
"eval_loss": 0.48714086413383484,
"eval_micro_f1": 0.9573468276220894,
"step": 100000
},
{
"epoch": 156.640625,
"eval_loss": 0.4609386920928955,
"eval_micro_f1": 0.9575275614012327,
"step": 100250
},
{
"epoch": 157.03125,
"learning_rate": 4.765625000000001e-06,
"loss": 0.0019533694982528686,
"step": 100500
},
{
"epoch": 157.03125,
"eval_loss": 0.461384654045105,
"eval_micro_f1": 0.9578890289595193,
"step": 100500
},
{
"epoch": 157.421875,
"eval_loss": 0.4647699296474457,
"eval_micro_f1": 0.957708295180376,
"step": 100750
},
{
"epoch": 157.8125,
"learning_rate": 4.739583333333334e-06,
"loss": 0.0008373306393623352,
"step": 101000
},
{
"epoch": 157.8125,
"eval_loss": 0.4694337844848633,
"eval_micro_f1": 0.9580697627386626,
"step": 101000
},
{
"epoch": 158.203125,
"eval_loss": 0.47969159483909607,
"eval_micro_f1": 0.9573468276220894,
"step": 101250
},
{
"epoch": 158.59375,
"learning_rate": 4.7135416666666675e-06,
"loss": 0.0007067506313323975,
"step": 101500
},
{
"epoch": 158.59375,
"eval_loss": 0.47717732191085815,
"eval_micro_f1": 0.9576179282908044,
"step": 101500
},
{
"epoch": 158.984375,
"eval_loss": 0.47969603538513184,
"eval_micro_f1": 0.9560816911680863,
"step": 101750
},
{
"epoch": 159.375,
"learning_rate": 4.6875000000000004e-06,
"loss": 0.0014420950412750244,
"step": 102000
},
{
"epoch": 159.375,
"eval_loss": 0.47100016474723816,
"eval_micro_f1": 0.9568046262846596,
"step": 102000
},
{
"epoch": 159.765625,
"eval_loss": 0.4853743314743042,
"eval_micro_f1": 0.9553587560515131,
"step": 102250
},
{
"epoch": 160.15625,
"learning_rate": 4.661458333333333e-06,
"loss": 0.0012132378816604615,
"step": 102500
},
{
"epoch": 160.15625,
"eval_loss": 0.48170486092567444,
"eval_micro_f1": 0.9567142593950879,
"step": 102500
},
{
"epoch": 160.546875,
"eval_loss": 0.47489693760871887,
"eval_micro_f1": 0.9570757269533745,
"step": 102750
},
{
"epoch": 160.9375,
"learning_rate": 4.635416666666667e-06,
"loss": 0.0010259900093078614,
"step": 103000
},
{
"epoch": 160.9375,
"eval_loss": 0.47136181592941284,
"eval_micro_f1": 0.9572564607325178,
"step": 103000
},
{
"epoch": 161.328125,
"eval_loss": 0.47522711753845215,
"eval_micro_f1": 0.9578890289595193,
"step": 103250
},
{
"epoch": 161.71875,
"learning_rate": 4.609375e-06,
"loss": 0.001224056363105774,
"step": 103500
},
{
"epoch": 161.71875,
"eval_loss": 0.4777040481567383,
"eval_micro_f1": 0.957979395849091,
"step": 103500
},
{
"epoch": 162.109375,
"eval_loss": 0.47020062804222107,
"eval_micro_f1": 0.9580697627386626,
"step": 103750
},
{
"epoch": 162.5,
"learning_rate": 4.583333333333333e-06,
"loss": 0.0015057862997055053,
"step": 104000
},
{
"epoch": 162.5,
"eval_loss": 0.46319323778152466,
"eval_micro_f1": 0.9572564607325178,
"step": 104000
},
{
"epoch": 162.890625,
"eval_loss": 0.4765928089618683,
"eval_micro_f1": 0.9573468276220894,
"step": 104250
},
{
"epoch": 163.28125,
"learning_rate": 4.557291666666667e-06,
"loss": 0.001110297918319702,
"step": 104500
},
{
"epoch": 163.28125,
"eval_loss": 0.49123793840408325,
"eval_micro_f1": 0.9574371945116611,
"step": 104500
},
{
"epoch": 163.671875,
"eval_loss": 0.4772012531757355,
"eval_micro_f1": 0.9576179282908044,
"step": 104750
},
{
"epoch": 164.0625,
"learning_rate": 4.53125e-06,
"loss": 0.0017659571170806885,
"step": 105000
},
{
"epoch": 164.0625,
"eval_loss": 0.45409420132637024,
"eval_micro_f1": 0.9583408634073777,
"step": 105000
},
{
"epoch": 164.453125,
"eval_loss": 0.47786182165145874,
"eval_micro_f1": 0.9576179282908044,
"step": 105250
},
{
"epoch": 164.84375,
"learning_rate": 4.505208333333334e-06,
"loss": 0.0010535234212875365,
"step": 105500
},
{
"epoch": 164.84375,
"eval_loss": 0.4681532084941864,
"eval_micro_f1": 0.9587023309656643,
"step": 105500
},
{
"epoch": 165.234375,
"eval_loss": 0.47860291600227356,
"eval_micro_f1": 0.9568046262846596,
"step": 105750
},
{
"epoch": 165.625,
"learning_rate": 4.479166666666667e-06,
"loss": 0.0011317429542541503,
"step": 106000
},
{
"epoch": 165.625,
"eval_loss": 0.4745328724384308,
"eval_micro_f1": 0.9578890289595193,
"step": 106000
},
{
"epoch": 166.015625,
"eval_loss": 0.4724370539188385,
"eval_micro_f1": 0.9578890289595193,
"step": 106250
},
{
"epoch": 166.40625,
"learning_rate": 4.453125000000001e-06,
"loss": 0.0008380458950996399,
"step": 106500
},
{
"epoch": 166.40625,
"eval_loss": 0.4663918912410736,
"eval_micro_f1": 0.9582504965178059,
"step": 106500
},
{
"epoch": 166.796875,
"eval_loss": 0.468563973903656,
"eval_micro_f1": 0.9581601296282343,
"step": 106750
},
{
"epoch": 167.1875,
"learning_rate": 4.427083333333334e-06,
"loss": 0.000922056794166565,
"step": 107000
},
{
"epoch": 167.1875,
"eval_loss": 0.46217626333236694,
"eval_micro_f1": 0.9580697627386626,
"step": 107000
},
{
"epoch": 167.578125,
"eval_loss": 0.46807852387428284,
"eval_micro_f1": 0.9590637985239509,
"step": 107250
},
{
"epoch": 167.96875,
"learning_rate": 4.4010416666666675e-06,
"loss": 0.0006401723027229309,
"step": 107500
},
{
"epoch": 167.96875,
"eval_loss": 0.46928390860557556,
"eval_micro_f1": 0.9592445323030941,
"step": 107500
},
{
"epoch": 168.359375,
"eval_loss": 0.4859190583229065,
"eval_micro_f1": 0.9565335256159445,
"step": 107750
},
{
"epoch": 168.75,
"learning_rate": 4.3750000000000005e-06,
"loss": 0.000984980881214142,
"step": 108000
},
{
"epoch": 168.75,
"eval_loss": 0.48018431663513184,
"eval_micro_f1": 0.9570757269533745,
"step": 108000
},
{
"epoch": 169.140625,
"eval_loss": 0.47248557209968567,
"eval_micro_f1": 0.9568949931742312,
"step": 108250
},
{
"epoch": 169.53125,
"learning_rate": 4.3489583333333334e-06,
"loss": 0.0016572386026382445,
"step": 108500
},
{
"epoch": 169.53125,
"eval_loss": 0.46759989857673645,
"eval_micro_f1": 0.9567142593950879,
"step": 108500
},
{
"epoch": 169.921875,
"eval_loss": 0.4724884033203125,
"eval_micro_f1": 0.9571660938429462,
"step": 108750
},
{
"epoch": 170.3125,
"learning_rate": 4.322916666666667e-06,
"loss": 0.0009325624108314514,
"step": 109000
},
{
"epoch": 170.3125,
"eval_loss": 0.47318127751350403,
"eval_micro_f1": 0.9564431587263729,
"step": 109000
},
{
"epoch": 170.703125,
"eval_loss": 0.47040995955467224,
"eval_micro_f1": 0.9583408634073777,
"step": 109250
},
{
"epoch": 171.09375,
"learning_rate": 4.296875e-06,
"loss": 0.0012432781457901,
"step": 109500
},
{
"epoch": 171.09375,
"eval_loss": 0.4768226444721222,
"eval_micro_f1": 0.9573468276220894,
"step": 109500
},
{
"epoch": 171.484375,
"eval_loss": 0.47795194387435913,
"eval_micro_f1": 0.957708295180376,
"step": 109750
},
{
"epoch": 171.875,
"learning_rate": 4.270833333333333e-06,
"loss": 0.0008522326946258545,
"step": 110000
},
{
"epoch": 171.875,
"eval_loss": 0.4852602779865265,
"eval_micro_f1": 0.9574371945116611,
"step": 110000
},
{
"epoch": 172.265625,
"eval_loss": 0.48366743326187134,
"eval_micro_f1": 0.9573468276220894,
"step": 110250
},
{
"epoch": 172.65625,
"learning_rate": 4.244791666666667e-06,
"loss": 0.000891938030719757,
"step": 110500
},
{
"epoch": 172.65625,
"eval_loss": 0.4887804388999939,
"eval_micro_f1": 0.9575275614012327,
"step": 110500
},
{
"epoch": 173.046875,
"eval_loss": 0.48310956358909607,
"eval_micro_f1": 0.957979395849091,
"step": 110750
},
{
"epoch": 173.4375,
"learning_rate": 4.21875e-06,
"loss": 0.0006911165118217469,
"step": 111000
},
{
"epoch": 173.4375,
"eval_loss": 0.4882602393627167,
"eval_micro_f1": 0.9571660938429462,
"step": 111000
},
{
"epoch": 173.828125,
"eval_loss": 0.49786657094955444,
"eval_micro_f1": 0.9565335256159445,
"step": 111250
},
{
"epoch": 174.21875,
"learning_rate": 4.192708333333334e-06,
"loss": 0.000986850142478943,
"step": 111500
},
{
"epoch": 174.21875,
"eval_loss": 0.48125115036964417,
"eval_micro_f1": 0.9571660938429462,
"step": 111500
},
{
"epoch": 174.609375,
"eval_loss": 0.4873519539833069,
"eval_micro_f1": 0.9582504965178059,
"step": 111750
},
{
"epoch": 175.0,
"learning_rate": 4.166666666666667e-06,
"loss": 0.0013204609155654907,
"step": 112000
},
{
"epoch": 175.0,
"eval_loss": 0.4882551431655884,
"eval_micro_f1": 0.9583408634073777,
"step": 112000
},
{
"epoch": 175.390625,
"eval_loss": 0.49120211601257324,
"eval_micro_f1": 0.9576179282908044,
"step": 112250
},
{
"epoch": 175.78125,
"learning_rate": 4.140625000000001e-06,
"loss": 0.0009561948776245117,
"step": 112500
},
{
"epoch": 175.78125,
"eval_loss": 0.49580904841423035,
"eval_micro_f1": 0.957979395849091,
"step": 112500
},
{
"epoch": 176.171875,
"eval_loss": 0.4906345307826996,
"eval_micro_f1": 0.9578890289595193,
"step": 112750
},
{
"epoch": 176.5625,
"learning_rate": 4.114583333333334e-06,
"loss": 0.0008970845937728882,
"step": 113000
},
{
"epoch": 176.5625,
"eval_loss": 0.4977063238620758,
"eval_micro_f1": 0.9572564607325178,
"step": 113000
},
{
"epoch": 176.953125,
"eval_loss": 0.4948706328868866,
"eval_micro_f1": 0.9572564607325178,
"step": 113250
},
{
"epoch": 177.34375,
"learning_rate": 4.0885416666666675e-06,
"loss": 0.0009728407859802246,
"step": 113500
},
{
"epoch": 177.34375,
"eval_loss": 0.4964998662471771,
"eval_micro_f1": 0.9584312302969493,
"step": 113500
},
{
"epoch": 177.734375,
"eval_loss": 0.5009799599647522,
"eval_micro_f1": 0.9576179282908044,
"step": 113750
},
{
"epoch": 178.125,
"learning_rate": 4.0625000000000005e-06,
"loss": 0.00101343834400177,
"step": 114000
},
{
"epoch": 178.125,
"eval_loss": 0.48898354172706604,
"eval_micro_f1": 0.9593348991926658,
"step": 114000
},
{
"epoch": 178.515625,
"eval_loss": 0.4849947690963745,
"eval_micro_f1": 0.9587926978552359,
"step": 114250
},
{
"epoch": 178.90625,
"learning_rate": 4.0364583333333335e-06,
"loss": 0.0009337081313133239,
"step": 114500
},
{
"epoch": 178.90625,
"eval_loss": 0.4847766160964966,
"eval_micro_f1": 0.9587023309656643,
"step": 114500
},
{
"epoch": 179.296875,
"eval_loss": 0.4843084514141083,
"eval_micro_f1": 0.9584312302969493,
"step": 114750
},
{
"epoch": 179.6875,
"learning_rate": 4.010416666666667e-06,
"loss": 0.0007010631561279297,
"step": 115000
},
{
"epoch": 179.6875,
"eval_loss": 0.4959081709384918,
"eval_micro_f1": 0.9578890289595193,
"step": 115000
},
{
"epoch": 180.078125,
"eval_loss": 0.494048148393631,
"eval_micro_f1": 0.9576179282908044,
"step": 115250
},
{
"epoch": 180.46875,
"learning_rate": 3.984375e-06,
"loss": 0.0007556109428405762,
"step": 115500
},
{
"epoch": 180.46875,
"eval_loss": 0.4988362491130829,
"eval_micro_f1": 0.957708295180376,
"step": 115500
},
{
"epoch": 180.859375,
"eval_loss": 0.5043227076530457,
"eval_micro_f1": 0.9568949931742312,
"step": 115750
},
{
"epoch": 181.25,
"learning_rate": 3.958333333333333e-06,
"loss": 0.0008442431688308715,
"step": 116000
},
{
"epoch": 181.25,
"eval_loss": 0.49825724959373474,
"eval_micro_f1": 0.9568949931742312,
"step": 116000
},
{
"epoch": 181.640625,
"eval_loss": 0.484377920627594,
"eval_micro_f1": 0.9576179282908044,
"step": 116250
},
{
"epoch": 182.03125,
"learning_rate": 3.932291666666667e-06,
"loss": 0.0011664501428604126,
"step": 116500
},
{
"epoch": 182.03125,
"eval_loss": 0.49683716893196106,
"eval_micro_f1": 0.9575275614012327,
"step": 116500
},
{
"epoch": 182.421875,
"eval_loss": 0.4888589382171631,
"eval_micro_f1": 0.9581601296282343,
"step": 116750
},
{
"epoch": 182.8125,
"learning_rate": 3.90625e-06,
"loss": 0.0010419342517852784,
"step": 117000
},
{
"epoch": 182.8125,
"eval_loss": 0.4848276674747467,
"eval_micro_f1": 0.9588830647448077,
"step": 117000
},
{
"epoch": 183.203125,
"eval_loss": 0.505784809589386,
"eval_micro_f1": 0.9555394898306564,
"step": 117250
},
{
"epoch": 183.59375,
"learning_rate": 3.880208333333333e-06,
"loss": 0.0008966981172561645,
"step": 117500
},
{
"epoch": 183.59375,
"eval_loss": 0.49361130595207214,
"eval_micro_f1": 0.9569853600638029,
"step": 117500
},
{
"epoch": 183.984375,
"eval_loss": 0.4978514015674591,
"eval_micro_f1": 0.9569853600638029,
"step": 117750
},
{
"epoch": 184.375,
"learning_rate": 3.854166666666667e-06,
"loss": 0.0009907788634300231,
"step": 118000
},
{
"epoch": 184.375,
"eval_loss": 0.49482080340385437,
"eval_micro_f1": 0.9574371945116611,
"step": 118000
},
{
"epoch": 184.765625,
"eval_loss": 0.5190304517745972,
"eval_micro_f1": 0.9548165547140831,
"step": 118250
},
{
"epoch": 185.15625,
"learning_rate": 3.828125000000001e-06,
"loss": 0.0011906425952911378,
"step": 118500
},
{
"epoch": 185.15625,
"eval_loss": 0.5030191540718079,
"eval_micro_f1": 0.9568046262846596,
"step": 118500
},
{
"epoch": 185.546875,
"eval_loss": 0.5011093020439148,
"eval_micro_f1": 0.9567142593950879,
"step": 118750
},
{
"epoch": 185.9375,
"learning_rate": 3.8020833333333333e-06,
"loss": 0.0010390490293502807,
"step": 119000
},
{
"epoch": 185.9375,
"eval_loss": 0.5024372935295105,
"eval_micro_f1": 0.9568046262846596,
"step": 119000
},
{
"epoch": 186.328125,
"eval_loss": 0.5003212094306946,
"eval_micro_f1": 0.9560816911680863,
"step": 119250
},
{
"epoch": 186.71875,
"learning_rate": 3.776041666666667e-06,
"loss": 0.0008999536037445069,
"step": 119500
},
{
"epoch": 186.71875,
"eval_loss": 0.49735909700393677,
"eval_micro_f1": 0.9567142593950879,
"step": 119500
},
{
"epoch": 187.109375,
"eval_loss": 0.49392256140708923,
"eval_micro_f1": 0.9576179282908044,
"step": 119750
},
{
"epoch": 187.5,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0007821693420410156,
"step": 120000
},
{
"epoch": 187.5,
"eval_loss": 0.4976905286312103,
"eval_micro_f1": 0.9557202236097997,
"step": 120000
},
{
"epoch": 187.890625,
"eval_loss": 0.48605847358703613,
"eval_micro_f1": 0.957979395849091,
"step": 120250
},
{
"epoch": 188.28125,
"learning_rate": 3.7239583333333335e-06,
"loss": 0.0009131916165351868,
"step": 120500
},
{
"epoch": 188.28125,
"eval_loss": 0.4924144446849823,
"eval_micro_f1": 0.9571660938429462,
"step": 120500
},
{
"epoch": 188.671875,
"eval_loss": 0.49412932991981506,
"eval_micro_f1": 0.9575275614012327,
"step": 120750
},
{
"epoch": 189.0625,
"learning_rate": 3.6979166666666673e-06,
"loss": 0.0008989785313606262,
"step": 121000
},
{
"epoch": 189.0625,
"eval_loss": 0.50082927942276,
"eval_micro_f1": 0.9582504965178059,
"step": 121000
},
{
"epoch": 189.453125,
"eval_loss": 0.5013861060142517,
"eval_micro_f1": 0.9577986620699477,
"step": 121250
},
{
"epoch": 189.84375,
"learning_rate": 3.6718750000000003e-06,
"loss": 0.0008876891732215881,
"step": 121500
},
{
"epoch": 189.84375,
"eval_loss": 0.5116557478904724,
"eval_micro_f1": 0.9563527918368012,
"step": 121500
},
{
"epoch": 190.234375,
"eval_loss": 0.5034648776054382,
"eval_micro_f1": 0.9568949931742312,
"step": 121750
},
{
"epoch": 190.625,
"learning_rate": 3.6458333333333333e-06,
"loss": 0.0012079238891601562,
"step": 122000
},
{
"epoch": 190.625,
"eval_loss": 0.4991481304168701,
"eval_micro_f1": 0.9575275614012327,
"step": 122000
},
{
"epoch": 191.015625,
"eval_loss": 0.5042958855628967,
"eval_micro_f1": 0.9573468276220894,
"step": 122250
},
{
"epoch": 191.40625,
"learning_rate": 3.619791666666667e-06,
"loss": 0.0009264803528785706,
"step": 122500
},
{
"epoch": 191.40625,
"eval_loss": 0.5103209018707275,
"eval_micro_f1": 0.9569853600638029,
"step": 122500
},
{
"epoch": 191.796875,
"eval_loss": 0.49562931060791016,
"eval_micro_f1": 0.957979395849091,
"step": 122750
},
{
"epoch": 192.1875,
"learning_rate": 3.59375e-06,
"loss": 0.0012086286544799804,
"step": 123000
},
{
"epoch": 192.1875,
"eval_loss": 0.4893048405647278,
"eval_micro_f1": 0.9578890289595193,
"step": 123000
},
{
"epoch": 192.578125,
"eval_loss": 0.49696314334869385,
"eval_micro_f1": 0.9577986620699477,
"step": 123250
},
{
"epoch": 192.96875,
"learning_rate": 3.5677083333333335e-06,
"loss": 0.0008426801562309265,
"step": 123500
},
{
"epoch": 192.96875,
"eval_loss": 0.4968220293521881,
"eval_micro_f1": 0.9572564607325178,
"step": 123500
},
{
"epoch": 193.359375,
"eval_loss": 0.49120965600013733,
"eval_micro_f1": 0.9577986620699477,
"step": 123750
},
{
"epoch": 193.75,
"learning_rate": 3.5416666666666673e-06,
"loss": 0.0012935508489608765,
"step": 124000
},
{
"epoch": 193.75,
"eval_loss": 0.5025430917739868,
"eval_micro_f1": 0.9569853600638029,
"step": 124000
},
{
"epoch": 194.140625,
"eval_loss": 0.5204200148582458,
"eval_micro_f1": 0.9565335256159445,
"step": 124250
},
{
"epoch": 194.53125,
"learning_rate": 3.5156250000000003e-06,
"loss": 0.000847568154335022,
"step": 124500
},
{
"epoch": 194.53125,
"eval_loss": 0.5036535859107971,
"eval_micro_f1": 0.9564431587263729,
"step": 124500
},
{
"epoch": 194.921875,
"eval_loss": 0.5043352842330933,
"eval_micro_f1": 0.9570757269533745,
"step": 124750
},
{
"epoch": 195.3125,
"learning_rate": 3.4895833333333333e-06,
"loss": 0.0005985053777694703,
"step": 125000
},
{
"epoch": 195.3125,
"eval_loss": 0.5058684349060059,
"eval_micro_f1": 0.9571660938429462,
"step": 125000
},
{
"epoch": 195.703125,
"eval_loss": 0.504775881767273,
"eval_micro_f1": 0.9573468276220894,
"step": 125250
},
{
"epoch": 196.09375,
"learning_rate": 3.463541666666667e-06,
"loss": 0.000760340690612793,
"step": 125500
},
{
"epoch": 196.09375,
"eval_loss": 0.5167238712310791,
"eval_micro_f1": 0.9561720580576579,
"step": 125500
},
{
"epoch": 196.484375,
"eval_loss": 0.5206369161605835,
"eval_micro_f1": 0.9549069216036549,
"step": 125750
},
{
"epoch": 196.875,
"learning_rate": 3.4375e-06,
"loss": 0.0007314137816429138,
"step": 126000
},
{
"epoch": 196.875,
"eval_loss": 0.520684003829956,
"eval_micro_f1": 0.9569853600638029,
"step": 126000
},
{
"epoch": 197.265625,
"eval_loss": 0.508742094039917,
"eval_micro_f1": 0.9575275614012327,
"step": 126250
},
{
"epoch": 197.65625,
"learning_rate": 3.4114583333333335e-06,
"loss": 0.0007533628344535828,
"step": 126500
},
{
"epoch": 197.65625,
"eval_loss": 0.5212412476539612,
"eval_micro_f1": 0.9570757269533745,
"step": 126500
},
{
"epoch": 198.046875,
"eval_loss": 0.5236151218414307,
"eval_micro_f1": 0.9565335256159445,
"step": 126750
},
{
"epoch": 198.4375,
"learning_rate": 3.385416666666667e-06,
"loss": 0.0009761412739753724,
"step": 127000
},
{
"epoch": 198.4375,
"eval_loss": 0.5215271711349487,
"eval_micro_f1": 0.9569853600638029,
"step": 127000
},
{
"epoch": 198.828125,
"eval_loss": 0.5127024054527283,
"eval_micro_f1": 0.9564431587263729,
"step": 127250
},
{
"epoch": 199.21875,
"learning_rate": 3.3593750000000003e-06,
"loss": 0.0010261968374252319,
"step": 127500
},
{
"epoch": 199.21875,
"eval_loss": 0.4993469715118408,
"eval_micro_f1": 0.9578890289595193,
"step": 127500
},
{
"epoch": 199.609375,
"eval_loss": 0.49945196509361267,
"eval_micro_f1": 0.9582504965178059,
"step": 127750
},
{
"epoch": 200.0,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.0009934030175209046,
"step": 128000
},
{
"epoch": 200.0,
"eval_loss": 0.5086157321929932,
"eval_micro_f1": 0.9578890289595193,
"step": 128000
},
{
"epoch": 200.390625,
"eval_loss": 0.507448673248291,
"eval_micro_f1": 0.9582504965178059,
"step": 128250
},
{
"epoch": 200.78125,
"learning_rate": 3.307291666666667e-06,
"loss": 0.0005464105010032653,
"step": 128500
},
{
"epoch": 200.78125,
"eval_loss": 0.5059870481491089,
"eval_micro_f1": 0.9586119640760926,
"step": 128500
},
{
"epoch": 201.171875,
"eval_loss": 0.4933741092681885,
"eval_micro_f1": 0.9589734316343792,
"step": 128750
},
{
"epoch": 201.5625,
"learning_rate": 3.28125e-06,
"loss": 0.000765357255935669,
"step": 129000
},
{
"epoch": 201.5625,
"eval_loss": 0.4964316189289093,
"eval_micro_f1": 0.9580697627386626,
"step": 129000
},
{
"epoch": 201.953125,
"eval_loss": 0.5047451257705688,
"eval_micro_f1": 0.957979395849091,
"step": 129250
},
{
"epoch": 202.34375,
"learning_rate": 3.2552083333333335e-06,
"loss": 0.0011271116733551024,
"step": 129500
},
{
"epoch": 202.34375,
"eval_loss": 0.5160056948661804,
"eval_micro_f1": 0.9582504965178059,
"step": 129500
},
{
"epoch": 202.734375,
"eval_loss": 0.508975625038147,
"eval_micro_f1": 0.9578890289595193,
"step": 129750
},
{
"epoch": 203.125,
"learning_rate": 3.229166666666667e-06,
"loss": 0.0009115800857543945,
"step": 130000
},
{
"epoch": 203.125,
"eval_loss": 0.5098258852958679,
"eval_micro_f1": 0.9582504965178059,
"step": 130000
},
{
"epoch": 203.515625,
"eval_loss": 0.5018815398216248,
"eval_micro_f1": 0.958521597186521,
"step": 130250
},
{
"epoch": 203.90625,
"learning_rate": 3.2031250000000004e-06,
"loss": 0.0010934345722198487,
"step": 130500
},
{
"epoch": 203.90625,
"eval_loss": 0.5164996981620789,
"eval_micro_f1": 0.9567142593950879,
"step": 130500
},
{
"epoch": 204.296875,
"eval_loss": 0.5163960456848145,
"eval_micro_f1": 0.9571660938429462,
"step": 130750
},
{
"epoch": 204.6875,
"learning_rate": 3.1770833333333333e-06,
"loss": 0.000950707197189331,
"step": 131000
},
{
"epoch": 204.6875,
"eval_loss": 0.5176142454147339,
"eval_micro_f1": 0.9581601296282343,
"step": 131000
},
{
"epoch": 205.078125,
"eval_loss": 0.505891740322113,
"eval_micro_f1": 0.9580697627386626,
"step": 131250
},
{
"epoch": 205.46875,
"learning_rate": 3.151041666666667e-06,
"loss": 0.0008522922992706299,
"step": 131500
},
{
"epoch": 205.46875,
"eval_loss": 0.5079271197319031,
"eval_micro_f1": 0.9578890289595193,
"step": 131500
},
{
"epoch": 205.859375,
"eval_loss": 0.5189764499664307,
"eval_micro_f1": 0.9570757269533745,
"step": 131750
},
{
"epoch": 206.25,
"learning_rate": 3.125e-06,
"loss": 0.0009821898341178894,
"step": 132000
},
{
"epoch": 206.25,
"eval_loss": 0.511292040348053,
"eval_micro_f1": 0.9582504965178059,
"step": 132000
},
{
"epoch": 206.640625,
"eval_loss": 0.5130345225334167,
"eval_micro_f1": 0.9583408634073777,
"step": 132250
},
{
"epoch": 207.03125,
"learning_rate": 3.0989583333333336e-06,
"loss": 0.0006296157836914063,
"step": 132500
},
{
"epoch": 207.03125,
"eval_loss": 0.5168700218200684,
"eval_micro_f1": 0.9578890289595193,
"step": 132500
},
{
"epoch": 207.421875,
"eval_loss": 0.501091480255127,
"eval_micro_f1": 0.9581601296282343,
"step": 132750
},
{
"epoch": 207.8125,
"learning_rate": 3.072916666666667e-06,
"loss": 0.0008090575933456421,
"step": 133000
},
{
"epoch": 207.8125,
"eval_loss": 0.5111897587776184,
"eval_micro_f1": 0.9565335256159445,
"step": 133000
},
{
"epoch": 208.203125,
"eval_loss": 0.510709285736084,
"eval_micro_f1": 0.9569853600638029,
"step": 133250
},
{
"epoch": 208.59375,
"learning_rate": 3.0468750000000004e-06,
"loss": 0.0007818419337272644,
"step": 133500
},
{
"epoch": 208.59375,
"eval_loss": 0.5136948823928833,
"eval_micro_f1": 0.9570757269533745,
"step": 133500
},
{
"epoch": 208.984375,
"eval_loss": 0.5116780400276184,
"eval_micro_f1": 0.9577986620699477,
"step": 133750
},
{
"epoch": 209.375,
"learning_rate": 3.0208333333333334e-06,
"loss": 0.0009591399431228638,
"step": 134000
},
{
"epoch": 209.375,
"eval_loss": 0.5133483409881592,
"eval_micro_f1": 0.9574371945116611,
"step": 134000
},
{
"epoch": 209.765625,
"eval_loss": 0.5286172032356262,
"eval_micro_f1": 0.9569853600638029,
"step": 134250
},
{
"epoch": 210.15625,
"learning_rate": 2.994791666666667e-06,
"loss": 0.0009491474032402038,
"step": 134500
},
{
"epoch": 210.15625,
"eval_loss": 0.5094191431999207,
"eval_micro_f1": 0.957708295180376,
"step": 134500
},
{
"epoch": 210.546875,
"eval_loss": 0.4971115291118622,
"eval_micro_f1": 0.960328934977954,
"step": 134750
}
],
"max_steps": 192000,
"num_train_epochs": 300,
"total_flos": 2206433440016654256,
"trial_name": null,
"trial_params": null
}
{
"best_metric": 0.960328934977954,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/onto_final/class-ce-new/run-42/checkpoints/checkpoint-134750",
"epoch": 210.546875,
"global_step": 134750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.390625,
"eval_loss": 0.3807726800441742,
"eval_micro_f1": 0.9149647564129842,
"step": 250
},
{
"epoch": 0.78125,
"learning_rate": 9.973958333333335e-06,
"loss": 0.7134353637695312,
"step": 500
},
{
"epoch": 0.78125,
"eval_loss": 0.26241013407707214,
"eval_micro_f1": 0.9413518881679069,
"step": 500
},
{
"epoch": 1.171875,
"eval_loss": 0.21784928441047668,
"eval_micro_f1": 0.9512922460207887,
"step": 750
},
{
"epoch": 1.5625,
"learning_rate": 9.947916666666667e-06,
"loss": 0.19096646118164062,
"step": 1000
},
{
"epoch": 1.5625,
"eval_loss": 0.20647455751895905,
"eval_micro_f1": 0.9507500446833588,
"step": 1000
},
{
"epoch": 1.953125,
"eval_loss": 0.20064181089401245,
"eval_micro_f1": 0.9518344473582186,
"step": 1250
},
{
"epoch": 2.34375,
"learning_rate": 9.921875e-06,
"loss": 0.13846273803710937,
"step": 1500
},
{
"epoch": 2.34375,
"eval_loss": 0.2122383713722229,
"eval_micro_f1": 0.949936742677214,
"step": 1500
},
{
"epoch": 2.734375,
"eval_loss": 0.2097567319869995,
"eval_micro_f1": 0.9505693109042156,
"step": 1750
},
{
"epoch": 3.125,
"learning_rate": 9.895833333333334e-06,
"loss": 0.11275356292724609,
"step": 2000
},
{
"epoch": 3.125,
"eval_loss": 0.2129451185464859,
"eval_micro_f1": 0.9540032527079383,
"step": 2000
},
{
"epoch": 3.515625,
"eval_loss": 0.20601296424865723,
"eval_micro_f1": 0.9537321520392233,
"step": 2250
},
{
"epoch": 3.90625,
"learning_rate": 9.869791666666667e-06,
"loss": 0.092468017578125,
"step": 2500
},
{
"epoch": 3.90625,
"eval_loss": 0.20766089856624603,
"eval_micro_f1": 0.9565335256159445,
"step": 2500
},
{