| { | |
| "best_metric": 0.3541961908340454, | |
| "best_model_checkpoint": "./runtime-text-classification/electra-base-discriminator-CoLA/checkpoint-134", | |
| "epoch": 8.0, | |
| "global_step": 536, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 0.6818, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.705882352941177e-05, | |
| "loss": 0.6093, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.5991, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.999340483599093e-05, | |
| "loss": 0.5014, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.995310893151923e-05, | |
| "loss": 0.4253, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.987621796687375e-05, | |
| "loss": 0.4231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.976280237035291e-05, | |
| "loss": 0.411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.964584084578578e-05, | |
| "loss": 0.4267, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.95056379670812e-05, | |
| "loss": 0.4357, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.929782771972567e-05, | |
| "loss": 0.4468, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.905402261718713e-05, | |
| "loss": 0.4651, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.877444597281055e-05, | |
| "loss": 0.3906, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.845935386489366e-05, | |
| "loss": 0.4004, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.35688334703445435, | |
| "eval_matthews_correlation": 0.6339887598158311, | |
| "eval_runtime": 1.9677, | |
| "eval_samples_per_second": 530.071, | |
| "eval_steps_per_second": 33.542, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.810903490213196e-05, | |
| "loss": 0.3209, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.77238099592675e-05, | |
| "loss": 0.3024, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.730403188318356e-05, | |
| "loss": 0.2579, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 7.685008516971451e-05, | |
| "loss": 0.3063, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 7.636238561146672e-05, | |
| "loss": 0.2636, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 7.58413799169732e-05, | |
| "loss": 0.294, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.528754530153087e-05, | |
| "loss": 0.2836, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.470138905009503e-05, | |
| "loss": 0.3346, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.408344805263159e-05, | |
| "loss": 0.2939, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.343428831235258e-05, | |
| "loss": 0.2815, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.275450442728538e-05, | |
| "loss": 0.2799, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.204471904565049e-05, | |
| "loss": 0.2491, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.130558229554668e-05, | |
| "loss": 0.2843, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3541961908340454, | |
| "eval_matthews_correlation": 0.6579677841732349, | |
| "eval_runtime": 2.0826, | |
| "eval_samples_per_second": 500.817, | |
| "eval_steps_per_second": 31.691, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.053777118946615e-05, | |
| "loss": 0.2591, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.974198900418456e-05, | |
| "loss": 0.182, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 6.89189646365947e-05, | |
| "loss": 0.1888, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 6.806945193607303e-05, | |
| "loss": 0.1455, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.719422901399121e-05, | |
| "loss": 0.1544, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.629409753100488e-05, | |
| "loss": 0.1622, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 6.536988196277224e-05, | |
| "loss": 0.1784, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 6.442242884477545e-05, | |
| "loss": 0.203, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.345260599693621e-05, | |
| "loss": 0.1598, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.24613017287359e-05, | |
| "loss": 0.1555, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 6.144942402556829e-05, | |
| "loss": 0.1363, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 6.041789971707008e-05, | |
| "loss": 0.1907, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 5.9367673628191066e-05, | |
| "loss": 0.1935, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.8299707713781464e-05, | |
| "loss": 0.1228, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.42005565762519836, | |
| "eval_matthews_correlation": 0.6412441886324401, | |
| "eval_runtime": 1.931, | |
| "eval_samples_per_second": 540.144, | |
| "eval_steps_per_second": 34.18, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 5.721498017748917e-05, | |
| "loss": 0.1156, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 5.6114484575773854e-05, | |
| "loss": 0.0937, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 5.499922890785868e-05, | |
| "loss": 0.1138, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 5.3870234692453145e-05, | |
| "loss": 0.0948, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 5.272853603209279e-05, | |
| "loss": 0.0777, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 5.15751786659527e-05, | |
| "loss": 0.1148, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 5.0411219012002445e-05, | |
| "loss": 0.1676, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.92377231993798e-05, | |
| "loss": 0.0868, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 4.805576609186946e-05, | |
| "loss": 0.1009, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 4.686643030338131e-05, | |
| "loss": 0.1072, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 4.5670805206329904e-05, | |
| "loss": 0.0908, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 4.4469985933823594e-05, | |
| "loss": 0.1031, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 4.326507237657703e-05, | |
| "loss": 0.0989, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.4780134856700897, | |
| "eval_matthews_correlation": 0.6757073194553476, | |
| "eval_runtime": 1.9344, | |
| "eval_samples_per_second": 539.172, | |
| "eval_steps_per_second": 34.118, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.205716817546599e-05, | |
| "loss": 0.0854, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 4.084737971064728e-05, | |
| "loss": 0.0493, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 3.9636815088169476e-05, | |
| "loss": 0.0902, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 3.842658312500302e-05, | |
| "loss": 0.0567, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 3.721779233341892e-05, | |
| "loss": 0.0549, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 3.6011549905646726e-05, | |
| "loss": 0.0596, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.480896069974151e-05, | |
| "loss": 0.048, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 3.361112622758889e-05, | |
| "loss": 0.081, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 3.241914364597488e-05, | |
| "loss": 0.0871, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 3.123410475164486e-05, | |
| "loss": 0.062, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 3.005709498127213e-05, | |
| "loss": 0.0763, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.8889192417251865e-05, | |
| "loss": 0.0634, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.7731466800231328e-05, | |
| "loss": 0.0798, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.658497854928058e-05, | |
| "loss": 0.0681, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.49001187086105347, | |
| "eval_matthews_correlation": 0.6925407764960233, | |
| "eval_runtime": 1.9334, | |
| "eval_samples_per_second": 539.471, | |
| "eval_steps_per_second": 34.137, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.5450777790601394e-05, | |
| "loss": 0.0465, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 2.432990339566394e-05, | |
| "loss": 0.0674, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 2.322338202965213e-05, | |
| "loss": 0.0419, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.2132227211089496e-05, | |
| "loss": 0.0481, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.1057438383506473e-05, | |
| "loss": 0.0362, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 2.0000000000000012e-05, | |
| "loss": 0.0336, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 1.89608806215234e-05, | |
| "loss": 0.0571, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 1.79410320297327e-05, | |
| "loss": 0.0459, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.694138835520206e-05, | |
| "loss": 0.0238, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 1.5962865221806545e-05, | |
| "loss": 0.054, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 1.5006358908056302e-05, | |
| "loss": 0.017, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 1.4072745526149944e-05, | |
| "loss": 0.0224, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 1.316288021949944e-05, | |
| "loss": 0.0506, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.5837473273277283, | |
| "eval_matthews_correlation": 0.6785370776792806, | |
| "eval_runtime": 1.9297, | |
| "eval_samples_per_second": 540.494, | |
| "eval_steps_per_second": 34.202, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.2277596379461248e-05, | |
| "loss": 0.0317, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 1.1417704881991271e-05, | |
| "loss": 0.0451, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.0583993344922905e-05, | |
| "loss": 0.0061, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 9.777225406548166e-06, | |
| "loss": 0.028, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 8.998140026163119e-06, | |
| "loss": 0.0358, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 8.24745080721788e-06, | |
| "loss": 0.0154, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 7.5258453436913185e-06, | |
| "loss": 0.0194, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 6.83398459028922e-06, | |
| "loss": 0.0292, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 6.172502257042672e-06, | |
| "loss": 0.0473, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 5.542004228861171e-06, | |
| "loss": 0.0327, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 4.94306801057221e-06, | |
| "loss": 0.0106, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 4.376242197955542e-06, | |
| "loss": 0.0226, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 3.842045975256774e-06, | |
| "loss": 0.0093, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.6298416256904602, | |
| "eval_matthews_correlation": 0.6651627094568674, | |
| "eval_runtime": 2.9643, | |
| "eval_samples_per_second": 351.848, | |
| "eval_steps_per_second": 22.265, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 3.340968639640463e-06, | |
| "loss": 0.0178, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 2.8734691530181603e-06, | |
| "loss": 0.0129, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 2.439975721662231e-06, | |
| "loss": 0.034, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 2.040885403990136e-06, | |
| "loss": 0.0067, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.6765637468787011e-06, | |
| "loss": 0.0251, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.3473444508414102e-06, | |
| "loss": 0.0137, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1.0535290643752448e-06, | |
| "loss": 0.0125, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 7.953867077573396e-07, | |
| "loss": 0.0213, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 5.731538265441572e-07, | |
| "loss": 0.0297, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 3.870339749991292e-07, | |
| "loss": 0.0356, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 2.3719762964709903e-07, | |
| "loss": 0.0213, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.2378203312626292e-07, | |
| "loss": 0.0122, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 4.689106848078773e-08, | |
| "loss": 0.0355, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 6.595164009066679e-09, | |
| "loss": 0.0244, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6291629076004028, | |
| "eval_matthews_correlation": 0.6750024002589107, | |
| "eval_runtime": 2.0387, | |
| "eval_samples_per_second": 511.593, | |
| "eval_steps_per_second": 32.373, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 536, | |
| "total_flos": 4499725164216320.0, | |
| "train_loss": 0.148403340177402, | |
| "train_runtime": 707.366, | |
| "train_samples_per_second": 96.708, | |
| "train_steps_per_second": 0.758 | |
| } | |
| ], | |
| "max_steps": 536, | |
| "num_train_epochs": 8, | |
| "total_flos": 4499725164216320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |