| { | |
| "best_metric": 0.630589176753026, | |
| "best_model_checkpoint": "/beegfs/scratch/user/blee/project_3/models/NLU.mt5-base.task_type-1.fine_tune.gpu_a100-40g+.node-1x1.bsz-64.epochs-22.metric-ema.metric_lang-all/checkpoint-18712", | |
| "epoch": 13.0, | |
| "eval_steps": 500.0, | |
| "global_step": 30407, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4e-05, | |
| "loss": 14.5977, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8e-05, | |
| "loss": 3.2078, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.984392680166998e-05, | |
| "loss": 1.1863, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 7.968785360333997e-05, | |
| "loss": 0.9566, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.953178040500995e-05, | |
| "loss": 0.8517, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.937570720667994e-05, | |
| "loss": 0.7691, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.921963400834992e-05, | |
| "loss": 0.7125, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.906356081001991e-05, | |
| "loss": 0.6588, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.89074876116899e-05, | |
| "loss": 0.5986, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.875141441335988e-05, | |
| "loss": 0.5448, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.859534121502985e-05, | |
| "loss": 1.0722, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.843926801669984e-05, | |
| "loss": 0.6586, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.828319481836982e-05, | |
| "loss": 0.5673, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.81271216200398e-05, | |
| "loss": 0.5194, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.797104842170979e-05, | |
| "loss": 0.4766, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.781497522337976e-05, | |
| "loss": 0.4481, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.765890202504975e-05, | |
| "loss": 0.4148, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.750282882671974e-05, | |
| "loss": 0.3991, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 7.734675562838972e-05, | |
| "loss": 0.3878, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.719068243005971e-05, | |
| "loss": 0.3539, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.703460923172969e-05, | |
| "loss": 0.342, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.687853603339967e-05, | |
| "loss": 0.3232, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.672246283506966e-05, | |
| "loss": 0.3185, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_validation_all_ex_match_acc": 0.38741622486746025, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004872331191643575, | |
| "eval_validation_all_intent_acc": 0.7521256376913074, | |
| "eval_validation_all_intent_acc_stderr": 0.004318432694874057, | |
| "eval_validation_all_loss": 0.2968784272670746, | |
| "eval_validation_all_runtime": 177.009, | |
| "eval_validation_all_samples_per_second": 56.477, | |
| "eval_validation_all_slot_micro_f1": 0.47014790945299517, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0019384774099713345, | |
| "eval_validation_all_steps_per_second": 1.768, | |
| "step": 2339 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.656638963673963e-05, | |
| "loss": 0.3149, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.641031643840962e-05, | |
| "loss": 0.2844, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.62542432400796e-05, | |
| "loss": 0.2801, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.609817004174959e-05, | |
| "loss": 0.2616, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 7.594209684341957e-05, | |
| "loss": 0.2654, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 7.578602364508956e-05, | |
| "loss": 0.2536, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 7.562995044675953e-05, | |
| "loss": 0.2433, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 7.547387724842952e-05, | |
| "loss": 0.2407, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 7.53178040500995e-05, | |
| "loss": 0.2346, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 7.516173085176949e-05, | |
| "loss": 0.2374, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 7.500565765343947e-05, | |
| "loss": 0.2267, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.484958445510945e-05, | |
| "loss": 0.2177, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.469351125677944e-05, | |
| "loss": 0.2198, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.453743805844941e-05, | |
| "loss": 0.2116, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.43813648601194e-05, | |
| "loss": 0.2103, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.422529166178938e-05, | |
| "loss": 0.2044, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 7.406921846345937e-05, | |
| "loss": 0.2018, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 7.391314526512936e-05, | |
| "loss": 0.2038, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.375707206679934e-05, | |
| "loss": 0.199, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.360099886846931e-05, | |
| "loss": 0.1903, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.34449256701393e-05, | |
| "loss": 0.1908, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 7.328885247180928e-05, | |
| "loss": 0.1877, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 7.313277927347926e-05, | |
| "loss": 0.1878, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_validation_all_ex_match_acc": 0.5762728818645594, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004942223428876296, | |
| "eval_validation_all_intent_acc": 0.7468240472141643, | |
| "eval_validation_all_intent_acc_stderr": 0.004348961141535433, | |
| "eval_validation_all_loss": 0.1461012214422226, | |
| "eval_validation_all_runtime": 180.06, | |
| "eval_validation_all_samples_per_second": 55.52, | |
| "eval_validation_all_slot_micro_f1": 0.7408780686564123, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0017017337770766719, | |
| "eval_validation_all_steps_per_second": 1.738, | |
| "step": 4678 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.297670607514925e-05, | |
| "loss": 0.1804, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 7.282063287681923e-05, | |
| "loss": 0.17, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.266455967848922e-05, | |
| "loss": 0.1696, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 7.250848648015921e-05, | |
| "loss": 0.1644, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.235241328182918e-05, | |
| "loss": 0.1651, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.219634008349917e-05, | |
| "loss": 0.1696, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 7.204026688516915e-05, | |
| "loss": 0.1668, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.188419368683913e-05, | |
| "loss": 0.1615, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 7.172812048850912e-05, | |
| "loss": 0.1577, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.15720472901791e-05, | |
| "loss": 0.1592, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.141597409184909e-05, | |
| "loss": 0.1542, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 7.125990089351906e-05, | |
| "loss": 0.1543, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.110382769518905e-05, | |
| "loss": 0.1532, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.094775449685903e-05, | |
| "loss": 0.1559, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.079168129852902e-05, | |
| "loss": 0.1524, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.0635608100199e-05, | |
| "loss": 0.1509, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.047953490186899e-05, | |
| "loss": 0.1453, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 7.032346170353896e-05, | |
| "loss": 0.1474, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.016738850520894e-05, | |
| "loss": 0.1444, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.001131530687893e-05, | |
| "loss": 0.1468, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.985524210854891e-05, | |
| "loss": 0.1421, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 6.96991689102189e-05, | |
| "loss": 0.1427, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 6.954309571188888e-05, | |
| "loss": 0.14, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 6.938702251355887e-05, | |
| "loss": 0.1364, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_validation_all_ex_match_acc": 0.5900770231069321, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004918929939767899, | |
| "eval_validation_all_intent_acc": 0.7644293287986396, | |
| "eval_validation_all_intent_acc_stderr": 0.004244186252062078, | |
| "eval_validation_all_loss": 0.1383330225944519, | |
| "eval_validation_all_runtime": 180.3126, | |
| "eval_validation_all_samples_per_second": 55.443, | |
| "eval_validation_all_slot_micro_f1": 0.7396164830681355, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0017044183392999975, | |
| "eval_validation_all_steps_per_second": 1.736, | |
| "step": 7017 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 6.923094931522886e-05, | |
| "loss": 0.1338, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 6.907487611689883e-05, | |
| "loss": 0.1305, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 6.891880291856881e-05, | |
| "loss": 0.1255, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 6.87627297202388e-05, | |
| "loss": 0.1302, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 6.860665652190878e-05, | |
| "loss": 0.1312, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 6.845058332357877e-05, | |
| "loss": 0.1309, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 6.829451012524874e-05, | |
| "loss": 0.1272, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 6.813843692691872e-05, | |
| "loss": 0.1277, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 6.798236372858871e-05, | |
| "loss": 0.1297, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 6.78262905302587e-05, | |
| "loss": 0.1239, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 6.767021733192868e-05, | |
| "loss": 0.1227, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 6.751414413359867e-05, | |
| "loss": 0.1241, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 6.735807093526865e-05, | |
| "loss": 0.1224, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 6.720199773693864e-05, | |
| "loss": 0.1234, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 6.704592453860861e-05, | |
| "loss": 0.1218, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 6.688985134027859e-05, | |
| "loss": 0.121, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 6.673377814194858e-05, | |
| "loss": 0.1182, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 6.657770494361856e-05, | |
| "loss": 0.1219, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 6.642163174528855e-05, | |
| "loss": 0.1198, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 6.626555854695853e-05, | |
| "loss": 0.1213, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 6.610948534862852e-05, | |
| "loss": 0.1202, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 6.59534121502985e-05, | |
| "loss": 0.1147, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 6.579733895196848e-05, | |
| "loss": 0.1191, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_validation_all_ex_match_acc": 0.5862758827648294, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004925741170944722, | |
| "eval_validation_all_intent_acc": 0.7755326597979394, | |
| "eval_validation_all_intent_acc_stderr": 0.004172936538970462, | |
| "eval_validation_all_loss": 0.14330914616584778, | |
| "eval_validation_all_runtime": 182.6873, | |
| "eval_validation_all_samples_per_second": 54.722, | |
| "eval_validation_all_slot_micro_f1": 0.7288510293073724, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0017265912249300535, | |
| "eval_validation_all_steps_per_second": 1.713, | |
| "step": 9356 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 6.564126575363846e-05, | |
| "loss": 0.1091, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 6.548519255530845e-05, | |
| "loss": 0.1111, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 6.532911935697843e-05, | |
| "loss": 0.111, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.51730461586484e-05, | |
| "loss": 0.109, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.50169729603184e-05, | |
| "loss": 0.1177, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 6.486089976198837e-05, | |
| "loss": 0.1069, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 6.470482656365836e-05, | |
| "loss": 0.1133, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 6.454875336532834e-05, | |
| "loss": 0.1055, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 6.439268016699833e-05, | |
| "loss": 0.1048, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.423660696866832e-05, | |
| "loss": 0.1081, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 6.40805337703383e-05, | |
| "loss": 0.1073, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 6.392446057200827e-05, | |
| "loss": 0.1055, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 6.376838737367826e-05, | |
| "loss": 0.1032, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 6.361231417534824e-05, | |
| "loss": 0.1045, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 6.345624097701823e-05, | |
| "loss": 0.1062, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 6.330016777868821e-05, | |
| "loss": 0.0999, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 6.314409458035818e-05, | |
| "loss": 0.1036, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 6.298802138202817e-05, | |
| "loss": 0.1063, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 6.283194818369816e-05, | |
| "loss": 0.0997, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 6.267587498536814e-05, | |
| "loss": 0.1019, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 6.251980178703813e-05, | |
| "loss": 0.1009, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 6.236372858870811e-05, | |
| "loss": 0.1016, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 6.22076553903781e-05, | |
| "loss": 0.0967, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_validation_all_ex_match_acc": 0.6202860858257477, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004853884404661511, | |
| "eval_validation_all_intent_acc": 0.771631489446834, | |
| "eval_validation_all_intent_acc_stderr": 0.0041984427435098615, | |
| "eval_validation_all_loss": 0.12277400493621826, | |
| "eval_validation_all_runtime": 180.5655, | |
| "eval_validation_all_samples_per_second": 55.365, | |
| "eval_validation_all_slot_micro_f1": 0.7819573425859782, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0016037195659180058, | |
| "eval_validation_all_steps_per_second": 1.733, | |
| "step": 11695 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.205158219204808e-05, | |
| "loss": 0.1019, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 6.189550899371805e-05, | |
| "loss": 0.0958, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 6.173943579538804e-05, | |
| "loss": 0.0913, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 6.158336259705802e-05, | |
| "loss": 0.0914, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 6.142728939872801e-05, | |
| "loss": 0.092, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 6.127121620039799e-05, | |
| "loss": 0.0934, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 6.111514300206798e-05, | |
| "loss": 0.0918, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 6.095906980373796e-05, | |
| "loss": 0.09, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 6.0802996605407945e-05, | |
| "loss": 0.0896, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 6.064692340707792e-05, | |
| "loss": 0.0938, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 6.049085020874791e-05, | |
| "loss": 0.0927, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 6.033477701041789e-05, | |
| "loss": 0.0935, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 6.017870381208787e-05, | |
| "loss": 0.0904, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 6.002263061375786e-05, | |
| "loss": 0.0923, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 5.986655741542784e-05, | |
| "loss": 0.0911, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 5.971048421709782e-05, | |
| "loss": 0.0894, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 5.955441101876781e-05, | |
| "loss": 0.0902, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 5.939833782043779e-05, | |
| "loss": 0.091, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 5.9242264622107775e-05, | |
| "loss": 0.0904, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 5.908619142377776e-05, | |
| "loss": 0.0912, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 5.8930118225447735e-05, | |
| "loss": 0.0914, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 5.8774045027117726e-05, | |
| "loss": 0.0884, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 5.86179718287877e-05, | |
| "loss": 0.0856, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 5.8461898630457686e-05, | |
| "loss": 0.0874, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_validation_all_ex_match_acc": 0.6209862958887666, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004852143300552274, | |
| "eval_validation_all_intent_acc": 0.7756326898069421, | |
| "eval_validation_all_intent_acc_stderr": 0.0041722756855579295, | |
| "eval_validation_all_loss": 0.12295829504728317, | |
| "eval_validation_all_runtime": 180.0678, | |
| "eval_validation_all_samples_per_second": 55.518, | |
| "eval_validation_all_slot_micro_f1": 0.7860288720332762, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0015928064325804261, | |
| "eval_validation_all_steps_per_second": 1.738, | |
| "step": 14034 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 5.830582543212768e-05, | |
| "loss": 0.0846, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 5.8149752233797653e-05, | |
| "loss": 0.0821, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 5.7993679035467644e-05, | |
| "loss": 0.0845, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 5.783760583713762e-05, | |
| "loss": 0.0831, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 5.7681532638807604e-05, | |
| "loss": 0.0805, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 5.752545944047759e-05, | |
| "loss": 0.0816, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 5.736938624214757e-05, | |
| "loss": 0.0813, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 5.721331304381755e-05, | |
| "loss": 0.08, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 5.705723984548754e-05, | |
| "loss": 0.0777, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 5.690116664715752e-05, | |
| "loss": 0.0803, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 5.6745093448827506e-05, | |
| "loss": 0.0807, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 5.658902025049749e-05, | |
| "loss": 0.0829, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 5.6432947052167467e-05, | |
| "loss": 0.08, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 5.627687385383746e-05, | |
| "loss": 0.0798, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 5.6120800655507434e-05, | |
| "loss": 0.0813, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 5.596472745717742e-05, | |
| "loss": 0.081, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 5.580865425884741e-05, | |
| "loss": 0.0796, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 5.5652581060517385e-05, | |
| "loss": 0.0776, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 5.5496507862187375e-05, | |
| "loss": 0.0797, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 5.534043466385735e-05, | |
| "loss": 0.0816, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 5.5184361465527336e-05, | |
| "loss": 0.0776, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 5.5028288267197326e-05, | |
| "loss": 0.0806, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 5.48722150688673e-05, | |
| "loss": 0.0793, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_validation_all_ex_match_acc": 0.6250875262578773, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004841729420424345, | |
| "eval_validation_all_intent_acc": 0.77333199959988, | |
| "eval_validation_all_intent_acc_stderr": 0.004187388454167221, | |
| "eval_validation_all_loss": 0.12834610044956207, | |
| "eval_validation_all_runtime": 179.7767, | |
| "eval_validation_all_samples_per_second": 55.608, | |
| "eval_validation_all_slot_micro_f1": 0.7850994663777063, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0015953179494001197, | |
| "eval_validation_all_steps_per_second": 1.741, | |
| "step": 16373 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.471614187053728e-05, | |
| "loss": 0.0767, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 5.456006867220727e-05, | |
| "loss": 0.0738, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 5.4403995473877254e-05, | |
| "loss": 0.0701, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 5.424792227554724e-05, | |
| "loss": 0.0705, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 5.409184907721722e-05, | |
| "loss": 0.0724, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 5.39357758788872e-05, | |
| "loss": 0.0711, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 5.377970268055719e-05, | |
| "loss": 0.0727, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 5.362362948222717e-05, | |
| "loss": 0.0714, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 5.346755628389715e-05, | |
| "loss": 0.0711, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 5.331148308556714e-05, | |
| "loss": 0.0699, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 5.3155409887237116e-05, | |
| "loss": 0.0692, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 5.2999336688907106e-05, | |
| "loss": 0.0711, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 5.284326349057708e-05, | |
| "loss": 0.073, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 5.268719029224707e-05, | |
| "loss": 0.0701, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 5.253111709391706e-05, | |
| "loss": 0.0709, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 5.2375043895587034e-05, | |
| "loss": 0.0748, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 5.221897069725701e-05, | |
| "loss": 0.0713, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 5.2062897498927e-05, | |
| "loss": 0.0706, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 5.1906824300596985e-05, | |
| "loss": 0.0748, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 5.175075110226697e-05, | |
| "loss": 0.0694, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 5.159467790393695e-05, | |
| "loss": 0.072, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 5.143860470560693e-05, | |
| "loss": 0.0705, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 5.128253150727692e-05, | |
| "loss": 0.068, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 5.11264583089469e-05, | |
| "loss": 0.0687, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_validation_all_ex_match_acc": 0.630589176753026, | |
| "eval_validation_all_ex_match_acc_stderr": 0.0048271769371602165, | |
| "eval_validation_all_intent_acc": 0.7778333500050015, | |
| "eval_validation_all_intent_acc_stderr": 0.004157649429320968, | |
| "eval_validation_all_loss": 0.1259431391954422, | |
| "eval_validation_all_runtime": 170.3009, | |
| "eval_validation_all_samples_per_second": 58.702, | |
| "eval_validation_all_slot_micro_f1": 0.7861930842802256, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.001592361422278994, | |
| "eval_validation_all_steps_per_second": 1.838, | |
| "step": 18712 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 5.097038511061688e-05, | |
| "loss": 0.0635, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 5.081431191228687e-05, | |
| "loss": 0.0628, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 5.065823871395685e-05, | |
| "loss": 0.0674, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 5.050216551562683e-05, | |
| "loss": 0.064, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 5.0346092317296815e-05, | |
| "loss": 0.0634, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 5.01900191189668e-05, | |
| "loss": 0.0665, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 5.003394592063679e-05, | |
| "loss": 0.064, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 4.9877872722306765e-05, | |
| "loss": 0.0646, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 4.972179952397675e-05, | |
| "loss": 0.0669, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 4.956572632564673e-05, | |
| "loss": 0.0629, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 4.9409653127316716e-05, | |
| "loss": 0.0652, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 4.925357992898669e-05, | |
| "loss": 0.0642, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.9097506730656684e-05, | |
| "loss": 0.0652, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 4.894143353232666e-05, | |
| "loss": 0.0659, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.878536033399665e-05, | |
| "loss": 0.0632, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 4.8629287135666634e-05, | |
| "loss": 0.0655, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 4.847321393733661e-05, | |
| "loss": 0.0624, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 4.83171407390066e-05, | |
| "loss": 0.0646, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 4.816106754067658e-05, | |
| "loss": 0.0659, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 4.800499434234656e-05, | |
| "loss": 0.064, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.7848921144016546e-05, | |
| "loss": 0.0642, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 4.769284794568653e-05, | |
| "loss": 0.0665, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 4.753677474735652e-05, | |
| "loss": 0.0626, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_validation_all_ex_match_acc": 0.6302890867260178, | |
| "eval_validation_all_ex_match_acc_stderr": 0.0048279880103909295, | |
| "eval_validation_all_intent_acc": 0.7782334700410123, | |
| "eval_validation_all_intent_acc_stderr": 0.004154972051978152, | |
| "eval_validation_all_loss": 0.1310112625360489, | |
| "eval_validation_all_runtime": 170.1316, | |
| "eval_validation_all_samples_per_second": 58.76, | |
| "eval_validation_all_slot_micro_f1": 0.789992449441871, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0015819585080535143, | |
| "eval_validation_all_steps_per_second": 1.84, | |
| "step": 21051 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.73807015490265e-05, | |
| "loss": 0.0602, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 4.722462835069648e-05, | |
| "loss": 0.0594, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 4.7068555152366464e-05, | |
| "loss": 0.0583, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.691248195403645e-05, | |
| "loss": 0.0584, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 4.6756408755706424e-05, | |
| "loss": 0.0565, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.6600335557376415e-05, | |
| "loss": 0.0568, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 4.644426235904639e-05, | |
| "loss": 0.0586, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 4.628818916071638e-05, | |
| "loss": 0.0552, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 4.6132115962386366e-05, | |
| "loss": 0.0608, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 4.597604276405634e-05, | |
| "loss": 0.0595, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 4.581996956572633e-05, | |
| "loss": 0.0574, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 4.566389636739631e-05, | |
| "loss": 0.0572, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 4.5507823169066293e-05, | |
| "loss": 0.0585, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 4.5351749970736284e-05, | |
| "loss": 0.0584, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 4.519567677240626e-05, | |
| "loss": 0.0575, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 4.503960357407625e-05, | |
| "loss": 0.0601, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 4.488353037574623e-05, | |
| "loss": 0.0586, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 4.472745717741621e-05, | |
| "loss": 0.0576, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 4.4571383979086195e-05, | |
| "loss": 0.057, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 4.441531078075618e-05, | |
| "loss": 0.057, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 4.4259237582426156e-05, | |
| "loss": 0.0596, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 4.4103164384096146e-05, | |
| "loss": 0.0592, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 4.394709118576613e-05, | |
| "loss": 0.058, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_validation_all_ex_match_acc": 0.6262878863659098, | |
| "eval_validation_all_ex_match_acc_stderr": 0.00483861143551642, | |
| "eval_validation_all_intent_acc": 0.7731319395818745, | |
| "eval_validation_all_intent_acc_stderr": 0.00418869405726844, | |
| "eval_validation_all_loss": 0.13434068858623505, | |
| "eval_validation_all_runtime": 178.1682, | |
| "eval_validation_all_samples_per_second": 56.11, | |
| "eval_validation_all_slot_micro_f1": 0.7893436766357048, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0015837494632691346, | |
| "eval_validation_all_steps_per_second": 1.757, | |
| "step": 23390 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.379101798743611e-05, | |
| "loss": 0.0602, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 4.36349447891061e-05, | |
| "loss": 0.0527, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 4.3478871590776074e-05, | |
| "loss": 0.0558, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 4.3322798392446064e-05, | |
| "loss": 0.0515, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 4.316672519411604e-05, | |
| "loss": 0.0521, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 4.3010651995786025e-05, | |
| "loss": 0.0512, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 4.2854578797456015e-05, | |
| "loss": 0.0525, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 4.269850559912599e-05, | |
| "loss": 0.053, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 4.254243240079598e-05, | |
| "loss": 0.0531, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 10.39, | |
| "learning_rate": 4.238635920246596e-05, | |
| "loss": 0.0536, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 4.223028600413594e-05, | |
| "loss": 0.0543, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 4.2074212805805926e-05, | |
| "loss": 0.0521, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 4.191813960747591e-05, | |
| "loss": 0.0527, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 4.176206640914589e-05, | |
| "loss": 0.0554, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 4.160599321081588e-05, | |
| "loss": 0.0529, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 4.144992001248586e-05, | |
| "loss": 0.0541, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 4.1293846814155845e-05, | |
| "loss": 0.0556, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 4.113777361582583e-05, | |
| "loss": 0.0512, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.0981700417495805e-05, | |
| "loss": 0.0535, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 4.0825627219165796e-05, | |
| "loss": 0.0523, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 4.066955402083577e-05, | |
| "loss": 0.0517, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 4.0513480822505756e-05, | |
| "loss": 0.0537, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 4.0357407624175746e-05, | |
| "loss": 0.054, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 4.020133442584572e-05, | |
| "loss": 0.0519, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_validation_all_ex_match_acc": 0.6264879463839151, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004838088679693641, | |
| "eval_validation_all_intent_acc": 0.7737321196358907, | |
| "eval_validation_all_intent_acc_stderr": 0.004184773155844174, | |
| "eval_validation_all_loss": 0.1407793015241623, | |
| "eval_validation_all_runtime": 181.9271, | |
| "eval_validation_all_samples_per_second": 54.951, | |
| "eval_validation_all_slot_micro_f1": 0.7874137545030835, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0015890415122001155, | |
| "eval_validation_all_steps_per_second": 1.72, | |
| "step": 25729 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 4.004526122751571e-05, | |
| "loss": 0.0513, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 3.988918802918569e-05, | |
| "loss": 0.0493, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 3.9733114830855674e-05, | |
| "loss": 0.0491, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 3.957704163252566e-05, | |
| "loss": 0.0473, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.942096843419564e-05, | |
| "loss": 0.0488, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 3.9264895235865625e-05, | |
| "loss": 0.0494, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 3.910882203753561e-05, | |
| "loss": 0.048, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 3.895274883920559e-05, | |
| "loss": 0.0478, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 3.8796675640875576e-05, | |
| "loss": 0.049, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 3.864060244254556e-05, | |
| "loss": 0.0505, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 3.8484529244215536e-05, | |
| "loss": 0.0499, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 3.832845604588552e-05, | |
| "loss": 0.0495, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 3.8172382847555504e-05, | |
| "loss": 0.0501, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "learning_rate": 3.8016309649225494e-05, | |
| "loss": 0.047, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 3.786023645089547e-05, | |
| "loss": 0.0472, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 3.7704163252565455e-05, | |
| "loss": 0.0471, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 3.754809005423544e-05, | |
| "loss": 0.0488, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 3.739201685590542e-05, | |
| "loss": 0.0495, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 3.7235943657575405e-05, | |
| "loss": 0.0465, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.707987045924539e-05, | |
| "loss": 0.0476, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 3.692379726091537e-05, | |
| "loss": 0.048, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 3.6767724062585356e-05, | |
| "loss": 0.0487, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 11.97, | |
| "learning_rate": 3.661165086425534e-05, | |
| "loss": 0.0504, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_validation_all_ex_match_acc": 0.6299889966990097, | |
| "eval_validation_all_ex_match_acc_stderr": 0.004828797081892748, | |
| "eval_validation_all_intent_acc": 0.7760328098429529, | |
| "eval_validation_all_intent_acc_stderr": 0.004169628824053711, | |
| "eval_validation_all_loss": 0.1429910659790039, | |
| "eval_validation_all_runtime": 181.3487, | |
| "eval_validation_all_samples_per_second": 55.126, | |
| "eval_validation_all_slot_micro_f1": 0.7888446215139443, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.0015851230161344064, | |
| "eval_validation_all_steps_per_second": 1.726, | |
| "step": 28068 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 3.6455577665925324e-05, | |
| "loss": 0.0442, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 3.629950446759531e-05, | |
| "loss": 0.0423, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 3.614343126926529e-05, | |
| "loss": 0.0446, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 3.598735807093527e-05, | |
| "loss": 0.0419, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 3.583128487260525e-05, | |
| "loss": 0.0453, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 3.567521167427524e-05, | |
| "loss": 0.0434, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 3.5519138475945225e-05, | |
| "loss": 0.0433, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 3.53630652776152e-05, | |
| "loss": 0.0457, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 3.5206992079285186e-05, | |
| "loss": 0.0458, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 3.505091888095517e-05, | |
| "loss": 0.0436, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 3.489484568262515e-05, | |
| "loss": 0.0465, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.473877248429514e-05, | |
| "loss": 0.0454, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 3.458269928596512e-05, | |
| "loss": 0.0457, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 3.4426626087635104e-05, | |
| "loss": 0.0474, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 3.427055288930509e-05, | |
| "loss": 0.0458, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 3.411447969097507e-05, | |
| "loss": 0.0452, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 3.3958406492645055e-05, | |
| "loss": 0.0455, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 3.380233329431504e-05, | |
| "loss": 0.0436, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 3.364626009598502e-05, | |
| "loss": 0.0472, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 12.83, | |
| "learning_rate": 3.3490186897655e-05, | |
| "loss": 0.0454, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 3.333411369932498e-05, | |
| "loss": 0.0431, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 3.317804050099497e-05, | |
| "loss": 0.0455, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 3.3021967302664957e-05, | |
| "loss": 0.0433, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.2865894104334933e-05, | |
| "loss": 0.0438, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_validation_all_ex_match_acc": 0.6277883365009503, | |
| "eval_validation_all_ex_match_acc_stderr": 0.0048346692041261715, | |
| "eval_validation_all_intent_acc": 0.7767330199059718, | |
| "eval_validation_all_intent_acc_stderr": 0.004164983516855836, | |
| "eval_validation_all_loss": 0.1506633162498474, | |
| "eval_validation_all_runtime": 180.9233, | |
| "eval_validation_all_samples_per_second": 55.255, | |
| "eval_validation_all_slot_micro_f1": 0.7894693944086723, | |
| "eval_validation_all_slot_micro_f1_stderr": 0.001583402887351871, | |
| "eval_validation_all_steps_per_second": 1.73, | |
| "step": 30407 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 51458, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 22, | |
| "save_steps": 500.0, | |
| "total_flos": 7.470556690869043e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |