| { | |
| "best_metric": 82.80379041248607, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-parsing-ud-English-EWT/checkpoint-14000", | |
| "epoch": 38.265306122448976, | |
| "global_step": 15000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 4.8024, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.948456375838927e-05, | |
| "loss": 2.3642, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.894765100671142e-05, | |
| "loss": 1.8277, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.841073825503357e-05, | |
| "loss": 1.4984, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 7.78738255033557e-05, | |
| "loss": 1.1267, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_las": 70.16642777512342, | |
| "eval_loss": 1.2553037405014038, | |
| "eval_runtime": 10.77, | |
| "eval_samples_per_second": 185.794, | |
| "eval_steps_per_second": 23.305, | |
| "eval_uas": 76.15464245899028, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.733691275167786e-05, | |
| "loss": 1.0544, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 1.018, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 7.626308724832216e-05, | |
| "loss": 0.9047, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.57261744966443e-05, | |
| "loss": 0.6769, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.518926174496645e-05, | |
| "loss": 0.6696, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_las": 75.97945532728141, | |
| "eval_loss": 1.0503844022750854, | |
| "eval_runtime": 10.7423, | |
| "eval_samples_per_second": 186.272, | |
| "eval_steps_per_second": 23.366, | |
| "eval_uas": 81.06784519827998, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 7.46523489932886e-05, | |
| "loss": 0.6544, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.411543624161075e-05, | |
| "loss": 0.5963, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 7.35785234899329e-05, | |
| "loss": 0.433, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 7.304161073825505e-05, | |
| "loss": 0.4691, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.25046979865772e-05, | |
| "loss": 0.4775, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_las": 78.6510590858417, | |
| "eval_loss": 1.0519626140594482, | |
| "eval_runtime": 10.7438, | |
| "eval_samples_per_second": 186.246, | |
| "eval_steps_per_second": 23.362, | |
| "eval_uas": 83.1820353559484, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 7.196778523489934e-05, | |
| "loss": 0.4186, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 7.143087248322148e-05, | |
| "loss": 0.3303, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 7.089395973154363e-05, | |
| "loss": 0.3402, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 7.035704697986578e-05, | |
| "loss": 0.3397, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 6.982013422818792e-05, | |
| "loss": 0.3092, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_las": 79.2323618410575, | |
| "eval_loss": 1.2302210330963135, | |
| "eval_runtime": 10.7322, | |
| "eval_samples_per_second": 186.449, | |
| "eval_steps_per_second": 23.388, | |
| "eval_uas": 83.76731963688485, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 6.928322147651007e-05, | |
| "loss": 0.2589, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 6.874630872483222e-05, | |
| "loss": 0.2649, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 6.820939597315437e-05, | |
| "loss": 0.2664, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 6.767248322147652e-05, | |
| "loss": 0.2355, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 6.713557046979866e-05, | |
| "loss": 0.207, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "eval_las": 79.93311036789298, | |
| "eval_loss": 1.3027677536010742, | |
| "eval_runtime": 10.7196, | |
| "eval_samples_per_second": 186.667, | |
| "eval_steps_per_second": 23.415, | |
| "eval_uas": 84.44019748367575, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 6.659865771812081e-05, | |
| "loss": 0.2012, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 6.606174496644296e-05, | |
| "loss": 0.218, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 6.55248322147651e-05, | |
| "loss": 0.1879, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 6.498791946308724e-05, | |
| "loss": 0.1666, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 6.445100671140939e-05, | |
| "loss": 0.1809, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "eval_las": 80.13616817964643, | |
| "eval_loss": 1.3230667114257812, | |
| "eval_runtime": 10.6879, | |
| "eval_samples_per_second": 187.221, | |
| "eval_steps_per_second": 23.484, | |
| "eval_uas": 84.6711259754738, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 6.391409395973154e-05, | |
| "loss": 0.1722, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 6.337718120805369e-05, | |
| "loss": 0.1486, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 6.284026845637584e-05, | |
| "loss": 0.1365, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 6.230335570469799e-05, | |
| "loss": 0.1423, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 6.176644295302013e-05, | |
| "loss": 0.158, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_las": 80.49848702022615, | |
| "eval_loss": 1.3992433547973633, | |
| "eval_runtime": 10.7436, | |
| "eval_samples_per_second": 186.25, | |
| "eval_steps_per_second": 23.363, | |
| "eval_uas": 84.8702022615066, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 6.122953020134228e-05, | |
| "loss": 0.131, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 6.069261744966444e-05, | |
| "loss": 0.1146, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 6.0155704697986585e-05, | |
| "loss": 0.1294, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 5.9618791946308734e-05, | |
| "loss": 0.1273, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 5.9081879194630875e-05, | |
| "loss": 0.1048, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "eval_las": 80.72543398630356, | |
| "eval_loss": 1.6042977571487427, | |
| "eval_runtime": 10.7363, | |
| "eval_samples_per_second": 186.377, | |
| "eval_steps_per_second": 23.379, | |
| "eval_uas": 84.95381430164038, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.46, | |
| "learning_rate": 5.854496644295302e-05, | |
| "loss": 0.1054, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 5.800805369127517e-05, | |
| "loss": 0.1101, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 5.747114093959732e-05, | |
| "loss": 0.1083, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 5.693422818791947e-05, | |
| "loss": 0.084, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 5.6397315436241616e-05, | |
| "loss": 0.0887, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "eval_las": 80.97627010670489, | |
| "eval_loss": 1.5820705890655518, | |
| "eval_runtime": 10.7457, | |
| "eval_samples_per_second": 186.214, | |
| "eval_steps_per_second": 23.358, | |
| "eval_uas": 85.23650262780697, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 5.5860402684563764e-05, | |
| "loss": 0.1013, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 5.532348993288591e-05, | |
| "loss": 0.0996, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 5.478657718120806e-05, | |
| "loss": 0.0769, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 5.424966442953021e-05, | |
| "loss": 0.0839, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 5.371275167785236e-05, | |
| "loss": 0.0822, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "eval_las": 80.7493231406275, | |
| "eval_loss": 1.635920763015747, | |
| "eval_runtime": 10.7365, | |
| "eval_samples_per_second": 186.373, | |
| "eval_steps_per_second": 23.378, | |
| "eval_uas": 85.16483516483517, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 5.31758389261745e-05, | |
| "loss": 0.0889, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 5.263892617449665e-05, | |
| "loss": 0.0665, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 5.2102013422818795e-05, | |
| "loss": 0.0736, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 5.1565100671140944e-05, | |
| "loss": 0.0759, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 5.102818791946309e-05, | |
| "loss": 0.0742, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "eval_las": 81.01608536391144, | |
| "eval_loss": 1.7281749248504639, | |
| "eval_runtime": 10.7423, | |
| "eval_samples_per_second": 186.274, | |
| "eval_steps_per_second": 23.366, | |
| "eval_uas": 85.16483516483517, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 5.049127516778524e-05, | |
| "loss": 0.0615, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 14.54, | |
| "learning_rate": 4.995436241610739e-05, | |
| "loss": 0.0642, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 4.941744966442954e-05, | |
| "loss": 0.0669, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 4.8880536912751685e-05, | |
| "loss": 0.0662, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 4.834362416107383e-05, | |
| "loss": 0.0616, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "eval_las": 81.02802994107343, | |
| "eval_loss": 1.7688270807266235, | |
| "eval_runtime": 10.7229, | |
| "eval_samples_per_second": 186.61, | |
| "eval_steps_per_second": 23.408, | |
| "eval_uas": 85.2882624621755, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 4.780671140939598e-05, | |
| "loss": 0.0616, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 4.726979865771813e-05, | |
| "loss": 0.0648, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 4.673825503355705e-05, | |
| "loss": 0.0561, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 4.62013422818792e-05, | |
| "loss": 0.0488, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 4.5664429530201346e-05, | |
| "loss": 0.056, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "eval_las": 81.33062589584328, | |
| "eval_loss": 1.8782949447631836, | |
| "eval_runtime": 10.7117, | |
| "eval_samples_per_second": 186.804, | |
| "eval_steps_per_second": 23.432, | |
| "eval_uas": 85.45548654244305, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 4.5127516778523494e-05, | |
| "loss": 0.0551, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 4.459060402684564e-05, | |
| "loss": 0.0528, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 4.405369127516779e-05, | |
| "loss": 0.0489, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.351677852348994e-05, | |
| "loss": 0.0516, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 4.297986577181209e-05, | |
| "loss": 0.0488, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "eval_las": 81.38636725593247, | |
| "eval_loss": 1.9307818412780762, | |
| "eval_runtime": 10.8381, | |
| "eval_samples_per_second": 184.626, | |
| "eval_steps_per_second": 23.159, | |
| "eval_uas": 85.57493231406275, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 4.244295302013423e-05, | |
| "loss": 0.0522, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 18.37, | |
| "learning_rate": 4.190604026845638e-05, | |
| "loss": 0.0467, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 18.62, | |
| "learning_rate": 4.1369127516778525e-05, | |
| "loss": 0.0482, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.0832214765100673e-05, | |
| "loss": 0.0433, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 4.029530201342282e-05, | |
| "loss": 0.0431, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "eval_las": 81.95970695970696, | |
| "eval_loss": 2.003589153289795, | |
| "eval_runtime": 10.7383, | |
| "eval_samples_per_second": 186.342, | |
| "eval_steps_per_second": 23.374, | |
| "eval_uas": 85.9969740404523, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 19.39, | |
| "learning_rate": 3.975838926174497e-05, | |
| "loss": 0.04, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 3.922147651006712e-05, | |
| "loss": 0.0427, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 3.8684563758389266e-05, | |
| "loss": 0.036, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 20.15, | |
| "learning_rate": 3.814765100671141e-05, | |
| "loss": 0.0418, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 20.41, | |
| "learning_rate": 3.7610738255033556e-05, | |
| "loss": 0.0438, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 20.41, | |
| "eval_las": 81.75266762223285, | |
| "eval_loss": 2.004507541656494, | |
| "eval_runtime": 10.7632, | |
| "eval_samples_per_second": 185.912, | |
| "eval_steps_per_second": 23.32, | |
| "eval_uas": 85.94123268036311, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 3.7073825503355704e-05, | |
| "loss": 0.0315, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "learning_rate": 3.653691275167785e-05, | |
| "loss": 0.0379, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 21.17, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0364, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 3.546308724832215e-05, | |
| "loss": 0.0322, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "learning_rate": 3.49261744966443e-05, | |
| "loss": 0.039, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "eval_las": 81.68498168498168, | |
| "eval_loss": 1.990915298461914, | |
| "eval_runtime": 10.7084, | |
| "eval_samples_per_second": 186.863, | |
| "eval_steps_per_second": 23.44, | |
| "eval_uas": 85.65854435419654, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 3.4389261744966446e-05, | |
| "loss": 0.0319, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 22.19, | |
| "learning_rate": 3.3852348993288594e-05, | |
| "loss": 0.0355, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "learning_rate": 3.331543624161074e-05, | |
| "loss": 0.0276, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "learning_rate": 3.277852348993289e-05, | |
| "loss": 0.0293, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "learning_rate": 3.224161073825504e-05, | |
| "loss": 0.0351, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "eval_las": 81.86813186813187, | |
| "eval_loss": 2.0062038898468018, | |
| "eval_runtime": 10.7485, | |
| "eval_samples_per_second": 186.165, | |
| "eval_steps_per_second": 23.352, | |
| "eval_uas": 85.8257684344641, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 23.21, | |
| "learning_rate": 3.170469798657718e-05, | |
| "loss": 0.0321, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 3.116778523489933e-05, | |
| "loss": 0.03, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 23.72, | |
| "learning_rate": 3.0630872483221477e-05, | |
| "loss": 0.0306, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 23.98, | |
| "learning_rate": 3.0093959731543628e-05, | |
| "loss": 0.0264, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 24.23, | |
| "learning_rate": 2.9557046979865776e-05, | |
| "loss": 0.0262, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 24.23, | |
| "eval_las": 81.89998407389712, | |
| "eval_loss": 2.160494804382324, | |
| "eval_runtime": 10.723, | |
| "eval_samples_per_second": 186.608, | |
| "eval_steps_per_second": 23.408, | |
| "eval_uas": 86.05271540054149, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "learning_rate": 2.9020134228187925e-05, | |
| "loss": 0.0299, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 24.74, | |
| "learning_rate": 2.848322147651007e-05, | |
| "loss": 0.0284, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.7946308724832218e-05, | |
| "loss": 0.0308, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 25.26, | |
| "learning_rate": 2.7409395973154366e-05, | |
| "loss": 0.0225, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 25.51, | |
| "learning_rate": 2.6872483221476514e-05, | |
| "loss": 0.0248, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 25.51, | |
| "eval_las": 82.34193342888994, | |
| "eval_loss": 2.2547311782836914, | |
| "eval_runtime": 10.7226, | |
| "eval_samples_per_second": 186.616, | |
| "eval_steps_per_second": 23.409, | |
| "eval_uas": 86.42697881828316, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 25.77, | |
| "learning_rate": 2.6335570469798663e-05, | |
| "loss": 0.0238, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.5798657718120804e-05, | |
| "loss": 0.0243, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "learning_rate": 2.5261744966442952e-05, | |
| "loss": 0.0236, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 2.47248322147651e-05, | |
| "loss": 0.0207, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 26.79, | |
| "learning_rate": 2.4187919463087252e-05, | |
| "loss": 0.0181, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 26.79, | |
| "eval_las": 81.99952221691352, | |
| "eval_loss": 2.2970921993255615, | |
| "eval_runtime": 10.7206, | |
| "eval_samples_per_second": 186.649, | |
| "eval_steps_per_second": 23.413, | |
| "eval_uas": 86.07262302914476, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 2.36510067114094e-05, | |
| "loss": 0.0225, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 27.3, | |
| "learning_rate": 2.311409395973155e-05, | |
| "loss": 0.019, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 2.257718120805369e-05, | |
| "loss": 0.0212, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 27.81, | |
| "learning_rate": 2.204026845637584e-05, | |
| "loss": 0.0183, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 2.1503355704697987e-05, | |
| "loss": 0.0233, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "eval_las": 82.28619206880077, | |
| "eval_loss": 2.4315474033355713, | |
| "eval_runtime": 10.7511, | |
| "eval_samples_per_second": 186.12, | |
| "eval_steps_per_second": 23.346, | |
| "eval_uas": 86.18012422360249, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.0966442953020135e-05, | |
| "loss": 0.0196, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.0429530201342283e-05, | |
| "loss": 0.0178, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 28.83, | |
| "learning_rate": 1.989261744966443e-05, | |
| "loss": 0.019, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 29.08, | |
| "learning_rate": 1.935570469798658e-05, | |
| "loss": 0.0199, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "learning_rate": 1.8818791946308724e-05, | |
| "loss": 0.0201, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "eval_las": 82.27822901735945, | |
| "eval_loss": 2.434476613998413, | |
| "eval_runtime": 10.7536, | |
| "eval_samples_per_second": 186.078, | |
| "eval_steps_per_second": 23.341, | |
| "eval_uas": 86.20401337792643, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 29.59, | |
| "learning_rate": 1.8281879194630873e-05, | |
| "loss": 0.0143, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 1.774496644295302e-05, | |
| "loss": 0.0152, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 30.1, | |
| "learning_rate": 1.720805369127517e-05, | |
| "loss": 0.0191, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 1.6671140939597317e-05, | |
| "loss": 0.0185, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 30.61, | |
| "learning_rate": 1.6134228187919466e-05, | |
| "loss": 0.0148, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 30.61, | |
| "eval_las": 82.41758241758241, | |
| "eval_loss": 2.4714443683624268, | |
| "eval_runtime": 10.7353, | |
| "eval_samples_per_second": 186.395, | |
| "eval_steps_per_second": 23.381, | |
| "eval_uas": 86.38318203535594, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 30.87, | |
| "learning_rate": 1.560268456375839e-05, | |
| "loss": 0.0179, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 31.12, | |
| "learning_rate": 1.5065771812080539e-05, | |
| "loss": 0.0179, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "learning_rate": 1.4528859060402685e-05, | |
| "loss": 0.0156, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 31.63, | |
| "learning_rate": 1.3991946308724834e-05, | |
| "loss": 0.0142, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 31.89, | |
| "learning_rate": 1.3455033557046982e-05, | |
| "loss": 0.0148, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 31.89, | |
| "eval_las": 82.3459149546106, | |
| "eval_loss": 2.4893686771392822, | |
| "eval_runtime": 10.7166, | |
| "eval_samples_per_second": 186.719, | |
| "eval_steps_per_second": 23.422, | |
| "eval_uas": 86.33540372670807, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "learning_rate": 1.2918120805369127e-05, | |
| "loss": 0.0142, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 32.4, | |
| "learning_rate": 1.2381208053691277e-05, | |
| "loss": 0.0118, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 32.65, | |
| "learning_rate": 1.1844295302013425e-05, | |
| "loss": 0.0121, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 1.130738255033557e-05, | |
| "loss": 0.0139, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 1.0770469798657718e-05, | |
| "loss": 0.0146, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "eval_las": 82.38971173753782, | |
| "eval_loss": 2.5669312477111816, | |
| "eval_runtime": 10.72, | |
| "eval_samples_per_second": 186.661, | |
| "eval_steps_per_second": 23.414, | |
| "eval_uas": 86.24382863513299, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 33.42, | |
| "learning_rate": 1.0233557046979868e-05, | |
| "loss": 0.0146, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 33.67, | |
| "learning_rate": 9.702013422818793e-06, | |
| "loss": 0.0104, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 9.165100671140941e-06, | |
| "loss": 0.0118, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 34.18, | |
| "learning_rate": 8.628187919463088e-06, | |
| "loss": 0.0083, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 8.091275167785234e-06, | |
| "loss": 0.0133, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "eval_las": 82.55693581780538, | |
| "eval_loss": 2.7767789363861084, | |
| "eval_runtime": 10.7894, | |
| "eval_samples_per_second": 185.46, | |
| "eval_steps_per_second": 23.264, | |
| "eval_uas": 86.33938525242874, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 34.69, | |
| "learning_rate": 7.5543624161073835e-06, | |
| "loss": 0.0117, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 7.017449664429531e-06, | |
| "loss": 0.0118, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "learning_rate": 6.480536912751678e-06, | |
| "loss": 0.0088, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 35.46, | |
| "learning_rate": 5.943624161073826e-06, | |
| "loss": 0.0127, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 5.406711409395974e-06, | |
| "loss": 0.012, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "eval_las": 82.80379041248607, | |
| "eval_loss": 2.7750918865203857, | |
| "eval_runtime": 10.7115, | |
| "eval_samples_per_second": 186.808, | |
| "eval_steps_per_second": 23.433, | |
| "eval_uas": 86.63401815575729, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 4.869798657718121e-06, | |
| "loss": 0.0131, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 36.22, | |
| "learning_rate": 4.332885906040269e-06, | |
| "loss": 0.0103, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 36.48, | |
| "learning_rate": 3.795973154362416e-06, | |
| "loss": 0.0091, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 36.73, | |
| "learning_rate": 3.259060402684564e-06, | |
| "loss": 0.0095, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "learning_rate": 2.722147651006712e-06, | |
| "loss": 0.0119, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "eval_las": 82.66045548654245, | |
| "eval_loss": 2.8619158267974854, | |
| "eval_runtime": 10.7166, | |
| "eval_samples_per_second": 186.719, | |
| "eval_steps_per_second": 23.422, | |
| "eval_uas": 86.49864628125498, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 37.24, | |
| "learning_rate": 2.185234899328859e-06, | |
| "loss": 0.0108, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 1.648322147651007e-06, | |
| "loss": 0.0097, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 37.76, | |
| "learning_rate": 1.1114093959731544e-06, | |
| "loss": 0.0094, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 5.74496644295302e-07, | |
| "loss": 0.0104, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 38.27, | |
| "learning_rate": 3.758389261744967e-08, | |
| "loss": 0.0121, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 38.27, | |
| "eval_las": 82.78388278388277, | |
| "eval_loss": 2.878222942352295, | |
| "eval_runtime": 10.7038, | |
| "eval_samples_per_second": 186.943, | |
| "eval_steps_per_second": 23.45, | |
| "eval_uas": 86.55836916706482, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 38.27, | |
| "step": 15000, | |
| "total_flos": 9.581458853161574e+16, | |
| "train_loss": 0.1857688402692477, | |
| "train_runtime": 6436.3421, | |
| "train_samples_per_second": 74.577, | |
| "train_steps_per_second": 2.331 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 39, | |
| "total_flos": 9.581458853161574e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |