| { | |
| "best_metric": 73.77547916032857, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-parsing-ud-Arabic-PADT/checkpoint-15000", | |
| "epoch": 78.94736842105263, | |
| "global_step": 15000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.6e-05, | |
| "loss": 4.5897, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.948993288590604e-05, | |
| "loss": 2.0458, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.895302013422819e-05, | |
| "loss": 1.5969, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.841610738255034e-05, | |
| "loss": 1.4122, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.787919463087249e-05, | |
| "loss": 1.1658, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_las": 67.36639286076462, | |
| "eval_loss": 1.6013022661209106, | |
| "eval_runtime": 6.4078, | |
| "eval_samples_per_second": 141.859, | |
| "eval_steps_per_second": 17.791, | |
| "eval_uas": 74.67802454112159, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.734228187919463e-05, | |
| "loss": 1.0887, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 7.680536912751678e-05, | |
| "loss": 0.9181, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 7.626845637583893e-05, | |
| "loss": 0.8432, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 7.573154362416108e-05, | |
| "loss": 0.7403, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 7.519463087248323e-05, | |
| "loss": 0.6848, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "eval_las": 69.60416455396681, | |
| "eval_loss": 1.8538918495178223, | |
| "eval_runtime": 6.402, | |
| "eval_samples_per_second": 141.987, | |
| "eval_steps_per_second": 17.807, | |
| "eval_uas": 76.92593719365853, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 7.465771812080537e-05, | |
| "loss": 0.6156, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 7.412080536912752e-05, | |
| "loss": 0.5488, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 7.358389261744967e-05, | |
| "loss": 0.5053, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 7.304697986577182e-05, | |
| "loss": 0.4459, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 7.251006711409397e-05, | |
| "loss": 0.4394, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_las": 70.65882432478112, | |
| "eval_loss": 1.9962742328643799, | |
| "eval_runtime": 6.3907, | |
| "eval_samples_per_second": 142.238, | |
| "eval_steps_per_second": 17.838, | |
| "eval_uas": 77.94679376669032, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 7.197315436241612e-05, | |
| "loss": 0.3671, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 7.143624161073826e-05, | |
| "loss": 0.3761, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 7.089932885906041e-05, | |
| "loss": 0.3076, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.036241610738256e-05, | |
| "loss": 0.3257, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 6.982550335570471e-05, | |
| "loss": 0.259, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "eval_las": 70.97657438393672, | |
| "eval_loss": 2.430649995803833, | |
| "eval_runtime": 6.3911, | |
| "eval_samples_per_second": 142.229, | |
| "eval_steps_per_second": 17.837, | |
| "eval_uas": 78.3625730994152, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 6.928859060402686e-05, | |
| "loss": 0.2775, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 6.8751677852349e-05, | |
| "loss": 0.2325, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 6.821476510067115e-05, | |
| "loss": 0.2426, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 6.76778523489933e-05, | |
| "loss": 0.2116, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 6.714093959731544e-05, | |
| "loss": 0.2116, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "eval_las": 71.21319676841429, | |
| "eval_loss": 2.8564882278442383, | |
| "eval_runtime": 6.4121, | |
| "eval_samples_per_second": 141.763, | |
| "eval_steps_per_second": 17.779, | |
| "eval_uas": 78.58905452455802, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 6.660402684563758e-05, | |
| "loss": 0.1948, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 6.606711409395973e-05, | |
| "loss": 0.1862, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 6.553020134228188e-05, | |
| "loss": 0.1754, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 6.499328859060403e-05, | |
| "loss": 0.1705, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 6.445637583892618e-05, | |
| "loss": 0.1618, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "eval_las": 71.65601865936517, | |
| "eval_loss": 2.8342225551605225, | |
| "eval_runtime": 6.4119, | |
| "eval_samples_per_second": 141.768, | |
| "eval_steps_per_second": 17.78, | |
| "eval_uas": 78.93046682216138, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 6.391946308724833e-05, | |
| "loss": 0.1507, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 6.338255033557047e-05, | |
| "loss": 0.153, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 6.284563758389262e-05, | |
| "loss": 0.1401, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 17.89, | |
| "learning_rate": 6.230872483221477e-05, | |
| "loss": 0.1416, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 18.42, | |
| "learning_rate": 6.177181208053692e-05, | |
| "loss": 0.1273, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 18.42, | |
| "eval_las": 71.52756650779165, | |
| "eval_loss": 3.102910280227661, | |
| "eval_runtime": 6.3959, | |
| "eval_samples_per_second": 142.122, | |
| "eval_steps_per_second": 17.824, | |
| "eval_uas": 78.93384714193962, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 6.123489932885907e-05, | |
| "loss": 0.132, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "learning_rate": 6.069798657718121e-05, | |
| "loss": 0.1188, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.016107382550336e-05, | |
| "loss": 0.1249, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 20.53, | |
| "learning_rate": 5.9624161073825505e-05, | |
| "loss": 0.1075, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 21.05, | |
| "learning_rate": 5.9087248322147654e-05, | |
| "loss": 0.1147, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 21.05, | |
| "eval_las": 71.81151336916473, | |
| "eval_loss": 3.3238770961761475, | |
| "eval_runtime": 6.4049, | |
| "eval_samples_per_second": 141.923, | |
| "eval_steps_per_second": 17.799, | |
| "eval_uas": 79.0048338572829, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 21.58, | |
| "learning_rate": 5.85503355704698e-05, | |
| "loss": 0.1037, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 22.11, | |
| "learning_rate": 5.801342281879195e-05, | |
| "loss": 0.1071, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 22.63, | |
| "learning_rate": 5.74765100671141e-05, | |
| "loss": 0.0993, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 23.16, | |
| "learning_rate": 5.6939597315436247e-05, | |
| "loss": 0.0986, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 5.6402684563758395e-05, | |
| "loss": 0.0916, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "eval_las": 71.7709495318257, | |
| "eval_loss": 3.397751569747925, | |
| "eval_runtime": 6.3879, | |
| "eval_samples_per_second": 142.3, | |
| "eval_steps_per_second": 17.846, | |
| "eval_uas": 79.10286313085217, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 5.586577181208054e-05, | |
| "loss": 0.0936, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 24.74, | |
| "learning_rate": 5.532885906040269e-05, | |
| "loss": 0.0917, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 25.26, | |
| "learning_rate": 5.479194630872483e-05, | |
| "loss": 0.0881, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 25.79, | |
| "learning_rate": 5.425503355704698e-05, | |
| "loss": 0.0853, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 5.371812080536913e-05, | |
| "loss": 0.0839, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "eval_las": 72.05827671297705, | |
| "eval_loss": 3.57505464553833, | |
| "eval_runtime": 6.3979, | |
| "eval_samples_per_second": 142.078, | |
| "eval_steps_per_second": 17.818, | |
| "eval_uas": 79.14680728796945, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "learning_rate": 5.318120805369128e-05, | |
| "loss": 0.0815, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 27.37, | |
| "learning_rate": 5.2644295302013426e-05, | |
| "loss": 0.0777, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "learning_rate": 5.2107382550335574e-05, | |
| "loss": 0.081, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "learning_rate": 5.157046979865772e-05, | |
| "loss": 0.0723, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 5.103355704697987e-05, | |
| "loss": 0.0771, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "eval_las": 72.2408139810026, | |
| "eval_loss": 3.521331787109375, | |
| "eval_runtime": 6.426, | |
| "eval_samples_per_second": 141.456, | |
| "eval_steps_per_second": 17.74, | |
| "eval_uas": 79.40371159111652, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 29.47, | |
| "learning_rate": 5.049664429530202e-05, | |
| "loss": 0.072, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.995973154362417e-05, | |
| "loss": 0.0745, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 30.53, | |
| "learning_rate": 4.9422818791946315e-05, | |
| "loss": 0.0681, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 31.05, | |
| "learning_rate": 4.888590604026846e-05, | |
| "loss": 0.069, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 31.58, | |
| "learning_rate": 4.8348993288590605e-05, | |
| "loss": 0.065, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 31.58, | |
| "eval_las": 71.79461177027346, | |
| "eval_loss": 3.818310022354126, | |
| "eval_runtime": 6.3782, | |
| "eval_samples_per_second": 142.517, | |
| "eval_steps_per_second": 17.873, | |
| "eval_uas": 79.04877801440017, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 32.11, | |
| "learning_rate": 4.781208053691275e-05, | |
| "loss": 0.066, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 32.63, | |
| "learning_rate": 4.72751677852349e-05, | |
| "loss": 0.0592, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 33.16, | |
| "learning_rate": 4.673825503355705e-05, | |
| "loss": 0.0637, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 33.68, | |
| "learning_rate": 4.62013422818792e-05, | |
| "loss": 0.0591, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 34.21, | |
| "learning_rate": 4.5664429530201346e-05, | |
| "loss": 0.0587, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 34.21, | |
| "eval_las": 72.31180069634587, | |
| "eval_loss": 3.807619333267212, | |
| "eval_runtime": 6.3984, | |
| "eval_samples_per_second": 142.068, | |
| "eval_steps_per_second": 17.817, | |
| "eval_uas": 79.51188182402055, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 34.74, | |
| "learning_rate": 4.5127516778523494e-05, | |
| "loss": 0.058, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 4.459060402684564e-05, | |
| "loss": 0.0572, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 35.79, | |
| "learning_rate": 4.405369127516779e-05, | |
| "loss": 0.0562, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 36.32, | |
| "learning_rate": 4.351677852348994e-05, | |
| "loss": 0.0547, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 36.84, | |
| "learning_rate": 4.297986577181209e-05, | |
| "loss": 0.0573, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 36.84, | |
| "eval_las": 72.48419700503668, | |
| "eval_loss": 3.9023566246032715, | |
| "eval_runtime": 6.3817, | |
| "eval_samples_per_second": 142.438, | |
| "eval_steps_per_second": 17.864, | |
| "eval_uas": 79.59638981847684, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "learning_rate": 4.244295302013423e-05, | |
| "loss": 0.0522, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 37.89, | |
| "learning_rate": 4.190604026845638e-05, | |
| "loss": 0.0525, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 38.42, | |
| "learning_rate": 4.1369127516778525e-05, | |
| "loss": 0.0485, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 38.95, | |
| "learning_rate": 4.0832214765100673e-05, | |
| "loss": 0.0536, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 4.029530201342282e-05, | |
| "loss": 0.0503, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "eval_las": 72.57884595882771, | |
| "eval_loss": 4.051434516906738, | |
| "eval_runtime": 6.3781, | |
| "eval_samples_per_second": 142.52, | |
| "eval_steps_per_second": 17.874, | |
| "eval_uas": 79.66399621404184, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.975838926174497e-05, | |
| "loss": 0.0488, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 40.53, | |
| "learning_rate": 3.922147651006712e-05, | |
| "loss": 0.0459, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 41.05, | |
| "learning_rate": 3.8684563758389266e-05, | |
| "loss": 0.0481, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 41.58, | |
| "learning_rate": 3.814765100671141e-05, | |
| "loss": 0.0464, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 42.11, | |
| "learning_rate": 3.7610738255033556e-05, | |
| "loss": 0.0476, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 42.11, | |
| "eval_las": 72.74786194774026, | |
| "eval_loss": 4.076736927032471, | |
| "eval_runtime": 6.3895, | |
| "eval_samples_per_second": 142.265, | |
| "eval_steps_per_second": 17.842, | |
| "eval_uas": 79.88033667984992, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 42.63, | |
| "learning_rate": 3.7073825503355704e-05, | |
| "loss": 0.0456, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 43.16, | |
| "learning_rate": 3.653691275167785e-05, | |
| "loss": 0.0464, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 43.68, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0429, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 44.21, | |
| "learning_rate": 3.546308724832215e-05, | |
| "loss": 0.0442, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 44.74, | |
| "learning_rate": 3.49261744966443e-05, | |
| "loss": 0.0427, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 44.74, | |
| "eval_las": 72.79180610485751, | |
| "eval_loss": 4.197169303894043, | |
| "eval_runtime": 6.3929, | |
| "eval_samples_per_second": 142.188, | |
| "eval_steps_per_second": 17.832, | |
| "eval_uas": 79.76540580738939, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 45.26, | |
| "learning_rate": 3.4389261744966446e-05, | |
| "loss": 0.0405, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 45.79, | |
| "learning_rate": 3.3852348993288594e-05, | |
| "loss": 0.0416, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 46.32, | |
| "learning_rate": 3.331543624161074e-05, | |
| "loss": 0.0402, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 46.84, | |
| "learning_rate": 3.277852348993289e-05, | |
| "loss": 0.0389, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 47.37, | |
| "learning_rate": 3.224161073825504e-05, | |
| "loss": 0.0415, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 47.37, | |
| "eval_las": 72.96758273332658, | |
| "eval_loss": 4.470444202423096, | |
| "eval_runtime": 6.3862, | |
| "eval_samples_per_second": 142.338, | |
| "eval_steps_per_second": 17.851, | |
| "eval_uas": 79.90737923807593, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 47.89, | |
| "learning_rate": 3.170469798657718e-05, | |
| "loss": 0.0402, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 48.42, | |
| "learning_rate": 3.116778523489933e-05, | |
| "loss": 0.036, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 48.95, | |
| "learning_rate": 3.0630872483221477e-05, | |
| "loss": 0.0391, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 49.47, | |
| "learning_rate": 3.0093959731543628e-05, | |
| "loss": 0.0351, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.9557046979865776e-05, | |
| "loss": 0.0389, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_las": 72.97434337288308, | |
| "eval_loss": 4.371275901794434, | |
| "eval_runtime": 6.4275, | |
| "eval_samples_per_second": 141.424, | |
| "eval_steps_per_second": 17.736, | |
| "eval_uas": 80.02231011053645, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 50.53, | |
| "learning_rate": 2.9020134228187925e-05, | |
| "loss": 0.036, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 51.05, | |
| "learning_rate": 2.848322147651007e-05, | |
| "loss": 0.0365, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 51.58, | |
| "learning_rate": 2.7946308724832218e-05, | |
| "loss": 0.0348, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 52.11, | |
| "learning_rate": 2.7409395973154366e-05, | |
| "loss": 0.0338, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 52.63, | |
| "learning_rate": 2.6872483221476514e-05, | |
| "loss": 0.0339, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 52.63, | |
| "eval_las": 73.21772639691714, | |
| "eval_loss": 4.721055507659912, | |
| "eval_runtime": 6.3848, | |
| "eval_samples_per_second": 142.369, | |
| "eval_steps_per_second": 17.855, | |
| "eval_uas": 80.05273298854073, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 53.16, | |
| "learning_rate": 2.6335570469798663e-05, | |
| "loss": 0.0336, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 53.68, | |
| "learning_rate": 2.5798657718120804e-05, | |
| "loss": 0.0338, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 54.21, | |
| "learning_rate": 2.5261744966442952e-05, | |
| "loss": 0.0312, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 54.74, | |
| "learning_rate": 2.47248322147651e-05, | |
| "loss": 0.0329, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 55.26, | |
| "learning_rate": 2.4187919463087252e-05, | |
| "loss": 0.0354, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 55.26, | |
| "eval_las": 72.97096305310482, | |
| "eval_loss": 4.761220455169678, | |
| "eval_runtime": 6.3891, | |
| "eval_samples_per_second": 142.275, | |
| "eval_steps_per_second": 17.843, | |
| "eval_uas": 79.91075955785418, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 55.79, | |
| "learning_rate": 2.36510067114094e-05, | |
| "loss": 0.0312, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 56.32, | |
| "learning_rate": 2.311409395973155e-05, | |
| "loss": 0.0322, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 56.84, | |
| "learning_rate": 2.257718120805369e-05, | |
| "loss": 0.0298, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 57.37, | |
| "learning_rate": 2.204026845637584e-05, | |
| "loss": 0.0304, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 57.89, | |
| "learning_rate": 2.1503355704697987e-05, | |
| "loss": 0.0304, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 57.89, | |
| "eval_las": 73.20420511780415, | |
| "eval_loss": 4.784778594970703, | |
| "eval_runtime": 6.3775, | |
| "eval_samples_per_second": 142.533, | |
| "eval_steps_per_second": 17.875, | |
| "eval_uas": 80.04935266876247, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 58.42, | |
| "learning_rate": 2.0966442953020135e-05, | |
| "loss": 0.0278, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 58.95, | |
| "learning_rate": 2.0429530201342283e-05, | |
| "loss": 0.0314, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 59.47, | |
| "learning_rate": 1.989261744966443e-05, | |
| "loss": 0.029, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.935570469798658e-05, | |
| "loss": 0.0278, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 60.53, | |
| "learning_rate": 1.8818791946308724e-05, | |
| "loss": 0.0273, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 60.53, | |
| "eval_las": 73.17716255957814, | |
| "eval_loss": 5.09051513671875, | |
| "eval_runtime": 6.4269, | |
| "eval_samples_per_second": 141.436, | |
| "eval_steps_per_second": 17.738, | |
| "eval_uas": 80.10005746543622, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 61.05, | |
| "learning_rate": 1.8281879194630873e-05, | |
| "loss": 0.0296, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 61.58, | |
| "learning_rate": 1.774496644295302e-05, | |
| "loss": 0.0281, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 62.11, | |
| "learning_rate": 1.720805369127517e-05, | |
| "loss": 0.0259, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 62.63, | |
| "learning_rate": 1.6671140939597317e-05, | |
| "loss": 0.0264, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 63.16, | |
| "learning_rate": 1.6134228187919466e-05, | |
| "loss": 0.0273, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 63.16, | |
| "eval_las": 73.50505357806848, | |
| "eval_loss": 5.068530559539795, | |
| "eval_runtime": 6.3815, | |
| "eval_samples_per_second": 142.442, | |
| "eval_steps_per_second": 17.864, | |
| "eval_uas": 80.3840043268093, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 63.68, | |
| "learning_rate": 1.559731543624161e-05, | |
| "loss": 0.026, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 64.21, | |
| "learning_rate": 1.506040268456376e-05, | |
| "loss": 0.0269, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 64.74, | |
| "learning_rate": 1.4523489932885909e-05, | |
| "loss": 0.0243, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 65.26, | |
| "learning_rate": 1.3986577181208053e-05, | |
| "loss": 0.0266, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 65.79, | |
| "learning_rate": 1.3449664429530202e-05, | |
| "loss": 0.0256, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 65.79, | |
| "eval_las": 73.54561741540749, | |
| "eval_loss": 5.208915710449219, | |
| "eval_runtime": 6.3736, | |
| "eval_samples_per_second": 142.619, | |
| "eval_steps_per_second": 17.886, | |
| "eval_uas": 80.3231585708008, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 66.32, | |
| "learning_rate": 1.2912751677852352e-05, | |
| "loss": 0.0245, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 66.84, | |
| "learning_rate": 1.2375838926174497e-05, | |
| "loss": 0.0265, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 67.37, | |
| "learning_rate": 1.1838926174496645e-05, | |
| "loss": 0.026, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 67.89, | |
| "learning_rate": 1.1302013422818795e-05, | |
| "loss": 0.0232, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 68.42, | |
| "learning_rate": 1.076510067114094e-05, | |
| "loss": 0.0231, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 68.42, | |
| "eval_las": 73.63350572964202, | |
| "eval_loss": 5.212841033935547, | |
| "eval_runtime": 6.4593, | |
| "eval_samples_per_second": 140.728, | |
| "eval_steps_per_second": 17.649, | |
| "eval_uas": 80.35020112902681, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 68.95, | |
| "learning_rate": 1.0228187919463088e-05, | |
| "loss": 0.0242, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 69.47, | |
| "learning_rate": 9.691275167785236e-06, | |
| "loss": 0.0256, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 9.154362416107383e-06, | |
| "loss": 0.0249, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 70.53, | |
| "learning_rate": 8.617449664429531e-06, | |
| "loss": 0.0236, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 71.05, | |
| "learning_rate": 8.080536912751679e-06, | |
| "loss": 0.0237, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 71.05, | |
| "eval_las": 73.65716796808978, | |
| "eval_loss": 5.283775806427002, | |
| "eval_runtime": 6.3678, | |
| "eval_samples_per_second": 142.751, | |
| "eval_steps_per_second": 17.903, | |
| "eval_uas": 80.42794848392658, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 71.58, | |
| "learning_rate": 7.543624161073826e-06, | |
| "loss": 0.0235, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 72.11, | |
| "learning_rate": 7.006711409395974e-06, | |
| "loss": 0.0221, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 72.63, | |
| "learning_rate": 6.469798657718121e-06, | |
| "loss": 0.0223, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 73.16, | |
| "learning_rate": 5.932885906040269e-06, | |
| "loss": 0.0227, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 73.68, | |
| "learning_rate": 5.395973154362416e-06, | |
| "loss": 0.0205, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 73.68, | |
| "eval_las": 73.76871852077207, | |
| "eval_loss": 5.542043209075928, | |
| "eval_runtime": 6.3741, | |
| "eval_samples_per_second": 142.609, | |
| "eval_steps_per_second": 17.885, | |
| "eval_uas": 80.4887942399351, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 74.21, | |
| "learning_rate": 4.859060402684564e-06, | |
| "loss": 0.023, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 74.74, | |
| "learning_rate": 4.322147651006712e-06, | |
| "loss": 0.0227, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 75.26, | |
| "learning_rate": 3.7852348993288595e-06, | |
| "loss": 0.0222, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 75.79, | |
| "learning_rate": 3.248322147651007e-06, | |
| "loss": 0.023, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 76.32, | |
| "learning_rate": 2.716778523489933e-06, | |
| "loss": 0.0221, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 76.32, | |
| "eval_las": 73.7112530845418, | |
| "eval_loss": 5.52190637588501, | |
| "eval_runtime": 6.3515, | |
| "eval_samples_per_second": 143.116, | |
| "eval_steps_per_second": 17.949, | |
| "eval_uas": 80.37048304769631, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 76.84, | |
| "learning_rate": 2.1798657718120807e-06, | |
| "loss": 0.0212, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 77.37, | |
| "learning_rate": 1.6429530201342283e-06, | |
| "loss": 0.021, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 77.89, | |
| "learning_rate": 1.1060402684563759e-06, | |
| "loss": 0.0226, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 78.42, | |
| "learning_rate": 5.691275167785235e-07, | |
| "loss": 0.0215, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 78.95, | |
| "learning_rate": 3.2214765100671145e-08, | |
| "loss": 0.0215, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 78.95, | |
| "eval_las": 73.77547916032857, | |
| "eval_loss": 5.533295154571533, | |
| "eval_runtime": 6.3578, | |
| "eval_samples_per_second": 142.973, | |
| "eval_steps_per_second": 17.931, | |
| "eval_uas": 80.46175168170909, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 78.95, | |
| "step": 15000, | |
| "total_flos": 9.574431893701632e+16, | |
| "train_loss": 0.1834182323773702, | |
| "train_runtime": 7377.9639, | |
| "train_samples_per_second": 65.059, | |
| "train_steps_per_second": 2.033 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 79, | |
| "total_flos": 9.574431893701632e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |