|
{ |
|
"best_metric": 46.35226680562793, |
|
"best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-parsing-ud-Vietnamese-VTB/checkpoint-15000", |
|
"epoch": 340.90909090909093, |
|
"global_step": 15000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 7.680000000000001e-05, |
|
"loss": 4.6843, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 7.948456375838927e-05, |
|
"loss": 1.7913, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 6.82, |
|
"learning_rate": 7.894765100671142e-05, |
|
"loss": 0.9052, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 9.09, |
|
"learning_rate": 7.841073825503357e-05, |
|
"loss": 0.5396, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 11.36, |
|
"learning_rate": 7.78738255033557e-05, |
|
"loss": 0.3325, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 11.36, |
|
"eval_las": 41.54073302067049, |
|
"eval_loss": 6.446278095245361, |
|
"eval_runtime": 4.4907, |
|
"eval_samples_per_second": 178.148, |
|
"eval_steps_per_second": 22.268, |
|
"eval_uas": 54.17752301545944, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 13.64, |
|
"learning_rate": 7.733691275167786e-05, |
|
"loss": 0.2541, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 15.91, |
|
"learning_rate": 7.680000000000001e-05, |
|
"loss": 0.2108, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 18.18, |
|
"learning_rate": 7.626308724832216e-05, |
|
"loss": 0.157, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 20.45, |
|
"learning_rate": 7.57261744966443e-05, |
|
"loss": 0.132, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 22.73, |
|
"learning_rate": 7.518926174496645e-05, |
|
"loss": 0.1145, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 22.73, |
|
"eval_las": 42.226854264373806, |
|
"eval_loss": 7.4281005859375, |
|
"eval_runtime": 4.4917, |
|
"eval_samples_per_second": 178.106, |
|
"eval_steps_per_second": 22.263, |
|
"eval_uas": 54.32516935904117, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"learning_rate": 7.46523489932886e-05, |
|
"loss": 0.101, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 27.27, |
|
"learning_rate": 7.411543624161075e-05, |
|
"loss": 0.0852, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 29.55, |
|
"learning_rate": 7.35785234899329e-05, |
|
"loss": 0.0731, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 31.82, |
|
"learning_rate": 7.304161073825505e-05, |
|
"loss": 0.0672, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 34.09, |
|
"learning_rate": 7.25046979865772e-05, |
|
"loss": 0.0568, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 34.09, |
|
"eval_las": 42.7653291644954, |
|
"eval_loss": 8.853192329406738, |
|
"eval_runtime": 4.4837, |
|
"eval_samples_per_second": 178.424, |
|
"eval_steps_per_second": 22.303, |
|
"eval_uas": 54.828903943025885, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 36.36, |
|
"learning_rate": 7.196778523489934e-05, |
|
"loss": 0.0602, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 38.64, |
|
"learning_rate": 7.143087248322148e-05, |
|
"loss": 0.0498, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 40.91, |
|
"learning_rate": 7.089395973154363e-05, |
|
"loss": 0.0466, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 43.18, |
|
"learning_rate": 7.035704697986578e-05, |
|
"loss": 0.0446, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 45.45, |
|
"learning_rate": 6.982013422818792e-05, |
|
"loss": 0.0449, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 45.45, |
|
"eval_las": 43.798853569567484, |
|
"eval_loss": 8.242417335510254, |
|
"eval_runtime": 4.4843, |
|
"eval_samples_per_second": 178.401, |
|
"eval_steps_per_second": 22.3, |
|
"eval_uas": 56.09692548202189, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 47.73, |
|
"learning_rate": 6.928322147651007e-05, |
|
"loss": 0.0439, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"learning_rate": 6.874630872483222e-05, |
|
"loss": 0.0379, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 52.27, |
|
"learning_rate": 6.820939597315437e-05, |
|
"loss": 0.0367, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 54.55, |
|
"learning_rate": 6.767248322147652e-05, |
|
"loss": 0.0316, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 56.82, |
|
"learning_rate": 6.713557046979866e-05, |
|
"loss": 0.0292, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 56.82, |
|
"eval_las": 43.1735278791037, |
|
"eval_loss": 10.03981876373291, |
|
"eval_runtime": 4.5122, |
|
"eval_samples_per_second": 177.298, |
|
"eval_steps_per_second": 22.162, |
|
"eval_uas": 55.315268368942164, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 59.09, |
|
"learning_rate": 6.659865771812081e-05, |
|
"loss": 0.0312, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 61.36, |
|
"learning_rate": 6.606174496644296e-05, |
|
"loss": 0.0275, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 63.64, |
|
"learning_rate": 6.55248322147651e-05, |
|
"loss": 0.0253, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 65.91, |
|
"learning_rate": 6.498791946308724e-05, |
|
"loss": 0.0256, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 68.18, |
|
"learning_rate": 6.445100671140939e-05, |
|
"loss": 0.0246, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 68.18, |
|
"eval_las": 43.87701928087546, |
|
"eval_loss": 9.3908052444458, |
|
"eval_runtime": 4.4873, |
|
"eval_samples_per_second": 178.28, |
|
"eval_steps_per_second": 22.285, |
|
"eval_uas": 55.75820739968733, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 70.45, |
|
"learning_rate": 6.391409395973154e-05, |
|
"loss": 0.0204, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 72.73, |
|
"learning_rate": 6.337718120805369e-05, |
|
"loss": 0.021, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 75.0, |
|
"learning_rate": 6.284026845637584e-05, |
|
"loss": 0.0226, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 77.27, |
|
"learning_rate": 6.230335570469799e-05, |
|
"loss": 0.0236, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 79.55, |
|
"learning_rate": 6.176644295302013e-05, |
|
"loss": 0.0183, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 79.55, |
|
"eval_las": 44.337328469689076, |
|
"eval_loss": 10.381277084350586, |
|
"eval_runtime": 4.4792, |
|
"eval_samples_per_second": 178.602, |
|
"eval_steps_per_second": 22.325, |
|
"eval_uas": 55.99270453361126, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 81.82, |
|
"learning_rate": 6.122953020134228e-05, |
|
"loss": 0.0185, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 84.09, |
|
"learning_rate": 6.069261744966444e-05, |
|
"loss": 0.0158, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 86.36, |
|
"learning_rate": 6.0155704697986585e-05, |
|
"loss": 0.0137, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 88.64, |
|
"learning_rate": 5.9618791946308734e-05, |
|
"loss": 0.0164, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 90.91, |
|
"learning_rate": 5.9081879194630875e-05, |
|
"loss": 0.0161, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 90.91, |
|
"eval_las": 43.93781483411499, |
|
"eval_loss": 10.604333877563477, |
|
"eval_runtime": 4.4667, |
|
"eval_samples_per_second": 179.104, |
|
"eval_steps_per_second": 22.388, |
|
"eval_uas": 56.07955532395344, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 93.18, |
|
"learning_rate": 5.854496644295302e-05, |
|
"loss": 0.0167, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 95.45, |
|
"learning_rate": 5.800805369127517e-05, |
|
"loss": 0.017, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 97.73, |
|
"learning_rate": 5.747114093959732e-05, |
|
"loss": 0.0186, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 100.0, |
|
"learning_rate": 5.693422818791947e-05, |
|
"loss": 0.0153, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 102.27, |
|
"learning_rate": 5.6397315436241616e-05, |
|
"loss": 0.012, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 102.27, |
|
"eval_las": 42.98245614035088, |
|
"eval_loss": 11.038581848144531, |
|
"eval_runtime": 4.4727, |
|
"eval_samples_per_second": 178.864, |
|
"eval_steps_per_second": 22.358, |
|
"eval_uas": 55.03734583984714, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 104.55, |
|
"learning_rate": 5.5860402684563764e-05, |
|
"loss": 0.0137, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 106.82, |
|
"learning_rate": 5.532348993288591e-05, |
|
"loss": 0.0129, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 109.09, |
|
"learning_rate": 5.478657718120806e-05, |
|
"loss": 0.014, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 111.36, |
|
"learning_rate": 5.424966442953021e-05, |
|
"loss": 0.0126, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 113.64, |
|
"learning_rate": 5.371275167785236e-05, |
|
"loss": 0.0109, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 113.64, |
|
"eval_las": 44.172311968038905, |
|
"eval_loss": 10.87439250946045, |
|
"eval_runtime": 4.4729, |
|
"eval_samples_per_second": 178.856, |
|
"eval_steps_per_second": 22.357, |
|
"eval_uas": 56.218516588500954, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 115.91, |
|
"learning_rate": 5.31758389261745e-05, |
|
"loss": 0.0093, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 118.18, |
|
"learning_rate": 5.263892617449665e-05, |
|
"loss": 0.0128, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 120.45, |
|
"learning_rate": 5.2102013422818795e-05, |
|
"loss": 0.01, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 122.73, |
|
"learning_rate": 5.1565100671140944e-05, |
|
"loss": 0.0096, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 125.0, |
|
"learning_rate": 5.102818791946309e-05, |
|
"loss": 0.0091, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 125.0, |
|
"eval_las": 44.21573736321, |
|
"eval_loss": 10.962388038635254, |
|
"eval_runtime": 4.4768, |
|
"eval_samples_per_second": 178.7, |
|
"eval_steps_per_second": 22.338, |
|
"eval_uas": 56.261941983672045, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 127.27, |
|
"learning_rate": 5.049127516778524e-05, |
|
"loss": 0.0079, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 129.55, |
|
"learning_rate": 4.995436241610739e-05, |
|
"loss": 0.0113, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 131.82, |
|
"learning_rate": 4.941744966442954e-05, |
|
"loss": 0.0086, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 134.09, |
|
"learning_rate": 4.8880536912751685e-05, |
|
"loss": 0.0073, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 136.36, |
|
"learning_rate": 4.834362416107383e-05, |
|
"loss": 0.0081, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 136.36, |
|
"eval_las": 44.82369289560535, |
|
"eval_loss": 11.262748718261719, |
|
"eval_runtime": 4.4672, |
|
"eval_samples_per_second": 179.082, |
|
"eval_steps_per_second": 22.385, |
|
"eval_uas": 57.043599096751784, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 138.64, |
|
"learning_rate": 4.780671140939598e-05, |
|
"loss": 0.0073, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 140.91, |
|
"learning_rate": 4.726979865771813e-05, |
|
"loss": 0.0087, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 143.18, |
|
"learning_rate": 4.673288590604027e-05, |
|
"loss": 0.008, |
|
"step": 6300 |
|
}, |
|
{ |
|
"epoch": 145.45, |
|
"learning_rate": 4.619597315436242e-05, |
|
"loss": 0.0065, |
|
"step": 6400 |
|
}, |
|
{ |
|
"epoch": 147.73, |
|
"learning_rate": 4.565906040268457e-05, |
|
"loss": 0.0071, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 147.73, |
|
"eval_las": 44.40680910196283, |
|
"eval_loss": 11.929917335510254, |
|
"eval_runtime": 4.4685, |
|
"eval_samples_per_second": 179.032, |
|
"eval_steps_per_second": 22.379, |
|
"eval_uas": 56.053500086850796, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 150.0, |
|
"learning_rate": 4.5122147651006716e-05, |
|
"loss": 0.0068, |
|
"step": 6600 |
|
}, |
|
{ |
|
"epoch": 152.27, |
|
"learning_rate": 4.4585234899328864e-05, |
|
"loss": 0.0053, |
|
"step": 6700 |
|
}, |
|
{ |
|
"epoch": 154.55, |
|
"learning_rate": 4.404832214765101e-05, |
|
"loss": 0.006, |
|
"step": 6800 |
|
}, |
|
{ |
|
"epoch": 156.82, |
|
"learning_rate": 4.351140939597316e-05, |
|
"loss": 0.0047, |
|
"step": 6900 |
|
}, |
|
{ |
|
"epoch": 159.09, |
|
"learning_rate": 4.297449664429531e-05, |
|
"loss": 0.0062, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 159.09, |
|
"eval_las": 44.241792600312664, |
|
"eval_loss": 12.111156463623047, |
|
"eval_runtime": 4.4809, |
|
"eval_samples_per_second": 178.534, |
|
"eval_steps_per_second": 22.317, |
|
"eval_uas": 55.801632794858435, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 161.36, |
|
"learning_rate": 4.243758389261746e-05, |
|
"loss": 0.0059, |
|
"step": 7100 |
|
}, |
|
{ |
|
"epoch": 163.64, |
|
"learning_rate": 4.1900671140939605e-05, |
|
"loss": 0.0047, |
|
"step": 7200 |
|
}, |
|
{ |
|
"epoch": 165.91, |
|
"learning_rate": 4.1363758389261754e-05, |
|
"loss": 0.0055, |
|
"step": 7300 |
|
}, |
|
{ |
|
"epoch": 168.18, |
|
"learning_rate": 4.0826845637583895e-05, |
|
"loss": 0.0052, |
|
"step": 7400 |
|
}, |
|
{ |
|
"epoch": 170.45, |
|
"learning_rate": 4.028993288590604e-05, |
|
"loss": 0.0042, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 170.45, |
|
"eval_las": 44.441549418099704, |
|
"eval_loss": 12.920378684997559, |
|
"eval_runtime": 4.4707, |
|
"eval_samples_per_second": 178.943, |
|
"eval_steps_per_second": 22.368, |
|
"eval_uas": 56.1490359562272, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 172.73, |
|
"learning_rate": 3.975302013422819e-05, |
|
"loss": 0.0049, |
|
"step": 7600 |
|
}, |
|
{ |
|
"epoch": 175.0, |
|
"learning_rate": 3.921610738255034e-05, |
|
"loss": 0.0043, |
|
"step": 7700 |
|
}, |
|
{ |
|
"epoch": 177.27, |
|
"learning_rate": 3.867919463087249e-05, |
|
"loss": 0.0043, |
|
"step": 7800 |
|
}, |
|
{ |
|
"epoch": 179.55, |
|
"learning_rate": 3.8142281879194636e-05, |
|
"loss": 0.0057, |
|
"step": 7900 |
|
}, |
|
{ |
|
"epoch": 181.82, |
|
"learning_rate": 3.7605369127516784e-05, |
|
"loss": 0.0049, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 181.82, |
|
"eval_las": 44.78895257946847, |
|
"eval_loss": 12.573322296142578, |
|
"eval_runtime": 4.4578, |
|
"eval_samples_per_second": 179.462, |
|
"eval_steps_per_second": 22.433, |
|
"eval_uas": 56.61803022407504, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 184.09, |
|
"learning_rate": 3.706845637583893e-05, |
|
"loss": 0.0035, |
|
"step": 8100 |
|
}, |
|
{ |
|
"epoch": 186.36, |
|
"learning_rate": 3.653154362416108e-05, |
|
"loss": 0.0039, |
|
"step": 8200 |
|
}, |
|
{ |
|
"epoch": 188.64, |
|
"learning_rate": 3.599463087248322e-05, |
|
"loss": 0.006, |
|
"step": 8300 |
|
}, |
|
{ |
|
"epoch": 190.91, |
|
"learning_rate": 3.545771812080537e-05, |
|
"loss": 0.003, |
|
"step": 8400 |
|
}, |
|
{ |
|
"epoch": 193.18, |
|
"learning_rate": 3.492080536912752e-05, |
|
"loss": 0.0035, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 193.18, |
|
"eval_las": 44.98870939725552, |
|
"eval_loss": 13.518113136291504, |
|
"eval_runtime": 4.4808, |
|
"eval_samples_per_second": 178.539, |
|
"eval_steps_per_second": 22.317, |
|
"eval_uas": 56.86989751606739, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 195.45, |
|
"learning_rate": 3.438389261744967e-05, |
|
"loss": 0.0048, |
|
"step": 8600 |
|
}, |
|
{ |
|
"epoch": 197.73, |
|
"learning_rate": 3.3846979865771815e-05, |
|
"loss": 0.0038, |
|
"step": 8700 |
|
}, |
|
{ |
|
"epoch": 200.0, |
|
"learning_rate": 3.3310067114093964e-05, |
|
"loss": 0.004, |
|
"step": 8800 |
|
}, |
|
{ |
|
"epoch": 202.27, |
|
"learning_rate": 3.277315436241611e-05, |
|
"loss": 0.0026, |
|
"step": 8900 |
|
}, |
|
{ |
|
"epoch": 204.55, |
|
"learning_rate": 3.223624161073826e-05, |
|
"loss": 0.0024, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 204.55, |
|
"eval_las": 45.10161542470036, |
|
"eval_loss": 12.888202667236328, |
|
"eval_runtime": 4.4741, |
|
"eval_samples_per_second": 178.806, |
|
"eval_steps_per_second": 22.351, |
|
"eval_uas": 56.97411846447803, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 206.82, |
|
"learning_rate": 3.169932885906041e-05, |
|
"loss": 0.0029, |
|
"step": 9100 |
|
}, |
|
{ |
|
"epoch": 209.09, |
|
"learning_rate": 3.1162416107382557e-05, |
|
"loss": 0.0024, |
|
"step": 9200 |
|
}, |
|
{ |
|
"epoch": 211.36, |
|
"learning_rate": 3.0625503355704705e-05, |
|
"loss": 0.0022, |
|
"step": 9300 |
|
}, |
|
{ |
|
"epoch": 213.64, |
|
"learning_rate": 3.0088590604026846e-05, |
|
"loss": 0.0034, |
|
"step": 9400 |
|
}, |
|
{ |
|
"epoch": 215.91, |
|
"learning_rate": 2.9551677852348995e-05, |
|
"loss": 0.0016, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 215.91, |
|
"eval_las": 44.84106305367379, |
|
"eval_loss": 13.813431739807129, |
|
"eval_runtime": 4.4596, |
|
"eval_samples_per_second": 179.39, |
|
"eval_steps_per_second": 22.424, |
|
"eval_uas": 56.27931214174049, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 218.18, |
|
"learning_rate": 2.9014765100671143e-05, |
|
"loss": 0.0025, |
|
"step": 9600 |
|
}, |
|
{ |
|
"epoch": 220.45, |
|
"learning_rate": 2.847785234899329e-05, |
|
"loss": 0.0025, |
|
"step": 9700 |
|
}, |
|
{ |
|
"epoch": 222.73, |
|
"learning_rate": 2.794093959731544e-05, |
|
"loss": 0.0025, |
|
"step": 9800 |
|
}, |
|
{ |
|
"epoch": 225.0, |
|
"learning_rate": 2.7404026845637588e-05, |
|
"loss": 0.0026, |
|
"step": 9900 |
|
}, |
|
{ |
|
"epoch": 227.27, |
|
"learning_rate": 2.6867114093959732e-05, |
|
"loss": 0.0019, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 227.27, |
|
"eval_las": 44.76289734236582, |
|
"eval_loss": 13.865011215209961, |
|
"eval_runtime": 4.4812, |
|
"eval_samples_per_second": 178.524, |
|
"eval_steps_per_second": 22.316, |
|
"eval_uas": 56.244571825603614, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 229.55, |
|
"learning_rate": 2.633020134228188e-05, |
|
"loss": 0.0025, |
|
"step": 10100 |
|
}, |
|
{ |
|
"epoch": 231.82, |
|
"learning_rate": 2.579328859060403e-05, |
|
"loss": 0.0028, |
|
"step": 10200 |
|
}, |
|
{ |
|
"epoch": 234.09, |
|
"learning_rate": 2.5256375838926177e-05, |
|
"loss": 0.0028, |
|
"step": 10300 |
|
}, |
|
{ |
|
"epoch": 236.36, |
|
"learning_rate": 2.4719463087248325e-05, |
|
"loss": 0.0024, |
|
"step": 10400 |
|
}, |
|
{ |
|
"epoch": 238.64, |
|
"learning_rate": 2.4182550335570474e-05, |
|
"loss": 0.0051, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 238.64, |
|
"eval_las": 45.01476463435817, |
|
"eval_loss": 13.106086730957031, |
|
"eval_runtime": 4.468, |
|
"eval_samples_per_second": 179.051, |
|
"eval_steps_per_second": 22.381, |
|
"eval_uas": 56.60934514504083, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 240.91, |
|
"learning_rate": 2.364563758389262e-05, |
|
"loss": 0.0026, |
|
"step": 10600 |
|
}, |
|
{ |
|
"epoch": 243.18, |
|
"learning_rate": 2.3108724832214767e-05, |
|
"loss": 0.0036, |
|
"step": 10700 |
|
}, |
|
{ |
|
"epoch": 245.45, |
|
"learning_rate": 2.2571812080536915e-05, |
|
"loss": 0.0012, |
|
"step": 10800 |
|
}, |
|
{ |
|
"epoch": 247.73, |
|
"learning_rate": 2.2034899328859063e-05, |
|
"loss": 0.0016, |
|
"step": 10900 |
|
}, |
|
{ |
|
"epoch": 250.0, |
|
"learning_rate": 2.149798657718121e-05, |
|
"loss": 0.0016, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 250.0, |
|
"eval_las": 45.422963348966476, |
|
"eval_loss": 13.54307746887207, |
|
"eval_runtime": 4.4615, |
|
"eval_samples_per_second": 179.31, |
|
"eval_steps_per_second": 22.414, |
|
"eval_uas": 57.11307972902553, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 252.27, |
|
"learning_rate": 2.0961073825503356e-05, |
|
"loss": 0.0014, |
|
"step": 11100 |
|
}, |
|
{ |
|
"epoch": 254.55, |
|
"learning_rate": 2.0424161073825505e-05, |
|
"loss": 0.0016, |
|
"step": 11200 |
|
}, |
|
{ |
|
"epoch": 256.82, |
|
"learning_rate": 1.9887248322147653e-05, |
|
"loss": 0.0011, |
|
"step": 11300 |
|
}, |
|
{ |
|
"epoch": 259.09, |
|
"learning_rate": 1.93503355704698e-05, |
|
"loss": 0.0012, |
|
"step": 11400 |
|
}, |
|
{ |
|
"epoch": 261.36, |
|
"learning_rate": 1.881342281879195e-05, |
|
"loss": 0.0013, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 261.36, |
|
"eval_las": 46.083029355567135, |
|
"eval_loss": 13.587315559387207, |
|
"eval_runtime": 4.4668, |
|
"eval_samples_per_second": 179.098, |
|
"eval_steps_per_second": 22.387, |
|
"eval_uas": 57.747090498523534, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 263.64, |
|
"learning_rate": 1.8276510067114094e-05, |
|
"loss": 0.001, |
|
"step": 11600 |
|
}, |
|
{ |
|
"epoch": 265.91, |
|
"learning_rate": 1.7739597315436242e-05, |
|
"loss": 0.0012, |
|
"step": 11700 |
|
}, |
|
{ |
|
"epoch": 268.18, |
|
"learning_rate": 1.720268456375839e-05, |
|
"loss": 0.0013, |
|
"step": 11800 |
|
}, |
|
{ |
|
"epoch": 270.45, |
|
"learning_rate": 1.666577181208054e-05, |
|
"loss": 0.0011, |
|
"step": 11900 |
|
}, |
|
{ |
|
"epoch": 272.73, |
|
"learning_rate": 1.6128859060402687e-05, |
|
"loss": 0.0006, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 272.73, |
|
"eval_las": 45.84853222164322, |
|
"eval_loss": 13.865344047546387, |
|
"eval_runtime": 4.4568, |
|
"eval_samples_per_second": 179.499, |
|
"eval_steps_per_second": 22.437, |
|
"eval_uas": 57.712350182386665, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 275.0, |
|
"learning_rate": 1.5591946308724832e-05, |
|
"loss": 0.0006, |
|
"step": 12100 |
|
}, |
|
{ |
|
"epoch": 277.27, |
|
"learning_rate": 1.505503355704698e-05, |
|
"loss": 0.0008, |
|
"step": 12200 |
|
}, |
|
{ |
|
"epoch": 279.55, |
|
"learning_rate": 1.4518120805369128e-05, |
|
"loss": 0.0006, |
|
"step": 12300 |
|
}, |
|
{ |
|
"epoch": 281.82, |
|
"learning_rate": 1.3981208053691275e-05, |
|
"loss": 0.001, |
|
"step": 12400 |
|
}, |
|
{ |
|
"epoch": 284.09, |
|
"learning_rate": 1.3444295302013423e-05, |
|
"loss": 0.0007, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 284.09, |
|
"eval_las": 46.03091888136182, |
|
"eval_loss": 14.340444564819336, |
|
"eval_runtime": 4.4804, |
|
"eval_samples_per_second": 178.557, |
|
"eval_steps_per_second": 22.32, |
|
"eval_uas": 57.86868160500261, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 286.36, |
|
"learning_rate": 1.2907382550335571e-05, |
|
"loss": 0.001, |
|
"step": 12600 |
|
}, |
|
{ |
|
"epoch": 288.64, |
|
"learning_rate": 1.2370469798657718e-05, |
|
"loss": 0.0012, |
|
"step": 12700 |
|
}, |
|
{ |
|
"epoch": 290.91, |
|
"learning_rate": 1.1833557046979866e-05, |
|
"loss": 0.0005, |
|
"step": 12800 |
|
}, |
|
{ |
|
"epoch": 293.18, |
|
"learning_rate": 1.1296644295302015e-05, |
|
"loss": 0.0013, |
|
"step": 12900 |
|
}, |
|
{ |
|
"epoch": 295.45, |
|
"learning_rate": 1.0759731543624161e-05, |
|
"loss": 0.0006, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 295.45, |
|
"eval_las": 45.839847142608996, |
|
"eval_loss": 14.318921089172363, |
|
"eval_runtime": 4.4595, |
|
"eval_samples_per_second": 179.394, |
|
"eval_steps_per_second": 22.424, |
|
"eval_uas": 57.573388917839154, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 297.73, |
|
"learning_rate": 1.022281879194631e-05, |
|
"loss": 0.0006, |
|
"step": 13100 |
|
}, |
|
{ |
|
"epoch": 300.0, |
|
"learning_rate": 9.685906040268458e-06, |
|
"loss": 0.0006, |
|
"step": 13200 |
|
}, |
|
{ |
|
"epoch": 302.27, |
|
"learning_rate": 9.148993288590606e-06, |
|
"loss": 0.0009, |
|
"step": 13300 |
|
}, |
|
{ |
|
"epoch": 304.55, |
|
"learning_rate": 8.612080536912752e-06, |
|
"loss": 0.0006, |
|
"step": 13400 |
|
}, |
|
{ |
|
"epoch": 306.82, |
|
"learning_rate": 8.0751677852349e-06, |
|
"loss": 0.0005, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 306.82, |
|
"eval_las": 46.10908459266979, |
|
"eval_loss": 14.561714172363281, |
|
"eval_runtime": 4.4788, |
|
"eval_samples_per_second": 178.621, |
|
"eval_steps_per_second": 22.328, |
|
"eval_uas": 57.886051763071045, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 309.09, |
|
"learning_rate": 7.538255033557048e-06, |
|
"loss": 0.0006, |
|
"step": 13600 |
|
}, |
|
{ |
|
"epoch": 311.36, |
|
"learning_rate": 7.001342281879195e-06, |
|
"loss": 0.0003, |
|
"step": 13700 |
|
}, |
|
{ |
|
"epoch": 313.64, |
|
"learning_rate": 6.464429530201343e-06, |
|
"loss": 0.001, |
|
"step": 13800 |
|
}, |
|
{ |
|
"epoch": 315.91, |
|
"learning_rate": 5.92751677852349e-06, |
|
"loss": 0.0004, |
|
"step": 13900 |
|
}, |
|
{ |
|
"epoch": 318.18, |
|
"learning_rate": 5.390604026845638e-06, |
|
"loss": 0.0004, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 318.18, |
|
"eval_las": 46.195935383011985, |
|
"eval_loss": 14.694328308105469, |
|
"eval_runtime": 4.465, |
|
"eval_samples_per_second": 179.169, |
|
"eval_steps_per_second": 22.396, |
|
"eval_uas": 57.87736668403682, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 320.45, |
|
"learning_rate": 4.853691275167786e-06, |
|
"loss": 0.0003, |
|
"step": 14100 |
|
}, |
|
{ |
|
"epoch": 322.73, |
|
"learning_rate": 4.316778523489933e-06, |
|
"loss": 0.0005, |
|
"step": 14200 |
|
}, |
|
{ |
|
"epoch": 325.0, |
|
"learning_rate": 3.7798657718120806e-06, |
|
"loss": 0.0004, |
|
"step": 14300 |
|
}, |
|
{ |
|
"epoch": 327.27, |
|
"learning_rate": 3.2429530201342284e-06, |
|
"loss": 0.0004, |
|
"step": 14400 |
|
}, |
|
{ |
|
"epoch": 329.55, |
|
"learning_rate": 2.706040268456376e-06, |
|
"loss": 0.0003, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 329.55, |
|
"eval_las": 46.239360778183084, |
|
"eval_loss": 14.942312240600586, |
|
"eval_runtime": 4.4784, |
|
"eval_samples_per_second": 178.634, |
|
"eval_steps_per_second": 22.329, |
|
"eval_uas": 57.89473684210527, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 331.82, |
|
"learning_rate": 2.174496644295302e-06, |
|
"loss": 0.0004, |
|
"step": 14600 |
|
}, |
|
{ |
|
"epoch": 334.09, |
|
"learning_rate": 1.6375838926174498e-06, |
|
"loss": 0.0003, |
|
"step": 14700 |
|
}, |
|
{ |
|
"epoch": 336.36, |
|
"learning_rate": 1.1006711409395974e-06, |
|
"loss": 0.0003, |
|
"step": 14800 |
|
}, |
|
{ |
|
"epoch": 338.64, |
|
"learning_rate": 5.63758389261745e-07, |
|
"loss": 0.0006, |
|
"step": 14900 |
|
}, |
|
{ |
|
"epoch": 340.91, |
|
"learning_rate": 2.6845637583892618e-08, |
|
"loss": 0.0003, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 340.91, |
|
"eval_las": 46.35226680562793, |
|
"eval_loss": 14.943622589111328, |
|
"eval_runtime": 4.4704, |
|
"eval_samples_per_second": 178.956, |
|
"eval_steps_per_second": 22.369, |
|
"eval_uas": 57.98158763244745, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 340.91, |
|
"step": 15000, |
|
"total_flos": 9.527918213185536e+16, |
|
"train_loss": 0.0714812466767927, |
|
"train_runtime": 6138.5721, |
|
"train_samples_per_second": 78.194, |
|
"train_steps_per_second": 2.444 |
|
} |
|
], |
|
"max_steps": 15000, |
|
"num_train_epochs": 341, |
|
"total_flos": 9.527918213185536e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|