| { | |
| "best_metric": 73.27647476901208, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/bert-base-finetuned-parsing-ud-Chinese-GSD/checkpoint-14000", | |
| "epoch": 120.0, | |
| "global_step": 15000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 4.5737, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 7.948456375838927e-05, | |
| "loss": 2.1245, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.894765100671142e-05, | |
| "loss": 1.597, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.841073825503357e-05, | |
| "loss": 1.3112, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.78738255033557e-05, | |
| "loss": 1.101, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_las": 64.06064913527601, | |
| "eval_loss": 1.3798493146896362, | |
| "eval_runtime": 3.307, | |
| "eval_samples_per_second": 151.193, | |
| "eval_steps_per_second": 19.05, | |
| "eval_uas": 69.56487404248598, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 7.733691275167786e-05, | |
| "loss": 0.8747, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 0.7512, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.626308724832216e-05, | |
| "loss": 0.6672, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 7.57261744966443e-05, | |
| "loss": 0.5748, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 7.518926174496645e-05, | |
| "loss": 0.5202, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_las": 68.13551291163232, | |
| "eval_loss": 1.5277836322784424, | |
| "eval_runtime": 3.3863, | |
| "eval_samples_per_second": 147.653, | |
| "eval_steps_per_second": 18.604, | |
| "eval_uas": 73.33965095159125, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 7.46523489932886e-05, | |
| "loss": 0.4395, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.411543624161075e-05, | |
| "loss": 0.3923, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 7.35785234899329e-05, | |
| "loss": 0.3607, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 7.304161073825505e-05, | |
| "loss": 0.3235, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 7.25046979865772e-05, | |
| "loss": 0.3021, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_las": 69.40693358603806, | |
| "eval_loss": 1.897964596748352, | |
| "eval_runtime": 3.2504, | |
| "eval_samples_per_second": 153.829, | |
| "eval_steps_per_second": 19.382, | |
| "eval_uas": 74.69793887704336, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 7.196778523489934e-05, | |
| "loss": 0.2557, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 7.143087248322148e-05, | |
| "loss": 0.2355, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 7.089395973154363e-05, | |
| "loss": 0.2258, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 7.035704697986578e-05, | |
| "loss": 0.2039, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 6.982013422818792e-05, | |
| "loss": 0.1922, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_las": 70.1334596856985, | |
| "eval_loss": 2.0691661834716797, | |
| "eval_runtime": 3.237, | |
| "eval_samples_per_second": 154.463, | |
| "eval_steps_per_second": 19.462, | |
| "eval_uas": 75.53502329621733, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 6.928322147651007e-05, | |
| "loss": 0.1741, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 6.874630872483222e-05, | |
| "loss": 0.1636, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 6.820939597315437e-05, | |
| "loss": 0.1527, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 6.767248322147652e-05, | |
| "loss": 0.1474, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.713557046979866e-05, | |
| "loss": 0.138, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_las": 70.16504777698808, | |
| "eval_loss": 2.318901777267456, | |
| "eval_runtime": 3.2483, | |
| "eval_samples_per_second": 153.926, | |
| "eval_steps_per_second": 19.395, | |
| "eval_uas": 75.54292031903972, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 6.659865771812081e-05, | |
| "loss": 0.1252, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 6.606174496644296e-05, | |
| "loss": 0.1177, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 6.55248322147651e-05, | |
| "loss": 0.1131, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 6.498791946308724e-05, | |
| "loss": 0.108, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 6.445100671140939e-05, | |
| "loss": 0.1055, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_las": 70.98633815051726, | |
| "eval_loss": 2.5012738704681396, | |
| "eval_runtime": 3.232, | |
| "eval_samples_per_second": 154.704, | |
| "eval_steps_per_second": 19.493, | |
| "eval_uas": 75.92987443733712, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 6.391409395973154e-05, | |
| "loss": 0.096, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 6.337718120805369e-05, | |
| "loss": 0.0935, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 6.284026845637584e-05, | |
| "loss": 0.0857, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 6.230335570469799e-05, | |
| "loss": 0.0838, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 6.176644295302013e-05, | |
| "loss": 0.0798, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_las": 71.54702677090737, | |
| "eval_loss": 2.6194210052490234, | |
| "eval_runtime": 3.2513, | |
| "eval_samples_per_second": 153.784, | |
| "eval_steps_per_second": 19.377, | |
| "eval_uas": 76.27734344152255, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 6.122953020134228e-05, | |
| "loss": 0.0756, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 6.069261744966444e-05, | |
| "loss": 0.0724, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 6.0155704697986585e-05, | |
| "loss": 0.0708, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 31.2, | |
| "learning_rate": 5.9618791946308734e-05, | |
| "loss": 0.0682, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 5.9081879194630875e-05, | |
| "loss": 0.0646, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_las": 70.67835426044381, | |
| "eval_loss": 2.809868097305298, | |
| "eval_runtime": 3.2209, | |
| "eval_samples_per_second": 155.237, | |
| "eval_steps_per_second": 19.56, | |
| "eval_uas": 75.81141909500118, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 32.8, | |
| "learning_rate": 5.854496644295302e-05, | |
| "loss": 0.0627, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "learning_rate": 5.800805369127517e-05, | |
| "loss": 0.0612, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "learning_rate": 5.747114093959732e-05, | |
| "loss": 0.0569, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "learning_rate": 5.693422818791947e-05, | |
| "loss": 0.0568, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 5.6397315436241616e-05, | |
| "loss": 0.0535, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_las": 71.18376372107716, | |
| "eval_loss": 2.8807671070098877, | |
| "eval_runtime": 3.2489, | |
| "eval_samples_per_second": 153.901, | |
| "eval_steps_per_second": 19.391, | |
| "eval_uas": 76.31682855563453, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 5.5860402684563764e-05, | |
| "loss": 0.0503, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 37.6, | |
| "learning_rate": 5.532348993288591e-05, | |
| "loss": 0.0484, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "learning_rate": 5.478657718120806e-05, | |
| "loss": 0.0462, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "learning_rate": 5.424966442953021e-05, | |
| "loss": 0.045, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 5.371275167785236e-05, | |
| "loss": 0.0465, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_las": 71.76024638711206, | |
| "eval_loss": 3.0303280353546143, | |
| "eval_runtime": 3.2476, | |
| "eval_samples_per_second": 153.959, | |
| "eval_steps_per_second": 19.399, | |
| "eval_uas": 76.87751717602464, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 40.8, | |
| "learning_rate": 5.31758389261745e-05, | |
| "loss": 0.0424, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "learning_rate": 5.263892617449665e-05, | |
| "loss": 0.0411, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 42.4, | |
| "learning_rate": 5.2102013422818795e-05, | |
| "loss": 0.0397, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "learning_rate": 5.1565100671140944e-05, | |
| "loss": 0.0391, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 5.102818791946309e-05, | |
| "loss": 0.0368, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_las": 71.96556898049435, | |
| "eval_loss": 3.1702797412872314, | |
| "eval_runtime": 3.2488, | |
| "eval_samples_per_second": 153.903, | |
| "eval_steps_per_second": 19.392, | |
| "eval_uas": 77.01176656400537, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "learning_rate": 5.049127516778524e-05, | |
| "loss": 0.0368, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "learning_rate": 4.995436241610739e-05, | |
| "loss": 0.0353, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "learning_rate": 4.941744966442954e-05, | |
| "loss": 0.0348, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 47.2, | |
| "learning_rate": 4.8880536912751685e-05, | |
| "loss": 0.0346, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 4.834362416107383e-05, | |
| "loss": 0.0313, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_las": 71.61809997630894, | |
| "eval_loss": 3.2243900299072266, | |
| "eval_runtime": 3.2269, | |
| "eval_samples_per_second": 154.949, | |
| "eval_steps_per_second": 19.524, | |
| "eval_uas": 76.7669588565111, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 48.8, | |
| "learning_rate": 4.780671140939598e-05, | |
| "loss": 0.0297, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 4.726979865771813e-05, | |
| "loss": 0.032, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 50.4, | |
| "learning_rate": 4.673288590604027e-05, | |
| "loss": 0.0302, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "learning_rate": 4.619597315436242e-05, | |
| "loss": 0.0301, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 4.565906040268457e-05, | |
| "loss": 0.0296, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_las": 71.74445234146727, | |
| "eval_loss": 3.1685025691986084, | |
| "eval_runtime": 3.2336, | |
| "eval_samples_per_second": 154.625, | |
| "eval_steps_per_second": 19.483, | |
| "eval_uas": 76.71957671957672, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "learning_rate": 4.5122147651006716e-05, | |
| "loss": 0.0272, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 53.6, | |
| "learning_rate": 4.4585234899328864e-05, | |
| "loss": 0.0275, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "learning_rate": 4.404832214765101e-05, | |
| "loss": 0.0269, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 55.2, | |
| "learning_rate": 4.351140939597316e-05, | |
| "loss": 0.026, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 4.297449664429531e-05, | |
| "loss": 0.0262, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_las": 72.02084814025113, | |
| "eval_loss": 3.4257876873016357, | |
| "eval_runtime": 3.2313, | |
| "eval_samples_per_second": 154.737, | |
| "eval_steps_per_second": 19.497, | |
| "eval_uas": 77.12232488351891, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 4.243758389261746e-05, | |
| "loss": 0.0221, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "learning_rate": 4.1900671140939605e-05, | |
| "loss": 0.021, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 58.4, | |
| "learning_rate": 4.1363758389261754e-05, | |
| "loss": 0.0215, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "learning_rate": 4.0826845637583895e-05, | |
| "loss": 0.0226, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.028993288590604e-05, | |
| "loss": 0.0233, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_las": 71.80762852404644, | |
| "eval_loss": 3.463973045349121, | |
| "eval_runtime": 3.2516, | |
| "eval_samples_per_second": 153.771, | |
| "eval_steps_per_second": 19.375, | |
| "eval_uas": 76.79854694780069, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "learning_rate": 3.975302013422819e-05, | |
| "loss": 0.0213, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 61.6, | |
| "learning_rate": 3.921610738255034e-05, | |
| "loss": 0.02, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "learning_rate": 3.867919463087249e-05, | |
| "loss": 0.0204, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 63.2, | |
| "learning_rate": 3.8142281879194636e-05, | |
| "loss": 0.0197, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 3.7605369127516784e-05, | |
| "loss": 0.0193, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_las": 71.878701729448, | |
| "eval_loss": 3.574808120727539, | |
| "eval_runtime": 3.2387, | |
| "eval_samples_per_second": 154.383, | |
| "eval_steps_per_second": 19.452, | |
| "eval_uas": 77.03545763247256, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 64.8, | |
| "learning_rate": 3.706845637583893e-05, | |
| "loss": 0.0174, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "learning_rate": 3.653154362416108e-05, | |
| "loss": 0.0183, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 66.4, | |
| "learning_rate": 3.599463087248322e-05, | |
| "loss": 0.0193, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "learning_rate": 3.545771812080537e-05, | |
| "loss": 0.017, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "learning_rate": 3.492080536912752e-05, | |
| "loss": 0.0161, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_las": 71.98136302613915, | |
| "eval_loss": 3.7389907836914062, | |
| "eval_runtime": 3.2198, | |
| "eval_samples_per_second": 155.288, | |
| "eval_steps_per_second": 19.566, | |
| "eval_uas": 76.91700229013662, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "learning_rate": 3.438389261744967e-05, | |
| "loss": 0.0165, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 69.6, | |
| "learning_rate": 3.3846979865771815e-05, | |
| "loss": 0.0157, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "learning_rate": 3.3310067114093964e-05, | |
| "loss": 0.014, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 71.2, | |
| "learning_rate": 3.277315436241611e-05, | |
| "loss": 0.0144, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 3.223624161073826e-05, | |
| "loss": 0.0149, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_las": 72.36831714443655, | |
| "eval_loss": 3.806819438934326, | |
| "eval_runtime": 3.2367, | |
| "eval_samples_per_second": 154.477, | |
| "eval_steps_per_second": 19.464, | |
| "eval_uas": 77.35133854536839, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 72.8, | |
| "learning_rate": 3.169932885906041e-05, | |
| "loss": 0.0159, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "learning_rate": 3.1162416107382557e-05, | |
| "loss": 0.0126, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 74.4, | |
| "learning_rate": 3.0625503355704705e-05, | |
| "loss": 0.0128, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 75.2, | |
| "learning_rate": 3.0088590604026846e-05, | |
| "loss": 0.0143, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "learning_rate": 2.9551677852348995e-05, | |
| "loss": 0.0121, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_las": 72.39990523572614, | |
| "eval_loss": 3.9205520153045654, | |
| "eval_runtime": 3.2187, | |
| "eval_samples_per_second": 155.341, | |
| "eval_steps_per_second": 19.573, | |
| "eval_uas": 77.27236831714444, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 2.9014765100671143e-05, | |
| "loss": 0.012, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 77.6, | |
| "learning_rate": 2.847785234899329e-05, | |
| "loss": 0.0124, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 78.4, | |
| "learning_rate": 2.794093959731544e-05, | |
| "loss": 0.0109, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 79.2, | |
| "learning_rate": 2.7404026845637588e-05, | |
| "loss": 0.0112, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.6867114093959732e-05, | |
| "loss": 0.0113, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_las": 72.17878859669904, | |
| "eval_loss": 3.9717860221862793, | |
| "eval_runtime": 3.2195, | |
| "eval_samples_per_second": 155.302, | |
| "eval_steps_per_second": 19.568, | |
| "eval_uas": 77.15391297480849, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 80.8, | |
| "learning_rate": 2.633020134228188e-05, | |
| "loss": 0.0118, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 81.6, | |
| "learning_rate": 2.579328859060403e-05, | |
| "loss": 0.0102, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 82.4, | |
| "learning_rate": 2.5256375838926177e-05, | |
| "loss": 0.0112, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 83.2, | |
| "learning_rate": 2.4719463087248325e-05, | |
| "loss": 0.0109, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "learning_rate": 2.4182550335570474e-05, | |
| "loss": 0.0086, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_las": 72.4709784411277, | |
| "eval_loss": 4.107804775238037, | |
| "eval_runtime": 3.2109, | |
| "eval_samples_per_second": 155.72, | |
| "eval_steps_per_second": 19.621, | |
| "eval_uas": 77.41451472794756, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 84.8, | |
| "learning_rate": 2.364563758389262e-05, | |
| "loss": 0.0094, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 85.6, | |
| "learning_rate": 2.3108724832214767e-05, | |
| "loss": 0.009, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 86.4, | |
| "learning_rate": 2.2571812080536915e-05, | |
| "loss": 0.0078, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 87.2, | |
| "learning_rate": 2.2034899328859063e-05, | |
| "loss": 0.0082, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 2.149798657718121e-05, | |
| "loss": 0.0091, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_las": 72.34462607596936, | |
| "eval_loss": 4.17307710647583, | |
| "eval_runtime": 3.2189, | |
| "eval_samples_per_second": 155.332, | |
| "eval_steps_per_second": 19.572, | |
| "eval_uas": 77.18550106609808, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 88.8, | |
| "learning_rate": 2.0961073825503356e-05, | |
| "loss": 0.008, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 89.6, | |
| "learning_rate": 2.0424161073825505e-05, | |
| "loss": 0.0079, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 90.4, | |
| "learning_rate": 1.9887248322147653e-05, | |
| "loss": 0.0073, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 91.2, | |
| "learning_rate": 1.93503355704698e-05, | |
| "loss": 0.0075, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "learning_rate": 1.881342281879195e-05, | |
| "loss": 0.0072, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_las": 72.58153676064124, | |
| "eval_loss": 4.29336404800415, | |
| "eval_runtime": 3.2461, | |
| "eval_samples_per_second": 154.032, | |
| "eval_steps_per_second": 19.408, | |
| "eval_uas": 77.58824923004028, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 92.8, | |
| "learning_rate": 1.8276510067114094e-05, | |
| "loss": 0.0066, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 93.6, | |
| "learning_rate": 1.7739597315436242e-05, | |
| "loss": 0.0065, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 94.4, | |
| "learning_rate": 1.720268456375839e-05, | |
| "loss": 0.0068, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 95.2, | |
| "learning_rate": 1.666577181208054e-05, | |
| "loss": 0.0063, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "learning_rate": 1.6128859060402687e-05, | |
| "loss": 0.0058, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_las": 72.78685935402353, | |
| "eval_loss": 4.2894287109375, | |
| "eval_runtime": 3.1913, | |
| "eval_samples_per_second": 156.677, | |
| "eval_steps_per_second": 19.741, | |
| "eval_uas": 77.70670457237621, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 96.8, | |
| "learning_rate": 1.5591946308724832e-05, | |
| "loss": 0.0053, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 97.6, | |
| "learning_rate": 1.505503355704698e-05, | |
| "loss": 0.0058, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 98.4, | |
| "learning_rate": 1.4518120805369128e-05, | |
| "loss": 0.0055, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 99.2, | |
| "learning_rate": 1.3981208053691275e-05, | |
| "loss": 0.0061, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.3444295302013423e-05, | |
| "loss": 0.0058, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_las": 72.82634446813552, | |
| "eval_loss": 4.251532554626465, | |
| "eval_runtime": 3.1899, | |
| "eval_samples_per_second": 156.746, | |
| "eval_steps_per_second": 19.75, | |
| "eval_uas": 77.7461896864882, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 100.8, | |
| "learning_rate": 1.2912751677852352e-05, | |
| "loss": 0.0048, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 101.6, | |
| "learning_rate": 1.2375838926174497e-05, | |
| "loss": 0.0044, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 102.4, | |
| "learning_rate": 1.1838926174496645e-05, | |
| "loss": 0.0054, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 103.2, | |
| "learning_rate": 1.1302013422818795e-05, | |
| "loss": 0.0048, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "learning_rate": 1.076510067114094e-05, | |
| "loss": 0.0052, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_las": 72.66050698886521, | |
| "eval_loss": 4.392012596130371, | |
| "eval_runtime": 3.19, | |
| "eval_samples_per_second": 156.741, | |
| "eval_steps_per_second": 19.749, | |
| "eval_uas": 77.46979388770433, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 104.8, | |
| "learning_rate": 1.0228187919463088e-05, | |
| "loss": 0.005, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 105.6, | |
| "learning_rate": 9.691275167785236e-06, | |
| "loss": 0.0043, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 106.4, | |
| "learning_rate": 9.154362416107383e-06, | |
| "loss": 0.0039, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 107.2, | |
| "learning_rate": 8.617449664429531e-06, | |
| "loss": 0.0035, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "learning_rate": 8.085906040268458e-06, | |
| "loss": 0.0046, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_las": 72.97638790176103, | |
| "eval_loss": 4.4607110023498535, | |
| "eval_runtime": 3.1889, | |
| "eval_samples_per_second": 156.795, | |
| "eval_steps_per_second": 19.756, | |
| "eval_uas": 77.83305693753455, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 108.8, | |
| "learning_rate": 7.548993288590605e-06, | |
| "loss": 0.0038, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 109.6, | |
| "learning_rate": 7.012080536912752e-06, | |
| "loss": 0.0039, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 110.4, | |
| "learning_rate": 6.475167785234899e-06, | |
| "loss": 0.0034, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 111.2, | |
| "learning_rate": 5.938255033557048e-06, | |
| "loss": 0.0034, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "learning_rate": 5.401342281879195e-06, | |
| "loss": 0.003, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_las": 73.27647476901208, | |
| "eval_loss": 4.440804481506348, | |
| "eval_runtime": 3.1908, | |
| "eval_samples_per_second": 156.703, | |
| "eval_steps_per_second": 19.745, | |
| "eval_uas": 77.99889441680486, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 112.8, | |
| "learning_rate": 4.864429530201343e-06, | |
| "loss": 0.0035, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 113.6, | |
| "learning_rate": 4.32751677852349e-06, | |
| "loss": 0.0031, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 114.4, | |
| "learning_rate": 3.790604026845638e-06, | |
| "loss": 0.0029, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 115.2, | |
| "learning_rate": 3.253691275167786e-06, | |
| "loss": 0.0035, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "learning_rate": 2.716778523489933e-06, | |
| "loss": 0.0027, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_las": 73.2448866777225, | |
| "eval_loss": 4.51676607131958, | |
| "eval_runtime": 3.1897, | |
| "eval_samples_per_second": 156.756, | |
| "eval_steps_per_second": 19.751, | |
| "eval_uas": 77.91202716575852, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 116.8, | |
| "learning_rate": 2.1798657718120807e-06, | |
| "loss": 0.0026, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 117.6, | |
| "learning_rate": 1.6429530201342283e-06, | |
| "loss": 0.0028, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 118.4, | |
| "learning_rate": 1.1060402684563759e-06, | |
| "loss": 0.003, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 119.2, | |
| "learning_rate": 5.691275167785235e-07, | |
| "loss": 0.0035, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 3.2214765100671145e-08, | |
| "loss": 0.0032, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_las": 73.11853431256417, | |
| "eval_loss": 4.538000583648682, | |
| "eval_runtime": 3.1945, | |
| "eval_samples_per_second": 156.52, | |
| "eval_steps_per_second": 19.721, | |
| "eval_uas": 77.84095396035694, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "step": 15000, | |
| "total_flos": 9.575030782291968e+16, | |
| "train_loss": 0.140908819069465, | |
| "train_runtime": 6658.0803, | |
| "train_samples_per_second": 72.093, | |
| "train_steps_per_second": 2.253 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 120, | |
| "total_flos": 9.575030782291968e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |