| { | |
| "best_metric": 69.00867976244861, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/bert-base-finetuned-parsing-ud-Coptic-Scriptorium/checkpoint-9000", | |
| "epoch": 294.87179487179486, | |
| "global_step": 11500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 4.7843, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 7.948456375838927e-05, | |
| "loss": 2.0692, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 7.894765100671142e-05, | |
| "loss": 1.2357, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 7.841073825503357e-05, | |
| "loss": 0.8102, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 7.78738255033557e-05, | |
| "loss": 0.5577, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "eval_las": 61.26998629511192, | |
| "eval_loss": 2.625490188598633, | |
| "eval_runtime": 2.5145, | |
| "eval_samples_per_second": 151.518, | |
| "eval_steps_per_second": 19.089, | |
| "eval_uas": 69.51119232526267, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 7.733691275167786e-05, | |
| "loss": 0.4067, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 7.680000000000001e-05, | |
| "loss": 0.31, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 7.626308724832216e-05, | |
| "loss": 0.2329, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 7.57261744966443e-05, | |
| "loss": 0.2022, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 7.518926174496645e-05, | |
| "loss": 0.1537, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "eval_las": 64.12060301507537, | |
| "eval_loss": 3.8098294734954834, | |
| "eval_runtime": 2.5064, | |
| "eval_samples_per_second": 152.01, | |
| "eval_steps_per_second": 19.151, | |
| "eval_uas": 72.4988579259936, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 7.46523489932886e-05, | |
| "loss": 0.1318, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 7.411543624161075e-05, | |
| "loss": 0.1154, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 7.35785234899329e-05, | |
| "loss": 0.0959, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 7.304161073825505e-05, | |
| "loss": 0.09, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 7.25046979865772e-05, | |
| "loss": 0.08, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "eval_las": 65.40886249428964, | |
| "eval_loss": 4.147989273071289, | |
| "eval_runtime": 2.512, | |
| "eval_samples_per_second": 151.674, | |
| "eval_steps_per_second": 19.108, | |
| "eval_uas": 73.27546825034263, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 41.03, | |
| "learning_rate": 7.196778523489934e-05, | |
| "loss": 0.0696, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 43.59, | |
| "learning_rate": 7.143087248322148e-05, | |
| "loss": 0.0632, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 7.089395973154363e-05, | |
| "loss": 0.0566, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 48.72, | |
| "learning_rate": 7.035704697986578e-05, | |
| "loss": 0.0528, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 6.982013422818792e-05, | |
| "loss": 0.0523, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "eval_las": 66.48698035632708, | |
| "eval_loss": 4.477940559387207, | |
| "eval_runtime": 2.5091, | |
| "eval_samples_per_second": 151.846, | |
| "eval_steps_per_second": 19.13, | |
| "eval_uas": 74.16171767930561, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 6.928322147651007e-05, | |
| "loss": 0.0455, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 56.41, | |
| "learning_rate": 6.874630872483222e-05, | |
| "loss": 0.0436, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "learning_rate": 6.820939597315437e-05, | |
| "loss": 0.042, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 6.767248322147652e-05, | |
| "loss": 0.0379, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 6.713557046979866e-05, | |
| "loss": 0.0374, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "eval_las": 66.45043398812243, | |
| "eval_loss": 4.416062831878662, | |
| "eval_runtime": 2.5116, | |
| "eval_samples_per_second": 151.694, | |
| "eval_steps_per_second": 19.111, | |
| "eval_uas": 74.2439470077661, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 6.659865771812081e-05, | |
| "loss": 0.0337, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 6.606174496644296e-05, | |
| "loss": 0.0321, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 71.79, | |
| "learning_rate": 6.55248322147651e-05, | |
| "loss": 0.0283, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 74.36, | |
| "learning_rate": 6.498791946308724e-05, | |
| "loss": 0.0292, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "learning_rate": 6.445100671140939e-05, | |
| "loss": 0.0259, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 76.92, | |
| "eval_las": 66.7976244860667, | |
| "eval_loss": 4.949475288391113, | |
| "eval_runtime": 2.5044, | |
| "eval_samples_per_second": 152.134, | |
| "eval_steps_per_second": 19.166, | |
| "eval_uas": 74.59113750571036, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 79.49, | |
| "learning_rate": 6.391409395973154e-05, | |
| "loss": 0.0247, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 82.05, | |
| "learning_rate": 6.337718120805369e-05, | |
| "loss": 0.0259, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 84.62, | |
| "learning_rate": 6.284026845637584e-05, | |
| "loss": 0.0226, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 87.18, | |
| "learning_rate": 6.230335570469799e-05, | |
| "loss": 0.0247, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 89.74, | |
| "learning_rate": 6.176644295302013e-05, | |
| "loss": 0.0191, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 89.74, | |
| "eval_las": 66.78848789401553, | |
| "eval_loss": 5.227412700653076, | |
| "eval_runtime": 2.5046, | |
| "eval_samples_per_second": 152.118, | |
| "eval_steps_per_second": 19.164, | |
| "eval_uas": 74.36272270443125, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 92.31, | |
| "learning_rate": 6.122953020134228e-05, | |
| "loss": 0.0206, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 94.87, | |
| "learning_rate": 6.069261744966444e-05, | |
| "loss": 0.0203, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 97.44, | |
| "learning_rate": 6.0155704697986585e-05, | |
| "loss": 0.0196, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 5.9618791946308734e-05, | |
| "loss": 0.0176, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 102.56, | |
| "learning_rate": 5.9081879194630875e-05, | |
| "loss": 0.0181, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 102.56, | |
| "eval_las": 67.46459570580173, | |
| "eval_loss": 5.025106906890869, | |
| "eval_runtime": 2.5067, | |
| "eval_samples_per_second": 151.992, | |
| "eval_steps_per_second": 19.149, | |
| "eval_uas": 74.9200548195523, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 105.13, | |
| "learning_rate": 5.854496644295302e-05, | |
| "loss": 0.0164, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 107.69, | |
| "learning_rate": 5.800805369127517e-05, | |
| "loss": 0.0177, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 110.26, | |
| "learning_rate": 5.747114093959732e-05, | |
| "loss": 0.0151, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 112.82, | |
| "learning_rate": 5.693422818791947e-05, | |
| "loss": 0.0159, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 115.38, | |
| "learning_rate": 5.6397315436241616e-05, | |
| "loss": 0.0148, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 115.38, | |
| "eval_las": 67.21790772042027, | |
| "eval_loss": 5.194654941558838, | |
| "eval_runtime": 2.5047, | |
| "eval_samples_per_second": 152.112, | |
| "eval_steps_per_second": 19.164, | |
| "eval_uas": 74.71904979442668, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 117.95, | |
| "learning_rate": 5.5860402684563764e-05, | |
| "loss": 0.0158, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 120.51, | |
| "learning_rate": 5.532348993288591e-05, | |
| "loss": 0.0127, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 123.08, | |
| "learning_rate": 5.478657718120806e-05, | |
| "loss": 0.0141, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 125.64, | |
| "learning_rate": 5.424966442953021e-05, | |
| "loss": 0.012, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 128.21, | |
| "learning_rate": 5.371275167785236e-05, | |
| "loss": 0.012, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 128.21, | |
| "eval_las": 67.5011420740064, | |
| "eval_loss": 5.243346214294434, | |
| "eval_runtime": 2.5045, | |
| "eval_samples_per_second": 152.124, | |
| "eval_steps_per_second": 19.165, | |
| "eval_uas": 75.23983554134308, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 130.77, | |
| "learning_rate": 5.31758389261745e-05, | |
| "loss": 0.0118, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 133.33, | |
| "learning_rate": 5.263892617449665e-05, | |
| "loss": 0.0112, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 135.9, | |
| "learning_rate": 5.2102013422818795e-05, | |
| "loss": 0.0094, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 138.46, | |
| "learning_rate": 5.1565100671140944e-05, | |
| "loss": 0.0133, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 141.03, | |
| "learning_rate": 5.102818791946309e-05, | |
| "loss": 0.0098, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 141.03, | |
| "eval_las": 67.54682503426223, | |
| "eval_loss": 5.314740180969238, | |
| "eval_runtime": 2.5216, | |
| "eval_samples_per_second": 151.093, | |
| "eval_steps_per_second": 19.035, | |
| "eval_uas": 74.99314755596163, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 143.59, | |
| "learning_rate": 5.049127516778524e-05, | |
| "loss": 0.0096, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 146.15, | |
| "learning_rate": 4.995436241610739e-05, | |
| "loss": 0.0104, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 148.72, | |
| "learning_rate": 4.941744966442954e-05, | |
| "loss": 0.0095, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 151.28, | |
| "learning_rate": 4.8880536912751685e-05, | |
| "loss": 0.0078, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 153.85, | |
| "learning_rate": 4.834362416107383e-05, | |
| "loss": 0.0083, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 153.85, | |
| "eval_las": 67.90315212425764, | |
| "eval_loss": 5.257903575897217, | |
| "eval_runtime": 2.5051, | |
| "eval_samples_per_second": 152.089, | |
| "eval_steps_per_second": 19.161, | |
| "eval_uas": 75.16674280493376, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 156.41, | |
| "learning_rate": 4.780671140939598e-05, | |
| "loss": 0.0086, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 158.97, | |
| "learning_rate": 4.726979865771813e-05, | |
| "loss": 0.0088, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 161.54, | |
| "learning_rate": 4.673288590604027e-05, | |
| "loss": 0.0073, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 164.1, | |
| "learning_rate": 4.619597315436242e-05, | |
| "loss": 0.0075, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "learning_rate": 4.565906040268457e-05, | |
| "loss": 0.0075, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 166.67, | |
| "eval_las": 67.38236637734126, | |
| "eval_loss": 5.439788818359375, | |
| "eval_runtime": 2.5045, | |
| "eval_samples_per_second": 152.128, | |
| "eval_steps_per_second": 19.166, | |
| "eval_uas": 74.9200548195523, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 169.23, | |
| "learning_rate": 4.5122147651006716e-05, | |
| "loss": 0.0063, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 171.79, | |
| "learning_rate": 4.4585234899328864e-05, | |
| "loss": 0.0072, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 174.36, | |
| "learning_rate": 4.404832214765101e-05, | |
| "loss": 0.0062, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 176.92, | |
| "learning_rate": 4.351140939597316e-05, | |
| "loss": 0.0063, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 179.49, | |
| "learning_rate": 4.297449664429531e-05, | |
| "loss": 0.008, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 179.49, | |
| "eval_las": 67.61078117862037, | |
| "eval_loss": 5.429704189300537, | |
| "eval_runtime": 2.5048, | |
| "eval_samples_per_second": 152.105, | |
| "eval_steps_per_second": 19.163, | |
| "eval_uas": 75.58702603928734, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 182.05, | |
| "learning_rate": 4.243758389261746e-05, | |
| "loss": 0.0064, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 184.62, | |
| "learning_rate": 4.1900671140939605e-05, | |
| "loss": 0.0056, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 187.18, | |
| "learning_rate": 4.1363758389261754e-05, | |
| "loss": 0.0058, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 189.74, | |
| "learning_rate": 4.0826845637583895e-05, | |
| "loss": 0.0058, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 192.31, | |
| "learning_rate": 4.028993288590604e-05, | |
| "loss": 0.0064, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 192.31, | |
| "eval_las": 68.15897670169026, | |
| "eval_loss": 5.503659725189209, | |
| "eval_runtime": 2.5084, | |
| "eval_samples_per_second": 151.887, | |
| "eval_steps_per_second": 19.135, | |
| "eval_uas": 75.56875285518501, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 194.87, | |
| "learning_rate": 3.975302013422819e-05, | |
| "loss": 0.0067, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 197.44, | |
| "learning_rate": 3.921610738255034e-05, | |
| "loss": 0.0046, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 3.867919463087249e-05, | |
| "loss": 0.0045, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 202.56, | |
| "learning_rate": 3.8142281879194636e-05, | |
| "loss": 0.005, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 205.13, | |
| "learning_rate": 3.7605369127516784e-05, | |
| "loss": 0.0049, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 205.13, | |
| "eval_las": 67.86660575605299, | |
| "eval_loss": 5.539348125457764, | |
| "eval_runtime": 2.5096, | |
| "eval_samples_per_second": 151.815, | |
| "eval_steps_per_second": 19.126, | |
| "eval_uas": 75.4682503426222, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 207.69, | |
| "learning_rate": 3.706845637583893e-05, | |
| "loss": 0.0052, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 210.26, | |
| "learning_rate": 3.653154362416108e-05, | |
| "loss": 0.0043, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 212.82, | |
| "learning_rate": 3.599463087248322e-05, | |
| "loss": 0.0043, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 215.38, | |
| "learning_rate": 3.545771812080537e-05, | |
| "loss": 0.0041, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 217.95, | |
| "learning_rate": 3.492080536912752e-05, | |
| "loss": 0.0053, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 217.95, | |
| "eval_las": 68.07674737322978, | |
| "eval_loss": 5.689121246337891, | |
| "eval_runtime": 2.5046, | |
| "eval_samples_per_second": 152.121, | |
| "eval_steps_per_second": 19.165, | |
| "eval_uas": 75.678391959799, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 220.51, | |
| "learning_rate": 3.438389261744967e-05, | |
| "loss": 0.0039, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 223.08, | |
| "learning_rate": 3.3846979865771815e-05, | |
| "loss": 0.004, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 225.64, | |
| "learning_rate": 3.3310067114093964e-05, | |
| "loss": 0.0038, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 228.21, | |
| "learning_rate": 3.277315436241611e-05, | |
| "loss": 0.0038, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 230.77, | |
| "learning_rate": 3.223624161073826e-05, | |
| "loss": 0.0033, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 230.77, | |
| "eval_las": 69.00867976244861, | |
| "eval_loss": 5.695150852203369, | |
| "eval_runtime": 2.503, | |
| "eval_samples_per_second": 152.215, | |
| "eval_steps_per_second": 19.177, | |
| "eval_uas": 76.09867519415258, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 233.33, | |
| "learning_rate": 3.169932885906041e-05, | |
| "loss": 0.0038, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 235.9, | |
| "learning_rate": 3.1162416107382557e-05, | |
| "loss": 0.0034, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 238.46, | |
| "learning_rate": 3.0625503355704705e-05, | |
| "loss": 0.0036, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 241.03, | |
| "learning_rate": 3.0088590604026846e-05, | |
| "loss": 0.0037, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 243.59, | |
| "learning_rate": 2.9551677852348995e-05, | |
| "loss": 0.0033, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 243.59, | |
| "eval_las": 68.76199177706715, | |
| "eval_loss": 5.625730037689209, | |
| "eval_runtime": 2.5076, | |
| "eval_samples_per_second": 151.938, | |
| "eval_steps_per_second": 19.142, | |
| "eval_uas": 75.96162631338511, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 246.15, | |
| "learning_rate": 2.9014765100671143e-05, | |
| "loss": 0.0025, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 248.72, | |
| "learning_rate": 2.847785234899329e-05, | |
| "loss": 0.0029, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 251.28, | |
| "learning_rate": 2.794093959731544e-05, | |
| "loss": 0.0036, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 253.85, | |
| "learning_rate": 2.7404026845637588e-05, | |
| "loss": 0.0034, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 256.41, | |
| "learning_rate": 2.6867114093959732e-05, | |
| "loss": 0.0032, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 256.41, | |
| "eval_las": 68.68889904065783, | |
| "eval_loss": 5.689762115478516, | |
| "eval_runtime": 2.5074, | |
| "eval_samples_per_second": 151.949, | |
| "eval_steps_per_second": 19.143, | |
| "eval_uas": 75.68752855185016, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 258.97, | |
| "learning_rate": 2.633020134228188e-05, | |
| "loss": 0.0028, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 261.54, | |
| "learning_rate": 2.579328859060403e-05, | |
| "loss": 0.0027, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 264.1, | |
| "learning_rate": 2.5256375838926177e-05, | |
| "loss": 0.002, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 266.67, | |
| "learning_rate": 2.4719463087248325e-05, | |
| "loss": 0.0023, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 269.23, | |
| "learning_rate": 2.4182550335570474e-05, | |
| "loss": 0.002, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 269.23, | |
| "eval_las": 68.93558702603929, | |
| "eval_loss": 6.083931922912598, | |
| "eval_runtime": 2.511, | |
| "eval_samples_per_second": 151.731, | |
| "eval_steps_per_second": 19.116, | |
| "eval_uas": 76.0438556418456, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 271.79, | |
| "learning_rate": 2.364563758389262e-05, | |
| "loss": 0.0016, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 274.36, | |
| "learning_rate": 2.3108724832214767e-05, | |
| "loss": 0.0016, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 276.92, | |
| "learning_rate": 2.2571812080536915e-05, | |
| "loss": 0.0021, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 279.49, | |
| "learning_rate": 2.2034899328859063e-05, | |
| "loss": 0.0021, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 282.05, | |
| "learning_rate": 2.149798657718121e-05, | |
| "loss": 0.0019, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 282.05, | |
| "eval_las": 68.63407948835084, | |
| "eval_loss": 6.047039031982422, | |
| "eval_runtime": 2.5036, | |
| "eval_samples_per_second": 152.181, | |
| "eval_steps_per_second": 19.172, | |
| "eval_uas": 75.85198720877113, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 284.62, | |
| "learning_rate": 2.0961073825503356e-05, | |
| "loss": 0.0016, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 287.18, | |
| "learning_rate": 2.0424161073825505e-05, | |
| "loss": 0.0021, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 289.74, | |
| "learning_rate": 1.9887248322147653e-05, | |
| "loss": 0.0024, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 292.31, | |
| "learning_rate": 1.93503355704698e-05, | |
| "loss": 0.0017, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 294.87, | |
| "learning_rate": 1.881342281879195e-05, | |
| "loss": 0.0019, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 294.87, | |
| "eval_las": 68.79853814527182, | |
| "eval_loss": 6.113554000854492, | |
| "eval_runtime": 2.505, | |
| "eval_samples_per_second": 152.095, | |
| "eval_steps_per_second": 19.162, | |
| "eval_uas": 76.23572407492006, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 294.87, | |
| "step": 11500, | |
| "total_flos": 7.223115436230451e+16, | |
| "train_loss": 0.10975235502227493, | |
| "train_runtime": 5024.1647, | |
| "train_samples_per_second": 95.538, | |
| "train_steps_per_second": 2.986 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 385, | |
| "total_flos": 7.223115436230451e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |