| { | |
| "best_metric": 50.781657113079724, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/bert/bert-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": 7.52e-05, | |
| "loss": 4.4887, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 7.949530201342283e-05, | |
| "loss": 1.7443, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 7.895838926174497e-05, | |
| "loss": 0.8269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 7.842147651006712e-05, | |
| "loss": 0.4089, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 7.788456375838927e-05, | |
| "loss": 0.2343, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "eval_las": 48.28903943025882, | |
| "eval_loss": 3.7556207180023193, | |
| "eval_runtime": 5.1839, | |
| "eval_samples_per_second": 154.325, | |
| "eval_steps_per_second": 19.291, | |
| "eval_uas": 59.15407330206705, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 7.734765100671142e-05, | |
| "loss": 0.1547, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 7.681073825503357e-05, | |
| "loss": 0.1145, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 7.627382550335572e-05, | |
| "loss": 0.089, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 7.573691275167786e-05, | |
| "loss": 0.0777, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "learning_rate": 7.52e-05, | |
| "loss": 0.0697, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "eval_las": 47.168664234844535, | |
| "eval_loss": 5.077505588531494, | |
| "eval_runtime": 5.1923, | |
| "eval_samples_per_second": 154.073, | |
| "eval_steps_per_second": 19.259, | |
| "eval_uas": 57.755775577557756, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 7.466308724832215e-05, | |
| "loss": 0.0611, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 7.41261744966443e-05, | |
| "loss": 0.0498, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 7.358926174496644e-05, | |
| "loss": 0.049, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 7.305234899328859e-05, | |
| "loss": 0.0443, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 7.251543624161074e-05, | |
| "loss": 0.04, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "eval_las": 48.20218863991662, | |
| "eval_loss": 5.622523307800293, | |
| "eval_runtime": 5.1912, | |
| "eval_samples_per_second": 154.107, | |
| "eval_steps_per_second": 19.263, | |
| "eval_uas": 58.580858085808586, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "learning_rate": 7.197852348993289e-05, | |
| "loss": 0.0428, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 38.64, | |
| "learning_rate": 7.144161073825504e-05, | |
| "loss": 0.0402, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 40.91, | |
| "learning_rate": 7.090469798657718e-05, | |
| "loss": 0.0353, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 43.18, | |
| "learning_rate": 7.036778523489933e-05, | |
| "loss": 0.0292, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "learning_rate": 6.983087248322148e-05, | |
| "loss": 0.0363, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "eval_las": 48.53222164321696, | |
| "eval_loss": 6.002054214477539, | |
| "eval_runtime": 5.1905, | |
| "eval_samples_per_second": 154.128, | |
| "eval_steps_per_second": 19.266, | |
| "eval_uas": 59.37988535695675, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 47.73, | |
| "learning_rate": 6.929395973154363e-05, | |
| "loss": 0.0321, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 6.875704697986578e-05, | |
| "loss": 0.031, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 52.27, | |
| "learning_rate": 6.822013422818793e-05, | |
| "loss": 0.0282, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 54.55, | |
| "learning_rate": 6.768322147651007e-05, | |
| "loss": 0.0237, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 56.82, | |
| "learning_rate": 6.714630872483222e-05, | |
| "loss": 0.0238, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 56.82, | |
| "eval_las": 48.27166927219038, | |
| "eval_loss": 6.428050994873047, | |
| "eval_runtime": 5.1921, | |
| "eval_samples_per_second": 154.079, | |
| "eval_steps_per_second": 19.26, | |
| "eval_uas": 59.05853743269064, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 59.09, | |
| "learning_rate": 6.660939597315437e-05, | |
| "loss": 0.0246, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 61.36, | |
| "learning_rate": 6.607248322147652e-05, | |
| "loss": 0.0224, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 63.64, | |
| "learning_rate": 6.553557046979867e-05, | |
| "loss": 0.0231, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 65.91, | |
| "learning_rate": 6.499865771812081e-05, | |
| "loss": 0.0224, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 68.18, | |
| "learning_rate": 6.446174496644296e-05, | |
| "loss": 0.0184, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 68.18, | |
| "eval_las": 48.966475594927914, | |
| "eval_loss": 7.119157791137695, | |
| "eval_runtime": 5.1953, | |
| "eval_samples_per_second": 153.986, | |
| "eval_steps_per_second": 19.248, | |
| "eval_uas": 59.47542122633316, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 70.45, | |
| "learning_rate": 6.392483221476511e-05, | |
| "loss": 0.02, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 72.73, | |
| "learning_rate": 6.338791946308726e-05, | |
| "loss": 0.0198, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 6.28510067114094e-05, | |
| "loss": 0.0196, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 77.27, | |
| "learning_rate": 6.231409395973154e-05, | |
| "loss": 0.0177, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 79.55, | |
| "learning_rate": 6.177718120805369e-05, | |
| "loss": 0.0149, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 79.55, | |
| "eval_las": 48.75803369810665, | |
| "eval_loss": 7.0862298011779785, | |
| "eval_runtime": 5.1933, | |
| "eval_samples_per_second": 154.044, | |
| "eval_steps_per_second": 19.256, | |
| "eval_uas": 59.44936598923051, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 81.82, | |
| "learning_rate": 6.124026845637584e-05, | |
| "loss": 0.0138, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 84.09, | |
| "learning_rate": 6.070335570469799e-05, | |
| "loss": 0.0173, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 86.36, | |
| "learning_rate": 6.0166442953020136e-05, | |
| "loss": 0.0165, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 88.64, | |
| "learning_rate": 5.962953020134229e-05, | |
| "loss": 0.015, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 90.91, | |
| "learning_rate": 5.909261744966444e-05, | |
| "loss": 0.0132, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 90.91, | |
| "eval_las": 49.035956227201666, | |
| "eval_loss": 7.622977256774902, | |
| "eval_runtime": 5.1898, | |
| "eval_samples_per_second": 154.148, | |
| "eval_steps_per_second": 19.268, | |
| "eval_uas": 59.31908980371722, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 93.18, | |
| "learning_rate": 5.855570469798659e-05, | |
| "loss": 0.0154, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 95.45, | |
| "learning_rate": 5.8018791946308735e-05, | |
| "loss": 0.0131, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 97.73, | |
| "learning_rate": 5.7481879194630884e-05, | |
| "loss": 0.0124, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 5.694496644295303e-05, | |
| "loss": 0.0125, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 102.27, | |
| "learning_rate": 5.6408053691275166e-05, | |
| "loss": 0.0142, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 102.27, | |
| "eval_las": 49.27045336112559, | |
| "eval_loss": 7.618669509887695, | |
| "eval_runtime": 5.1961, | |
| "eval_samples_per_second": 153.962, | |
| "eval_steps_per_second": 19.245, | |
| "eval_uas": 59.47542122633316, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 104.55, | |
| "learning_rate": 5.5871140939597315e-05, | |
| "loss": 0.0131, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 106.82, | |
| "learning_rate": 5.533422818791946e-05, | |
| "loss": 0.0126, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 109.09, | |
| "learning_rate": 5.479731543624161e-05, | |
| "loss": 0.0101, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 111.36, | |
| "learning_rate": 5.426040268456376e-05, | |
| "loss": 0.0094, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 113.64, | |
| "learning_rate": 5.372348993288591e-05, | |
| "loss": 0.0098, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 113.64, | |
| "eval_las": 49.678652075733886, | |
| "eval_loss": 7.6977925300598145, | |
| "eval_runtime": 5.1957, | |
| "eval_samples_per_second": 153.974, | |
| "eval_steps_per_second": 19.247, | |
| "eval_uas": 59.82282438770192, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 115.91, | |
| "learning_rate": 5.3186577181208056e-05, | |
| "loss": 0.0096, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 118.18, | |
| "learning_rate": 5.2649664429530204e-05, | |
| "loss": 0.009, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 120.45, | |
| "learning_rate": 5.211275167785235e-05, | |
| "loss": 0.0104, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 122.73, | |
| "learning_rate": 5.15758389261745e-05, | |
| "loss": 0.0111, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 5.1038926174496656e-05, | |
| "loss": 0.0095, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_las": 49.17491749174918, | |
| "eval_loss": 7.922099590301514, | |
| "eval_runtime": 5.1917, | |
| "eval_samples_per_second": 154.091, | |
| "eval_steps_per_second": 19.261, | |
| "eval_uas": 59.80545422963349, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 127.27, | |
| "learning_rate": 5.050201342281879e-05, | |
| "loss": 0.0104, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 129.55, | |
| "learning_rate": 4.996510067114094e-05, | |
| "loss": 0.0103, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 131.82, | |
| "learning_rate": 4.942818791946309e-05, | |
| "loss": 0.0104, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 134.09, | |
| "learning_rate": 4.8891275167785235e-05, | |
| "loss": 0.0073, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 136.36, | |
| "learning_rate": 4.835436241610738e-05, | |
| "loss": 0.0085, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 136.36, | |
| "eval_las": 49.504950495049506, | |
| "eval_loss": 8.327244758605957, | |
| "eval_runtime": 5.1925, | |
| "eval_samples_per_second": 154.068, | |
| "eval_steps_per_second": 19.258, | |
| "eval_uas": 59.73597359735974, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 138.64, | |
| "learning_rate": 4.781744966442953e-05, | |
| "loss": 0.0076, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 140.91, | |
| "learning_rate": 4.728053691275168e-05, | |
| "loss": 0.0078, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 143.18, | |
| "learning_rate": 4.674362416107383e-05, | |
| "loss": 0.007, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 145.45, | |
| "learning_rate": 4.6206711409395976e-05, | |
| "loss": 0.005, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 147.73, | |
| "learning_rate": 4.5669798657718125e-05, | |
| "loss": 0.005, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 147.73, | |
| "eval_las": 49.71339239187076, | |
| "eval_loss": 8.44931697845459, | |
| "eval_runtime": 5.1924, | |
| "eval_samples_per_second": 154.072, | |
| "eval_steps_per_second": 19.259, | |
| "eval_uas": 59.96178565224943, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 4.513288590604027e-05, | |
| "loss": 0.0064, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 152.27, | |
| "learning_rate": 4.459597315436242e-05, | |
| "loss": 0.0049, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 154.55, | |
| "learning_rate": 4.405906040268456e-05, | |
| "loss": 0.0039, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 156.82, | |
| "learning_rate": 4.352214765100671e-05, | |
| "loss": 0.0044, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 159.09, | |
| "learning_rate": 4.298523489932886e-05, | |
| "loss": 0.0052, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 159.09, | |
| "eval_las": 49.70470731283655, | |
| "eval_loss": 8.672440528869629, | |
| "eval_runtime": 5.1898, | |
| "eval_samples_per_second": 154.15, | |
| "eval_steps_per_second": 19.269, | |
| "eval_uas": 60.36998436685774, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 161.36, | |
| "learning_rate": 4.244832214765101e-05, | |
| "loss": 0.0049, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 163.64, | |
| "learning_rate": 4.1911409395973156e-05, | |
| "loss": 0.0089, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 165.91, | |
| "learning_rate": 4.1374496644295304e-05, | |
| "loss": 0.0036, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 168.18, | |
| "learning_rate": 4.083758389261745e-05, | |
| "loss": 0.0056, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 170.45, | |
| "learning_rate": 4.03006711409396e-05, | |
| "loss": 0.0038, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 170.45, | |
| "eval_las": 49.58311620635748, | |
| "eval_loss": 8.693171501159668, | |
| "eval_runtime": 5.1886, | |
| "eval_samples_per_second": 154.183, | |
| "eval_steps_per_second": 19.273, | |
| "eval_uas": 60.700017370158065, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 172.73, | |
| "learning_rate": 3.976375838926175e-05, | |
| "loss": 0.0039, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 3.92268456375839e-05, | |
| "loss": 0.003, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 177.27, | |
| "learning_rate": 3.8689932885906045e-05, | |
| "loss": 0.0025, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 179.55, | |
| "learning_rate": 3.815302013422819e-05, | |
| "loss": 0.003, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 181.82, | |
| "learning_rate": 3.761610738255034e-05, | |
| "loss": 0.0035, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 181.82, | |
| "eval_las": 50.20844189682126, | |
| "eval_loss": 8.397028923034668, | |
| "eval_runtime": 5.1807, | |
| "eval_samples_per_second": 154.42, | |
| "eval_steps_per_second": 19.303, | |
| "eval_uas": 60.552371026576346, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 184.09, | |
| "learning_rate": 3.707919463087249e-05, | |
| "loss": 0.0034, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 186.36, | |
| "learning_rate": 3.654228187919463e-05, | |
| "loss": 0.0023, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 188.64, | |
| "learning_rate": 3.600536912751678e-05, | |
| "loss": 0.004, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 190.91, | |
| "learning_rate": 3.546845637583893e-05, | |
| "loss": 0.0031, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 193.18, | |
| "learning_rate": 3.4931543624161076e-05, | |
| "loss": 0.0037, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 193.18, | |
| "eval_las": 49.7741879451103, | |
| "eval_loss": 8.718303680419922, | |
| "eval_runtime": 5.1796, | |
| "eval_samples_per_second": 154.452, | |
| "eval_steps_per_second": 19.306, | |
| "eval_uas": 60.54368594754212, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 195.45, | |
| "learning_rate": 3.4394630872483224e-05, | |
| "loss": 0.003, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 197.73, | |
| "learning_rate": 3.385771812080537e-05, | |
| "loss": 0.004, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 3.332080536912752e-05, | |
| "loss": 0.004, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 202.27, | |
| "learning_rate": 3.278389261744967e-05, | |
| "loss": 0.0023, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 204.55, | |
| "learning_rate": 3.224697986577182e-05, | |
| "loss": 0.0029, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 204.55, | |
| "eval_las": 49.73944762897342, | |
| "eval_loss": 8.950847625732422, | |
| "eval_runtime": 5.1787, | |
| "eval_samples_per_second": 154.478, | |
| "eval_steps_per_second": 19.31, | |
| "eval_uas": 60.40472468299461, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 206.82, | |
| "learning_rate": 3.1710067114093965e-05, | |
| "loss": 0.0023, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 209.09, | |
| "learning_rate": 3.1173154362416114e-05, | |
| "loss": 0.004, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 211.36, | |
| "learning_rate": 3.0636241610738255e-05, | |
| "loss": 0.0023, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 213.64, | |
| "learning_rate": 3.0099328859060403e-05, | |
| "loss": 0.0056, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 215.91, | |
| "learning_rate": 2.956241610738255e-05, | |
| "loss": 0.0022, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 215.91, | |
| "eval_las": 49.75681778704186, | |
| "eval_loss": 8.873396873474121, | |
| "eval_runtime": 5.1795, | |
| "eval_samples_per_second": 154.455, | |
| "eval_steps_per_second": 19.307, | |
| "eval_uas": 60.23102310231023, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 218.18, | |
| "learning_rate": 2.90255033557047e-05, | |
| "loss": 0.0024, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 220.45, | |
| "learning_rate": 2.8488590604026848e-05, | |
| "loss": 0.0018, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 222.73, | |
| "learning_rate": 2.7951677852348996e-05, | |
| "loss": 0.0013, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 225.0, | |
| "learning_rate": 2.741476510067114e-05, | |
| "loss": 0.0016, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 227.27, | |
| "learning_rate": 2.687785234899329e-05, | |
| "loss": 0.0015, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 227.27, | |
| "eval_las": 50.225812054889694, | |
| "eval_loss": 9.140296936035156, | |
| "eval_runtime": 5.1821, | |
| "eval_samples_per_second": 154.379, | |
| "eval_steps_per_second": 19.297, | |
| "eval_uas": 60.70870244919229, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 229.55, | |
| "learning_rate": 2.6340939597315438e-05, | |
| "loss": 0.0013, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 231.82, | |
| "learning_rate": 2.5804026845637586e-05, | |
| "loss": 0.0013, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 234.09, | |
| "learning_rate": 2.5267114093959734e-05, | |
| "loss": 0.0031, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 236.36, | |
| "learning_rate": 2.4730201342281882e-05, | |
| "loss": 0.0018, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 238.64, | |
| "learning_rate": 2.4193288590604027e-05, | |
| "loss": 0.0015, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 238.64, | |
| "eval_las": 49.86972381448671, | |
| "eval_loss": 9.165424346923828, | |
| "eval_runtime": 5.1856, | |
| "eval_samples_per_second": 154.274, | |
| "eval_steps_per_second": 19.284, | |
| "eval_uas": 60.63922181691853, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 240.91, | |
| "learning_rate": 2.3656375838926175e-05, | |
| "loss": 0.0019, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 243.18, | |
| "learning_rate": 2.3119463087248324e-05, | |
| "loss": 0.0012, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 245.45, | |
| "learning_rate": 2.2582550335570472e-05, | |
| "loss": 0.0016, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 247.73, | |
| "learning_rate": 2.204563758389262e-05, | |
| "loss": 0.0005, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "learning_rate": 2.150872483221477e-05, | |
| "loss": 0.0007, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "eval_las": 50.48636442591628, | |
| "eval_loss": 8.970284461975098, | |
| "eval_runtime": 5.2059, | |
| "eval_samples_per_second": 153.671, | |
| "eval_steps_per_second": 19.209, | |
| "eval_uas": 61.09953100573215, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 252.27, | |
| "learning_rate": 2.0971812080536913e-05, | |
| "loss": 0.0005, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 254.55, | |
| "learning_rate": 2.043489932885906e-05, | |
| "loss": 0.0004, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 256.82, | |
| "learning_rate": 1.989798657718121e-05, | |
| "loss": 0.0004, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 259.09, | |
| "learning_rate": 1.9361073825503358e-05, | |
| "loss": 0.0009, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 261.36, | |
| "learning_rate": 1.8824161073825503e-05, | |
| "loss": 0.0009, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 261.36, | |
| "eval_las": 50.13027618551329, | |
| "eval_loss": 9.078216552734375, | |
| "eval_runtime": 5.2191, | |
| "eval_samples_per_second": 153.282, | |
| "eval_steps_per_second": 19.16, | |
| "eval_uas": 60.769498002431824, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 263.64, | |
| "learning_rate": 1.828724832214765e-05, | |
| "loss": 0.0005, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 265.91, | |
| "learning_rate": 1.77503355704698e-05, | |
| "loss": 0.0004, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 268.18, | |
| "learning_rate": 1.7213422818791948e-05, | |
| "loss": 0.0004, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 270.45, | |
| "learning_rate": 1.6676510067114096e-05, | |
| "loss": 0.0003, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 272.73, | |
| "learning_rate": 1.6139597315436244e-05, | |
| "loss": 0.0022, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 272.73, | |
| "eval_las": 50.13896126454751, | |
| "eval_loss": 8.995458602905273, | |
| "eval_runtime": 5.1822, | |
| "eval_samples_per_second": 154.375, | |
| "eval_steps_per_second": 19.297, | |
| "eval_uas": 60.61316657981588, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 275.0, | |
| "learning_rate": 1.560268456375839e-05, | |
| "loss": 0.0007, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 277.27, | |
| "learning_rate": 1.5065771812080539e-05, | |
| "loss": 0.0006, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 279.55, | |
| "learning_rate": 1.4528859060402685e-05, | |
| "loss": 0.0011, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 281.82, | |
| "learning_rate": 1.3991946308724834e-05, | |
| "loss": 0.0007, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 284.09, | |
| "learning_rate": 1.3455033557046982e-05, | |
| "loss": 0.0008, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 284.09, | |
| "eval_las": 50.23449713392392, | |
| "eval_loss": 9.353437423706055, | |
| "eval_runtime": 5.1815, | |
| "eval_samples_per_second": 154.397, | |
| "eval_steps_per_second": 19.3, | |
| "eval_uas": 60.969254820218865, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 286.36, | |
| "learning_rate": 1.2918120805369127e-05, | |
| "loss": 0.0004, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 288.64, | |
| "learning_rate": 1.2381208053691277e-05, | |
| "loss": 0.0005, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 290.91, | |
| "learning_rate": 1.1844295302013425e-05, | |
| "loss": 0.0004, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 293.18, | |
| "learning_rate": 1.130738255033557e-05, | |
| "loss": 0.0005, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 295.45, | |
| "learning_rate": 1.0770469798657718e-05, | |
| "loss": 0.0006, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 295.45, | |
| "eval_las": 50.62532569046378, | |
| "eval_loss": 9.346752166748047, | |
| "eval_runtime": 5.1837, | |
| "eval_samples_per_second": 154.331, | |
| "eval_steps_per_second": 19.291, | |
| "eval_uas": 61.54247003647734, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 297.73, | |
| "learning_rate": 1.0233557046979868e-05, | |
| "loss": 0.0004, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "learning_rate": 9.696644295302015e-06, | |
| "loss": 0.0004, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 302.27, | |
| "learning_rate": 9.159731543624161e-06, | |
| "loss": 0.0003, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 304.55, | |
| "learning_rate": 8.62281879194631e-06, | |
| "loss": 0.0003, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 306.82, | |
| "learning_rate": 8.085906040268458e-06, | |
| "loss": 0.0003, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 306.82, | |
| "eval_las": 50.37345839847143, | |
| "eval_loss": 9.42686653137207, | |
| "eval_runtime": 5.1835, | |
| "eval_samples_per_second": 154.335, | |
| "eval_steps_per_second": 19.292, | |
| "eval_uas": 61.281917665450756, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 309.09, | |
| "learning_rate": 7.548993288590605e-06, | |
| "loss": 0.0003, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 311.36, | |
| "learning_rate": 7.012080536912752e-06, | |
| "loss": 0.0003, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 313.64, | |
| "learning_rate": 6.475167785234899e-06, | |
| "loss": 0.0003, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 315.91, | |
| "learning_rate": 5.938255033557048e-06, | |
| "loss": 0.0002, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 318.18, | |
| "learning_rate": 5.401342281879195e-06, | |
| "loss": 0.0002, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 318.18, | |
| "eval_las": 50.64269584853223, | |
| "eval_loss": 9.432953834533691, | |
| "eval_runtime": 5.1928, | |
| "eval_samples_per_second": 154.06, | |
| "eval_steps_per_second": 19.258, | |
| "eval_uas": 61.50772972034046, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 320.45, | |
| "learning_rate": 4.864429530201343e-06, | |
| "loss": 0.0002, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 322.73, | |
| "learning_rate": 4.32751677852349e-06, | |
| "loss": 0.0003, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 325.0, | |
| "learning_rate": 3.790604026845638e-06, | |
| "loss": 0.0002, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 327.27, | |
| "learning_rate": 3.253691275167786e-06, | |
| "loss": 0.0003, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 329.55, | |
| "learning_rate": 2.716778523489933e-06, | |
| "loss": 0.0002, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 329.55, | |
| "eval_las": 50.73823171790863, | |
| "eval_loss": 9.487878799438477, | |
| "eval_runtime": 5.2057, | |
| "eval_samples_per_second": 153.676, | |
| "eval_steps_per_second": 19.21, | |
| "eval_uas": 61.42087892999827, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 331.82, | |
| "learning_rate": 2.1798657718120807e-06, | |
| "loss": 0.0002, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 334.09, | |
| "learning_rate": 1.6429530201342283e-06, | |
| "loss": 0.0002, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 336.36, | |
| "learning_rate": 1.1060402684563759e-06, | |
| "loss": 0.0003, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 338.64, | |
| "learning_rate": 5.691275167785235e-07, | |
| "loss": 0.0002, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 340.91, | |
| "learning_rate": 3.2214765100671145e-08, | |
| "loss": 0.0002, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 340.91, | |
| "eval_las": 50.781657113079724, | |
| "eval_loss": 9.509201049804688, | |
| "eval_runtime": 5.1995, | |
| "eval_samples_per_second": 153.862, | |
| "eval_steps_per_second": 19.233, | |
| "eval_uas": 61.53378495744312, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 340.91, | |
| "step": 15000, | |
| "total_flos": 7.969472217071616e+16, | |
| "train_loss": 0.06309178725369274, | |
| "train_runtime": 7782.9093, | |
| "train_samples_per_second": 61.674, | |
| "train_steps_per_second": 1.927 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 341, | |
| "total_flos": 7.969472217071616e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |