| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 30.0, |
| "eval_steps": 500, |
| "global_step": 8520, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5159730315208435, |
| "learning_rate": 4.8333333333333334e-05, |
| "loss": 0.5703, |
| "step": 284 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_srl_loss": 0.2537473142147064, |
| "eval_srl_runtime": 17.5701, |
| "eval_srl_samples_per_second": 129.197, |
| "eval_srl_steps_per_second": 16.164, |
| "step": 284 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_ner_loss": 0.31049808859825134, |
| "eval_ner_runtime": 17.5692, |
| "eval_ner_samples_per_second": 129.203, |
| "eval_ner_steps_per_second": 16.165, |
| "step": 284 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.9760362505912781, |
| "learning_rate": 4.666666666666667e-05, |
| "loss": 0.1433, |
| "step": 568 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_srl_loss": 0.17236216366291046, |
| "eval_srl_runtime": 17.5646, |
| "eval_srl_samples_per_second": 129.237, |
| "eval_srl_steps_per_second": 16.169, |
| "step": 568 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_ner_loss": 0.037721339613199234, |
| "eval_ner_runtime": 17.5653, |
| "eval_ner_samples_per_second": 129.232, |
| "eval_ner_steps_per_second": 16.168, |
| "step": 568 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.6804832220077515, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0805, |
| "step": 852 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_srl_loss": 0.15186269581317902, |
| "eval_srl_runtime": 17.7859, |
| "eval_srl_samples_per_second": 127.629, |
| "eval_srl_steps_per_second": 15.968, |
| "step": 852 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_ner_loss": 0.020406559109687805, |
| "eval_ner_runtime": 17.7913, |
| "eval_ner_samples_per_second": 127.591, |
| "eval_ner_steps_per_second": 15.963, |
| "step": 852 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.3662571907043457, |
| "learning_rate": 4.3333333333333334e-05, |
| "loss": 0.0581, |
| "step": 1136 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_srl_loss": 0.0956922098994255, |
| "eval_srl_runtime": 17.7671, |
| "eval_srl_samples_per_second": 127.764, |
| "eval_srl_steps_per_second": 15.985, |
| "step": 1136 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_ner_loss": 0.008525359444320202, |
| "eval_ner_runtime": 17.7782, |
| "eval_ner_samples_per_second": 127.684, |
| "eval_ner_steps_per_second": 15.975, |
| "step": 1136 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.767581582069397, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.0467, |
| "step": 1420 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_srl_loss": 0.08026313781738281, |
| "eval_srl_runtime": 17.7961, |
| "eval_srl_samples_per_second": 127.556, |
| "eval_srl_steps_per_second": 15.959, |
| "step": 1420 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_ner_loss": 0.005362341180443764, |
| "eval_ner_runtime": 17.7935, |
| "eval_ner_samples_per_second": 127.574, |
| "eval_ner_steps_per_second": 15.961, |
| "step": 1420 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.8563648462295532, |
| "learning_rate": 4e-05, |
| "loss": 0.0377, |
| "step": 1704 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_srl_loss": 0.062152598053216934, |
| "eval_srl_runtime": 17.7659, |
| "eval_srl_samples_per_second": 127.773, |
| "eval_srl_steps_per_second": 15.986, |
| "step": 1704 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_ner_loss": 0.0037422562018036842, |
| "eval_ner_runtime": 17.7731, |
| "eval_ner_samples_per_second": 127.721, |
| "eval_ner_steps_per_second": 15.979, |
| "step": 1704 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.06660082936286926, |
| "learning_rate": 3.8333333333333334e-05, |
| "loss": 0.0306, |
| "step": 1988 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_srl_loss": 0.04806334525346756, |
| "eval_srl_runtime": 17.7866, |
| "eval_srl_samples_per_second": 127.624, |
| "eval_srl_steps_per_second": 15.967, |
| "step": 1988 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_ner_loss": 0.0034043670166283846, |
| "eval_ner_runtime": 17.7804, |
| "eval_ner_samples_per_second": 127.669, |
| "eval_ner_steps_per_second": 15.973, |
| "step": 1988 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.520635187625885, |
| "learning_rate": 3.6666666666666666e-05, |
| "loss": 0.0253, |
| "step": 2272 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_srl_loss": 0.0377148799598217, |
| "eval_srl_runtime": 17.7743, |
| "eval_srl_samples_per_second": 127.713, |
| "eval_srl_steps_per_second": 15.978, |
| "step": 2272 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_ner_loss": 0.0033542541787028313, |
| "eval_ner_runtime": 17.7809, |
| "eval_ner_samples_per_second": 127.665, |
| "eval_ner_steps_per_second": 15.972, |
| "step": 2272 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 1.5942113399505615, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0207, |
| "step": 2556 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_srl_loss": 0.036016304045915604, |
| "eval_srl_runtime": 17.7903, |
| "eval_srl_samples_per_second": 127.598, |
| "eval_srl_steps_per_second": 15.964, |
| "step": 2556 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_ner_loss": 0.0024884804151952267, |
| "eval_ner_runtime": 17.7971, |
| "eval_ner_samples_per_second": 127.549, |
| "eval_ner_steps_per_second": 15.958, |
| "step": 2556 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.18361079692840576, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0173, |
| "step": 2840 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_srl_loss": 0.024318644776940346, |
| "eval_srl_runtime": 17.7929, |
| "eval_srl_samples_per_second": 127.579, |
| "eval_srl_steps_per_second": 15.961, |
| "step": 2840 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_ner_loss": 0.0017394711030647159, |
| "eval_ner_runtime": 17.8065, |
| "eval_ner_samples_per_second": 127.482, |
| "eval_ner_steps_per_second": 15.949, |
| "step": 2840 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.1815880984067917, |
| "learning_rate": 3.1666666666666666e-05, |
| "loss": 0.0143, |
| "step": 3124 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_srl_loss": 0.023377003148198128, |
| "eval_srl_runtime": 17.7486, |
| "eval_srl_samples_per_second": 127.897, |
| "eval_srl_steps_per_second": 16.001, |
| "step": 3124 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_ner_loss": 0.0016144798137247562, |
| "eval_ner_runtime": 17.7863, |
| "eval_ner_samples_per_second": 127.626, |
| "eval_ner_steps_per_second": 15.967, |
| "step": 3124 |
| }, |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.9344964027404785, |
| "learning_rate": 3e-05, |
| "loss": 0.0117, |
| "step": 3408 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_srl_loss": 0.016138222068548203, |
| "eval_srl_runtime": 17.5666, |
| "eval_srl_samples_per_second": 129.222, |
| "eval_srl_steps_per_second": 16.167, |
| "step": 3408 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_ner_loss": 0.0013956058537587523, |
| "eval_ner_runtime": 17.5632, |
| "eval_ner_samples_per_second": 129.248, |
| "eval_ner_steps_per_second": 16.17, |
| "step": 3408 |
| }, |
| { |
| "epoch": 13.0, |
| "grad_norm": 0.962304949760437, |
| "learning_rate": 2.8333333333333335e-05, |
| "loss": 0.0105, |
| "step": 3692 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_srl_loss": 0.01380192395299673, |
| "eval_srl_runtime": 17.569, |
| "eval_srl_samples_per_second": 129.205, |
| "eval_srl_steps_per_second": 16.165, |
| "step": 3692 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_ner_loss": 0.0013204001588746905, |
| "eval_ner_runtime": 17.5704, |
| "eval_ner_samples_per_second": 129.195, |
| "eval_ner_steps_per_second": 16.164, |
| "step": 3692 |
| }, |
| { |
| "epoch": 14.0, |
| "grad_norm": 0.45638516545295715, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 0.0089, |
| "step": 3976 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_srl_loss": 0.01093687117099762, |
| "eval_srl_runtime": 17.57, |
| "eval_srl_samples_per_second": 129.197, |
| "eval_srl_steps_per_second": 16.164, |
| "step": 3976 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_ner_loss": 0.0010757059790194035, |
| "eval_ner_runtime": 17.5648, |
| "eval_ner_samples_per_second": 129.236, |
| "eval_ner_steps_per_second": 16.169, |
| "step": 3976 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 0.3635445833206177, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0079, |
| "step": 4260 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_srl_loss": 0.011952933855354786, |
| "eval_srl_runtime": 17.5622, |
| "eval_srl_samples_per_second": 129.255, |
| "eval_srl_steps_per_second": 16.171, |
| "step": 4260 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_ner_loss": 0.001067746547050774, |
| "eval_ner_runtime": 17.5636, |
| "eval_ner_samples_per_second": 129.245, |
| "eval_ner_steps_per_second": 16.17, |
| "step": 4260 |
| }, |
| { |
| "epoch": 16.0, |
| "grad_norm": 0.11766979098320007, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.0068, |
| "step": 4544 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_srl_loss": 0.008437857031822205, |
| "eval_srl_runtime": 17.5643, |
| "eval_srl_samples_per_second": 129.239, |
| "eval_srl_steps_per_second": 16.169, |
| "step": 4544 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_ner_loss": 0.0009184295195154846, |
| "eval_ner_runtime": 17.5679, |
| "eval_ner_samples_per_second": 129.213, |
| "eval_ner_steps_per_second": 16.166, |
| "step": 4544 |
| }, |
| { |
| "epoch": 17.0, |
| "grad_norm": 0.20853333175182343, |
| "learning_rate": 2.1666666666666667e-05, |
| "loss": 0.0062, |
| "step": 4828 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_srl_loss": 0.007432564627379179, |
| "eval_srl_runtime": 17.5647, |
| "eval_srl_samples_per_second": 129.236, |
| "eval_srl_steps_per_second": 16.169, |
| "step": 4828 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_ner_loss": 0.0009312801994383335, |
| "eval_ner_runtime": 17.5704, |
| "eval_ner_samples_per_second": 129.194, |
| "eval_ner_steps_per_second": 16.164, |
| "step": 4828 |
| }, |
| { |
| "epoch": 18.0, |
| "grad_norm": 0.10051178932189941, |
| "learning_rate": 2e-05, |
| "loss": 0.005, |
| "step": 5112 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_srl_loss": 0.006476872134953737, |
| "eval_srl_runtime": 17.564, |
| "eval_srl_samples_per_second": 129.241, |
| "eval_srl_steps_per_second": 16.169, |
| "step": 5112 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_ner_loss": 0.0008163392194546759, |
| "eval_ner_runtime": 17.5706, |
| "eval_ner_samples_per_second": 129.193, |
| "eval_ner_steps_per_second": 16.163, |
| "step": 5112 |
| }, |
| { |
| "epoch": 19.0, |
| "grad_norm": 0.3805777132511139, |
| "learning_rate": 1.8333333333333333e-05, |
| "loss": 0.0046, |
| "step": 5396 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_srl_loss": 0.005975746084004641, |
| "eval_srl_runtime": 17.5674, |
| "eval_srl_samples_per_second": 129.216, |
| "eval_srl_steps_per_second": 16.166, |
| "step": 5396 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_ner_loss": 0.001090305158868432, |
| "eval_ner_runtime": 17.5791, |
| "eval_ner_samples_per_second": 129.13, |
| "eval_ner_steps_per_second": 16.156, |
| "step": 5396 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.2945084273815155, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0043, |
| "step": 5680 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_srl_loss": 0.005685478448867798, |
| "eval_srl_runtime": 17.5743, |
| "eval_srl_samples_per_second": 129.166, |
| "eval_srl_steps_per_second": 16.16, |
| "step": 5680 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_ner_loss": 0.0006339964456856251, |
| "eval_ner_runtime": 17.5756, |
| "eval_ner_samples_per_second": 129.156, |
| "eval_ner_steps_per_second": 16.159, |
| "step": 5680 |
| }, |
| { |
| "epoch": 21.0, |
| "grad_norm": 0.39416804909706116, |
| "learning_rate": 1.5e-05, |
| "loss": 0.0038, |
| "step": 5964 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_srl_loss": 0.005070784129202366, |
| "eval_srl_runtime": 17.5904, |
| "eval_srl_samples_per_second": 129.048, |
| "eval_srl_steps_per_second": 16.145, |
| "step": 5964 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_ner_loss": 0.0006808372563682497, |
| "eval_ner_runtime": 17.5977, |
| "eval_ner_samples_per_second": 128.994, |
| "eval_ner_steps_per_second": 16.138, |
| "step": 5964 |
| }, |
| { |
| "epoch": 22.0, |
| "grad_norm": 0.39179959893226624, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.0035, |
| "step": 6248 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_srl_loss": 0.00477498397231102, |
| "eval_srl_runtime": 17.5631, |
| "eval_srl_samples_per_second": 129.248, |
| "eval_srl_steps_per_second": 16.17, |
| "step": 6248 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_ner_loss": 0.0005992591031827033, |
| "eval_ner_runtime": 17.5704, |
| "eval_ner_samples_per_second": 129.195, |
| "eval_ner_steps_per_second": 16.164, |
| "step": 6248 |
| }, |
| { |
| "epoch": 23.0, |
| "grad_norm": 0.1726011037826538, |
| "learning_rate": 1.1666666666666668e-05, |
| "loss": 0.0031, |
| "step": 6532 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_srl_loss": 0.004426795057952404, |
| "eval_srl_runtime": 17.5671, |
| "eval_srl_samples_per_second": 129.219, |
| "eval_srl_steps_per_second": 16.167, |
| "step": 6532 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_ner_loss": 0.0005771311116404831, |
| "eval_ner_runtime": 17.5705, |
| "eval_ner_samples_per_second": 129.194, |
| "eval_ner_steps_per_second": 16.163, |
| "step": 6532 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 0.21839284896850586, |
| "learning_rate": 1e-05, |
| "loss": 0.0029, |
| "step": 6816 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_srl_loss": 0.00477210059762001, |
| "eval_srl_runtime": 17.5725, |
| "eval_srl_samples_per_second": 129.179, |
| "eval_srl_steps_per_second": 16.162, |
| "step": 6816 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_ner_loss": 0.0006085642380639911, |
| "eval_ner_runtime": 17.5728, |
| "eval_ner_samples_per_second": 129.177, |
| "eval_ner_steps_per_second": 16.161, |
| "step": 6816 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 0.31567102670669556, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.0027, |
| "step": 7100 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_srl_loss": 0.003935088403522968, |
| "eval_srl_runtime": 17.5754, |
| "eval_srl_samples_per_second": 129.158, |
| "eval_srl_steps_per_second": 16.159, |
| "step": 7100 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_ner_loss": 0.000611834810115397, |
| "eval_ner_runtime": 17.5758, |
| "eval_ner_samples_per_second": 129.155, |
| "eval_ner_steps_per_second": 16.159, |
| "step": 7100 |
| }, |
| { |
| "epoch": 26.0, |
| "grad_norm": 0.14785556495189667, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.0026, |
| "step": 7384 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_srl_loss": 0.00404845317825675, |
| "eval_srl_runtime": 17.5681, |
| "eval_srl_samples_per_second": 129.211, |
| "eval_srl_steps_per_second": 16.166, |
| "step": 7384 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_ner_loss": 0.0005031172186136246, |
| "eval_ner_runtime": 17.5675, |
| "eval_ner_samples_per_second": 129.216, |
| "eval_ner_steps_per_second": 16.166, |
| "step": 7384 |
| }, |
| { |
| "epoch": 27.0, |
| "grad_norm": 0.22755762934684753, |
| "learning_rate": 5e-06, |
| "loss": 0.0025, |
| "step": 7668 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_srl_loss": 0.0036419888492673635, |
| "eval_srl_runtime": 17.5746, |
| "eval_srl_samples_per_second": 129.164, |
| "eval_srl_steps_per_second": 16.16, |
| "step": 7668 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_ner_loss": 0.0004956649499945343, |
| "eval_ner_runtime": 17.5715, |
| "eval_ner_samples_per_second": 129.186, |
| "eval_ner_steps_per_second": 16.163, |
| "step": 7668 |
| }, |
| { |
| "epoch": 28.0, |
| "grad_norm": 0.03562552109360695, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.0023, |
| "step": 7952 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_srl_loss": 0.0035714716650545597, |
| "eval_srl_runtime": 17.5746, |
| "eval_srl_samples_per_second": 129.164, |
| "eval_srl_steps_per_second": 16.16, |
| "step": 7952 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_ner_loss": 0.0004828003002330661, |
| "eval_ner_runtime": 17.5755, |
| "eval_ner_samples_per_second": 129.157, |
| "eval_ner_steps_per_second": 16.159, |
| "step": 7952 |
| }, |
| { |
| "epoch": 29.0, |
| "grad_norm": 0.1542978137731552, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": 0.0021, |
| "step": 8236 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_srl_loss": 0.003562468569725752, |
| "eval_srl_runtime": 17.6836, |
| "eval_srl_samples_per_second": 128.368, |
| "eval_srl_steps_per_second": 16.06, |
| "step": 8236 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_ner_loss": 0.0004974309122189879, |
| "eval_ner_runtime": 17.5765, |
| "eval_ner_samples_per_second": 129.149, |
| "eval_ner_steps_per_second": 16.158, |
| "step": 8236 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 0.015293457545340061, |
| "learning_rate": 0.0, |
| "loss": 0.002, |
| "step": 8520 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_srl_loss": 0.003541701938956976, |
| "eval_srl_runtime": 17.5723, |
| "eval_srl_samples_per_second": 129.181, |
| "eval_srl_steps_per_second": 16.162, |
| "step": 8520 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_ner_loss": 0.0004944342072121799, |
| "eval_ner_runtime": 17.5784, |
| "eval_ner_samples_per_second": 129.136, |
| "eval_ner_steps_per_second": 16.156, |
| "step": 8520 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8520, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 30, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.58531004841984e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
