| { | |
| "best_metric": 0.15368719398975372, | |
| "best_model_checkpoint": "/output/longformer-large-4096-finetuned-full/checkpoint-35000", | |
| "epoch": 3.0, | |
| "global_step": 38073, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.934336669030547e-05, | |
| "loss": 0.8478, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8686733380610934e-05, | |
| "loss": 0.5067, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.80301000709164e-05, | |
| "loss": 0.4272, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7373466761221866e-05, | |
| "loss": 0.3848, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.671683345152733e-05, | |
| "loss": 0.354, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.60602001418328e-05, | |
| "loss": 0.3333, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.540356683213826e-05, | |
| "loss": 0.319, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.474693352244373e-05, | |
| "loss": 0.3051, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.40903002127492e-05, | |
| "loss": 0.294, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.343366690305466e-05, | |
| "loss": 0.2837, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.9413275913410438, | |
| "eval_loss": 0.25030046701431274, | |
| "eval_runtime": 11955.9114, | |
| "eval_samples_per_second": 2.126, | |
| "eval_steps_per_second": 0.531, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.277703359336013e-05, | |
| "loss": 0.2756, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.212040028366559e-05, | |
| "loss": 0.2684, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.1463766973971054e-05, | |
| "loss": 0.2627, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.0807133664276524e-05, | |
| "loss": 0.2564, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.0150500354581986e-05, | |
| "loss": 0.2531, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9493867044887455e-05, | |
| "loss": 0.2457, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.883723373519292e-05, | |
| "loss": 0.2424, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.818060042549839e-05, | |
| "loss": 0.2384, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7523967115803856e-05, | |
| "loss": 0.2352, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.686733380610932e-05, | |
| "loss": 0.2305, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.9494652483570813, | |
| "eval_loss": 0.20809219777584076, | |
| "eval_runtime": 11956.3035, | |
| "eval_samples_per_second": 2.125, | |
| "eval_steps_per_second": 0.531, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.621070049641479e-05, | |
| "loss": 0.2286, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.555406718672025e-05, | |
| "loss": 0.2251, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.489743387702571e-05, | |
| "loss": 0.2233, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.424080056733118e-05, | |
| "loss": 0.2206, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.3584167257636644e-05, | |
| "loss": 0.2165, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.292753394794211e-05, | |
| "loss": 0.2135, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.227090063824758e-05, | |
| "loss": 0.2128, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1614267328553045e-05, | |
| "loss": 0.2105, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.0957634018858514e-05, | |
| "loss": 0.2096, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.0301000709163973e-05, | |
| "loss": 0.2069, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.9537146569573595, | |
| "eval_loss": 0.18708214163780212, | |
| "eval_runtime": 11958.4868, | |
| "eval_samples_per_second": 2.125, | |
| "eval_steps_per_second": 0.531, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9644367399469442e-05, | |
| "loss": 0.2052, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.8987734089774908e-05, | |
| "loss": 0.2026, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.833110078008037e-05, | |
| "loss": 0.2013, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.767446747038584e-05, | |
| "loss": 0.2003, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.7017834160691302e-05, | |
| "loss": 0.1979, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.636120085099677e-05, | |
| "loss": 0.197, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5704567541302237e-05, | |
| "loss": 0.1959, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.50479342316077e-05, | |
| "loss": 0.1943, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.439130092191317e-05, | |
| "loss": 0.1945, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3734667612218634e-05, | |
| "loss": 0.1909, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_accuracy": 0.9563928580029224, | |
| "eval_loss": 0.17498859763145447, | |
| "eval_runtime": 11959.4736, | |
| "eval_samples_per_second": 2.125, | |
| "eval_steps_per_second": 0.531, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.30780343025241e-05, | |
| "loss": 0.1904, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.2421400992829566e-05, | |
| "loss": 0.1895, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.176476768313503e-05, | |
| "loss": 0.1883, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1108134373440497e-05, | |
| "loss": 0.1869, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.0451501063745963e-05, | |
| "loss": 0.1857, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.9794867754051426e-05, | |
| "loss": 0.1841, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.9138234444356895e-05, | |
| "loss": 0.1841, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.848160113466236e-05, | |
| "loss": 0.183, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7824967824967826e-05, | |
| "loss": 0.1809, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7168334515273292e-05, | |
| "loss": 0.181, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.9582902012352269, | |
| "eval_loss": 0.16556869447231293, | |
| "eval_runtime": 11952.7546, | |
| "eval_samples_per_second": 2.126, | |
| "eval_steps_per_second": 0.532, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.6511701205578758e-05, | |
| "loss": 0.1791, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.5855067895884224e-05, | |
| "loss": 0.1782, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.519843458618969e-05, | |
| "loss": 0.1786, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.4541801276495154e-05, | |
| "loss": 0.1771, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3885167966800621e-05, | |
| "loss": 0.1761, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.3228534657106087e-05, | |
| "loss": 0.1748, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.2571901347411553e-05, | |
| "loss": 0.1738, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.1915268037717017e-05, | |
| "loss": 0.1736, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1258634728022484e-05, | |
| "loss": 0.1724, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0602001418327948e-05, | |
| "loss": 0.172, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_accuracy": 0.9597659108954908, | |
| "eval_loss": 0.15860329568386078, | |
| "eval_runtime": 11965.9783, | |
| "eval_samples_per_second": 2.124, | |
| "eval_steps_per_second": 0.531, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.945368108633416e-06, | |
| "loss": 0.1717, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 9.28873479893888e-06, | |
| "loss": 0.1711, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.632101489244348e-06, | |
| "loss": 0.1705, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 7.975468179549812e-06, | |
| "loss": 0.1703, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.318834869855279e-06, | |
| "loss": 0.1704, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 6.662201560160744e-06, | |
| "loss": 0.1695, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.00556825046621e-06, | |
| "loss": 0.168, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.348934940771676e-06, | |
| "loss": 0.168, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.6923016310771415e-06, | |
| "loss": 0.1676, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.035668321382607e-06, | |
| "loss": 0.1669, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.9607826213936019, | |
| "eval_loss": 0.15368719398975372, | |
| "eval_runtime": 11962.7904, | |
| "eval_samples_per_second": 2.124, | |
| "eval_steps_per_second": 0.531, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.3790350116880735e-06, | |
| "loss": 0.1669, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.722401701993539e-06, | |
| "loss": 0.1653, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.0657683922990046e-06, | |
| "loss": 0.1655, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.4091350826044704e-06, | |
| "loss": 0.1649, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 7.525017729099362e-07, | |
| "loss": 0.1649, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.5868463215402e-08, | |
| "loss": 0.166, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 38073, | |
| "total_flos": 5.673660618532037e+18, | |
| "train_loss": 0.22367710902254853, | |
| "train_runtime": 1559138.7742, | |
| "train_samples_per_second": 0.391, | |
| "train_steps_per_second": 0.024 | |
| } | |
| ], | |
| "max_steps": 38073, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.673660618532037e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |