| { | |
| "best_metric": 0.8241184949874878, | |
| "best_model_checkpoint": "./exper6_mesum5/checkpoint-3200", | |
| "epoch": 16.0, | |
| "global_step": 6880, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001997093023255814, | |
| "loss": 4.9635, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001994186046511628, | |
| "loss": 4.8696, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001991279069767442, | |
| "loss": 4.708, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001988372093023256, | |
| "loss": 4.5785, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019854651162790697, | |
| "loss": 4.4821, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019825581395348837, | |
| "loss": 4.3261, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019796511627906977, | |
| "loss": 4.2779, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019767441860465116, | |
| "loss": 4.1096, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019738372093023256, | |
| "loss": 3.9778, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00019709302325581396, | |
| "loss": 3.9276, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.20887573964497042, | |
| "eval_loss": 3.854965925216675, | |
| "eval_runtime": 19.1052, | |
| "eval_samples_per_second": 88.458, | |
| "eval_steps_per_second": 11.096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019680232558139536, | |
| "loss": 3.8116, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019651162790697676, | |
| "loss": 3.7272, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00019622093023255815, | |
| "loss": 3.5731, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019593023255813952, | |
| "loss": 3.5953, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019563953488372092, | |
| "loss": 3.52, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019534883720930232, | |
| "loss": 3.4349, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019505813953488372, | |
| "loss": 3.4109, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019476744186046511, | |
| "loss": 3.2972, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001944767441860465, | |
| "loss": 3.3065, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001941860465116279, | |
| "loss": 3.0853, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.34142011834319524, | |
| "eval_loss": 3.110643148422241, | |
| "eval_runtime": 22.1056, | |
| "eval_samples_per_second": 76.451, | |
| "eval_steps_per_second": 9.59, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001938953488372093, | |
| "loss": 2.9937, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001936046511627907, | |
| "loss": 3.0255, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001933139534883721, | |
| "loss": 3.0166, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001930232558139535, | |
| "loss": 3.0653, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001927325581395349, | |
| "loss": 2.9586, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001924418604651163, | |
| "loss": 2.7897, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001921511627906977, | |
| "loss": 2.6827, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001918604651162791, | |
| "loss": 2.8452, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001915697674418605, | |
| "loss": 2.6622, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001912790697674419, | |
| "loss": 2.604, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_accuracy": 0.4378698224852071, | |
| "eval_loss": 2.5731914043426514, | |
| "eval_runtime": 21.3181, | |
| "eval_samples_per_second": 79.275, | |
| "eval_steps_per_second": 9.945, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00019098837209302326, | |
| "loss": 2.5822, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00019069767441860466, | |
| "loss": 2.6295, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019040697674418605, | |
| "loss": 2.5692, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00019011627906976745, | |
| "loss": 2.5343, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00018982558139534885, | |
| "loss": 2.3988, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018953488372093025, | |
| "loss": 2.2905, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00018924418604651164, | |
| "loss": 2.3851, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00018895348837209304, | |
| "loss": 2.3761, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00018866279069767444, | |
| "loss": 2.1169, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00018837209302325584, | |
| "loss": 2.3183, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.4881656804733728, | |
| "eval_loss": 2.230799674987793, | |
| "eval_runtime": 22.1174, | |
| "eval_samples_per_second": 76.411, | |
| "eval_steps_per_second": 9.585, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001880813953488372, | |
| "loss": 2.224, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0001877906976744186, | |
| "loss": 2.1761, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001875, | |
| "loss": 2.1799, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001872093023255814, | |
| "loss": 1.8892, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001869186046511628, | |
| "loss": 1.7544, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001866279069767442, | |
| "loss": 1.6763, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001863372093023256, | |
| "loss": 1.7986, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.000186046511627907, | |
| "loss": 1.756, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001857558139534884, | |
| "loss": 1.7029, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00018546511627906976, | |
| "loss": 1.5326, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.5828402366863905, | |
| "eval_loss": 1.7903438806533813, | |
| "eval_runtime": 21.7201, | |
| "eval_samples_per_second": 77.808, | |
| "eval_steps_per_second": 9.761, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018517441860465116, | |
| "loss": 1.6573, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018488372093023256, | |
| "loss": 1.532, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00018459302325581395, | |
| "loss": 1.6078, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00018430232558139535, | |
| "loss": 1.4049, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00018401162790697675, | |
| "loss": 1.5065, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00018372093023255815, | |
| "loss": 1.4879, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00018343023255813955, | |
| "loss": 1.4246, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00018313953488372094, | |
| "loss": 1.4955, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001828488372093023, | |
| "loss": 1.4211, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001825581395348837, | |
| "loss": 1.3367, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_accuracy": 0.6349112426035503, | |
| "eval_loss": 1.5523816347122192, | |
| "eval_runtime": 21.782, | |
| "eval_samples_per_second": 77.587, | |
| "eval_steps_per_second": 9.733, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0001822674418604651, | |
| "loss": 1.4084, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0001819767441860465, | |
| "loss": 1.3584, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0001816860465116279, | |
| "loss": 1.2075, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.0001813953488372093, | |
| "loss": 1.3725, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00018110465116279073, | |
| "loss": 1.2105, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00018081395348837212, | |
| "loss": 1.2496, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0001805232558139535, | |
| "loss": 1.2328, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0001802325581395349, | |
| "loss": 1.239, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0001799418604651163, | |
| "loss": 1.1195, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0001796511627906977, | |
| "loss": 1.1544, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.6644970414201183, | |
| "eval_loss": 1.3166899681091309, | |
| "eval_runtime": 19.8081, | |
| "eval_samples_per_second": 85.319, | |
| "eval_steps_per_second": 10.703, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00017936046511627909, | |
| "loss": 1.1486, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00017906976744186048, | |
| "loss": 1.2199, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00017877906976744188, | |
| "loss": 1.1614, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00017848837209302328, | |
| "loss": 1.2016, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00017819767441860468, | |
| "loss": 1.201, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00017790697674418605, | |
| "loss": 1.2429, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00017761627906976745, | |
| "loss": 1.1186, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00017732558139534884, | |
| "loss": 1.1247, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00017703488372093024, | |
| "loss": 1.0676, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00017674418604651164, | |
| "loss": 1.0788, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.6384615384615384, | |
| "eval_loss": 1.3422621488571167, | |
| "eval_runtime": 20.1813, | |
| "eval_samples_per_second": 83.741, | |
| "eval_steps_per_second": 10.505, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00017645348837209304, | |
| "loss": 0.9643, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00017616279069767443, | |
| "loss": 0.979, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00017587209302325583, | |
| "loss": 1.0375, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00017558139534883723, | |
| "loss": 1.09, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001752906976744186, | |
| "loss": 1.0986, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.000175, | |
| "loss": 1.0348, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0001747093023255814, | |
| "loss": 0.6244, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0001744186046511628, | |
| "loss": 0.6798, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0001741279069767442, | |
| "loss": 0.7497, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0001738372093023256, | |
| "loss": 0.6762, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_accuracy": 0.7124260355029586, | |
| "eval_loss": 1.0780307054519653, | |
| "eval_runtime": 19.6778, | |
| "eval_samples_per_second": 85.884, | |
| "eval_steps_per_second": 10.774, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.000173546511627907, | |
| "loss": 0.6405, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00017325581395348838, | |
| "loss": 0.6018, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00017296511627906978, | |
| "loss": 0.5615, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00017267441860465118, | |
| "loss": 0.5467, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00017238372093023255, | |
| "loss": 0.6774, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.00017209302325581395, | |
| "loss": 0.5896, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00017180232558139535, | |
| "loss": 0.6513, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00017151162790697674, | |
| "loss": 0.6664, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00017122093023255814, | |
| "loss": 0.5849, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00017093023255813954, | |
| "loss": 0.6483, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.7284023668639054, | |
| "eval_loss": 1.0090051889419556, | |
| "eval_runtime": 19.6928, | |
| "eval_samples_per_second": 85.818, | |
| "eval_steps_per_second": 10.765, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00017063953488372094, | |
| "loss": 0.5701, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00017034883720930233, | |
| "loss": 0.7286, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00017005813953488373, | |
| "loss": 0.5599, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.0001697674418604651, | |
| "loss": 0.6162, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0001694767441860465, | |
| "loss": 0.5847, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0001691860465116279, | |
| "loss": 0.5539, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.0001688953488372093, | |
| "loss": 0.4776, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00016860465116279072, | |
| "loss": 0.442, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00016831395348837212, | |
| "loss": 0.6188, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.00016802325581395352, | |
| "loss": 0.6321, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.7023668639053254, | |
| "eval_loss": 1.0861115455627441, | |
| "eval_runtime": 19.7513, | |
| "eval_samples_per_second": 85.564, | |
| "eval_steps_per_second": 10.733, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.00016773255813953491, | |
| "loss": 0.5657, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00016744186046511629, | |
| "loss": 0.6551, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00016715116279069768, | |
| "loss": 0.6151, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00016686046511627908, | |
| "loss": 0.5413, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00016656976744186048, | |
| "loss": 0.6669, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00016627906976744188, | |
| "loss": 0.5427, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.00016598837209302327, | |
| "loss": 0.548, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00016569767441860467, | |
| "loss": 0.6277, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00016540697674418607, | |
| "loss": 0.4861, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.00016511627906976747, | |
| "loss": 0.5558, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.7183431952662722, | |
| "eval_loss": 0.9933034777641296, | |
| "eval_runtime": 19.592, | |
| "eval_samples_per_second": 86.26, | |
| "eval_steps_per_second": 10.821, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.00016482558139534884, | |
| "loss": 0.6277, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00016453488372093024, | |
| "loss": 0.4351, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00016424418604651163, | |
| "loss": 0.6863, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00016395348837209303, | |
| "loss": 0.3771, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00016366279069767443, | |
| "loss": 0.4199, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.00016337209302325583, | |
| "loss": 0.5126, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 0.00016308139534883722, | |
| "loss": 0.5266, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.00016279069767441862, | |
| "loss": 0.484, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00016250000000000002, | |
| "loss": 0.5512, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0001622093023255814, | |
| "loss": 0.342, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.7461538461538462, | |
| "eval_loss": 0.8871344923973083, | |
| "eval_runtime": 19.4426, | |
| "eval_samples_per_second": 86.922, | |
| "eval_steps_per_second": 10.904, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0001619186046511628, | |
| "loss": 0.3381, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.00016162790697674419, | |
| "loss": 0.3243, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.00016133720930232558, | |
| "loss": 0.3988, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00016104651162790698, | |
| "loss": 0.3494, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.00016075581395348838, | |
| "loss": 0.3225, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00016046511627906978, | |
| "loss": 0.3465, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.00016017441860465117, | |
| "loss": 0.3548, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.00015988372093023257, | |
| "loss": 0.3608, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.00015959302325581394, | |
| "loss": 0.3628, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.00015930232558139534, | |
| "loss": 0.2964, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_accuracy": 0.7408284023668639, | |
| "eval_loss": 0.9330073595046997, | |
| "eval_runtime": 20.0846, | |
| "eval_samples_per_second": 84.144, | |
| "eval_steps_per_second": 10.555, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.00015901162790697674, | |
| "loss": 0.3113, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 0.00015872093023255814, | |
| "loss": 0.2259, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00015843023255813953, | |
| "loss": 0.3578, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00015813953488372093, | |
| "loss": 0.3785, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 0.00015784883720930233, | |
| "loss": 0.2789, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 0.00015755813953488373, | |
| "loss": 0.3959, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.00015726744186046512, | |
| "loss": 0.2746, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.00015697674418604652, | |
| "loss": 0.2857, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.0001566860465116279, | |
| "loss": 0.2855, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.0001563953488372093, | |
| "loss": 0.1959, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_accuracy": 0.7343195266272189, | |
| "eval_loss": 0.9367092847824097, | |
| "eval_runtime": 20.8713, | |
| "eval_samples_per_second": 80.973, | |
| "eval_steps_per_second": 10.158, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.00015610465116279072, | |
| "loss": 0.3419, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.0001558139534883721, | |
| "loss": 0.392, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0001555232558139535, | |
| "loss": 0.3795, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 0.0001552325581395349, | |
| "loss": 0.2489, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.0001549418604651163, | |
| "loss": 0.3559, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.00015465116279069768, | |
| "loss": 0.331, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.00015436046511627907, | |
| "loss": 0.2491, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00015406976744186047, | |
| "loss": 0.3103, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.00015377906976744187, | |
| "loss": 0.3525, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 0.00015348837209302327, | |
| "loss": 0.368, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_accuracy": 0.7550295857988165, | |
| "eval_loss": 0.8471658229827881, | |
| "eval_runtime": 20.8742, | |
| "eval_samples_per_second": 80.961, | |
| "eval_steps_per_second": 10.156, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.00015319767441860467, | |
| "loss": 0.2621, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.00015290697674418606, | |
| "loss": 0.2263, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 0.00015261627906976746, | |
| "loss": 0.2258, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00015232558139534886, | |
| "loss": 0.3655, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00015203488372093026, | |
| "loss": 0.3367, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.00015174418604651163, | |
| "loss": 0.3217, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.00015145348837209303, | |
| "loss": 0.2554, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00015116279069767442, | |
| "loss": 0.2802, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.00015087209302325582, | |
| "loss": 0.3895, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00015058139534883722, | |
| "loss": 0.1821, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_accuracy": 0.7568047337278107, | |
| "eval_loss": 0.8936548233032227, | |
| "eval_runtime": 20.6899, | |
| "eval_samples_per_second": 81.682, | |
| "eval_steps_per_second": 10.247, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00015029069767441862, | |
| "loss": 0.3801, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.2355, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.0001497093023255814, | |
| "loss": 0.1641, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0001494186046511628, | |
| "loss": 0.2115, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00014912790697674418, | |
| "loss": 0.1822, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00014883720930232558, | |
| "loss": 0.2037, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.00014854651162790698, | |
| "loss": 0.1064, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00014825581395348837, | |
| "loss": 0.2264, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.00014796511627906977, | |
| "loss": 0.1047, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.00014767441860465117, | |
| "loss": 0.1851, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_accuracy": 0.7485207100591716, | |
| "eval_loss": 0.9546371698379517, | |
| "eval_runtime": 20.6297, | |
| "eval_samples_per_second": 81.921, | |
| "eval_steps_per_second": 10.276, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00014738372093023257, | |
| "loss": 0.1683, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00014709302325581396, | |
| "loss": 0.207, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.00014680232558139536, | |
| "loss": 0.2609, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.00014651162790697673, | |
| "loss": 0.1561, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00014622093023255813, | |
| "loss": 0.1005, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 0.00014593023255813953, | |
| "loss": 0.1654, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 0.00014563953488372093, | |
| "loss": 0.196, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.00014534883720930232, | |
| "loss": 0.2025, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.00014505813953488372, | |
| "loss": 0.2896, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.00014476744186046512, | |
| "loss": 0.1648, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_accuracy": 0.7355029585798817, | |
| "eval_loss": 0.9789932370185852, | |
| "eval_runtime": 20.2913, | |
| "eval_samples_per_second": 83.287, | |
| "eval_steps_per_second": 10.448, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00014447674418604652, | |
| "loss": 0.1939, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.00014418604651162791, | |
| "loss": 0.2458, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00014389534883720929, | |
| "loss": 0.1921, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.0001436046511627907, | |
| "loss": 0.2645, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 0.0001433139534883721, | |
| "loss": 0.1075, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 0.0001430232558139535, | |
| "loss": 0.1901, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.0001427325581395349, | |
| "loss": 0.0808, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 0.0001424418604651163, | |
| "loss": 0.0717, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.0001421511627906977, | |
| "loss": 0.219, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.0001418604651162791, | |
| "loss": 0.172, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_accuracy": 0.7627218934911243, | |
| "eval_loss": 0.894668459892273, | |
| "eval_runtime": 20.9503, | |
| "eval_samples_per_second": 80.667, | |
| "eval_steps_per_second": 10.119, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 0.00014156976744186047, | |
| "loss": 0.1577, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00014127906976744186, | |
| "loss": 0.1368, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.00014098837209302326, | |
| "loss": 0.1603, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.00014069767441860466, | |
| "loss": 0.1428, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.00014040697674418606, | |
| "loss": 0.1691, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.00014011627906976746, | |
| "loss": 0.1191, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.00013982558139534885, | |
| "loss": 0.1983, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00013953488372093025, | |
| "loss": 0.2286, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00013924418604651165, | |
| "loss": 0.1685, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 0.00013895348837209302, | |
| "loss": 0.0928, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_accuracy": 0.7461538461538462, | |
| "eval_loss": 1.00932776927948, | |
| "eval_runtime": 20.3616, | |
| "eval_samples_per_second": 82.999, | |
| "eval_steps_per_second": 10.412, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 0.0001386918604651163, | |
| "loss": 0.1579, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.0001384011627906977, | |
| "loss": 0.1777, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0001381104651162791, | |
| "loss": 0.1203, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.00013781976744186046, | |
| "loss": 0.2178, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00013752906976744185, | |
| "loss": 0.2459, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.00013723837209302325, | |
| "loss": 0.0927, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00013694767441860465, | |
| "loss": 0.0788, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00013665697674418605, | |
| "loss": 0.0649, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00013636627906976745, | |
| "loss": 0.0697, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00013607558139534884, | |
| "loss": 0.0699, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_accuracy": 0.763905325443787, | |
| "eval_loss": 0.8374068140983582, | |
| "eval_runtime": 19.6306, | |
| "eval_samples_per_second": 86.09, | |
| "eval_steps_per_second": 10.799, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.00013578488372093024, | |
| "loss": 0.0625, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.00013549418604651164, | |
| "loss": 0.2028, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 0.00013520348837209304, | |
| "loss": 0.0315, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 0.0001349127906976744, | |
| "loss": 0.0782, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 0.0001346220930232558, | |
| "loss": 0.0494, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.0001343313953488372, | |
| "loss": 0.0985, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.0001340406976744186, | |
| "loss": 0.0495, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.00013375, | |
| "loss": 0.1215, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 0.0001334593023255814, | |
| "loss": 0.1362, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 0.0001331686046511628, | |
| "loss": 0.0988, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "eval_accuracy": 0.7644970414201183, | |
| "eval_loss": 0.91892409324646, | |
| "eval_runtime": 19.328, | |
| "eval_samples_per_second": 87.438, | |
| "eval_steps_per_second": 10.969, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.0001328779069767442, | |
| "loss": 0.1252, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.0001325872093023256, | |
| "loss": 0.1492, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 0.000132296511627907, | |
| "loss": 0.0964, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 0.00013200581395348838, | |
| "loss": 0.0844, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 0.00013171511627906978, | |
| "loss": 0.0469, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.00013142441860465118, | |
| "loss": 0.1314, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 0.00013113372093023258, | |
| "loss": 0.0499, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.00013084302325581398, | |
| "loss": 0.0977, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.00013055232558139537, | |
| "loss": 0.1448, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 0.00013026162790697674, | |
| "loss": 0.0822, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "eval_accuracy": 0.7579881656804733, | |
| "eval_loss": 0.9511772394180298, | |
| "eval_runtime": 19.4727, | |
| "eval_samples_per_second": 86.788, | |
| "eval_steps_per_second": 10.887, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00012997093023255814, | |
| "loss": 0.0852, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 0.00012968023255813954, | |
| "loss": 0.083, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.00012938953488372094, | |
| "loss": 0.1243, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00012912790697674418, | |
| "loss": 0.1436, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.00012883720930232558, | |
| "loss": 0.1154, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 0.00012854651162790698, | |
| "loss": 0.0987, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 0.00012825581395348838, | |
| "loss": 0.071, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.00012796511627906977, | |
| "loss": 0.2107, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 0.00012767441860465117, | |
| "loss": 0.0542, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00012738372093023257, | |
| "loss": 0.1223, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "eval_accuracy": 0.7349112426035503, | |
| "eval_loss": 1.0808570384979248, | |
| "eval_runtime": 19.4776, | |
| "eval_samples_per_second": 86.766, | |
| "eval_steps_per_second": 10.884, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.00012709302325581397, | |
| "loss": 0.0997, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.00012680232558139536, | |
| "loss": 0.0534, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.00012651162790697676, | |
| "loss": 0.0594, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 0.00012622093023255813, | |
| "loss": 0.0816, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.00012593023255813953, | |
| "loss": 0.0275, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.00012563953488372093, | |
| "loss": 0.0481, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 0.00012534883720930233, | |
| "loss": 0.1013, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00012505813953488372, | |
| "loss": 0.0881, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.00012476744186046512, | |
| "loss": 0.0648, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.00012447674418604652, | |
| "loss": 0.0509, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_accuracy": 0.7769230769230769, | |
| "eval_loss": 0.9296752214431763, | |
| "eval_runtime": 19.3041, | |
| "eval_samples_per_second": 87.546, | |
| "eval_steps_per_second": 10.982, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 0.00012418604651162792, | |
| "loss": 0.0404, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 0.00012389534883720931, | |
| "loss": 0.0816, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00012360465116279068, | |
| "loss": 0.0349, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00012331395348837208, | |
| "loss": 0.0942, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 0.00012302325581395348, | |
| "loss": 0.0618, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00012273255813953488, | |
| "loss": 0.0388, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.00012244186046511628, | |
| "loss": 0.026, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 0.00012215116279069767, | |
| "loss": 0.1201, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.00012186046511627907, | |
| "loss": 0.0445, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 0.00012156976744186046, | |
| "loss": 0.0511, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "eval_accuracy": 0.7822485207100591, | |
| "eval_loss": 0.898115336894989, | |
| "eval_runtime": 19.3662, | |
| "eval_samples_per_second": 87.265, | |
| "eval_steps_per_second": 10.947, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.00012127906976744185, | |
| "loss": 0.0678, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.00012098837209302328, | |
| "loss": 0.0136, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00012069767441860466, | |
| "loss": 0.0363, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 0.00012040697674418606, | |
| "loss": 0.0503, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00012011627906976746, | |
| "loss": 0.011, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 0.00011982558139534886, | |
| "loss": 0.0152, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 0.00011953488372093025, | |
| "loss": 0.0193, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.00011924418604651164, | |
| "loss": 0.0281, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 0.00011895348837209303, | |
| "loss": 0.0215, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00011866279069767443, | |
| "loss": 0.0596, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "eval_accuracy": 0.770414201183432, | |
| "eval_loss": 0.9468280673027039, | |
| "eval_runtime": 19.5157, | |
| "eval_samples_per_second": 86.597, | |
| "eval_steps_per_second": 10.863, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.00011837209302325583, | |
| "loss": 0.034, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.00011808139534883721, | |
| "loss": 0.0153, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 0.00011779069767441861, | |
| "loss": 0.0231, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 0.00011750000000000001, | |
| "loss": 0.0593, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 0.00011720930232558141, | |
| "loss": 0.0623, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 0.0001169186046511628, | |
| "loss": 0.0372, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00011662790697674419, | |
| "loss": 0.0404, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.00011633720930232559, | |
| "loss": 0.064, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00011604651162790699, | |
| "loss": 0.0345, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.00011575581395348838, | |
| "loss": 0.0494, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "eval_accuracy": 0.7869822485207101, | |
| "eval_loss": 0.9045378565788269, | |
| "eval_runtime": 19.375, | |
| "eval_samples_per_second": 87.226, | |
| "eval_steps_per_second": 10.942, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 0.00011546511627906977, | |
| "loss": 0.0712, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 0.00011517441860465116, | |
| "loss": 0.0888, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00011488372093023256, | |
| "loss": 0.0806, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 0.00011459302325581396, | |
| "loss": 0.0421, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 0.00011430232558139536, | |
| "loss": 0.0164, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.00011401162790697674, | |
| "loss": 0.0948, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 0.00011372093023255814, | |
| "loss": 0.1075, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 0.00011343023255813954, | |
| "loss": 0.073, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 0.00011313953488372094, | |
| "loss": 0.0758, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.00011284883720930233, | |
| "loss": 0.0643, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.7390532544378698, | |
| "eval_loss": 1.1559150218963623, | |
| "eval_runtime": 19.3968, | |
| "eval_samples_per_second": 87.128, | |
| "eval_steps_per_second": 10.93, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00011255813953488372, | |
| "loss": 0.0779, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 0.00011226744186046512, | |
| "loss": 0.0617, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.00011197674418604651, | |
| "loss": 0.0469, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 0.00011168604651162791, | |
| "loss": 0.0301, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 0.0001113953488372093, | |
| "loss": 0.0488, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 0.00011110465116279069, | |
| "loss": 0.0244, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00011081395348837209, | |
| "loss": 0.0216, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 0.00011052325581395349, | |
| "loss": 0.0653, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.00011023255813953489, | |
| "loss": 0.059, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.00010994186046511627, | |
| "loss": 0.0158, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_accuracy": 0.7899408284023669, | |
| "eval_loss": 0.8450144529342651, | |
| "eval_runtime": 19.5061, | |
| "eval_samples_per_second": 86.639, | |
| "eval_steps_per_second": 10.868, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 0.00010965116279069767, | |
| "loss": 0.0223, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.00010936046511627907, | |
| "loss": 0.0222, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.00010906976744186046, | |
| "loss": 0.0279, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.00010877906976744186, | |
| "loss": 0.0728, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 0.00010848837209302327, | |
| "loss": 0.0216, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.00010819767441860467, | |
| "loss": 0.0185, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.00010790697674418607, | |
| "loss": 0.0127, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 0.00010761627906976745, | |
| "loss": 0.0491, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.00010732558139534885, | |
| "loss": 0.0088, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 0.00010703488372093025, | |
| "loss": 0.0129, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "eval_accuracy": 0.8035502958579882, | |
| "eval_loss": 0.8241184949874878, | |
| "eval_runtime": 19.3609, | |
| "eval_samples_per_second": 87.289, | |
| "eval_steps_per_second": 10.95, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.00010674418604651165, | |
| "loss": 0.0119, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 0.00010645348837209303, | |
| "loss": 0.0293, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 0.00010616279069767443, | |
| "loss": 0.0083, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.00010587209302325582, | |
| "loss": 0.0099, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 0.00010558139534883722, | |
| "loss": 0.0052, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.00010529069767441862, | |
| "loss": 0.0401, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 0.000105, | |
| "loss": 0.038, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 0.0001047093023255814, | |
| "loss": 0.0179, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 0.0001044186046511628, | |
| "loss": 0.0609, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 0.0001041279069767442, | |
| "loss": 0.0441, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_accuracy": 0.7751479289940828, | |
| "eval_loss": 0.9678510427474976, | |
| "eval_runtime": 19.577, | |
| "eval_samples_per_second": 86.326, | |
| "eval_steps_per_second": 10.829, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 0.0001038372093023256, | |
| "loss": 0.0551, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 0.00010354651162790698, | |
| "loss": 0.0221, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.00010325581395348838, | |
| "loss": 0.0485, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 0.00010296511627906977, | |
| "loss": 0.019, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 0.00010267441860465117, | |
| "loss": 0.0875, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 0.00010238372093023256, | |
| "loss": 0.0138, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.00010209302325581395, | |
| "loss": 0.0346, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 0.00010180232558139535, | |
| "loss": 0.0312, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.00010151162790697675, | |
| "loss": 0.0086, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.00010122093023255815, | |
| "loss": 0.0697, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_accuracy": 0.7751479289940828, | |
| "eval_loss": 1.0387126207351685, | |
| "eval_runtime": 19.9298, | |
| "eval_samples_per_second": 84.797, | |
| "eval_steps_per_second": 10.637, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 0.00010093023255813953, | |
| "loss": 0.0371, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 0.00010063953488372093, | |
| "loss": 0.0061, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 0.00010034883720930233, | |
| "loss": 0.0104, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00010005813953488373, | |
| "loss": 0.0044, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.976744186046511e-05, | |
| "loss": 0.0053, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 9.947674418604651e-05, | |
| "loss": 0.0414, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.918604651162792e-05, | |
| "loss": 0.0037, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 9.889534883720932e-05, | |
| "loss": 0.0038, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.86046511627907e-05, | |
| "loss": 0.0328, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.83139534883721e-05, | |
| "loss": 0.0084, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "eval_accuracy": 0.7946745562130177, | |
| "eval_loss": 0.9440802335739136, | |
| "eval_runtime": 19.3002, | |
| "eval_samples_per_second": 87.564, | |
| "eval_steps_per_second": 10.984, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 9.80232558139535e-05, | |
| "loss": 0.0046, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 9.77325581395349e-05, | |
| "loss": 0.0036, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 9.744186046511629e-05, | |
| "loss": 0.0278, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 9.715116279069768e-05, | |
| "loss": 0.0034, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 9.686046511627907e-05, | |
| "loss": 0.013, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 9.656976744186047e-05, | |
| "loss": 0.0028, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 9.627906976744187e-05, | |
| "loss": 0.0039, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 9.598837209302327e-05, | |
| "loss": 0.0038, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 9.569767441860465e-05, | |
| "loss": 0.0039, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 9.540697674418605e-05, | |
| "loss": 0.0182, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "eval_accuracy": 0.7994082840236686, | |
| "eval_loss": 0.8966801166534424, | |
| "eval_runtime": 19.5928, | |
| "eval_samples_per_second": 86.256, | |
| "eval_steps_per_second": 10.82, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 9.511627906976745e-05, | |
| "loss": 0.0218, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 9.482558139534884e-05, | |
| "loss": 0.0056, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 9.453488372093023e-05, | |
| "loss": 0.0032, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 9.424418604651163e-05, | |
| "loss": 0.008, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 9.395348837209302e-05, | |
| "loss": 0.0024, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 9.366279069767442e-05, | |
| "loss": 0.0236, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 9.337209302325582e-05, | |
| "loss": 0.0335, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 9.308139534883722e-05, | |
| "loss": 0.0048, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 9.279069767441861e-05, | |
| "loss": 0.0046, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 9.250000000000001e-05, | |
| "loss": 0.0042, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "eval_accuracy": 0.8041420118343195, | |
| "eval_loss": 0.8750348687171936, | |
| "eval_runtime": 19.4025, | |
| "eval_samples_per_second": 87.102, | |
| "eval_steps_per_second": 10.926, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 9.220930232558141e-05, | |
| "loss": 0.0027, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 9.19186046511628e-05, | |
| "loss": 0.0092, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 9.162790697674419e-05, | |
| "loss": 0.0025, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 9.133720930232559e-05, | |
| "loss": 0.0128, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 9.104651162790699e-05, | |
| "loss": 0.0138, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 9.075581395348837e-05, | |
| "loss": 0.0084, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 9.046511627906977e-05, | |
| "loss": 0.0029, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 9.017441860465117e-05, | |
| "loss": 0.0031, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 8.988372093023256e-05, | |
| "loss": 0.0042, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 8.959302325581396e-05, | |
| "loss": 0.0028, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_accuracy": 0.8041420118343195, | |
| "eval_loss": 0.9348833560943604, | |
| "eval_runtime": 19.5336, | |
| "eval_samples_per_second": 86.517, | |
| "eval_steps_per_second": 10.853, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 8.930232558139535e-05, | |
| "loss": 0.0027, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 8.901162790697674e-05, | |
| "loss": 0.0021, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 8.872093023255814e-05, | |
| "loss": 0.0033, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 8.843023255813954e-05, | |
| "loss": 0.003, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 8.813953488372094e-05, | |
| "loss": 0.0029, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 8.784883720930232e-05, | |
| "loss": 0.0058, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 8.755813953488372e-05, | |
| "loss": 0.0613, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 8.726744186046512e-05, | |
| "loss": 0.0024, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 8.697674418604652e-05, | |
| "loss": 0.0471, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 8.668604651162791e-05, | |
| "loss": 0.0053, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "eval_accuracy": 0.7982248520710059, | |
| "eval_loss": 0.9403174519538879, | |
| "eval_runtime": 19.5345, | |
| "eval_samples_per_second": 86.514, | |
| "eval_steps_per_second": 10.853, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 8.639534883720931e-05, | |
| "loss": 0.0543, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 8.610465116279071e-05, | |
| "loss": 0.0378, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 8.58139534883721e-05, | |
| "loss": 0.0026, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 8.552325581395349e-05, | |
| "loss": 0.0189, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 8.523255813953489e-05, | |
| "loss": 0.0072, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 8.494186046511629e-05, | |
| "loss": 0.003, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 8.465116279069768e-05, | |
| "loss": 0.0039, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 8.436046511627908e-05, | |
| "loss": 0.0323, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 8.406976744186047e-05, | |
| "loss": 0.0028, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 8.377906976744186e-05, | |
| "loss": 0.0266, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_accuracy": 0.7958579881656804, | |
| "eval_loss": 0.99658203125, | |
| "eval_runtime": 19.397, | |
| "eval_samples_per_second": 87.127, | |
| "eval_steps_per_second": 10.93, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 8.348837209302326e-05, | |
| "loss": 0.0059, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 8.319767441860466e-05, | |
| "loss": 0.0022, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 8.290697674418604e-05, | |
| "loss": 0.0097, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 8.261627906976744e-05, | |
| "loss": 0.0239, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 8.232558139534884e-05, | |
| "loss": 0.0024, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 8.203488372093024e-05, | |
| "loss": 0.0051, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 8.174418604651163e-05, | |
| "loss": 0.0022, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 8.145348837209302e-05, | |
| "loss": 0.0103, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 8.116279069767442e-05, | |
| "loss": 0.0019, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 8.087209302325581e-05, | |
| "loss": 0.0022, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_accuracy": 0.8017751479289941, | |
| "eval_loss": 0.9471782445907593, | |
| "eval_runtime": 19.5879, | |
| "eval_samples_per_second": 86.278, | |
| "eval_steps_per_second": 10.823, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 8.058139534883722e-05, | |
| "loss": 0.0071, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 8.029069767441861e-05, | |
| "loss": 0.0027, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0022, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 7.97093023255814e-05, | |
| "loss": 0.0027, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 7.94186046511628e-05, | |
| "loss": 0.0019, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 7.912790697674419e-05, | |
| "loss": 0.0061, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 7.883720930232558e-05, | |
| "loss": 0.002, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 7.854651162790698e-05, | |
| "loss": 0.0048, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 7.825581395348838e-05, | |
| "loss": 0.0126, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 7.796511627906978e-05, | |
| "loss": 0.0018, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "eval_accuracy": 0.8136094674556213, | |
| "eval_loss": 0.8716549873352051, | |
| "eval_runtime": 19.5631, | |
| "eval_samples_per_second": 86.387, | |
| "eval_steps_per_second": 10.837, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 7.767441860465116e-05, | |
| "loss": 0.0016, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 7.738372093023256e-05, | |
| "loss": 0.0018, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 7.709302325581396e-05, | |
| "loss": 0.0052, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.680232558139535e-05, | |
| "loss": 0.0017, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 7.651162790697675e-05, | |
| "loss": 0.0307, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 7.622093023255814e-05, | |
| "loss": 0.0037, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 7.593023255813953e-05, | |
| "loss": 0.028, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 7.563953488372093e-05, | |
| "loss": 0.0055, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 7.534883720930233e-05, | |
| "loss": 0.0021, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.505813953488371e-05, | |
| "loss": 0.0018, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.808284023668639, | |
| "eval_loss": 0.8963714241981506, | |
| "eval_runtime": 19.5353, | |
| "eval_samples_per_second": 86.51, | |
| "eval_steps_per_second": 10.852, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 7.476744186046511e-05, | |
| "loss": 0.0015, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 7.447674418604651e-05, | |
| "loss": 0.0016, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 7.418604651162792e-05, | |
| "loss": 0.0014, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 7.38953488372093e-05, | |
| "loss": 0.0015, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 7.36046511627907e-05, | |
| "loss": 0.002, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 7.33139534883721e-05, | |
| "loss": 0.0018, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 7.30232558139535e-05, | |
| "loss": 0.0014, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 7.27325581395349e-05, | |
| "loss": 0.0014, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 7.244186046511628e-05, | |
| "loss": 0.0012, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 7.215116279069768e-05, | |
| "loss": 0.0046, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "eval_accuracy": 0.8159763313609467, | |
| "eval_loss": 0.8622729182243347, | |
| "eval_runtime": 19.8545, | |
| "eval_samples_per_second": 85.119, | |
| "eval_steps_per_second": 10.678, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 7.186046511627908e-05, | |
| "loss": 0.0014, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 7.156976744186047e-05, | |
| "loss": 0.0017, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 7.127906976744186e-05, | |
| "loss": 0.0026, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 7.098837209302326e-05, | |
| "loss": 0.0014, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 7.069767441860465e-05, | |
| "loss": 0.0015, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 7.040697674418605e-05, | |
| "loss": 0.0013, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 7.011627906976745e-05, | |
| "loss": 0.0021, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 6.982558139534883e-05, | |
| "loss": 0.0021, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 6.953488372093023e-05, | |
| "loss": 0.004, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "learning_rate": 6.924418604651163e-05, | |
| "loss": 0.0037, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 10.47, | |
| "eval_accuracy": 0.8171597633136095, | |
| "eval_loss": 0.8762088418006897, | |
| "eval_runtime": 19.4119, | |
| "eval_samples_per_second": 87.06, | |
| "eval_steps_per_second": 10.921, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 6.895348837209303e-05, | |
| "loss": 0.0013, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 6.866279069767442e-05, | |
| "loss": 0.0015, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 6.837209302325581e-05, | |
| "loss": 0.0014, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 6.808139534883722e-05, | |
| "loss": 0.0014, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 10.58, | |
| "learning_rate": 6.779069767441862e-05, | |
| "loss": 0.0014, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 6.750000000000001e-05, | |
| "loss": 0.0013, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 10.63, | |
| "learning_rate": 6.72093023255814e-05, | |
| "loss": 0.0148, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 6.69186046511628e-05, | |
| "loss": 0.0013, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 6.66279069767442e-05, | |
| "loss": 0.0012, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 6.633720930232559e-05, | |
| "loss": 0.0013, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "eval_accuracy": 0.8142011834319527, | |
| "eval_loss": 0.9028135538101196, | |
| "eval_runtime": 19.6824, | |
| "eval_samples_per_second": 85.863, | |
| "eval_steps_per_second": 10.771, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 6.604651162790698e-05, | |
| "loss": 0.0014, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 10.74, | |
| "learning_rate": 6.575581395348837e-05, | |
| "loss": 0.0015, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 6.546511627906977e-05, | |
| "loss": 0.0013, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 6.517441860465117e-05, | |
| "loss": 0.0013, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 6.488372093023257e-05, | |
| "loss": 0.0342, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 6.459302325581395e-05, | |
| "loss": 0.0013, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 6.430232558139535e-05, | |
| "loss": 0.0054, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 6.401162790697675e-05, | |
| "loss": 0.0044, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 6.372093023255814e-05, | |
| "loss": 0.0012, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 6.343023255813953e-05, | |
| "loss": 0.0013, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "eval_accuracy": 0.8177514792899409, | |
| "eval_loss": 0.9084253311157227, | |
| "eval_runtime": 19.8763, | |
| "eval_samples_per_second": 85.026, | |
| "eval_steps_per_second": 10.666, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 6.313953488372093e-05, | |
| "loss": 0.023, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 6.284883720930232e-05, | |
| "loss": 0.0012, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 6.255813953488372e-05, | |
| "loss": 0.002, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 6.226744186046512e-05, | |
| "loss": 0.0012, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 6.19767441860465e-05, | |
| "loss": 0.0011, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 6.168604651162791e-05, | |
| "loss": 0.0012, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 6.139534883720931e-05, | |
| "loss": 0.0011, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 6.110465116279071e-05, | |
| "loss": 0.001, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 6.08139534883721e-05, | |
| "loss": 0.0242, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 6.052325581395349e-05, | |
| "loss": 0.0013, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "eval_accuracy": 0.821301775147929, | |
| "eval_loss": 0.8732948899269104, | |
| "eval_runtime": 19.32, | |
| "eval_samples_per_second": 87.474, | |
| "eval_steps_per_second": 10.973, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 6.023255813953489e-05, | |
| "loss": 0.0022, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 5.994186046511628e-05, | |
| "loss": 0.002, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 5.965116279069768e-05, | |
| "loss": 0.0012, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 5.9360465116279077e-05, | |
| "loss": 0.0014, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 5.906976744186047e-05, | |
| "loss": 0.0014, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 5.8779069767441865e-05, | |
| "loss": 0.001, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 11.33, | |
| "learning_rate": 5.8488372093023256e-05, | |
| "loss": 0.0011, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 5.8197674418604654e-05, | |
| "loss": 0.0011, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 5.7906976744186045e-05, | |
| "loss": 0.001, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 5.761627906976744e-05, | |
| "loss": 0.001, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "eval_accuracy": 0.8207100591715977, | |
| "eval_loss": 0.8823328614234924, | |
| "eval_runtime": 19.5982, | |
| "eval_samples_per_second": 86.232, | |
| "eval_steps_per_second": 10.817, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 5.732558139534884e-05, | |
| "loss": 0.0011, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 5.703488372093023e-05, | |
| "loss": 0.0012, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 5.674418604651163e-05, | |
| "loss": 0.001, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 5.645348837209302e-05, | |
| "loss": 0.0012, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 5.616279069767442e-05, | |
| "loss": 0.001, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 5.587209302325581e-05, | |
| "loss": 0.0013, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 5.558139534883722e-05, | |
| "loss": 0.0011, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 5.529069767441861e-05, | |
| "loss": 0.001, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.001, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "learning_rate": 5.47093023255814e-05, | |
| "loss": 0.0009, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 11.63, | |
| "eval_accuracy": 0.821301775147929, | |
| "eval_loss": 0.8768606781959534, | |
| "eval_runtime": 19.504, | |
| "eval_samples_per_second": 86.649, | |
| "eval_steps_per_second": 10.87, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 5.44186046511628e-05, | |
| "loss": 0.001, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 5.412790697674419e-05, | |
| "loss": 0.0011, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 5.3837209302325586e-05, | |
| "loss": 0.0011, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 5.3546511627906984e-05, | |
| "loss": 0.001, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 5.3255813953488375e-05, | |
| "loss": 0.001, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 5.296511627906977e-05, | |
| "loss": 0.0009, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 5.2674418604651164e-05, | |
| "loss": 0.001, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 5.238372093023256e-05, | |
| "loss": 0.0056, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 5.209302325581395e-05, | |
| "loss": 0.0009, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 5.180232558139535e-05, | |
| "loss": 0.0282, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "eval_accuracy": 0.8218934911242604, | |
| "eval_loss": 0.8791326284408569, | |
| "eval_runtime": 19.8353, | |
| "eval_samples_per_second": 85.202, | |
| "eval_steps_per_second": 10.688, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 5.151162790697675e-05, | |
| "loss": 0.0014, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 5.122093023255814e-05, | |
| "loss": 0.0443, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 11.93, | |
| "learning_rate": 5.0930232558139536e-05, | |
| "loss": 0.001, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 5.063953488372093e-05, | |
| "loss": 0.0009, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 5.0348837209302325e-05, | |
| "loss": 0.0009, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.0058139534883716e-05, | |
| "loss": 0.0011, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.976744186046512e-05, | |
| "loss": 0.0009, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 4.947674418604651e-05, | |
| "loss": 0.001, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 4.918604651162791e-05, | |
| "loss": 0.001, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 4.889534883720931e-05, | |
| "loss": 0.001, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "eval_accuracy": 0.8248520710059172, | |
| "eval_loss": 0.8673256635665894, | |
| "eval_runtime": 19.9585, | |
| "eval_samples_per_second": 84.676, | |
| "eval_steps_per_second": 10.622, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 4.86046511627907e-05, | |
| "loss": 0.001, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 4.8313953488372096e-05, | |
| "loss": 0.0009, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 4.802325581395349e-05, | |
| "loss": 0.0009, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 12.19, | |
| "learning_rate": 4.773255813953489e-05, | |
| "loss": 0.0009, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 4.744186046511628e-05, | |
| "loss": 0.0009, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 4.715116279069768e-05, | |
| "loss": 0.0048, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 4.686046511627907e-05, | |
| "loss": 0.001, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "learning_rate": 4.656976744186047e-05, | |
| "loss": 0.001, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 4.627906976744186e-05, | |
| "loss": 0.001, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 4.598837209302326e-05, | |
| "loss": 0.0016, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "eval_accuracy": 0.8224852071005917, | |
| "eval_loss": 0.8632799386978149, | |
| "eval_runtime": 19.7371, | |
| "eval_samples_per_second": 85.625, | |
| "eval_steps_per_second": 10.741, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 4.5697674418604655e-05, | |
| "loss": 0.0009, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 4.5406976744186046e-05, | |
| "loss": 0.001, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.5116279069767444e-05, | |
| "loss": 0.0009, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 4.4825581395348835e-05, | |
| "loss": 0.0009, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 4.453488372093024e-05, | |
| "loss": 0.0009, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 12.47, | |
| "learning_rate": 4.424418604651163e-05, | |
| "loss": 0.0009, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 4.395348837209303e-05, | |
| "loss": 0.0181, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 4.366279069767442e-05, | |
| "loss": 0.0009, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 4.337209302325582e-05, | |
| "loss": 0.0008, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 4.3081395348837214e-05, | |
| "loss": 0.0008, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "eval_accuracy": 0.8195266272189349, | |
| "eval_loss": 0.876582145690918, | |
| "eval_runtime": 19.7438, | |
| "eval_samples_per_second": 85.596, | |
| "eval_steps_per_second": 10.738, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 12.58, | |
| "learning_rate": 4.2790697674418605e-05, | |
| "loss": 0.0009, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.0008, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 4.2209302325581394e-05, | |
| "loss": 0.0009, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 4.191860465116279e-05, | |
| "loss": 0.0014, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 4.162790697674418e-05, | |
| "loss": 0.0008, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 4.133720930232559e-05, | |
| "loss": 0.0009, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 4.104651162790698e-05, | |
| "loss": 0.0008, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "learning_rate": 4.0755813953488376e-05, | |
| "loss": 0.0008, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 4.046511627906977e-05, | |
| "loss": 0.0008, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "learning_rate": 4.0174418604651165e-05, | |
| "loss": 0.0008, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 12.79, | |
| "eval_accuracy": 0.8224852071005917, | |
| "eval_loss": 0.8743496537208557, | |
| "eval_runtime": 19.5102, | |
| "eval_samples_per_second": 86.621, | |
| "eval_steps_per_second": 10.866, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 3.988372093023256e-05, | |
| "loss": 0.0008, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 3.959302325581395e-05, | |
| "loss": 0.0008, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 3.930232558139535e-05, | |
| "loss": 0.0008, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 3.901162790697674e-05, | |
| "loss": 0.0008, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 3.872093023255814e-05, | |
| "loss": 0.0008, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 3.843023255813954e-05, | |
| "loss": 0.001, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 3.8139534883720935e-05, | |
| "loss": 0.0008, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 3.7848837209302326e-05, | |
| "loss": 0.0008, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.7558139534883724e-05, | |
| "loss": 0.0008, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.726744186046512e-05, | |
| "loss": 0.0008, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_accuracy": 0.823076923076923, | |
| "eval_loss": 0.875207245349884, | |
| "eval_runtime": 19.8654, | |
| "eval_samples_per_second": 85.073, | |
| "eval_steps_per_second": 10.672, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 3.697674418604651e-05, | |
| "loss": 0.0008, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 3.668604651162791e-05, | |
| "loss": 0.0008, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 3.63953488372093e-05, | |
| "loss": 0.0022, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.61046511627907e-05, | |
| "loss": 0.0007, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 3.581395348837209e-05, | |
| "loss": 0.0008, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 3.552325581395349e-05, | |
| "loss": 0.0014, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 3.5232558139534886e-05, | |
| "loss": 0.0008, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 3.494186046511628e-05, | |
| "loss": 0.0007, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 3.465116279069768e-05, | |
| "loss": 0.015, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 3.436046511627907e-05, | |
| "loss": 0.0008, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "eval_accuracy": 0.8236686390532545, | |
| "eval_loss": 0.8675829172134399, | |
| "eval_runtime": 20.0005, | |
| "eval_samples_per_second": 84.498, | |
| "eval_steps_per_second": 10.6, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 3.406976744186047e-05, | |
| "loss": 0.0008, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 3.377906976744186e-05, | |
| "loss": 0.0008, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.348837209302326e-05, | |
| "loss": 0.0008, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "learning_rate": 3.319767441860465e-05, | |
| "loss": 0.0007, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 13.37, | |
| "learning_rate": 3.290697674418605e-05, | |
| "loss": 0.0008, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 3.261627906976744e-05, | |
| "loss": 0.0008, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 3.2325581395348836e-05, | |
| "loss": 0.0008, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.2034883720930234e-05, | |
| "loss": 0.0007, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 3.174418604651163e-05, | |
| "loss": 0.0008, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "learning_rate": 3.145348837209303e-05, | |
| "loss": 0.0007, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 13.49, | |
| "eval_accuracy": 0.8236686390532545, | |
| "eval_loss": 0.8677453994750977, | |
| "eval_runtime": 20.9181, | |
| "eval_samples_per_second": 80.791, | |
| "eval_steps_per_second": 10.135, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 3.116279069767442e-05, | |
| "loss": 0.0008, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 3.087209302325582e-05, | |
| "loss": 0.0008, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 3.058139534883721e-05, | |
| "loss": 0.0007, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 3.0290697674418606e-05, | |
| "loss": 0.0008, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0009, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 2.9709302325581395e-05, | |
| "loss": 0.0007, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "learning_rate": 2.941860465116279e-05, | |
| "loss": 0.0008, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 2.9127906976744184e-05, | |
| "loss": 0.0007, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 2.8837209302325585e-05, | |
| "loss": 0.0007, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 2.854651162790698e-05, | |
| "loss": 0.0008, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "eval_accuracy": 0.8236686390532545, | |
| "eval_loss": 0.8702542781829834, | |
| "eval_runtime": 19.5203, | |
| "eval_samples_per_second": 86.577, | |
| "eval_steps_per_second": 10.86, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 2.8255813953488374e-05, | |
| "loss": 0.0007, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 2.7965116279069768e-05, | |
| "loss": 0.0007, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 13.79, | |
| "learning_rate": 2.7674418604651166e-05, | |
| "loss": 0.0008, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 2.738372093023256e-05, | |
| "loss": 0.0007, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "learning_rate": 2.7093023255813954e-05, | |
| "loss": 0.0007, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "learning_rate": 2.680232558139535e-05, | |
| "loss": 0.0007, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 2.6511627906976743e-05, | |
| "loss": 0.0007, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 2.6220930232558137e-05, | |
| "loss": 0.0007, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 2.593023255813954e-05, | |
| "loss": 0.0008, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 2.5639534883720933e-05, | |
| "loss": 0.0007, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "eval_accuracy": 0.8236686390532545, | |
| "eval_loss": 0.8725163340568542, | |
| "eval_runtime": 20.0258, | |
| "eval_samples_per_second": 84.391, | |
| "eval_steps_per_second": 10.586, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 2.5348837209302327e-05, | |
| "loss": 0.0007, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 2.5058139534883725e-05, | |
| "loss": 0.0007, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 2.476744186046512e-05, | |
| "loss": 0.0007, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 2.4476744186046514e-05, | |
| "loss": 0.0007, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 2.4186046511627908e-05, | |
| "loss": 0.0007, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 2.3895348837209302e-05, | |
| "loss": 0.0007, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 2.3604651162790697e-05, | |
| "loss": 0.0007, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 2.3313953488372095e-05, | |
| "loss": 0.0007, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 14.16, | |
| "learning_rate": 2.302325581395349e-05, | |
| "loss": 0.0008, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 2.2732558139534883e-05, | |
| "loss": 0.0006, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "eval_accuracy": 0.823076923076923, | |
| "eval_loss": 0.8740601539611816, | |
| "eval_runtime": 19.4221, | |
| "eval_samples_per_second": 87.014, | |
| "eval_steps_per_second": 10.915, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 2.244186046511628e-05, | |
| "loss": 0.0007, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 14.23, | |
| "learning_rate": 2.2151162790697675e-05, | |
| "loss": 0.0007, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 2.1860465116279073e-05, | |
| "loss": 0.0007, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 14.28, | |
| "learning_rate": 2.1569767441860467e-05, | |
| "loss": 0.0007, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 2.1279069767441862e-05, | |
| "loss": 0.0007, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 2.0988372093023256e-05, | |
| "loss": 0.0007, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 2.069767441860465e-05, | |
| "loss": 0.0007, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 2.0406976744186048e-05, | |
| "loss": 0.0007, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.0116279069767443e-05, | |
| "loss": 0.0006, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 1.9825581395348837e-05, | |
| "loss": 0.0006, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "eval_accuracy": 0.8236686390532545, | |
| "eval_loss": 0.8757566809654236, | |
| "eval_runtime": 19.9623, | |
| "eval_samples_per_second": 84.66, | |
| "eval_steps_per_second": 10.62, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 1.9534883720930235e-05, | |
| "loss": 0.0007, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 1.924418604651163e-05, | |
| "loss": 0.0007, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 14.49, | |
| "learning_rate": 1.8953488372093023e-05, | |
| "loss": 0.0034, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 1.866279069767442e-05, | |
| "loss": 0.0007, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 14.53, | |
| "learning_rate": 1.8372093023255815e-05, | |
| "loss": 0.0008, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 1.808139534883721e-05, | |
| "loss": 0.0007, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 1.7790697674418604e-05, | |
| "loss": 0.0007, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.0007, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 1.7209302325581396e-05, | |
| "loss": 0.0007, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 1.691860465116279e-05, | |
| "loss": 0.0008, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "eval_accuracy": 0.8242603550295858, | |
| "eval_loss": 0.8745740056037903, | |
| "eval_runtime": 19.6178, | |
| "eval_samples_per_second": 86.146, | |
| "eval_steps_per_second": 10.807, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 1.6627906976744188e-05, | |
| "loss": 0.0007, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 1.6337209302325583e-05, | |
| "loss": 0.0007, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 1.6046511627906977e-05, | |
| "loss": 0.0012, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 1.5755813953488375e-05, | |
| "loss": 0.0006, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 14.77, | |
| "learning_rate": 1.546511627906977e-05, | |
| "loss": 0.0006, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 1.5174418604651163e-05, | |
| "loss": 0.0007, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 1.488372093023256e-05, | |
| "loss": 0.0007, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 1.4593023255813954e-05, | |
| "loss": 0.0007, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 1.4302325581395348e-05, | |
| "loss": 0.0007, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 1.4011627906976746e-05, | |
| "loss": 0.0007, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "eval_accuracy": 0.8242603550295858, | |
| "eval_loss": 0.8759431838989258, | |
| "eval_runtime": 20.1834, | |
| "eval_samples_per_second": 83.732, | |
| "eval_steps_per_second": 10.504, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 1.372093023255814e-05, | |
| "loss": 0.0007, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 1.3430232558139536e-05, | |
| "loss": 0.0007, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 1.313953488372093e-05, | |
| "loss": 0.0007, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "learning_rate": 1.2848837209302325e-05, | |
| "loss": 0.0103, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.2558139534883723e-05, | |
| "loss": 0.0006, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 1.2267441860465115e-05, | |
| "loss": 0.0006, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 1.1976744186046513e-05, | |
| "loss": 0.0007, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 1.1686046511627907e-05, | |
| "loss": 0.0007, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 1.1395348837209304e-05, | |
| "loss": 0.0006, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 15.12, | |
| "learning_rate": 1.1104651162790698e-05, | |
| "loss": 0.0007, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 15.12, | |
| "eval_accuracy": 0.823076923076923, | |
| "eval_loss": 0.8802584409713745, | |
| "eval_runtime": 20.3293, | |
| "eval_samples_per_second": 83.131, | |
| "eval_steps_per_second": 10.428, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 1.0813953488372092e-05, | |
| "loss": 0.0007, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 1.052325581395349e-05, | |
| "loss": 0.0006, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 1.0232558139534884e-05, | |
| "loss": 0.0006, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 15.21, | |
| "learning_rate": 9.941860465116279e-06, | |
| "loss": 0.0006, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 9.651162790697675e-06, | |
| "loss": 0.0006, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 9.360465116279069e-06, | |
| "loss": 0.0008, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 9.069767441860467e-06, | |
| "loss": 0.0007, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 8.779069767441861e-06, | |
| "loss": 0.0006, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 8.488372093023256e-06, | |
| "loss": 0.0007, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 8.197674418604652e-06, | |
| "loss": 0.0007, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "eval_accuracy": 0.8236686390532545, | |
| "eval_loss": 0.8807607293128967, | |
| "eval_runtime": 20.1768, | |
| "eval_samples_per_second": 83.76, | |
| "eval_steps_per_second": 10.507, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 7.906976744186048e-06, | |
| "loss": 0.0007, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 7.616279069767442e-06, | |
| "loss": 0.0006, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 7.325581395348838e-06, | |
| "loss": 0.0007, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 7.034883720930232e-06, | |
| "loss": 0.0006, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 6.744186046511629e-06, | |
| "loss": 0.0045, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 6.453488372093024e-06, | |
| "loss": 0.0007, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 15.51, | |
| "learning_rate": 6.162790697674419e-06, | |
| "loss": 0.0006, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 5.872093023255814e-06, | |
| "loss": 0.0006, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 5.581395348837209e-06, | |
| "loss": 0.0006, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 5.290697674418605e-06, | |
| "loss": 0.0007, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "eval_accuracy": 0.8242603550295858, | |
| "eval_loss": 0.8798006772994995, | |
| "eval_runtime": 19.5473, | |
| "eval_samples_per_second": 86.457, | |
| "eval_steps_per_second": 10.846, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0006, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 4.709302325581396e-06, | |
| "loss": 0.0006, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 4.418604651162791e-06, | |
| "loss": 0.0006, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 15.67, | |
| "learning_rate": 4.127906976744186e-06, | |
| "loss": 0.0007, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 3.837209302325582e-06, | |
| "loss": 0.0006, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 15.72, | |
| "learning_rate": 3.546511627906977e-06, | |
| "loss": 0.0006, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 3.255813953488372e-06, | |
| "loss": 0.0006, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 15.77, | |
| "learning_rate": 2.9651162790697676e-06, | |
| "loss": 0.0011, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 2.674418604651163e-06, | |
| "loss": 0.0069, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 2.3837209302325585e-06, | |
| "loss": 0.0007, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "eval_accuracy": 0.8242603550295858, | |
| "eval_loss": 0.8805208206176758, | |
| "eval_runtime": 20.2245, | |
| "eval_samples_per_second": 83.562, | |
| "eval_steps_per_second": 10.482, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.0930232558139536e-06, | |
| "loss": 0.0006, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 1.802325581395349e-06, | |
| "loss": 0.0007, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 1.5116279069767443e-06, | |
| "loss": 0.0006, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 1.2209302325581397e-06, | |
| "loss": 0.0007, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 9.30232558139535e-07, | |
| "loss": 0.0007, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 6.395348837209303e-07, | |
| "loss": 0.0006, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 3.4883720930232557e-07, | |
| "loss": 0.0007, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.8139534883720935e-08, | |
| "loss": 0.0006, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "step": 6880, | |
| "total_flos": 8.541557034744545e+18, | |
| "train_loss": 0.3646200400029937, | |
| "train_runtime": 4032.5455, | |
| "train_samples_per_second": 27.298, | |
| "train_steps_per_second": 1.706 | |
| } | |
| ], | |
| "max_steps": 6880, | |
| "num_train_epochs": 16, | |
| "total_flos": 8.541557034744545e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |