| { | |
| "best_metric": 0.051206715404987335, | |
| "best_model_checkpoint": "./egujr001-swim2-base-model/checkpoint-5700", | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 7782, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.418485237483954e-07, | |
| "loss": 0.711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.2836970474967908e-06, | |
| "loss": 0.7059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.8613607188703468e-06, | |
| "loss": 0.6897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.503209242618742e-06, | |
| "loss": 0.7061, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.1450577663671376e-06, | |
| "loss": 0.6902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.7869062901155326e-06, | |
| "loss": 0.6769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.428754813863929e-06, | |
| "loss": 0.6704, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.0706033376123234e-06, | |
| "loss": 0.6682, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.71245186136072e-06, | |
| "loss": 0.6452, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.354300385109114e-06, | |
| "loss": 0.6254, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.7049961441004737, | |
| "eval_loss": 0.584004282951355, | |
| "eval_runtime": 88.2264, | |
| "eval_samples_per_second": 411.532, | |
| "eval_steps_per_second": 6.438, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.99614890885751e-06, | |
| "loss": 0.5976, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.637997432605905e-06, | |
| "loss": 0.561, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.2798459563543e-06, | |
| "loss": 0.5638, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.921694480102696e-06, | |
| "loss": 0.5135, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.563543003851091e-06, | |
| "loss": 0.4949, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.0205391527599487e-05, | |
| "loss": 0.4596, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.0847240051347884e-05, | |
| "loss": 0.4655, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.1489088575096278e-05, | |
| "loss": 0.4333, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.2130937098844673e-05, | |
| "loss": 0.4324, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.277278562259307e-05, | |
| "loss": 0.3998, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8506665197752561, | |
| "eval_loss": 0.35248830914497375, | |
| "eval_runtime": 90.26, | |
| "eval_samples_per_second": 402.26, | |
| "eval_steps_per_second": 6.293, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.3414634146341466e-05, | |
| "loss": 0.3763, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.405648267008986e-05, | |
| "loss": 0.3491, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4698331193838255e-05, | |
| "loss": 0.3078, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.534017971758665e-05, | |
| "loss": 0.3124, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.5982028241335045e-05, | |
| "loss": 0.3281, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.662387676508344e-05, | |
| "loss": 0.2936, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7265725288831836e-05, | |
| "loss": 0.3083, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.7907573812580232e-05, | |
| "loss": 0.2861, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8549422336328627e-05, | |
| "loss": 0.287, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9191270860077023e-05, | |
| "loss": 0.2796, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.8974881568800265, | |
| "eval_loss": 0.27103182673454285, | |
| "eval_runtime": 91.5194, | |
| "eval_samples_per_second": 396.724, | |
| "eval_steps_per_second": 6.206, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9833119383825418e-05, | |
| "loss": 0.2846, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.0474967907573813e-05, | |
| "loss": 0.243, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.111681643132221e-05, | |
| "loss": 0.2676, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.1758664955070604e-05, | |
| "loss": 0.2768, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.2400513478819e-05, | |
| "loss": 0.2324, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.3042362002567395e-05, | |
| "loss": 0.2318, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.24, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.4326059050064186e-05, | |
| "loss": 0.2268, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.496790757381258e-05, | |
| "loss": 0.2416, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.5609756097560977e-05, | |
| "loss": 0.23, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.9012338878484081, | |
| "eval_loss": 0.26600146293640137, | |
| "eval_runtime": 89.74, | |
| "eval_samples_per_second": 404.591, | |
| "eval_steps_per_second": 6.329, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.6251604621309372e-05, | |
| "loss": 0.2158, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.6893453145057767e-05, | |
| "loss": 0.2284, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.7535301668806163e-05, | |
| "loss": 0.2321, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.817715019255456e-05, | |
| "loss": 0.25, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.8818998716302954e-05, | |
| "loss": 0.196, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.946084724005135e-05, | |
| "loss": 0.2326, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.0102695763799745e-05, | |
| "loss": 0.2762, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.074454428754814e-05, | |
| "loss": 0.189, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.138639281129653e-05, | |
| "loss": 0.1907, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.202824133504493e-05, | |
| "loss": 0.2372, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.9400958466453674, | |
| "eval_loss": 0.1678195595741272, | |
| "eval_runtime": 91.7573, | |
| "eval_samples_per_second": 395.696, | |
| "eval_steps_per_second": 6.19, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.267008985879333e-05, | |
| "loss": 0.2145, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.331193838254172e-05, | |
| "loss": 0.175, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.395378690629012e-05, | |
| "loss": 0.1979, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.459563543003851e-05, | |
| "loss": 0.186, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.523748395378691e-05, | |
| "loss": 0.2302, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.58793324775353e-05, | |
| "loss": 0.2083, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.65211810012837e-05, | |
| "loss": 0.2225, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.7163029525032094e-05, | |
| "loss": 0.1781, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.780487804878049e-05, | |
| "loss": 0.2095, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.8446726572528885e-05, | |
| "loss": 0.1944, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.9436763247769087, | |
| "eval_loss": 0.14370502531528473, | |
| "eval_runtime": 90.007, | |
| "eval_samples_per_second": 403.391, | |
| "eval_steps_per_second": 6.311, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.908857509627728e-05, | |
| "loss": 0.1954, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.9730423620025676e-05, | |
| "loss": 0.1709, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.037227214377407e-05, | |
| "loss": 0.1922, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.1014120667522467e-05, | |
| "loss": 0.1943, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.165596919127086e-05, | |
| "loss": 0.1818, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.229781771501926e-05, | |
| "loss": 0.1745, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.293966623876765e-05, | |
| "loss": 0.1946, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.358151476251605e-05, | |
| "loss": 0.1564, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.422336328626445e-05, | |
| "loss": 0.1876, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.486521181001284e-05, | |
| "loss": 0.1635, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.9503415225294701, | |
| "eval_loss": 0.12306568771600723, | |
| "eval_runtime": 89.7748, | |
| "eval_samples_per_second": 404.434, | |
| "eval_steps_per_second": 6.327, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.550706033376124e-05, | |
| "loss": 0.1233, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.614890885750963e-05, | |
| "loss": 0.1472, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.679075738125803e-05, | |
| "loss": 0.1953, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.743260590500642e-05, | |
| "loss": 0.1362, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.807445442875482e-05, | |
| "loss": 0.1533, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.871630295250321e-05, | |
| "loss": 0.1558, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.935815147625161e-05, | |
| "loss": 0.1675, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1529, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.993574182493217e-05, | |
| "loss": 0.1325, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.986434385263459e-05, | |
| "loss": 0.1463, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.9550512283794205, | |
| "eval_loss": 0.13529589772224426, | |
| "eval_runtime": 89.295, | |
| "eval_samples_per_second": 406.607, | |
| "eval_steps_per_second": 6.361, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.9792945880337e-05, | |
| "loss": 0.1664, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.9721547908039415e-05, | |
| "loss": 0.1442, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.965014993574183e-05, | |
| "loss": 0.1237, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.957875196344424e-05, | |
| "loss": 0.1159, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.9507353991146656e-05, | |
| "loss": 0.1144, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.9435956018849063e-05, | |
| "loss": 0.1478, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.936455804655148e-05, | |
| "loss": 0.1481, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.929316007425389e-05, | |
| "loss": 0.1433, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.922176210195631e-05, | |
| "loss": 0.1532, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.915036412965872e-05, | |
| "loss": 0.1287, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.952297014432081, | |
| "eval_loss": 0.1216319128870964, | |
| "eval_runtime": 90.7733, | |
| "eval_samples_per_second": 399.985, | |
| "eval_steps_per_second": 6.257, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.907896615736113e-05, | |
| "loss": 0.121, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.900756818506355e-05, | |
| "loss": 0.1014, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.893617021276596e-05, | |
| "loss": 0.1354, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.886477224046837e-05, | |
| "loss": 0.1335, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.879337426817079e-05, | |
| "loss": 0.171, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.87219762958732e-05, | |
| "loss": 0.1669, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.865057832357561e-05, | |
| "loss": 0.1554, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.8579180351278024e-05, | |
| "loss": 0.1473, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.850778237898044e-05, | |
| "loss": 0.1604, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.843638440668285e-05, | |
| "loss": 0.1208, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.9351382615401564, | |
| "eval_loss": 0.16954024136066437, | |
| "eval_runtime": 89.8639, | |
| "eval_samples_per_second": 404.033, | |
| "eval_steps_per_second": 6.321, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.8364986434385265e-05, | |
| "loss": 0.1427, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.829358846208768e-05, | |
| "loss": 0.107, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.822219048979009e-05, | |
| "loss": 0.1294, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.815079251749251e-05, | |
| "loss": 0.2427, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.8079394545194914e-05, | |
| "loss": 0.1689, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.8007996572897335e-05, | |
| "loss": 0.1436, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.793659860059975e-05, | |
| "loss": 0.1405, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.7865200628302156e-05, | |
| "loss": 0.1287, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.779380265600457e-05, | |
| "loss": 0.1217, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.7722404683706984e-05, | |
| "loss": 0.1204, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9556846975873086, | |
| "eval_loss": 0.12210479378700256, | |
| "eval_runtime": 90.877, | |
| "eval_samples_per_second": 399.529, | |
| "eval_steps_per_second": 6.25, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.76510067114094e-05, | |
| "loss": 0.1352, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.757960873911181e-05, | |
| "loss": 0.123, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.7508210766814225e-05, | |
| "loss": 0.1501, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.743681279451664e-05, | |
| "loss": 0.0773, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.736541482221905e-05, | |
| "loss": 0.0918, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.729401684992146e-05, | |
| "loss": 0.1164, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.7222618877623874e-05, | |
| "loss": 0.1187, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.7151220905326295e-05, | |
| "loss": 0.1071, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.707982293302871e-05, | |
| "loss": 0.1083, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.7008424960731116e-05, | |
| "loss": 0.1064, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.943208108405861, | |
| "eval_loss": 0.16051389276981354, | |
| "eval_runtime": 93.1274, | |
| "eval_samples_per_second": 389.874, | |
| "eval_steps_per_second": 6.099, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.693702698843353e-05, | |
| "loss": 0.1056, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.6865629016135944e-05, | |
| "loss": 0.1037, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.679423104383836e-05, | |
| "loss": 0.1151, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.672283307154077e-05, | |
| "loss": 0.1338, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.6651435099243185e-05, | |
| "loss": 0.1088, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.65800371269456e-05, | |
| "loss": 0.1323, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.6508639154648007e-05, | |
| "loss": 0.1391, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.643724118235042e-05, | |
| "loss": 0.0913, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.636584321005284e-05, | |
| "loss": 0.1233, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.6294445237755255e-05, | |
| "loss": 0.1114, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.961303294039881, | |
| "eval_loss": 0.09980010241270065, | |
| "eval_runtime": 91.0363, | |
| "eval_samples_per_second": 398.83, | |
| "eval_steps_per_second": 6.239, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.622304726545766e-05, | |
| "loss": 0.1039, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.6151649293160076e-05, | |
| "loss": 0.1265, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.608025132086249e-05, | |
| "loss": 0.0831, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.6008853348564904e-05, | |
| "loss": 0.0948, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.593745537626732e-05, | |
| "loss": 0.12, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.586605740396973e-05, | |
| "loss": 0.0904, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.5794659431672146e-05, | |
| "loss": 0.117, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.572326145937455e-05, | |
| "loss": 0.0968, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.565186348707697e-05, | |
| "loss": 0.1063, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.558046551477938e-05, | |
| "loss": 0.1324, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.9650214828687892, | |
| "eval_loss": 0.08880817890167236, | |
| "eval_runtime": 90.3375, | |
| "eval_samples_per_second": 401.915, | |
| "eval_steps_per_second": 6.288, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.55090675424818e-05, | |
| "loss": 0.0962, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.543766957018421e-05, | |
| "loss": 0.1292, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.536627159788662e-05, | |
| "loss": 0.0907, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.5294873625589036e-05, | |
| "loss": 0.102, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.522347565329145e-05, | |
| "loss": 0.1031, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.515207768099386e-05, | |
| "loss": 0.0948, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.508067970869628e-05, | |
| "loss": 0.1013, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.500928173639869e-05, | |
| "loss": 0.0912, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.49378837641011e-05, | |
| "loss": 0.109, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.486648579180351e-05, | |
| "loss": 0.0997, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.9685744188608572, | |
| "eval_loss": 0.08101337403059006, | |
| "eval_runtime": 92.1751, | |
| "eval_samples_per_second": 393.902, | |
| "eval_steps_per_second": 6.162, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.479508781950593e-05, | |
| "loss": 0.0732, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.472368984720834e-05, | |
| "loss": 0.1071, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.4652291874910755e-05, | |
| "loss": 0.1504, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.458089390261317e-05, | |
| "loss": 0.0904, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.450949593031558e-05, | |
| "loss": 0.0913, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.4438097958017996e-05, | |
| "loss": 0.1043, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.4366699985720403e-05, | |
| "loss": 0.0912, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.4295302013422824e-05, | |
| "loss": 0.0911, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.422390404112524e-05, | |
| "loss": 0.0944, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.4152506068827645e-05, | |
| "loss": 0.0904, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.965489699239837, | |
| "eval_loss": 0.09450588375329971, | |
| "eval_runtime": 90.6753, | |
| "eval_samples_per_second": 400.418, | |
| "eval_steps_per_second": 6.264, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.408110809653006e-05, | |
| "loss": 0.1005, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.400971012423247e-05, | |
| "loss": 0.0871, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.393831215193489e-05, | |
| "loss": 0.0828, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.38669141796373e-05, | |
| "loss": 0.0907, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.3795516207339715e-05, | |
| "loss": 0.0971, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.372411823504213e-05, | |
| "loss": 0.0906, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.365272026274454e-05, | |
| "loss": 0.1115, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.358132229044695e-05, | |
| "loss": 0.1044, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3509924318149364e-05, | |
| "loss": 0.105, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.3438526345851784e-05, | |
| "loss": 0.0975, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.9635066651977525, | |
| "eval_loss": 0.0978260189294815, | |
| "eval_runtime": 90.8859, | |
| "eval_samples_per_second": 399.49, | |
| "eval_steps_per_second": 6.25, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.336712837355419e-05, | |
| "loss": 0.0913, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.3295730401256605e-05, | |
| "loss": 0.1066, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.322433242895902e-05, | |
| "loss": 0.0938, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.315293445666143e-05, | |
| "loss": 0.0853, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.308153648436385e-05, | |
| "loss": 0.1347, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.301013851206626e-05, | |
| "loss": 0.0903, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.2938740539768675e-05, | |
| "loss": 0.097, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.286734256747109e-05, | |
| "loss": 0.0984, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.2795944595173496e-05, | |
| "loss": 0.0948, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.272454662287591e-05, | |
| "loss": 0.0859, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.9696485623003195, | |
| "eval_loss": 0.08576656132936478, | |
| "eval_runtime": 90.8861, | |
| "eval_samples_per_second": 399.489, | |
| "eval_steps_per_second": 6.25, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.2653148650578324e-05, | |
| "loss": 0.0655, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.258175067828074e-05, | |
| "loss": 0.127, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.2517492503212915e-05, | |
| "loss": 0.1156, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.244609453091533e-05, | |
| "loss": 0.1073, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.2374696558617736e-05, | |
| "loss": 0.0966, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.230329858632015e-05, | |
| "loss": 0.0836, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.2231900614022564e-05, | |
| "loss": 0.0756, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.216050264172498e-05, | |
| "loss": 0.0901, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.208910466942739e-05, | |
| "loss": 0.1102, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.2017706697129805e-05, | |
| "loss": 0.0785, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9721824391318717, | |
| "eval_loss": 0.07492977380752563, | |
| "eval_runtime": 91.7229, | |
| "eval_samples_per_second": 395.844, | |
| "eval_steps_per_second": 6.193, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.194630872483222e-05, | |
| "loss": 0.0953, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.1874910752534626e-05, | |
| "loss": 0.1098, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.180351278023704e-05, | |
| "loss": 0.0836, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.1732114807939454e-05, | |
| "loss": 0.09, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.1660716835641875e-05, | |
| "loss": 0.0823, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.158931886334428e-05, | |
| "loss": 0.0756, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.1517920891046696e-05, | |
| "loss": 0.075, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.144652291874911e-05, | |
| "loss": 0.1043, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.1375124946451524e-05, | |
| "loss": 0.0706, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.130372697415393e-05, | |
| "loss": 0.0743, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9726781976423928, | |
| "eval_loss": 0.07634202390909195, | |
| "eval_runtime": 91.429, | |
| "eval_samples_per_second": 397.117, | |
| "eval_steps_per_second": 6.212, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.123232900185635e-05, | |
| "loss": 0.0634, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.1160931029558765e-05, | |
| "loss": 0.0664, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.108953305726117e-05, | |
| "loss": 0.0622, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.1018135084963587e-05, | |
| "loss": 0.0798, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.0946737112666e-05, | |
| "loss": 0.0813, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.0875339140368414e-05, | |
| "loss": 0.1109, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.080394116807083e-05, | |
| "loss": 0.0631, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.073254319577324e-05, | |
| "loss": 0.1125, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.0661145223475656e-05, | |
| "loss": 0.0944, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.058974725117807e-05, | |
| "loss": 0.0815, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.972760824060813, | |
| "eval_loss": 0.07654329389333725, | |
| "eval_runtime": 89.9169, | |
| "eval_samples_per_second": 403.795, | |
| "eval_steps_per_second": 6.317, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.051834927888048e-05, | |
| "loss": 0.0711, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.04469513065829e-05, | |
| "loss": 0.0659, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.037555333428531e-05, | |
| "loss": 0.0604, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.030415536198772e-05, | |
| "loss": 0.1177, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.023275738969013e-05, | |
| "loss": 0.1128, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.016135941739255e-05, | |
| "loss": 0.0633, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.008996144509496e-05, | |
| "loss": 0.0636, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.0018563472797374e-05, | |
| "loss": 0.0853, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.994716550049979e-05, | |
| "loss": 0.0733, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.98757675282022e-05, | |
| "loss": 0.0674, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9702544893687342, | |
| "eval_loss": 0.08813291043043137, | |
| "eval_runtime": 89.3704, | |
| "eval_samples_per_second": 406.264, | |
| "eval_steps_per_second": 6.356, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.9804369555904616e-05, | |
| "loss": 0.1019, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.973297158360702e-05, | |
| "loss": 0.0683, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.966157361130944e-05, | |
| "loss": 0.0871, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.959017563901186e-05, | |
| "loss": 0.0929, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.951877766671427e-05, | |
| "loss": 0.0782, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.944737969441668e-05, | |
| "loss": 0.0607, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.937598172211909e-05, | |
| "loss": 0.0685, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.930458374982151e-05, | |
| "loss": 0.0913, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.923318577752392e-05, | |
| "loss": 0.1056, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.9161787805226335e-05, | |
| "loss": 0.0726, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.9715765120634571, | |
| "eval_loss": 0.0874953344464302, | |
| "eval_runtime": 90.7873, | |
| "eval_samples_per_second": 399.924, | |
| "eval_steps_per_second": 6.256, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.909038983292875e-05, | |
| "loss": 0.1111, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.901899186063116e-05, | |
| "loss": 0.0778, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.894759388833357e-05, | |
| "loss": 0.0833, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.8876195916035983e-05, | |
| "loss": 0.0979, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.8804797943738404e-05, | |
| "loss": 0.0758, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.873339997144082e-05, | |
| "loss": 0.0569, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.8662001999143225e-05, | |
| "loss": 0.0606, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.859060402684564e-05, | |
| "loss": 0.0694, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.851920605454805e-05, | |
| "loss": 0.0616, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.844780808225047e-05, | |
| "loss": 0.0633, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.972127354852925, | |
| "eval_loss": 0.09115993231534958, | |
| "eval_runtime": 91.6608, | |
| "eval_samples_per_second": 396.112, | |
| "eval_steps_per_second": 6.197, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.837641010995288e-05, | |
| "loss": 0.1006, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.8305012137655295e-05, | |
| "loss": 0.0821, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.823361416535771e-05, | |
| "loss": 0.1062, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.8162216193060116e-05, | |
| "loss": 0.0823, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.809081822076253e-05, | |
| "loss": 0.0572, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.8019420248464944e-05, | |
| "loss": 0.096, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.7948022276167364e-05, | |
| "loss": 0.0507, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.787662430386977e-05, | |
| "loss": 0.0901, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.7805226331572185e-05, | |
| "loss": 0.0749, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.77338283592746e-05, | |
| "loss": 0.0501, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.974991737358158, | |
| "eval_loss": 0.0743347555398941, | |
| "eval_runtime": 90.6492, | |
| "eval_samples_per_second": 400.533, | |
| "eval_steps_per_second": 6.266, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.766243038697701e-05, | |
| "loss": 0.058, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.759103241467942e-05, | |
| "loss": 0.0746, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.751963444238184e-05, | |
| "loss": 0.0688, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.7448236470084255e-05, | |
| "loss": 0.1108, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.737683849778666e-05, | |
| "loss": 0.0966, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.7305440525489076e-05, | |
| "loss": 0.0851, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.723404255319149e-05, | |
| "loss": 0.0933, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.7162644580893904e-05, | |
| "loss": 0.0466, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.709124660859632e-05, | |
| "loss": 0.0731, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.701984863629873e-05, | |
| "loss": 0.0927, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9759281701002533, | |
| "eval_loss": 0.06946322321891785, | |
| "eval_runtime": 90.3507, | |
| "eval_samples_per_second": 401.857, | |
| "eval_steps_per_second": 6.287, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.6948450664001145e-05, | |
| "loss": 0.0992, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.687705269170356e-05, | |
| "loss": 0.0728, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.6805654719405966e-05, | |
| "loss": 0.0848, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.673425674710839e-05, | |
| "loss": 0.0551, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.66628587748108e-05, | |
| "loss": 0.0989, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.659146080251321e-05, | |
| "loss": 0.0914, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.652006283021562e-05, | |
| "loss": 0.0723, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.6448664857918036e-05, | |
| "loss": 0.0469, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.637726688562045e-05, | |
| "loss": 0.0751, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.6305868913322864e-05, | |
| "loss": 0.0766, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_accuracy": 0.9733116668502809, | |
| "eval_loss": 0.0787879079580307, | |
| "eval_runtime": 91.073, | |
| "eval_samples_per_second": 398.669, | |
| "eval_steps_per_second": 6.237, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.623447094102528e-05, | |
| "loss": 0.0656, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.616307296872769e-05, | |
| "loss": 0.0733, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6091674996430105e-05, | |
| "loss": 0.1334, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.602027702413251e-05, | |
| "loss": 0.0432, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.5948879051834926e-05, | |
| "loss": 0.0705, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.587748107953735e-05, | |
| "loss": 0.0624, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.5806083107239754e-05, | |
| "loss": 0.0648, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.573468513494217e-05, | |
| "loss": 0.0794, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.566328716264458e-05, | |
| "loss": 0.0666, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.5591889190346996e-05, | |
| "loss": 0.0934, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_accuracy": 0.9753222430318387, | |
| "eval_loss": 0.06987004727125168, | |
| "eval_runtime": 90.9784, | |
| "eval_samples_per_second": 399.084, | |
| "eval_steps_per_second": 6.243, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.55204912180494e-05, | |
| "loss": 0.0569, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.5449093245751824e-05, | |
| "loss": 0.0546, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.537769527345424e-05, | |
| "loss": 0.0468, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.530629730115665e-05, | |
| "loss": 0.0709, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.523489932885906e-05, | |
| "loss": 0.0871, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.516350135656147e-05, | |
| "loss": 0.0845, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.509210338426389e-05, | |
| "loss": 0.0568, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.50207054119663e-05, | |
| "loss": 0.0398, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.4949307439668714e-05, | |
| "loss": 0.0764, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.487790946737113e-05, | |
| "loss": 0.0714, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.9761760493555139, | |
| "eval_loss": 0.0756218284368515, | |
| "eval_runtime": 90.5231, | |
| "eval_samples_per_second": 401.091, | |
| "eval_steps_per_second": 6.275, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.480651149507354e-05, | |
| "loss": 0.0744, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.4735113522775956e-05, | |
| "loss": 0.0621, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.466371555047837e-05, | |
| "loss": 0.0644, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.4592317578180784e-05, | |
| "loss": 0.0661, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.45209196058832e-05, | |
| "loss": 0.0804, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.4449521633585605e-05, | |
| "loss": 0.0365, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.437812366128802e-05, | |
| "loss": 0.0616, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.430672568899043e-05, | |
| "loss": 0.0744, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.423532771669285e-05, | |
| "loss": 0.1068, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.416392974439526e-05, | |
| "loss": 0.069, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.9706125371818883, | |
| "eval_loss": 0.08592033386230469, | |
| "eval_runtime": 90.5837, | |
| "eval_samples_per_second": 400.823, | |
| "eval_steps_per_second": 6.27, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.4092531772097675e-05, | |
| "loss": 0.0506, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.402113379980009e-05, | |
| "loss": 0.0596, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.39497358275025e-05, | |
| "loss": 0.0517, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.387833785520491e-05, | |
| "loss": 0.0581, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.380693988290733e-05, | |
| "loss": 0.0784, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.3735541910609744e-05, | |
| "loss": 0.0714, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.366414393831215e-05, | |
| "loss": 0.0753, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.3592745966014565e-05, | |
| "loss": 0.0862, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.352134799371698e-05, | |
| "loss": 0.0579, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.344995002141939e-05, | |
| "loss": 0.0702, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.9657926627740443, | |
| "eval_loss": 0.10006406903266907, | |
| "eval_runtime": 90.1449, | |
| "eval_samples_per_second": 402.774, | |
| "eval_steps_per_second": 6.301, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.337855204912181e-05, | |
| "loss": 0.07, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.330715407682422e-05, | |
| "loss": 0.0734, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.3235756104526635e-05, | |
| "loss": 0.0712, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.316435813222905e-05, | |
| "loss": 0.0386, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.3092960159931456e-05, | |
| "loss": 0.0595, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.3021562187633876e-05, | |
| "loss": 0.0689, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.295016421533629e-05, | |
| "loss": 0.0284, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.28787662430387e-05, | |
| "loss": 0.0703, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.280736827074111e-05, | |
| "loss": 0.0735, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.2735970298443525e-05, | |
| "loss": 0.0633, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_accuracy": 0.9755701222870993, | |
| "eval_loss": 0.07237298041582108, | |
| "eval_runtime": 91.1953, | |
| "eval_samples_per_second": 398.134, | |
| "eval_steps_per_second": 6.228, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.266457232614594e-05, | |
| "loss": 0.0478, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.259317435384835e-05, | |
| "loss": 0.0822, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.252177638155077e-05, | |
| "loss": 0.1011, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.245037840925318e-05, | |
| "loss": 0.0632, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.2378980436955595e-05, | |
| "loss": 0.0797, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.2314722261887765e-05, | |
| "loss": 0.0801, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.224332428959018e-05, | |
| "loss": 0.0461, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.2171926317292586e-05, | |
| "loss": 0.0475, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2100528344995e-05, | |
| "loss": 0.058, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.202913037269742e-05, | |
| "loss": 0.0756, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.9744684367081635, | |
| "eval_loss": 0.07339043915271759, | |
| "eval_runtime": 88.0484, | |
| "eval_samples_per_second": 412.364, | |
| "eval_steps_per_second": 6.451, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.195773240039983e-05, | |
| "loss": 0.0627, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.188633442810224e-05, | |
| "loss": 0.0588, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1814936455804656e-05, | |
| "loss": 0.0519, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.174353848350707e-05, | |
| "loss": 0.0782, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.1672140511209484e-05, | |
| "loss": 0.0478, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.16007425389119e-05, | |
| "loss": 0.0724, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.152934456661431e-05, | |
| "loss": 0.0507, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.1457946594316725e-05, | |
| "loss": 0.0823, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.138654862201913e-05, | |
| "loss": 0.0618, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.1315150649721546e-05, | |
| "loss": 0.0617, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.9746612316844773, | |
| "eval_loss": 0.07039716094732285, | |
| "eval_runtime": 89.0277, | |
| "eval_samples_per_second": 407.828, | |
| "eval_steps_per_second": 6.38, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.124375267742397e-05, | |
| "loss": 0.0858, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.117235470512638e-05, | |
| "loss": 0.0488, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.110095673282879e-05, | |
| "loss": 0.0797, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.10295587605312e-05, | |
| "loss": 0.0854, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.0958160788233616e-05, | |
| "loss": 0.0538, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.088676281593603e-05, | |
| "loss": 0.0623, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.0815364843638444e-05, | |
| "loss": 0.0721, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.074396687134086e-05, | |
| "loss": 0.0525, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.067256889904327e-05, | |
| "loss": 0.0536, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.060117092674568e-05, | |
| "loss": 0.0498, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_accuracy": 0.9787925526054864, | |
| "eval_loss": 0.0651274248957634, | |
| "eval_runtime": 89.6706, | |
| "eval_samples_per_second": 404.904, | |
| "eval_steps_per_second": 6.334, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.052977295444809e-05, | |
| "loss": 0.0672, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.0458374982150506e-05, | |
| "loss": 0.0921, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.0386977009852924e-05, | |
| "loss": 0.0458, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.0315579037555338e-05, | |
| "loss": 0.0378, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.0244181065257748e-05, | |
| "loss": 0.0626, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.0172783092960162e-05, | |
| "loss": 0.0553, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.0101385120662573e-05, | |
| "loss": 0.0463, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.0029987148364987e-05, | |
| "loss": 0.0667, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.9958589176067404e-05, | |
| "loss": 0.0518, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9887191203769814e-05, | |
| "loss": 0.0668, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.9790955161396937, | |
| "eval_loss": 0.06246523559093475, | |
| "eval_runtime": 89.5439, | |
| "eval_samples_per_second": 405.477, | |
| "eval_steps_per_second": 6.343, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9815793231472228e-05, | |
| "loss": 0.0554, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.974439525917464e-05, | |
| "loss": 0.0746, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.9672997286877053e-05, | |
| "loss": 0.0641, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.960159931457947e-05, | |
| "loss": 0.0699, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9530201342281884e-05, | |
| "loss": 0.0362, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9458803369984294e-05, | |
| "loss": 0.0663, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9387405397686708e-05, | |
| "loss": 0.0428, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.931600742538912e-05, | |
| "loss": 0.0618, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9244609453091533e-05, | |
| "loss": 0.0351, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.917321148079395e-05, | |
| "loss": 0.0441, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.9774429877712901, | |
| "eval_loss": 0.07142552733421326, | |
| "eval_runtime": 88.9935, | |
| "eval_samples_per_second": 407.985, | |
| "eval_steps_per_second": 6.382, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.910181350849636e-05, | |
| "loss": 0.0546, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9030415536198774e-05, | |
| "loss": 0.0614, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.8959017563901185e-05, | |
| "loss": 0.055, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.88876195916036e-05, | |
| "loss": 0.0913, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.881622161930601e-05, | |
| "loss": 0.058, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.874482364700843e-05, | |
| "loss": 0.0514, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.867342567471084e-05, | |
| "loss": 0.057, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.8602027702413254e-05, | |
| "loss": 0.0508, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.8530629730115665e-05, | |
| "loss": 0.0754, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.845923175781808e-05, | |
| "loss": 0.0789, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.9721824391318717, | |
| "eval_loss": 0.08800222724676132, | |
| "eval_runtime": 90.4034, | |
| "eval_samples_per_second": 401.622, | |
| "eval_steps_per_second": 6.283, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.838783378552049e-05, | |
| "loss": 0.0517, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8316435813222907e-05, | |
| "loss": 0.0461, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.824503784092532e-05, | |
| "loss": 0.0562, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.817363986862773e-05, | |
| "loss": 0.0814, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8102241896330145e-05, | |
| "loss": 0.072, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.8030843924032556e-05, | |
| "loss": 0.0672, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.795944595173497e-05, | |
| "loss": 0.0613, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7888047979437387e-05, | |
| "loss": 0.0503, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.78166500071398e-05, | |
| "loss": 0.0412, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.774525203484221e-05, | |
| "loss": 0.0464, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_accuracy": 0.9749091109397378, | |
| "eval_loss": 0.07199686020612717, | |
| "eval_runtime": 90.0683, | |
| "eval_samples_per_second": 403.116, | |
| "eval_steps_per_second": 6.306, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7673854062544625e-05, | |
| "loss": 0.0421, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7602456090247036e-05, | |
| "loss": 0.079, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7531058117949453e-05, | |
| "loss": 0.0486, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7459660145651867e-05, | |
| "loss": 0.056, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7388262173354277e-05, | |
| "loss": 0.0489, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.731686420105669e-05, | |
| "loss": 0.0572, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.7245466228759102e-05, | |
| "loss": 0.0612, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.7174068256461516e-05, | |
| "loss": 0.07, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.7102670284163933e-05, | |
| "loss": 0.0523, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.7031272311866347e-05, | |
| "loss": 0.0532, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_accuracy": 0.9781590833975983, | |
| "eval_loss": 0.06813658028841019, | |
| "eval_runtime": 88.4513, | |
| "eval_samples_per_second": 410.486, | |
| "eval_steps_per_second": 6.422, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.6959874339568757e-05, | |
| "loss": 0.0531, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.688847636727117e-05, | |
| "loss": 0.0733, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.6817078394973582e-05, | |
| "loss": 0.0667, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6745680422675996e-05, | |
| "loss": 0.0317, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6674282450378413e-05, | |
| "loss": 0.0495, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6602884478080824e-05, | |
| "loss": 0.0645, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6531486505783237e-05, | |
| "loss": 0.0619, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6460088533485648e-05, | |
| "loss": 0.049, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6388690561188062e-05, | |
| "loss": 0.049, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6317292588890476e-05, | |
| "loss": 0.0677, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_accuracy": 0.9736146303844883, | |
| "eval_loss": 0.07331439107656479, | |
| "eval_runtime": 89.6814, | |
| "eval_samples_per_second": 404.855, | |
| "eval_steps_per_second": 6.334, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6245894616592893e-05, | |
| "loss": 0.049, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.6174496644295304e-05, | |
| "loss": 0.0612, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.6103098671997718e-05, | |
| "loss": 0.0873, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6031700699700128e-05, | |
| "loss": 0.0255, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.5960302727402542e-05, | |
| "loss": 0.0451, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.5888904755104952e-05, | |
| "loss": 0.0516, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.581750678280737e-05, | |
| "loss": 0.0552, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5746108810509784e-05, | |
| "loss": 0.0369, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5674710838212198e-05, | |
| "loss": 0.0515, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5603312865914608e-05, | |
| "loss": 0.0654, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_accuracy": 0.9802247438581029, | |
| "eval_loss": 0.06100200489163399, | |
| "eval_runtime": 90.286, | |
| "eval_samples_per_second": 402.144, | |
| "eval_steps_per_second": 6.291, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5531914893617022e-05, | |
| "loss": 0.0623, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.546051692131944e-05, | |
| "loss": 0.0511, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.538911894902185e-05, | |
| "loss": 0.0539, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.5317720976724264e-05, | |
| "loss": 0.0529, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.5246323004426674e-05, | |
| "loss": 0.0585, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.5174925032129088e-05, | |
| "loss": 0.083, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.51035270598315e-05, | |
| "loss": 0.04, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5032129087533916e-05, | |
| "loss": 0.0678, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.4960731115236326e-05, | |
| "loss": 0.0401, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.4889333142938744e-05, | |
| "loss": 0.0554, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.9739726781976424, | |
| "eval_loss": 0.08250666409730911, | |
| "eval_runtime": 89.9026, | |
| "eval_samples_per_second": 403.859, | |
| "eval_steps_per_second": 6.318, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.4817935170641154e-05, | |
| "loss": 0.0587, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.4746537198343568e-05, | |
| "loss": 0.0407, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.4675139226045982e-05, | |
| "loss": 0.045, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.4603741253748393e-05, | |
| "loss": 0.0786, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.453234328145081e-05, | |
| "loss": 0.0729, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.446094530915322e-05, | |
| "loss": 0.0475, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.4389547336855634e-05, | |
| "loss": 0.0646, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.4318149364558048e-05, | |
| "loss": 0.0262, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.4246751392260462e-05, | |
| "loss": 0.0527, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4175353419962873e-05, | |
| "loss": 0.0836, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_accuracy": 0.9779662884212845, | |
| "eval_loss": 0.0694098174571991, | |
| "eval_runtime": 89.2762, | |
| "eval_samples_per_second": 406.693, | |
| "eval_steps_per_second": 6.362, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.410395544766529e-05, | |
| "loss": 0.0759, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.40325574753677e-05, | |
| "loss": 0.0549, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.3961159503070114e-05, | |
| "loss": 0.0318, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.3889761530772528e-05, | |
| "loss": 0.0298, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.381836355847494e-05, | |
| "loss": 0.0469, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3746965586177353e-05, | |
| "loss": 0.0453, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3675567613879767e-05, | |
| "loss": 0.0578, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.360416964158218e-05, | |
| "loss": 0.0424, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.353277166928459e-05, | |
| "loss": 0.0509, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.346137369698701e-05, | |
| "loss": 0.0688, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_accuracy": 0.9813264294370386, | |
| "eval_loss": 0.05985138192772865, | |
| "eval_runtime": 88.3381, | |
| "eval_samples_per_second": 411.012, | |
| "eval_steps_per_second": 6.43, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.338997572468942e-05, | |
| "loss": 0.0853, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.3318577752391833e-05, | |
| "loss": 0.0372, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.3247179780094247e-05, | |
| "loss": 0.0418, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.317578180779666e-05, | |
| "loss": 0.0689, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.310438383549907e-05, | |
| "loss": 0.0406, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.3032985863201485e-05, | |
| "loss": 0.0666, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.29615878909039e-05, | |
| "loss": 0.0424, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.2890189918606313e-05, | |
| "loss": 0.0533, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.2818791946308727e-05, | |
| "loss": 0.0645, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.2747393974011137e-05, | |
| "loss": 0.052, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.9672799383056075, | |
| "eval_loss": 0.09324605017900467, | |
| "eval_runtime": 87.8971, | |
| "eval_samples_per_second": 413.074, | |
| "eval_steps_per_second": 6.462, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2675996001713555e-05, | |
| "loss": 0.0668, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2604598029415965e-05, | |
| "loss": 0.0642, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.253320005711838e-05, | |
| "loss": 0.0369, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2461802084820793e-05, | |
| "loss": 0.061, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2390404112523207e-05, | |
| "loss": 0.0414, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.2319006140225617e-05, | |
| "loss": 0.0481, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.2247608167928035e-05, | |
| "loss": 0.0419, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.2176210195630445e-05, | |
| "loss": 0.0497, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.210481222333286e-05, | |
| "loss": 0.056, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.2033414251035273e-05, | |
| "loss": 0.0515, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_accuracy": 0.97590062796078, | |
| "eval_loss": 0.078504778444767, | |
| "eval_runtime": 88.0936, | |
| "eval_samples_per_second": 412.153, | |
| "eval_steps_per_second": 6.448, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1962016278737683e-05, | |
| "loss": 0.0657, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1890618306440097e-05, | |
| "loss": 0.0436, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.181922033414251e-05, | |
| "loss": 0.0334, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.1754962159074682e-05, | |
| "loss": 0.0672, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.1683564186777096e-05, | |
| "loss": 0.0544, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.161216621447951e-05, | |
| "loss": 0.0565, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.1540768242181923e-05, | |
| "loss": 0.0399, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.1469370269884337e-05, | |
| "loss": 0.0412, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.1397972297586748e-05, | |
| "loss": 0.082, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.1326574325289162e-05, | |
| "loss": 0.0586, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_accuracy": 0.9787374683265396, | |
| "eval_loss": 0.06596303731203079, | |
| "eval_runtime": 88.927, | |
| "eval_samples_per_second": 408.29, | |
| "eval_steps_per_second": 6.387, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.1255176352991576e-05, | |
| "loss": 0.0375, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.118377838069399e-05, | |
| "loss": 0.0607, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.1112380408396404e-05, | |
| "loss": 0.0518, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.1040982436098817e-05, | |
| "loss": 0.0506, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0969584463801228e-05, | |
| "loss": 0.0759, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0898186491503642e-05, | |
| "loss": 0.0528, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.0826788519206056e-05, | |
| "loss": 0.0468, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.075539054690847e-05, | |
| "loss": 0.0526, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.0683992574610884e-05, | |
| "loss": 0.0603, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.0612594602313294e-05, | |
| "loss": 0.056, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.9782692519554919, | |
| "eval_loss": 0.06120914965867996, | |
| "eval_runtime": 89.7575, | |
| "eval_samples_per_second": 404.512, | |
| "eval_steps_per_second": 6.328, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.0541196630015708e-05, | |
| "loss": 0.0524, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0469798657718122e-05, | |
| "loss": 0.0602, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0398400685420536e-05, | |
| "loss": 0.034, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0327002713122946e-05, | |
| "loss": 0.0505, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0255604740825364e-05, | |
| "loss": 0.0543, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0184206768527774e-05, | |
| "loss": 0.0711, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.0112808796230188e-05, | |
| "loss": 0.0329, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.0041410823932602e-05, | |
| "loss": 0.057, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.9970012851635016e-05, | |
| "loss": 0.0368, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.9898614879337426e-05, | |
| "loss": 0.037, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.9794811060923212, | |
| "eval_loss": 0.06448051333427429, | |
| "eval_runtime": 88.8993, | |
| "eval_samples_per_second": 408.417, | |
| "eval_steps_per_second": 6.389, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.982721690703984e-05, | |
| "loss": 0.0443, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9755818934742254e-05, | |
| "loss": 0.0611, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9684420962444665e-05, | |
| "loss": 0.0393, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9613022990147082e-05, | |
| "loss": 0.0419, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9541625017849493e-05, | |
| "loss": 0.0639, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9470227045551906e-05, | |
| "loss": 0.0389, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.939882907325432e-05, | |
| "loss": 0.0562, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.9327431100956734e-05, | |
| "loss": 0.0531, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.9256033128659148e-05, | |
| "loss": 0.0458, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.9184635156361562e-05, | |
| "loss": 0.0541, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.9809132973449377, | |
| "eval_loss": 0.060034461319446564, | |
| "eval_runtime": 88.5529, | |
| "eval_samples_per_second": 410.015, | |
| "eval_steps_per_second": 6.414, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.9113237184063973e-05, | |
| "loss": 0.0433, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.9041839211766387e-05, | |
| "loss": 0.0511, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.89704412394688e-05, | |
| "loss": 0.0775, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.889904326717121e-05, | |
| "loss": 0.0727, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.8827645294873628e-05, | |
| "loss": 0.0568, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.875624732257604e-05, | |
| "loss": 0.0297, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.8684849350278453e-05, | |
| "loss": 0.0344, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8613451377980867e-05, | |
| "loss": 0.043, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.854205340568328e-05, | |
| "loss": 0.0559, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.847065543338569e-05, | |
| "loss": 0.0521, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9737247989423818, | |
| "eval_loss": 0.08755724132061005, | |
| "eval_runtime": 88.2358, | |
| "eval_samples_per_second": 411.488, | |
| "eval_steps_per_second": 6.437, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.8399257461088108e-05, | |
| "loss": 0.0401, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.832785948879052e-05, | |
| "loss": 0.0459, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8256461516492933e-05, | |
| "loss": 0.0522, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8185063544195347e-05, | |
| "loss": 0.0439, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8113665571897757e-05, | |
| "loss": 0.0429, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.804226759960017e-05, | |
| "loss": 0.0609, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.7970869627302585e-05, | |
| "loss": 0.039, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.7899471655005e-05, | |
| "loss": 0.0344, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.782807368270741e-05, | |
| "loss": 0.0571, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.7756675710409827e-05, | |
| "loss": 0.0352, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.9779662884212845, | |
| "eval_loss": 0.07093251496553421, | |
| "eval_runtime": 87.9597, | |
| "eval_samples_per_second": 412.78, | |
| "eval_steps_per_second": 6.458, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7685277738112237e-05, | |
| "loss": 0.057, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.761387976581465e-05, | |
| "loss": 0.0661, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7542481793517065e-05, | |
| "loss": 0.0409, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.747108382121948e-05, | |
| "loss": 0.033, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.7399685848921893e-05, | |
| "loss": 0.0579, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.7328287876624307e-05, | |
| "loss": 0.0416, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.7256889904326717e-05, | |
| "loss": 0.041, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.718549193202913e-05, | |
| "loss": 0.0378, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7114093959731545e-05, | |
| "loss": 0.0443, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7042695987433956e-05, | |
| "loss": 0.0498, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_accuracy": 0.980858213065991, | |
| "eval_loss": 0.06104397773742676, | |
| "eval_runtime": 87.7557, | |
| "eval_samples_per_second": 413.739, | |
| "eval_steps_per_second": 6.473, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.6971298015136373e-05, | |
| "loss": 0.0409, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.6899900042838783e-05, | |
| "loss": 0.0455, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.6828502070541197e-05, | |
| "loss": 0.0476, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.675710409824361e-05, | |
| "loss": 0.0351, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6685706125946025e-05, | |
| "loss": 0.052, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6614308153648436e-05, | |
| "loss": 0.0247, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.6542910181350853e-05, | |
| "loss": 0.0293, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.6471512209053263e-05, | |
| "loss": 0.0193, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6400114236755677e-05, | |
| "loss": 0.0371, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.632871626445809e-05, | |
| "loss": 0.0424, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.9829789578054423, | |
| "eval_loss": 0.05687294527888298, | |
| "eval_runtime": 89.7152, | |
| "eval_samples_per_second": 404.703, | |
| "eval_steps_per_second": 6.331, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6257318292160502e-05, | |
| "loss": 0.0409, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.6185920319862916e-05, | |
| "loss": 0.0682, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.611452234756533e-05, | |
| "loss": 0.0444, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.6043124375267743e-05, | |
| "loss": 0.0625, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.5971726402970154e-05, | |
| "loss": 0.0448, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.590032843067257e-05, | |
| "loss": 0.0357, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.5828930458374982e-05, | |
| "loss": 0.0374, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.5757532486077396e-05, | |
| "loss": 0.0599, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.568613451377981e-05, | |
| "loss": 0.0569, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5614736541482224e-05, | |
| "loss": 0.0532, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_accuracy": 0.9820425250633469, | |
| "eval_loss": 0.06247245892882347, | |
| "eval_runtime": 89.0414, | |
| "eval_samples_per_second": 407.766, | |
| "eval_steps_per_second": 6.379, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5543338569184637e-05, | |
| "loss": 0.0172, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5471940596887048e-05, | |
| "loss": 0.0704, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5400542624589462e-05, | |
| "loss": 0.0513, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5329144652291876e-05, | |
| "loss": 0.0285, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.525774667999429e-05, | |
| "loss": 0.0303, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.5186348707696702e-05, | |
| "loss": 0.0335, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.5114950735399116e-05, | |
| "loss": 0.0463, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.5043552763101528e-05, | |
| "loss": 0.0504, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.4972154790803942e-05, | |
| "loss": 0.0596, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.4900756818506356e-05, | |
| "loss": 0.046, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.9842183540817451, | |
| "eval_loss": 0.051206715404987335, | |
| "eval_runtime": 88.4481, | |
| "eval_samples_per_second": 410.501, | |
| "eval_steps_per_second": 6.422, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.4829358846208768e-05, | |
| "loss": 0.0472, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.475796087391118e-05, | |
| "loss": 0.0185, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4686562901613596e-05, | |
| "loss": 0.0282, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4615164929316008e-05, | |
| "loss": 0.0334, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.454376695701842e-05, | |
| "loss": 0.0264, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4472368984720836e-05, | |
| "loss": 0.0287, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4400971012423248e-05, | |
| "loss": 0.0514, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.432957304012566e-05, | |
| "loss": 0.0553, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4258175067828076e-05, | |
| "loss": 0.0476, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4186777095530488e-05, | |
| "loss": 0.0453, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.9812988872975653, | |
| "eval_loss": 0.06078343093395233, | |
| "eval_runtime": 88.3817, | |
| "eval_samples_per_second": 410.809, | |
| "eval_steps_per_second": 6.427, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.41153791232329e-05, | |
| "loss": 0.0167, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4043981150935314e-05, | |
| "loss": 0.0237, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3972583178637726e-05, | |
| "loss": 0.0427, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3901185206340139e-05, | |
| "loss": 0.0446, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3829787234042554e-05, | |
| "loss": 0.0419, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3758389261744966e-05, | |
| "loss": 0.037, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3686991289447382e-05, | |
| "loss": 0.026, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3615593317149794e-05, | |
| "loss": 0.0316, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3544195344852207e-05, | |
| "loss": 0.0386, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3472797372554622e-05, | |
| "loss": 0.0577, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.9811060923212516, | |
| "eval_loss": 0.06966891139745712, | |
| "eval_runtime": 87.7534, | |
| "eval_samples_per_second": 413.75, | |
| "eval_steps_per_second": 6.473, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3401399400257034e-05, | |
| "loss": 0.0477, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3330001427959447e-05, | |
| "loss": 0.0275, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.325860345566186e-05, | |
| "loss": 0.0201, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3187205483364273e-05, | |
| "loss": 0.0274, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3115807511066685e-05, | |
| "loss": 0.0527, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.30444095387691e-05, | |
| "loss": 0.0181, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2973011566471513e-05, | |
| "loss": 0.0389, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2901613594173925e-05, | |
| "loss": 0.0318, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.283021562187634e-05, | |
| "loss": 0.0236, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2758817649578753e-05, | |
| "loss": 0.0397, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.981629392971246, | |
| "eval_loss": 0.06878527998924255, | |
| "eval_runtime": 87.6465, | |
| "eval_samples_per_second": 414.255, | |
| "eval_steps_per_second": 6.481, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2687419677281165e-05, | |
| "loss": 0.0484, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.261602170498358e-05, | |
| "loss": 0.0386, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2544623732685993e-05, | |
| "loss": 0.0399, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2473225760388407e-05, | |
| "loss": 0.0377, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2401827788090819e-05, | |
| "loss": 0.0306, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2330429815793231e-05, | |
| "loss": 0.0695, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2259031843495645e-05, | |
| "loss": 0.0438, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2187633871198059e-05, | |
| "loss": 0.0353, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2116235898900471e-05, | |
| "loss": 0.0499, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2044837926602885e-05, | |
| "loss": 0.0494, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_accuracy": 0.9834196320370167, | |
| "eval_loss": 0.05344979837536812, | |
| "eval_runtime": 88.5338, | |
| "eval_samples_per_second": 410.103, | |
| "eval_steps_per_second": 6.416, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1973439954305299e-05, | |
| "loss": 0.0688, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1902041982007711e-05, | |
| "loss": 0.0364, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1830644009710125e-05, | |
| "loss": 0.0481, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1759246037412539e-05, | |
| "loss": 0.0293, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1687848065114951e-05, | |
| "loss": 0.0492, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1616450092817365e-05, | |
| "loss": 0.024, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1545052120519779e-05, | |
| "loss": 0.0185, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1473654148222191e-05, | |
| "loss": 0.0292, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1402256175924603e-05, | |
| "loss": 0.0277, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1330858203627017e-05, | |
| "loss": 0.0158, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_accuracy": 0.9774429877712901, | |
| "eval_loss": 0.08603409677743912, | |
| "eval_runtime": 86.9446, | |
| "eval_samples_per_second": 417.599, | |
| "eval_steps_per_second": 6.533, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1259460231329431e-05, | |
| "loss": 0.0337, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1188062259031843e-05, | |
| "loss": 0.0267, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1116664286734257e-05, | |
| "loss": 0.0206, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.1045266314436671e-05, | |
| "loss": 0.046, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.0973868342139083e-05, | |
| "loss": 0.0495, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.0902470369841497e-05, | |
| "loss": 0.0524, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0831072397543911e-05, | |
| "loss": 0.0499, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0759674425246323e-05, | |
| "loss": 0.0133, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0688276452948737e-05, | |
| "loss": 0.0416, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.061687848065115e-05, | |
| "loss": 0.0297, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_accuracy": 0.9835573427343836, | |
| "eval_loss": 0.059268660843372345, | |
| "eval_runtime": 89.1604, | |
| "eval_samples_per_second": 407.221, | |
| "eval_steps_per_second": 6.371, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0545480508353562e-05, | |
| "loss": 0.0215, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0474082536055976e-05, | |
| "loss": 0.0301, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.040268456375839e-05, | |
| "loss": 0.0469, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0331286591460804e-05, | |
| "loss": 0.0338, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0259888619163216e-05, | |
| "loss": 0.0336, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.018849064686563e-05, | |
| "loss": 0.0429, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.0117092674568044e-05, | |
| "loss": 0.0465, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 1.0045694702270456e-05, | |
| "loss": 0.0529, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.97429672997287e-06, | |
| "loss": 0.0525, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.902898757675284e-06, | |
| "loss": 0.055, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_accuracy": 0.9820976093422937, | |
| "eval_loss": 0.05791514739394188, | |
| "eval_runtime": 88.2819, | |
| "eval_samples_per_second": 411.274, | |
| "eval_steps_per_second": 6.434, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.831500785377696e-06, | |
| "loss": 0.0343, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.76010281308011e-06, | |
| "loss": 0.0356, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.688704840782522e-06, | |
| "loss": 0.043, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.617306868484934e-06, | |
| "loss": 0.0484, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.545908896187348e-06, | |
| "loss": 0.0247, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.474510923889762e-06, | |
| "loss": 0.0488, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.403112951592176e-06, | |
| "loss": 0.0322, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.331714979294588e-06, | |
| "loss": 0.0493, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.260317006997002e-06, | |
| "loss": 0.0265, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.188919034699416e-06, | |
| "loss": 0.0368, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_accuracy": 0.9796188167896882, | |
| "eval_loss": 0.07286185771226883, | |
| "eval_runtime": 89.8434, | |
| "eval_samples_per_second": 404.125, | |
| "eval_steps_per_second": 6.322, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.117521062401828e-06, | |
| "loss": 0.0207, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 9.046123090104242e-06, | |
| "loss": 0.0543, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.974725117806656e-06, | |
| "loss": 0.0397, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.903327145509068e-06, | |
| "loss": 0.0447, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.83192917321148e-06, | |
| "loss": 0.0593, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.760531200913894e-06, | |
| "loss": 0.0293, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.689133228616306e-06, | |
| "loss": 0.0223, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.61773525631872e-06, | |
| "loss": 0.0215, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.546337284021134e-06, | |
| "loss": 0.0397, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.474939311723546e-06, | |
| "loss": 0.0754, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_accuracy": 0.982675994271235, | |
| "eval_loss": 0.060067031532526016, | |
| "eval_runtime": 89.7498, | |
| "eval_samples_per_second": 404.547, | |
| "eval_steps_per_second": 6.329, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.40354133942596e-06, | |
| "loss": 0.0227, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.332143367128374e-06, | |
| "loss": 0.0549, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.260745394830788e-06, | |
| "loss": 0.038, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.1893474225332e-06, | |
| "loss": 0.0248, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.117949450235614e-06, | |
| "loss": 0.0248, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.046551477938028e-06, | |
| "loss": 0.0433, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 7.97515350564044e-06, | |
| "loss": 0.0215, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.903755533342853e-06, | |
| "loss": 0.0193, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.832357561045267e-06, | |
| "loss": 0.0287, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.760959588747679e-06, | |
| "loss": 0.0523, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_accuracy": 0.9824281150159745, | |
| "eval_loss": 0.059657733887434006, | |
| "eval_runtime": 89.4609, | |
| "eval_samples_per_second": 405.853, | |
| "eval_steps_per_second": 6.349, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.689561616450093e-06, | |
| "loss": 0.0223, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.618163644152507e-06, | |
| "loss": 0.0316, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.546765671854919e-06, | |
| "loss": 0.0433, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.475367699557333e-06, | |
| "loss": 0.0386, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.403969727259747e-06, | |
| "loss": 0.0248, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.33257175496216e-06, | |
| "loss": 0.0254, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.261173782664573e-06, | |
| "loss": 0.0277, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.189775810366986e-06, | |
| "loss": 0.0531, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.1183778380694e-06, | |
| "loss": 0.0488, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.046979865771812e-06, | |
| "loss": 0.0433, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.9840531012449047, | |
| "eval_loss": 0.05469777435064316, | |
| "eval_runtime": 89.6994, | |
| "eval_samples_per_second": 404.774, | |
| "eval_steps_per_second": 6.332, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.975581893474226e-06, | |
| "loss": 0.028, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.904183921176639e-06, | |
| "loss": 0.0334, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.832785948879052e-06, | |
| "loss": 0.0361, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.761387976581465e-06, | |
| "loss": 0.0252, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.689990004283879e-06, | |
| "loss": 0.0481, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.618592031986291e-06, | |
| "loss": 0.0304, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.547194059688705e-06, | |
| "loss": 0.0329, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.475796087391119e-06, | |
| "loss": 0.052, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.404398115093532e-06, | |
| "loss": 0.0502, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.333000142795944e-06, | |
| "loss": 0.0164, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.9827310785501818, | |
| "eval_loss": 0.06196733936667442, | |
| "eval_runtime": 88.1689, | |
| "eval_samples_per_second": 411.8, | |
| "eval_steps_per_second": 6.442, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.261602170498358e-06, | |
| "loss": 0.03, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.190204198200771e-06, | |
| "loss": 0.0354, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.118806225903185e-06, | |
| "loss": 0.039, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 6.047408253605598e-06, | |
| "loss": 0.0348, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.976010281308011e-06, | |
| "loss": 0.0271, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.904612309010424e-06, | |
| "loss": 0.029, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.833214336712837e-06, | |
| "loss": 0.0201, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.761816364415251e-06, | |
| "loss": 0.0204, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.690418392117664e-06, | |
| "loss": 0.0405, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.619020419820077e-06, | |
| "loss": 0.015, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_accuracy": 0.9822353200396606, | |
| "eval_loss": 0.0639323964715004, | |
| "eval_runtime": 89.1796, | |
| "eval_samples_per_second": 407.133, | |
| "eval_steps_per_second": 6.369, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.54762244752249e-06, | |
| "loss": 0.0448, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.4762244752249035e-06, | |
| "loss": 0.0563, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.4048265029273165e-06, | |
| "loss": 0.0236, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.3334285306297304e-06, | |
| "loss": 0.0325, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.2620305583321435e-06, | |
| "loss": 0.0381, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.190632586034557e-06, | |
| "loss": 0.0265, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.1192346137369705e-06, | |
| "loss": 0.0286, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.047836641439383e-06, | |
| "loss": 0.0547, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.976438669141797e-06, | |
| "loss": 0.028, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.90504069684421e-06, | |
| "loss": 0.0415, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_accuracy": 0.9836675112922771, | |
| "eval_loss": 0.05758131295442581, | |
| "eval_runtime": 85.956, | |
| "eval_samples_per_second": 422.402, | |
| "eval_steps_per_second": 6.608, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.8336427245466236e-06, | |
| "loss": 0.0102, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.762244752249037e-06, | |
| "loss": 0.0515, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.69084677995145e-06, | |
| "loss": 0.0223, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.619448807653863e-06, | |
| "loss": 0.0471, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.548050835356276e-06, | |
| "loss": 0.0318, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.476652863058689e-06, | |
| "loss": 0.0568, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.405254890761103e-06, | |
| "loss": 0.026, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.333856918463516e-06, | |
| "loss": 0.0229, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.26245894616593e-06, | |
| "loss": 0.0083, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.191060973868342e-06, | |
| "loss": 0.0257, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_accuracy": 0.9820425250633469, | |
| "eval_loss": 0.06198680028319359, | |
| "eval_runtime": 89.7768, | |
| "eval_samples_per_second": 404.425, | |
| "eval_steps_per_second": 6.327, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.119663001570755e-06, | |
| "loss": 0.0413, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.048265029273169e-06, | |
| "loss": 0.0401, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.976867056975582e-06, | |
| "loss": 0.028, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.905469084677996e-06, | |
| "loss": 0.0359, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.834071112380409e-06, | |
| "loss": 0.0389, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.7626731400828216e-06, | |
| "loss": 0.0481, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.6912751677852355e-06, | |
| "loss": 0.0252, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.619877195487648e-06, | |
| "loss": 0.031, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.548479223190061e-06, | |
| "loss": 0.0459, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.477081250892475e-06, | |
| "loss": 0.0268, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.9836675112922771, | |
| "eval_loss": 0.05676598474383354, | |
| "eval_runtime": 89.3838, | |
| "eval_samples_per_second": 406.203, | |
| "eval_steps_per_second": 6.355, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.4056832785948877e-06, | |
| "loss": 0.0173, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.3342853062973016e-06, | |
| "loss": 0.0208, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.2628873339997147e-06, | |
| "loss": 0.0436, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.1914893617021277e-06, | |
| "loss": 0.052, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.120091389404541e-06, | |
| "loss": 0.0369, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.0486934171069543e-06, | |
| "loss": 0.0535, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.9772954448093674e-06, | |
| "loss": 0.0471, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.905897472511781e-06, | |
| "loss": 0.053, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.8344995002141943e-06, | |
| "loss": 0.0313, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.7631015279166074e-06, | |
| "loss": 0.043, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_accuracy": 0.9836399691528038, | |
| "eval_loss": 0.05576753616333008, | |
| "eval_runtime": 88.288, | |
| "eval_samples_per_second": 411.245, | |
| "eval_steps_per_second": 6.433, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.6917035556190204e-06, | |
| "loss": 0.041, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.620305583321434e-06, | |
| "loss": 0.0149, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.548907611023847e-06, | |
| "loss": 0.0232, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.47750963872626e-06, | |
| "loss": 0.0299, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.4061116664286735e-06, | |
| "loss": 0.0189, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.334713694131087e-06, | |
| "loss": 0.0296, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.2633157218335e-06, | |
| "loss": 0.0243, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.191917749535913e-06, | |
| "loss": 0.0561, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.1205197772383266e-06, | |
| "loss": 0.0445, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.0491218049407397e-06, | |
| "loss": 0.0339, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.9839429326870112, | |
| "eval_loss": 0.0554034560918808, | |
| "eval_runtime": 90.0961, | |
| "eval_samples_per_second": 402.992, | |
| "eval_steps_per_second": 6.304, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.977723832643153e-06, | |
| "loss": 0.0334, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.9063258603455664e-06, | |
| "loss": 0.0416, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.8349278880479795e-06, | |
| "loss": 0.0257, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.7635299157503928e-06, | |
| "loss": 0.0394, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.692131943452806e-06, | |
| "loss": 0.0485, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.6207339711552195e-06, | |
| "loss": 0.0332, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.5493359988576326e-06, | |
| "loss": 0.0299, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.4779380265600456e-06, | |
| "loss": 0.0285, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.4065400542624591e-06, | |
| "loss": 0.0366, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.3351420819648722e-06, | |
| "loss": 0.0263, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.9836950534317506, | |
| "eval_loss": 0.05521493777632713, | |
| "eval_runtime": 88.8813, | |
| "eval_samples_per_second": 408.5, | |
| "eval_steps_per_second": 6.391, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.2637441096672855e-06, | |
| "loss": 0.0339, | |
| "step": 7610 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.1923461373696987e-06, | |
| "loss": 0.0348, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.120948165072112e-06, | |
| "loss": 0.0366, | |
| "step": 7630 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.0495501927745253e-06, | |
| "loss": 0.037, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.781522204769385e-07, | |
| "loss": 0.0444, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.067542481793518e-07, | |
| "loss": 0.0304, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 8.35356275881765e-07, | |
| "loss": 0.0253, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.639583035841782e-07, | |
| "loss": 0.0412, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.925603312865915e-07, | |
| "loss": 0.0289, | |
| "step": 7690 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 6.211623589890047e-07, | |
| "loss": 0.0428, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.9842458962212185, | |
| "eval_loss": 0.0534803606569767, | |
| "eval_runtime": 90.2141, | |
| "eval_samples_per_second": 402.465, | |
| "eval_steps_per_second": 6.296, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.49764386691418e-07, | |
| "loss": 0.0308, | |
| "step": 7710 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.783664143938312e-07, | |
| "loss": 0.0349, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.0696844209624455e-07, | |
| "loss": 0.0304, | |
| "step": 7730 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.355704697986577e-07, | |
| "loss": 0.0204, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.64172497501071e-07, | |
| "loss": 0.0286, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.9277452520348424e-07, | |
| "loss": 0.0418, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.2137655290589748e-07, | |
| "loss": 0.0297, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.9978580608310726e-08, | |
| "loss": 0.0336, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 7782, | |
| "total_flos": 1.6202290803162218e+19, | |
| "train_loss": 0.0875718877881773, | |
| "train_runtime": 10188.5801, | |
| "train_samples_per_second": 48.879, | |
| "train_steps_per_second": 0.764 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 7782, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.6202290803162218e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |