| { | |
| "best_metric": 0.9781420765027322, | |
| "best_model_checkpoint": "resnet-50-shortSleeveCleanedData/checkpoint-1470", | |
| "epoch": 10.0, | |
| "global_step": 1470, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.982817869415808e-05, | |
| "loss": 1.0936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.948453608247423e-05, | |
| "loss": 1.0859, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.9140893470790375e-05, | |
| "loss": 1.0726, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.879725085910653e-05, | |
| "loss": 1.0655, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.845360824742268e-05, | |
| "loss": 1.0659, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.810996563573883e-05, | |
| "loss": 1.0552, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.776632302405499e-05, | |
| "loss": 1.0441, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.7422680412371134e-05, | |
| "loss": 1.0318, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.7079037800687284e-05, | |
| "loss": 1.0237, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.673539518900344e-05, | |
| "loss": 1.0043, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.639175257731959e-05, | |
| "loss": 1.0046, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6048109965635736e-05, | |
| "loss": 0.9857, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.570446735395189e-05, | |
| "loss": 0.973, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.726775956284153, | |
| "eval_loss": 0.9370501637458801, | |
| "eval_runtime": 577.0712, | |
| "eval_samples_per_second": 1.586, | |
| "eval_steps_per_second": 0.199, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.536082474226804e-05, | |
| "loss": 0.9592, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.5017182130584194e-05, | |
| "loss": 0.9381, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.467353951890035e-05, | |
| "loss": 0.9292, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.4329896907216494e-05, | |
| "loss": 0.8919, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.3986254295532645e-05, | |
| "loss": 0.8828, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.36426116838488e-05, | |
| "loss": 0.8452, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 4.329896907216495e-05, | |
| "loss": 0.8414, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.2955326460481096e-05, | |
| "loss": 0.8229, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.261168384879725e-05, | |
| "loss": 0.8034, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.2268041237113404e-05, | |
| "loss": 0.7824, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.1924398625429554e-05, | |
| "loss": 0.7358, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 4.158075601374571e-05, | |
| "loss": 0.7344, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 4.1237113402061855e-05, | |
| "loss": 0.6981, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.0893470790378005e-05, | |
| "loss": 0.6869, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.054982817869416e-05, | |
| "loss": 0.6565, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8710382513661202, | |
| "eval_loss": 0.5519522428512573, | |
| "eval_runtime": 27.0894, | |
| "eval_samples_per_second": 33.777, | |
| "eval_steps_per_second": 4.245, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.020618556701031e-05, | |
| "loss": 0.663, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.9862542955326463e-05, | |
| "loss": 0.648, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.9518900343642614e-05, | |
| "loss": 0.6162, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.9175257731958764e-05, | |
| "loss": 0.5981, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 3.8831615120274915e-05, | |
| "loss": 0.5583, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.848797250859107e-05, | |
| "loss": 0.5563, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.8144329896907216e-05, | |
| "loss": 0.563, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.7800687285223366e-05, | |
| "loss": 0.534, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.745704467353952e-05, | |
| "loss": 0.5228, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.7113402061855674e-05, | |
| "loss": 0.5041, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 3.6769759450171824e-05, | |
| "loss": 0.4817, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.6426116838487974e-05, | |
| "loss": 0.5135, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.6082474226804125e-05, | |
| "loss": 0.4676, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 3.5738831615120275e-05, | |
| "loss": 0.4882, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.539518900343643e-05, | |
| "loss": 0.4609, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9278688524590164, | |
| "eval_loss": 0.29834744334220886, | |
| "eval_runtime": 25.7025, | |
| "eval_samples_per_second": 35.6, | |
| "eval_steps_per_second": 4.474, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.5051546391752576e-05, | |
| "loss": 0.4741, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.4707903780068726e-05, | |
| "loss": 0.4635, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.4364261168384884e-05, | |
| "loss": 0.4645, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.4020618556701034e-05, | |
| "loss": 0.4558, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3676975945017185e-05, | |
| "loss": 0.4318, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4389, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 3.2989690721649485e-05, | |
| "loss": 0.4614, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 3.2646048109965636e-05, | |
| "loss": 0.3683, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.230240549828179e-05, | |
| "loss": 0.4364, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3.1958762886597937e-05, | |
| "loss": 0.4254, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.161512027491409e-05, | |
| "loss": 0.4524, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.1271477663230244e-05, | |
| "loss": 0.4369, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.0927835051546395e-05, | |
| "loss": 0.3894, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 3.0584192439862545e-05, | |
| "loss": 0.3937, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9486338797814208, | |
| "eval_loss": 0.20506763458251953, | |
| "eval_runtime": 26.8515, | |
| "eval_samples_per_second": 34.076, | |
| "eval_steps_per_second": 4.283, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 3.0240549828178692e-05, | |
| "loss": 0.4192, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 2.9896907216494846e-05, | |
| "loss": 0.4003, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.9553264604811e-05, | |
| "loss": 0.4544, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 2.920962199312715e-05, | |
| "loss": 0.3996, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 2.8865979381443297e-05, | |
| "loss": 0.4168, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.852233676975945e-05, | |
| "loss": 0.3964, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 2.81786941580756e-05, | |
| "loss": 0.4113, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 2.7835051546391755e-05, | |
| "loss": 0.3912, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 2.749140893470791e-05, | |
| "loss": 0.3793, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.7147766323024053e-05, | |
| "loss": 0.4175, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.6804123711340206e-05, | |
| "loss": 0.3831, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.646048109965636e-05, | |
| "loss": 0.3818, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.611683848797251e-05, | |
| "loss": 0.3901, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.5773195876288658e-05, | |
| "loss": 0.3541, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 2.542955326460481e-05, | |
| "loss": 0.3723, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9726775956284153, | |
| "eval_loss": 0.15214987099170685, | |
| "eval_runtime": 26.7904, | |
| "eval_samples_per_second": 34.154, | |
| "eval_steps_per_second": 4.293, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 2.5085910652920962e-05, | |
| "loss": 0.3624, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 2.4742268041237116e-05, | |
| "loss": 0.3777, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.4398625429553266e-05, | |
| "loss": 0.3625, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.4054982817869417e-05, | |
| "loss": 0.3478, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 2.3711340206185567e-05, | |
| "loss": 0.3732, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.336769759450172e-05, | |
| "loss": 0.3508, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 2.3024054982817868e-05, | |
| "loss": 0.373, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 2.268041237113402e-05, | |
| "loss": 0.406, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2.2336769759450175e-05, | |
| "loss": 0.3409, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 2.1993127147766322e-05, | |
| "loss": 0.3647, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.1649484536082476e-05, | |
| "loss": 0.3719, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 2.1305841924398627e-05, | |
| "loss": 0.3631, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 2.0962199312714777e-05, | |
| "loss": 0.3574, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 2.0618556701030927e-05, | |
| "loss": 0.3704, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 2.027491408934708e-05, | |
| "loss": 0.3926, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9672131147540983, | |
| "eval_loss": 0.14902302622795105, | |
| "eval_runtime": 25.8181, | |
| "eval_samples_per_second": 35.44, | |
| "eval_steps_per_second": 4.454, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.9931271477663232e-05, | |
| "loss": 0.3687, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 1.9587628865979382e-05, | |
| "loss": 0.3601, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.9243986254295536e-05, | |
| "loss": 0.3455, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 1.8900343642611683e-05, | |
| "loss": 0.3983, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.8556701030927837e-05, | |
| "loss": 0.3627, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.8213058419243987e-05, | |
| "loss": 0.3731, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.7869415807560138e-05, | |
| "loss": 0.3517, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.7525773195876288e-05, | |
| "loss": 0.3834, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 1.7182130584192442e-05, | |
| "loss": 0.3294, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.6838487972508592e-05, | |
| "loss": 0.301, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 1.6494845360824743e-05, | |
| "loss": 0.3338, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.6151202749140896e-05, | |
| "loss": 0.3375, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.5807560137457044e-05, | |
| "loss": 0.359, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.5463917525773197e-05, | |
| "loss": 0.3326, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9650273224043716, | |
| "eval_loss": 0.1366710066795349, | |
| "eval_runtime": 26.9372, | |
| "eval_samples_per_second": 33.968, | |
| "eval_steps_per_second": 4.269, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.5120274914089346e-05, | |
| "loss": 0.3346, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.47766323024055e-05, | |
| "loss": 0.3585, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.4432989690721649e-05, | |
| "loss": 0.3262, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 1.40893470790378e-05, | |
| "loss": 0.329, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1.3745704467353954e-05, | |
| "loss": 0.3365, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.3402061855670103e-05, | |
| "loss": 0.3348, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.3058419243986255e-05, | |
| "loss": 0.3666, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 1.2714776632302406e-05, | |
| "loss": 0.3044, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.2371134020618558e-05, | |
| "loss": 0.3048, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.2027491408934708e-05, | |
| "loss": 0.2838, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 1.168384879725086e-05, | |
| "loss": 0.3713, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 1.134020618556701e-05, | |
| "loss": 0.3235, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 1.0996563573883161e-05, | |
| "loss": 0.3703, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.0652920962199313e-05, | |
| "loss": 0.3923, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.0309278350515464e-05, | |
| "loss": 0.3166, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9737704918032787, | |
| "eval_loss": 0.11094537377357483, | |
| "eval_runtime": 26.7688, | |
| "eval_samples_per_second": 34.182, | |
| "eval_steps_per_second": 4.296, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 9.965635738831616e-06, | |
| "loss": 0.3415, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 9.621993127147768e-06, | |
| "loss": 0.3692, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 9.278350515463918e-06, | |
| "loss": 0.3247, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 8.934707903780069e-06, | |
| "loss": 0.2912, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 8.591065292096221e-06, | |
| "loss": 0.3685, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 8.247422680412371e-06, | |
| "loss": 0.3102, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 7.903780068728522e-06, | |
| "loss": 0.3595, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 7.560137457044673e-06, | |
| "loss": 0.3045, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 7.216494845360824e-06, | |
| "loss": 0.3092, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 6.872852233676977e-06, | |
| "loss": 0.3247, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 6.529209621993128e-06, | |
| "loss": 0.3052, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 6.185567010309279e-06, | |
| "loss": 0.2978, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 5.84192439862543e-06, | |
| "loss": 0.3043, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 5.498281786941581e-06, | |
| "loss": 0.3189, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 5.154639175257732e-06, | |
| "loss": 0.3492, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9759562841530055, | |
| "eval_loss": 0.1108308881521225, | |
| "eval_runtime": 26.5259, | |
| "eval_samples_per_second": 34.495, | |
| "eval_steps_per_second": 4.335, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 4.810996563573884e-06, | |
| "loss": 0.3084, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 4.467353951890034e-06, | |
| "loss": 0.2987, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 4.123711340206186e-06, | |
| "loss": 0.3322, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.7800687285223365e-06, | |
| "loss": 0.293, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.4364261168384886e-06, | |
| "loss": 0.338, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 3.0927835051546395e-06, | |
| "loss": 0.304, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 2.7491408934707903e-06, | |
| "loss": 0.3074, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 2.405498281786942e-06, | |
| "loss": 0.3073, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 2.061855670103093e-06, | |
| "loss": 0.2956, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.7182130584192443e-06, | |
| "loss": 0.3137, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 1.3745704467353952e-06, | |
| "loss": 0.3035, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.0309278350515464e-06, | |
| "loss": 0.3166, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 6.872852233676976e-07, | |
| "loss": 0.2696, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 3.436426116838488e-07, | |
| "loss": 0.3482, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.3228, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9781420765027322, | |
| "eval_loss": 0.1102537140250206, | |
| "eval_runtime": 26.664, | |
| "eval_samples_per_second": 34.316, | |
| "eval_steps_per_second": 4.313, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1470, | |
| "total_flos": 1.7471888881490534e+18, | |
| "train_loss": 0.49037140356440123, | |
| "train_runtime": 8760.81, | |
| "train_samples_per_second": 9.391, | |
| "train_steps_per_second": 0.168 | |
| } | |
| ], | |
| "max_steps": 1470, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.7471888881490534e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |