| { | |
| "best_metric": 0.2699800729751587, | |
| "best_model_checkpoint": "./microsoft-resnet-50/checkpoint-1300", | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 1440, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019875, | |
| "loss": 1.7161, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019736111111111113, | |
| "loss": 1.6446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019597222222222222, | |
| "loss": 1.5387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019458333333333334, | |
| "loss": 1.496, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019319444444444446, | |
| "loss": 1.447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00019180555555555558, | |
| "loss": 1.3626, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019055555555555555, | |
| "loss": 1.4671, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00018916666666666667, | |
| "loss": 1.3349, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00018777777777777779, | |
| "loss": 1.4366, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001863888888888889, | |
| "loss": 1.2751, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.2986714839935303, | |
| "eval_runtime": 21.8933, | |
| "eval_samples_per_second": 32.887, | |
| "eval_steps_per_second": 4.111, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 1.1875, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00018361111111111112, | |
| "loss": 1.3566, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018222222222222224, | |
| "loss": 1.2153, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018083333333333336, | |
| "loss": 1.1098, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017944444444444445, | |
| "loss": 1.1864, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017805555555555554, | |
| "loss": 1.1079, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00017666666666666666, | |
| "loss": 0.9994, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00017527777777777778, | |
| "loss": 0.9984, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001738888888888889, | |
| "loss": 0.9585, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00017250000000000002, | |
| "loss": 0.9665, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.7416666666666667, | |
| "eval_loss": 0.8483774662017822, | |
| "eval_runtime": 21.2905, | |
| "eval_samples_per_second": 33.818, | |
| "eval_steps_per_second": 4.227, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001711111111111111, | |
| "loss": 0.9685, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00016972222222222223, | |
| "loss": 0.9409, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00016833333333333335, | |
| "loss": 0.8592, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016694444444444447, | |
| "loss": 0.8387, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00016555555555555556, | |
| "loss": 0.8408, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00016416666666666668, | |
| "loss": 0.9102, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00016277777777777777, | |
| "loss": 0.7093, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001613888888888889, | |
| "loss": 0.579, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00016, | |
| "loss": 0.7381, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0001586111111111111, | |
| "loss": 0.7891, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.8013888888888889, | |
| "eval_loss": 0.5900831818580627, | |
| "eval_runtime": 20.5317, | |
| "eval_samples_per_second": 35.068, | |
| "eval_steps_per_second": 4.383, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00015722222222222223, | |
| "loss": 0.7218, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00015583333333333334, | |
| "loss": 0.6484, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00015444444444444446, | |
| "loss": 0.7177, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00015305555555555556, | |
| "loss": 0.6766, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00015166666666666668, | |
| "loss": 0.5569, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001502777777777778, | |
| "loss": 0.5577, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001488888888888889, | |
| "loss": 0.6603, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001475, | |
| "loss": 0.5291, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001461111111111111, | |
| "loss": 0.6346, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00014472222222222222, | |
| "loss": 0.6075, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_accuracy": 0.8069444444444445, | |
| "eval_loss": 0.5183315873146057, | |
| "eval_runtime": 20.4274, | |
| "eval_samples_per_second": 35.247, | |
| "eval_steps_per_second": 4.406, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00014333333333333334, | |
| "loss": 0.4894, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00014194444444444446, | |
| "loss": 0.6165, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00014055555555555555, | |
| "loss": 0.6294, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00013916666666666667, | |
| "loss": 0.626, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0001377777777777778, | |
| "loss": 0.6382, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001363888888888889, | |
| "loss": 0.5621, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013500000000000003, | |
| "loss": 0.5238, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013361111111111112, | |
| "loss": 0.4544, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00013222222222222221, | |
| "loss": 0.4835, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00013083333333333333, | |
| "loss": 0.4731, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.8277777777777777, | |
| "eval_loss": 0.46654924750328064, | |
| "eval_runtime": 20.6176, | |
| "eval_samples_per_second": 34.922, | |
| "eval_steps_per_second": 4.365, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00012944444444444445, | |
| "loss": 0.5663, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00012805555555555555, | |
| "loss": 0.4657, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00012666666666666666, | |
| "loss": 0.3986, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00012527777777777778, | |
| "loss": 0.4535, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001238888888888889, | |
| "loss": 0.5688, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00012250000000000002, | |
| "loss": 0.4095, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0001211111111111111, | |
| "loss": 0.4686, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00011972222222222222, | |
| "loss": 0.3797, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00011833333333333334, | |
| "loss": 0.4314, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00011694444444444446, | |
| "loss": 0.473, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.8388888888888889, | |
| "eval_loss": 0.41562873125076294, | |
| "eval_runtime": 20.4078, | |
| "eval_samples_per_second": 35.281, | |
| "eval_steps_per_second": 4.41, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 0.4057, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00011416666666666667, | |
| "loss": 0.3984, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00011277777777777778, | |
| "loss": 0.354, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0001113888888888889, | |
| "loss": 0.3913, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.3833, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00010861111111111111, | |
| "loss": 0.45, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010722222222222223, | |
| "loss": 0.3667, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00010583333333333334, | |
| "loss": 0.4559, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00010444444444444445, | |
| "loss": 0.377, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00010305555555555555, | |
| "loss": 0.3476, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.8625, | |
| "eval_loss": 0.3583880066871643, | |
| "eval_runtime": 20.4332, | |
| "eval_samples_per_second": 35.237, | |
| "eval_steps_per_second": 4.405, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010166666666666667, | |
| "loss": 0.4298, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00010027777777777779, | |
| "loss": 0.2979, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.888888888888889e-05, | |
| "loss": 0.2801, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.75e-05, | |
| "loss": 0.2997, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.611111111111112e-05, | |
| "loss": 0.3106, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.472222222222222e-05, | |
| "loss": 0.395, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.2502, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.194444444444445e-05, | |
| "loss": 0.3314, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 9.055555555555556e-05, | |
| "loss": 0.2078, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.916666666666667e-05, | |
| "loss": 0.3235, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_accuracy": 0.8652777777777778, | |
| "eval_loss": 0.35252687335014343, | |
| "eval_runtime": 20.5648, | |
| "eval_samples_per_second": 35.011, | |
| "eval_steps_per_second": 4.376, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 8.777777777777778e-05, | |
| "loss": 0.3869, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 8.63888888888889e-05, | |
| "loss": 0.308, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.3955, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 8.361111111111111e-05, | |
| "loss": 0.3579, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.222222222222222e-05, | |
| "loss": 0.2413, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.083333333333334e-05, | |
| "loss": 0.2826, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 7.944444444444444e-05, | |
| "loss": 0.2625, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 7.805555555555556e-05, | |
| "loss": 0.2701, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 0.2574, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.527777777777777e-05, | |
| "loss": 0.2648, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.8847222222222222, | |
| "eval_loss": 0.32447561621665955, | |
| "eval_runtime": 20.794, | |
| "eval_samples_per_second": 34.625, | |
| "eval_steps_per_second": 4.328, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.38888888888889e-05, | |
| "loss": 0.2452, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.25e-05, | |
| "loss": 0.2738, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 0.359, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.972222222222223e-05, | |
| "loss": 0.2361, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.833333333333333e-05, | |
| "loss": 0.2952, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.694444444444444e-05, | |
| "loss": 0.3463, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 6.555555555555556e-05, | |
| "loss": 0.254, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.416666666666668e-05, | |
| "loss": 0.2879, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 6.277777777777778e-05, | |
| "loss": 0.304, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.13888888888889e-05, | |
| "loss": 0.3162, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_accuracy": 0.8888888888888888, | |
| "eval_loss": 0.32011502981185913, | |
| "eval_runtime": 20.3712, | |
| "eval_samples_per_second": 35.344, | |
| "eval_steps_per_second": 4.418, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2438, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 5.8611111111111114e-05, | |
| "loss": 0.2046, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 5.722222222222222e-05, | |
| "loss": 0.2474, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 5.583333333333334e-05, | |
| "loss": 0.1641, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.4444444444444446e-05, | |
| "loss": 0.1701, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.305555555555556e-05, | |
| "loss": 0.3574, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 5.166666666666667e-05, | |
| "loss": 0.3587, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.027777777777778e-05, | |
| "loss": 0.2541, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.1796, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.1631, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.8888888888888888, | |
| "eval_loss": 0.3001420199871063, | |
| "eval_runtime": 20.5513, | |
| "eval_samples_per_second": 35.034, | |
| "eval_steps_per_second": 4.379, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.1814, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 4.472222222222223e-05, | |
| "loss": 0.2224, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.2558, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.194444444444445e-05, | |
| "loss": 0.2015, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.1935, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.9166666666666665e-05, | |
| "loss": 0.0995, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.3104, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.638888888888889e-05, | |
| "loss": 0.2151, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1301, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3611111111111116e-05, | |
| "loss": 0.2089, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_accuracy": 0.8986111111111111, | |
| "eval_loss": 0.3063691556453705, | |
| "eval_runtime": 20.4185, | |
| "eval_samples_per_second": 35.262, | |
| "eval_steps_per_second": 4.408, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.1688, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.0833333333333335e-05, | |
| "loss": 0.1876, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.1789, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 2.8055555555555557e-05, | |
| "loss": 0.2619, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.2282, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 2.527777777777778e-05, | |
| "loss": 0.1946, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.1774, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.1341, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.1997, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.9722222222222224e-05, | |
| "loss": 0.1675, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_accuracy": 0.9069444444444444, | |
| "eval_loss": 0.2699800729751587, | |
| "eval_runtime": 20.2148, | |
| "eval_samples_per_second": 35.617, | |
| "eval_steps_per_second": 4.452, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.1926, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6944444444444446e-05, | |
| "loss": 0.1852, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.1892, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4166666666666668e-05, | |
| "loss": 0.1566, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 0.1548, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.138888888888889e-05, | |
| "loss": 0.2014, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1e-05, | |
| "loss": 0.201, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 8.611111111111112e-06, | |
| "loss": 0.2024, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 0.1275, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 0.2036, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "eval_accuracy": 0.9027777777777778, | |
| "eval_loss": 0.2744775116443634, | |
| "eval_runtime": 21.0629, | |
| "eval_samples_per_second": 34.183, | |
| "eval_steps_per_second": 4.273, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.1253, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.0555555555555556e-06, | |
| "loss": 0.1474, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.1865, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.777777777777778e-07, | |
| "loss": 0.1624, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1440, | |
| "total_flos": 4.894342454653747e+17, | |
| "train_loss": 0.5006750662293699, | |
| "train_runtime": 1387.5559, | |
| "train_samples_per_second": 16.605, | |
| "train_steps_per_second": 1.038 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8805555555555555, | |
| "eval_loss": 0.35284003615379333, | |
| "eval_runtime": 21.8169, | |
| "eval_samples_per_second": 33.002, | |
| "eval_steps_per_second": 4.125, | |
| "step": 1440 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1440, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "total_flos": 4.894342454653747e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |