| { |
| "best_metric": 0.6226525821596244, |
| "best_model_checkpoint": "large-algae-vit-rgb/checkpoint-2280", |
| "epoch": 20.0, |
| "global_step": 2400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 2.0833333333333334e-06, |
| "loss": 1.7796, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 1.6643, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 6.25e-06, |
| "loss": 1.4798, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 1.3417, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 1.0416666666666668e-05, |
| "loss": 1.2473, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 1.25e-05, |
| "loss": 1.1897, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 1.4583333333333335e-05, |
| "loss": 1.1835, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.1931, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 1.1324, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 1.1343, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 2.2916666666666667e-05, |
| "loss": 1.124, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 2.5e-05, |
| "loss": 1.1433, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5575117370892019, |
| "eval_loss": 1.0966269969940186, |
| "eval_runtime": 22.9114, |
| "eval_samples_per_second": 74.374, |
| "eval_steps_per_second": 2.357, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 2.7083333333333332e-05, |
| "loss": 1.1211, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 1.0712, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 3.125e-05, |
| "loss": 1.0919, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.0908, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 3.541666666666667e-05, |
| "loss": 1.0912, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.1271, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 3.958333333333333e-05, |
| "loss": 1.0785, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 1.0361, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 4.375e-05, |
| "loss": 1.1093, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 1.0827, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 4.791666666666667e-05, |
| "loss": 1.0748, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 5e-05, |
| "loss": 1.0507, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5856807511737089, |
| "eval_loss": 1.0356614589691162, |
| "eval_runtime": 22.7063, |
| "eval_samples_per_second": 75.045, |
| "eval_steps_per_second": 2.378, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 4.976851851851852e-05, |
| "loss": 1.0658, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 4.9537037037037035e-05, |
| "loss": 1.0552, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 4.930555555555556e-05, |
| "loss": 1.0831, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 4.9074074074074075e-05, |
| "loss": 1.0378, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 4.8842592592592595e-05, |
| "loss": 1.0336, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 4.8611111111111115e-05, |
| "loss": 1.0519, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 4.837962962962963e-05, |
| "loss": 1.0065, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 4.814814814814815e-05, |
| "loss": 1.0432, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 4.791666666666667e-05, |
| "loss": 1.0496, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 4.768518518518519e-05, |
| "loss": 1.0635, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.92, |
| "learning_rate": 4.745370370370371e-05, |
| "loss": 1.0402, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.722222222222222e-05, |
| "loss": 1.0104, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5921361502347418, |
| "eval_loss": 1.0168485641479492, |
| "eval_runtime": 22.8587, |
| "eval_samples_per_second": 74.545, |
| "eval_steps_per_second": 2.362, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 4.699074074074074e-05, |
| "loss": 0.9874, |
| "step": 370 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 4.675925925925926e-05, |
| "loss": 1.0564, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 4.652777777777778e-05, |
| "loss": 1.002, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 4.62962962962963e-05, |
| "loss": 1.0306, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 4.6064814814814814e-05, |
| "loss": 1.0384, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 4.5833333333333334e-05, |
| "loss": 1.0109, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 4.5601851851851854e-05, |
| "loss": 1.0797, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 4.5370370370370374e-05, |
| "loss": 1.0382, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 4.5138888888888894e-05, |
| "loss": 1.0057, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.83, |
| "learning_rate": 4.490740740740741e-05, |
| "loss": 1.0405, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.92, |
| "learning_rate": 4.467592592592593e-05, |
| "loss": 1.015, |
| "step": 470 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 1.0353, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.5856807511737089, |
| "eval_loss": 1.0344651937484741, |
| "eval_runtime": 22.8799, |
| "eval_samples_per_second": 74.476, |
| "eval_steps_per_second": 2.36, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 4.4212962962962966e-05, |
| "loss": 1.0024, |
| "step": 490 |
| }, |
| { |
| "epoch": 4.17, |
| "learning_rate": 4.3981481481481486e-05, |
| "loss": 0.9605, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.25, |
| "learning_rate": 4.375e-05, |
| "loss": 1.0132, |
| "step": 510 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 4.351851851851852e-05, |
| "loss": 0.9964, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.42, |
| "learning_rate": 4.328703703703704e-05, |
| "loss": 1.0063, |
| "step": 530 |
| }, |
| { |
| "epoch": 4.5, |
| "learning_rate": 4.305555555555556e-05, |
| "loss": 1.0355, |
| "step": 540 |
| }, |
| { |
| "epoch": 4.58, |
| "learning_rate": 4.282407407407408e-05, |
| "loss": 1.0556, |
| "step": 550 |
| }, |
| { |
| "epoch": 4.67, |
| "learning_rate": 4.259259259259259e-05, |
| "loss": 0.9885, |
| "step": 560 |
| }, |
| { |
| "epoch": 4.75, |
| "learning_rate": 4.236111111111111e-05, |
| "loss": 0.9804, |
| "step": 570 |
| }, |
| { |
| "epoch": 4.83, |
| "learning_rate": 4.212962962962963e-05, |
| "loss": 1.0036, |
| "step": 580 |
| }, |
| { |
| "epoch": 4.92, |
| "learning_rate": 4.1898148148148145e-05, |
| "loss": 1.0063, |
| "step": 590 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.166666666666667e-05, |
| "loss": 0.9629, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6015258215962441, |
| "eval_loss": 0.983875036239624, |
| "eval_runtime": 22.9086, |
| "eval_samples_per_second": 74.383, |
| "eval_steps_per_second": 2.357, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.08, |
| "learning_rate": 4.1435185185185185e-05, |
| "loss": 0.9983, |
| "step": 610 |
| }, |
| { |
| "epoch": 5.17, |
| "learning_rate": 4.1203703703703705e-05, |
| "loss": 1.0425, |
| "step": 620 |
| }, |
| { |
| "epoch": 5.25, |
| "learning_rate": 4.0972222222222225e-05, |
| "loss": 1.0025, |
| "step": 630 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.9785, |
| "step": 640 |
| }, |
| { |
| "epoch": 5.42, |
| "learning_rate": 4.0509259259259265e-05, |
| "loss": 1.0057, |
| "step": 650 |
| }, |
| { |
| "epoch": 5.5, |
| "learning_rate": 4.027777777777778e-05, |
| "loss": 0.9692, |
| "step": 660 |
| }, |
| { |
| "epoch": 5.58, |
| "learning_rate": 4.00462962962963e-05, |
| "loss": 0.9976, |
| "step": 670 |
| }, |
| { |
| "epoch": 5.67, |
| "learning_rate": 3.981481481481482e-05, |
| "loss": 0.9917, |
| "step": 680 |
| }, |
| { |
| "epoch": 5.75, |
| "learning_rate": 3.958333333333333e-05, |
| "loss": 0.9818, |
| "step": 690 |
| }, |
| { |
| "epoch": 5.83, |
| "learning_rate": 3.935185185185186e-05, |
| "loss": 0.996, |
| "step": 700 |
| }, |
| { |
| "epoch": 5.92, |
| "learning_rate": 3.912037037037037e-05, |
| "loss": 0.9892, |
| "step": 710 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.9684, |
| "step": 720 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6068075117370892, |
| "eval_loss": 0.9672098159790039, |
| "eval_runtime": 22.7827, |
| "eval_samples_per_second": 74.794, |
| "eval_steps_per_second": 2.37, |
| "step": 720 |
| }, |
| { |
| "epoch": 6.08, |
| "learning_rate": 3.865740740740741e-05, |
| "loss": 0.9977, |
| "step": 730 |
| }, |
| { |
| "epoch": 6.17, |
| "learning_rate": 3.8425925925925924e-05, |
| "loss": 0.9858, |
| "step": 740 |
| }, |
| { |
| "epoch": 6.25, |
| "learning_rate": 3.8194444444444444e-05, |
| "loss": 1.0029, |
| "step": 750 |
| }, |
| { |
| "epoch": 6.33, |
| "learning_rate": 3.7962962962962964e-05, |
| "loss": 0.9715, |
| "step": 760 |
| }, |
| { |
| "epoch": 6.42, |
| "learning_rate": 3.7731481481481484e-05, |
| "loss": 0.9484, |
| "step": 770 |
| }, |
| { |
| "epoch": 6.5, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.9948, |
| "step": 780 |
| }, |
| { |
| "epoch": 6.58, |
| "learning_rate": 3.726851851851852e-05, |
| "loss": 0.9935, |
| "step": 790 |
| }, |
| { |
| "epoch": 6.67, |
| "learning_rate": 3.7037037037037037e-05, |
| "loss": 1.0129, |
| "step": 800 |
| }, |
| { |
| "epoch": 6.75, |
| "learning_rate": 3.6805555555555556e-05, |
| "loss": 0.94, |
| "step": 810 |
| }, |
| { |
| "epoch": 6.83, |
| "learning_rate": 3.6574074074074076e-05, |
| "loss": 0.9886, |
| "step": 820 |
| }, |
| { |
| "epoch": 6.92, |
| "learning_rate": 3.6342592592592596e-05, |
| "loss": 0.9441, |
| "step": 830 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 3.611111111111111e-05, |
| "loss": 0.9727, |
| "step": 840 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.6132629107981221, |
| "eval_loss": 0.9590299129486084, |
| "eval_runtime": 22.8896, |
| "eval_samples_per_second": 74.444, |
| "eval_steps_per_second": 2.359, |
| "step": 840 |
| }, |
| { |
| "epoch": 7.08, |
| "learning_rate": 3.587962962962963e-05, |
| "loss": 0.9784, |
| "step": 850 |
| }, |
| { |
| "epoch": 7.17, |
| "learning_rate": 3.564814814814815e-05, |
| "loss": 0.9698, |
| "step": 860 |
| }, |
| { |
| "epoch": 7.25, |
| "learning_rate": 3.541666666666667e-05, |
| "loss": 0.9599, |
| "step": 870 |
| }, |
| { |
| "epoch": 7.33, |
| "learning_rate": 3.518518518518519e-05, |
| "loss": 0.961, |
| "step": 880 |
| }, |
| { |
| "epoch": 7.42, |
| "learning_rate": 3.49537037037037e-05, |
| "loss": 0.9919, |
| "step": 890 |
| }, |
| { |
| "epoch": 7.5, |
| "learning_rate": 3.472222222222222e-05, |
| "loss": 0.9915, |
| "step": 900 |
| }, |
| { |
| "epoch": 7.58, |
| "learning_rate": 3.449074074074074e-05, |
| "loss": 0.9777, |
| "step": 910 |
| }, |
| { |
| "epoch": 7.67, |
| "learning_rate": 3.425925925925926e-05, |
| "loss": 0.9584, |
| "step": 920 |
| }, |
| { |
| "epoch": 7.75, |
| "learning_rate": 3.402777777777778e-05, |
| "loss": 0.9627, |
| "step": 930 |
| }, |
| { |
| "epoch": 7.83, |
| "learning_rate": 3.3796296296296295e-05, |
| "loss": 0.9634, |
| "step": 940 |
| }, |
| { |
| "epoch": 7.92, |
| "learning_rate": 3.3564814814814815e-05, |
| "loss": 0.9518, |
| "step": 950 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.9626, |
| "step": 960 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.6126760563380281, |
| "eval_loss": 0.9426460266113281, |
| "eval_runtime": 22.8408, |
| "eval_samples_per_second": 74.603, |
| "eval_steps_per_second": 2.364, |
| "step": 960 |
| }, |
| { |
| "epoch": 8.08, |
| "learning_rate": 3.3101851851851855e-05, |
| "loss": 0.9318, |
| "step": 970 |
| }, |
| { |
| "epoch": 8.17, |
| "learning_rate": 3.2870370370370375e-05, |
| "loss": 0.993, |
| "step": 980 |
| }, |
| { |
| "epoch": 8.25, |
| "learning_rate": 3.263888888888889e-05, |
| "loss": 0.9247, |
| "step": 990 |
| }, |
| { |
| "epoch": 8.33, |
| "learning_rate": 3.240740740740741e-05, |
| "loss": 0.9803, |
| "step": 1000 |
| }, |
| { |
| "epoch": 8.42, |
| "learning_rate": 3.217592592592593e-05, |
| "loss": 0.9353, |
| "step": 1010 |
| }, |
| { |
| "epoch": 8.5, |
| "learning_rate": 3.194444444444444e-05, |
| "loss": 0.9683, |
| "step": 1020 |
| }, |
| { |
| "epoch": 8.58, |
| "learning_rate": 3.171296296296297e-05, |
| "loss": 0.9368, |
| "step": 1030 |
| }, |
| { |
| "epoch": 8.67, |
| "learning_rate": 3.148148148148148e-05, |
| "loss": 0.9811, |
| "step": 1040 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 3.125e-05, |
| "loss": 0.9497, |
| "step": 1050 |
| }, |
| { |
| "epoch": 8.83, |
| "learning_rate": 3.101851851851852e-05, |
| "loss": 0.9227, |
| "step": 1060 |
| }, |
| { |
| "epoch": 8.92, |
| "learning_rate": 3.0787037037037034e-05, |
| "loss": 0.9876, |
| "step": 1070 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 3.055555555555556e-05, |
| "loss": 0.9857, |
| "step": 1080 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.607981220657277, |
| "eval_loss": 0.9669484496116638, |
| "eval_runtime": 22.8277, |
| "eval_samples_per_second": 74.646, |
| "eval_steps_per_second": 2.366, |
| "step": 1080 |
| }, |
| { |
| "epoch": 9.08, |
| "learning_rate": 3.0324074074074077e-05, |
| "loss": 0.8884, |
| "step": 1090 |
| }, |
| { |
| "epoch": 9.17, |
| "learning_rate": 3.0092592592592593e-05, |
| "loss": 0.9424, |
| "step": 1100 |
| }, |
| { |
| "epoch": 9.25, |
| "learning_rate": 2.9861111111111113e-05, |
| "loss": 0.9701, |
| "step": 1110 |
| }, |
| { |
| "epoch": 9.33, |
| "learning_rate": 2.962962962962963e-05, |
| "loss": 0.9577, |
| "step": 1120 |
| }, |
| { |
| "epoch": 9.42, |
| "learning_rate": 2.9398148148148146e-05, |
| "loss": 0.9542, |
| "step": 1130 |
| }, |
| { |
| "epoch": 9.5, |
| "learning_rate": 2.916666666666667e-05, |
| "loss": 0.9483, |
| "step": 1140 |
| }, |
| { |
| "epoch": 9.58, |
| "learning_rate": 2.8935185185185186e-05, |
| "loss": 0.9406, |
| "step": 1150 |
| }, |
| { |
| "epoch": 9.67, |
| "learning_rate": 2.8703703703703706e-05, |
| "loss": 0.9335, |
| "step": 1160 |
| }, |
| { |
| "epoch": 9.75, |
| "learning_rate": 2.8472222222222223e-05, |
| "loss": 0.9205, |
| "step": 1170 |
| }, |
| { |
| "epoch": 9.83, |
| "learning_rate": 2.824074074074074e-05, |
| "loss": 0.9193, |
| "step": 1180 |
| }, |
| { |
| "epoch": 9.92, |
| "learning_rate": 2.8009259259259263e-05, |
| "loss": 0.956, |
| "step": 1190 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.9321, |
| "step": 1200 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.6109154929577465, |
| "eval_loss": 0.9396657347679138, |
| "eval_runtime": 22.8434, |
| "eval_samples_per_second": 74.595, |
| "eval_steps_per_second": 2.364, |
| "step": 1200 |
| }, |
| { |
| "epoch": 10.08, |
| "learning_rate": 2.75462962962963e-05, |
| "loss": 0.9324, |
| "step": 1210 |
| }, |
| { |
| "epoch": 10.17, |
| "learning_rate": 2.7314814814814816e-05, |
| "loss": 0.9112, |
| "step": 1220 |
| }, |
| { |
| "epoch": 10.25, |
| "learning_rate": 2.7083333333333332e-05, |
| "loss": 0.9613, |
| "step": 1230 |
| }, |
| { |
| "epoch": 10.33, |
| "learning_rate": 2.6851851851851855e-05, |
| "loss": 0.9083, |
| "step": 1240 |
| }, |
| { |
| "epoch": 10.42, |
| "learning_rate": 2.6620370370370372e-05, |
| "loss": 0.9691, |
| "step": 1250 |
| }, |
| { |
| "epoch": 10.5, |
| "learning_rate": 2.6388888888888892e-05, |
| "loss": 0.9256, |
| "step": 1260 |
| }, |
| { |
| "epoch": 10.58, |
| "learning_rate": 2.615740740740741e-05, |
| "loss": 0.929, |
| "step": 1270 |
| }, |
| { |
| "epoch": 10.67, |
| "learning_rate": 2.5925925925925925e-05, |
| "loss": 0.9056, |
| "step": 1280 |
| }, |
| { |
| "epoch": 10.75, |
| "learning_rate": 2.5694444444444445e-05, |
| "loss": 0.979, |
| "step": 1290 |
| }, |
| { |
| "epoch": 10.83, |
| "learning_rate": 2.5462962962962965e-05, |
| "loss": 0.9242, |
| "step": 1300 |
| }, |
| { |
| "epoch": 10.92, |
| "learning_rate": 2.5231481481481485e-05, |
| "loss": 0.9118, |
| "step": 1310 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 2.5e-05, |
| "loss": 0.9052, |
| "step": 1320 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.602112676056338, |
| "eval_loss": 0.9402132034301758, |
| "eval_runtime": 23.1769, |
| "eval_samples_per_second": 73.522, |
| "eval_steps_per_second": 2.33, |
| "step": 1320 |
| }, |
| { |
| "epoch": 11.08, |
| "learning_rate": 2.4768518518518518e-05, |
| "loss": 0.9046, |
| "step": 1330 |
| }, |
| { |
| "epoch": 11.17, |
| "learning_rate": 2.4537037037037038e-05, |
| "loss": 0.9401, |
| "step": 1340 |
| }, |
| { |
| "epoch": 11.25, |
| "learning_rate": 2.4305555555555558e-05, |
| "loss": 0.8835, |
| "step": 1350 |
| }, |
| { |
| "epoch": 11.33, |
| "learning_rate": 2.4074074074074074e-05, |
| "loss": 0.8835, |
| "step": 1360 |
| }, |
| { |
| "epoch": 11.42, |
| "learning_rate": 2.3842592592592594e-05, |
| "loss": 0.8896, |
| "step": 1370 |
| }, |
| { |
| "epoch": 11.5, |
| "learning_rate": 2.361111111111111e-05, |
| "loss": 0.9183, |
| "step": 1380 |
| }, |
| { |
| "epoch": 11.58, |
| "learning_rate": 2.337962962962963e-05, |
| "loss": 0.9436, |
| "step": 1390 |
| }, |
| { |
| "epoch": 11.67, |
| "learning_rate": 2.314814814814815e-05, |
| "loss": 0.8846, |
| "step": 1400 |
| }, |
| { |
| "epoch": 11.75, |
| "learning_rate": 2.2916666666666667e-05, |
| "loss": 0.9532, |
| "step": 1410 |
| }, |
| { |
| "epoch": 11.83, |
| "learning_rate": 2.2685185185185187e-05, |
| "loss": 0.9215, |
| "step": 1420 |
| }, |
| { |
| "epoch": 11.92, |
| "learning_rate": 2.2453703703703703e-05, |
| "loss": 0.933, |
| "step": 1430 |
| }, |
| { |
| "epoch": 12.0, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.9457, |
| "step": 1440 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.6214788732394366, |
| "eval_loss": 0.9181148409843445, |
| "eval_runtime": 22.9806, |
| "eval_samples_per_second": 74.15, |
| "eval_steps_per_second": 2.35, |
| "step": 1440 |
| }, |
| { |
| "epoch": 12.08, |
| "learning_rate": 2.1990740740740743e-05, |
| "loss": 0.8826, |
| "step": 1450 |
| }, |
| { |
| "epoch": 12.17, |
| "learning_rate": 2.175925925925926e-05, |
| "loss": 0.908, |
| "step": 1460 |
| }, |
| { |
| "epoch": 12.25, |
| "learning_rate": 2.152777777777778e-05, |
| "loss": 0.916, |
| "step": 1470 |
| }, |
| { |
| "epoch": 12.33, |
| "learning_rate": 2.1296296296296296e-05, |
| "loss": 0.8875, |
| "step": 1480 |
| }, |
| { |
| "epoch": 12.42, |
| "learning_rate": 2.1064814814814816e-05, |
| "loss": 0.897, |
| "step": 1490 |
| }, |
| { |
| "epoch": 12.5, |
| "learning_rate": 2.0833333333333336e-05, |
| "loss": 0.9158, |
| "step": 1500 |
| }, |
| { |
| "epoch": 12.58, |
| "learning_rate": 2.0601851851851853e-05, |
| "loss": 0.9398, |
| "step": 1510 |
| }, |
| { |
| "epoch": 12.67, |
| "learning_rate": 2.037037037037037e-05, |
| "loss": 0.9385, |
| "step": 1520 |
| }, |
| { |
| "epoch": 12.75, |
| "learning_rate": 2.013888888888889e-05, |
| "loss": 0.8998, |
| "step": 1530 |
| }, |
| { |
| "epoch": 12.83, |
| "learning_rate": 1.990740740740741e-05, |
| "loss": 0.9058, |
| "step": 1540 |
| }, |
| { |
| "epoch": 12.92, |
| "learning_rate": 1.967592592592593e-05, |
| "loss": 0.8997, |
| "step": 1550 |
| }, |
| { |
| "epoch": 13.0, |
| "learning_rate": 1.9444444444444445e-05, |
| "loss": 0.9101, |
| "step": 1560 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.6185446009389671, |
| "eval_loss": 0.9350312352180481, |
| "eval_runtime": 23.0031, |
| "eval_samples_per_second": 74.077, |
| "eval_steps_per_second": 2.348, |
| "step": 1560 |
| }, |
| { |
| "epoch": 13.08, |
| "learning_rate": 1.9212962962962962e-05, |
| "loss": 0.9129, |
| "step": 1570 |
| }, |
| { |
| "epoch": 13.17, |
| "learning_rate": 1.8981481481481482e-05, |
| "loss": 0.8878, |
| "step": 1580 |
| }, |
| { |
| "epoch": 13.25, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 0.8675, |
| "step": 1590 |
| }, |
| { |
| "epoch": 13.33, |
| "learning_rate": 1.8518518518518518e-05, |
| "loss": 0.8817, |
| "step": 1600 |
| }, |
| { |
| "epoch": 13.42, |
| "learning_rate": 1.8287037037037038e-05, |
| "loss": 0.8981, |
| "step": 1610 |
| }, |
| { |
| "epoch": 13.5, |
| "learning_rate": 1.8055555555555555e-05, |
| "loss": 0.9016, |
| "step": 1620 |
| }, |
| { |
| "epoch": 13.58, |
| "learning_rate": 1.7824074074074075e-05, |
| "loss": 0.8743, |
| "step": 1630 |
| }, |
| { |
| "epoch": 13.67, |
| "learning_rate": 1.7592592592592595e-05, |
| "loss": 0.8778, |
| "step": 1640 |
| }, |
| { |
| "epoch": 13.75, |
| "learning_rate": 1.736111111111111e-05, |
| "loss": 0.8631, |
| "step": 1650 |
| }, |
| { |
| "epoch": 13.83, |
| "learning_rate": 1.712962962962963e-05, |
| "loss": 0.9453, |
| "step": 1660 |
| }, |
| { |
| "epoch": 13.92, |
| "learning_rate": 1.6898148148148148e-05, |
| "loss": 0.9266, |
| "step": 1670 |
| }, |
| { |
| "epoch": 14.0, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.8772, |
| "step": 1680 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.6050469483568075, |
| "eval_loss": 0.9537418484687805, |
| "eval_runtime": 22.909, |
| "eval_samples_per_second": 74.381, |
| "eval_steps_per_second": 2.357, |
| "step": 1680 |
| }, |
| { |
| "epoch": 14.08, |
| "learning_rate": 1.6435185185185187e-05, |
| "loss": 0.8748, |
| "step": 1690 |
| }, |
| { |
| "epoch": 14.17, |
| "learning_rate": 1.6203703703703704e-05, |
| "loss": 0.8794, |
| "step": 1700 |
| }, |
| { |
| "epoch": 14.25, |
| "learning_rate": 1.597222222222222e-05, |
| "loss": 0.8645, |
| "step": 1710 |
| }, |
| { |
| "epoch": 14.33, |
| "learning_rate": 1.574074074074074e-05, |
| "loss": 0.902, |
| "step": 1720 |
| }, |
| { |
| "epoch": 14.42, |
| "learning_rate": 1.550925925925926e-05, |
| "loss": 0.9094, |
| "step": 1730 |
| }, |
| { |
| "epoch": 14.5, |
| "learning_rate": 1.527777777777778e-05, |
| "loss": 0.9081, |
| "step": 1740 |
| }, |
| { |
| "epoch": 14.58, |
| "learning_rate": 1.5046296296296297e-05, |
| "loss": 0.8869, |
| "step": 1750 |
| }, |
| { |
| "epoch": 14.67, |
| "learning_rate": 1.4814814814814815e-05, |
| "loss": 0.8552, |
| "step": 1760 |
| }, |
| { |
| "epoch": 14.75, |
| "learning_rate": 1.4583333333333335e-05, |
| "loss": 0.9357, |
| "step": 1770 |
| }, |
| { |
| "epoch": 14.83, |
| "learning_rate": 1.4351851851851853e-05, |
| "loss": 0.8996, |
| "step": 1780 |
| }, |
| { |
| "epoch": 14.92, |
| "learning_rate": 1.412037037037037e-05, |
| "loss": 0.9254, |
| "step": 1790 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 1.388888888888889e-05, |
| "loss": 0.8865, |
| "step": 1800 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.6126760563380281, |
| "eval_loss": 0.9256580471992493, |
| "eval_runtime": 22.8459, |
| "eval_samples_per_second": 74.587, |
| "eval_steps_per_second": 2.364, |
| "step": 1800 |
| }, |
| { |
| "epoch": 15.08, |
| "learning_rate": 1.3657407407407408e-05, |
| "loss": 0.8656, |
| "step": 1810 |
| }, |
| { |
| "epoch": 15.17, |
| "learning_rate": 1.3425925925925928e-05, |
| "loss": 0.8727, |
| "step": 1820 |
| }, |
| { |
| "epoch": 15.25, |
| "learning_rate": 1.3194444444444446e-05, |
| "loss": 0.8891, |
| "step": 1830 |
| }, |
| { |
| "epoch": 15.33, |
| "learning_rate": 1.2962962962962962e-05, |
| "loss": 0.8763, |
| "step": 1840 |
| }, |
| { |
| "epoch": 15.42, |
| "learning_rate": 1.2731481481481482e-05, |
| "loss": 0.883, |
| "step": 1850 |
| }, |
| { |
| "epoch": 15.5, |
| "learning_rate": 1.25e-05, |
| "loss": 0.9007, |
| "step": 1860 |
| }, |
| { |
| "epoch": 15.58, |
| "learning_rate": 1.2268518518518519e-05, |
| "loss": 0.8868, |
| "step": 1870 |
| }, |
| { |
| "epoch": 15.67, |
| "learning_rate": 1.2037037037037037e-05, |
| "loss": 0.8687, |
| "step": 1880 |
| }, |
| { |
| "epoch": 15.75, |
| "learning_rate": 1.1805555555555555e-05, |
| "loss": 0.8334, |
| "step": 1890 |
| }, |
| { |
| "epoch": 15.83, |
| "learning_rate": 1.1574074074074075e-05, |
| "loss": 0.8756, |
| "step": 1900 |
| }, |
| { |
| "epoch": 15.92, |
| "learning_rate": 1.1342592592592593e-05, |
| "loss": 0.8799, |
| "step": 1910 |
| }, |
| { |
| "epoch": 16.0, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 0.8454, |
| "step": 1920 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.6214788732394366, |
| "eval_loss": 0.9159719347953796, |
| "eval_runtime": 22.7638, |
| "eval_samples_per_second": 74.856, |
| "eval_steps_per_second": 2.372, |
| "step": 1920 |
| }, |
| { |
| "epoch": 16.08, |
| "learning_rate": 1.087962962962963e-05, |
| "loss": 0.9168, |
| "step": 1930 |
| }, |
| { |
| "epoch": 16.17, |
| "learning_rate": 1.0648148148148148e-05, |
| "loss": 0.8289, |
| "step": 1940 |
| }, |
| { |
| "epoch": 16.25, |
| "learning_rate": 1.0416666666666668e-05, |
| "loss": 0.8544, |
| "step": 1950 |
| }, |
| { |
| "epoch": 16.33, |
| "learning_rate": 1.0185185185185185e-05, |
| "loss": 0.8349, |
| "step": 1960 |
| }, |
| { |
| "epoch": 16.42, |
| "learning_rate": 9.953703703703704e-06, |
| "loss": 0.9044, |
| "step": 1970 |
| }, |
| { |
| "epoch": 16.5, |
| "learning_rate": 9.722222222222223e-06, |
| "loss": 0.8508, |
| "step": 1980 |
| }, |
| { |
| "epoch": 16.58, |
| "learning_rate": 9.490740740740741e-06, |
| "loss": 0.8482, |
| "step": 1990 |
| }, |
| { |
| "epoch": 16.67, |
| "learning_rate": 9.259259259259259e-06, |
| "loss": 0.8412, |
| "step": 2000 |
| }, |
| { |
| "epoch": 16.75, |
| "learning_rate": 9.027777777777777e-06, |
| "loss": 0.8827, |
| "step": 2010 |
| }, |
| { |
| "epoch": 16.83, |
| "learning_rate": 8.796296296296297e-06, |
| "loss": 0.9122, |
| "step": 2020 |
| }, |
| { |
| "epoch": 16.92, |
| "learning_rate": 8.564814814814816e-06, |
| "loss": 0.8558, |
| "step": 2030 |
| }, |
| { |
| "epoch": 17.0, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.8909, |
| "step": 2040 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.613849765258216, |
| "eval_loss": 0.9154210090637207, |
| "eval_runtime": 22.6154, |
| "eval_samples_per_second": 75.347, |
| "eval_steps_per_second": 2.388, |
| "step": 2040 |
| }, |
| { |
| "epoch": 17.08, |
| "learning_rate": 8.101851851851852e-06, |
| "loss": 0.8449, |
| "step": 2050 |
| }, |
| { |
| "epoch": 17.17, |
| "learning_rate": 7.87037037037037e-06, |
| "loss": 0.8799, |
| "step": 2060 |
| }, |
| { |
| "epoch": 17.25, |
| "learning_rate": 7.63888888888889e-06, |
| "loss": 0.8713, |
| "step": 2070 |
| }, |
| { |
| "epoch": 17.33, |
| "learning_rate": 7.4074074074074075e-06, |
| "loss": 0.8708, |
| "step": 2080 |
| }, |
| { |
| "epoch": 17.42, |
| "learning_rate": 7.1759259259259266e-06, |
| "loss": 0.8545, |
| "step": 2090 |
| }, |
| { |
| "epoch": 17.5, |
| "learning_rate": 6.944444444444445e-06, |
| "loss": 0.853, |
| "step": 2100 |
| }, |
| { |
| "epoch": 17.58, |
| "learning_rate": 6.712962962962964e-06, |
| "loss": 0.8293, |
| "step": 2110 |
| }, |
| { |
| "epoch": 17.67, |
| "learning_rate": 6.481481481481481e-06, |
| "loss": 0.8409, |
| "step": 2120 |
| }, |
| { |
| "epoch": 17.75, |
| "learning_rate": 6.25e-06, |
| "loss": 0.8404, |
| "step": 2130 |
| }, |
| { |
| "epoch": 17.83, |
| "learning_rate": 6.0185185185185185e-06, |
| "loss": 0.836, |
| "step": 2140 |
| }, |
| { |
| "epoch": 17.92, |
| "learning_rate": 5.787037037037038e-06, |
| "loss": 0.8787, |
| "step": 2150 |
| }, |
| { |
| "epoch": 18.0, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.8473, |
| "step": 2160 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.6185446009389671, |
| "eval_loss": 0.9096030592918396, |
| "eval_runtime": 22.3019, |
| "eval_samples_per_second": 76.406, |
| "eval_steps_per_second": 2.421, |
| "step": 2160 |
| }, |
| { |
| "epoch": 18.08, |
| "learning_rate": 5.324074074074074e-06, |
| "loss": 0.8474, |
| "step": 2170 |
| }, |
| { |
| "epoch": 18.17, |
| "learning_rate": 5.092592592592592e-06, |
| "loss": 0.8388, |
| "step": 2180 |
| }, |
| { |
| "epoch": 18.25, |
| "learning_rate": 4.861111111111111e-06, |
| "loss": 0.8502, |
| "step": 2190 |
| }, |
| { |
| "epoch": 18.33, |
| "learning_rate": 4.6296296296296296e-06, |
| "loss": 0.8149, |
| "step": 2200 |
| }, |
| { |
| "epoch": 18.42, |
| "learning_rate": 4.398148148148149e-06, |
| "loss": 0.8442, |
| "step": 2210 |
| }, |
| { |
| "epoch": 18.5, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 0.8348, |
| "step": 2220 |
| }, |
| { |
| "epoch": 18.58, |
| "learning_rate": 3.935185185185185e-06, |
| "loss": 0.8841, |
| "step": 2230 |
| }, |
| { |
| "epoch": 18.67, |
| "learning_rate": 3.7037037037037037e-06, |
| "loss": 0.8669, |
| "step": 2240 |
| }, |
| { |
| "epoch": 18.75, |
| "learning_rate": 3.4722222222222224e-06, |
| "loss": 0.8684, |
| "step": 2250 |
| }, |
| { |
| "epoch": 18.83, |
| "learning_rate": 3.2407407407407406e-06, |
| "loss": 0.8048, |
| "step": 2260 |
| }, |
| { |
| "epoch": 18.92, |
| "learning_rate": 3.0092592592592593e-06, |
| "loss": 0.8316, |
| "step": 2270 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 2.777777777777778e-06, |
| "loss": 0.8979, |
| "step": 2280 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.6226525821596244, |
| "eval_loss": 0.9150213599205017, |
| "eval_runtime": 22.6094, |
| "eval_samples_per_second": 75.367, |
| "eval_steps_per_second": 2.388, |
| "step": 2280 |
| }, |
| { |
| "epoch": 19.08, |
| "learning_rate": 2.546296296296296e-06, |
| "loss": 0.8163, |
| "step": 2290 |
| }, |
| { |
| "epoch": 19.17, |
| "learning_rate": 2.3148148148148148e-06, |
| "loss": 0.823, |
| "step": 2300 |
| }, |
| { |
| "epoch": 19.25, |
| "learning_rate": 2.0833333333333334e-06, |
| "loss": 0.8712, |
| "step": 2310 |
| }, |
| { |
| "epoch": 19.33, |
| "learning_rate": 1.8518518518518519e-06, |
| "loss": 0.8384, |
| "step": 2320 |
| }, |
| { |
| "epoch": 19.42, |
| "learning_rate": 1.6203703703703703e-06, |
| "loss": 0.855, |
| "step": 2330 |
| }, |
| { |
| "epoch": 19.5, |
| "learning_rate": 1.388888888888889e-06, |
| "loss": 0.8418, |
| "step": 2340 |
| }, |
| { |
| "epoch": 19.58, |
| "learning_rate": 1.1574074074074074e-06, |
| "loss": 0.8504, |
| "step": 2350 |
| }, |
| { |
| "epoch": 19.67, |
| "learning_rate": 9.259259259259259e-07, |
| "loss": 0.8736, |
| "step": 2360 |
| }, |
| { |
| "epoch": 19.75, |
| "learning_rate": 6.944444444444445e-07, |
| "loss": 0.7959, |
| "step": 2370 |
| }, |
| { |
| "epoch": 19.83, |
| "learning_rate": 4.6296296296296297e-07, |
| "loss": 0.8431, |
| "step": 2380 |
| }, |
| { |
| "epoch": 19.92, |
| "learning_rate": 2.3148148148148148e-07, |
| "loss": 0.8712, |
| "step": 2390 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 0.0, |
| "loss": 0.8337, |
| "step": 2400 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.6220657276995305, |
| "eval_loss": 0.9112741351127625, |
| "eval_runtime": 23.2097, |
| "eval_samples_per_second": 73.418, |
| "eval_steps_per_second": 2.327, |
| "step": 2400 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 2400, |
| "total_flos": 2.3761445690374963e+19, |
| "train_loss": 0.9564308677117029, |
| "train_runtime": 12406.5537, |
| "train_samples_per_second": 24.714, |
| "train_steps_per_second": 0.193 |
| } |
| ], |
| "max_steps": 2400, |
| "num_train_epochs": 20, |
| "total_flos": 2.3761445690374963e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
