| { | |
| "best_metric": 0.5022222222222222, | |
| "best_model_checkpoint": "ansilmbabl/cards-blt-swin-tiny-patch4-window7-224-finetuned-v2/checkpoint-337", | |
| "epoch": 99.55555555555556, | |
| "eval_steps": 500, | |
| "global_step": 5600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.928571428571428e-07, | |
| "loss": 1.415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.7857142857142857e-06, | |
| "loss": 1.4195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.6785714285714285e-06, | |
| "loss": 1.419, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 1.3573, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 1.4297, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.49333333333333335, | |
| "eval_loss": 1.1976468563079834, | |
| "eval_runtime": 6.9062, | |
| "eval_samples_per_second": 260.637, | |
| "eval_steps_per_second": 8.253, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 1.4063, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.3637, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.402, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.035714285714286e-06, | |
| "loss": 1.3807, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 1.4298, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 9.821428571428573e-06, | |
| "loss": 1.4078, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.5011111111111111, | |
| "eval_loss": 1.196445345878601, | |
| "eval_runtime": 6.7224, | |
| "eval_samples_per_second": 267.76, | |
| "eval_steps_per_second": 8.479, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 1.3884, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1607142857142857e-05, | |
| "loss": 1.3689, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.4214, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.3392857142857144e-05, | |
| "loss": 1.3834, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.417, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.4961111111111111, | |
| "eval_loss": 1.2024986743927002, | |
| "eval_runtime": 6.8464, | |
| "eval_samples_per_second": 262.91, | |
| "eval_steps_per_second": 8.325, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.5178571428571429e-05, | |
| "loss": 1.4647, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.6071428571428572e-05, | |
| "loss": 1.4384, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.6964285714285715e-05, | |
| "loss": 1.3899, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.4333, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.3869, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.9642857142857145e-05, | |
| "loss": 1.4163, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.48833333333333334, | |
| "eval_loss": 1.2295453548431396, | |
| "eval_runtime": 6.7471, | |
| "eval_samples_per_second": 266.783, | |
| "eval_steps_per_second": 8.448, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.0535714285714285e-05, | |
| "loss": 1.4564, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 1.4539, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.2321428571428575e-05, | |
| "loss": 1.4111, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.3214285714285715e-05, | |
| "loss": 1.4174, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.4107142857142858e-05, | |
| "loss": 1.386, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4318, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.495, | |
| "eval_loss": 1.2330048084259033, | |
| "eval_runtime": 6.8802, | |
| "eval_samples_per_second": 261.621, | |
| "eval_steps_per_second": 8.285, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.5892857142857148e-05, | |
| "loss": 1.3915, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 1.3905, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 1.4094, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.4484, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 2.9464285714285718e-05, | |
| "loss": 1.4383, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.5022222222222222, | |
| "eval_loss": 1.2162481546401978, | |
| "eval_runtime": 6.9019, | |
| "eval_samples_per_second": 260.797, | |
| "eval_steps_per_second": 8.259, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 3.0357142857142857e-05, | |
| "loss": 1.4271, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.3845, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 1.4332, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "learning_rate": 3.303571428571429e-05, | |
| "loss": 1.4743, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 3.392857142857143e-05, | |
| "loss": 1.3979, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 3.4821428571428574e-05, | |
| "loss": 1.4212, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.4716666666666667, | |
| "eval_loss": 1.2634377479553223, | |
| "eval_runtime": 6.8985, | |
| "eval_samples_per_second": 260.925, | |
| "eval_steps_per_second": 8.263, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.4537, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 3.6607142857142853e-05, | |
| "loss": 1.4253, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.4421, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 3.839285714285715e-05, | |
| "loss": 1.4282, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 1.4997, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 1.4346, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4688888888888889, | |
| "eval_loss": 1.3083486557006836, | |
| "eval_runtime": 6.7559, | |
| "eval_samples_per_second": 266.436, | |
| "eval_steps_per_second": 8.437, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 4.107142857142857e-05, | |
| "loss": 1.4238, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 4.196428571428572e-05, | |
| "loss": 1.4162, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.3962, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 4.375e-05, | |
| "loss": 1.38, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 1.419, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.48055555555555557, | |
| "eval_loss": 1.271929383277893, | |
| "eval_runtime": 6.6282, | |
| "eval_samples_per_second": 271.567, | |
| "eval_steps_per_second": 8.6, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 4.5535714285714286e-05, | |
| "loss": 1.4266, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.4394, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 4.732142857142857e-05, | |
| "loss": 1.4178, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.8214285714285716e-05, | |
| "loss": 1.4636, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 4.910714285714286e-05, | |
| "loss": 1.3616, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4252, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.4911111111111111, | |
| "eval_loss": 1.3047653436660767, | |
| "eval_runtime": 7.0266, | |
| "eval_samples_per_second": 256.17, | |
| "eval_steps_per_second": 8.112, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 10.13, | |
| "learning_rate": 4.990079365079365e-05, | |
| "loss": 1.4389, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 4.9801587301587306e-05, | |
| "loss": 1.3925, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 4.9702380952380955e-05, | |
| "loss": 1.4302, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 4.960317460317461e-05, | |
| "loss": 1.405, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 4.950396825396826e-05, | |
| "loss": 1.4522, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.47944444444444445, | |
| "eval_loss": 1.2707706689834595, | |
| "eval_runtime": 7.1468, | |
| "eval_samples_per_second": 251.861, | |
| "eval_steps_per_second": 7.976, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.940476190476191e-05, | |
| "loss": 1.4201, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 1.3786, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.38, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 1.4126, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 4.910714285714286e-05, | |
| "loss": 1.4261, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 4.900793650793651e-05, | |
| "loss": 1.3891, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 4.8908730158730156e-05, | |
| "loss": 1.3748, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.43833333333333335, | |
| "eval_loss": 1.3720223903656006, | |
| "eval_runtime": 6.9318, | |
| "eval_samples_per_second": 259.673, | |
| "eval_steps_per_second": 8.223, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 4.880952380952381e-05, | |
| "loss": 1.479, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 4.871031746031746e-05, | |
| "loss": 1.3825, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.4049, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 4.8511904761904764e-05, | |
| "loss": 1.422, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 4.841269841269841e-05, | |
| "loss": 1.3707, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 4.831349206349207e-05, | |
| "loss": 1.3966, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.45944444444444443, | |
| "eval_loss": 1.3094544410705566, | |
| "eval_runtime": 7.1035, | |
| "eval_samples_per_second": 253.396, | |
| "eval_steps_per_second": 8.024, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 4.8214285714285716e-05, | |
| "loss": 1.3888, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 4.811507936507937e-05, | |
| "loss": 1.4374, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 4.801587301587302e-05, | |
| "loss": 1.4004, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 13.69, | |
| "learning_rate": 4.791666666666667e-05, | |
| "loss": 1.4099, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 13.87, | |
| "learning_rate": 4.781746031746032e-05, | |
| "loss": 1.4507, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_accuracy": 0.485, | |
| "eval_loss": 1.2430291175842285, | |
| "eval_runtime": 7.2727, | |
| "eval_samples_per_second": 247.502, | |
| "eval_steps_per_second": 7.838, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 4.771825396825397e-05, | |
| "loss": 1.4554, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 1.3986, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 4.751984126984127e-05, | |
| "loss": 1.4145, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 4.7420634920634924e-05, | |
| "loss": 1.4258, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 4.732142857142857e-05, | |
| "loss": 1.4066, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.4033, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.47944444444444445, | |
| "eval_loss": 1.272768497467041, | |
| "eval_runtime": 6.8312, | |
| "eval_samples_per_second": 263.498, | |
| "eval_steps_per_second": 8.344, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 4.7123015873015876e-05, | |
| "loss": 1.4264, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 15.29, | |
| "learning_rate": 4.7023809523809525e-05, | |
| "loss": 1.3796, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 15.47, | |
| "learning_rate": 4.692460317460317e-05, | |
| "loss": 1.3972, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 4.682539682539683e-05, | |
| "loss": 1.3486, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 4.672619047619048e-05, | |
| "loss": 1.3769, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.662698412698413e-05, | |
| "loss": 1.3972, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.48833333333333334, | |
| "eval_loss": 1.261121392250061, | |
| "eval_runtime": 6.6409, | |
| "eval_samples_per_second": 271.049, | |
| "eval_steps_per_second": 8.583, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 4.652777777777778e-05, | |
| "loss": 1.3787, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.3228, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 4.6329365079365085e-05, | |
| "loss": 1.3655, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.71, | |
| "learning_rate": 4.623015873015873e-05, | |
| "loss": 1.3589, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 4.613095238095239e-05, | |
| "loss": 1.4136, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.45, | |
| "eval_loss": 1.3166221380233765, | |
| "eval_runtime": 6.9227, | |
| "eval_samples_per_second": 260.013, | |
| "eval_steps_per_second": 8.234, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 17.07, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 1.4259, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.24, | |
| "learning_rate": 4.5932539682539685e-05, | |
| "loss": 1.3792, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 17.42, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 1.3724, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.573412698412698e-05, | |
| "loss": 1.4, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 4.563492063492064e-05, | |
| "loss": 1.3087, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 4.5535714285714286e-05, | |
| "loss": 1.3992, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "eval_accuracy": 0.4855555555555556, | |
| "eval_loss": 1.3103010654449463, | |
| "eval_runtime": 6.5821, | |
| "eval_samples_per_second": 273.469, | |
| "eval_steps_per_second": 8.66, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 4.543650793650794e-05, | |
| "loss": 1.3577, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 4.533730158730159e-05, | |
| "loss": 1.3907, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 4.523809523809524e-05, | |
| "loss": 1.3839, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 1.3949, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 4.503968253968254e-05, | |
| "loss": 1.3614, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.44222222222222224, | |
| "eval_loss": 1.3302438259124756, | |
| "eval_runtime": 6.9237, | |
| "eval_samples_per_second": 259.976, | |
| "eval_steps_per_second": 8.233, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 4.494047619047619e-05, | |
| "loss": 1.3348, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.4841269841269846e-05, | |
| "loss": 1.3525, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 4.4742063492063494e-05, | |
| "loss": 1.3349, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 1.3511, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 4.45436507936508e-05, | |
| "loss": 1.3608, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.3747, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.4855555555555556, | |
| "eval_loss": 1.2918972969055176, | |
| "eval_runtime": 6.9094, | |
| "eval_samples_per_second": 260.515, | |
| "eval_steps_per_second": 8.25, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 4.4345238095238095e-05, | |
| "loss": 1.372, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 4.4246031746031744e-05, | |
| "loss": 1.3213, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 4.41468253968254e-05, | |
| "loss": 1.3659, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 20.62, | |
| "learning_rate": 4.404761904761905e-05, | |
| "loss": 1.374, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 4.39484126984127e-05, | |
| "loss": 1.3621, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "learning_rate": 4.384920634920635e-05, | |
| "loss": 1.3868, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.4727777777777778, | |
| "eval_loss": 1.3165982961654663, | |
| "eval_runtime": 6.6725, | |
| "eval_samples_per_second": 269.765, | |
| "eval_steps_per_second": 8.543, | |
| "step": 1181 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 4.375e-05, | |
| "loss": 1.3344, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 1.3649, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 21.51, | |
| "learning_rate": 4.35515873015873e-05, | |
| "loss": 1.2993, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 21.69, | |
| "learning_rate": 4.345238095238096e-05, | |
| "loss": 1.3745, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 4.335317460317461e-05, | |
| "loss": 1.3399, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "eval_accuracy": 0.4672222222222222, | |
| "eval_loss": 1.3200290203094482, | |
| "eval_runtime": 6.7301, | |
| "eval_samples_per_second": 267.457, | |
| "eval_steps_per_second": 8.469, | |
| "step": 1237 | |
| }, | |
| { | |
| "epoch": 22.04, | |
| "learning_rate": 4.3253968253968256e-05, | |
| "loss": 1.3777, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 4.315476190476191e-05, | |
| "loss": 1.3122, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 1.3405, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 22.58, | |
| "learning_rate": 4.295634920634921e-05, | |
| "loss": 1.299, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 22.76, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.3672, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "learning_rate": 4.2757936507936505e-05, | |
| "loss": 1.3943, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.4811111111111111, | |
| "eval_loss": 1.2920361757278442, | |
| "eval_runtime": 6.9015, | |
| "eval_samples_per_second": 260.815, | |
| "eval_steps_per_second": 8.259, | |
| "step": 1293 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 4.265873015873016e-05, | |
| "loss": 1.3459, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 23.29, | |
| "learning_rate": 4.255952380952381e-05, | |
| "loss": 1.3264, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 4.2460317460317464e-05, | |
| "loss": 1.3297, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "learning_rate": 4.236111111111111e-05, | |
| "loss": 1.3092, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 4.226190476190476e-05, | |
| "loss": 1.3551, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.2162698412698416e-05, | |
| "loss": 1.3635, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.3109022378921509, | |
| "eval_runtime": 6.7144, | |
| "eval_samples_per_second": 268.079, | |
| "eval_steps_per_second": 8.489, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 4.2063492063492065e-05, | |
| "loss": 1.3229, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 24.36, | |
| "learning_rate": 4.196428571428572e-05, | |
| "loss": 1.3578, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 24.53, | |
| "learning_rate": 4.186507936507937e-05, | |
| "loss": 1.3052, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "learning_rate": 4.176587301587302e-05, | |
| "loss": 1.3843, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3724, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.46444444444444444, | |
| "eval_loss": 1.3099535703659058, | |
| "eval_runtime": 6.6043, | |
| "eval_samples_per_second": 272.552, | |
| "eval_steps_per_second": 8.631, | |
| "step": 1406 | |
| }, | |
| { | |
| "epoch": 25.07, | |
| "learning_rate": 4.156746031746032e-05, | |
| "loss": 1.3264, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 4.1468253968253976e-05, | |
| "loss": 1.2923, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 4.136904761904762e-05, | |
| "loss": 1.34, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 1.2817, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "learning_rate": 4.117063492063492e-05, | |
| "loss": 1.3498, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 25.96, | |
| "learning_rate": 4.107142857142857e-05, | |
| "loss": 1.3141, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "eval_accuracy": 0.49777777777777776, | |
| "eval_loss": 1.3263020515441895, | |
| "eval_runtime": 9.6902, | |
| "eval_samples_per_second": 185.755, | |
| "eval_steps_per_second": 5.882, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 26.13, | |
| "learning_rate": 4.0972222222222225e-05, | |
| "loss": 1.3192, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 26.31, | |
| "learning_rate": 4.0873015873015874e-05, | |
| "loss": 1.3228, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 26.49, | |
| "learning_rate": 4.077380952380952e-05, | |
| "loss": 1.2749, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 4.067460317460318e-05, | |
| "loss": 1.289, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "learning_rate": 4.0575396825396826e-05, | |
| "loss": 1.3576, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.4772222222222222, | |
| "eval_loss": 1.330748438835144, | |
| "eval_runtime": 6.6957, | |
| "eval_samples_per_second": 268.828, | |
| "eval_steps_per_second": 8.513, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.047619047619048e-05, | |
| "loss": 1.3147, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.037698412698413e-05, | |
| "loss": 1.2995, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 27.38, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 1.2871, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 27.56, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 1.313, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 27.73, | |
| "learning_rate": 4.007936507936508e-05, | |
| "loss": 1.361, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 3.998015873015874e-05, | |
| "loss": 1.3022, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.49777777777777776, | |
| "eval_loss": 1.3408504724502563, | |
| "eval_runtime": 6.9866, | |
| "eval_samples_per_second": 257.635, | |
| "eval_steps_per_second": 8.158, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 3.9880952380952386e-05, | |
| "loss": 1.2554, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 28.27, | |
| "learning_rate": 3.9781746031746034e-05, | |
| "loss": 1.3175, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 1.2905, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 28.62, | |
| "learning_rate": 3.958333333333333e-05, | |
| "loss": 1.2806, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.9484126984126986e-05, | |
| "loss": 1.3055, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 28.98, | |
| "learning_rate": 3.9384920634920635e-05, | |
| "loss": 1.2982, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.4583333333333333, | |
| "eval_loss": 1.3961677551269531, | |
| "eval_runtime": 6.8118, | |
| "eval_samples_per_second": 264.246, | |
| "eval_steps_per_second": 8.368, | |
| "step": 1631 | |
| }, | |
| { | |
| "epoch": 29.16, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 1.2994, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 29.33, | |
| "learning_rate": 3.918650793650794e-05, | |
| "loss": 1.2676, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 29.51, | |
| "learning_rate": 3.908730158730159e-05, | |
| "loss": 1.2888, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 29.69, | |
| "learning_rate": 3.898809523809524e-05, | |
| "loss": 1.2839, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 29.87, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.2657, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 29.99, | |
| "eval_accuracy": 0.4816666666666667, | |
| "eval_loss": 1.3329031467437744, | |
| "eval_runtime": 6.7377, | |
| "eval_samples_per_second": 267.155, | |
| "eval_steps_per_second": 8.46, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 30.04, | |
| "learning_rate": 3.878968253968254e-05, | |
| "loss": 1.2745, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 3.8690476190476195e-05, | |
| "loss": 1.3186, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 30.4, | |
| "learning_rate": 3.859126984126984e-05, | |
| "loss": 1.2745, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 30.58, | |
| "learning_rate": 3.84920634920635e-05, | |
| "loss": 1.3076, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 30.76, | |
| "learning_rate": 3.839285714285715e-05, | |
| "loss": 1.2578, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 30.93, | |
| "learning_rate": 3.8293650793650795e-05, | |
| "loss": 1.3152, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "eval_accuracy": 0.49, | |
| "eval_loss": 1.2973191738128662, | |
| "eval_runtime": 7.0246, | |
| "eval_samples_per_second": 256.242, | |
| "eval_steps_per_second": 8.114, | |
| "step": 1743 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 1.248, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 31.29, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 1.2537, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "learning_rate": 3.799603174603175e-05, | |
| "loss": 1.247, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 3.7896825396825396e-05, | |
| "loss": 1.2904, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 3.779761904761905e-05, | |
| "loss": 1.3096, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 3.76984126984127e-05, | |
| "loss": 1.2924, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.3158966302871704, | |
| "eval_runtime": 6.8489, | |
| "eval_samples_per_second": 262.815, | |
| "eval_steps_per_second": 8.322, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 32.18, | |
| "learning_rate": 3.759920634920635e-05, | |
| "loss": 1.2709, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.2427, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 32.53, | |
| "learning_rate": 3.740079365079365e-05, | |
| "loss": 1.2435, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 32.71, | |
| "learning_rate": 3.730158730158731e-05, | |
| "loss": 1.2843, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 3.7202380952380956e-05, | |
| "loss": 1.214, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.395532488822937, | |
| "eval_runtime": 6.7585, | |
| "eval_samples_per_second": 266.33, | |
| "eval_steps_per_second": 8.434, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 33.07, | |
| "learning_rate": 3.7103174603174604e-05, | |
| "loss": 1.3143, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 33.24, | |
| "learning_rate": 3.700396825396826e-05, | |
| "loss": 1.2143, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 33.42, | |
| "learning_rate": 3.690476190476191e-05, | |
| "loss": 1.2721, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "learning_rate": 3.6805555555555556e-05, | |
| "loss": 1.2267, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 33.78, | |
| "learning_rate": 3.6706349206349205e-05, | |
| "loss": 1.2616, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 33.96, | |
| "learning_rate": 3.6607142857142853e-05, | |
| "loss": 1.2717, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 33.99, | |
| "eval_accuracy": 0.46, | |
| "eval_loss": 1.4583297967910767, | |
| "eval_runtime": 6.7797, | |
| "eval_samples_per_second": 265.497, | |
| "eval_steps_per_second": 8.407, | |
| "step": 1912 | |
| }, | |
| { | |
| "epoch": 34.13, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 1.2594, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 34.31, | |
| "learning_rate": 3.640873015873016e-05, | |
| "loss": 1.3058, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 34.49, | |
| "learning_rate": 3.630952380952381e-05, | |
| "loss": 1.285, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "learning_rate": 3.621031746031746e-05, | |
| "loss": 1.2276, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 34.84, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.2692, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "eval_accuracy": 0.4938888888888889, | |
| "eval_loss": 1.3503786325454712, | |
| "eval_runtime": 6.4105, | |
| "eval_samples_per_second": 280.79, | |
| "eval_steps_per_second": 8.892, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 3.6011904761904765e-05, | |
| "loss": 1.2435, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 35.2, | |
| "learning_rate": 3.591269841269841e-05, | |
| "loss": 1.2224, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 3.581349206349207e-05, | |
| "loss": 1.2219, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.2391, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 3.5615079365079365e-05, | |
| "loss": 1.2594, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 35.91, | |
| "learning_rate": 3.551587301587302e-05, | |
| "loss": 1.2127, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.48333333333333334, | |
| "eval_loss": 1.378441333770752, | |
| "eval_runtime": 6.7487, | |
| "eval_samples_per_second": 266.719, | |
| "eval_steps_per_second": 8.446, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 36.09, | |
| "learning_rate": 3.541666666666667e-05, | |
| "loss": 1.2251, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 36.27, | |
| "learning_rate": 3.5317460317460324e-05, | |
| "loss": 1.2232, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 3.521825396825397e-05, | |
| "loss": 1.2207, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 36.62, | |
| "learning_rate": 3.511904761904762e-05, | |
| "loss": 1.2139, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 3.501984126984127e-05, | |
| "loss": 1.2464, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 36.98, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 1.1956, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.4816666666666667, | |
| "eval_loss": 1.4183870553970337, | |
| "eval_runtime": 6.7564, | |
| "eval_samples_per_second": 266.414, | |
| "eval_steps_per_second": 8.436, | |
| "step": 2081 | |
| }, | |
| { | |
| "epoch": 37.16, | |
| "learning_rate": 3.4821428571428574e-05, | |
| "loss": 1.199, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 37.33, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 1.2005, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 37.51, | |
| "learning_rate": 3.462301587301587e-05, | |
| "loss": 1.193, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 37.69, | |
| "learning_rate": 3.4523809523809526e-05, | |
| "loss": 1.2632, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 37.87, | |
| "learning_rate": 3.4424603174603174e-05, | |
| "loss": 1.2408, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 37.99, | |
| "eval_accuracy": 0.49444444444444446, | |
| "eval_loss": 1.3849085569381714, | |
| "eval_runtime": 7.0969, | |
| "eval_samples_per_second": 253.633, | |
| "eval_steps_per_second": 8.032, | |
| "step": 2137 | |
| }, | |
| { | |
| "epoch": 38.04, | |
| "learning_rate": 3.432539682539683e-05, | |
| "loss": 1.1826, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 38.22, | |
| "learning_rate": 3.422619047619048e-05, | |
| "loss": 1.2048, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "learning_rate": 3.412698412698413e-05, | |
| "loss": 1.2153, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 38.58, | |
| "learning_rate": 3.402777777777778e-05, | |
| "loss": 1.2151, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 38.76, | |
| "learning_rate": 3.392857142857143e-05, | |
| "loss": 1.23, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 38.93, | |
| "learning_rate": 3.3829365079365086e-05, | |
| "loss": 1.1699, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "eval_accuracy": 0.48444444444444446, | |
| "eval_loss": 1.429752230644226, | |
| "eval_runtime": 6.9781, | |
| "eval_samples_per_second": 257.951, | |
| "eval_steps_per_second": 8.168, | |
| "step": 2193 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 3.3730158730158734e-05, | |
| "loss": 1.1914, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 39.29, | |
| "learning_rate": 3.363095238095238e-05, | |
| "loss": 1.218, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 3.353174603174603e-05, | |
| "loss": 1.2134, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 39.64, | |
| "learning_rate": 3.343253968253968e-05, | |
| "loss": 1.1926, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 39.82, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.1607, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.3234126984126983e-05, | |
| "loss": 1.1727, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.4772222222222222, | |
| "eval_loss": 1.4331458806991577, | |
| "eval_runtime": 6.6454, | |
| "eval_samples_per_second": 270.865, | |
| "eval_steps_per_second": 8.577, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 40.18, | |
| "learning_rate": 3.313492063492064e-05, | |
| "loss": 1.1827, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 40.36, | |
| "learning_rate": 3.303571428571429e-05, | |
| "loss": 1.1691, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 40.53, | |
| "learning_rate": 3.2936507936507936e-05, | |
| "loss": 1.2009, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 40.71, | |
| "learning_rate": 3.283730158730159e-05, | |
| "loss": 1.1939, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "learning_rate": 3.273809523809524e-05, | |
| "loss": 1.1485, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.4672222222222222, | |
| "eval_loss": 1.4596869945526123, | |
| "eval_runtime": 6.7934, | |
| "eval_samples_per_second": 264.961, | |
| "eval_steps_per_second": 8.39, | |
| "step": 2306 | |
| }, | |
| { | |
| "epoch": 41.07, | |
| "learning_rate": 3.263888888888889e-05, | |
| "loss": 1.185, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 41.24, | |
| "learning_rate": 3.253968253968254e-05, | |
| "loss": 1.1438, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 41.42, | |
| "learning_rate": 3.244047619047619e-05, | |
| "loss": 1.2154, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "learning_rate": 3.234126984126985e-05, | |
| "loss": 1.1789, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "learning_rate": 3.2242063492063495e-05, | |
| "loss": 1.1464, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 1.1668, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 41.99, | |
| "eval_accuracy": 0.47833333333333333, | |
| "eval_loss": 1.4428596496582031, | |
| "eval_runtime": 6.9455, | |
| "eval_samples_per_second": 259.161, | |
| "eval_steps_per_second": 8.207, | |
| "step": 2362 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "learning_rate": 3.20436507936508e-05, | |
| "loss": 1.1201, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 42.31, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 1.1545, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 42.49, | |
| "learning_rate": 3.1845238095238096e-05, | |
| "loss": 1.1587, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 1.1606, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 42.84, | |
| "learning_rate": 3.16468253968254e-05, | |
| "loss": 1.1881, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 42.99, | |
| "eval_accuracy": 0.48388888888888887, | |
| "eval_loss": 1.455505132675171, | |
| "eval_runtime": 6.7551, | |
| "eval_samples_per_second": 266.464, | |
| "eval_steps_per_second": 8.438, | |
| "step": 2418 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 3.154761904761905e-05, | |
| "loss": 1.1859, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 43.2, | |
| "learning_rate": 3.14484126984127e-05, | |
| "loss": 1.1149, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 43.38, | |
| "learning_rate": 3.134920634920635e-05, | |
| "loss": 1.1699, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 43.56, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.1132, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 43.73, | |
| "learning_rate": 3.1150793650793656e-05, | |
| "loss": 1.129, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 43.91, | |
| "learning_rate": 3.1051587301587304e-05, | |
| "loss": 1.1204, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.47833333333333333, | |
| "eval_loss": 1.464751958847046, | |
| "eval_runtime": 6.9852, | |
| "eval_samples_per_second": 257.688, | |
| "eval_steps_per_second": 8.16, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 44.09, | |
| "learning_rate": 3.095238095238095e-05, | |
| "loss": 1.1405, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 44.27, | |
| "learning_rate": 3.085317460317461e-05, | |
| "loss": 1.1173, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 3.075396825396826e-05, | |
| "loss": 1.1739, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 3.0654761904761905e-05, | |
| "loss": 1.1311, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 44.8, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 1.1483, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 44.98, | |
| "learning_rate": 3.0456349206349206e-05, | |
| "loss": 1.1523, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.47333333333333333, | |
| "eval_loss": 1.474352240562439, | |
| "eval_runtime": 6.7424, | |
| "eval_samples_per_second": 266.966, | |
| "eval_steps_per_second": 8.454, | |
| "step": 2531 | |
| }, | |
| { | |
| "epoch": 45.16, | |
| "learning_rate": 3.0357142857142857e-05, | |
| "loss": 1.1291, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 45.33, | |
| "learning_rate": 3.0257936507936506e-05, | |
| "loss": 1.1552, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 45.51, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 1.1652, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 45.69, | |
| "learning_rate": 3.005952380952381e-05, | |
| "loss": 1.1732, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 45.87, | |
| "learning_rate": 2.996031746031746e-05, | |
| "loss": 1.1206, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 45.99, | |
| "eval_accuracy": 0.4905555555555556, | |
| "eval_loss": 1.4791755676269531, | |
| "eval_runtime": 6.7618, | |
| "eval_samples_per_second": 266.202, | |
| "eval_steps_per_second": 8.43, | |
| "step": 2587 | |
| }, | |
| { | |
| "epoch": 46.04, | |
| "learning_rate": 2.9861111111111113e-05, | |
| "loss": 1.1128, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 46.22, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 1.1148, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 46.4, | |
| "learning_rate": 2.9662698412698414e-05, | |
| "loss": 1.1391, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 46.58, | |
| "learning_rate": 2.9563492063492066e-05, | |
| "loss": 1.1445, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 46.76, | |
| "learning_rate": 2.9464285714285718e-05, | |
| "loss": 1.1596, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 46.93, | |
| "learning_rate": 2.9365079365079366e-05, | |
| "loss": 1.1135, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 46.99, | |
| "eval_accuracy": 0.4677777777777778, | |
| "eval_loss": 1.5008630752563477, | |
| "eval_runtime": 7.3069, | |
| "eval_samples_per_second": 246.342, | |
| "eval_steps_per_second": 7.801, | |
| "step": 2643 | |
| }, | |
| { | |
| "epoch": 47.11, | |
| "learning_rate": 2.9265873015873018e-05, | |
| "loss": 1.1324, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 47.29, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 1.0933, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 47.47, | |
| "learning_rate": 2.906746031746032e-05, | |
| "loss": 1.1701, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 47.64, | |
| "learning_rate": 2.8968253968253974e-05, | |
| "loss": 1.1505, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 47.82, | |
| "learning_rate": 2.886904761904762e-05, | |
| "loss": 1.1117, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.876984126984127e-05, | |
| "loss": 1.1227, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.47333333333333333, | |
| "eval_loss": 1.5479964017868042, | |
| "eval_runtime": 6.7183, | |
| "eval_samples_per_second": 267.925, | |
| "eval_steps_per_second": 8.484, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 48.18, | |
| "learning_rate": 2.867063492063492e-05, | |
| "loss": 1.1419, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 48.36, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.0893, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 48.53, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 1.0633, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 48.71, | |
| "learning_rate": 2.8373015873015875e-05, | |
| "loss": 1.0889, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "learning_rate": 2.8273809523809523e-05, | |
| "loss": 1.1017, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.46444444444444444, | |
| "eval_loss": 1.590686559677124, | |
| "eval_runtime": 9.0291, | |
| "eval_samples_per_second": 199.355, | |
| "eval_steps_per_second": 6.313, | |
| "step": 2756 | |
| }, | |
| { | |
| "epoch": 49.07, | |
| "learning_rate": 2.8174603174603175e-05, | |
| "loss": 1.0731, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 49.24, | |
| "learning_rate": 2.8075396825396827e-05, | |
| "loss": 1.0992, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 49.42, | |
| "learning_rate": 2.797619047619048e-05, | |
| "loss": 1.0779, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 49.6, | |
| "learning_rate": 2.787698412698413e-05, | |
| "loss": 1.0771, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 49.78, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1053, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 49.96, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 1.1601, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 49.99, | |
| "eval_accuracy": 0.47, | |
| "eval_loss": 1.5136301517486572, | |
| "eval_runtime": 6.8103, | |
| "eval_samples_per_second": 264.305, | |
| "eval_steps_per_second": 8.37, | |
| "step": 2812 | |
| }, | |
| { | |
| "epoch": 50.13, | |
| "learning_rate": 2.7579365079365083e-05, | |
| "loss": 1.1253, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 50.31, | |
| "learning_rate": 2.7480158730158735e-05, | |
| "loss": 1.0357, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 50.49, | |
| "learning_rate": 2.7380952380952383e-05, | |
| "loss": 1.0808, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 50.67, | |
| "learning_rate": 2.7281746031746032e-05, | |
| "loss": 1.0321, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 50.84, | |
| "learning_rate": 2.718253968253968e-05, | |
| "loss": 1.1239, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 50.99, | |
| "eval_accuracy": 0.47888888888888886, | |
| "eval_loss": 1.5383570194244385, | |
| "eval_runtime": 6.9446, | |
| "eval_samples_per_second": 259.194, | |
| "eval_steps_per_second": 8.208, | |
| "step": 2868 | |
| }, | |
| { | |
| "epoch": 51.02, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 1.1178, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 51.2, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 1.0706, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 51.38, | |
| "learning_rate": 2.6884920634920636e-05, | |
| "loss": 1.077, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 51.56, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 1.0307, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 51.73, | |
| "learning_rate": 2.6686507936507936e-05, | |
| "loss": 1.0621, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 2.6587301587301588e-05, | |
| "loss": 1.09, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.4711111111111111, | |
| "eval_loss": 1.5716180801391602, | |
| "eval_runtime": 6.726, | |
| "eval_samples_per_second": 267.618, | |
| "eval_steps_per_second": 8.475, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 52.09, | |
| "learning_rate": 2.648809523809524e-05, | |
| "loss": 1.1091, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 52.27, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 1.0716, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 52.44, | |
| "learning_rate": 2.628968253968254e-05, | |
| "loss": 1.0558, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 52.62, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 1.0986, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 52.8, | |
| "learning_rate": 2.6091269841269844e-05, | |
| "loss": 1.0729, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 52.98, | |
| "learning_rate": 2.5992063492063496e-05, | |
| "loss": 1.1023, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.4727777777777778, | |
| "eval_loss": 1.5735939741134644, | |
| "eval_runtime": 6.8239, | |
| "eval_samples_per_second": 263.777, | |
| "eval_steps_per_second": 8.353, | |
| "step": 2981 | |
| }, | |
| { | |
| "epoch": 53.16, | |
| "learning_rate": 2.5892857142857148e-05, | |
| "loss": 1.017, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 2.5793650793650796e-05, | |
| "loss": 1.103, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 53.51, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 1.0374, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 53.69, | |
| "learning_rate": 2.5595238095238093e-05, | |
| "loss": 1.0361, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 53.87, | |
| "learning_rate": 2.5496031746031745e-05, | |
| "loss": 1.1038, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 53.99, | |
| "eval_accuracy": 0.45555555555555555, | |
| "eval_loss": 1.5918738842010498, | |
| "eval_runtime": 6.817, | |
| "eval_samples_per_second": 264.046, | |
| "eval_steps_per_second": 8.361, | |
| "step": 3037 | |
| }, | |
| { | |
| "epoch": 54.04, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 1.0261, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 54.22, | |
| "learning_rate": 2.529761904761905e-05, | |
| "loss": 1.0808, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 54.4, | |
| "learning_rate": 2.5198412698412697e-05, | |
| "loss": 1.0486, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 54.58, | |
| "learning_rate": 2.509920634920635e-05, | |
| "loss": 1.0311, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 54.76, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.0527, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 54.93, | |
| "learning_rate": 2.4900793650793653e-05, | |
| "loss": 1.058, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 54.99, | |
| "eval_accuracy": 0.4772222222222222, | |
| "eval_loss": 1.5533833503723145, | |
| "eval_runtime": 6.859, | |
| "eval_samples_per_second": 262.427, | |
| "eval_steps_per_second": 8.31, | |
| "step": 3093 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 2.4801587301587305e-05, | |
| "loss": 1.0369, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 55.29, | |
| "learning_rate": 2.4702380952380953e-05, | |
| "loss": 1.0456, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 55.47, | |
| "learning_rate": 2.4603174603174602e-05, | |
| "loss": 1.0249, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 55.64, | |
| "learning_rate": 2.4503968253968254e-05, | |
| "loss": 1.04, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 55.82, | |
| "learning_rate": 2.4404761904761906e-05, | |
| "loss": 1.0552, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 1.0405, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.4716666666666667, | |
| "eval_loss": 1.5788267850875854, | |
| "eval_runtime": 6.7843, | |
| "eval_samples_per_second": 265.32, | |
| "eval_steps_per_second": 8.402, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 56.18, | |
| "learning_rate": 2.4206349206349206e-05, | |
| "loss": 1.0667, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 56.36, | |
| "learning_rate": 2.4107142857142858e-05, | |
| "loss": 1.046, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 2.400793650793651e-05, | |
| "loss": 1.0146, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 56.71, | |
| "learning_rate": 2.390873015873016e-05, | |
| "loss": 1.0656, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 56.89, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 1.0172, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.4766666666666667, | |
| "eval_loss": 1.585532546043396, | |
| "eval_runtime": 6.9697, | |
| "eval_samples_per_second": 258.26, | |
| "eval_steps_per_second": 8.178, | |
| "step": 3206 | |
| }, | |
| { | |
| "epoch": 57.07, | |
| "learning_rate": 2.3710317460317462e-05, | |
| "loss": 1.0719, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 57.24, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 1.0542, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 57.42, | |
| "learning_rate": 2.3511904761904762e-05, | |
| "loss": 1.0316, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 57.6, | |
| "learning_rate": 2.3412698412698414e-05, | |
| "loss": 0.993, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 57.78, | |
| "learning_rate": 2.3313492063492066e-05, | |
| "loss": 1.0508, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 57.96, | |
| "learning_rate": 2.3214285714285715e-05, | |
| "loss": 1.0036, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 57.99, | |
| "eval_accuracy": 0.455, | |
| "eval_loss": 1.6425151824951172, | |
| "eval_runtime": 7.0778, | |
| "eval_samples_per_second": 254.315, | |
| "eval_steps_per_second": 8.053, | |
| "step": 3262 | |
| }, | |
| { | |
| "epoch": 58.13, | |
| "learning_rate": 2.3115079365079367e-05, | |
| "loss": 1.0261, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 58.31, | |
| "learning_rate": 2.3015873015873015e-05, | |
| "loss": 1.0191, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 58.49, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 1.0035, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 58.67, | |
| "learning_rate": 2.281746031746032e-05, | |
| "loss": 0.9924, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 58.84, | |
| "learning_rate": 2.271825396825397e-05, | |
| "loss": 1.0124, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 58.99, | |
| "eval_accuracy": 0.4677777777777778, | |
| "eval_loss": 1.6039385795593262, | |
| "eval_runtime": 6.8431, | |
| "eval_samples_per_second": 263.038, | |
| "eval_steps_per_second": 8.33, | |
| "step": 3318 | |
| }, | |
| { | |
| "epoch": 59.02, | |
| "learning_rate": 2.261904761904762e-05, | |
| "loss": 1.0292, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 59.2, | |
| "learning_rate": 2.251984126984127e-05, | |
| "loss": 0.9945, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 59.38, | |
| "learning_rate": 2.2420634920634923e-05, | |
| "loss": 1.0021, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 59.56, | |
| "learning_rate": 2.2321428571428575e-05, | |
| "loss": 1.0187, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 59.73, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.0092, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 59.91, | |
| "learning_rate": 2.2123015873015872e-05, | |
| "loss": 1.0647, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.4572222222222222, | |
| "eval_loss": 1.5890642404556274, | |
| "eval_runtime": 11.7484, | |
| "eval_samples_per_second": 153.212, | |
| "eval_steps_per_second": 4.852, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 60.09, | |
| "learning_rate": 2.2023809523809524e-05, | |
| "loss": 1.009, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 60.27, | |
| "learning_rate": 2.1924603174603176e-05, | |
| "loss": 0.9819, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 60.44, | |
| "learning_rate": 2.1825396825396827e-05, | |
| "loss": 1.0114, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 60.62, | |
| "learning_rate": 2.172619047619048e-05, | |
| "loss": 1.0253, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 60.8, | |
| "learning_rate": 2.1626984126984128e-05, | |
| "loss": 0.9988, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 60.98, | |
| "learning_rate": 2.152777777777778e-05, | |
| "loss": 1.0143, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.4483333333333333, | |
| "eval_loss": 1.6265422105789185, | |
| "eval_runtime": 6.6939, | |
| "eval_samples_per_second": 268.9, | |
| "eval_steps_per_second": 8.515, | |
| "step": 3431 | |
| }, | |
| { | |
| "epoch": 61.16, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.9913, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "learning_rate": 2.132936507936508e-05, | |
| "loss": 0.978, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 61.51, | |
| "learning_rate": 2.1230158730158732e-05, | |
| "loss": 0.9833, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 61.69, | |
| "learning_rate": 2.113095238095238e-05, | |
| "loss": 1.049, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 61.87, | |
| "learning_rate": 2.1031746031746032e-05, | |
| "loss": 1.0051, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 61.99, | |
| "eval_accuracy": 0.4633333333333333, | |
| "eval_loss": 1.6208295822143555, | |
| "eval_runtime": 6.6968, | |
| "eval_samples_per_second": 268.784, | |
| "eval_steps_per_second": 8.511, | |
| "step": 3487 | |
| }, | |
| { | |
| "epoch": 62.04, | |
| "learning_rate": 2.0932539682539684e-05, | |
| "loss": 1.0076, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.0126, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 62.4, | |
| "learning_rate": 2.0734126984126988e-05, | |
| "loss": 0.9634, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 62.58, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 0.9616, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 62.76, | |
| "learning_rate": 2.0535714285714285e-05, | |
| "loss": 1.0025, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 62.93, | |
| "learning_rate": 2.0436507936507937e-05, | |
| "loss": 0.9571, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "eval_accuracy": 0.4483333333333333, | |
| "eval_loss": 1.6873899698257446, | |
| "eval_runtime": 6.8101, | |
| "eval_samples_per_second": 264.314, | |
| "eval_steps_per_second": 8.37, | |
| "step": 3543 | |
| }, | |
| { | |
| "epoch": 63.11, | |
| "learning_rate": 2.033730158730159e-05, | |
| "loss": 0.9859, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 63.29, | |
| "learning_rate": 2.023809523809524e-05, | |
| "loss": 0.9828, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 63.47, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 0.9969, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 63.64, | |
| "learning_rate": 2.003968253968254e-05, | |
| "loss": 1.0127, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 63.82, | |
| "learning_rate": 1.9940476190476193e-05, | |
| "loss": 0.9949, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.9838, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.45166666666666666, | |
| "eval_loss": 1.6777788400650024, | |
| "eval_runtime": 6.4627, | |
| "eval_samples_per_second": 278.521, | |
| "eval_steps_per_second": 8.82, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 64.18, | |
| "learning_rate": 1.9742063492063493e-05, | |
| "loss": 0.9745, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 64.36, | |
| "learning_rate": 1.9642857142857145e-05, | |
| "loss": 0.9895, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 64.53, | |
| "learning_rate": 1.9543650793650793e-05, | |
| "loss": 0.9219, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 64.71, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.9853, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 64.89, | |
| "learning_rate": 1.9345238095238097e-05, | |
| "loss": 0.9995, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.6247550249099731, | |
| "eval_runtime": 6.6147, | |
| "eval_samples_per_second": 272.12, | |
| "eval_steps_per_second": 8.617, | |
| "step": 3656 | |
| }, | |
| { | |
| "epoch": 65.07, | |
| "learning_rate": 1.924603174603175e-05, | |
| "loss": 0.9911, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 65.24, | |
| "learning_rate": 1.9146825396825398e-05, | |
| "loss": 1.0129, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.9734, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 65.6, | |
| "learning_rate": 1.8948412698412698e-05, | |
| "loss": 0.9699, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 65.78, | |
| "learning_rate": 1.884920634920635e-05, | |
| "loss": 0.9707, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 65.96, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.0374, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 65.99, | |
| "eval_accuracy": 0.4666666666666667, | |
| "eval_loss": 1.6644623279571533, | |
| "eval_runtime": 6.7375, | |
| "eval_samples_per_second": 267.163, | |
| "eval_steps_per_second": 8.46, | |
| "step": 3712 | |
| }, | |
| { | |
| "epoch": 66.13, | |
| "learning_rate": 1.8650793650793654e-05, | |
| "loss": 0.9862, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 66.31, | |
| "learning_rate": 1.8551587301587302e-05, | |
| "loss": 0.9879, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 66.49, | |
| "learning_rate": 1.8452380952380954e-05, | |
| "loss": 0.951, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 1.8353174603174602e-05, | |
| "loss": 0.991, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 66.84, | |
| "learning_rate": 1.8253968253968254e-05, | |
| "loss": 0.9483, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 66.99, | |
| "eval_accuracy": 0.46111111111111114, | |
| "eval_loss": 1.6306700706481934, | |
| "eval_runtime": 6.7855, | |
| "eval_samples_per_second": 265.273, | |
| "eval_steps_per_second": 8.4, | |
| "step": 3768 | |
| }, | |
| { | |
| "epoch": 67.02, | |
| "learning_rate": 1.8154761904761906e-05, | |
| "loss": 0.9483, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 67.2, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.9179, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 67.38, | |
| "learning_rate": 1.7956349206349207e-05, | |
| "loss": 0.9575, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 67.56, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.9647, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 67.73, | |
| "learning_rate": 1.775793650793651e-05, | |
| "loss": 0.9526, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 67.91, | |
| "learning_rate": 1.7658730158730162e-05, | |
| "loss": 0.9825, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.4661111111111111, | |
| "eval_loss": 1.6661802530288696, | |
| "eval_runtime": 6.7756, | |
| "eval_samples_per_second": 265.661, | |
| "eval_steps_per_second": 8.413, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 68.09, | |
| "learning_rate": 1.755952380952381e-05, | |
| "loss": 0.9248, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 68.27, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.925, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 68.44, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.9444, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 68.62, | |
| "learning_rate": 1.7261904761904763e-05, | |
| "loss": 0.9719, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 68.8, | |
| "learning_rate": 1.7162698412698415e-05, | |
| "loss": 0.9858, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 68.98, | |
| "learning_rate": 1.7063492063492063e-05, | |
| "loss": 1.0023, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.46, | |
| "eval_loss": 1.6650328636169434, | |
| "eval_runtime": 6.9757, | |
| "eval_samples_per_second": 258.039, | |
| "eval_steps_per_second": 8.171, | |
| "step": 3881 | |
| }, | |
| { | |
| "epoch": 69.16, | |
| "learning_rate": 1.6964285714285715e-05, | |
| "loss": 0.9709, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 69.33, | |
| "learning_rate": 1.6865079365079367e-05, | |
| "loss": 0.9281, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 69.51, | |
| "learning_rate": 1.6765873015873016e-05, | |
| "loss": 0.9137, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 69.69, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.9541, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 69.87, | |
| "learning_rate": 1.656746031746032e-05, | |
| "loss": 0.9642, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 69.99, | |
| "eval_accuracy": 0.4494444444444444, | |
| "eval_loss": 1.6953352689743042, | |
| "eval_runtime": 6.89, | |
| "eval_samples_per_second": 261.249, | |
| "eval_steps_per_second": 8.273, | |
| "step": 3937 | |
| }, | |
| { | |
| "epoch": 70.04, | |
| "learning_rate": 1.6468253968253968e-05, | |
| "loss": 0.978, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 70.22, | |
| "learning_rate": 1.636904761904762e-05, | |
| "loss": 0.9182, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 70.4, | |
| "learning_rate": 1.626984126984127e-05, | |
| "loss": 0.9306, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 70.58, | |
| "learning_rate": 1.6170634920634923e-05, | |
| "loss": 0.9004, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 70.76, | |
| "learning_rate": 1.6071428571428572e-05, | |
| "loss": 0.9347, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 70.93, | |
| "learning_rate": 1.597222222222222e-05, | |
| "loss": 0.9687, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 70.99, | |
| "eval_accuracy": 0.4661111111111111, | |
| "eval_loss": 1.707597017288208, | |
| "eval_runtime": 6.4216, | |
| "eval_samples_per_second": 280.303, | |
| "eval_steps_per_second": 8.876, | |
| "step": 3993 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.9244, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 71.29, | |
| "learning_rate": 1.5773809523809524e-05, | |
| "loss": 0.921, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 71.47, | |
| "learning_rate": 1.5674603174603176e-05, | |
| "loss": 0.9421, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 71.64, | |
| "learning_rate": 1.5575396825396828e-05, | |
| "loss": 0.9144, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 71.82, | |
| "learning_rate": 1.5476190476190476e-05, | |
| "loss": 1.0043, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "learning_rate": 1.537698412698413e-05, | |
| "loss": 0.9542, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.46555555555555556, | |
| "eval_loss": 1.7011748552322388, | |
| "eval_runtime": 6.7739, | |
| "eval_samples_per_second": 265.725, | |
| "eval_steps_per_second": 8.415, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 72.18, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.9239, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 72.36, | |
| "learning_rate": 1.5178571428571429e-05, | |
| "loss": 0.9682, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 72.53, | |
| "learning_rate": 1.5079365079365079e-05, | |
| "loss": 0.942, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 72.71, | |
| "learning_rate": 1.498015873015873e-05, | |
| "loss": 0.9036, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 72.89, | |
| "learning_rate": 1.4880952380952381e-05, | |
| "loss": 0.9378, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.4533333333333333, | |
| "eval_loss": 1.7056083679199219, | |
| "eval_runtime": 6.5401, | |
| "eval_samples_per_second": 275.223, | |
| "eval_steps_per_second": 8.715, | |
| "step": 4106 | |
| }, | |
| { | |
| "epoch": 73.07, | |
| "learning_rate": 1.4781746031746033e-05, | |
| "loss": 0.9286, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 73.24, | |
| "learning_rate": 1.4682539682539683e-05, | |
| "loss": 0.9517, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 73.42, | |
| "learning_rate": 1.4583333333333335e-05, | |
| "loss": 0.9557, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "learning_rate": 1.4484126984126987e-05, | |
| "loss": 0.9168, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 73.78, | |
| "learning_rate": 1.4384920634920635e-05, | |
| "loss": 0.9524, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 73.96, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.9542, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 73.99, | |
| "eval_accuracy": 0.4572222222222222, | |
| "eval_loss": 1.7331255674362183, | |
| "eval_runtime": 6.6227, | |
| "eval_samples_per_second": 271.793, | |
| "eval_steps_per_second": 8.607, | |
| "step": 4162 | |
| }, | |
| { | |
| "epoch": 74.13, | |
| "learning_rate": 1.4186507936507937e-05, | |
| "loss": 0.9507, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 74.31, | |
| "learning_rate": 1.4087301587301587e-05, | |
| "loss": 0.8558, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 74.49, | |
| "learning_rate": 1.398809523809524e-05, | |
| "loss": 0.8986, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 74.67, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.9561, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 74.84, | |
| "learning_rate": 1.3789682539682541e-05, | |
| "loss": 0.9035, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 74.99, | |
| "eval_accuracy": 0.44166666666666665, | |
| "eval_loss": 1.7459461688995361, | |
| "eval_runtime": 6.917, | |
| "eval_samples_per_second": 260.229, | |
| "eval_steps_per_second": 8.241, | |
| "step": 4218 | |
| }, | |
| { | |
| "epoch": 75.02, | |
| "learning_rate": 1.3690476190476192e-05, | |
| "loss": 0.9349, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 75.2, | |
| "learning_rate": 1.359126984126984e-05, | |
| "loss": 0.9391, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 75.38, | |
| "learning_rate": 1.3492063492063492e-05, | |
| "loss": 0.9477, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 75.56, | |
| "learning_rate": 1.3392857142857144e-05, | |
| "loss": 0.8942, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 75.73, | |
| "learning_rate": 1.3293650793650794e-05, | |
| "loss": 0.9168, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 75.91, | |
| "learning_rate": 1.3194444444444446e-05, | |
| "loss": 0.9631, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.465, | |
| "eval_loss": 1.723626732826233, | |
| "eval_runtime": 6.7505, | |
| "eval_samples_per_second": 266.648, | |
| "eval_steps_per_second": 8.444, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 76.09, | |
| "learning_rate": 1.3095238095238096e-05, | |
| "loss": 0.9378, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 76.27, | |
| "learning_rate": 1.2996031746031748e-05, | |
| "loss": 0.9081, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 76.44, | |
| "learning_rate": 1.2896825396825398e-05, | |
| "loss": 0.9126, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 76.62, | |
| "learning_rate": 1.2797619047619047e-05, | |
| "loss": 0.8934, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.9844, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 76.98, | |
| "learning_rate": 1.2599206349206349e-05, | |
| "loss": 0.8759, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.455, | |
| "eval_loss": 1.7293672561645508, | |
| "eval_runtime": 6.715, | |
| "eval_samples_per_second": 268.058, | |
| "eval_steps_per_second": 8.489, | |
| "step": 4331 | |
| }, | |
| { | |
| "epoch": 77.16, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.9142, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 77.33, | |
| "learning_rate": 1.2400793650793652e-05, | |
| "loss": 0.9153, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 77.51, | |
| "learning_rate": 1.2301587301587301e-05, | |
| "loss": 0.9225, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 77.69, | |
| "learning_rate": 1.2202380952380953e-05, | |
| "loss": 0.9304, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 77.87, | |
| "learning_rate": 1.2103174603174603e-05, | |
| "loss": 0.9218, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 77.99, | |
| "eval_accuracy": 0.4577777777777778, | |
| "eval_loss": 1.7653708457946777, | |
| "eval_runtime": 7.1048, | |
| "eval_samples_per_second": 253.348, | |
| "eval_steps_per_second": 8.023, | |
| "step": 4387 | |
| }, | |
| { | |
| "epoch": 78.04, | |
| "learning_rate": 1.2003968253968255e-05, | |
| "loss": 0.8532, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 78.22, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.8794, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 78.4, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 0.8853, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 78.58, | |
| "learning_rate": 1.1706349206349207e-05, | |
| "loss": 0.8914, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 78.76, | |
| "learning_rate": 1.1607142857142857e-05, | |
| "loss": 0.9161, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 78.93, | |
| "learning_rate": 1.1507936507936508e-05, | |
| "loss": 0.9077, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 78.99, | |
| "eval_accuracy": 0.45944444444444443, | |
| "eval_loss": 1.7234431505203247, | |
| "eval_runtime": 6.668, | |
| "eval_samples_per_second": 269.947, | |
| "eval_steps_per_second": 8.548, | |
| "step": 4443 | |
| }, | |
| { | |
| "epoch": 79.11, | |
| "learning_rate": 1.140873015873016e-05, | |
| "loss": 0.897, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 79.29, | |
| "learning_rate": 1.130952380952381e-05, | |
| "loss": 0.8687, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 79.47, | |
| "learning_rate": 1.1210317460317461e-05, | |
| "loss": 0.8983, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 79.64, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.9047, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 79.82, | |
| "learning_rate": 1.1011904761904762e-05, | |
| "loss": 0.8923, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.0912698412698414e-05, | |
| "loss": 0.8924, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.4683333333333333, | |
| "eval_loss": 1.7255866527557373, | |
| "eval_runtime": 6.948, | |
| "eval_samples_per_second": 259.067, | |
| "eval_steps_per_second": 8.204, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 80.18, | |
| "learning_rate": 1.0813492063492064e-05, | |
| "loss": 0.8976, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 80.36, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 0.8618, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 80.53, | |
| "learning_rate": 1.0615079365079366e-05, | |
| "loss": 0.8743, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 80.71, | |
| "learning_rate": 1.0515873015873016e-05, | |
| "loss": 0.9115, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 80.89, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.9156, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.4677777777777778, | |
| "eval_loss": 1.73197603225708, | |
| "eval_runtime": 6.9362, | |
| "eval_samples_per_second": 259.509, | |
| "eval_steps_per_second": 8.218, | |
| "step": 4556 | |
| }, | |
| { | |
| "epoch": 81.07, | |
| "learning_rate": 1.0317460317460318e-05, | |
| "loss": 0.8605, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 81.24, | |
| "learning_rate": 1.0218253968253968e-05, | |
| "loss": 0.8848, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 81.42, | |
| "learning_rate": 1.011904761904762e-05, | |
| "loss": 0.875, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 81.6, | |
| "learning_rate": 1.001984126984127e-05, | |
| "loss": 0.896, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 81.78, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 0.8848, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 81.96, | |
| "learning_rate": 9.821428571428573e-06, | |
| "loss": 0.806, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 81.99, | |
| "eval_accuracy": 0.4661111111111111, | |
| "eval_loss": 1.734808087348938, | |
| "eval_runtime": 6.8749, | |
| "eval_samples_per_second": 261.821, | |
| "eval_steps_per_second": 8.291, | |
| "step": 4612 | |
| }, | |
| { | |
| "epoch": 82.13, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.8712, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 82.31, | |
| "learning_rate": 9.623015873015875e-06, | |
| "loss": 0.8963, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 82.49, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.871, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 82.67, | |
| "learning_rate": 9.424603174603175e-06, | |
| "loss": 0.854, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 82.84, | |
| "learning_rate": 9.325396825396827e-06, | |
| "loss": 0.8863, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 82.99, | |
| "eval_accuracy": 0.46055555555555555, | |
| "eval_loss": 1.7513699531555176, | |
| "eval_runtime": 6.8287, | |
| "eval_samples_per_second": 263.592, | |
| "eval_steps_per_second": 8.347, | |
| "step": 4668 | |
| }, | |
| { | |
| "epoch": 83.02, | |
| "learning_rate": 9.226190476190477e-06, | |
| "loss": 0.9394, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 83.2, | |
| "learning_rate": 9.126984126984127e-06, | |
| "loss": 0.887, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 83.38, | |
| "learning_rate": 9.027777777777777e-06, | |
| "loss": 0.8937, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 83.56, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.8514, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 83.73, | |
| "learning_rate": 8.829365079365081e-06, | |
| "loss": 0.8772, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 83.91, | |
| "learning_rate": 8.73015873015873e-06, | |
| "loss": 0.8698, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.4661111111111111, | |
| "eval_loss": 1.7483917474746704, | |
| "eval_runtime": 6.4282, | |
| "eval_samples_per_second": 280.014, | |
| "eval_steps_per_second": 8.867, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 84.09, | |
| "learning_rate": 8.630952380952381e-06, | |
| "loss": 0.8657, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 84.27, | |
| "learning_rate": 8.531746031746032e-06, | |
| "loss": 0.8555, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 8.432539682539684e-06, | |
| "loss": 0.8727, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 84.62, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.8733, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 84.8, | |
| "learning_rate": 8.234126984126984e-06, | |
| "loss": 0.9119, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 84.98, | |
| "learning_rate": 8.134920634920636e-06, | |
| "loss": 0.8623, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.4777777777777778, | |
| "eval_loss": 1.7420405149459839, | |
| "eval_runtime": 7.1131, | |
| "eval_samples_per_second": 253.054, | |
| "eval_steps_per_second": 8.013, | |
| "step": 4781 | |
| }, | |
| { | |
| "epoch": 85.16, | |
| "learning_rate": 8.035714285714286e-06, | |
| "loss": 0.9058, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 85.33, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.9022, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 85.51, | |
| "learning_rate": 7.837301587301588e-06, | |
| "loss": 0.8344, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 85.69, | |
| "learning_rate": 7.738095238095238e-06, | |
| "loss": 0.8355, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 85.87, | |
| "learning_rate": 7.63888888888889e-06, | |
| "loss": 0.8643, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 85.99, | |
| "eval_accuracy": 0.46166666666666667, | |
| "eval_loss": 1.7636218070983887, | |
| "eval_runtime": 6.5419, | |
| "eval_samples_per_second": 275.149, | |
| "eval_steps_per_second": 8.713, | |
| "step": 4837 | |
| }, | |
| { | |
| "epoch": 86.04, | |
| "learning_rate": 7.5396825396825394e-06, | |
| "loss": 0.8704, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 86.22, | |
| "learning_rate": 7.4404761904761905e-06, | |
| "loss": 0.8238, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 86.4, | |
| "learning_rate": 7.3412698412698415e-06, | |
| "loss": 0.8606, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 86.58, | |
| "learning_rate": 7.242063492063493e-06, | |
| "loss": 0.8792, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 86.76, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.8643, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 86.93, | |
| "learning_rate": 7.043650793650794e-06, | |
| "loss": 0.8914, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 86.99, | |
| "eval_accuracy": 0.465, | |
| "eval_loss": 1.7551671266555786, | |
| "eval_runtime": 6.4893, | |
| "eval_samples_per_second": 277.379, | |
| "eval_steps_per_second": 8.784, | |
| "step": 4893 | |
| }, | |
| { | |
| "epoch": 87.11, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.8279, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 87.29, | |
| "learning_rate": 6.845238095238096e-06, | |
| "loss": 0.8537, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 87.47, | |
| "learning_rate": 6.746031746031746e-06, | |
| "loss": 0.8736, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 87.64, | |
| "learning_rate": 6.646825396825397e-06, | |
| "loss": 0.8449, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 87.82, | |
| "learning_rate": 6.547619047619048e-06, | |
| "loss": 0.8282, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "learning_rate": 6.448412698412699e-06, | |
| "loss": 0.837, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.46444444444444444, | |
| "eval_loss": 1.755152702331543, | |
| "eval_runtime": 6.8002, | |
| "eval_samples_per_second": 264.7, | |
| "eval_steps_per_second": 8.382, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 88.18, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.8562, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 88.36, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.8646, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 88.53, | |
| "learning_rate": 6.1507936507936505e-06, | |
| "loss": 0.8499, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 88.71, | |
| "learning_rate": 6.0515873015873015e-06, | |
| "loss": 0.8845, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.8217, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.4638888888888889, | |
| "eval_loss": 1.7532140016555786, | |
| "eval_runtime": 7.0476, | |
| "eval_samples_per_second": 255.408, | |
| "eval_steps_per_second": 8.088, | |
| "step": 5006 | |
| }, | |
| { | |
| "epoch": 89.07, | |
| "learning_rate": 5.8531746031746036e-06, | |
| "loss": 0.8373, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 89.24, | |
| "learning_rate": 5.753968253968254e-06, | |
| "loss": 0.7907, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 89.42, | |
| "learning_rate": 5.654761904761905e-06, | |
| "loss": 0.8347, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 89.6, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.867, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 89.78, | |
| "learning_rate": 5.456349206349207e-06, | |
| "loss": 0.8816, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 89.96, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.8601, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 89.99, | |
| "eval_accuracy": 0.4683333333333333, | |
| "eval_loss": 1.7447186708450317, | |
| "eval_runtime": 6.3932, | |
| "eval_samples_per_second": 281.551, | |
| "eval_steps_per_second": 8.916, | |
| "step": 5062 | |
| }, | |
| { | |
| "epoch": 90.13, | |
| "learning_rate": 5.257936507936508e-06, | |
| "loss": 0.8323, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 90.31, | |
| "learning_rate": 5.158730158730159e-06, | |
| "loss": 0.8112, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 90.49, | |
| "learning_rate": 5.05952380952381e-06, | |
| "loss": 0.8216, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 90.67, | |
| "learning_rate": 4.96031746031746e-06, | |
| "loss": 0.8778, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 90.84, | |
| "learning_rate": 4.861111111111111e-06, | |
| "loss": 0.8293, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 90.99, | |
| "eval_accuracy": 0.46111111111111114, | |
| "eval_loss": 1.7622219324111938, | |
| "eval_runtime": 6.9088, | |
| "eval_samples_per_second": 260.536, | |
| "eval_steps_per_second": 8.25, | |
| "step": 5118 | |
| }, | |
| { | |
| "epoch": 91.02, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.8845, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 91.2, | |
| "learning_rate": 4.662698412698413e-06, | |
| "loss": 0.8444, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 91.38, | |
| "learning_rate": 4.563492063492064e-06, | |
| "loss": 0.8317, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 91.56, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 0.8954, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 91.73, | |
| "learning_rate": 4.365079365079365e-06, | |
| "loss": 0.8456, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 91.91, | |
| "learning_rate": 4.265873015873016e-06, | |
| "loss": 0.8301, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.4633333333333333, | |
| "eval_loss": 1.7615541219711304, | |
| "eval_runtime": 6.8433, | |
| "eval_samples_per_second": 263.03, | |
| "eval_steps_per_second": 8.329, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 92.09, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.8093, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 92.27, | |
| "learning_rate": 4.067460317460318e-06, | |
| "loss": 0.777, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 92.44, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.8227, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 92.62, | |
| "learning_rate": 3.869047619047619e-06, | |
| "loss": 0.8856, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 92.8, | |
| "learning_rate": 3.7698412698412697e-06, | |
| "loss": 0.8843, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 92.98, | |
| "learning_rate": 3.6706349206349208e-06, | |
| "loss": 0.7752, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.758492112159729, | |
| "eval_runtime": 6.7386, | |
| "eval_samples_per_second": 267.116, | |
| "eval_steps_per_second": 8.459, | |
| "step": 5231 | |
| }, | |
| { | |
| "epoch": 93.16, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.8809, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 93.33, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.8723, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 93.51, | |
| "learning_rate": 3.373015873015873e-06, | |
| "loss": 0.8171, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 93.69, | |
| "learning_rate": 3.273809523809524e-06, | |
| "loss": 0.8263, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 93.87, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.8533, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 93.99, | |
| "eval_accuracy": 0.46166666666666667, | |
| "eval_loss": 1.7842094898223877, | |
| "eval_runtime": 6.567, | |
| "eval_samples_per_second": 274.097, | |
| "eval_steps_per_second": 8.68, | |
| "step": 5287 | |
| }, | |
| { | |
| "epoch": 94.04, | |
| "learning_rate": 3.0753968253968252e-06, | |
| "loss": 0.8544, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 94.22, | |
| "learning_rate": 2.9761904761904763e-06, | |
| "loss": 0.8108, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 94.4, | |
| "learning_rate": 2.876984126984127e-06, | |
| "loss": 0.8582, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 94.58, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.796, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 94.76, | |
| "learning_rate": 2.6785714285714285e-06, | |
| "loss": 0.8624, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 94.93, | |
| "learning_rate": 2.5793650793650795e-06, | |
| "loss": 0.8156, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 94.99, | |
| "eval_accuracy": 0.4622222222222222, | |
| "eval_loss": 1.7836720943450928, | |
| "eval_runtime": 7.173, | |
| "eval_samples_per_second": 250.943, | |
| "eval_steps_per_second": 7.947, | |
| "step": 5343 | |
| }, | |
| { | |
| "epoch": 95.11, | |
| "learning_rate": 2.48015873015873e-06, | |
| "loss": 0.8156, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 95.29, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.8371, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 95.47, | |
| "learning_rate": 2.281746031746032e-06, | |
| "loss": 0.8235, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 95.64, | |
| "learning_rate": 2.1825396825396824e-06, | |
| "loss": 0.8466, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 95.82, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.8283, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "learning_rate": 1.984126984126984e-06, | |
| "loss": 0.8094, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.4583333333333333, | |
| "eval_loss": 1.7896106243133545, | |
| "eval_runtime": 6.5048, | |
| "eval_samples_per_second": 276.719, | |
| "eval_steps_per_second": 8.763, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 96.18, | |
| "learning_rate": 1.8849206349206349e-06, | |
| "loss": 0.7934, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 96.36, | |
| "learning_rate": 1.7857142857142857e-06, | |
| "loss": 0.8529, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 96.53, | |
| "learning_rate": 1.6865079365079365e-06, | |
| "loss": 0.8691, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 96.71, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 0.8508, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 96.89, | |
| "learning_rate": 1.4880952380952381e-06, | |
| "loss": 0.839, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.465, | |
| "eval_loss": 1.7834640741348267, | |
| "eval_runtime": 6.5614, | |
| "eval_samples_per_second": 274.333, | |
| "eval_steps_per_second": 8.687, | |
| "step": 5456 | |
| }, | |
| { | |
| "epoch": 97.07, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.8844, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 97.24, | |
| "learning_rate": 1.2896825396825398e-06, | |
| "loss": 0.8183, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 97.42, | |
| "learning_rate": 1.1904761904761904e-06, | |
| "loss": 0.8597, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 97.6, | |
| "learning_rate": 1.0912698412698412e-06, | |
| "loss": 0.8369, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 97.78, | |
| "learning_rate": 9.92063492063492e-07, | |
| "loss": 0.8169, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 97.96, | |
| "learning_rate": 8.928571428571428e-07, | |
| "loss": 0.839, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "eval_accuracy": 0.46, | |
| "eval_loss": 1.7882862091064453, | |
| "eval_runtime": 6.3877, | |
| "eval_samples_per_second": 281.793, | |
| "eval_steps_per_second": 8.923, | |
| "step": 5512 | |
| }, | |
| { | |
| "epoch": 98.13, | |
| "learning_rate": 7.936507936507937e-07, | |
| "loss": 0.8395, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 98.31, | |
| "learning_rate": 6.944444444444445e-07, | |
| "loss": 0.8356, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 98.49, | |
| "learning_rate": 5.952380952380952e-07, | |
| "loss": 0.8396, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 98.67, | |
| "learning_rate": 4.96031746031746e-07, | |
| "loss": 0.8194, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 98.84, | |
| "learning_rate": 3.9682539682539683e-07, | |
| "loss": 0.7763, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 98.99, | |
| "eval_accuracy": 0.45944444444444443, | |
| "eval_loss": 1.7838345766067505, | |
| "eval_runtime": 6.912, | |
| "eval_samples_per_second": 260.415, | |
| "eval_steps_per_second": 8.246, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 99.02, | |
| "learning_rate": 2.976190476190476e-07, | |
| "loss": 0.809, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 99.2, | |
| "learning_rate": 1.9841269841269841e-07, | |
| "loss": 0.8239, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 99.38, | |
| "learning_rate": 9.920634920634921e-08, | |
| "loss": 0.7982, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 99.56, | |
| "learning_rate": 0.0, | |
| "loss": 0.8186, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 99.56, | |
| "eval_accuracy": 0.46055555555555555, | |
| "eval_loss": 1.7836859226226807, | |
| "eval_runtime": 6.4969, | |
| "eval_samples_per_second": 277.055, | |
| "eval_steps_per_second": 8.773, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 99.56, | |
| "step": 5600, | |
| "total_flos": 1.782025780985856e+19, | |
| "train_loss": 1.117841152037893, | |
| "train_runtime": 7254.7208, | |
| "train_samples_per_second": 99.246, | |
| "train_steps_per_second": 0.772 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "total_flos": 1.782025780985856e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |