| { | |
| "best_metric": 0.7057676232933965, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned/checkpoint-1122", | |
| "epoch": 9.977728285077951, | |
| "eval_steps": 500, | |
| "global_step": 2240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.2321428571428573e-06, | |
| "loss": 0.5702, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 0.5531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.696428571428572e-06, | |
| "loss": 0.5328, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.5412, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.1160714285714287e-05, | |
| "loss": 0.5131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.3392857142857144e-05, | |
| "loss": 0.5021, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.4657, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.4831, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0089285714285717e-05, | |
| "loss": 0.4942, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.2321428571428575e-05, | |
| "loss": 0.531, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.455357142857143e-05, | |
| "loss": 0.4907, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 0.4482, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.9017857142857146e-05, | |
| "loss": 0.5041, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.4777, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.348214285714286e-05, | |
| "loss": 0.4692, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.4646, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.794642857142857e-05, | |
| "loss": 0.4503, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 0.5269, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.2410714285714285e-05, | |
| "loss": 0.4849, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 0.4956, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.4993, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.910714285714286e-05, | |
| "loss": 0.4887, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6776260796879353, | |
| "eval_loss": 0.9212561845779419, | |
| "eval_runtime": 60.2714, | |
| "eval_samples_per_second": 119.095, | |
| "eval_steps_per_second": 3.733, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.985119047619048e-05, | |
| "loss": 0.5157, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.960317460317461e-05, | |
| "loss": 0.5364, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.9355158730158735e-05, | |
| "loss": 0.5125, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.910714285714286e-05, | |
| "loss": 0.5028, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.8859126984126984e-05, | |
| "loss": 0.4801, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.5442, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.836309523809524e-05, | |
| "loss": 0.4718, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.811507936507937e-05, | |
| "loss": 0.5095, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.7867063492063496e-05, | |
| "loss": 0.5151, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.4909, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.7371031746031745e-05, | |
| "loss": 0.4797, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.7123015873015876e-05, | |
| "loss": 0.4604, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.5055, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.662698412698413e-05, | |
| "loss": 0.5105, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.637896825396826e-05, | |
| "loss": 0.4788, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.613095238095239e-05, | |
| "loss": 0.4973, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.5882936507936506e-05, | |
| "loss": 0.5572, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 4.563492063492064e-05, | |
| "loss": 0.5182, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.538690476190476e-05, | |
| "loss": 0.4698, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.4881, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 4.489087301587302e-05, | |
| "loss": 0.4835, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 0.4969, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6926720534967957, | |
| "eval_loss": 0.9037817716598511, | |
| "eval_runtime": 60.4491, | |
| "eval_samples_per_second": 118.744, | |
| "eval_steps_per_second": 3.722, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.439484126984127e-05, | |
| "loss": 0.4971, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.41468253968254e-05, | |
| "loss": 0.4229, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 4.3898809523809523e-05, | |
| "loss": 0.3694, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 0.4295, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.340277777777778e-05, | |
| "loss": 0.3998, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.315476190476191e-05, | |
| "loss": 0.4112, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.290674603174603e-05, | |
| "loss": 0.3728, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.265873015873016e-05, | |
| "loss": 0.4243, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.2410714285714285e-05, | |
| "loss": 0.4209, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 4.2162698412698416e-05, | |
| "loss": 0.3886, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.191468253968254e-05, | |
| "loss": 0.3707, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4203, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.14186507936508e-05, | |
| "loss": 0.4213, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.117063492063492e-05, | |
| "loss": 0.3677, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.0922619047619046e-05, | |
| "loss": 0.4198, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.067460317460318e-05, | |
| "loss": 0.4307, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.04265873015873e-05, | |
| "loss": 0.4073, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 0.3957, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.993055555555556e-05, | |
| "loss": 0.479, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.4069, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.943452380952381e-05, | |
| "loss": 0.417, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.918650793650794e-05, | |
| "loss": 0.4129, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 3.893849206349206e-05, | |
| "loss": 0.4095, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6976873780997492, | |
| "eval_loss": 0.9076758027076721, | |
| "eval_runtime": 60.0956, | |
| "eval_samples_per_second": 119.443, | |
| "eval_steps_per_second": 3.744, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.8690476190476195e-05, | |
| "loss": 0.3228, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.844246031746032e-05, | |
| "loss": 0.3362, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.3026, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.794642857142857e-05, | |
| "loss": 0.3237, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.76984126984127e-05, | |
| "loss": 0.3192, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.7450396825396824e-05, | |
| "loss": 0.3461, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.7202380952380956e-05, | |
| "loss": 0.3568, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.695436507936508e-05, | |
| "loss": 0.3143, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.6706349206349205e-05, | |
| "loss": 0.3381, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 3.6458333333333336e-05, | |
| "loss": 0.3297, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 3.621031746031746e-05, | |
| "loss": 0.3333, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 3.5962301587301586e-05, | |
| "loss": 0.3232, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.3449, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.546626984126984e-05, | |
| "loss": 0.3563, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 3.521825396825397e-05, | |
| "loss": 0.3326, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 3.49702380952381e-05, | |
| "loss": 0.333, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.3357, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 3.4474206349206354e-05, | |
| "loss": 0.3738, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 3.422619047619048e-05, | |
| "loss": 0.3769, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 3.397817460317461e-05, | |
| "loss": 0.3667, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.3730158730158734e-05, | |
| "loss": 0.3459, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 3.348214285714286e-05, | |
| "loss": 0.3344, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6989412092504876, | |
| "eval_loss": 0.939809262752533, | |
| "eval_runtime": 60.4275, | |
| "eval_samples_per_second": 118.787, | |
| "eval_steps_per_second": 3.723, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 3.3234126984126983e-05, | |
| "loss": 0.3389, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.2986111111111115e-05, | |
| "loss": 0.274, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 3.273809523809524e-05, | |
| "loss": 0.2425, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.249007936507937e-05, | |
| "loss": 0.2447, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 3.2242063492063495e-05, | |
| "loss": 0.2604, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 3.199404761904762e-05, | |
| "loss": 0.26, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.2547, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 3.1498015873015876e-05, | |
| "loss": 0.2642, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.2564, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3.100198412698413e-05, | |
| "loss": 0.2667, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 3.075396825396826e-05, | |
| "loss": 0.2687, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.0505952380952385e-05, | |
| "loss": 0.2744, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 3.0257936507936506e-05, | |
| "loss": 0.2594, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 3.0009920634920634e-05, | |
| "loss": 0.3404, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 0.3398, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.951388888888889e-05, | |
| "loss": 0.2875, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.9265873015873018e-05, | |
| "loss": 0.3213, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.9017857142857146e-05, | |
| "loss": 0.3015, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.876984126984127e-05, | |
| "loss": 0.2809, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 2.8521825396825395e-05, | |
| "loss": 0.3107, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.8273809523809523e-05, | |
| "loss": 0.3181, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.802579365079365e-05, | |
| "loss": 0.2677, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3055, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7057676232933965, | |
| "eval_loss": 0.9803113341331482, | |
| "eval_runtime": 60.4436, | |
| "eval_samples_per_second": 118.755, | |
| "eval_steps_per_second": 3.722, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 2.7529761904761907e-05, | |
| "loss": 0.2474, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 2.7281746031746032e-05, | |
| "loss": 0.2207, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.703373015873016e-05, | |
| "loss": 0.2116, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 0.1894, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.6537698412698416e-05, | |
| "loss": 0.2606, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.628968253968254e-05, | |
| "loss": 0.1872, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.604166666666667e-05, | |
| "loss": 0.215, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2.5793650793650796e-05, | |
| "loss": 0.1991, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 2.554563492063492e-05, | |
| "loss": 0.2105, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 2.529761904761905e-05, | |
| "loss": 0.2384, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 2.5049603174603177e-05, | |
| "loss": 0.222, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 2.4801587301587305e-05, | |
| "loss": 0.2175, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.455357142857143e-05, | |
| "loss": 0.2362, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.2768, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.4057539682539686e-05, | |
| "loss": 0.2614, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.2127, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 2.3561507936507938e-05, | |
| "loss": 0.2232, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.3313492063492066e-05, | |
| "loss": 0.2089, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 2.3065476190476194e-05, | |
| "loss": 0.2321, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.281746031746032e-05, | |
| "loss": 0.242, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 2.2569444444444447e-05, | |
| "loss": 0.2388, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 2.2321428571428575e-05, | |
| "loss": 0.2214, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6953190303705767, | |
| "eval_loss": 1.0336716175079346, | |
| "eval_runtime": 60.3923, | |
| "eval_samples_per_second": 118.856, | |
| "eval_steps_per_second": 3.726, | |
| "step": 1347 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.20734126984127e-05, | |
| "loss": 0.2192, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 2.1825396825396827e-05, | |
| "loss": 0.1988, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 2.1577380952380955e-05, | |
| "loss": 0.1624, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 2.132936507936508e-05, | |
| "loss": 0.1565, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 2.1081349206349208e-05, | |
| "loss": 0.1683, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.181, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 2.058531746031746e-05, | |
| "loss": 0.2063, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 2.033730158730159e-05, | |
| "loss": 0.1847, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 2.0089285714285717e-05, | |
| "loss": 0.1802, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.1626, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.959325396825397e-05, | |
| "loss": 0.1446, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.9345238095238097e-05, | |
| "loss": 0.1693, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.9097222222222222e-05, | |
| "loss": 0.1996, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 1.884920634920635e-05, | |
| "loss": 0.1653, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.8601190476190478e-05, | |
| "loss": 0.1622, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 1.8353174603174602e-05, | |
| "loss": 0.1654, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 1.810515873015873e-05, | |
| "loss": 0.1843, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.1779, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.7609126984126986e-05, | |
| "loss": 0.1801, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.1829, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1.711309523809524e-05, | |
| "loss": 0.1789, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 1.6865079365079367e-05, | |
| "loss": 0.1894, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.6617063492063492e-05, | |
| "loss": 0.1575, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6976873780997492, | |
| "eval_loss": 1.0642220973968506, | |
| "eval_runtime": 59.9724, | |
| "eval_samples_per_second": 119.688, | |
| "eval_steps_per_second": 3.752, | |
| "step": 1571 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 1.636904761904762e-05, | |
| "loss": 0.1495, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.6121031746031748e-05, | |
| "loss": 0.1392, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.1095, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.1353, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.537698412698413e-05, | |
| "loss": 0.1332, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1.5128968253968253e-05, | |
| "loss": 0.1227, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.4880952380952381e-05, | |
| "loss": 0.1459, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.4632936507936509e-05, | |
| "loss": 0.1221, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.4384920634920635e-05, | |
| "loss": 0.1167, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.4136904761904762e-05, | |
| "loss": 0.1597, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1395, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.3640873015873016e-05, | |
| "loss": 0.1197, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.3392857142857144e-05, | |
| "loss": 0.1435, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.314484126984127e-05, | |
| "loss": 0.1084, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.2896825396825398e-05, | |
| "loss": 0.1581, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.2648809523809524e-05, | |
| "loss": 0.1389, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.2400793650793652e-05, | |
| "loss": 0.1297, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 1.2152777777777779e-05, | |
| "loss": 0.1641, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.127, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.1656746031746033e-05, | |
| "loss": 0.1252, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 1.140873015873016e-05, | |
| "loss": 0.1661, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.1160714285714287e-05, | |
| "loss": 0.1169, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7029813318473113, | |
| "eval_loss": 1.0828742980957031, | |
| "eval_runtime": 59.6867, | |
| "eval_samples_per_second": 120.261, | |
| "eval_steps_per_second": 3.77, | |
| "step": 1796 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 1.0912698412698414e-05, | |
| "loss": 0.1218, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 1.066468253968254e-05, | |
| "loss": 0.1021, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.1241, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 1.0168650793650794e-05, | |
| "loss": 0.1004, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 0.1279, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 9.672619047619049e-06, | |
| "loss": 0.1132, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 9.424603174603175e-06, | |
| "loss": 0.1137, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 9.176587301587301e-06, | |
| "loss": 0.0887, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.1115, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 8.680555555555556e-06, | |
| "loss": 0.0955, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 8.432539682539684e-06, | |
| "loss": 0.1268, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 8.18452380952381e-06, | |
| "loss": 0.1007, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.1025, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 7.688492063492064e-06, | |
| "loss": 0.1082, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.4404761904761905e-06, | |
| "loss": 0.0988, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 7.192460317460318e-06, | |
| "loss": 0.1012, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.1512, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 6.696428571428572e-06, | |
| "loss": 0.0984, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 6.448412698412699e-06, | |
| "loss": 0.1254, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 6.200396825396826e-06, | |
| "loss": 0.0763, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.0746, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 5.70436507936508e-06, | |
| "loss": 0.0933, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 5.456349206349207e-06, | |
| "loss": 0.0917, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7047924212872666, | |
| "eval_loss": 1.1121457815170288, | |
| "eval_runtime": 59.8317, | |
| "eval_samples_per_second": 119.97, | |
| "eval_steps_per_second": 3.761, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 5.208333333333334e-06, | |
| "loss": 0.078, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.96031746031746e-06, | |
| "loss": 0.0989, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 4.7123015873015875e-06, | |
| "loss": 0.0725, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 0.0887, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 4.216269841269842e-06, | |
| "loss": 0.0723, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.0656, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 3.7202380952380952e-06, | |
| "loss": 0.078, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.1117, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.2242063492063495e-06, | |
| "loss": 0.0865, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 2.9761904761904763e-06, | |
| "loss": 0.1098, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 2.7281746031746034e-06, | |
| "loss": 0.0955, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 2.48015873015873e-06, | |
| "loss": 0.0943, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.2321428571428573e-06, | |
| "loss": 0.0811, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.984126984126984e-06, | |
| "loss": 0.0648, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.7361111111111112e-06, | |
| "loss": 0.1009, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.4880952380952381e-06, | |
| "loss": 0.082, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 1.240079365079365e-06, | |
| "loss": 0.0714, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 9.92063492063492e-07, | |
| "loss": 0.0613, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 7.440476190476191e-07, | |
| "loss": 0.106, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 4.96031746031746e-07, | |
| "loss": 0.0915, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 2.48015873015873e-07, | |
| "loss": 0.0756, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 0.0, | |
| "loss": 0.0785, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.7052103650041794, | |
| "eval_loss": 1.1279975175857544, | |
| "eval_runtime": 66.0405, | |
| "eval_samples_per_second": 108.691, | |
| "eval_steps_per_second": 3.407, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "step": 2240, | |
| "total_flos": 2.2200667552042852e+19, | |
| "train_loss": 0.27600424638284105, | |
| "train_runtime": 6453.2956, | |
| "train_samples_per_second": 44.487, | |
| "train_steps_per_second": 0.347 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.2200667552042852e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |