| { | |
| "best_metric": 0.7222222222222222, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-55-fold4/checkpoint-87", | |
| "epoch": 57.142857142857146, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5714285714285714, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.250338077545166, | |
| "eval_runtime": 0.4949, | |
| "eval_samples_per_second": 72.745, | |
| "eval_steps_per_second": 4.041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.1730682849884033, | |
| "eval_runtime": 0.5091, | |
| "eval_samples_per_second": 70.719, | |
| "eval_steps_per_second": 3.929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.08519446849823, | |
| "eval_runtime": 0.5213, | |
| "eval_samples_per_second": 69.053, | |
| "eval_steps_per_second": 3.836, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0786566734313965, | |
| "eval_runtime": 0.5105, | |
| "eval_samples_per_second": 70.517, | |
| "eval_steps_per_second": 3.918, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.119874358177185, | |
| "eval_runtime": 0.508, | |
| "eval_samples_per_second": 70.865, | |
| "eval_steps_per_second": 3.937, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 8.105093955993652, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0532, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.058439016342163, | |
| "eval_runtime": 0.503, | |
| "eval_samples_per_second": 71.568, | |
| "eval_steps_per_second": 3.976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.079984426498413, | |
| "eval_runtime": 0.5018, | |
| "eval_samples_per_second": 71.749, | |
| "eval_steps_per_second": 3.986, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1634804010391235, | |
| "eval_runtime": 0.5036, | |
| "eval_samples_per_second": 71.489, | |
| "eval_steps_per_second": 3.972, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.117082118988037, | |
| "eval_runtime": 0.5076, | |
| "eval_samples_per_second": 70.927, | |
| "eval_steps_per_second": 3.94, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.5253615379333496, | |
| "eval_runtime": 0.5046, | |
| "eval_samples_per_second": 71.347, | |
| "eval_steps_per_second": 3.964, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.1235523223876953, | |
| "eval_runtime": 0.5095, | |
| "eval_samples_per_second": 70.659, | |
| "eval_steps_per_second": 3.925, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 16.025110244750977, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0255379676818848, | |
| "eval_runtime": 0.5017, | |
| "eval_samples_per_second": 71.753, | |
| "eval_steps_per_second": 3.986, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1108105182647705, | |
| "eval_runtime": 0.516, | |
| "eval_samples_per_second": 69.764, | |
| "eval_steps_per_second": 3.876, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.0364958047866821, | |
| "eval_runtime": 0.5056, | |
| "eval_samples_per_second": 71.2, | |
| "eval_steps_per_second": 3.956, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0637767314910889, | |
| "eval_runtime": 0.5108, | |
| "eval_samples_per_second": 70.473, | |
| "eval_steps_per_second": 3.915, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.109029769897461, | |
| "eval_runtime": 0.507, | |
| "eval_samples_per_second": 71.009, | |
| "eval_steps_per_second": 3.945, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.1166322231292725, | |
| "eval_runtime": 0.4998, | |
| "eval_samples_per_second": 72.031, | |
| "eval_steps_per_second": 4.002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 11.769331932067871, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0649690628051758, | |
| "eval_runtime": 0.504, | |
| "eval_samples_per_second": 71.43, | |
| "eval_steps_per_second": 3.968, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.3084824085235596, | |
| "eval_runtime": 0.5052, | |
| "eval_samples_per_second": 71.258, | |
| "eval_steps_per_second": 3.959, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.1624348163604736, | |
| "eval_runtime": 0.5109, | |
| "eval_samples_per_second": 70.462, | |
| "eval_steps_per_second": 3.915, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9994204640388489, | |
| "eval_runtime": 0.5057, | |
| "eval_samples_per_second": 71.195, | |
| "eval_steps_per_second": 3.955, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.1053564548492432, | |
| "eval_runtime": 0.5041, | |
| "eval_samples_per_second": 71.413, | |
| "eval_steps_per_second": 3.967, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 7.592797756195068, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7472, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.0925507545471191, | |
| "eval_runtime": 0.4991, | |
| "eval_samples_per_second": 72.127, | |
| "eval_steps_per_second": 4.007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.1053681373596191, | |
| "eval_runtime": 0.5058, | |
| "eval_samples_per_second": 71.175, | |
| "eval_steps_per_second": 3.954, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.04859459400177, | |
| "eval_runtime": 0.5067, | |
| "eval_samples_per_second": 71.055, | |
| "eval_steps_per_second": 3.947, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0454154014587402, | |
| "eval_runtime": 0.5025, | |
| "eval_samples_per_second": 71.639, | |
| "eval_steps_per_second": 3.98, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0266634225845337, | |
| "eval_runtime": 0.5075, | |
| "eval_samples_per_second": 70.931, | |
| "eval_steps_per_second": 3.941, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0684125423431396, | |
| "eval_runtime": 0.5046, | |
| "eval_samples_per_second": 71.346, | |
| "eval_steps_per_second": 3.964, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 7.337016582489014, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.572, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.057525396347046, | |
| "eval_runtime": 0.5071, | |
| "eval_samples_per_second": 70.989, | |
| "eval_steps_per_second": 3.944, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1591463088989258, | |
| "eval_runtime": 0.5037, | |
| "eval_samples_per_second": 71.472, | |
| "eval_steps_per_second": 3.971, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.183729648590088, | |
| "eval_runtime": 0.5163, | |
| "eval_samples_per_second": 69.722, | |
| "eval_steps_per_second": 3.873, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0444092750549316, | |
| "eval_runtime": 0.5038, | |
| "eval_samples_per_second": 71.46, | |
| "eval_steps_per_second": 3.97, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.044967770576477, | |
| "eval_runtime": 0.508, | |
| "eval_samples_per_second": 70.871, | |
| "eval_steps_per_second": 3.937, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0974643230438232, | |
| "eval_runtime": 0.4984, | |
| "eval_samples_per_second": 72.234, | |
| "eval_steps_per_second": 4.013, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 8.1001615524292, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.471, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1130671501159668, | |
| "eval_runtime": 0.505, | |
| "eval_samples_per_second": 71.281, | |
| "eval_steps_per_second": 3.96, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1204286813735962, | |
| "eval_runtime": 0.5001, | |
| "eval_samples_per_second": 71.986, | |
| "eval_steps_per_second": 3.999, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.099246621131897, | |
| "eval_runtime": 0.5133, | |
| "eval_samples_per_second": 70.135, | |
| "eval_steps_per_second": 3.896, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0879067182540894, | |
| "eval_runtime": 0.5049, | |
| "eval_samples_per_second": 71.304, | |
| "eval_steps_per_second": 3.961, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.098131537437439, | |
| "eval_runtime": 0.5395, | |
| "eval_samples_per_second": 66.732, | |
| "eval_steps_per_second": 3.707, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 9.05555534362793, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.3896, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0576390027999878, | |
| "eval_runtime": 0.5079, | |
| "eval_samples_per_second": 70.882, | |
| "eval_steps_per_second": 3.938, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0612225532531738, | |
| "eval_runtime": 0.5106, | |
| "eval_samples_per_second": 70.508, | |
| "eval_steps_per_second": 3.917, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1194814443588257, | |
| "eval_runtime": 0.5145, | |
| "eval_samples_per_second": 69.967, | |
| "eval_steps_per_second": 3.887, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1973522901535034, | |
| "eval_runtime": 0.5092, | |
| "eval_samples_per_second": 70.697, | |
| "eval_steps_per_second": 3.928, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1352990865707397, | |
| "eval_runtime": 0.5064, | |
| "eval_samples_per_second": 71.085, | |
| "eval_steps_per_second": 3.949, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.114302158355713, | |
| "eval_runtime": 0.5104, | |
| "eval_samples_per_second": 70.53, | |
| "eval_steps_per_second": 3.918, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 9.793930053710938, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3775, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.105540156364441, | |
| "eval_runtime": 0.5086, | |
| "eval_samples_per_second": 70.788, | |
| "eval_steps_per_second": 3.933, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1997466087341309, | |
| "eval_runtime": 0.5316, | |
| "eval_samples_per_second": 67.716, | |
| "eval_steps_per_second": 3.762, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.3267438411712646, | |
| "eval_runtime": 0.5066, | |
| "eval_samples_per_second": 71.055, | |
| "eval_steps_per_second": 3.948, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.302685022354126, | |
| "eval_runtime": 0.5007, | |
| "eval_samples_per_second": 71.896, | |
| "eval_steps_per_second": 3.994, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_loss": 1.1592612266540527, | |
| "eval_runtime": 0.5068, | |
| "eval_samples_per_second": 71.034, | |
| "eval_steps_per_second": 3.946, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 50.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.097033143043518, | |
| "eval_runtime": 0.5092, | |
| "eval_samples_per_second": 70.706, | |
| "eval_steps_per_second": 3.928, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 7.551269054412842, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3623, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0902420282363892, | |
| "eval_runtime": 0.5309, | |
| "eval_samples_per_second": 67.809, | |
| "eval_steps_per_second": 3.767, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 52.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0907739400863647, | |
| "eval_runtime": 0.5094, | |
| "eval_samples_per_second": 70.667, | |
| "eval_steps_per_second": 3.926, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 53.714285714285715, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.1213774681091309, | |
| "eval_runtime": 0.5019, | |
| "eval_samples_per_second": 71.726, | |
| "eval_steps_per_second": 3.985, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 54.857142857142854, | |
| "eval_accuracy": 0.6944444444444444, | |
| "eval_loss": 1.1691011190414429, | |
| "eval_runtime": 0.5009, | |
| "eval_samples_per_second": 71.877, | |
| "eval_steps_per_second": 3.993, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1913933753967285, | |
| "eval_runtime": 0.5224, | |
| "eval_samples_per_second": 68.909, | |
| "eval_steps_per_second": 3.828, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 56.57142857142857, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1948727369308472, | |
| "eval_runtime": 0.5073, | |
| "eval_samples_per_second": 70.97, | |
| "eval_steps_per_second": 3.943, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 7.683139801025391, | |
| "learning_rate": 0.0, | |
| "loss": 0.3455, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1951266527175903, | |
| "eval_runtime": 0.5088, | |
| "eval_samples_per_second": 70.76, | |
| "eval_steps_per_second": 3.931, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "step": 100, | |
| "total_flos": 8.766873360020644e+17, | |
| "train_loss": 0.6019677090644836, | |
| "train_runtime": 552.2645, | |
| "train_samples_per_second": 35.852, | |
| "train_steps_per_second": 0.181 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_loss": 1.1592612266540527, | |
| "eval_runtime": 0.602, | |
| "eval_samples_per_second": 59.796, | |
| "eval_steps_per_second": 3.322, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.766873360020644e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |