| { | |
| "best_metric": 0.6944444444444444, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-55-fold2/checkpoint-77", | |
| "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": 0.3611111111111111, | |
| "eval_loss": 1.1041027307510376, | |
| "eval_runtime": 0.5095, | |
| "eval_samples_per_second": 70.656, | |
| "eval_steps_per_second": 3.925, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.106285572052002, | |
| "eval_runtime": 0.5093, | |
| "eval_samples_per_second": 70.689, | |
| "eval_steps_per_second": 3.927, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.116863489151001, | |
| "eval_runtime": 0.5172, | |
| "eval_samples_per_second": 69.611, | |
| "eval_steps_per_second": 3.867, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4444444444444444, | |
| "eval_loss": 1.0612921714782715, | |
| "eval_runtime": 0.5053, | |
| "eval_samples_per_second": 71.241, | |
| "eval_steps_per_second": 3.958, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "eval_accuracy": 0.4166666666666667, | |
| "eval_loss": 1.0636686086654663, | |
| "eval_runtime": 0.5118, | |
| "eval_samples_per_second": 70.334, | |
| "eval_steps_per_second": 3.907, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 7.565515995025635, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0545856952667236, | |
| "eval_runtime": 0.4989, | |
| "eval_samples_per_second": 72.153, | |
| "eval_steps_per_second": 4.009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_accuracy": 0.3611111111111111, | |
| "eval_loss": 1.1360119581222534, | |
| "eval_runtime": 0.5099, | |
| "eval_samples_per_second": 70.601, | |
| "eval_steps_per_second": 3.922, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0112028121948242, | |
| "eval_runtime": 0.5164, | |
| "eval_samples_per_second": 69.719, | |
| "eval_steps_per_second": 3.873, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.972854733467102, | |
| "eval_runtime": 0.5112, | |
| "eval_samples_per_second": 70.423, | |
| "eval_steps_per_second": 3.912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 9.714285714285714, | |
| "eval_accuracy": 0.4722222222222222, | |
| "eval_loss": 1.0749499797821045, | |
| "eval_runtime": 0.5086, | |
| "eval_samples_per_second": 70.781, | |
| "eval_steps_per_second": 3.932, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.9542882442474365, | |
| "eval_runtime": 0.4979, | |
| "eval_samples_per_second": 72.305, | |
| "eval_steps_per_second": 4.017, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 12.968563079833984, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.8719, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.3888888888888889, | |
| "eval_loss": 1.128890872001648, | |
| "eval_runtime": 0.5169, | |
| "eval_samples_per_second": 69.65, | |
| "eval_steps_per_second": 3.869, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 12.571428571428571, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.072733759880066, | |
| "eval_runtime": 0.5188, | |
| "eval_samples_per_second": 69.397, | |
| "eval_steps_per_second": 3.855, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 13.714285714285714, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.9727240800857544, | |
| "eval_runtime": 0.5053, | |
| "eval_samples_per_second": 71.251, | |
| "eval_steps_per_second": 3.958, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.9646502733230591, | |
| "eval_runtime": 0.5005, | |
| "eval_samples_per_second": 71.934, | |
| "eval_steps_per_second": 3.996, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9078366160392761, | |
| "eval_runtime": 0.4935, | |
| "eval_samples_per_second": 72.955, | |
| "eval_steps_per_second": 4.053, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 16.571428571428573, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.9655910134315491, | |
| "eval_runtime": 0.4976, | |
| "eval_samples_per_second": 72.34, | |
| "eval_steps_per_second": 4.019, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 7.82759952545166, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 17.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9225682020187378, | |
| "eval_runtime": 0.5102, | |
| "eval_samples_per_second": 70.564, | |
| "eval_steps_per_second": 3.92, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9611958265304565, | |
| "eval_runtime": 0.5104, | |
| "eval_samples_per_second": 70.529, | |
| "eval_steps_per_second": 3.918, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0379403829574585, | |
| "eval_runtime": 0.5058, | |
| "eval_samples_per_second": 71.181, | |
| "eval_steps_per_second": 3.955, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 20.571428571428573, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9973686933517456, | |
| "eval_runtime": 0.5179, | |
| "eval_samples_per_second": 69.513, | |
| "eval_steps_per_second": 3.862, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 21.714285714285715, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.971027672290802, | |
| "eval_runtime": 0.509, | |
| "eval_samples_per_second": 70.728, | |
| "eval_steps_per_second": 3.929, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 8.475027084350586, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6453, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.014967441558838, | |
| "eval_runtime": 0.5075, | |
| "eval_samples_per_second": 70.933, | |
| "eval_steps_per_second": 3.941, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9737722873687744, | |
| "eval_runtime": 0.5044, | |
| "eval_samples_per_second": 71.366, | |
| "eval_steps_per_second": 3.965, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 24.571428571428573, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0279996395111084, | |
| "eval_runtime": 0.5022, | |
| "eval_samples_per_second": 71.686, | |
| "eval_steps_per_second": 3.983, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0642218589782715, | |
| "eval_runtime": 0.5125, | |
| "eval_samples_per_second": 70.24, | |
| "eval_steps_per_second": 3.902, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 26.857142857142858, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.023775339126587, | |
| "eval_runtime": 0.5146, | |
| "eval_samples_per_second": 69.955, | |
| "eval_steps_per_second": 3.886, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0698802471160889, | |
| "eval_runtime": 0.5156, | |
| "eval_samples_per_second": 69.82, | |
| "eval_steps_per_second": 3.879, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "grad_norm": 8.836658477783203, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5475, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 28.571428571428573, | |
| "eval_accuracy": 0.5277777777777778, | |
| "eval_loss": 1.139428734779358, | |
| "eval_runtime": 0.5078, | |
| "eval_samples_per_second": 70.889, | |
| "eval_steps_per_second": 3.938, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 29.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9907392859458923, | |
| "eval_runtime": 0.5072, | |
| "eval_samples_per_second": 70.978, | |
| "eval_steps_per_second": 3.943, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 30.857142857142858, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.020514965057373, | |
| "eval_runtime": 0.5132, | |
| "eval_samples_per_second": 70.155, | |
| "eval_steps_per_second": 3.897, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.9423442482948303, | |
| "eval_runtime": 0.5086, | |
| "eval_samples_per_second": 70.783, | |
| "eval_steps_per_second": 3.932, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 32.57142857142857, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 0.920100748538971, | |
| "eval_runtime": 0.5189, | |
| "eval_samples_per_second": 69.376, | |
| "eval_steps_per_second": 3.854, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 33.714285714285715, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9101274013519287, | |
| "eval_runtime": 0.5117, | |
| "eval_samples_per_second": 70.351, | |
| "eval_steps_per_second": 3.908, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "grad_norm": 6.754205226898193, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.546, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 34.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9030135273933411, | |
| "eval_runtime": 0.5132, | |
| "eval_samples_per_second": 70.143, | |
| "eval_steps_per_second": 3.897, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.9389871954917908, | |
| "eval_runtime": 0.5076, | |
| "eval_samples_per_second": 70.925, | |
| "eval_steps_per_second": 3.94, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 36.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 0.951619565486908, | |
| "eval_runtime": 0.5115, | |
| "eval_samples_per_second": 70.383, | |
| "eval_steps_per_second": 3.91, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 37.714285714285715, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9317401051521301, | |
| "eval_runtime": 0.5138, | |
| "eval_samples_per_second": 70.069, | |
| "eval_steps_per_second": 3.893, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 38.857142857142854, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0006005764007568, | |
| "eval_runtime": 0.5079, | |
| "eval_samples_per_second": 70.885, | |
| "eval_steps_per_second": 3.938, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 5.250147342681885, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.4129, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.0144152641296387, | |
| "eval_runtime": 0.5123, | |
| "eval_samples_per_second": 70.277, | |
| "eval_steps_per_second": 3.904, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 40.57142857142857, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.0584615468978882, | |
| "eval_runtime": 0.5052, | |
| "eval_samples_per_second": 71.265, | |
| "eval_steps_per_second": 3.959, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 41.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0727044343948364, | |
| "eval_runtime": 0.5389, | |
| "eval_samples_per_second": 66.8, | |
| "eval_steps_per_second": 3.711, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 42.857142857142854, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0666199922561646, | |
| "eval_runtime": 0.5525, | |
| "eval_samples_per_second": 65.161, | |
| "eval_steps_per_second": 3.62, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6944444444444444, | |
| "eval_loss": 1.0368133783340454, | |
| "eval_runtime": 0.5004, | |
| "eval_samples_per_second": 71.938, | |
| "eval_steps_per_second": 3.997, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 44.57142857142857, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0238240957260132, | |
| "eval_runtime": 0.5382, | |
| "eval_samples_per_second": 66.886, | |
| "eval_steps_per_second": 3.716, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "grad_norm": 6.9052534103393555, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3913, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0247043371200562, | |
| "eval_runtime": 0.5069, | |
| "eval_samples_per_second": 71.023, | |
| "eval_steps_per_second": 3.946, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 46.857142857142854, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.048457145690918, | |
| "eval_runtime": 0.5167, | |
| "eval_samples_per_second": 69.667, | |
| "eval_steps_per_second": 3.87, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0709590911865234, | |
| "eval_runtime": 0.5203, | |
| "eval_samples_per_second": 69.185, | |
| "eval_steps_per_second": 3.844, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 48.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0898953676223755, | |
| "eval_runtime": 0.515, | |
| "eval_samples_per_second": 69.909, | |
| "eval_steps_per_second": 3.884, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 49.714285714285715, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.075623869895935, | |
| "eval_runtime": 0.5069, | |
| "eval_samples_per_second": 71.022, | |
| "eval_steps_per_second": 3.946, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 50.857142857142854, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0664737224578857, | |
| "eval_runtime": 0.5079, | |
| "eval_samples_per_second": 70.874, | |
| "eval_steps_per_second": 3.937, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 51.42857142857143, | |
| "grad_norm": 6.685548305511475, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3324, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0853261947631836, | |
| "eval_runtime": 0.5086, | |
| "eval_samples_per_second": 70.781, | |
| "eval_steps_per_second": 3.932, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 52.57142857142857, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.089843988418579, | |
| "eval_runtime": 0.5275, | |
| "eval_samples_per_second": 68.251, | |
| "eval_steps_per_second": 3.792, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 53.714285714285715, | |
| "eval_accuracy": 0.6111111111111112, | |
| "eval_loss": 1.0802342891693115, | |
| "eval_runtime": 0.5071, | |
| "eval_samples_per_second": 70.998, | |
| "eval_steps_per_second": 3.944, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 54.857142857142854, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0719918012619019, | |
| "eval_runtime": 0.5162, | |
| "eval_samples_per_second": 69.737, | |
| "eval_steps_per_second": 3.874, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0648752450942993, | |
| "eval_runtime": 0.5121, | |
| "eval_samples_per_second": 70.306, | |
| "eval_steps_per_second": 3.906, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 56.57142857142857, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.0633796453475952, | |
| "eval_runtime": 0.5339, | |
| "eval_samples_per_second": 67.433, | |
| "eval_steps_per_second": 3.746, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 8.975576400756836, | |
| "learning_rate": 0.0, | |
| "loss": 0.3117, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6388888888888888, | |
| "eval_loss": 1.062869906425476, | |
| "eval_runtime": 0.512, | |
| "eval_samples_per_second": 70.314, | |
| "eval_steps_per_second": 3.906, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "step": 100, | |
| "total_flos": 8.766873360020644e+17, | |
| "train_loss": 0.589066035747528, | |
| "train_runtime": 541.8822, | |
| "train_samples_per_second": 36.539, | |
| "train_steps_per_second": 0.185 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.6944444444444444, | |
| "eval_loss": 1.0368133783340454, | |
| "eval_runtime": 0.5959, | |
| "eval_samples_per_second": 60.41, | |
| "eval_steps_per_second": 3.356, | |
| "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 | |
| } | |