| { | |
| "best_metric": 0.8285714285714286, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-ADC-3cls-0922/checkpoint-40", | |
| "epoch": 200.0, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6875032186508179, | |
| "eval_runtime": 0.8381, | |
| "eval_samples_per_second": 83.526, | |
| "eval_steps_per_second": 2.386, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6874324083328247, | |
| "eval_runtime": 0.6285, | |
| "eval_samples_per_second": 111.384, | |
| "eval_steps_per_second": 3.182, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6873045563697815, | |
| "eval_runtime": 0.6533, | |
| "eval_samples_per_second": 107.153, | |
| "eval_steps_per_second": 3.062, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.687107264995575, | |
| "eval_runtime": 0.8041, | |
| "eval_samples_per_second": 87.057, | |
| "eval_steps_per_second": 2.487, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.7555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6868652701377869, | |
| "eval_runtime": 0.6585, | |
| "eval_samples_per_second": 106.309, | |
| "eval_steps_per_second": 3.037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.686565101146698, | |
| "eval_runtime": 0.6372, | |
| "eval_samples_per_second": 109.86, | |
| "eval_steps_per_second": 3.139, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6861968636512756, | |
| "eval_runtime": 0.8401, | |
| "eval_samples_per_second": 83.326, | |
| "eval_steps_per_second": 2.381, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.685771644115448, | |
| "eval_runtime": 0.6402, | |
| "eval_samples_per_second": 109.344, | |
| "eval_steps_per_second": 3.124, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6853042244911194, | |
| "eval_runtime": 0.638, | |
| "eval_samples_per_second": 109.711, | |
| "eval_steps_per_second": 3.135, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7576, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6847913861274719, | |
| "eval_runtime": 0.8284, | |
| "eval_samples_per_second": 84.496, | |
| "eval_steps_per_second": 2.414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6842377185821533, | |
| "eval_runtime": 0.6408, | |
| "eval_samples_per_second": 109.237, | |
| "eval_steps_per_second": 3.121, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6836268901824951, | |
| "eval_runtime": 0.6496, | |
| "eval_samples_per_second": 107.755, | |
| "eval_steps_per_second": 3.079, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6829591393470764, | |
| "eval_runtime": 0.8145, | |
| "eval_samples_per_second": 85.938, | |
| "eval_steps_per_second": 2.455, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6822755336761475, | |
| "eval_runtime": 0.6641, | |
| "eval_samples_per_second": 105.412, | |
| "eval_steps_per_second": 3.012, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6815804839134216, | |
| "eval_runtime": 0.6278, | |
| "eval_samples_per_second": 111.502, | |
| "eval_steps_per_second": 3.186, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6808401346206665, | |
| "eval_runtime": 0.8247, | |
| "eval_samples_per_second": 84.88, | |
| "eval_steps_per_second": 2.425, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6800239086151123, | |
| "eval_runtime": 0.6376, | |
| "eval_samples_per_second": 109.794, | |
| "eval_steps_per_second": 3.137, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.679133951663971, | |
| "eval_runtime": 0.6356, | |
| "eval_samples_per_second": 110.128, | |
| "eval_steps_per_second": 3.147, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6781331896781921, | |
| "eval_runtime": 0.8136, | |
| "eval_samples_per_second": 86.039, | |
| "eval_steps_per_second": 2.458, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7564, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6770716309547424, | |
| "eval_runtime": 0.627, | |
| "eval_samples_per_second": 111.643, | |
| "eval_steps_per_second": 3.19, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6759592294692993, | |
| "eval_runtime": 0.6244, | |
| "eval_samples_per_second": 112.113, | |
| "eval_steps_per_second": 3.203, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.674824059009552, | |
| "eval_runtime": 0.72, | |
| "eval_samples_per_second": 97.226, | |
| "eval_steps_per_second": 2.778, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6736522912979126, | |
| "eval_runtime": 0.6356, | |
| "eval_samples_per_second": 110.125, | |
| "eval_steps_per_second": 3.146, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6724562644958496, | |
| "eval_runtime": 0.6465, | |
| "eval_samples_per_second": 108.268, | |
| "eval_steps_per_second": 3.093, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 6.25e-05, | |
| "loss": 0.7508, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6713314056396484, | |
| "eval_runtime": 0.6458, | |
| "eval_samples_per_second": 108.385, | |
| "eval_steps_per_second": 3.097, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6701393723487854, | |
| "eval_runtime": 0.7532, | |
| "eval_samples_per_second": 92.934, | |
| "eval_steps_per_second": 2.655, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6688514947891235, | |
| "eval_runtime": 0.6275, | |
| "eval_samples_per_second": 111.546, | |
| "eval_steps_per_second": 3.187, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6674489378929138, | |
| "eval_runtime": 0.6455, | |
| "eval_samples_per_second": 108.446, | |
| "eval_steps_per_second": 3.098, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6660061478614807, | |
| "eval_runtime": 0.7926, | |
| "eval_samples_per_second": 88.312, | |
| "eval_steps_per_second": 2.523, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.747, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6645620465278625, | |
| "eval_runtime": 0.6238, | |
| "eval_samples_per_second": 112.214, | |
| "eval_steps_per_second": 3.206, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6631242632865906, | |
| "eval_runtime": 0.651, | |
| "eval_samples_per_second": 107.52, | |
| "eval_steps_per_second": 3.072, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6616196036338806, | |
| "eval_runtime": 0.8036, | |
| "eval_samples_per_second": 87.111, | |
| "eval_steps_per_second": 2.489, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6600926518440247, | |
| "eval_runtime": 0.638, | |
| "eval_samples_per_second": 109.722, | |
| "eval_steps_per_second": 3.135, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6585766673088074, | |
| "eval_runtime": 0.6365, | |
| "eval_samples_per_second": 109.973, | |
| "eval_steps_per_second": 3.142, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 8.75e-05, | |
| "loss": 0.7343, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6569960117340088, | |
| "eval_runtime": 0.7913, | |
| "eval_samples_per_second": 88.467, | |
| "eval_steps_per_second": 2.528, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6553293466567993, | |
| "eval_runtime": 0.6317, | |
| "eval_samples_per_second": 110.815, | |
| "eval_steps_per_second": 3.166, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6535871028900146, | |
| "eval_runtime": 0.6261, | |
| "eval_samples_per_second": 111.81, | |
| "eval_steps_per_second": 3.195, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6517333388328552, | |
| "eval_runtime": 0.7801, | |
| "eval_samples_per_second": 89.727, | |
| "eval_steps_per_second": 2.564, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6498710513114929, | |
| "eval_runtime": 0.6688, | |
| "eval_samples_per_second": 104.667, | |
| "eval_steps_per_second": 2.99, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7532, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6480462551116943, | |
| "eval_runtime": 0.6422, | |
| "eval_samples_per_second": 108.998, | |
| "eval_steps_per_second": 3.114, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6461040377616882, | |
| "eval_runtime": 0.7878, | |
| "eval_samples_per_second": 88.86, | |
| "eval_steps_per_second": 2.539, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6441839337348938, | |
| "eval_runtime": 0.6221, | |
| "eval_samples_per_second": 112.518, | |
| "eval_steps_per_second": 3.215, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6423068046569824, | |
| "eval_runtime": 0.6404, | |
| "eval_samples_per_second": 109.306, | |
| "eval_steps_per_second": 3.123, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6404834985733032, | |
| "eval_runtime": 0.8194, | |
| "eval_samples_per_second": 85.431, | |
| "eval_steps_per_second": 2.441, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 9.687500000000001e-05, | |
| "loss": 0.7239, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.638668417930603, | |
| "eval_runtime": 0.6293, | |
| "eval_samples_per_second": 111.227, | |
| "eval_steps_per_second": 3.178, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6368482112884521, | |
| "eval_runtime": 0.6307, | |
| "eval_samples_per_second": 110.981, | |
| "eval_steps_per_second": 3.171, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6351889967918396, | |
| "eval_runtime": 0.8243, | |
| "eval_samples_per_second": 84.921, | |
| "eval_steps_per_second": 2.426, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6336590051651001, | |
| "eval_runtime": 0.6325, | |
| "eval_samples_per_second": 110.664, | |
| "eval_steps_per_second": 3.162, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6321325302124023, | |
| "eval_runtime": 0.6292, | |
| "eval_samples_per_second": 111.258, | |
| "eval_steps_per_second": 3.179, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 9.375e-05, | |
| "loss": 0.7085, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6307134628295898, | |
| "eval_runtime": 0.8147, | |
| "eval_samples_per_second": 85.924, | |
| "eval_steps_per_second": 2.455, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6293519139289856, | |
| "eval_runtime": 0.6273, | |
| "eval_samples_per_second": 111.588, | |
| "eval_steps_per_second": 3.188, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6278188228607178, | |
| "eval_runtime": 0.6366, | |
| "eval_samples_per_second": 109.96, | |
| "eval_steps_per_second": 3.142, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6263061165809631, | |
| "eval_runtime": 0.8106, | |
| "eval_samples_per_second": 86.353, | |
| "eval_steps_per_second": 2.467, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6247809529304504, | |
| "eval_runtime": 0.637, | |
| "eval_samples_per_second": 109.885, | |
| "eval_steps_per_second": 3.14, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 9.062500000000001e-05, | |
| "loss": 0.7203, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6232935190200806, | |
| "eval_runtime": 0.6312, | |
| "eval_samples_per_second": 110.901, | |
| "eval_steps_per_second": 3.169, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6218679547309875, | |
| "eval_runtime": 0.8253, | |
| "eval_samples_per_second": 84.819, | |
| "eval_steps_per_second": 2.423, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6204643845558167, | |
| "eval_runtime": 0.6393, | |
| "eval_samples_per_second": 109.495, | |
| "eval_steps_per_second": 3.128, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6191075444221497, | |
| "eval_runtime": 0.6278, | |
| "eval_samples_per_second": 111.495, | |
| "eval_steps_per_second": 3.186, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6178752779960632, | |
| "eval_runtime": 0.8233, | |
| "eval_samples_per_second": 85.027, | |
| "eval_steps_per_second": 2.429, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 8.75e-05, | |
| "loss": 0.7136, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6167242527008057, | |
| "eval_runtime": 0.6489, | |
| "eval_samples_per_second": 107.881, | |
| "eval_steps_per_second": 3.082, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6156985759735107, | |
| "eval_runtime": 0.6472, | |
| "eval_samples_per_second": 108.154, | |
| "eval_steps_per_second": 3.09, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.61481112241745, | |
| "eval_runtime": 0.8228, | |
| "eval_samples_per_second": 85.073, | |
| "eval_steps_per_second": 2.431, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6138356328010559, | |
| "eval_runtime": 0.6327, | |
| "eval_samples_per_second": 110.64, | |
| "eval_steps_per_second": 3.161, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6125301122665405, | |
| "eval_runtime": 0.6379, | |
| "eval_samples_per_second": 109.736, | |
| "eval_steps_per_second": 3.135, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 8.4375e-05, | |
| "loss": 0.7123, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6110576391220093, | |
| "eval_runtime": 0.825, | |
| "eval_samples_per_second": 84.849, | |
| "eval_steps_per_second": 2.424, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6096405982971191, | |
| "eval_runtime": 0.6376, | |
| "eval_samples_per_second": 109.782, | |
| "eval_steps_per_second": 3.137, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6083278656005859, | |
| "eval_runtime": 0.8232, | |
| "eval_samples_per_second": 85.037, | |
| "eval_steps_per_second": 2.43, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6069909930229187, | |
| "eval_runtime": 0.8193, | |
| "eval_samples_per_second": 85.437, | |
| "eval_steps_per_second": 2.441, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6057179570198059, | |
| "eval_runtime": 0.6486, | |
| "eval_samples_per_second": 107.925, | |
| "eval_steps_per_second": 3.084, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 8.125000000000001e-05, | |
| "loss": 0.7076, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.604619562625885, | |
| "eval_runtime": 0.6358, | |
| "eval_samples_per_second": 110.095, | |
| "eval_steps_per_second": 3.146, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6034784913063049, | |
| "eval_runtime": 0.8201, | |
| "eval_samples_per_second": 85.352, | |
| "eval_steps_per_second": 2.439, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6022736430168152, | |
| "eval_runtime": 0.6311, | |
| "eval_samples_per_second": 110.91, | |
| "eval_steps_per_second": 3.169, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.6011058688163757, | |
| "eval_runtime": 0.6566, | |
| "eval_samples_per_second": 106.607, | |
| "eval_steps_per_second": 3.046, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5999324917793274, | |
| "eval_runtime": 0.8174, | |
| "eval_samples_per_second": 85.64, | |
| "eval_steps_per_second": 2.447, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 7.8125e-05, | |
| "loss": 0.6878, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5987647175788879, | |
| "eval_runtime": 0.6275, | |
| "eval_samples_per_second": 111.562, | |
| "eval_steps_per_second": 3.187, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5975351333618164, | |
| "eval_runtime": 0.6296, | |
| "eval_samples_per_second": 111.178, | |
| "eval_steps_per_second": 3.177, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5963953137397766, | |
| "eval_runtime": 0.8044, | |
| "eval_samples_per_second": 87.018, | |
| "eval_steps_per_second": 2.486, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5952684879302979, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 107.669, | |
| "eval_steps_per_second": 3.076, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5942099094390869, | |
| "eval_runtime": 0.6469, | |
| "eval_samples_per_second": 108.203, | |
| "eval_steps_per_second": 3.092, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6657, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5932222008705139, | |
| "eval_runtime": 0.8259, | |
| "eval_samples_per_second": 84.754, | |
| "eval_steps_per_second": 2.422, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5923032760620117, | |
| "eval_runtime": 0.6393, | |
| "eval_samples_per_second": 109.49, | |
| "eval_steps_per_second": 3.128, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5914328098297119, | |
| "eval_runtime": 0.6466, | |
| "eval_samples_per_second": 108.262, | |
| "eval_steps_per_second": 3.093, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5905909538269043, | |
| "eval_runtime": 0.8278, | |
| "eval_samples_per_second": 84.56, | |
| "eval_steps_per_second": 2.416, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5897351503372192, | |
| "eval_runtime": 0.6485, | |
| "eval_samples_per_second": 107.935, | |
| "eval_steps_per_second": 3.084, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 7.1875e-05, | |
| "loss": 0.6434, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.588803768157959, | |
| "eval_runtime": 0.6407, | |
| "eval_samples_per_second": 109.255, | |
| "eval_steps_per_second": 3.122, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5878075361251831, | |
| "eval_runtime": 0.7846, | |
| "eval_samples_per_second": 89.216, | |
| "eval_steps_per_second": 2.549, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5868256688117981, | |
| "eval_runtime": 0.6427, | |
| "eval_samples_per_second": 108.917, | |
| "eval_steps_per_second": 3.112, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5859082341194153, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 109.65, | |
| "eval_steps_per_second": 3.133, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5850787162780762, | |
| "eval_runtime": 0.7009, | |
| "eval_samples_per_second": 99.878, | |
| "eval_steps_per_second": 2.854, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 6.875e-05, | |
| "loss": 0.6825, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5843265652656555, | |
| "eval_runtime": 0.6343, | |
| "eval_samples_per_second": 110.361, | |
| "eval_steps_per_second": 3.153, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5835766792297363, | |
| "eval_runtime": 0.645, | |
| "eval_samples_per_second": 108.529, | |
| "eval_steps_per_second": 3.101, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5828419923782349, | |
| "eval_runtime": 0.6414, | |
| "eval_samples_per_second": 109.129, | |
| "eval_steps_per_second": 3.118, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5822591781616211, | |
| "eval_runtime": 0.6506, | |
| "eval_samples_per_second": 107.585, | |
| "eval_steps_per_second": 3.074, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5817149877548218, | |
| "eval_runtime": 0.6481, | |
| "eval_samples_per_second": 108.003, | |
| "eval_steps_per_second": 3.086, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 6.562500000000001e-05, | |
| "loss": 0.6695, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5809342265129089, | |
| "eval_runtime": 0.6426, | |
| "eval_samples_per_second": 108.939, | |
| "eval_steps_per_second": 3.113, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5801157355308533, | |
| "eval_runtime": 0.7408, | |
| "eval_samples_per_second": 94.487, | |
| "eval_steps_per_second": 2.7, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5793442130088806, | |
| "eval_runtime": 0.6328, | |
| "eval_samples_per_second": 110.628, | |
| "eval_steps_per_second": 3.161, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5787318348884583, | |
| "eval_runtime": 0.6404, | |
| "eval_samples_per_second": 109.309, | |
| "eval_steps_per_second": 3.123, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5780039429664612, | |
| "eval_runtime": 0.7894, | |
| "eval_samples_per_second": 88.678, | |
| "eval_steps_per_second": 2.534, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 6.25e-05, | |
| "loss": 0.6672, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5772114992141724, | |
| "eval_runtime": 0.6485, | |
| "eval_samples_per_second": 107.942, | |
| "eval_steps_per_second": 3.084, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5762485265731812, | |
| "eval_runtime": 0.632, | |
| "eval_samples_per_second": 110.757, | |
| "eval_steps_per_second": 3.164, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5753609538078308, | |
| "eval_runtime": 0.8156, | |
| "eval_samples_per_second": 85.824, | |
| "eval_steps_per_second": 2.452, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5745884776115417, | |
| "eval_runtime": 0.641, | |
| "eval_samples_per_second": 109.197, | |
| "eval_steps_per_second": 3.12, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.573843777179718, | |
| "eval_runtime": 0.64, | |
| "eval_samples_per_second": 109.374, | |
| "eval_steps_per_second": 3.125, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "learning_rate": 5.9375e-05, | |
| "loss": 0.6569, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5731338858604431, | |
| "eval_runtime": 0.8165, | |
| "eval_samples_per_second": 85.735, | |
| "eval_steps_per_second": 2.45, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5723776817321777, | |
| "eval_runtime": 0.6448, | |
| "eval_samples_per_second": 108.558, | |
| "eval_steps_per_second": 3.102, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5715596675872803, | |
| "eval_runtime": 0.6552, | |
| "eval_samples_per_second": 106.837, | |
| "eval_steps_per_second": 3.052, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5707866549491882, | |
| "eval_runtime": 0.7955, | |
| "eval_samples_per_second": 87.991, | |
| "eval_steps_per_second": 2.514, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.570074737071991, | |
| "eval_runtime": 0.6364, | |
| "eval_samples_per_second": 109.993, | |
| "eval_steps_per_second": 3.143, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "learning_rate": 5.6250000000000005e-05, | |
| "loss": 0.6748, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5693923830986023, | |
| "eval_runtime": 0.6356, | |
| "eval_samples_per_second": 110.138, | |
| "eval_steps_per_second": 3.147, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5686994791030884, | |
| "eval_runtime": 0.8207, | |
| "eval_samples_per_second": 85.298, | |
| "eval_steps_per_second": 2.437, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5680269598960876, | |
| "eval_runtime": 0.6498, | |
| "eval_samples_per_second": 107.722, | |
| "eval_steps_per_second": 3.078, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5673888325691223, | |
| "eval_runtime": 0.6711, | |
| "eval_samples_per_second": 104.299, | |
| "eval_steps_per_second": 2.98, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5668244957923889, | |
| "eval_runtime": 0.8599, | |
| "eval_samples_per_second": 81.4, | |
| "eval_steps_per_second": 2.326, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "learning_rate": 5.3125000000000004e-05, | |
| "loss": 0.6388, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.56624835729599, | |
| "eval_runtime": 0.639, | |
| "eval_samples_per_second": 109.549, | |
| "eval_steps_per_second": 3.13, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5657045841217041, | |
| "eval_runtime": 0.6452, | |
| "eval_samples_per_second": 108.495, | |
| "eval_steps_per_second": 3.1, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5652384757995605, | |
| "eval_runtime": 0.8319, | |
| "eval_samples_per_second": 84.146, | |
| "eval_steps_per_second": 2.404, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5648259520530701, | |
| "eval_runtime": 0.6475, | |
| "eval_samples_per_second": 108.103, | |
| "eval_steps_per_second": 3.089, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5644696354866028, | |
| "eval_runtime": 0.6531, | |
| "eval_samples_per_second": 107.184, | |
| "eval_steps_per_second": 3.062, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6551, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5640624165534973, | |
| "eval_runtime": 0.8277, | |
| "eval_samples_per_second": 84.574, | |
| "eval_steps_per_second": 2.416, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5636399388313293, | |
| "eval_runtime": 0.6478, | |
| "eval_samples_per_second": 108.056, | |
| "eval_steps_per_second": 3.087, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.563149094581604, | |
| "eval_runtime": 0.6338, | |
| "eval_samples_per_second": 110.453, | |
| "eval_steps_per_second": 3.156, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5627174973487854, | |
| "eval_runtime": 0.8111, | |
| "eval_samples_per_second": 86.304, | |
| "eval_steps_per_second": 2.466, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.562400221824646, | |
| "eval_runtime": 0.649, | |
| "eval_samples_per_second": 107.86, | |
| "eval_steps_per_second": 3.082, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.6452, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5621911287307739, | |
| "eval_runtime": 0.6465, | |
| "eval_samples_per_second": 108.279, | |
| "eval_steps_per_second": 3.094, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5620221495628357, | |
| "eval_runtime": 0.827, | |
| "eval_samples_per_second": 84.639, | |
| "eval_steps_per_second": 2.418, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5617978572845459, | |
| "eval_runtime": 0.6221, | |
| "eval_samples_per_second": 112.525, | |
| "eval_steps_per_second": 3.215, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5614616870880127, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 109.65, | |
| "eval_steps_per_second": 3.133, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5612771511077881, | |
| "eval_runtime": 0.8188, | |
| "eval_samples_per_second": 85.487, | |
| "eval_steps_per_second": 2.442, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.645, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5610944032669067, | |
| "eval_runtime": 0.6274, | |
| "eval_samples_per_second": 111.57, | |
| "eval_steps_per_second": 3.188, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 131.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5608205199241638, | |
| "eval_runtime": 0.6351, | |
| "eval_samples_per_second": 110.223, | |
| "eval_steps_per_second": 3.149, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 132.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5606086254119873, | |
| "eval_runtime": 0.8451, | |
| "eval_samples_per_second": 82.832, | |
| "eval_steps_per_second": 2.367, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 133.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5602155923843384, | |
| "eval_runtime": 0.6314, | |
| "eval_samples_per_second": 110.864, | |
| "eval_steps_per_second": 3.168, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 134.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5596277713775635, | |
| "eval_runtime": 0.6347, | |
| "eval_samples_per_second": 110.28, | |
| "eval_steps_per_second": 3.151, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 0.629, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 135.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.558956503868103, | |
| "eval_runtime": 0.8112, | |
| "eval_samples_per_second": 86.289, | |
| "eval_steps_per_second": 2.465, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 136.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5582412481307983, | |
| "eval_runtime": 0.6394, | |
| "eval_samples_per_second": 109.485, | |
| "eval_steps_per_second": 3.128, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 137.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5576009750366211, | |
| "eval_runtime": 0.6293, | |
| "eval_samples_per_second": 111.232, | |
| "eval_steps_per_second": 3.178, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 138.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5571399927139282, | |
| "eval_runtime": 0.8108, | |
| "eval_samples_per_second": 86.33, | |
| "eval_steps_per_second": 2.467, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 139.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5567926168441772, | |
| "eval_runtime": 0.6262, | |
| "eval_samples_per_second": 111.788, | |
| "eval_steps_per_second": 3.194, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.7126, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 140.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.556534469127655, | |
| "eval_runtime": 0.6392, | |
| "eval_samples_per_second": 109.51, | |
| "eval_steps_per_second": 3.129, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 141.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5563255548477173, | |
| "eval_runtime": 0.8384, | |
| "eval_samples_per_second": 83.488, | |
| "eval_steps_per_second": 2.385, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 142.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5561147928237915, | |
| "eval_runtime": 0.6382, | |
| "eval_samples_per_second": 109.687, | |
| "eval_steps_per_second": 3.134, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 143.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5559044480323792, | |
| "eval_runtime": 0.647, | |
| "eval_samples_per_second": 108.191, | |
| "eval_steps_per_second": 3.091, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 144.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.555549681186676, | |
| "eval_runtime": 0.8257, | |
| "eval_samples_per_second": 84.779, | |
| "eval_steps_per_second": 2.422, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 0.669, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 145.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5551820397377014, | |
| "eval_runtime": 0.6311, | |
| "eval_samples_per_second": 110.921, | |
| "eval_steps_per_second": 3.169, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 146.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.55474454164505, | |
| "eval_runtime": 0.653, | |
| "eval_samples_per_second": 107.193, | |
| "eval_steps_per_second": 3.063, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 147.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5542392134666443, | |
| "eval_runtime": 0.8093, | |
| "eval_samples_per_second": 86.493, | |
| "eval_steps_per_second": 2.471, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 148.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5537976622581482, | |
| "eval_runtime": 0.6472, | |
| "eval_samples_per_second": 108.161, | |
| "eval_steps_per_second": 3.09, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 149.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5534089803695679, | |
| "eval_runtime": 0.6283, | |
| "eval_samples_per_second": 111.403, | |
| "eval_steps_per_second": 3.183, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.6481, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5530030727386475, | |
| "eval_runtime": 0.8284, | |
| "eval_samples_per_second": 84.505, | |
| "eval_steps_per_second": 2.414, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 151.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5526387095451355, | |
| "eval_runtime": 0.6358, | |
| "eval_samples_per_second": 110.105, | |
| "eval_steps_per_second": 3.146, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 152.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5522416830062866, | |
| "eval_runtime": 0.6285, | |
| "eval_samples_per_second": 111.384, | |
| "eval_steps_per_second": 3.182, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 153.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5518553853034973, | |
| "eval_runtime": 0.7207, | |
| "eval_samples_per_second": 97.122, | |
| "eval_steps_per_second": 2.775, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 154.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5514690279960632, | |
| "eval_runtime": 0.6359, | |
| "eval_samples_per_second": 110.085, | |
| "eval_steps_per_second": 3.145, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 0.6211, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 155.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5510378479957581, | |
| "eval_runtime": 0.636, | |
| "eval_samples_per_second": 110.056, | |
| "eval_steps_per_second": 3.144, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 156.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5506120920181274, | |
| "eval_runtime": 0.6297, | |
| "eval_samples_per_second": 111.157, | |
| "eval_steps_per_second": 3.176, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 157.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5502142906188965, | |
| "eval_runtime": 0.6795, | |
| "eval_samples_per_second": 103.02, | |
| "eval_steps_per_second": 2.943, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 158.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5498998761177063, | |
| "eval_runtime": 0.6321, | |
| "eval_samples_per_second": 110.745, | |
| "eval_steps_per_second": 3.164, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 159.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5495581030845642, | |
| "eval_runtime": 0.6392, | |
| "eval_samples_per_second": 109.52, | |
| "eval_steps_per_second": 3.129, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6458, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 160.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5492438077926636, | |
| "eval_runtime": 0.8024, | |
| "eval_samples_per_second": 87.237, | |
| "eval_steps_per_second": 2.492, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 161.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5489979982376099, | |
| "eval_runtime": 0.6575, | |
| "eval_samples_per_second": 106.471, | |
| "eval_steps_per_second": 3.042, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 162.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5487762689590454, | |
| "eval_runtime": 0.6515, | |
| "eval_samples_per_second": 107.45, | |
| "eval_steps_per_second": 3.07, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 163.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.548595130443573, | |
| "eval_runtime": 0.8069, | |
| "eval_samples_per_second": 86.752, | |
| "eval_steps_per_second": 2.479, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 164.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5483713746070862, | |
| "eval_runtime": 0.6447, | |
| "eval_samples_per_second": 108.582, | |
| "eval_steps_per_second": 3.102, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "learning_rate": 2.1875e-05, | |
| "loss": 0.6317, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 165.0, | |
| "eval_accuracy": 0.8142857142857143, | |
| "eval_loss": 0.5481104254722595, | |
| "eval_runtime": 0.6486, | |
| "eval_samples_per_second": 107.926, | |
| "eval_steps_per_second": 3.084, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 166.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5478586554527283, | |
| "eval_runtime": 0.8209, | |
| "eval_samples_per_second": 85.268, | |
| "eval_steps_per_second": 2.436, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 167.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5475797653198242, | |
| "eval_runtime": 0.7417, | |
| "eval_samples_per_second": 94.381, | |
| "eval_steps_per_second": 2.697, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 168.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5473471879959106, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 107.671, | |
| "eval_steps_per_second": 3.076, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 169.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5471236705780029, | |
| "eval_runtime": 0.7944, | |
| "eval_samples_per_second": 88.115, | |
| "eval_steps_per_second": 2.518, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 170.0, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.6154, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 170.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5469514727592468, | |
| "eval_runtime": 0.6378, | |
| "eval_samples_per_second": 109.76, | |
| "eval_steps_per_second": 3.136, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 171.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5467889308929443, | |
| "eval_runtime": 0.6433, | |
| "eval_samples_per_second": 108.819, | |
| "eval_steps_per_second": 3.109, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 172.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5466357469558716, | |
| "eval_runtime": 0.8146, | |
| "eval_samples_per_second": 85.93, | |
| "eval_steps_per_second": 2.455, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 173.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5464411973953247, | |
| "eval_runtime": 0.6826, | |
| "eval_samples_per_second": 102.554, | |
| "eval_steps_per_second": 2.93, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 174.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5462457537651062, | |
| "eval_runtime": 0.6413, | |
| "eval_samples_per_second": 109.146, | |
| "eval_steps_per_second": 3.118, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.6323, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 175.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5460384488105774, | |
| "eval_runtime": 0.8055, | |
| "eval_samples_per_second": 86.906, | |
| "eval_steps_per_second": 2.483, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 176.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.545864999294281, | |
| "eval_runtime": 0.635, | |
| "eval_samples_per_second": 110.23, | |
| "eval_steps_per_second": 3.149, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 177.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.54571932554245, | |
| "eval_runtime": 0.6362, | |
| "eval_samples_per_second": 110.035, | |
| "eval_steps_per_second": 3.144, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 178.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5455992817878723, | |
| "eval_runtime": 0.8155, | |
| "eval_samples_per_second": 85.839, | |
| "eval_steps_per_second": 2.453, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 179.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5454698801040649, | |
| "eval_runtime": 0.6543, | |
| "eval_samples_per_second": 106.992, | |
| "eval_steps_per_second": 3.057, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 180.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.6331, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 180.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5453290343284607, | |
| "eval_runtime": 0.6499, | |
| "eval_samples_per_second": 107.716, | |
| "eval_steps_per_second": 3.078, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 181.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5451884865760803, | |
| "eval_runtime": 0.8265, | |
| "eval_samples_per_second": 84.691, | |
| "eval_steps_per_second": 2.42, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 182.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5450613498687744, | |
| "eval_runtime": 0.6389, | |
| "eval_samples_per_second": 109.556, | |
| "eval_steps_per_second": 3.13, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 183.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5449284911155701, | |
| "eval_runtime": 0.6467, | |
| "eval_samples_per_second": 108.243, | |
| "eval_steps_per_second": 3.093, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 184.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5448177456855774, | |
| "eval_runtime": 0.825, | |
| "eval_samples_per_second": 84.846, | |
| "eval_steps_per_second": 2.424, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 185.0, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.6333, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 185.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.544733464717865, | |
| "eval_runtime": 0.6541, | |
| "eval_samples_per_second": 107.012, | |
| "eval_steps_per_second": 3.057, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 186.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5446553230285645, | |
| "eval_runtime": 0.6491, | |
| "eval_samples_per_second": 107.838, | |
| "eval_steps_per_second": 3.081, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 187.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5445802211761475, | |
| "eval_runtime": 0.8184, | |
| "eval_samples_per_second": 85.533, | |
| "eval_steps_per_second": 2.444, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 188.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5445207357406616, | |
| "eval_runtime": 0.6378, | |
| "eval_samples_per_second": 109.754, | |
| "eval_steps_per_second": 3.136, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 189.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5444640517234802, | |
| "eval_runtime": 0.6708, | |
| "eval_samples_per_second": 104.36, | |
| "eval_steps_per_second": 2.982, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 190.0, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.608, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 190.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.544407069683075, | |
| "eval_runtime": 0.8392, | |
| "eval_samples_per_second": 83.416, | |
| "eval_steps_per_second": 2.383, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 191.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5443536043167114, | |
| "eval_runtime": 0.6405, | |
| "eval_samples_per_second": 109.293, | |
| "eval_steps_per_second": 3.123, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 192.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5443087816238403, | |
| "eval_runtime": 0.6431, | |
| "eval_samples_per_second": 108.85, | |
| "eval_steps_per_second": 3.11, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 193.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5442724823951721, | |
| "eval_runtime": 0.8311, | |
| "eval_samples_per_second": 84.221, | |
| "eval_steps_per_second": 2.406, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 194.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5442416667938232, | |
| "eval_runtime": 0.6416, | |
| "eval_samples_per_second": 109.095, | |
| "eval_steps_per_second": 3.117, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 195.0, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.6155, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 195.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5442100763320923, | |
| "eval_runtime": 0.6472, | |
| "eval_samples_per_second": 108.158, | |
| "eval_steps_per_second": 3.09, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 196.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5441816449165344, | |
| "eval_runtime": 0.8234, | |
| "eval_samples_per_second": 85.016, | |
| "eval_steps_per_second": 2.429, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 197.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5441582202911377, | |
| "eval_runtime": 0.6411, | |
| "eval_samples_per_second": 109.183, | |
| "eval_steps_per_second": 3.12, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 198.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5441429615020752, | |
| "eval_runtime": 0.6367, | |
| "eval_samples_per_second": 109.941, | |
| "eval_steps_per_second": 3.141, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 199.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5441319346427917, | |
| "eval_runtime": 0.8204, | |
| "eval_samples_per_second": 85.32, | |
| "eval_steps_per_second": 2.438, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.6272, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.5441268086433411, | |
| "eval_runtime": 0.646, | |
| "eval_samples_per_second": 108.365, | |
| "eval_steps_per_second": 3.096, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "step": 400, | |
| "total_flos": 2.23710151698432e+18, | |
| "train_loss": 0.6791047298908234, | |
| "train_runtime": 1022.1437, | |
| "train_samples_per_second": 88.05, | |
| "train_steps_per_second": 0.391 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 400, | |
| "num_train_epochs": 200, | |
| "save_steps": 500, | |
| "total_flos": 2.23710151698432e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |