| { | |
| "best_metric": 0.8260869565217391, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-ve-U11-b-40\\checkpoint-195", | |
| "epoch": 36.92307692307692, | |
| "eval_steps": 500, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.5799462795257568, | |
| "eval_runtime": 0.5821, | |
| "eval_samples_per_second": 79.027, | |
| "eval_steps_per_second": 3.436, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 2.1773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.5648330450057983, | |
| "eval_runtime": 0.6134, | |
| "eval_samples_per_second": 74.998, | |
| "eval_steps_per_second": 3.261, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.5181727409362793, | |
| "eval_runtime": 0.6128, | |
| "eval_samples_per_second": 75.067, | |
| "eval_steps_per_second": 3.264, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.1773, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.423189401626587, | |
| "eval_runtime": 0.6036, | |
| "eval_samples_per_second": 76.205, | |
| "eval_steps_per_second": 3.313, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.8993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.391304347826087, | |
| "eval_loss": 1.350540280342102, | |
| "eval_runtime": 0.5704, | |
| "eval_samples_per_second": 80.642, | |
| "eval_steps_per_second": 3.506, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2747217416763306, | |
| "eval_runtime": 0.6013, | |
| "eval_samples_per_second": 76.504, | |
| "eval_steps_per_second": 3.326, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.5045, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2452056407928467, | |
| "eval_runtime": 0.6025, | |
| "eval_samples_per_second": 76.343, | |
| "eval_steps_per_second": 3.319, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 1.2431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.1981565952301025, | |
| "eval_runtime": 0.6075, | |
| "eval_samples_per_second": 75.724, | |
| "eval_steps_per_second": 3.292, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.211159110069275, | |
| "eval_runtime": 0.5789, | |
| "eval_samples_per_second": 79.463, | |
| "eval_steps_per_second": 3.455, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.1225, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0159635543823242, | |
| "eval_runtime": 0.5933, | |
| "eval_samples_per_second": 77.528, | |
| "eval_steps_per_second": 3.371, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.9942, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.0138229131698608, | |
| "eval_runtime": 0.5808, | |
| "eval_samples_per_second": 79.195, | |
| "eval_steps_per_second": 3.443, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 0.9093583822250366, | |
| "eval_runtime": 0.5854, | |
| "eval_samples_per_second": 78.579, | |
| "eval_steps_per_second": 3.416, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.9212, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 0.8859941959381104, | |
| "eval_runtime": 0.6003, | |
| "eval_samples_per_second": 76.627, | |
| "eval_steps_per_second": 3.332, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.816, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.76930171251297, | |
| "eval_runtime": 0.5807, | |
| "eval_samples_per_second": 79.208, | |
| "eval_steps_per_second": 3.444, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.8289525508880615, | |
| "eval_runtime": 0.6004, | |
| "eval_samples_per_second": 76.619, | |
| "eval_steps_per_second": 3.331, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.741, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.7809844017028809, | |
| "eval_runtime": 0.5868, | |
| "eval_samples_per_second": 78.396, | |
| "eval_steps_per_second": 3.409, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.631, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6341724991798401, | |
| "eval_runtime": 0.6046, | |
| "eval_samples_per_second": 76.081, | |
| "eval_steps_per_second": 3.308, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7676540613174438, | |
| "eval_runtime": 0.5863, | |
| "eval_samples_per_second": 78.453, | |
| "eval_steps_per_second": 3.411, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6402, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6283207535743713, | |
| "eval_runtime": 0.5721, | |
| "eval_samples_per_second": 80.402, | |
| "eval_steps_per_second": 3.496, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.5477, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.6686931848526001, | |
| "eval_runtime": 0.6092, | |
| "eval_samples_per_second": 75.512, | |
| "eval_steps_per_second": 3.283, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6369442939758301, | |
| "eval_runtime": 0.6232, | |
| "eval_samples_per_second": 73.807, | |
| "eval_steps_per_second": 3.209, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.5023, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6333862543106079, | |
| "eval_runtime": 0.5864, | |
| "eval_samples_per_second": 78.448, | |
| "eval_steps_per_second": 3.411, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6355035305023193, | |
| "eval_runtime": 0.592, | |
| "eval_samples_per_second": 77.698, | |
| "eval_steps_per_second": 3.378, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.4802, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.5975824594497681, | |
| "eval_runtime": 0.5851, | |
| "eval_samples_per_second": 78.623, | |
| "eval_steps_per_second": 3.418, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.4336, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6111952066421509, | |
| "eval_runtime": 0.5995, | |
| "eval_samples_per_second": 76.726, | |
| "eval_steps_per_second": 3.336, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6147894859313965, | |
| "eval_runtime": 0.5855, | |
| "eval_samples_per_second": 78.56, | |
| "eval_steps_per_second": 3.416, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.4203, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.637995719909668, | |
| "eval_runtime": 0.6015, | |
| "eval_samples_per_second": 76.478, | |
| "eval_steps_per_second": 3.325, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.429, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6031981706619263, | |
| "eval_runtime": 0.5868, | |
| "eval_samples_per_second": 78.388, | |
| "eval_steps_per_second": 3.408, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6347993612289429, | |
| "eval_runtime": 0.5954, | |
| "eval_samples_per_second": 77.256, | |
| "eval_steps_per_second": 3.359, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.4013, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6120511293411255, | |
| "eval_runtime": 0.5862, | |
| "eval_samples_per_second": 78.467, | |
| "eval_steps_per_second": 3.412, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.3747, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6520815491676331, | |
| "eval_runtime": 0.584, | |
| "eval_samples_per_second": 78.773, | |
| "eval_steps_per_second": 3.425, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.642352283000946, | |
| "eval_runtime": 0.5991, | |
| "eval_samples_per_second": 76.785, | |
| "eval_steps_per_second": 3.338, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3668, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6149412989616394, | |
| "eval_runtime": 0.5861, | |
| "eval_samples_per_second": 78.481, | |
| "eval_steps_per_second": 3.412, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.3287, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6426060795783997, | |
| "eval_runtime": 0.586, | |
| "eval_samples_per_second": 78.496, | |
| "eval_steps_per_second": 3.413, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6378837823867798, | |
| "eval_runtime": 0.6002, | |
| "eval_samples_per_second": 76.643, | |
| "eval_steps_per_second": 3.332, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.372, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6434963941574097, | |
| "eval_runtime": 0.6209, | |
| "eval_samples_per_second": 74.08, | |
| "eval_steps_per_second": 3.221, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 0.0, | |
| "loss": 0.3236, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6449573636054993, | |
| "eval_runtime": 0.5774, | |
| "eval_samples_per_second": 79.664, | |
| "eval_steps_per_second": 3.464, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "step": 240, | |
| "total_flos": 7.519854010178765e+17, | |
| "train_loss": 0.8269948333501815, | |
| "train_runtime": 291.9837, | |
| "train_samples_per_second": 112.198, | |
| "train_steps_per_second": 0.822 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 7.519854010178765e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |