| { | |
| "best_metric": 0.45652173913043476, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-DMAE-ex\\checkpoint-7", | |
| "epoch": 34.285714285714285, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 45.53202438354492, | |
| "eval_runtime": 0.7612, | |
| "eval_samples_per_second": 60.431, | |
| "eval_steps_per_second": 3.941, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 11.398162841796875, | |
| "eval_runtime": 0.7452, | |
| "eval_samples_per_second": 61.727, | |
| "eval_steps_per_second": 4.026, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.09166666666666667, | |
| "loss": 37.3882, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 14.659239768981934, | |
| "eval_runtime": 0.7983, | |
| "eval_samples_per_second": 57.624, | |
| "eval_steps_per_second": 3.758, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 5.432069301605225, | |
| "eval_runtime": 0.8472, | |
| "eval_samples_per_second": 54.298, | |
| "eval_steps_per_second": 3.541, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 2.191324234008789, | |
| "eval_runtime": 0.7984, | |
| "eval_samples_per_second": 57.617, | |
| "eval_steps_per_second": 3.758, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.08333333333333334, | |
| "loss": 7.8109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.573766231536865, | |
| "eval_runtime": 0.8305, | |
| "eval_samples_per_second": 55.388, | |
| "eval_steps_per_second": 3.612, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 8.57021427154541, | |
| "eval_runtime": 0.7898, | |
| "eval_samples_per_second": 58.244, | |
| "eval_steps_per_second": 3.799, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.530113220214844, | |
| "eval_runtime": 0.7503, | |
| "eval_samples_per_second": 61.31, | |
| "eval_steps_per_second": 3.998, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.07500000000000001, | |
| "loss": 6.7711, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 2.6876065731048584, | |
| "eval_runtime": 0.8036, | |
| "eval_samples_per_second": 57.245, | |
| "eval_steps_per_second": 3.733, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.8742014169692993, | |
| "eval_runtime": 0.864, | |
| "eval_samples_per_second": 53.242, | |
| "eval_steps_per_second": 3.472, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.5266066789627075, | |
| "eval_runtime": 0.8225, | |
| "eval_samples_per_second": 55.927, | |
| "eval_steps_per_second": 3.647, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.06666666666666667, | |
| "loss": 1.7995, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.5311237573623657, | |
| "eval_runtime": 0.7469, | |
| "eval_samples_per_second": 61.585, | |
| "eval_steps_per_second": 4.016, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.4438916444778442, | |
| "eval_runtime": 0.8487, | |
| "eval_samples_per_second": 54.199, | |
| "eval_steps_per_second": 3.535, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2218061685562134, | |
| "eval_runtime": 0.7762, | |
| "eval_samples_per_second": 59.266, | |
| "eval_steps_per_second": 3.865, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.05833333333333334, | |
| "loss": 1.5366, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.322609305381775, | |
| "eval_runtime": 0.7716, | |
| "eval_samples_per_second": 59.618, | |
| "eval_steps_per_second": 3.888, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.6288353204727173, | |
| "eval_runtime": 0.8457, | |
| "eval_samples_per_second": 54.39, | |
| "eval_steps_per_second": 3.547, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.7525928020477295, | |
| "eval_runtime": 0.8164, | |
| "eval_samples_per_second": 56.343, | |
| "eval_steps_per_second": 3.675, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.05, | |
| "loss": 1.5748, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.369892954826355, | |
| "eval_runtime": 0.817, | |
| "eval_samples_per_second": 56.302, | |
| "eval_steps_per_second": 3.672, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2662850618362427, | |
| "eval_runtime": 0.7845, | |
| "eval_samples_per_second": 58.632, | |
| "eval_steps_per_second": 3.824, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.04166666666666667, | |
| "loss": 1.3933, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2221952676773071, | |
| "eval_runtime": 0.8295, | |
| "eval_samples_per_second": 55.453, | |
| "eval_steps_per_second": 3.617, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.238777756690979, | |
| "eval_runtime": 1.2232, | |
| "eval_samples_per_second": 37.606, | |
| "eval_steps_per_second": 2.453, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2831048965454102, | |
| "eval_runtime": 0.7467, | |
| "eval_samples_per_second": 61.605, | |
| "eval_steps_per_second": 4.018, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 0.03333333333333333, | |
| "loss": 1.2788, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2515243291854858, | |
| "eval_runtime": 0.768, | |
| "eval_samples_per_second": 59.895, | |
| "eval_steps_per_second": 3.906, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2105132341384888, | |
| "eval_runtime": 0.7735, | |
| "eval_samples_per_second": 59.469, | |
| "eval_steps_per_second": 3.878, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.214127779006958, | |
| "eval_runtime": 0.7825, | |
| "eval_samples_per_second": 58.787, | |
| "eval_steps_per_second": 3.834, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 0.025, | |
| "loss": 1.2218, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2214648723602295, | |
| "eval_runtime": 0.7783, | |
| "eval_samples_per_second": 59.1, | |
| "eval_steps_per_second": 3.854, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2189139127731323, | |
| "eval_runtime": 0.779, | |
| "eval_samples_per_second": 59.048, | |
| "eval_steps_per_second": 3.851, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.210168719291687, | |
| "eval_runtime": 0.7611, | |
| "eval_samples_per_second": 60.441, | |
| "eval_steps_per_second": 3.942, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.016666666666666666, | |
| "loss": 1.2039, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2094049453735352, | |
| "eval_runtime": 0.7482, | |
| "eval_samples_per_second": 61.482, | |
| "eval_steps_per_second": 4.01, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.206476092338562, | |
| "eval_runtime": 0.7612, | |
| "eval_samples_per_second": 60.431, | |
| "eval_steps_per_second": 3.941, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2124706506729126, | |
| "eval_runtime": 0.761, | |
| "eval_samples_per_second": 60.451, | |
| "eval_steps_per_second": 3.942, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 0.008333333333333333, | |
| "loss": 1.2131, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2106635570526123, | |
| "eval_runtime": 0.8627, | |
| "eval_samples_per_second": 53.321, | |
| "eval_steps_per_second": 3.477, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2078120708465576, | |
| "eval_runtime": 0.7667, | |
| "eval_samples_per_second": 59.998, | |
| "eval_steps_per_second": 3.913, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2067822217941284, | |
| "eval_runtime": 0.7636, | |
| "eval_samples_per_second": 60.24, | |
| "eval_steps_per_second": 3.929, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 1.211, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2067316770553589, | |
| "eval_runtime": 0.9703, | |
| "eval_samples_per_second": 47.408, | |
| "eval_steps_per_second": 3.092, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.3770905934823424e+17, | |
| "train_loss": 5.366930524508159, | |
| "train_runtime": 206.997, | |
| "train_samples_per_second": 41.16, | |
| "train_steps_per_second": 0.58 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 2.3770905934823424e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |