| { | |
| "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": 0.10869565217391304, | |
| "eval_loss": 3.488030195236206, | |
| "eval_runtime": 1.0513, | |
| "eval_samples_per_second": 43.757, | |
| "eval_steps_per_second": 2.854, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 2.8350560665130615, | |
| "eval_runtime": 0.7512, | |
| "eval_samples_per_second": 61.235, | |
| "eval_steps_per_second": 3.994, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.04166666666666667, | |
| "loss": 9.7554, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 3.851775884628296, | |
| "eval_runtime": 1.1058, | |
| "eval_samples_per_second": 41.6, | |
| "eval_steps_per_second": 2.713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 2.7397520542144775, | |
| "eval_runtime": 0.7536, | |
| "eval_samples_per_second": 61.039, | |
| "eval_steps_per_second": 3.981, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 4.487335681915283, | |
| "eval_runtime": 0.7686, | |
| "eval_samples_per_second": 59.851, | |
| "eval_steps_per_second": 3.903, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.0462962962962963, | |
| "loss": 3.9513, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 3.855928421020508, | |
| "eval_runtime": 0.7493, | |
| "eval_samples_per_second": 61.394, | |
| "eval_steps_per_second": 4.004, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 2.14131760597229, | |
| "eval_runtime": 0.7545, | |
| "eval_samples_per_second": 60.964, | |
| "eval_steps_per_second": 3.976, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.4669885635375977, | |
| "eval_runtime": 0.7599, | |
| "eval_samples_per_second": 60.535, | |
| "eval_steps_per_second": 3.948, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.04166666666666667, | |
| "loss": 2.7557, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.352333426475525, | |
| "eval_runtime": 0.7315, | |
| "eval_samples_per_second": 62.884, | |
| "eval_steps_per_second": 4.101, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.415340781211853, | |
| "eval_runtime": 0.7434, | |
| "eval_samples_per_second": 61.88, | |
| "eval_steps_per_second": 4.036, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.3797227144241333, | |
| "eval_runtime": 0.7782, | |
| "eval_samples_per_second": 59.107, | |
| "eval_steps_per_second": 3.855, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.037037037037037035, | |
| "loss": 1.6168, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.4730011224746704, | |
| "eval_runtime": 0.7535, | |
| "eval_samples_per_second": 61.049, | |
| "eval_steps_per_second": 3.981, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2619987726211548, | |
| "eval_runtime": 0.734, | |
| "eval_samples_per_second": 62.674, | |
| "eval_steps_per_second": 4.087, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2209850549697876, | |
| "eval_runtime": 0.7662, | |
| "eval_samples_per_second": 60.038, | |
| "eval_steps_per_second": 3.915, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.032407407407407406, | |
| "loss": 1.4447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2587504386901855, | |
| "eval_runtime": 0.7387, | |
| "eval_samples_per_second": 62.274, | |
| "eval_steps_per_second": 4.061, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2458689212799072, | |
| "eval_runtime": 0.7367, | |
| "eval_samples_per_second": 62.44, | |
| "eval_steps_per_second": 4.072, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2858344316482544, | |
| "eval_runtime": 0.7717, | |
| "eval_samples_per_second": 59.607, | |
| "eval_steps_per_second": 3.887, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.02777777777777778, | |
| "loss": 1.2597, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2520229816436768, | |
| "eval_runtime": 0.7474, | |
| "eval_samples_per_second": 61.55, | |
| "eval_steps_per_second": 4.014, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2308332920074463, | |
| "eval_runtime": 0.7704, | |
| "eval_samples_per_second": 59.708, | |
| "eval_steps_per_second": 3.894, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.02314814814814815, | |
| "loss": 1.2406, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.223983645439148, | |
| "eval_runtime": 1.0122, | |
| "eval_samples_per_second": 45.445, | |
| "eval_steps_per_second": 2.964, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2277472019195557, | |
| "eval_runtime": 0.7687, | |
| "eval_samples_per_second": 59.844, | |
| "eval_steps_per_second": 3.903, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.243747353553772, | |
| "eval_runtime": 0.7578, | |
| "eval_samples_per_second": 60.702, | |
| "eval_steps_per_second": 3.959, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 0.018518518518518517, | |
| "loss": 1.2506, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2311103343963623, | |
| "eval_runtime": 0.7393, | |
| "eval_samples_per_second": 62.222, | |
| "eval_steps_per_second": 4.058, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.210280179977417, | |
| "eval_runtime": 0.7435, | |
| "eval_samples_per_second": 61.873, | |
| "eval_steps_per_second": 4.035, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2071959972381592, | |
| "eval_runtime": 0.8851, | |
| "eval_samples_per_second": 51.974, | |
| "eval_steps_per_second": 3.39, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 0.01388888888888889, | |
| "loss": 1.2026, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.217361569404602, | |
| "eval_runtime": 0.8382, | |
| "eval_samples_per_second": 54.876, | |
| "eval_steps_per_second": 3.579, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2164480686187744, | |
| "eval_runtime": 0.7529, | |
| "eval_samples_per_second": 61.098, | |
| "eval_steps_per_second": 3.985, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.214943528175354, | |
| "eval_runtime": 0.7901, | |
| "eval_samples_per_second": 58.217, | |
| "eval_steps_per_second": 3.797, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.009259259259259259, | |
| "loss": 1.2, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.206203579902649, | |
| "eval_runtime": 0.7505, | |
| "eval_samples_per_second": 61.295, | |
| "eval_steps_per_second": 3.997, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2065629959106445, | |
| "eval_runtime": 0.7493, | |
| "eval_samples_per_second": 61.394, | |
| "eval_steps_per_second": 4.004, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.208692193031311, | |
| "eval_runtime": 0.7358, | |
| "eval_samples_per_second": 62.513, | |
| "eval_steps_per_second": 4.077, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 0.004629629629629629, | |
| "loss": 1.2065, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2076929807662964, | |
| "eval_runtime": 0.7508, | |
| "eval_samples_per_second": 61.264, | |
| "eval_steps_per_second": 3.995, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.206972599029541, | |
| "eval_runtime": 0.7519, | |
| "eval_samples_per_second": 61.176, | |
| "eval_steps_per_second": 3.99, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2067426443099976, | |
| "eval_runtime": 0.7542, | |
| "eval_samples_per_second": 60.994, | |
| "eval_steps_per_second": 3.978, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 1.1998, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2067285776138306, | |
| "eval_runtime": 0.8157, | |
| "eval_samples_per_second": 56.395, | |
| "eval_steps_per_second": 3.678, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.3770905934823424e+17, | |
| "train_loss": 2.340296713511149, | |
| "train_runtime": 200.1533, | |
| "train_samples_per_second": 42.567, | |
| "train_steps_per_second": 0.6 | |
| } | |
| ], | |
| "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 | |
| } | |