| { | |
| "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": 7.501729488372803, | |
| "eval_runtime": 0.7613, | |
| "eval_samples_per_second": 60.421, | |
| "eval_steps_per_second": 3.941, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.6895416975021362, | |
| "eval_runtime": 0.7697, | |
| "eval_samples_per_second": 59.762, | |
| "eval_steps_per_second": 3.898, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0016666666666666668, | |
| "loss": 4.88, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.138199329376221, | |
| "eval_runtime": 0.7697, | |
| "eval_samples_per_second": 59.76, | |
| "eval_steps_per_second": 3.897, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.5189474821090698, | |
| "eval_runtime": 0.7775, | |
| "eval_samples_per_second": 59.16, | |
| "eval_steps_per_second": 3.858, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.4063533544540405, | |
| "eval_runtime": 0.8154, | |
| "eval_samples_per_second": 56.416, | |
| "eval_steps_per_second": 3.679, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.001851851851851852, | |
| "loss": 1.7482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.3558485507965088, | |
| "eval_runtime": 0.8427, | |
| "eval_samples_per_second": 54.584, | |
| "eval_steps_per_second": 3.56, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.3179720640182495, | |
| "eval_runtime": 0.8639, | |
| "eval_samples_per_second": 53.247, | |
| "eval_steps_per_second": 3.473, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2377893924713135, | |
| "eval_runtime": 0.7959, | |
| "eval_samples_per_second": 57.795, | |
| "eval_steps_per_second": 3.769, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.0016666666666666668, | |
| "loss": 1.3281, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.338990569114685, | |
| "eval_runtime": 0.9078, | |
| "eval_samples_per_second": 50.675, | |
| "eval_steps_per_second": 3.305, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2144430875778198, | |
| "eval_runtime": 1.1213, | |
| "eval_samples_per_second": 41.024, | |
| "eval_steps_per_second": 2.675, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2492074966430664, | |
| "eval_runtime": 0.8022, | |
| "eval_samples_per_second": 57.343, | |
| "eval_steps_per_second": 3.74, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.0014814814814814814, | |
| "loss": 1.2367, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2685078382492065, | |
| "eval_runtime": 0.7767, | |
| "eval_samples_per_second": 59.225, | |
| "eval_steps_per_second": 3.862, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.239018440246582, | |
| "eval_runtime": 0.8102, | |
| "eval_samples_per_second": 56.778, | |
| "eval_steps_per_second": 3.703, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.2648324966430664, | |
| "eval_runtime": 0.7642, | |
| "eval_samples_per_second": 60.192, | |
| "eval_steps_per_second": 3.926, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.0012962962962962963, | |
| "loss": 1.2707, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2209372520446777, | |
| "eval_runtime": 1.1243, | |
| "eval_samples_per_second": 40.916, | |
| "eval_steps_per_second": 2.668, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2627573013305664, | |
| "eval_runtime": 0.7265, | |
| "eval_samples_per_second": 63.313, | |
| "eval_steps_per_second": 4.129, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2172560691833496, | |
| "eval_runtime": 0.7692, | |
| "eval_samples_per_second": 59.804, | |
| "eval_steps_per_second": 3.9, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.0011111111111111111, | |
| "loss": 1.2699, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2144685983657837, | |
| "eval_runtime": 0.7427, | |
| "eval_samples_per_second": 61.937, | |
| "eval_steps_per_second": 4.039, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.43478260869565216, | |
| "eval_loss": 1.233435869216919, | |
| "eval_runtime": 0.8122, | |
| "eval_samples_per_second": 56.636, | |
| "eval_steps_per_second": 3.694, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.000925925925925926, | |
| "loss": 1.2509, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2693239450454712, | |
| "eval_runtime": 0.7922, | |
| "eval_samples_per_second": 58.066, | |
| "eval_steps_per_second": 3.787, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2040687799453735, | |
| "eval_runtime": 0.7802, | |
| "eval_samples_per_second": 58.961, | |
| "eval_steps_per_second": 3.845, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.230669379234314, | |
| "eval_runtime": 0.7355, | |
| "eval_samples_per_second": 62.546, | |
| "eval_steps_per_second": 4.079, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 0.0007407407407407407, | |
| "loss": 1.1936, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.21720552444458, | |
| "eval_runtime": 1.1738, | |
| "eval_samples_per_second": 39.19, | |
| "eval_steps_per_second": 2.556, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.210868000984192, | |
| "eval_runtime": 0.7282, | |
| "eval_samples_per_second": 63.171, | |
| "eval_steps_per_second": 4.12, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.205082893371582, | |
| "eval_runtime": 0.7492, | |
| "eval_samples_per_second": 61.4, | |
| "eval_steps_per_second": 4.004, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 0.0005555555555555556, | |
| "loss": 1.1629, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2083849906921387, | |
| "eval_runtime": 0.7267, | |
| "eval_samples_per_second": 63.298, | |
| "eval_steps_per_second": 4.128, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2217854261398315, | |
| "eval_runtime": 0.7642, | |
| "eval_samples_per_second": 60.195, | |
| "eval_steps_per_second": 3.926, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.229410171508789, | |
| "eval_runtime": 0.9487, | |
| "eval_samples_per_second": 48.486, | |
| "eval_steps_per_second": 3.162, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.00037037037037037035, | |
| "loss": 1.1606, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2059509754180908, | |
| "eval_runtime": 0.7608, | |
| "eval_samples_per_second": 60.46, | |
| "eval_steps_per_second": 3.943, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.41304347826086957, | |
| "eval_loss": 1.2063390016555786, | |
| "eval_runtime": 0.7622, | |
| "eval_samples_per_second": 60.353, | |
| "eval_steps_per_second": 3.936, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.41304347826086957, | |
| "eval_loss": 1.2118929624557495, | |
| "eval_runtime": 0.7777, | |
| "eval_samples_per_second": 59.146, | |
| "eval_steps_per_second": 3.857, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 0.00018518518518518518, | |
| "loss": 1.1525, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2072707414627075, | |
| "eval_runtime": 0.7829, | |
| "eval_samples_per_second": 58.755, | |
| "eval_steps_per_second": 3.832, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.1994774341583252, | |
| "eval_runtime": 0.9102, | |
| "eval_samples_per_second": 50.537, | |
| "eval_steps_per_second": 3.296, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.1953673362731934, | |
| "eval_runtime": 0.7781, | |
| "eval_samples_per_second": 59.118, | |
| "eval_steps_per_second": 3.856, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 1.1326, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.195010781288147, | |
| "eval_runtime": 0.7669, | |
| "eval_samples_per_second": 59.984, | |
| "eval_steps_per_second": 3.912, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.3770905934823424e+17, | |
| "train_loss": 1.5655512491861978, | |
| "train_runtime": 205.1989, | |
| "train_samples_per_second": 41.521, | |
| "train_steps_per_second": 0.585 | |
| } | |
| ], | |
| "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 | |
| } | |