| { | |
| "best_metric": 0.10869565217391304, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-DMAE-15e\\checkpoint-3", | |
| "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": 7.923763275146484, | |
| "eval_runtime": 0.7392, | |
| "eval_samples_per_second": 62.232, | |
| "eval_steps_per_second": 4.059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.874618053436279, | |
| "eval_runtime": 0.7127, | |
| "eval_samples_per_second": 64.546, | |
| "eval_steps_per_second": 4.21, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.375e-05, | |
| "loss": 7.9273, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.818479537963867, | |
| "eval_runtime": 0.7227, | |
| "eval_samples_per_second": 63.653, | |
| "eval_steps_per_second": 4.151, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.699648857116699, | |
| "eval_runtime": 0.7342, | |
| "eval_samples_per_second": 62.655, | |
| "eval_steps_per_second": 4.086, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.587607383728027, | |
| "eval_runtime": 0.7147, | |
| "eval_samples_per_second": 64.365, | |
| "eval_steps_per_second": 4.198, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 1.25e-05, | |
| "loss": 7.6529, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.418882846832275, | |
| "eval_runtime": 0.7092, | |
| "eval_samples_per_second": 64.866, | |
| "eval_steps_per_second": 4.23, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.2678446769714355, | |
| "eval_runtime": 0.7064, | |
| "eval_samples_per_second": 65.116, | |
| "eval_steps_per_second": 4.247, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 7.0488600730896, | |
| "eval_runtime": 0.8282, | |
| "eval_samples_per_second": 55.543, | |
| "eval_steps_per_second": 3.622, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 1.125e-05, | |
| "loss": 7.1056, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 6.886016368865967, | |
| "eval_runtime": 0.7082, | |
| "eval_samples_per_second": 64.957, | |
| "eval_steps_per_second": 4.236, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 6.686739921569824, | |
| "eval_runtime": 0.7412, | |
| "eval_samples_per_second": 62.064, | |
| "eval_steps_per_second": 4.048, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 6.55491304397583, | |
| "eval_runtime": 0.7112, | |
| "eval_samples_per_second": 64.683, | |
| "eval_steps_per_second": 4.218, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 6.8482, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 6.365451335906982, | |
| "eval_runtime": 0.7332, | |
| "eval_samples_per_second": 62.742, | |
| "eval_steps_per_second": 4.092, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 6.215301990509033, | |
| "eval_runtime": 0.7252, | |
| "eval_samples_per_second": 63.433, | |
| "eval_steps_per_second": 4.137, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 6.0311198234558105, | |
| "eval_runtime": 0.7212, | |
| "eval_samples_per_second": 63.785, | |
| "eval_steps_per_second": 4.16, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 8.750000000000001e-06, | |
| "loss": 6.223, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.903781414031982, | |
| "eval_runtime": 0.7222, | |
| "eval_samples_per_second": 63.696, | |
| "eval_steps_per_second": 4.154, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.7399983406066895, | |
| "eval_runtime": 0.7477, | |
| "eval_samples_per_second": 61.524, | |
| "eval_steps_per_second": 4.012, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.627634525299072, | |
| "eval_runtime": 0.7197, | |
| "eval_samples_per_second": 63.918, | |
| "eval_steps_per_second": 4.169, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 7.5e-06, | |
| "loss": 5.8233, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.488417148590088, | |
| "eval_runtime": 0.7112, | |
| "eval_samples_per_second": 64.683, | |
| "eval_steps_per_second": 4.218, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.391030311584473, | |
| "eval_runtime": 0.7452, | |
| "eval_samples_per_second": 61.731, | |
| "eval_steps_per_second": 4.026, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.25e-06, | |
| "loss": 5.5432, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.2689528465271, | |
| "eval_runtime": 0.7257, | |
| "eval_samples_per_second": 63.39, | |
| "eval_steps_per_second": 4.134, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.182785511016846, | |
| "eval_runtime": 0.7282, | |
| "eval_samples_per_second": 63.173, | |
| "eval_steps_per_second": 4.12, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.076084136962891, | |
| "eval_runtime": 0.7192, | |
| "eval_samples_per_second": 63.963, | |
| "eval_steps_per_second": 4.172, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 5.2554, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 5.0026044845581055, | |
| "eval_runtime": 0.8007, | |
| "eval_samples_per_second": 57.45, | |
| "eval_steps_per_second": 3.747, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.913613796234131, | |
| "eval_runtime": 0.7312, | |
| "eval_samples_per_second": 62.913, | |
| "eval_steps_per_second": 4.103, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.852543830871582, | |
| "eval_runtime": 0.7112, | |
| "eval_samples_per_second": 64.683, | |
| "eval_steps_per_second": 4.218, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 3.75e-06, | |
| "loss": 5.0175, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.7791571617126465, | |
| "eval_runtime": 0.7142, | |
| "eval_samples_per_second": 64.411, | |
| "eval_steps_per_second": 4.201, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.730408191680908, | |
| "eval_runtime": 0.7222, | |
| "eval_samples_per_second": 63.698, | |
| "eval_steps_per_second": 4.154, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.673551559448242, | |
| "eval_runtime": 0.7282, | |
| "eval_samples_per_second": 63.173, | |
| "eval_steps_per_second": 4.12, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.4999999999999998e-06, | |
| "loss": 4.7765, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.637141227722168, | |
| "eval_runtime": 0.7492, | |
| "eval_samples_per_second": 61.401, | |
| "eval_steps_per_second": 4.004, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.596778392791748, | |
| "eval_runtime": 0.7372, | |
| "eval_samples_per_second": 62.401, | |
| "eval_steps_per_second": 4.07, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.572619915008545, | |
| "eval_runtime": 0.7372, | |
| "eval_samples_per_second": 62.401, | |
| "eval_steps_per_second": 4.07, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 1.2499999999999999e-06, | |
| "loss": 4.7339, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.548309326171875, | |
| "eval_runtime": 0.7537, | |
| "eval_samples_per_second": 61.034, | |
| "eval_steps_per_second": 3.98, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.536120414733887, | |
| "eval_runtime": 0.7227, | |
| "eval_samples_per_second": 63.652, | |
| "eval_steps_per_second": 4.151, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.528027057647705, | |
| "eval_runtime": 0.7282, | |
| "eval_samples_per_second": 63.172, | |
| "eval_steps_per_second": 4.12, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 4.6747, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 4.527446746826172, | |
| "eval_runtime": 0.7392, | |
| "eval_samples_per_second": 62.232, | |
| "eval_steps_per_second": 4.059, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.3770905934823424e+17, | |
| "train_loss": 5.965131664276123, | |
| "train_runtime": 192.4021, | |
| "train_samples_per_second": 44.282, | |
| "train_steps_per_second": 0.624 | |
| } | |
| ], | |
| "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 | |
| } | |