| { | |
| "best_metric": 0.6739130434782609, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RD-aptos19\\checkpoint-73", | |
| "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": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.8177, | |
| "eval_samples_per_second": 56.255, | |
| "eval_steps_per_second": 3.669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.86, | |
| "eval_samples_per_second": 53.49, | |
| "eval_steps_per_second": 3.488, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.000125, | |
| "loss": 1.417358234639283e+35, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7417, | |
| "eval_samples_per_second": 62.021, | |
| "eval_steps_per_second": 4.045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.9387, | |
| "eval_samples_per_second": 49.003, | |
| "eval_steps_per_second": 3.196, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7142, | |
| "eval_samples_per_second": 64.411, | |
| "eval_steps_per_second": 4.201, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 1.4838618788847814e+35, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7437, | |
| "eval_samples_per_second": 61.855, | |
| "eval_steps_per_second": 4.034, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7257, | |
| "eval_samples_per_second": 63.39, | |
| "eval_steps_per_second": 4.134, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.8812, | |
| "eval_samples_per_second": 52.201, | |
| "eval_steps_per_second": 3.404, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.000125, | |
| "loss": 1.666746464805008e+35, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7237, | |
| "eval_samples_per_second": 63.565, | |
| "eval_steps_per_second": 4.146, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7237, | |
| "eval_samples_per_second": 63.565, | |
| "eval_steps_per_second": 4.146, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7807, | |
| "eval_samples_per_second": 58.923, | |
| "eval_steps_per_second": 3.843, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.00011111111111111109, | |
| "loss": 1.2303167847164203e+35, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7182, | |
| "eval_samples_per_second": 64.053, | |
| "eval_steps_per_second": 4.177, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7442, | |
| "eval_samples_per_second": 61.814, | |
| "eval_steps_per_second": 4.031, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7632, | |
| "eval_samples_per_second": 60.275, | |
| "eval_steps_per_second": 3.931, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 9.722222222222222e-05, | |
| "loss": 1.6043994468776581e+35, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.8082, | |
| "eval_samples_per_second": 56.918, | |
| "eval_steps_per_second": 3.712, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7607, | |
| "eval_samples_per_second": 60.472, | |
| "eval_steps_per_second": 3.944, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.8022, | |
| "eval_samples_per_second": 57.343, | |
| "eval_steps_per_second": 3.74, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 1.5129574708301948e+35, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7327, | |
| "eval_samples_per_second": 62.784, | |
| "eval_steps_per_second": 4.095, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7832, | |
| "eval_samples_per_second": 58.734, | |
| "eval_steps_per_second": 3.83, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 1.4215145440447813e+35, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7967, | |
| "eval_samples_per_second": 57.739, | |
| "eval_steps_per_second": 3.766, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7772, | |
| "eval_samples_per_second": 59.189, | |
| "eval_steps_per_second": 3.86, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7242, | |
| "eval_samples_per_second": 63.522, | |
| "eval_steps_per_second": 4.143, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 5.5555555555555545e-05, | |
| "loss": 1.3716372466155514e+35, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7907, | |
| "eval_samples_per_second": 58.177, | |
| "eval_steps_per_second": 3.794, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7842, | |
| "eval_samples_per_second": 58.659, | |
| "eval_steps_per_second": 3.826, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7632, | |
| "eval_samples_per_second": 60.273, | |
| "eval_steps_per_second": 3.931, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 4.1666666666666665e-05, | |
| "loss": 1.3716369297029012e+35, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.8202, | |
| "eval_samples_per_second": 56.084, | |
| "eval_steps_per_second": 3.658, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7622, | |
| "eval_samples_per_second": 60.352, | |
| "eval_steps_per_second": 3.936, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7687, | |
| "eval_samples_per_second": 59.842, | |
| "eval_steps_per_second": 3.903, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.7777777777777772e-05, | |
| "loss": 1.554521832535778e+35, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7632, | |
| "eval_samples_per_second": 60.273, | |
| "eval_steps_per_second": 3.931, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.8737, | |
| "eval_samples_per_second": 52.649, | |
| "eval_steps_per_second": 3.434, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7987, | |
| "eval_samples_per_second": 57.595, | |
| "eval_steps_per_second": 3.756, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 1.3888888888888886e-05, | |
| "loss": 1.3965755784175162e+35, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7802, | |
| "eval_samples_per_second": 58.961, | |
| "eval_steps_per_second": 3.845, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7962, | |
| "eval_samples_per_second": 57.776, | |
| "eval_steps_per_second": 3.768, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7867, | |
| "eval_samples_per_second": 58.473, | |
| "eval_steps_per_second": 3.813, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 1.4173579177266329e+35, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.44573075075951e+35, | |
| "eval_runtime": 0.7957, | |
| "eval_samples_per_second": 57.812, | |
| "eval_steps_per_second": 3.77, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.3770905934823424e+17, | |
| "train_loss": 1.4540736941497088e+35, | |
| "train_runtime": 197.0327, | |
| "train_samples_per_second": 43.242, | |
| "train_steps_per_second": 0.609 | |
| } | |
| ], | |
| "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 | |
| } | |