| { | |
| "best_metric": 0.7833333333333333, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-dmae-va-U5-42B\\checkpoint-155", | |
| "epoch": 26.967741935483872, | |
| "eval_steps": 500, | |
| "global_step": 209, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.45, | |
| "eval_loss": 1.3843282461166382, | |
| "eval_runtime": 0.8985, | |
| "eval_samples_per_second": 66.778, | |
| "eval_steps_per_second": 2.226, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.3855, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.45, | |
| "eval_loss": 1.3692599534988403, | |
| "eval_runtime": 0.8682, | |
| "eval_samples_per_second": 69.109, | |
| "eval_steps_per_second": 2.304, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.45, | |
| "eval_loss": 1.3112239837646484, | |
| "eval_runtime": 0.8507, | |
| "eval_samples_per_second": 70.53, | |
| "eval_steps_per_second": 2.351, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.3665, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.182310938835144, | |
| "eval_runtime": 0.8795, | |
| "eval_samples_per_second": 68.219, | |
| "eval_steps_per_second": 2.274, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 3.909090909090909e-05, | |
| "loss": 1.2656, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_accuracy": 0.5166666666666667, | |
| "eval_loss": 1.0430983304977417, | |
| "eval_runtime": 0.8504, | |
| "eval_samples_per_second": 70.556, | |
| "eval_steps_per_second": 2.352, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.9782969951629639, | |
| "eval_runtime": 0.8875, | |
| "eval_samples_per_second": 67.607, | |
| "eval_steps_per_second": 2.254, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 3.7272727272727276e-05, | |
| "loss": 1.1097, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 0.9232853651046753, | |
| "eval_runtime": 0.9233, | |
| "eval_samples_per_second": 64.981, | |
| "eval_steps_per_second": 2.166, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 3.545454545454546e-05, | |
| "loss": 0.9542, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 0.8490957617759705, | |
| "eval_runtime": 0.9001, | |
| "eval_samples_per_second": 66.661, | |
| "eval_steps_per_second": 2.222, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.8462814092636108, | |
| "eval_runtime": 0.8868, | |
| "eval_samples_per_second": 67.657, | |
| "eval_steps_per_second": 2.255, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 3.363636363636364e-05, | |
| "loss": 0.8565, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.8351749777793884, | |
| "eval_runtime": 1.1225, | |
| "eval_samples_per_second": 53.451, | |
| "eval_steps_per_second": 1.782, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.7473, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 0.8304904699325562, | |
| "eval_runtime": 1.0952, | |
| "eval_samples_per_second": 54.782, | |
| "eval_steps_per_second": 1.826, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.65, | |
| "eval_loss": 0.7703030109405518, | |
| "eval_runtime": 0.9077, | |
| "eval_samples_per_second": 66.103, | |
| "eval_steps_per_second": 2.203, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 3.0000000000000004e-05, | |
| "loss": 0.6981, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 0.8429493308067322, | |
| "eval_runtime": 0.9329, | |
| "eval_samples_per_second": 64.316, | |
| "eval_steps_per_second": 2.144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 2.8181818181818185e-05, | |
| "loss": 0.5937, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.7051786780357361, | |
| "eval_runtime": 0.9214, | |
| "eval_samples_per_second": 65.121, | |
| "eval_steps_per_second": 2.171, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "eval_accuracy": 0.6833333333333333, | |
| "eval_loss": 0.6948642134666443, | |
| "eval_runtime": 0.9648, | |
| "eval_samples_per_second": 62.189, | |
| "eval_steps_per_second": 2.073, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 2.6363636363636365e-05, | |
| "loss": 0.549, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.740279495716095, | |
| "eval_runtime": 0.9273, | |
| "eval_samples_per_second": 64.707, | |
| "eval_steps_per_second": 2.157, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6784736514091492, | |
| "eval_runtime": 0.9242, | |
| "eval_samples_per_second": 64.921, | |
| "eval_steps_per_second": 2.164, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 2.454545454545455e-05, | |
| "loss": 0.4983, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6915722489356995, | |
| "eval_runtime": 0.941, | |
| "eval_samples_per_second": 63.762, | |
| "eval_steps_per_second": 2.125, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 18.58, | |
| "learning_rate": 2.2727272727272733e-05, | |
| "loss": 0.4534, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6501169800758362, | |
| "eval_runtime": 0.8838, | |
| "eval_samples_per_second": 67.889, | |
| "eval_steps_per_second": 2.263, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7833333333333333, | |
| "eval_loss": 0.6499305963516235, | |
| "eval_runtime": 1.2045, | |
| "eval_samples_per_second": 49.812, | |
| "eval_steps_per_second": 1.66, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 20.13, | |
| "learning_rate": 2.090909090909091e-05, | |
| "loss": 0.4209, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.8589470386505127, | |
| "eval_runtime": 0.995, | |
| "eval_samples_per_second": 60.3, | |
| "eval_steps_per_second": 2.01, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 21.68, | |
| "learning_rate": 1.9090909090909094e-05, | |
| "loss": 0.4248, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.6511362791061401, | |
| "eval_runtime": 0.9148, | |
| "eval_samples_per_second": 65.586, | |
| "eval_steps_per_second": 2.186, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 0.7100386023521423, | |
| "eval_runtime": 1.135, | |
| "eval_samples_per_second": 52.865, | |
| "eval_steps_per_second": 1.762, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 1.7272727272727274e-05, | |
| "loss": 0.3901, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6456588506698608, | |
| "eval_runtime": 0.9592, | |
| "eval_samples_per_second": 62.554, | |
| "eval_steps_per_second": 2.085, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 24.77, | |
| "learning_rate": 1.5454545454545454e-05, | |
| "loss": 0.3477, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6582431197166443, | |
| "eval_runtime": 0.8667, | |
| "eval_samples_per_second": 69.227, | |
| "eval_steps_per_second": 2.308, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6813774704933167, | |
| "eval_runtime": 1.0831, | |
| "eval_samples_per_second": 55.399, | |
| "eval_steps_per_second": 1.847, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 0.3236, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 26.97, | |
| "eval_accuracy": 0.7166666666666667, | |
| "eval_loss": 0.712448239326477, | |
| "eval_runtime": 0.9632, | |
| "eval_samples_per_second": 62.295, | |
| "eval_steps_per_second": 2.077, | |
| "step": 209 | |
| } | |
| ], | |
| "logging_steps": 12, | |
| "max_steps": 294, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 42, | |
| "save_steps": 500, | |
| "total_flos": 8.556354835395379e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |