| { | |
| "best_metric": 0.9590163934426229, | |
| "best_model_checkpoint": "./vit-LungCancerViT/checkpoint-350", | |
| "epoch": 20.0, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.3951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.9527, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.7463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7213114754098361, | |
| "eval_loss": 0.7026457190513611, | |
| "eval_runtime": 52.9268, | |
| "eval_samples_per_second": 2.305, | |
| "eval_steps_per_second": 0.302, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.5309, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.4553, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.3735, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2276, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8360655737704918, | |
| "eval_loss": 0.3694429099559784, | |
| "eval_runtime": 1.4376, | |
| "eval_samples_per_second": 84.864, | |
| "eval_steps_per_second": 11.13, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00019682539682539682, | |
| "loss": 0.321, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00019365079365079365, | |
| "loss": 0.1708, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00019047619047619048, | |
| "loss": 0.3134, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.860655737704918, | |
| "eval_loss": 0.3415001332759857, | |
| "eval_runtime": 1.2015, | |
| "eval_samples_per_second": 101.542, | |
| "eval_steps_per_second": 13.317, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.00018730158730158731, | |
| "loss": 0.1296, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 0.00018412698412698412, | |
| "loss": 0.1161, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.00018095238095238095, | |
| "loss": 0.0696, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.1487, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.860655737704918, | |
| "eval_loss": 0.4990597069263458, | |
| "eval_runtime": 1.1086, | |
| "eval_samples_per_second": 110.045, | |
| "eval_steps_per_second": 14.432, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00017460317460317462, | |
| "loss": 0.0783, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.1082, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00016825396825396826, | |
| "loss": 0.0301, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8934426229508197, | |
| "eval_loss": 0.2610397934913635, | |
| "eval_runtime": 1.1421, | |
| "eval_samples_per_second": 106.821, | |
| "eval_steps_per_second": 14.009, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 0.0001650793650793651, | |
| "loss": 0.0994, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00016190476190476192, | |
| "loss": 0.1404, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00015873015873015873, | |
| "loss": 0.0216, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 0.0567, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9098360655737705, | |
| "eval_loss": 0.2997801601886749, | |
| "eval_runtime": 1.3611, | |
| "eval_samples_per_second": 89.633, | |
| "eval_steps_per_second": 11.755, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.00015238095238095237, | |
| "loss": 0.0529, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.00014920634920634923, | |
| "loss": 0.0305, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 0.00014603174603174603, | |
| "loss": 0.0084, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9016393442622951, | |
| "eval_loss": 0.4632587730884552, | |
| "eval_runtime": 1.1837, | |
| "eval_samples_per_second": 103.068, | |
| "eval_steps_per_second": 13.517, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.0174, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 0.00013968253968253967, | |
| "loss": 0.0027, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 0.0001365079365079365, | |
| "loss": 0.0245, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0071, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9508196721311475, | |
| "eval_loss": 0.21911580860614777, | |
| "eval_runtime": 1.1253, | |
| "eval_samples_per_second": 108.412, | |
| "eval_steps_per_second": 14.218, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 0.00013015873015873017, | |
| "loss": 0.0169, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.00012698412698412698, | |
| "loss": 0.014, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 0.0001238095238095238, | |
| "loss": 0.0231, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9344262295081968, | |
| "eval_loss": 0.3097061216831207, | |
| "eval_runtime": 1.1316, | |
| "eval_samples_per_second": 107.81, | |
| "eval_steps_per_second": 14.139, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00012063492063492063, | |
| "loss": 0.0003, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 0.00011746031746031746, | |
| "loss": 0.0195, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.0062, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.0003, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.2627410292625427, | |
| "eval_runtime": 1.345, | |
| "eval_samples_per_second": 90.707, | |
| "eval_steps_per_second": 11.896, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 0.00010793650793650794, | |
| "loss": 0.0004, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 0.00010476190476190477, | |
| "loss": 0.003, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.00010158730158730159, | |
| "loss": 0.0002, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9508196721311475, | |
| "eval_loss": 0.284305602312088, | |
| "eval_runtime": 1.3379, | |
| "eval_samples_per_second": 91.19, | |
| "eval_steps_per_second": 11.959, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "learning_rate": 9.841269841269841e-05, | |
| "loss": 0.0051, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.0001, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 11.71, | |
| "learning_rate": 9.206349206349206e-05, | |
| "loss": 0.0016, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.005, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9508196721311475, | |
| "eval_loss": 0.28199827671051025, | |
| "eval_runtime": 1.1031, | |
| "eval_samples_per_second": 110.597, | |
| "eval_steps_per_second": 14.505, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.0001, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 8.253968253968255e-05, | |
| "loss": 0.0001, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.0054, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9508196721311475, | |
| "eval_loss": 0.2708677649497986, | |
| "eval_runtime": 1.117, | |
| "eval_samples_per_second": 109.217, | |
| "eval_steps_per_second": 14.324, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 7.619047619047618e-05, | |
| "loss": 0.0001, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 7.301587301587302e-05, | |
| "loss": 0.0001, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 6.984126984126984e-05, | |
| "loss": 0.0027, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0026, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9508196721311475, | |
| "eval_loss": 0.2664688229560852, | |
| "eval_runtime": 1.2394, | |
| "eval_samples_per_second": 98.438, | |
| "eval_steps_per_second": 12.91, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 6.349206349206349e-05, | |
| "loss": 0.0023, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 14.57, | |
| "learning_rate": 6.0317460317460316e-05, | |
| "loss": 0.0038, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.0001, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.2634933888912201, | |
| "eval_runtime": 1.3242, | |
| "eval_samples_per_second": 92.133, | |
| "eval_steps_per_second": 12.083, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 5.396825396825397e-05, | |
| "loss": 0.0023, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 5.0793650793650794e-05, | |
| "loss": 0.0028, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.0001, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0001, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.26172590255737305, | |
| "eval_runtime": 1.134, | |
| "eval_samples_per_second": 107.579, | |
| "eval_steps_per_second": 14.109, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.0025, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.0026, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 0.0001, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.26094985008239746, | |
| "eval_runtime": 1.1056, | |
| "eval_samples_per_second": 110.343, | |
| "eval_steps_per_second": 14.471, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.0001, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0025, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 0.0001, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0026, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.2608335614204407, | |
| "eval_runtime": 1.0804, | |
| "eval_samples_per_second": 112.918, | |
| "eval_steps_per_second": 14.809, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.0023, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.0001, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.0028, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.2601701617240906, | |
| "eval_runtime": 1.2677, | |
| "eval_samples_per_second": 96.24, | |
| "eval_steps_per_second": 12.622, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 19.14, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.0001, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.0026, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.0001, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0022, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9590163934426229, | |
| "eval_loss": 0.2600506544113159, | |
| "eval_runtime": 1.1031, | |
| "eval_samples_per_second": 110.597, | |
| "eval_steps_per_second": 14.504, | |
| "step": 700 | |
| } | |
| ], | |
| "max_steps": 700, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.6924553905235558e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |