| { | |
| "best_metric": 0.6808762581409118, | |
| "best_model_checkpoint": "Distilled-Melanoma-Classification-EfficientNet/checkpoint-63325", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 75990, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 1.8409, | |
| "step": 2533 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5792382080126307, | |
| "eval_loss": 1.383086085319519, | |
| "eval_runtime": 438.7758, | |
| "eval_samples_per_second": 11.548, | |
| "eval_steps_per_second": 1.445, | |
| "step": 2533 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 1.549, | |
| "step": 5066 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5859482928754687, | |
| "eval_loss": 1.3424272537231445, | |
| "eval_runtime": 452.7141, | |
| "eval_samples_per_second": 11.192, | |
| "eval_steps_per_second": 1.4, | |
| "step": 5066 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.45, | |
| "step": 7599 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6295638444839156, | |
| "eval_loss": 1.33952796459198, | |
| "eval_runtime": 461.2274, | |
| "eval_samples_per_second": 10.986, | |
| "eval_steps_per_second": 1.375, | |
| "step": 7599 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 1.3614, | |
| "step": 10132 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6277876455496348, | |
| "eval_loss": 1.282675862312317, | |
| "eval_runtime": 466.1134, | |
| "eval_samples_per_second": 10.871, | |
| "eval_steps_per_second": 1.36, | |
| "step": 10132 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2856, | |
| "step": 12665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6481152555752911, | |
| "eval_loss": 1.0961527824401855, | |
| "eval_runtime": 474.1304, | |
| "eval_samples_per_second": 10.687, | |
| "eval_steps_per_second": 1.337, | |
| "step": 12665 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2093, | |
| "step": 15198 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6502861653838563, | |
| "eval_loss": 1.1280168294906616, | |
| "eval_runtime": 453.7056, | |
| "eval_samples_per_second": 11.168, | |
| "eval_steps_per_second": 1.397, | |
| "step": 15198 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 1.1307, | |
| "step": 17731 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6599565818038287, | |
| "eval_loss": 1.045525312423706, | |
| "eval_runtime": 440.9718, | |
| "eval_samples_per_second": 11.491, | |
| "eval_steps_per_second": 1.438, | |
| "step": 17731 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 1.043, | |
| "step": 20264 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6623248470495362, | |
| "eval_loss": 1.115827202796936, | |
| "eval_runtime": 441.2314, | |
| "eval_samples_per_second": 11.484, | |
| "eval_steps_per_second": 1.437, | |
| "step": 20264 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.9456, | |
| "step": 22797 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6562068284981252, | |
| "eval_loss": 1.2251527309417725, | |
| "eval_runtime": 449.8822, | |
| "eval_samples_per_second": 11.263, | |
| "eval_steps_per_second": 1.409, | |
| "step": 22797 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8582, | |
| "step": 25330 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6573909611209788, | |
| "eval_loss": 1.1615424156188965, | |
| "eval_runtime": 447.1634, | |
| "eval_samples_per_second": 11.331, | |
| "eval_steps_per_second": 1.418, | |
| "step": 25330 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.7617, | |
| "step": 27863 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6637063351095323, | |
| "eval_loss": 1.1989778280258179, | |
| "eval_runtime": 453.7466, | |
| "eval_samples_per_second": 11.167, | |
| "eval_steps_per_second": 1.397, | |
| "step": 27863 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6806, | |
| "step": 30396 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.658180382869548, | |
| "eval_loss": 1.3517282009124756, | |
| "eval_runtime": 458.6814, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 1.382, | |
| "step": 30396 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.6083, | |
| "step": 32929 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6250246694296427, | |
| "eval_loss": 1.7902203798294067, | |
| "eval_runtime": 459.1268, | |
| "eval_samples_per_second": 11.036, | |
| "eval_steps_per_second": 1.381, | |
| "step": 32929 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.5496, | |
| "step": 35462 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6694296427866587, | |
| "eval_loss": 1.3157224655151367, | |
| "eval_runtime": 459.084, | |
| "eval_samples_per_second": 11.037, | |
| "eval_steps_per_second": 1.381, | |
| "step": 35462 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4897, | |
| "step": 37995 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6510755871324255, | |
| "eval_loss": 1.738616943359375, | |
| "eval_runtime": 460.8902, | |
| "eval_samples_per_second": 10.994, | |
| "eval_steps_per_second": 1.376, | |
| "step": 37995 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.4478, | |
| "step": 40528 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6560094730609828, | |
| "eval_loss": 1.4945268630981445, | |
| "eval_runtime": 459.5191, | |
| "eval_samples_per_second": 11.027, | |
| "eval_steps_per_second": 1.38, | |
| "step": 40528 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.4032, | |
| "step": 43061 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6692322873495165, | |
| "eval_loss": 1.2260057926177979, | |
| "eval_runtime": 465.3259, | |
| "eval_samples_per_second": 10.889, | |
| "eval_steps_per_second": 1.362, | |
| "step": 43061 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3728, | |
| "step": 45594 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6315373988553384, | |
| "eval_loss": 1.3818838596343994, | |
| "eval_runtime": 466.0275, | |
| "eval_samples_per_second": 10.873, | |
| "eval_steps_per_second": 1.36, | |
| "step": 45594 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.3323, | |
| "step": 48127 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6605486481152556, | |
| "eval_loss": 1.3816238641738892, | |
| "eval_runtime": 469.6622, | |
| "eval_samples_per_second": 10.789, | |
| "eval_steps_per_second": 1.35, | |
| "step": 48127 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.3101, | |
| "step": 50660 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6668640221038089, | |
| "eval_loss": 1.2838419675827026, | |
| "eval_runtime": 468.0234, | |
| "eval_samples_per_second": 10.826, | |
| "eval_steps_per_second": 1.355, | |
| "step": 50660 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2834, | |
| "step": 53193 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6779159265837774, | |
| "eval_loss": 1.144907832145691, | |
| "eval_runtime": 467.7943, | |
| "eval_samples_per_second": 10.832, | |
| "eval_steps_per_second": 1.355, | |
| "step": 53193 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.2604, | |
| "step": 55726 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6639036905466745, | |
| "eval_loss": 1.1774488687515259, | |
| "eval_runtime": 466.3084, | |
| "eval_samples_per_second": 10.866, | |
| "eval_steps_per_second": 1.36, | |
| "step": 55726 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.2408, | |
| "step": 58259 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.670219064535228, | |
| "eval_loss": 1.0753474235534668, | |
| "eval_runtime": 472.9792, | |
| "eval_samples_per_second": 10.713, | |
| "eval_steps_per_second": 1.34, | |
| "step": 58259 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2247, | |
| "step": 60792 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6692322873495165, | |
| "eval_loss": 1.1826834678649902, | |
| "eval_runtime": 459.776, | |
| "eval_samples_per_second": 11.021, | |
| "eval_steps_per_second": 1.379, | |
| "step": 60792 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.2106, | |
| "step": 63325 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.6808762581409118, | |
| "eval_loss": 1.1205148696899414, | |
| "eval_runtime": 531.3791, | |
| "eval_samples_per_second": 9.536, | |
| "eval_steps_per_second": 1.193, | |
| "step": 63325 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1954, | |
| "step": 65858 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6727846852180778, | |
| "eval_loss": 1.1761797666549683, | |
| "eval_runtime": 463.5443, | |
| "eval_samples_per_second": 10.931, | |
| "eval_steps_per_second": 1.368, | |
| "step": 65858 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 5e-06, | |
| "loss": 0.1846, | |
| "step": 68391 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.6800868363923426, | |
| "eval_loss": 1.0658093690872192, | |
| "eval_runtime": 460.4726, | |
| "eval_samples_per_second": 11.004, | |
| "eval_steps_per_second": 1.377, | |
| "step": 68391 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.1761, | |
| "step": 70924 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6714031971580817, | |
| "eval_loss": 1.2492362260818481, | |
| "eval_runtime": 459.0542, | |
| "eval_samples_per_second": 11.038, | |
| "eval_steps_per_second": 1.381, | |
| "step": 70924 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.1689, | |
| "step": 73457 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.6684428656009473, | |
| "eval_loss": 1.0898562669754028, | |
| "eval_runtime": 465.3023, | |
| "eval_samples_per_second": 10.89, | |
| "eval_steps_per_second": 1.363, | |
| "step": 73457 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.163, | |
| "step": 75990 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6759423722123544, | |
| "eval_loss": 1.1256953477859497, | |
| "eval_runtime": 459.4721, | |
| "eval_samples_per_second": 11.028, | |
| "eval_steps_per_second": 1.38, | |
| "step": 75990 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 75990, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 3.503372757110489e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |