| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/fine_scale/resnet-50-2024_09_13-batch-size32_epochs150_freeze/checkpoint-273", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 3003, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.499453523472468, | |
| "eval_runtime": 431.8634, | |
| "eval_samples_per_second": 6.683, | |
| "eval_steps_per_second": 0.211, | |
| "learning_rate": 0.001, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.8315018315018317, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.001, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.000693000693000693, | |
| "eval_f1_macro": 0.00040576181781294376, | |
| "eval_f1_micro": 0.00031409501374165687, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.4992791043687002, | |
| "eval_runtime": 437.2143, | |
| "eval_samples_per_second": 6.601, | |
| "eval_steps_per_second": 0.208, | |
| "learning_rate": 0.001, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0017325017325017325, | |
| "eval_f1_macro": 0.0010049241282283187, | |
| "eval_f1_micro": 0.0007850525985241011, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.4993980575804369, | |
| "eval_runtime": 449.0005, | |
| "eval_samples_per_second": 6.428, | |
| "eval_steps_per_second": 0.203, | |
| "learning_rate": 0.001, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 3.663003663003663, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.001, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49914125117102115, | |
| "eval_runtime": 438.2382, | |
| "eval_samples_per_second": 6.585, | |
| "eval_steps_per_second": 0.208, | |
| "learning_rate": 0.001, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.0010395010395010396, | |
| "eval_f1_macro": 0.0006430178973314757, | |
| "eval_f1_micro": 0.00047177229124076113, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.4994358575523217, | |
| "eval_runtime": 457.0913, | |
| "eval_samples_per_second": 6.314, | |
| "eval_steps_per_second": 0.199, | |
| "learning_rate": 0.001, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.001, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.0003465003465003465, | |
| "eval_f1_macro": 0.000206782464846981, | |
| "eval_f1_micro": 0.00015712153350616704, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49927198166285536, | |
| "eval_runtime": 425.3309, | |
| "eval_samples_per_second": 6.785, | |
| "eval_steps_per_second": 0.214, | |
| "learning_rate": 0.001, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49929738732174456, | |
| "eval_runtime": 423.0556, | |
| "eval_samples_per_second": 6.822, | |
| "eval_steps_per_second": 0.215, | |
| "learning_rate": 0.0001, | |
| "step": 1911 | |
| }, | |
| { | |
| "epoch": 7.326007326007326, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.0003465003465003465, | |
| "eval_f1_macro": 0.0002061218179944347, | |
| "eval_f1_micro": 0.00015710919088766695, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49926547598990856, | |
| "eval_runtime": 417.1408, | |
| "eval_samples_per_second": 6.919, | |
| "eval_steps_per_second": 0.218, | |
| "learning_rate": 0.0001, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49944051212657437, | |
| "eval_runtime": 408.1598, | |
| "eval_samples_per_second": 7.071, | |
| "eval_steps_per_second": 0.223, | |
| "learning_rate": 0.0001, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 9.157509157509157, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.000693000693000693, | |
| "eval_f1_macro": 0.0004230565838180856, | |
| "eval_f1_micro": 0.00031441597233139445, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49936367811700877, | |
| "eval_runtime": 430.9669, | |
| "eval_samples_per_second": 6.697, | |
| "eval_steps_per_second": 0.211, | |
| "learning_rate": 0.0001, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.0, | |
| "eval_f1_macro": 0.0, | |
| "eval_f1_micro": 0.0, | |
| "eval_loss": NaN, | |
| "eval_roc_auc": 0.49943400645362757, | |
| "eval_runtime": 416.2683, | |
| "eval_samples_per_second": 6.933, | |
| "eval_steps_per_second": 0.219, | |
| "learning_rate": 0.0001, | |
| "step": 3003 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 0.0001, | |
| "step": 3003, | |
| "total_flos": 1.09151596234231e+19, | |
| "train_loss": 0.0, | |
| "train_runtime": 18978.5009, | |
| "train_samples_per_second": 68.888, | |
| "train_steps_per_second": 2.158 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 40950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 150, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.09151596234231e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |