| { | |
| "best_metric": 0.8152, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0249/checkpoints/checkpoint-1332", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1332, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 76.75713348388672, | |
| "learning_rate": 7.681980515339464e-05, | |
| "loss": 3.0884, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6448, | |
| "eval_loss": 1.442893385887146, | |
| "eval_runtime": 15.5242, | |
| "eval_samples_per_second": 241.559, | |
| "eval_steps_per_second": 3.801, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 300.1126403808594, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0052, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7674666666666666, | |
| "eval_loss": 0.7820600867271423, | |
| "eval_runtime": 15.3769, | |
| "eval_samples_per_second": 243.872, | |
| "eval_steps_per_second": 3.837, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 167.801513671875, | |
| "learning_rate": 1.3180194846605365e-05, | |
| "loss": 0.6876, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8093333333333333, | |
| "eval_loss": 0.6371462941169739, | |
| "eval_runtime": 15.4327, | |
| "eval_samples_per_second": 242.99, | |
| "eval_steps_per_second": 3.823, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 159.0595245361328, | |
| "learning_rate": 0.0, | |
| "loss": 0.6205, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8152, | |
| "eval_loss": 0.6107262969017029, | |
| "eval_runtime": 15.4321, | |
| "eval_samples_per_second": 243.0, | |
| "eval_steps_per_second": 3.823, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1332, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |