| { | |
| "best_metric": 0.8456, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0227/checkpoints/checkpoint-666", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 666, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 30.032756805419922, | |
| "learning_rate": 0.0005, | |
| "loss": 1.4638, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8026666666666666, | |
| "eval_loss": 0.6609347462654114, | |
| "eval_runtime": 5.3783, | |
| "eval_samples_per_second": 697.249, | |
| "eval_steps_per_second": 10.97, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 26.29765510559082, | |
| "learning_rate": 0.0005, | |
| "loss": 0.5469, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8456, | |
| "eval_loss": 0.5194752812385559, | |
| "eval_runtime": 5.413, | |
| "eval_samples_per_second": 692.774, | |
| "eval_steps_per_second": 10.9, | |
| "step": 666 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 999, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6352858479104e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |