| { | |
| "best_metric": 0.8296, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0547/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": 88.69751739501953, | |
| "learning_rate": 0.00015, | |
| "loss": 1.7444, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7896, | |
| "eval_loss": 0.6685646772384644, | |
| "eval_runtime": 13.762, | |
| "eval_samples_per_second": 272.489, | |
| "eval_steps_per_second": 4.287, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 74.84727478027344, | |
| "learning_rate": 0.0, | |
| "loss": 0.548, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8296, | |
| "eval_loss": 0.5505244731903076, | |
| "eval_runtime": 13.3172, | |
| "eval_samples_per_second": 281.591, | |
| "eval_steps_per_second": 4.43, | |
| "step": 666 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 666, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.6352858479104e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |