| { | |
| "best_metric": 0.8850666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0492/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": 119.4534912109375, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.6459, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7536, | |
| "eval_loss": 0.8758018612861633, | |
| "eval_runtime": 7.8449, | |
| "eval_samples_per_second": 478.02, | |
| "eval_steps_per_second": 7.521, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 65.36090087890625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.684, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8322666666666667, | |
| "eval_loss": 0.5424671173095703, | |
| "eval_runtime": 8.2472, | |
| "eval_samples_per_second": 454.698, | |
| "eval_steps_per_second": 7.154, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 102.93122863769531, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4559, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8581333333333333, | |
| "eval_loss": 0.43838372826576233, | |
| "eval_runtime": 7.743, | |
| "eval_samples_per_second": 484.31, | |
| "eval_steps_per_second": 7.62, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 65.11959838867188, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3559, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8850666666666667, | |
| "eval_loss": 0.3861728012561798, | |
| "eval_runtime": 8.3942, | |
| "eval_samples_per_second": 446.739, | |
| "eval_steps_per_second": 7.029, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1998, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |