| { | |
| "best_metric": 0.8765333333333334, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0786/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": 32.37533950805664, | |
| "learning_rate": 0.0005, | |
| "loss": 1.2436, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8341333333333333, | |
| "eval_loss": 0.5900858044624329, | |
| "eval_runtime": 15.3352, | |
| "eval_samples_per_second": 244.535, | |
| "eval_steps_per_second": 3.847, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 38.30799865722656, | |
| "learning_rate": 0.0005, | |
| "loss": 0.4204, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.86, | |
| "eval_loss": 0.48139849305152893, | |
| "eval_runtime": 15.3883, | |
| "eval_samples_per_second": 243.692, | |
| "eval_steps_per_second": 3.834, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 18.75383186340332, | |
| "learning_rate": 0.0005, | |
| "loss": 0.2723, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8749333333333333, | |
| "eval_loss": 0.4349713921546936, | |
| "eval_runtime": 15.2296, | |
| "eval_samples_per_second": 246.231, | |
| "eval_steps_per_second": 3.874, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 31.5809326171875, | |
| "learning_rate": 0.0005, | |
| "loss": 0.1981, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8765333333333334, | |
| "eval_loss": 0.48451271653175354, | |
| "eval_runtime": 15.334, | |
| "eval_samples_per_second": 244.555, | |
| "eval_steps_per_second": 3.848, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1665, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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 | |
| } | |