| { | |
| "best_metric": 0.8930666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0210/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": 206.05252075195312, | |
| "learning_rate": 7e-05, | |
| "loss": 3.2348, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6890666666666667, | |
| "eval_loss": 1.4580652713775635, | |
| "eval_runtime": 15.5784, | |
| "eval_samples_per_second": 240.717, | |
| "eval_steps_per_second": 3.787, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 138.36749267578125, | |
| "learning_rate": 7e-05, | |
| "loss": 0.874, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8442666666666667, | |
| "eval_loss": 0.5785519480705261, | |
| "eval_runtime": 15.6389, | |
| "eval_samples_per_second": 239.787, | |
| "eval_steps_per_second": 3.773, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 138.07675170898438, | |
| "learning_rate": 7e-05, | |
| "loss": 0.4979, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8794666666666666, | |
| "eval_loss": 0.40985533595085144, | |
| "eval_runtime": 15.497, | |
| "eval_samples_per_second": 241.982, | |
| "eval_steps_per_second": 3.807, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 94.4365234375, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3782, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8930666666666667, | |
| "eval_loss": 0.36750736832618713, | |
| "eval_runtime": 15.5023, | |
| "eval_samples_per_second": 241.9, | |
| "eval_steps_per_second": 3.806, | |
| "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 | |
| } | |