| { |
| "best_metric": 0.8789333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0930/checkpoints/checkpoint-1665", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1665, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 101.11022186279297, |
| "learning_rate": 9e-05, |
| "loss": 2.8245, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7517333333333334, |
| "eval_loss": 0.9406514763832092, |
| "eval_runtime": 12.3494, |
| "eval_samples_per_second": 303.658, |
| "eval_steps_per_second": 4.778, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 63.170291900634766, |
| "learning_rate": 9e-05, |
| "loss": 0.6716, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8421333333333333, |
| "eval_loss": 0.5034469962120056, |
| "eval_runtime": 12.4374, |
| "eval_samples_per_second": 301.51, |
| "eval_steps_per_second": 4.744, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 51.57673645019531, |
| "learning_rate": 9e-05, |
| "loss": 0.3847, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8701333333333333, |
| "eval_loss": 0.41411691904067993, |
| "eval_runtime": 12.3987, |
| "eval_samples_per_second": 302.451, |
| "eval_steps_per_second": 4.759, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 100.77507781982422, |
| "learning_rate": 9e-05, |
| "loss": 0.2535, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8768, |
| "eval_loss": 0.4046610891819, |
| "eval_runtime": 12.308, |
| "eval_samples_per_second": 304.679, |
| "eval_steps_per_second": 4.794, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 51.58750915527344, |
| "learning_rate": 9e-05, |
| "loss": 0.1766, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8789333333333333, |
| "eval_loss": 0.3900980055332184, |
| "eval_runtime": 12.2189, |
| "eval_samples_per_second": 306.9, |
| "eval_steps_per_second": 4.829, |
| "step": 1665 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
