| { |
| "best_metric": 0.8922666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0405/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": 51.4105110168457, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 1.6199, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8136, |
| "eval_loss": 0.6037173271179199, |
| "eval_runtime": 7.6645, |
| "eval_samples_per_second": 489.269, |
| "eval_steps_per_second": 7.698, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 89.4127197265625, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.4838, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8461333333333333, |
| "eval_loss": 0.4707730710506439, |
| "eval_runtime": 7.5691, |
| "eval_samples_per_second": 495.435, |
| "eval_steps_per_second": 7.795, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 77.28679656982422, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.3106, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8744, |
| "eval_loss": 0.411425918340683, |
| "eval_runtime": 8.2384, |
| "eval_samples_per_second": 455.184, |
| "eval_steps_per_second": 7.162, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 72.23634338378906, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.1999, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8834666666666666, |
| "eval_loss": 0.3835867941379547, |
| "eval_runtime": 7.521, |
| "eval_samples_per_second": 498.606, |
| "eval_steps_per_second": 7.845, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 41.718360900878906, |
| "learning_rate": 0.0, |
| "loss": 0.1362, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8922666666666667, |
| "eval_loss": 0.3786093294620514, |
| "eval_runtime": 7.5897, |
| "eval_samples_per_second": 494.089, |
| "eval_steps_per_second": 7.774, |
| "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 |
| } |
|
|
