| { |
| "best_metric": 0.9106666666666666, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0712/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": 67.0896987915039, |
| "learning_rate": 0.000375, |
| "loss": 1.2404, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8466666666666667, |
| "eval_loss": 0.5153259038925171, |
| "eval_runtime": 13.9957, |
| "eval_samples_per_second": 267.939, |
| "eval_steps_per_second": 4.216, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 35.93023681640625, |
| "learning_rate": 0.00025, |
| "loss": 0.38, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8888, |
| "eval_loss": 0.34226343035697937, |
| "eval_runtime": 13.5996, |
| "eval_samples_per_second": 275.744, |
| "eval_steps_per_second": 4.338, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 38.598506927490234, |
| "learning_rate": 0.000125, |
| "loss": 0.2004, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9096, |
| "eval_loss": 0.3084923028945923, |
| "eval_runtime": 13.5913, |
| "eval_samples_per_second": 275.911, |
| "eval_steps_per_second": 4.341, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 49.59001922607422, |
| "learning_rate": 0.0, |
| "loss": 0.1055, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9106666666666666, |
| "eval_loss": 0.2989835739135742, |
| "eval_runtime": 13.5458, |
| "eval_samples_per_second": 276.838, |
| "eval_steps_per_second": 4.356, |
| "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 |
| } |
|
|
