| { |
| "best_metric": 0.896, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0877/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": 330.84521484375, |
| "learning_rate": 0.0001, |
| "loss": 2.8497, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7352, |
| "eval_loss": 1.0476884841918945, |
| "eval_runtime": 8.1786, |
| "eval_samples_per_second": 458.512, |
| "eval_steps_per_second": 7.214, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 64.40320587158203, |
| "learning_rate": 0.0001, |
| "loss": 0.723, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8544, |
| "eval_loss": 0.509489119052887, |
| "eval_runtime": 7.9279, |
| "eval_samples_per_second": 473.013, |
| "eval_steps_per_second": 7.442, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 55.60065841674805, |
| "learning_rate": 0.0001, |
| "loss": 0.4203, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8816, |
| "eval_loss": 0.41752779483795166, |
| "eval_runtime": 7.9002, |
| "eval_samples_per_second": 474.672, |
| "eval_steps_per_second": 7.468, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 45.879173278808594, |
| "learning_rate": 0.0001, |
| "loss": 0.2866, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.896, |
| "eval_loss": 0.3494924008846283, |
| "eval_runtime": 8.0324, |
| "eval_samples_per_second": 466.858, |
| "eval_steps_per_second": 7.345, |
| "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 |
| } |
|
|
