| { |
| "best_metric": 0.8589333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0747/checkpoints/checkpoint-999", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 999, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 77.9583969116211, |
| "learning_rate": 7.681980515339464e-05, |
| "loss": 2.8806, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7328, |
| "eval_loss": 1.0771111249923706, |
| "eval_runtime": 14.1596, |
| "eval_samples_per_second": 264.839, |
| "eval_steps_per_second": 4.167, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 68.54283142089844, |
| "learning_rate": 4.5e-05, |
| "loss": 0.7643, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8394666666666667, |
| "eval_loss": 0.5558658838272095, |
| "eval_runtime": 13.3566, |
| "eval_samples_per_second": 280.76, |
| "eval_steps_per_second": 4.417, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 159.14202880859375, |
| "learning_rate": 1.3180194846605365e-05, |
| "loss": 0.4698, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8589333333333333, |
| "eval_loss": 0.48742759227752686, |
| "eval_runtime": 13.3733, |
| "eval_samples_per_second": 280.41, |
| "eval_steps_per_second": 4.412, |
| "step": 999 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
