| { |
| "best_metric": 0.8682666666666666, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0761/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": 50.911651611328125, |
| "learning_rate": 0.000225, |
| "loss": 1.7398, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8069333333333333, |
| "eval_loss": 0.6165790557861328, |
| "eval_runtime": 15.3828, |
| "eval_samples_per_second": 243.78, |
| "eval_steps_per_second": 3.835, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 25.80537223815918, |
| "learning_rate": 7.500000000000002e-05, |
| "loss": 0.499, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8573333333333333, |
| "eval_loss": 0.457011342048645, |
| "eval_runtime": 15.4255, |
| "eval_samples_per_second": 243.104, |
| "eval_steps_per_second": 3.825, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 90.46163177490234, |
| "learning_rate": 0.0, |
| "loss": 0.3142, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8682666666666666, |
| "eval_loss": 0.41550078988075256, |
| "eval_runtime": 15.516, |
| "eval_samples_per_second": 241.686, |
| "eval_steps_per_second": 3.803, |
| "step": 999 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 999, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
