| { |
| "best_metric": 0.8634666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0423/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": 44.43929672241211, |
| "learning_rate": 0.0005, |
| "loss": 1.3647, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8064, |
| "eval_loss": 0.6258230209350586, |
| "eval_runtime": 8.8812, |
| "eval_samples_per_second": 422.242, |
| "eval_steps_per_second": 6.643, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 31.288841247558594, |
| "learning_rate": 0.0005, |
| "loss": 0.4867, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8394666666666667, |
| "eval_loss": 0.5400484204292297, |
| "eval_runtime": 8.855, |
| "eval_samples_per_second": 423.491, |
| "eval_steps_per_second": 6.663, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 24.87687873840332, |
| "learning_rate": 0.0005, |
| "loss": 0.3392, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8536, |
| "eval_loss": 0.49989989399909973, |
| "eval_runtime": 8.8563, |
| "eval_samples_per_second": 423.429, |
| "eval_steps_per_second": 6.662, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 20.625282287597656, |
| "learning_rate": 0.0005, |
| "loss": 0.2544, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8634666666666667, |
| "eval_loss": 0.46891841292381287, |
| "eval_runtime": 8.6221, |
| "eval_samples_per_second": 434.93, |
| "eval_steps_per_second": 6.843, |
| "step": 1332 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1998, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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 |
| } |
|
|
