| { |
| "best_metric": 0.8808, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0021/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": 122.36292266845703, |
| "learning_rate": 0.0001, |
| "loss": 2.7027, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7581333333333333, |
| "eval_loss": 0.8977652788162231, |
| "eval_runtime": 13.0202, |
| "eval_samples_per_second": 288.013, |
| "eval_steps_per_second": 4.531, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 65.87313079833984, |
| "learning_rate": 0.0001, |
| "loss": 0.6759, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8402666666666667, |
| "eval_loss": 0.5236380696296692, |
| "eval_runtime": 12.6348, |
| "eval_samples_per_second": 296.8, |
| "eval_steps_per_second": 4.67, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 75.8592300415039, |
| "learning_rate": 0.0001, |
| "loss": 0.3856, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.86, |
| "eval_loss": 0.466505229473114, |
| "eval_runtime": 12.5099, |
| "eval_samples_per_second": 299.763, |
| "eval_steps_per_second": 4.716, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 96.59623718261719, |
| "learning_rate": 0.0001, |
| "loss": 0.2448, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8808, |
| "eval_loss": 0.3982797861099243, |
| "eval_runtime": 13.1069, |
| "eval_samples_per_second": 286.109, |
| "eval_steps_per_second": 4.501, |
| "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 |
| } |
|
|
