| { |
| "best_metric": 0.88, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0221/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": 72.95460510253906, |
| "learning_rate": 0.0003, |
| "loss": 1.5822, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8112, |
| "eval_loss": 0.6189942955970764, |
| "eval_runtime": 7.9836, |
| "eval_samples_per_second": 469.713, |
| "eval_steps_per_second": 7.39, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 53.085304260253906, |
| "learning_rate": 0.0003, |
| "loss": 0.4636, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8610666666666666, |
| "eval_loss": 0.4616861045360565, |
| "eval_runtime": 7.6551, |
| "eval_samples_per_second": 489.869, |
| "eval_steps_per_second": 7.707, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 92.92632293701172, |
| "learning_rate": 0.0003, |
| "loss": 0.3048, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8672, |
| "eval_loss": 0.4460427165031433, |
| "eval_runtime": 7.8135, |
| "eval_samples_per_second": 479.938, |
| "eval_steps_per_second": 7.551, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 61.92770767211914, |
| "learning_rate": 0.0003, |
| "loss": 0.2134, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.88, |
| "eval_loss": 0.41429445147514343, |
| "eval_runtime": 8.6503, |
| "eval_samples_per_second": 433.511, |
| "eval_steps_per_second": 6.821, |
| "step": 1332 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2331, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "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 |
| } |
|
|
