| { |
| "best_metric": 0.9096, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0600/checkpoints/checkpoint-2997", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 2997, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 28.45771026611328, |
| "learning_rate": 0.0004444444444444444, |
| "loss": 1.2107, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8608, |
| "eval_loss": 0.46688157320022583, |
| "eval_runtime": 7.6022, |
| "eval_samples_per_second": 493.278, |
| "eval_steps_per_second": 7.761, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 22.515621185302734, |
| "learning_rate": 0.0003888888888888889, |
| "loss": 0.3488, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8746666666666667, |
| "eval_loss": 0.4282216727733612, |
| "eval_runtime": 7.4484, |
| "eval_samples_per_second": 503.464, |
| "eval_steps_per_second": 7.921, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 26.487083435058594, |
| "learning_rate": 0.0003333333333333333, |
| "loss": 0.1802, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8858666666666667, |
| "eval_loss": 0.4211350381374359, |
| "eval_runtime": 7.5316, |
| "eval_samples_per_second": 497.903, |
| "eval_steps_per_second": 7.834, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 31.017868041992188, |
| "learning_rate": 0.0002777777777777778, |
| "loss": 0.1028, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8898666666666667, |
| "eval_loss": 0.4667320251464844, |
| "eval_runtime": 7.5704, |
| "eval_samples_per_second": 495.349, |
| "eval_steps_per_second": 7.793, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 20.456336975097656, |
| "learning_rate": 0.0002222222222222222, |
| "loss": 0.0557, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9002666666666667, |
| "eval_loss": 0.4441961646080017, |
| "eval_runtime": 7.667, |
| "eval_samples_per_second": 489.11, |
| "eval_steps_per_second": 7.695, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 23.944442749023438, |
| "learning_rate": 0.00016666666666666666, |
| "loss": 0.0302, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9026666666666666, |
| "eval_loss": 0.45439833402633667, |
| "eval_runtime": 7.6437, |
| "eval_samples_per_second": 490.6, |
| "eval_steps_per_second": 7.719, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 26.694232940673828, |
| "learning_rate": 0.0001111111111111111, |
| "loss": 0.0182, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9029333333333334, |
| "eval_loss": 0.4346791207790375, |
| "eval_runtime": 7.5793, |
| "eval_samples_per_second": 494.766, |
| "eval_steps_per_second": 7.784, |
| "step": 2331 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 34.33024597167969, |
| "learning_rate": 5.555555555555555e-05, |
| "loss": 0.0163, |
| "step": 2664 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8984, |
| "eval_loss": 0.47606003284454346, |
| "eval_runtime": 7.7006, |
| "eval_samples_per_second": 486.978, |
| "eval_steps_per_second": 7.662, |
| "step": 2664 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 33.204505920410156, |
| "learning_rate": 0.0, |
| "loss": 0.0143, |
| "step": 2997 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9096, |
| "eval_loss": 0.4393239915370941, |
| "eval_runtime": 7.5669, |
| "eval_samples_per_second": 495.576, |
| "eval_steps_per_second": 7.797, |
| "step": 2997 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2997, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 7.3587863155968e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
