| { | |
| "best_metric": 0.8957333333333334, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0536/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": 80.25953674316406, | |
| "learning_rate": 8.728616793536588e-05, | |
| "loss": 3.0062, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 1.150546669960022, | |
| "eval_runtime": 15.7486, | |
| "eval_samples_per_second": 238.117, | |
| "eval_steps_per_second": 3.746, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 153.71412658691406, | |
| "learning_rate": 7.947199994035401e-05, | |
| "loss": 0.8119, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8434666666666667, | |
| "eval_loss": 0.5453342199325562, | |
| "eval_runtime": 15.6579, | |
| "eval_samples_per_second": 239.495, | |
| "eval_steps_per_second": 3.768, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 68.43222045898438, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.4949, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8616, | |
| "eval_loss": 0.47265660762786865, | |
| "eval_runtime": 15.6185, | |
| "eval_samples_per_second": 240.1, | |
| "eval_steps_per_second": 3.778, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 117.41171264648438, | |
| "learning_rate": 5.2814167995011876e-05, | |
| "loss": 0.3766, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8717333333333334, | |
| "eval_loss": 0.44128191471099854, | |
| "eval_runtime": 15.6551, | |
| "eval_samples_per_second": 239.538, | |
| "eval_steps_per_second": 3.769, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 84.53934478759766, | |
| "learning_rate": 3.7185832004988136e-05, | |
| "loss": 0.3055, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8813333333333333, | |
| "eval_loss": 0.4071558713912964, | |
| "eval_runtime": 15.6475, | |
| "eval_samples_per_second": 239.654, | |
| "eval_steps_per_second": 3.771, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 72.11973571777344, | |
| "learning_rate": 2.250000000000001e-05, | |
| "loss": 0.2687, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8837333333333334, | |
| "eval_loss": 0.4111470580101013, | |
| "eval_runtime": 15.9745, | |
| "eval_samples_per_second": 234.75, | |
| "eval_steps_per_second": 3.693, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 51.82630920410156, | |
| "learning_rate": 1.0528000059645995e-05, | |
| "loss": 0.2313, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8898666666666667, | |
| "eval_loss": 0.4017169773578644, | |
| "eval_runtime": 15.6793, | |
| "eval_samples_per_second": 239.169, | |
| "eval_steps_per_second": 3.763, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 98.36753845214844, | |
| "learning_rate": 2.7138320646341257e-06, | |
| "loss": 0.2175, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8914666666666666, | |
| "eval_loss": 0.3698836863040924, | |
| "eval_runtime": 15.7842, | |
| "eval_samples_per_second": 237.579, | |
| "eval_steps_per_second": 3.738, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 87.48957824707031, | |
| "learning_rate": 0.0, | |
| "loss": 0.2158, | |
| "step": 2997 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8957333333333334, | |
| "eval_loss": 0.3750994801521301, | |
| "eval_runtime": 15.8877, | |
| "eval_samples_per_second": 236.032, | |
| "eval_steps_per_second": 3.714, | |
| "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 | |
| } | |