| { |
| "best_metric": 0.9104, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0180/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": 45.48494338989258, |
| "learning_rate": 0.0004849231551964771, |
| "loss": 1.2866, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8253333333333334, |
| "eval_loss": 0.5949100255966187, |
| "eval_runtime": 5.0184, |
| "eval_samples_per_second": 747.245, |
| "eval_steps_per_second": 11.757, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 29.821104049682617, |
| "learning_rate": 0.0004415111107797445, |
| "loss": 0.423, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8666666666666667, |
| "eval_loss": 0.43908655643463135, |
| "eval_runtime": 5.0225, |
| "eval_samples_per_second": 746.641, |
| "eval_steps_per_second": 11.747, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 25.670103073120117, |
| "learning_rate": 0.000375, |
| "loss": 0.2613, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8786666666666667, |
| "eval_loss": 0.42521676421165466, |
| "eval_runtime": 5.0053, |
| "eval_samples_per_second": 749.212, |
| "eval_steps_per_second": 11.788, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 32.18095397949219, |
| "learning_rate": 0.00029341204441673266, |
| "loss": 0.1594, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8842666666666666, |
| "eval_loss": 0.4045007526874542, |
| "eval_runtime": 4.9525, |
| "eval_samples_per_second": 757.186, |
| "eval_steps_per_second": 11.913, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 35.147125244140625, |
| "learning_rate": 0.00020658795558326743, |
| "loss": 0.0919, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8984, |
| "eval_loss": 0.3998246192932129, |
| "eval_runtime": 5.0966, |
| "eval_samples_per_second": 735.785, |
| "eval_steps_per_second": 11.576, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 25.1690673828125, |
| "learning_rate": 0.00012500000000000006, |
| "loss": 0.0468, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9037333333333334, |
| "eval_loss": 0.3972958028316498, |
| "eval_runtime": 4.9756, |
| "eval_samples_per_second": 753.678, |
| "eval_steps_per_second": 11.858, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 21.144067764282227, |
| "learning_rate": 5.848888922025553e-05, |
| "loss": 0.0278, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9048, |
| "eval_loss": 0.3851996064186096, |
| "eval_runtime": 4.9897, |
| "eval_samples_per_second": 751.553, |
| "eval_steps_per_second": 11.824, |
| "step": 2331 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 36.19491195678711, |
| "learning_rate": 1.5076844803522921e-05, |
| "loss": 0.0234, |
| "step": 2664 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.9061333333333333, |
| "eval_loss": 0.37618979811668396, |
| "eval_runtime": 5.0152, |
| "eval_samples_per_second": 747.724, |
| "eval_steps_per_second": 11.764, |
| "step": 2664 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 24.752777099609375, |
| "learning_rate": 0.0, |
| "loss": 0.0153, |
| "step": 2997 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.9104, |
| "eval_loss": 0.3684804141521454, |
| "eval_runtime": 4.998, |
| "eval_samples_per_second": 750.307, |
| "eval_steps_per_second": 11.805, |
| "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 |
| } |
|
|
