| { | |
| "best_metric": 0.8757333333333334, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0398/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": 38.75714874267578, | |
| "learning_rate": 0.0003, | |
| "loss": 1.617, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8322666666666667, | |
| "eval_loss": 0.5671864748001099, | |
| "eval_runtime": 7.6123, | |
| "eval_samples_per_second": 492.622, | |
| "eval_steps_per_second": 7.751, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 37.799110412597656, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4904, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8512, | |
| "eval_loss": 0.49777090549468994, | |
| "eval_runtime": 7.7458, | |
| "eval_samples_per_second": 484.135, | |
| "eval_steps_per_second": 7.617, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 36.545738220214844, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3176, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8685333333333334, | |
| "eval_loss": 0.43015000224113464, | |
| "eval_runtime": 7.5989, | |
| "eval_samples_per_second": 493.493, | |
| "eval_steps_per_second": 7.764, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 38.0368537902832, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2407, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8757333333333334, | |
| "eval_loss": 0.42973724007606506, | |
| "eval_runtime": 7.5128, | |
| "eval_samples_per_second": 499.151, | |
| "eval_steps_per_second": 7.853, | |
| "step": 1332 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |