| { | |
| "best_metric": 0.8965333333333333, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0324/checkpoints/checkpoint-2331", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2331, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 88.42060852050781, | |
| "learning_rate": 9e-05, | |
| "loss": 3.0592, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7104, | |
| "eval_loss": 1.1932069063186646, | |
| "eval_runtime": 8.3917, | |
| "eval_samples_per_second": 446.869, | |
| "eval_steps_per_second": 7.031, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 56.0634765625, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8103, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8317333333333333, | |
| "eval_loss": 0.5802273154258728, | |
| "eval_runtime": 8.4286, | |
| "eval_samples_per_second": 444.914, | |
| "eval_steps_per_second": 7.0, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 48.54353332519531, | |
| "learning_rate": 9e-05, | |
| "loss": 0.5038, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8661333333333333, | |
| "eval_loss": 0.443949818611145, | |
| "eval_runtime": 8.408, | |
| "eval_samples_per_second": 446.005, | |
| "eval_steps_per_second": 7.017, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 101.32244873046875, | |
| "learning_rate": 9e-05, | |
| "loss": 0.3676, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8698666666666667, | |
| "eval_loss": 0.4244947135448456, | |
| "eval_runtime": 8.3545, | |
| "eval_samples_per_second": 448.859, | |
| "eval_steps_per_second": 7.062, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 126.50972747802734, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2972, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8834666666666666, | |
| "eval_loss": 0.40064162015914917, | |
| "eval_runtime": 8.3779, | |
| "eval_samples_per_second": 447.607, | |
| "eval_steps_per_second": 7.042, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 58.08767318725586, | |
| "learning_rate": 9e-05, | |
| "loss": 0.231, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8898666666666667, | |
| "eval_loss": 0.35977059602737427, | |
| "eval_runtime": 8.38, | |
| "eval_samples_per_second": 447.496, | |
| "eval_steps_per_second": 7.041, | |
| "step": 1998 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 71.41222381591797, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2015, | |
| "step": 2331 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8965333333333333, | |
| "eval_loss": 0.35049742460250854, | |
| "eval_runtime": 8.7717, | |
| "eval_samples_per_second": 427.513, | |
| "eval_steps_per_second": 6.726, | |
| "step": 2331 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2664, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 5.7235004676864e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |