| { | |
| "best_metric": 0.8978666666666667, | |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0971/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": 165.46981811523438, | |
| "learning_rate": 7e-05, | |
| "loss": 3.2323, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7002666666666667, | |
| "eval_loss": 1.56610107421875, | |
| "eval_runtime": 14.4206, | |
| "eval_samples_per_second": 260.044, | |
| "eval_steps_per_second": 4.091, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 169.23626708984375, | |
| "learning_rate": 7e-05, | |
| "loss": 0.8431, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8568, | |
| "eval_loss": 0.5010253190994263, | |
| "eval_runtime": 13.6006, | |
| "eval_samples_per_second": 275.722, | |
| "eval_steps_per_second": 4.338, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 201.387939453125, | |
| "learning_rate": 7e-05, | |
| "loss": 0.4501, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8733333333333333, | |
| "eval_loss": 0.42264360189437866, | |
| "eval_runtime": 13.623, | |
| "eval_samples_per_second": 275.271, | |
| "eval_steps_per_second": 4.331, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 116.7824935913086, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3152, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8978666666666667, | |
| "eval_loss": 0.33754217624664307, | |
| "eval_runtime": 13.5054, | |
| "eval_samples_per_second": 277.666, | |
| "eval_steps_per_second": 4.369, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1332, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 3.2705716958208e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |