| { |
| "best_metric": 0.5901333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0612/checkpoints/checkpoint-999", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 999, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 151.53807067871094, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 3.8465, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.3778666666666667, |
| "eval_loss": 3.7326536178588867, |
| "eval_runtime": 7.2686, |
| "eval_samples_per_second": 515.915, |
| "eval_steps_per_second": 8.117, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 75.04006958007812, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 3.4993, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5565333333333333, |
| "eval_loss": 3.3300209045410156, |
| "eval_runtime": 7.2251, |
| "eval_samples_per_second": 519.027, |
| "eval_steps_per_second": 8.166, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 134.89276123046875, |
| "learning_rate": 0.0, |
| "loss": 3.1236, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5901333333333333, |
| "eval_loss": 3.1439714431762695, |
| "eval_runtime": 7.2143, |
| "eval_samples_per_second": 519.8, |
| "eval_steps_per_second": 8.178, |
| "step": 999 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 999, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
