| { |
| "best_metric": 0.7024, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0160/checkpoints/checkpoint-1665", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1665, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 262.3330078125, |
| "learning_rate": 2.7990381056766583e-05, |
| "loss": 3.8472, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.3656, |
| "eval_loss": 3.7304606437683105, |
| "eval_runtime": 15.3684, |
| "eval_samples_per_second": 244.008, |
| "eval_steps_per_second": 3.839, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 104.3553466796875, |
| "learning_rate": 2.25e-05, |
| "loss": 3.2343, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5176, |
| "eval_loss": 2.796813488006592, |
| "eval_runtime": 15.1894, |
| "eval_samples_per_second": 246.883, |
| "eval_steps_per_second": 3.884, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 94.42123413085938, |
| "learning_rate": 1.5e-05, |
| "loss": 2.1486, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6309333333333333, |
| "eval_loss": 1.7061794996261597, |
| "eval_runtime": 15.2885, |
| "eval_samples_per_second": 245.282, |
| "eval_steps_per_second": 3.859, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 162.3461456298828, |
| "learning_rate": 7.500000000000004e-06, |
| "loss": 1.5244, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6792, |
| "eval_loss": 1.399641513824463, |
| "eval_runtime": 15.1418, |
| "eval_samples_per_second": 247.658, |
| "eval_steps_per_second": 3.896, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 200.46395874023438, |
| "learning_rate": 2.0096189432334194e-06, |
| "loss": 1.3291, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7024, |
| "eval_loss": 1.2725963592529297, |
| "eval_runtime": 15.2516, |
| "eval_samples_per_second": 245.875, |
| "eval_steps_per_second": 3.868, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1998, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
