| { |
| "best_metric": 0.8554666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0831/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": 111.66926574707031, |
| "learning_rate": 8.397114317029975e-05, |
| "loss": 3.0332, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6496, |
| "eval_loss": 1.3863377571105957, |
| "eval_runtime": 8.0417, |
| "eval_samples_per_second": 466.32, |
| "eval_steps_per_second": 7.337, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 214.32296752929688, |
| "learning_rate": 6.75e-05, |
| "loss": 0.9537, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7933333333333333, |
| "eval_loss": 0.6688243746757507, |
| "eval_runtime": 8.0826, |
| "eval_samples_per_second": 463.959, |
| "eval_steps_per_second": 7.3, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 189.57028198242188, |
| "learning_rate": 4.5e-05, |
| "loss": 0.5842, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8322666666666667, |
| "eval_loss": 0.5325037240982056, |
| "eval_runtime": 7.9633, |
| "eval_samples_per_second": 470.909, |
| "eval_steps_per_second": 7.409, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 67.59638214111328, |
| "learning_rate": 2.250000000000001e-05, |
| "loss": 0.4513, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8554666666666667, |
| "eval_loss": 0.4785503149032593, |
| "eval_runtime": 7.9861, |
| "eval_samples_per_second": 469.565, |
| "eval_steps_per_second": 7.388, |
| "step": 1332 |
| } |
| ], |
| "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": 3.2705716958208e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
