| { |
| "best_metric": 0.8437333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0434/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": 86.303955078125, |
| "learning_rate": 7.681980515339464e-05, |
| "loss": 3.1074, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6666666666666666, |
| "eval_loss": 1.4695498943328857, |
| "eval_runtime": 9.7058, |
| "eval_samples_per_second": 386.368, |
| "eval_steps_per_second": 6.079, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 123.69164276123047, |
| "learning_rate": 4.5e-05, |
| "loss": 0.93, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8109333333333333, |
| "eval_loss": 0.6591599583625793, |
| "eval_runtime": 9.6505, |
| "eval_samples_per_second": 388.579, |
| "eval_steps_per_second": 6.114, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 168.02476501464844, |
| "learning_rate": 1.3180194846605365e-05, |
| "loss": 0.5871, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8437333333333333, |
| "eval_loss": 0.5257493257522583, |
| "eval_runtime": 9.8311, |
| "eval_samples_per_second": 381.441, |
| "eval_steps_per_second": 6.001, |
| "step": 999 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
