| { |
| "best_metric": 0.8736, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0656/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": 171.50242614746094, |
| "learning_rate": 5e-05, |
| "loss": 3.5981, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5733333333333334, |
| "eval_loss": 2.8123927116394043, |
| "eval_runtime": 8.081, |
| "eval_samples_per_second": 464.05, |
| "eval_steps_per_second": 7.301, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 200.65841674804688, |
| "learning_rate": 5e-05, |
| "loss": 1.538, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7946666666666666, |
| "eval_loss": 0.8104856014251709, |
| "eval_runtime": 7.8994, |
| "eval_samples_per_second": 474.721, |
| "eval_steps_per_second": 7.469, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 56.31884765625, |
| "learning_rate": 5e-05, |
| "loss": 0.6627, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8408, |
| "eval_loss": 0.5590971112251282, |
| "eval_runtime": 7.8862, |
| "eval_samples_per_second": 475.517, |
| "eval_steps_per_second": 7.481, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 113.18806457519531, |
| "learning_rate": 5e-05, |
| "loss": 0.454, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8610666666666666, |
| "eval_loss": 0.46225905418395996, |
| "eval_runtime": 7.8883, |
| "eval_samples_per_second": 475.389, |
| "eval_steps_per_second": 7.479, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 328.9425964355469, |
| "learning_rate": 5e-05, |
| "loss": 0.3298, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8736, |
| "eval_loss": 0.40600794553756714, |
| "eval_runtime": 7.8723, |
| "eval_samples_per_second": 476.356, |
| "eval_steps_per_second": 7.495, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1665, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
