| { |
| "best_metric": 0.8418666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0653/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": 66.07706451416016, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 2.7396, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7170666666666666, |
| "eval_loss": 1.0093129873275757, |
| "eval_runtime": 7.2382, |
| "eval_samples_per_second": 518.084, |
| "eval_steps_per_second": 8.151, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 127.29890441894531, |
| "learning_rate": 5e-05, |
| "loss": 0.7533, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8258666666666666, |
| "eval_loss": 0.5549300909042358, |
| "eval_runtime": 7.2203, |
| "eval_samples_per_second": 519.369, |
| "eval_steps_per_second": 8.171, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 83.23411560058594, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.5045, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8418666666666667, |
| "eval_loss": 0.49961593747138977, |
| "eval_runtime": 7.3401, |
| "eval_samples_per_second": 510.891, |
| "eval_steps_per_second": 8.038, |
| "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 |
| } |
|
|
