| { |
| "best_metric": 0.8978666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0470/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": 36.96174621582031, |
| "learning_rate": 0.0004522542485937369, |
| "loss": 1.3684, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.84, |
| "eval_loss": 0.5403386354446411, |
| "eval_runtime": 15.4494, |
| "eval_samples_per_second": 242.728, |
| "eval_steps_per_second": 3.819, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 27.981266021728516, |
| "learning_rate": 0.00032725424859373687, |
| "loss": 0.4797, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8581333333333333, |
| "eval_loss": 0.4706296920776367, |
| "eval_runtime": 15.436, |
| "eval_samples_per_second": 242.938, |
| "eval_steps_per_second": 3.822, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 45.77500915527344, |
| "learning_rate": 0.00017274575140626317, |
| "loss": 0.2701, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.884, |
| "eval_loss": 0.40142565965652466, |
| "eval_runtime": 15.3112, |
| "eval_samples_per_second": 244.919, |
| "eval_steps_per_second": 3.853, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 63.04391860961914, |
| "learning_rate": 4.7745751406263163e-05, |
| "loss": 0.1512, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8909333333333334, |
| "eval_loss": 0.37005701661109924, |
| "eval_runtime": 15.2896, |
| "eval_samples_per_second": 245.265, |
| "eval_steps_per_second": 3.859, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 64.16574096679688, |
| "learning_rate": 0.0, |
| "loss": 0.0987, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8978666666666667, |
| "eval_loss": 0.3690126836299896, |
| "eval_runtime": 15.3421, |
| "eval_samples_per_second": 244.425, |
| "eval_steps_per_second": 3.846, |
| "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 |
| } |
|
|
