| { |
| "best_metric": 0.8882666666666666, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0789/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": 192.98973083496094, |
| "learning_rate": 9e-05, |
| "loss": 2.885, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7101333333333333, |
| "eval_loss": 1.1232208013534546, |
| "eval_runtime": 13.3255, |
| "eval_samples_per_second": 281.415, |
| "eval_steps_per_second": 4.428, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 60.18983459472656, |
| "learning_rate": 9e-05, |
| "loss": 0.7826, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8272, |
| "eval_loss": 0.544028103351593, |
| "eval_runtime": 13.2272, |
| "eval_samples_per_second": 283.508, |
| "eval_steps_per_second": 4.461, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 75.75183868408203, |
| "learning_rate": 9e-05, |
| "loss": 0.4851, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8650666666666667, |
| "eval_loss": 0.43011653423309326, |
| "eval_runtime": 13.5056, |
| "eval_samples_per_second": 277.663, |
| "eval_steps_per_second": 4.369, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 149.39646911621094, |
| "learning_rate": 9e-05, |
| "loss": 0.3695, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8821333333333333, |
| "eval_loss": 0.3761574625968933, |
| "eval_runtime": 13.5342, |
| "eval_samples_per_second": 277.075, |
| "eval_steps_per_second": 4.359, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 63.283180236816406, |
| "learning_rate": 9e-05, |
| "loss": 0.2811, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8882666666666666, |
| "eval_loss": 0.37348106503486633, |
| "eval_runtime": 13.4867, |
| "eval_samples_per_second": 278.053, |
| "eval_steps_per_second": 4.375, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2331, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "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": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
