| { |
| "best_metric": 0.876, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0346/checkpoints/checkpoint-1332", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 1332, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 136.6346893310547, |
| "learning_rate": 9e-05, |
| "loss": 2.7663, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7568, |
| "eval_loss": 0.9826899766921997, |
| "eval_runtime": 8.7607, |
| "eval_samples_per_second": 428.049, |
| "eval_steps_per_second": 6.735, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 107.3460693359375, |
| "learning_rate": 9e-05, |
| "loss": 0.6444, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8522666666666666, |
| "eval_loss": 0.4780538082122803, |
| "eval_runtime": 8.5724, |
| "eval_samples_per_second": 437.451, |
| "eval_steps_per_second": 6.883, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 108.46403503417969, |
| "learning_rate": 9e-05, |
| "loss": 0.3589, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8744, |
| "eval_loss": 0.4125499427318573, |
| "eval_runtime": 8.5661, |
| "eval_samples_per_second": 437.775, |
| "eval_steps_per_second": 6.888, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 63.675537109375, |
| "learning_rate": 9e-05, |
| "loss": 0.2333, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.876, |
| "eval_loss": 0.39891672134399414, |
| "eval_runtime": 8.5792, |
| "eval_samples_per_second": 437.104, |
| "eval_steps_per_second": 6.877, |
| "step": 1332 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.2705716958208e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
