| { |
| "best_metric": 0.8602666666666666, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0927/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": 26.61699104309082, |
| "learning_rate": 0.0005, |
| "loss": 1.4355, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7888, |
| "eval_loss": 0.6997042894363403, |
| "eval_runtime": 7.8726, |
| "eval_samples_per_second": 476.336, |
| "eval_steps_per_second": 7.494, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 42.860931396484375, |
| "learning_rate": 0.0005, |
| "loss": 0.5249, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8256, |
| "eval_loss": 0.5739554762840271, |
| "eval_runtime": 7.816, |
| "eval_samples_per_second": 479.786, |
| "eval_steps_per_second": 7.549, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 31.8571834564209, |
| "learning_rate": 0.0005, |
| "loss": 0.3548, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8565333333333334, |
| "eval_loss": 0.5195701122283936, |
| "eval_runtime": 7.8451, |
| "eval_samples_per_second": 478.006, |
| "eval_steps_per_second": 7.521, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 18.56851577758789, |
| "learning_rate": 0.0005, |
| "loss": 0.2733, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8602666666666666, |
| "eval_loss": 0.4808447062969208, |
| "eval_runtime": 7.7238, |
| "eval_samples_per_second": 485.514, |
| "eval_steps_per_second": 7.639, |
| "step": 1332 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1998, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 3.2705716958208e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
