| { |
| "best_metric": 0.7992, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0290/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": 162.58517456054688, |
| "learning_rate": 3e-05, |
| "loss": 3.8563, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.28933333333333333, |
| "eval_loss": 3.7533435821533203, |
| "eval_runtime": 15.5968, |
| "eval_samples_per_second": 240.434, |
| "eval_steps_per_second": 3.783, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 512.8773803710938, |
| "learning_rate": 3e-05, |
| "loss": 3.2355, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5376, |
| "eval_loss": 2.6015334129333496, |
| "eval_runtime": 15.6127, |
| "eval_samples_per_second": 240.188, |
| "eval_steps_per_second": 3.779, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 63.18917465209961, |
| "learning_rate": 3e-05, |
| "loss": 1.756, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6965333333333333, |
| "eval_loss": 1.1687393188476562, |
| "eval_runtime": 15.552, |
| "eval_samples_per_second": 241.127, |
| "eval_steps_per_second": 3.794, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 205.95433044433594, |
| "learning_rate": 3e-05, |
| "loss": 1.0065, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7570666666666667, |
| "eval_loss": 0.8231334090232849, |
| "eval_runtime": 15.4497, |
| "eval_samples_per_second": 242.723, |
| "eval_steps_per_second": 3.819, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 232.56837463378906, |
| "learning_rate": 3e-05, |
| "loss": 0.7541, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7992, |
| "eval_loss": 0.6712449193000793, |
| "eval_runtime": 15.6331, |
| "eval_samples_per_second": 239.876, |
| "eval_steps_per_second": 3.774, |
| "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 |
| } |
|
|
