| { |
| "best_metric": 0.8824, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0105/checkpoints/checkpoint-2997", |
| "epoch": 9.0, |
| "eval_steps": 500, |
| "global_step": 2997, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 93.66116333007812, |
| "learning_rate": 5e-05, |
| "loss": 3.5781, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6104, |
| "eval_loss": 2.789259910583496, |
| "eval_runtime": 5.0483, |
| "eval_samples_per_second": 742.828, |
| "eval_steps_per_second": 11.687, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 201.43775939941406, |
| "learning_rate": 5e-05, |
| "loss": 1.4405, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7949333333333334, |
| "eval_loss": 0.7377238869667053, |
| "eval_runtime": 5.0168, |
| "eval_samples_per_second": 747.492, |
| "eval_steps_per_second": 11.761, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 250.66461181640625, |
| "learning_rate": 5e-05, |
| "loss": 0.629, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8264, |
| "eval_loss": 0.5450374484062195, |
| "eval_runtime": 5.0629, |
| "eval_samples_per_second": 740.681, |
| "eval_steps_per_second": 11.653, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 74.75858306884766, |
| "learning_rate": 5e-05, |
| "loss": 0.4378, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8552, |
| "eval_loss": 0.44762372970581055, |
| "eval_runtime": 5.0272, |
| "eval_samples_per_second": 745.94, |
| "eval_steps_per_second": 11.736, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 80.36298370361328, |
| "learning_rate": 5e-05, |
| "loss": 0.3234, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8597333333333333, |
| "eval_loss": 0.43369361758232117, |
| "eval_runtime": 4.9875, |
| "eval_samples_per_second": 751.878, |
| "eval_steps_per_second": 11.83, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 91.50684356689453, |
| "learning_rate": 5e-05, |
| "loss": 0.2549, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8688, |
| "eval_loss": 0.41042885184288025, |
| "eval_runtime": 4.9887, |
| "eval_samples_per_second": 751.701, |
| "eval_steps_per_second": 11.827, |
| "step": 1998 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 314.6053771972656, |
| "learning_rate": 5e-05, |
| "loss": 0.1862, |
| "step": 2331 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8736, |
| "eval_loss": 0.3988228440284729, |
| "eval_runtime": 4.9659, |
| "eval_samples_per_second": 755.146, |
| "eval_steps_per_second": 11.881, |
| "step": 2331 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 268.6302795410156, |
| "learning_rate": 5e-05, |
| "loss": 0.1446, |
| "step": 2664 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8770666666666667, |
| "eval_loss": 0.4174762964248657, |
| "eval_runtime": 4.9576, |
| "eval_samples_per_second": 756.422, |
| "eval_steps_per_second": 11.901, |
| "step": 2664 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 75.27823638916016, |
| "learning_rate": 5e-05, |
| "loss": 0.1066, |
| "step": 2997 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8824, |
| "eval_loss": 0.3900984227657318, |
| "eval_runtime": 5.1401, |
| "eval_samples_per_second": 729.561, |
| "eval_steps_per_second": 11.478, |
| "step": 2997 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2997, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 7.3587863155968e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
