| { |
| "best_metric": 0.7922666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0040/checkpoints/checkpoint-999", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 999, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 80.87100982666016, |
| "learning_rate": 6.75e-05, |
| "loss": 3.0348, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6581333333333333, |
| "eval_loss": 1.3814650774002075, |
| "eval_runtime": 14.359, |
| "eval_samples_per_second": 261.16, |
| "eval_steps_per_second": 4.109, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 100.23920440673828, |
| "learning_rate": 2.250000000000001e-05, |
| "loss": 0.9691, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7882666666666667, |
| "eval_loss": 0.7520945072174072, |
| "eval_runtime": 13.4731, |
| "eval_samples_per_second": 278.333, |
| "eval_steps_per_second": 4.379, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 65.33767700195312, |
| "learning_rate": 0.0, |
| "loss": 0.7166, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7922666666666667, |
| "eval_loss": 0.6990333199501038, |
| "eval_runtime": 13.6968, |
| "eval_samples_per_second": 273.787, |
| "eval_steps_per_second": 4.308, |
| "step": 999 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 999, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
