| { |
| "best_metric": 0.8586666666666667, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0148/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": 1018.748291015625, |
| "learning_rate": 6.331559480312315e-05, |
| "loss": 3.243, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6682666666666667, |
| "eval_loss": 1.70267915725708, |
| "eval_runtime": 12.5651, |
| "eval_samples_per_second": 298.447, |
| "eval_steps_per_second": 4.696, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 126.8888931274414, |
| "learning_rate": 4.581559480312316e-05, |
| "loss": 1.0005, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8202666666666667, |
| "eval_loss": 0.6526823043823242, |
| "eval_runtime": 12.5678, |
| "eval_samples_per_second": 298.382, |
| "eval_steps_per_second": 4.695, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 202.71054077148438, |
| "learning_rate": 2.4184405196876842e-05, |
| "loss": 0.5566, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8464, |
| "eval_loss": 0.503829300403595, |
| "eval_runtime": 12.8175, |
| "eval_samples_per_second": 292.569, |
| "eval_steps_per_second": 4.603, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 143.05429077148438, |
| "learning_rate": 6.684405196876842e-06, |
| "loss": 0.4312, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8584, |
| "eval_loss": 0.4636790454387665, |
| "eval_runtime": 12.4362, |
| "eval_samples_per_second": 301.54, |
| "eval_steps_per_second": 4.744, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 162.30844116210938, |
| "learning_rate": 0.0, |
| "loss": 0.3861, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8586666666666667, |
| "eval_loss": 0.45789921283721924, |
| "eval_runtime": 12.6978, |
| "eval_samples_per_second": 295.327, |
| "eval_steps_per_second": 4.646, |
| "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 |
| } |
|
|
