| { |
| "best_metric": 0.8584, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0569/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": 32.71794128417969, |
| "learning_rate": 0.0003, |
| "loss": 1.6985, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7922666666666667, |
| "eval_loss": 0.6854488253593445, |
| "eval_runtime": 17.09, |
| "eval_samples_per_second": 219.427, |
| "eval_steps_per_second": 3.452, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 65.78317260742188, |
| "learning_rate": 0.0003, |
| "loss": 0.5434, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8378666666666666, |
| "eval_loss": 0.5295833349227905, |
| "eval_runtime": 16.8204, |
| "eval_samples_per_second": 222.944, |
| "eval_steps_per_second": 3.508, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 40.53878402709961, |
| "learning_rate": 0.0003, |
| "loss": 0.3656, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8536, |
| "eval_loss": 0.49800580739974976, |
| "eval_runtime": 16.5004, |
| "eval_samples_per_second": 227.268, |
| "eval_steps_per_second": 3.576, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 37.81058120727539, |
| "learning_rate": 0.0003, |
| "loss": 0.2616, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8522666666666666, |
| "eval_loss": 0.49607864022254944, |
| "eval_runtime": 16.3854, |
| "eval_samples_per_second": 228.862, |
| "eval_steps_per_second": 3.601, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 47.56358337402344, |
| "learning_rate": 0.0003, |
| "loss": 0.1974, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8584, |
| "eval_loss": 0.5002295970916748, |
| "eval_runtime": 16.6159, |
| "eval_samples_per_second": 225.687, |
| "eval_steps_per_second": 3.551, |
| "step": 1665 |
| } |
| ], |
| "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": 4.088214619776e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
